Merge tag 'health-monitoring-7.0_2026-01-20' of https://git.kernel.org/pub/scm/linux/kernel/git/djwong/xfs-linux into xfs-7.0-merge

xfs: autonomous self healing of filesystems [v7]

This patchset builds new functionality to deliver live information about
filesystem health events to userspace.  This is done by creating an
anonymous file that can be read() for events by userspace programs.
Events are captured by hooking various parts of XFS and iomap so that
metadata health failures, file I/O errors, and major changes in
filesystem state (unmounts, shutdowns, etc.) can be observed by
programs.

When an event occurs, the hook functions queue an event object to each
event anonfd for later processing.  Programs must have CAP_SYS_ADMIN
to open the anonfd and there's a maximum event lag to prevent resource
overconsumption.  The events themselves can be read() from the anonfd
as C structs for the xfs_healer daemon.

In userspace, we create a new daemon program that will read the event
objects and initiate repairs automatically.  This daemon is managed
entirely by systemd and will not block unmounting of the filesystem
unless repairs are ongoing.  They are auto-started by a starter
service that uses fanotify.

This patchset depends on the new fserror code that Christian Brauner
has tentatively accepted for Linux 7.0:
https://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs.git/log/?h=vfs-7.0.fserror

v7: more cleanups of the media verification ioctl, improve comments, and
    reuse the bio
v6: fix pi-breaking bugs, make verify failures trigger health reports
    and filter bio status flags better
v5: add verify-media ioctl, collapse small helper funcs with only
    one caller
v4: drop multiple client support so we can make direct calls into
    healthmon instead of chasing pointers and doing indirect calls
v3: drag out of rfc status

With a bit of luck, this should all go splendidly.

Conflicts:
	This merge required an update on files:
		- fs/xfs/xfs_healthmon.c
		- fs/xfs/xfs_verify_media.c
	Such change was required because a parallel developement changed
	XFS header file xfs.h naming to xfs_platform.h, so the merge
	required to update those includes in both files above

Signed-off-by: "Darrick J. Wong" <djwong@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>

Author: cmaiolino

arch/alpha/include/uapi/asm/errno.h

@@ -55,6 +55,7 @@
 #define	ENOSR		82	/* Out of streams resources */
 #define	ETIME		83	/* Timer expired */
 #define	EBADMSG		84	/* Not a data message */
+#define	EFSBADCRC	EBADMSG	/* Bad CRC detected */
 #define	EPROTO		85	/* Protocol error */
 #define	ENODATA		86	/* No data available */
 #define	ENOSTR		87	/* Device not a stream */
@@ -96,6 +97,7 @@
 #define	EREMCHG		115	/* Remote address changed */
 
 #define	EUCLEAN		117	/* Structure needs cleaning */
+#define	EFSCORRUPTED	EUCLEAN	/* Filesystem is corrupted */
 #define	ENOTNAM		118	/* Not a XENIX named type file */
 #define	ENAVAIL		119	/* No XENIX semaphores available */
 #define	EISNAM		120	/* Is a named type file */

arch/mips/include/uapi/asm/errno.h

@@ -50,6 +50,7 @@
 #define EDOTDOT		73	/* RFS specific error */
 #define EMULTIHOP	74	/* Multihop attempted */
 #define EBADMSG		77	/* Not a data message */
+#define EFSBADCRC	EBADMSG	/* Bad CRC detected */
 #define ENAMETOOLONG	78	/* File name too long */
 #define EOVERFLOW	79	/* Value too large for defined data type */
 #define ENOTUNIQ	80	/* Name not unique on network */
@@ -88,6 +89,7 @@
 #define EISCONN		133	/* Transport endpoint is already connected */
 #define ENOTCONN	134	/* Transport endpoint is not connected */
 #define EUCLEAN		135	/* Structure needs cleaning */
+#define EFSCORRUPTED	EUCLEAN	/* Filesystem is corrupted */
 #define ENOTNAM		137	/* Not a XENIX named type file */
 #define ENAVAIL		138	/* No XENIX semaphores available */
 #define EISNAM		139	/* Is a named type file */

arch/parisc/include/uapi/asm/errno.h

@@ -36,6 +36,7 @@
 
 #define	EDOTDOT		66	/* RFS specific error */
 #define	EBADMSG		67	/* Not a data message */
+#define	EFSBADCRC	EBADMSG	/* Bad CRC detected */
 #define	EUSERS		68	/* Too many users */
 #define	EDQUOT		69	/* Quota exceeded */
 #define	ESTALE		70	/* Stale file handle */
@@ -62,6 +63,7 @@
 #define	ERESTART	175	/* Interrupted system call should be restarted */
 #define	ESTRPIPE	176	/* Streams pipe error */
 #define	EUCLEAN		177	/* Structure needs cleaning */
+#define	EFSCORRUPTED	EUCLEAN	/* Filesystem is corrupted */
 #define	ENOTNAM		178	/* Not a XENIX named type file */
 #define	ENAVAIL		179	/* No XENIX semaphores available */
 #define	EISNAM		180	/* Is a named type file */

