Merge tag 'ubifs-for-linus-6.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rw/ubifs

Pull UBI and UBIFS updates from Richard Weinberger:
 "UBI:
   - Add Zhihao Cheng as reviewer
   - Attach via device tree
   - Add NVMEM layer
   - Various fastmap related fixes

  UBIFS:
   - Add Zhihao Cheng as reviewer
   - Convert to folios
   - Various fixes (memory leaks in error paths, function prototypes)"

* tag 'ubifs-for-linus-6.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rw/ubifs: (34 commits)
  mtd: ubi: fix NVMEM over UBI volumes on 32-bit systems
  mtd: ubi: provide NVMEM layer over UBI volumes
  mtd: ubi: populate ubi volume fwnode
  mtd: ubi: introduce pre-removal notification for UBI volumes
  mtd: ubi: attach from device tree
  mtd: ubi: block: use notifier to create ubiblock from parameter
  dt-bindings: mtd: ubi-volume: allow UBI volumes to provide NVMEM
  dt-bindings: mtd: add basic bindings for UBI
  ubifs: Queue up space reservation tasks if retrying many times
  ubifs: ubifs_symlink: Fix memleak of inode->i_link in error path
  ubifs: dbg_check_idx_size: Fix kmemleak if loading znode failed
  ubi: Correct the number of PEBs after a volume resize failure
  ubi: fix slab-out-of-bounds in ubi_eba_get_ldesc+0xfb/0x130
  ubi: correct the calculation of fastmap size
  ubifs: Remove unreachable code in dbg_check_ltab_lnum
  ubifs: fix function pointer cast warnings
  ubifs: fix sort function prototype
  ubi: Check for too small LEB size in VTBL code
  MAINTAINERS: Add Zhihao Cheng as UBI/UBIFS reviewer
  ubifs: Convert populate_page() to take a folio
  ...

Documentation/devicetree/bindings/mtd/partitions/linux,ubi.yaml

+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/mtd/partitions/linux,ubi.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Unsorted Block Images
+
+description: |
+  UBI ("Unsorted Block Images") is a volume management system for raw
+  flash devices which manages multiple logical volumes on a single
+  physical flash device and spreads the I/O load (i.e wear-leveling)
+  across the whole flash chip.
+
+maintainers:
+  - Daniel Golle <daniel@makrotopia.org>
+
+allOf:
+  - $ref: partition.yaml#
+
+properties:
+  compatible:
+    const: linux,ubi
+
+  volumes:
+    type: object
+    description: UBI Volumes
+
+    patternProperties:
+      "^ubi-volume-.*$":
+        $ref: /schemas/mtd/partitions/ubi-volume.yaml#
+
+    unevaluatedProperties: false
+
+required:
+  - compatible
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    partitions {
+        compatible = "fixed-partitions";
+        #address-cells = <1>;
+        #size-cells = <1>;
+
+        partition@0 {
+            reg = <0x0 0x100000>;
+            label = "bootloader";
+            read-only;
+        };
+
+        partition@100000 {
+            reg = <0x100000 0x1ff00000>;
+            label = "ubi";
+            compatible = "linux,ubi";
+
+            volumes {
+                ubi-volume-caldata {
+                    volid = <2>;
+                    volname = "rf";
+
+                    nvmem-layout {
+                        compatible = "fixed-layout";
+                        #address-cells = <1>;
+                        #size-cells = <1>;
+
+                        eeprom@0 {
+                            reg = <0x0 0x1000>;
+                        };
+                    };
+                };
+            };
+        };
+    };

Documentation/devicetree/bindings/mtd/partitions/ubi-volume.yaml

+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/mtd/partitions/ubi-volume.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: UBI volume
+
+description: |
+  This binding describes a single UBI volume. Volumes can be matches either
+  by their ID or their name, or both.
+
+maintainers:
+  - Daniel Golle <daniel@makrotopia.org>
+
+properties:
+  volid:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    description:
+      Match UBI volume ID
+
+  volname:
+    $ref: /schemas/types.yaml#/definitions/string
+    description:
+      Match UBI volume ID
+
+  nvmem-layout:
+    $ref: /schemas/nvmem/layouts/nvmem-layout.yaml#
+    description:
+      This container may reference an NVMEM layout parser.
+
+anyOf:
+  - required:
+      - volid
+
+  - required:
+      - volname
+
+# This is a generic file other binding inherit from and extend
+additionalProperties: true

Documentation/mm/page_cache.rst

@@ -3,3 +3,13 @@
 ==========
 Page Cache
 ==========
+
+The page cache is the primary way that the user and the rest of the kernel
+interact with filesystems.  It can be bypassed (e.g. with O_DIRECT),
+but normal reads, writes and mmaps go through the page cache.
+
+Folios
+======
+
+The folio is the unit of memory management within the page cache.
+Operations 

MAINTAINERS

@@ -22573,6 +22573,7 @@ F:	include/uapi/misc/uacce/
 
 UBI FILE SYSTEM (UBIFS)
 M:	Richard Weinberger <richard@nod.at>
+R:	Zhihao Cheng <chengzhihao1@huawei.com>
 L:	linux-mtd@lists.infradead.org
 S:	Supported
 W:	http://www.linux-mtd.infradead.org/doc/ubifs.html
@@ -22718,6 +22719,7 @@ F:	drivers/ufs/host/ufs-renesas.c
 
 UNSORTED BLOCK IMAGES (UBI)
 M:	Richard Weinberger <richard@nod.at>
+R:	Zhihao Cheng <chengzhihao1@huawei.com>
 L:	linux-mtd@lists.infradead.org
 S:	Supported
 W:	http://www.linux-mtd.infradead.org/

drivers/mtd/ubi/Kconfig

@@ -113,4 +113,17 @@ config MTD_UBI_FAULT_INJECTION
 	   testing purposes.
 
