Add support for boot environment data to be stored in the label

Modern bootloaders leverage data stored in the root filesystem to 
enable some of their powerful features. GRUB specifically has a grubenv 
file which can store large amounts of configuration data that can be 
read and written at boot time and during normal operation. This allows 
sysadmins to configure useful features like automated failover after 
failed boot attempts. Unfortunately, due to the Copy-on-Write nature 
of ZFS, the standard behavior of these tools cannot handle writing to
ZFS files safely at boot time. We need an alternative way to store 
data that allows the bootloader to make changes to the data.

This work is very similar to work that was done on Illumos to enable 
similar functionality in the FreeBSD bootloader. This patch is different 
in that the data being stored is a raw grubenv file; this file can store 
arbitrary variables and values, and the scripting provided by grub is 
powerful enough that special structures are not required to implement 
advanced behavior.

We repurpose the second padding area in each label to store the grubenv 
file, protected by an embedded checksum. We add two ioctls to get and 
set this data, and libzfs_core and libzfs functions to access them more 
easily. There are no direct command line interfaces to these functions; 
these will be added directly to the bootloader utilities.

Reviewed-by: Pavel Zakharov <[email protected]>
Reviewed-by: Matthew Ahrens <[email protected]>
Reviewed-by: Brian Behlendorf <[email protected]>
Signed-off-by: Paul Dagnelie <[email protected]>
Closes #10009 

3 files changed, 31 insertions, 7 deletions

diff --git a/include/sys/fs/zfs.h b/include/sys/fs/zfs.h
index f5aced0da..39be630d8 100644
--- a/include/sys/fs/zfs.h
+++ b/include/sys/fs/zfs.h
@@ -21,7 +21,7 @@
 
 /*
  * Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
- * Copyright (c) 2011, 2018 by Delphix. All rights reserved.
+ * Copyright (c) 2011, 2020 by Delphix. All rights reserved.
  * Copyright 2011 Nexenta Systems, Inc.  All rights reserved.
  * Copyright (c) 2013, 2017 Joyent, Inc. All rights reserved.
  * Copyright (c) 2014 Integros [integros.com]
@@ -1290,7 +1290,7 @@ typedef enum zfs_ioc {
 	ZFS_IOC_WAIT_FS,			/* 0x5a54 */
 
 	/*
-	 * Per-platform (Optional) - 6/128 numbers reserved.
+	 * Per-platform (Optional) - 8/128 numbers reserved.
 	 */
 	ZFS_IOC_PLATFORM = ZFS_IOC_FIRST + 0x80,
 	ZFS_IOC_EVENTS_NEXT,			/* 0x81 (Linux) */
@@ -1299,6 +1299,8 @@ typedef enum zfs_ioc {
 	ZFS_IOC_NEXTBOOT,			/* 0x84 (FreeBSD) */
 	ZFS_IOC_JAIL,				/* 0x85 (FreeBSD) */
 	ZFS_IOC_UNJAIL,				/* 0x86 (FreeBSD) */
+	ZFS_IOC_SET_BOOTENV,			/* 0x87 (Linux) */
+	ZFS_IOC_GET_BOOTENV,			/* 0x88 (Linux) */
 	ZFS_IOC_LAST
 } zfs_ioc_t;
 
diff --git a/include/sys/vdev.h b/include/sys/vdev.h
index 56a869fec..c4ef479b5 100644
--- a/include/sys/vdev.h
+++ b/include/sys/vdev.h
@@ -21,7 +21,7 @@
 
 /*
  * Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
- * Copyright (c) 2011, 2017 by Delphix. All rights reserved.
+ * Copyright (c) 2011, 2020 by Delphix. All rights reserved.
  * Copyright (c) 2017, Intel Corporation.
  * Copyright (c) 2019, Datto Inc. All rights reserved.
  */
@@ -179,6 +179,8 @@ extern void vdev_uberblock_load(vdev_t *, struct uberblock *, nvlist_t **);
 extern void vdev_config_generate_stats(vdev_t *vd, nvlist_t *nv);
 extern void vdev_label_write(zio_t *zio, vdev_t *vd, int l, abd_t *buf, uint64_t
     offset, uint64_t size, zio_done_func_t *done, void *private, int flags);
+extern int vdev_label_read_bootenv(vdev_t *, nvlist_t *);
+extern int vdev_label_write_bootenv(vdev_t *, char *);
 
 typedef enum {
 	VDEV_LABEL_CREATE,	/* create/add a new device */
diff --git a/include/sys/vdev_impl.h b/include/sys/vdev_impl.h
index b55871a5d..96546ac35 100644
--- a/include/sys/vdev_impl.h
+++ b/include/sys/vdev_impl.h
@@ -20,7 +20,7 @@
  */
 /*
  * Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
- * Copyright (c) 2011, 2019 by Delphix. All rights reserved.
+ * Copyright (c) 2011, 2020 by Delphix. All rights reserved.
  * Copyright (c) 2017, Intel Corporation.
  */
 
@@ -414,7 +414,7 @@ struct vdev {
 #define	VDEV_RAIDZ_MAXPARITY	3
 
 #define	VDEV_PAD_SIZE		(8 << 10)
-/* 2 padding areas (vl_pad1 and vl_pad2) to skip */
+/* 2 padding areas (vl_pad1 and vl_be) to skip */
 #define	VDEV_SKIP_SIZE		VDEV_PAD_SIZE * 2
 #define	VDEV_PHYS_SIZE		(112 << 10)
 #define	VDEV_UBERBLOCK_RING	(128 << 10)
@@ -441,12 +441,32 @@ typedef struct vdev_phys {
 	zio_eck_t	vp_zbt;
 } vdev_phys_t;
 
+typedef enum vbe_vers {
+	/* The bootenv file is stored as ascii text in the envblock */
+	VB_RAW = 0,
+
+	/*
+	 * The bootenv file is converted to an nvlist and then packed into the
+	 * envblock.
+	 */
+	VB_NVLIST = 1
+} vbe_vers_t;
+
+typedef struct vdev_boot_envblock {
+	uint64_t	vbe_version;
+	char		vbe_bootenv[VDEV_PAD_SIZE - sizeof (uint64_t) -
+			sizeof (zio_eck_t)];
+	zio_eck_t	vbe_zbt;
+} vdev_boot_envblock_t;
+
+CTASSERT_GLOBAL(sizeof (vdev_boot_envblock_t) == VDEV_PAD_SIZE);
+
 typedef struct vdev_label {
 	char		vl_pad1[VDEV_PAD_SIZE];			/*  8K */
-	char		vl_pad2[VDEV_PAD_SIZE];			/*  8K */
+	vdev_boot_envblock_t	vl_be;				/*  8K */
 	vdev_phys_t	vl_vdev_phys;				/* 112K	*/
 	char		vl_uberblock[VDEV_UBERBLOCK_RING];	/* 128K	*/
-} vdev_label_t;							/* 256K total */
+} vdev_label_t;						/* 256K total */
 
 /*
  * vdev_dirty() flags