arch/sparc/include/uapi/asm/errno.h

@@ -48,6 +48,7 @@
 #define	ENOSR		74	/* Out of streams resources */
 #define	ENOMSG		75	/* No message of desired type */
 #define	EBADMSG		76	/* Not a data message */
+#define	EFSBADCRC	EBADMSG	/* Bad CRC detected */
 #define	EIDRM		77	/* Identifier removed */
 #define	EDEADLK		78	/* Resource deadlock would occur */
 #define	ENOLCK		79	/* No record locks available */
@@ -91,6 +92,7 @@
 #define	ENOTUNIQ	115	/* Name not unique on network */
 #define	ERESTART	116	/* Interrupted syscall should be restarted */
 #define	EUCLEAN		117	/* Structure needs cleaning */
+#define	EFSCORRUPTED	EUCLEAN	/* Filesystem is corrupted */
 #define	ENOTNAM		118	/* Not a XENIX named type file */
 #define	ENAVAIL		119	/* No XENIX semaphores available */
 #define	EISNAM		120	/* Is a named type file */

fs/Makefile

@@ -16,7 +16,7 @@ obj-y :=	open.o read_write.o file_table.o super.o \
 		stack.o fs_struct.o statfs.o fs_pin.o nsfs.o \
 		fs_dirent.o fs_context.o fs_parser.o fsopen.o init.o \
 		kernel_read_file.o mnt_idmapping.o remap_range.o pidfs.o \
-		file_attr.o
+		file_attr.o fserror.o
 
 obj-$(CONFIG_BUFFER_HEAD)	+= buffer.o mpage.o
 obj-$(CONFIG_PROC_FS)		+= proc_namespace.o

fs/erofs/internal.h

@@ -541,6 +541,4 @@ long erofs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg);
 long erofs_compat_ioctl(struct file *filp, unsigned int cmd,
 			unsigned long arg);
 
-#define EFSCORRUPTED    EUCLEAN         /* Filesystem is corrupted */
-
 #endif	/* __EROFS_INTERNAL_H */

fs/ext2/ext2.h

@@ -357,7 +357,6 @@ struct ext2_inode {
  */
 #define	EXT2_VALID_FS			0x0001	/* Unmounted cleanly */
 #define	EXT2_ERROR_FS			0x0002	/* Errors detected */
-#define	EFSCORRUPTED			EUCLEAN	/* Filesystem is corrupted */
 
 /*
  * Mount flags

fs/ext4/ext4.h

@@ -3938,7 +3938,4 @@ extern int ext4_block_write_begin(handle_t *handle, struct folio *folio,
 				  get_block_t *get_block);
 #endif	/* __KERNEL__ */
 
-#define EFSBADCRC	EBADMSG		/* Bad CRC detected */
-#define EFSCORRUPTED	EUCLEAN		/* Filesystem is corrupted */
-
 #endif	/* _EXT4_H */

fs/ext4/ioctl.c

@@ -26,6 +26,7 @@
 #include <linux/fsmap.h>
 #include "fsmap.h"
 #include <trace/events/ext4.h>
+#include <linux/fserror.h>
 
 typedef void ext4_update_sb_callback(struct ext4_sb_info *sbi,
 				     struct ext4_super_block *es,
@@ -844,6 +845,7 @@ int ext4_force_shutdown(struct super_block *sb, u32 flags)
 		return -EINVAL;
 	}
 	clear_opt(sb, DISCARD);
+	fserror_report_shutdown(sb, GFP_KERNEL);
 	return 0;
 }
 

fs/ext4/super.c

@@ -48,6 +48,7 @@
 #include <linux/fsnotify.h>
 #include <linux/fs_context.h>
 #include <linux/fs_parser.h>
+#include <linux/fserror.h>
 
 #include "ext4.h"
 #include "ext4_extents.h"	/* Needed for trace points definition */
@@ -824,7 +825,8 @@ 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);
+	fserror_report_metadata(sb, error ? -abs(error) : -EFSCORRUPTED,
+				GFP_ATOMIC);
 
 	ext4_handle_error(sb, force_ro, error, 0, block, function, line);
 }
@@ -856,7 +858,9 @@ 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);
+	fserror_report_file_metadata(inode,
+				     error ? -abs(error) : -EFSCORRUPTED,
+				     GFP_ATOMIC);
 
 	ext4_handle_error(inode->i_sb, false, error, inode->i_ino, block,
 			  function, line);
@@ -896,7 +900,7 @@ 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);
+	fserror_report_file_metadata(inode, -EFSCORRUPTED, GFP_ATOMIC);
 
 	ext4_handle_error(inode->i_sb, false, EFSCORRUPTED, inode->i_ino, block,
 			  function, line);
@@ -965,7 +969,8 @@ 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);
+	fserror_report_metadata(sb, errno ? -abs(errno) : -EFSCORRUPTED,
+				GFP_ATOMIC);
 
 	ext4_handle_error(sb, false, -errno, 0, 0, function, line);
 }