 	   If in doubt, say "N".
+
+config MTD_UBI_NVMEM
+	tristate "UBI virtual NVMEM"
+	default n
+	depends on NVMEM
+	help
+	   This option enabled an additional driver exposing UBI volumes as NVMEM
+	   providers, intended for platforms where UBI is part of the firmware
+	   specification and used to store also e.g. MAC addresses or board-
+	   specific Wi-Fi calibration data.
+
+	   If in doubt, say "N".
+
 endif # MTD_UBI

drivers/mtd/ubi/Makefile

@@ -7,3 +7,4 @@ ubi-$(CONFIG_MTD_UBI_FASTMAP) += fastmap.o
 ubi-$(CONFIG_MTD_UBI_BLOCK) += block.o
 
 obj-$(CONFIG_MTD_UBI_GLUEBI) += gluebi.o
+obj-$(CONFIG_MTD_UBI_NVMEM) += nvmem.o

drivers/mtd/ubi/block.c

@@ -65,10 +65,10 @@ struct ubiblock_pdu {
 };
 
 /* Numbers of elements set in the @ubiblock_param array */
-static int ubiblock_devs __initdata;
+static int ubiblock_devs;
 
 /* MTD devices specification parameters */
-static struct ubiblock_param ubiblock_param[UBIBLOCK_MAX_DEVICES] __initdata;
+static struct ubiblock_param ubiblock_param[UBIBLOCK_MAX_DEVICES];
 
 struct ubiblock {
 	struct ubi_volume_desc *desc;
@@ -536,6 +536,70 @@ static int ubiblock_resize(struct ubi_volume_info *vi)
 	return 0;
 }
 
+static bool
+match_volume_desc(struct ubi_volume_info *vi, const char *name, int ubi_num, int vol_id)
+{
+	int err, len, cur_ubi_num, cur_vol_id;
+
+	if (ubi_num == -1) {
+		/* No ubi num, name must be a vol device path */
+		err = ubi_get_num_by_path(name, &cur_ubi_num, &cur_vol_id);
+		if (err || vi->ubi_num != cur_ubi_num || vi->vol_id != cur_vol_id)
+			return false;
+
+		return true;
+	}
+
+	if (vol_id == -1) {
+		/* Got ubi_num, but no vol_id, name must be volume name */
+		if (vi->ubi_num != ubi_num)
+			return false;
+
+		len = strnlen(name, UBI_VOL_NAME_MAX + 1);
+		if (len < 1 || vi->name_len != len)
+			return false;
+
+		if (strcmp(name, vi->name))
+			return false;
+
+		return true;
+	}
+
+	if (vi->ubi_num != ubi_num)
+		return false;
+
+	if (vi->vol_id != vol_id)
+		return false;
+
+	return true;
+}
+
+static void
+ubiblock_create_from_param(struct ubi_volume_info *vi)
+{
+	int i, ret = 0;
+	struct ubiblock_param *p;
+
+	/*
+	 * Iterate over ubiblock cmdline parameters. If a parameter matches the
+	 * newly added volume create the ubiblock device for it.
+	 */
+	for (i = 0; i < ubiblock_devs; i++) {
+		p = &ubiblock_param[i];
+
+		if (!match_volume_desc(vi, p->name, p->ubi_num, p->vol_id))
+			continue;
+
+		ret = ubiblock_create(vi);
+		if (ret) {
+			pr_err(
+			       "UBI: block: can't add '%s' volume on ubi%d_%d, err=%d\n",
+			       vi->name, p->ubi_num, p->vol_id, ret);
+		}
+		break;
+	}
+}
+
 static int ubiblock_notify(struct notifier_block *nb,
 			 unsigned long notification_type, void *ns_ptr)
 {
@@ -543,10 +607,7 @@ static int ubiblock_notify(struct notifier_block *nb,
 
 	switch (notification_type) {
 	case UBI_VOLUME_ADDED:
-		/*
-		 * We want to enforce explicit block device creation for
-		 * volumes, so when a volume is added we do nothing.
-		 */
+		ubiblock_create_from_param(&nt->vi);
 		break;
 	case UBI_VOLUME_REMOVED:
 		ubiblock_remove(&nt->vi);
@@ -572,56 +633,6 @@ static struct notifier_block ubiblock_notifier = {
 	.notifier_call = ubiblock_notify,
 };
 
-static struct ubi_volume_desc * __init
-open_volume_desc(const char *name, int ubi_num, int vol_id)
-{
-	if (ubi_num == -1)
-		/* No ubi num, name must be a vol device path */
-		return ubi_open_volume_path(name, UBI_READONLY);
-	else if (vol_id == -1)
-		/* No vol_id, must be vol_name */
-		return ubi_open_volume_nm(ubi_num, name, UBI_READONLY);
-	else
-		return ubi_open_volume(ubi_num, vol_id, UBI_READONLY);
-}
-
-static void __init ubiblock_create_from_param(void)
-{
-	int i, ret = 0;
-	struct ubiblock_param *p;
-	struct ubi_volume_desc *desc;
-	struct ubi_volume_info vi;
-
-	/*
-	 * If there is an error creating one of the ubiblocks, continue on to
-	 * create the following ubiblocks. This helps in a circumstance where
-	 * the kernel command-line specifies multiple block devices and some
-	 * may be broken, but we still want the working ones to come up.
-	 */
-	for (i = 0; i < ubiblock_devs; i++) {
-		p = &ubiblock_param[i];
-
-		desc = open_volume_desc(p->name, p->ubi_num, p->vol_id);
-		if (IS_ERR(desc)) {
-			pr_err(
-			       "UBI: block: can't open volume on ubi%d_%d, err=%ld\n",
-			       p->ubi_num, p->vol_id, PTR_ERR(desc));
-			continue;
-		}
-
-		ubi_get_volume_info(desc, &vi);
-		ubi_close_volume(desc);
-
-		ret = ubiblock_create(&vi);
-		if (ret) {
-			pr_err(
-			       "UBI: block: can't add '%s' volume on ubi%d_%d, err=%d\n",
-			       vi.name, p->ubi_num, p->vol_id, ret);
-			continue;
-		}
-	}
-}
-
 static void ubiblock_remove_all(void)
 {
 	struct ubiblock *next;
@@ -647,18 +658,7 @@ int __init ubiblock_init(void)
 	if (ubiblock_major < 0)
 		return ubiblock_major;
 
-	/*
-	 * Attach block devices from 'block=' module param.
-	 * Even if one block device in the param list fails to come up,
-	 * still allow the module to load and leave any others up.
-	 */
-	ubiblock_create_from_param();
-
-	/*
-	 * Block devices are only created upon user requests, so we ignore
-	 * existing volumes.
-	 */
-	ret = ubi_register_volume_notifier(&ubiblock_notifier, 1);
+	ret = ubi_register_volume_notifier(&ubiblock_notifier, 0);
 	if (ret)
 		goto err_unreg;
 	return 0;

drivers/mtd/ubi/build.c

@@ -27,6 +27,7 @@
 #include <linux/log2.h>
 #include <linux/kthread.h>
 #include <linux/kernel.h>
+#include <linux/of.h>
 #include <linux/slab.h>
 #include <linux/major.h>
 #include "ubi.h"
@@ -92,7 +93,7 @@ static struct ubi_device *ubi_devices[UBI_MAX_DEVICES];
 /* Serializes UBI devices creations and removals */
 DEFINE_MUTEX(ubi_devices_mutex);
 
-/* Protects @ubi_devices and @ubi->ref_count */
+/* Protects @ubi_devices, @ubi->ref_count and @ubi->is_dead */
 static DEFINE_SPINLOCK(ubi_devices_lock);
 
 /* "Show" method for files in '/<sysfs>/class/ubi/' */
@@ -260,6 +261,9 @@ struct ubi_device *ubi_get_device(int ubi_num)
 
 	spin_lock(&ubi_devices_lock);
 	ubi = ubi_devices[ubi_num];
+	if (ubi && ubi->is_dead)
+		ubi = NULL;
+
 	if (ubi) {
 		ubi_assert(ubi->ref_count >= 0);
 		ubi->ref_count += 1;
@@ -297,7 +301,7 @@ struct ubi_device *ubi_get_by_major(int major)
 	spin_lock(&ubi_devices_lock);
 	for (i = 0; i < UBI_MAX_DEVICES; i++) {
 		ubi = ubi_devices[i];
-		if (ubi && MAJOR(ubi->cdev.dev) == major) {
+		if (ubi && !ubi->is_dead && MAJOR(ubi->cdev.dev) == major) {
 			ubi_assert(ubi->ref_count >= 0);
 			ubi->ref_count += 1;
 			get_device(&ubi->dev);
@@ -326,7 +330,7 @@ int ubi_major2num(int major)
 	for (i = 0; i < UBI_MAX_DEVICES; i++) {
 		struct ubi_device *ubi = ubi_devices[i];
 
-		if (ubi && MAJOR(ubi->cdev.dev) == major) {
+		if (ubi && !ubi->is_dead && MAJOR(ubi->cdev.dev) == major) {
 			ubi_num = ubi->ubi_num;
 			break;
 		}
@@ -513,7 +517,7 @@ static void ubi_free_volumes_from(struct ubi_device *ubi, int from)
 	int i;
 
 	for (i = from; i < ubi->vtbl_slots + UBI_INT_VOL_COUNT; i++) {
-		if (!ubi->volumes[i])
+		if (!ubi->volumes[i] || ubi->volumes[i]->is_dead)
 			continue;
 		ubi_eba_replace_table(ubi->volumes[i], NULL);
 		ubi_fastmap_destroy_checkmap(ubi->volumes[i]);
@@ -1098,7 +1102,6 @@ int ubi_detach_mtd_dev(int ubi_num, int anyway)
 		return -EINVAL;
 
 	spin_lock(&ubi_devices_lock);
-	put_device(&ubi->dev);
 	ubi->ref_count -= 1;
 	if (ubi->ref_count) {
 		if (!anyway) {
@@ -1109,6 +1112,13 @@ int ubi_detach_mtd_dev(int ubi_num, int anyway)
 		ubi_err(ubi, "%s reference count %d, destroy anyway",
 			ubi->ubi_name, ubi->ref_count);
 	}
+	ubi->is_dead = true;
+	spin_unlock(&ubi_devices_lock);
+
+	ubi_notify_all(ubi, UBI_VOLUME_SHUTDOWN, NULL);
+
+	spin_lock(&ubi_devices_lock);
+	put_device(&ubi->dev);
 	ubi_devices[ubi_num] = NULL;
 	spin_unlock(&ubi_devices_lock);
 
@@ -1219,43 +1229,43 @@ static struct mtd_info * __init open_mtd_device(const char *mtd_dev)
 	return mtd;
 }
 
-static int __init ubi_init(void)
+static void ubi_notify_add(struct mtd_info *mtd)
 {
-	int err, i, k;
+	struct device_node *np = mtd_get_of_node(mtd);
+	int err;
 
-	/* Ensure that EC and VID headers have correct size */
-	BUILD_BUG_ON(sizeof(struct ubi_ec_hdr) != 64);
-	BUILD_BUG_ON(sizeof(struct ubi_vid_hdr) != 64);
+	if (!of_device_is_compatible(np, "linux,ubi"))
+		return;
 
-	if (mtd_devs > UBI_MAX_DEVICES) {
-		pr_err("UBI error: too many MTD devices, maximum is %d\n",
-		       UBI_MAX_DEVICES);
-		return -EINVAL;
-	}
+	/*
+	 * we are already holding &mtd_table_mutex, but still need
+	 * to bump refcount
+	 */
+	err = __get_mtd_device(mtd);
+	if (err)
+		return;
 
-	/* Create base sysfs directory and sysfs files */
-	err = class_register(&ubi_class);
+	/* called while holding mtd_table_mutex */
+	mutex_lock_nested(&ubi_devices_mutex, SINGLE_DEPTH_NESTING);
+	err = ubi_attach_mtd_dev(mtd, UBI_DEV_NUM_AUTO, 0, 0, false, false);
+	mutex_unlock(&ubi_devices_mutex);
 	if (err < 0)
-		return err;
-
-	err = misc_register(&ubi_ctrl_cdev);
-	if (err) {
-		pr_err("UBI error: cannot register device\n");
-		goto out;
-	}
+		__put_mtd_device(mtd);
+}
 
-	ubi_wl_entry_slab = kmem_cache_create("ubi_wl_entry_slab",
-					      sizeof(struct ubi_wl_entry),
-					      0, 0, NULL);
-	if (!ubi_wl_entry_slab) {
-		err = -ENOMEM;
-		goto out_dev_unreg;
-	}
+static void ubi_notify_remove(struct mtd_info *mtd)
+{
+	/* do nothing for now */
+}
 
-	err = ubi_debugfs_init();
-	if (err)
-		goto out_slab;
+static struct mtd_notifier ubi_mtd_notifier = {
+	.add = ubi_notify_add,
+	.remove = ubi_notify_remove,
+};
 
+static int __init ubi_init_attach(void)
+{
+	int err, i, k;
 
 	/* Attach MTD devices */
 	for (i = 0; i < mtd_devs; i++) {
@@ -1304,25 +1314,79 @@ static int __init ubi_init(void)
 		}
 	}
 
+	return 0;
+
+out_detach:
+	for (k = 0; k < i; k++)
+		if (ubi_devices[k]) {
+			mutex_lock(&ubi_devices_mutex);
+			ubi_detach_mtd_dev(ubi_devices[k]->ubi_num, 1);
+			mutex_unlock(&ubi_devices_mutex);
+		}
+	return err;
+}
+#ifndef CONFIG_MTD_UBI_MODULE
+late_initcall(ubi_init_attach);
+#endif
+
+static int __init ubi_init(void)
+{
+	int err;
+
+	/* Ensure that EC and VID headers have correct size */
+	BUILD_BUG_ON(sizeof(struct ubi_ec_hdr) != 64);
+	BUILD_BUG_ON(sizeof(struct ubi_vid_hdr) != 64);
+
+	if (mtd_devs > UBI_MAX_DEVICES) {
+		pr_err("UBI error: too many MTD devices, maximum is %d\n",
+		       UBI_MAX_DEVICES);
+		return -EINVAL;
+	}
+
+	/* Create base sysfs directory and sysfs files */
+	err = class_register(&ubi_class);
+	if (err < 0)
+		return err;
+
+	err = misc_register(&ubi_ctrl_cdev);
+	if (err) {
+		pr_err("UBI error: cannot register device\n");
+		goto out;
+	}
+
+	ubi_wl_entry_slab = kmem_cache_create("ubi_wl_entry_slab",
+					      sizeof(struct ubi_wl_entry),
+					      0, 0, NULL);
+	if (!ubi_wl_entry_slab) {
+		err = -ENOMEM;
+		goto out_dev_unreg;
+	}
+
+	err = ubi_debugfs_init();
+	if (err)
+		goto out_slab;
+
 	err = ubiblock_init();
 	if (err) {
 		pr_err("UBI error: block: cannot initialize, error %d\n", err);
 
 		/* See comment above re-ubi_is_module(). */
 		if (ubi_is_module())
-			goto out_detach;
+			goto out_slab;
+	}
+
+	register_mtd_user(&ubi_mtd_notifier);
+
+	if (ubi_is_module()) {
+		err = ubi_init_attach();
+		if (err)
+			goto out_mtd_notifier;
 	}
 
 	return 0;
 
-out_detach:
-	for (k = 0; k < i; k++)
-		if (ubi_devices[k]) {
-			mutex_lock(&ubi_devices_mutex);
-			ubi_detach_mtd_dev(ubi_devices[k]->ubi_num, 1);
-			mutex_unlock(&ubi_devices_mutex);
-		}
-	ubi_debugfs_exit();
+out_mtd_notifier:
+	unregister_mtd_user(&ubi_mtd_notifier);
 out_slab:
 	kmem_cache_destroy(ubi_wl_entry_slab);
 out_dev_unreg:
@@ -1332,13 +1396,15 @@ static int __init ubi_init(void)
 	pr_err("UBI error: cannot initialize UBI, error %d\n", err);
 	return err;
 }
-late_initcall(ubi_init);
+device_initcall(ubi_init);
+
 
 static void __exit ubi_exit(void)
 {
 	int i;
 
 	ubiblock_exit();
+	unregister_mtd_user(&ubi_mtd_notifier);
 
 	for (i = 0; i < UBI_MAX_DEVICES; i++)
 		if (ubi_devices[i]) {

drivers/mtd/ubi/eba.c

@@ -1456,7 +1456,14 @@ int ubi_eba_copy_leb(struct ubi_device *ubi, int from, int to,
 	}
 
 	ubi_assert(vol->eba_tbl->entries[lnum].pnum == from);
+
+	/**
+	 * The volumes_lock lock is needed here to prevent the expired old eba_tbl
+	 * being updated when the eba_tbl is copied in the ubi_resize_volume() process.
+	 */
+	spin_lock(&ubi->volumes_lock);
 	vol->eba_tbl->entries[lnum].pnum = to;
+	spin_unlock(&ubi->volumes_lock);
 
 out_unlock_buf:
 	mutex_unlock(&ubi->buf_mutex);

drivers/mtd/ubi/fastmap.c

@@ -85,9 +85,10 @@ size_t ubi_calc_fm_size(struct ubi_device *ubi)
 		sizeof(struct ubi_fm_scan_pool) +
 		sizeof(struct ubi_fm_scan_pool) +
 		(ubi->peb_count * sizeof(struct ubi_fm_ec)) +
-		(sizeof(struct ubi_fm_eba) +
-		(ubi->peb_count * sizeof(__be32))) +
-		sizeof(struct ubi_fm_volhdr) * UBI_MAX_VOLUMES;
+		((sizeof(struct ubi_fm_eba) +
+		  sizeof(struct ubi_fm_volhdr)) *
+		 (UBI_MAX_VOLUMES + UBI_INT_VOL_COUNT)) +
+		(ubi->peb_count * sizeof(__be32));
 	return roundup(size, ubi->leb_size);
 }
 

drivers/mtd/ubi/kapi.c

@@ -152,7 +152,7 @@ struct ubi_volume_desc *ubi_open_volume(int ubi_num, int vol_id, int mode)
 
 	spin_lock(&ubi->volumes_lock);
 	vol = ubi->volumes[vol_id];
-	if (!vol)
+	if (!vol || vol->is_dead)
 		goto out_unlock;
 
 	err = -EBUSY;
@@ -279,6 +279,41 @@ struct ubi_volume_desc *ubi_open_volume_nm(int ubi_num, const char *name,
 }
 EXPORT_SYMBOL_GPL(ubi_open_volume_nm);
 
+/**
+ * ubi_get_num_by_path - get UBI device and volume number from device path
+ * @pathname: volume character device node path
+ * @ubi_num: pointer to UBI device number to be set
+ * @vol_id: pointer to UBI volume ID to be set
+ *
+ * Returns 0 on success and sets ubi_num and vol_id, returns error otherwise.
+ */
+int ubi_get_num_by_path(const char *pathname, int *ubi_num, int *vol_id)
+{
+	int error;
+	struct path path;
+	struct kstat stat;
+
+	error = kern_path(pathname, LOOKUP_FOLLOW, &path);
+	if (error)
+		return error;
+
+	error = vfs_getattr(&path, &stat, STATX_TYPE, AT_STATX_SYNC_AS_STAT);
+	path_put(&path);
+	if (error)
+		return error;
+
+	if (!S_ISCHR(stat.mode))
+		return -EINVAL;
+
+	*ubi_num = ubi_major2num(MAJOR(stat.rdev));
+	*vol_id = MINOR(stat.rdev) - 1;
+
+	if (*vol_id < 0 || *ubi_num < 0)
+		return -ENODEV;
+
+	return 0;
+}
+
 /**
  * ubi_open_volume_path - open UBI volume by its character device node path.
  * @pathname: volume character device node path
@@ -290,32 +325,17 @@ EXPORT_SYMBOL_GPL(ubi_open_volume_nm);
 struct ubi_volume_desc *ubi_open_volume_path(const char *pathname, int mode)
 {
 	int error, ubi_num, vol_id;
-	struct path path;
-	struct kstat stat;
 
 	dbg_gen("open volume %s, mode %d", pathname, mode);
 
 	if (!pathname || !*pathname)
 		return ERR_PTR(-EINVAL);
 
-	error = kern_path(pathname, LOOKUP_FOLLOW, &path);
-	if (error)
-		return ERR_PTR(error);
-
-	error = vfs_getattr(&path, &stat, STATX_TYPE, AT_STATX_SYNC_AS_STAT);
-	path_put(&path);
+	error = ubi_get_num_by_path(pathname, &ubi_num, &vol_id);
 	if (error)
 		return ERR_PTR(error);
 
-	if (!S_ISCHR(stat.mode))
-		return ERR_PTR(-EINVAL);
-
-	ubi_num = ubi_major2num(MAJOR(stat.rdev));
-	vol_id = MINOR(stat.rdev) - 1;
-
-	if (vol_id >= 0 && ubi_num >= 0)
-		return ubi_open_volume(ubi_num, vol_id, mode);
-	return ERR_PTR(-ENODEV);
+	return ubi_open_volume(ubi_num, vol_id, mode);
 }
 EXPORT_SYMBOL_GPL(ubi_open_volume_path);
 

drivers/mtd/ubi/nvmem.c

+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2023 Daniel Golle <daniel@makrotopia.org>
+ */
+
+/* UBI NVMEM provider */
+#include "ubi.h"
+#include <linux/nvmem-provider.h>
+#include <asm/div64.h>
+
+/* List of all NVMEM devices */
+static LIST_HEAD(nvmem_devices);
+static DEFINE_MUTEX(devices_mutex);
+
+struct ubi_nvmem {
+	struct nvmem_device *nvmem;
+	int ubi_num;
+	int vol_id;
+	int usable_leb_size;
+	struct list_head list;
+};
+
+static int ubi_nvmem_reg_read(void *priv, unsigned int from,
+			      void *val, size_t bytes)
+{
+	size_t to_read, bytes_left = bytes;
+	struct ubi_nvmem *unv = priv;
+	struct ubi_volume_desc *desc;
+	uint32_t offs;
+	uint64_t lnum = from;
+	int err = 0;
+
+	desc = ubi_open_volume(unv->ubi_num, unv->vol_id, UBI_READONLY);
+	if (IS_ERR(desc))
+		return PTR_ERR(desc);
+
+	offs = do_div(lnum, unv->usable_leb_size);
+	while (bytes_left) {
+		to_read = unv->usable_leb_size - offs;
+
+		if (to_read > bytes_left)
+			to_read = bytes_left;
+
+		err = ubi_read(desc, lnum, val, offs, to_read);
+		if (err)
+			break;
+
+		lnum += 1;
+		offs = 0;
+		bytes_left -= to_read;
+		val += to_read;
+	}
+	ubi_close_volume(desc);
+
+	if (err)
+		return err;
+
+	return bytes_left == 0 ? 0 : -EIO;
+}
+
+static int ubi_nvmem_add(struct ubi_volume_info *vi)
+{
+	struct device_node *np = dev_of_node(vi->dev);
+	struct nvmem_config config = {};
+	struct ubi_nvmem *unv;
+	int ret;
+
+	if (!np)
+		return 0;
+
+	if (!of_get_child_by_name(np, "nvmem-layout"))
+		return 0;
+
+	if (WARN_ON_ONCE(vi->usable_leb_size <= 0) ||
+	    WARN_ON_ONCE(vi->size <= 0))
+		return -EINVAL;
+
+	unv = kzalloc(sizeof(struct ubi_nvmem), GFP_KERNEL);
+	if (!unv)
+		return -ENOMEM;
+
+	config.id = NVMEM_DEVID_NONE;
+	config.dev = vi->dev;
+	config.name = dev_name(vi->dev);
+	config.owner = THIS_MODULE;
+	config.priv = unv;
+	config.reg_read = ubi_nvmem_reg_read;
+	config.size = vi->usable_leb_size * vi->size;
+	config.word_size = 1;
+	config.stride = 1;
+	config.read_only = true;
+	config.root_only = true;
+	config.ignore_wp = true;
+	config.of_node = np;
+
+	unv->ubi_num = vi->ubi_num;
+	unv->vol_id = vi->vol_id;
+	unv->usable_leb_size = vi->usable_leb_size;
+	unv->nvmem = nvmem_register(&config);
+	if (IS_ERR(unv->nvmem)) {
+		ret = dev_err_probe(vi->dev, PTR_ERR(unv->nvmem),
+				    "Failed to register NVMEM device\n");
+		kfree(unv);
+		return ret;
+	}
+
+	mutex_lock(&devices_mutex);
+	list_add_tail(&unv->list, &nvmem_devices);
+	mutex_unlock(&devices_mutex);
+
+	return 0;
+}
+
+static void ubi_nvmem_remove(struct ubi_volume_info *vi)
+{
+	struct ubi_nvmem *unv_c, *unv = NULL;
+
+	mutex_lock(&devices_mutex);
+	list_for_each_entry(unv_c, &nvmem_devices, list)
+		if (unv_c->ubi_num == vi->ubi_num && unv_c->vol_id == vi->vol_id) {
+			unv = unv_c;
+			break;
+		}
+
+	if (!unv) {
+		mutex_unlock(&devices_mutex);
+		return;
+	}
+
+	list_del(&unv->list);
+	mutex_unlock(&devices_mutex);
+	nvmem_unregister(unv->nvmem);
+	kfree(unv);
+}
+
+/**
+ * nvmem_notify - UBI notification handler.
+ * @nb: registered notifier block
+ * @l: notification type
+ * @ns_ptr: pointer to the &struct ubi_notification object
+ */
+static int nvmem_notify(struct notifier_block *nb, unsigned long l,
+			 void *ns_ptr)
+{
+	struct ubi_notification *nt = ns_ptr;
+
+	switch (l) {
+	case UBI_VOLUME_RESIZED:
+		ubi_nvmem_remove(&nt->vi);
+		fallthrough;
+	case UBI_VOLUME_ADDED:
+		ubi_nvmem_add(&nt->vi);
+		break;
+	case UBI_VOLUME_SHUTDOWN:
+		ubi_nvmem_remove(&nt->vi);
+		break;
+	default:
+		break;
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block nvmem_notifier = {
+	.notifier_call = nvmem_notify,
+};
+
+static int __init ubi_nvmem_init(void)
+{
+	return ubi_register_volume_notifier(&nvmem_notifier, 0);
+}
+
+static void __exit ubi_nvmem_exit(void)
+{
+	struct ubi_nvmem *unv, *tmp;
+
+	mutex_lock(&devices_mutex);
+	list_for_each_entry_safe(unv, tmp, &nvmem_devices, list) {
+		nvmem_unregister(unv->nvmem);
+		list_del(&unv->list);
+		kfree(unv);
+	}
+	mutex_unlock(&devices_mutex);
+
+	ubi_unregister_volume_notifier(&nvmem_notifier);
+}
+
+module_init(ubi_nvmem_init);
+module_exit(ubi_nvmem_exit);
+MODULE_DESCRIPTION("NVMEM layer over UBI volumes");
+MODULE_AUTHOR("Daniel Golle");
+MODULE_LICENSE("GPL");

drivers/mtd/ubi/ubi.h

@@ -337,6 +337,7 @@ struct ubi_volume {
 	int writers;
 	int exclusive;
 	int metaonly;
+	bool is_dead;
 
 	int reserved_pebs;
 	int vol_type;
@@ -561,6 +562,7 @@ struct ubi_device {
 	spinlock_t volumes_lock;
 	int ref_count;
 	int image_seq;
+	bool is_dead;
 
 	int rsvd_pebs;
 	int avail_pebs;
@@ -955,6 +957,7 @@ void ubi_free_internal_volumes(struct ubi_device *ubi);
 void ubi_do_get_device_info(struct ubi_device *ubi, struct ubi_device_info *di);
 void ubi_do_get_volume_info(struct ubi_device *ubi, struct ubi_volume *vol,
 			    struct ubi_volume_info *vi);
+int ubi_get_num_by_path(const char *pathname, int *ubi_num, int *vol_id);
 /* scan.c */
 int ubi_compare_lebs(struct ubi_device *ubi, const struct ubi_ainf_peb *aeb,
 		      int pnum, const struct ubi_vid_hdr *vid_hdr);

drivers/mtd/ubi/vmt.c

@@ -59,7 +59,7 @@ static ssize_t vol_attribute_show(struct device *dev,
 	struct ubi_device *ubi = vol->ubi;
 
 	spin_lock(&ubi->volumes_lock);
-	if (!ubi->volumes[vol->vol_id]) {
+	if (!ubi->volumes[vol->vol_id] || ubi->volumes[vol->vol_id]->is_dead) {
 		spin_unlock(&ubi->volumes_lock);
 		return -ENODEV;
 	}
@@ -124,6 +124,31 @@ static void vol_release(struct device *dev)
 	kfree(vol);
 }
 
+static struct fwnode_handle *find_volume_fwnode(struct ubi_volume *vol)
+{
+	struct fwnode_handle *fw_vols, *fw_vol;
+	const char *volname;
+	u32 volid;
+
+	fw_vols = device_get_named_child_node(vol->dev.parent->parent, "volumes");
+	if (!fw_vols)
+		return NULL;
+
+	fwnode_for_each_child_node(fw_vols, fw_vol) {
+		if (!fwnode_property_read_string(fw_vol, "volname", &volname) &&
+		    strncmp(volname, vol->name, vol->name_len))
+			continue;
+
+		if (!fwnode_property_read_u32(fw_vol, "volid", &volid) &&
+		    vol->vol_id != volid)
+			continue;
+
+		return fw_vol;
+	}
+
+	return NULL;
+}
+
 /**
  * ubi_create_volume - create volume.
  * @ubi: UBI device description object
@@ -189,7 +214,7 @@ int ubi_create_volume(struct ubi_device *ubi, struct ubi_mkvol_req *req)
 
 	/* Ensure that the name is unique */
 	for (i = 0; i < ubi->vtbl_slots; i++)
-		if (ubi->volumes[i] &&
+		if (ubi->volumes[i] && !ubi->volumes[i]->is_dead &&
 		    ubi->volumes[i]->name_len == req->name_len &&
 		    !strcmp(ubi->volumes[i]->name, req->name)) {
 			ubi_err(ubi, "volume \"%s\" exists (ID %d)",
@@ -223,6 +248,7 @@ int ubi_create_volume(struct ubi_device *ubi, struct ubi_mkvol_req *req)
 	vol->name_len  = req->name_len;
 	memcpy(vol->name, req->name, vol->name_len);
 	vol->ubi = ubi;
+	device_set_node(&vol->dev, find_volume_fwnode(vol));
 
 	/*
 	 * Finish all pending erases because there may be some LEBs belonging
@@ -352,6 +378,19 @@ int ubi_remove_volume(struct ubi_volume_desc *desc, int no_vtbl)
 		err = -EBUSY;
 		goto out_unlock;
 	}
+
+	/*
+	 * Mark volume as dead at this point to prevent that anyone
+	 * can take a reference to the volume from now on.
+	 * This is necessary as we have to release the spinlock before
+	 * calling ubi_volume_notify.
+	 */
+	vol->is_dead = true;
+	spin_unlock(&ubi->volumes_lock);
+
+	ubi_volume_notify(ubi, vol, UBI_VOLUME_SHUTDOWN);
+
+	spin_lock(&ubi->volumes_lock);
 	ubi->volumes[vol_id] = NULL;
 	spin_unlock(&ubi->volumes_lock);
 
@@ -408,6 +447,7 @@ int ubi_resize_volume(struct ubi_volume_desc *desc, int reserved_pebs)
 	struct ubi_device *ubi = vol->ubi;
 	struct ubi_vtbl_record vtbl_rec;
 	struct ubi_eba_table *new_eba_tbl = NULL;
+	struct ubi_eba_table *old_eba_tbl = NULL;
 	int vol_id = vol->vol_id;
 
 	if (ubi->ro_mode)
@@ -453,10 +493,13 @@ int ubi_resize_volume(struct ubi_volume_desc *desc, int reserved_pebs)
 			err = -ENOSPC;
 			goto out_free;
 		}
+
 		ubi->avail_pebs -= pebs;
 		ubi->rsvd_pebs += pebs;
 		ubi_eba_copy_table(vol, new_eba_tbl, vol->reserved_pebs);
-		ubi_eba_replace_table(vol, new_eba_tbl);
+		old_eba_tbl = vol->eba_tbl;
+		vol->eba_tbl = new_eba_tbl;
+		vol->reserved_pebs = reserved_pebs;
 		spin_unlock(&ubi->volumes_lock);
 	}
 
@@ -471,7 +514,9 @@ int ubi_resize_volume(struct ubi_volume_desc *desc, int reserved_pebs)
 		ubi->avail_pebs -= pebs;
 		ubi_update_reserved(ubi);
 		ubi_eba_copy_table(vol, new_eba_tbl, reserved_pebs);
-		ubi_eba_replace_table(vol, new_eba_tbl);
+		old_eba_tbl = vol->eba_tbl;
+		vol->eba_tbl = new_eba_tbl;
+		vol->reserved_pebs = reserved_pebs;
 		spin_unlock(&ubi->volumes_lock);
 	}
 
@@ -493,7 +538,6 @@ int ubi_resize_volume(struct ubi_volume_desc *desc, int reserved_pebs)
 	if (err)
 		goto out_acc;
 
-	vol->reserved_pebs = reserved_pebs;
 	if (vol->vol_type == UBI_DYNAMIC_VOLUME) {
 		vol->used_ebs = reserved_pebs;
 		vol->last_eb_bytes = vol->usable_leb_size;
@@ -501,19 +545,23 @@ int ubi_resize_volume(struct ubi_volume_desc *desc, int reserved_pebs)
 			(long long)vol->used_ebs * vol->usable_leb_size;
 	}
 
+	/* destroy old table */
+	ubi_eba_destroy_table(old_eba_tbl);
 	ubi_volume_notify(ubi, vol, UBI_VOLUME_RESIZED);
 	self_check_volumes(ubi);
 	return err;
 
 out_acc:
-	if (pebs > 0) {
-		spin_lock(&ubi->volumes_lock);
-		ubi->rsvd_pebs -= pebs;
-		ubi->avail_pebs += pebs;
-		spin_unlock(&ubi->volumes_lock);
-	}
-	return err;
-
+	spin_lock(&ubi->volumes_lock);
+	vol->reserved_pebs = reserved_pebs - pebs;
+	ubi->rsvd_pebs -= pebs;
+	ubi->avail_pebs += pebs;
+	if (pebs > 0)
+		ubi_eba_copy_table(vol, old_eba_tbl, vol->reserved_pebs);
+	else
+		ubi_eba_copy_table(vol, old_eba_tbl, reserved_pebs);
+	vol->eba_tbl = old_eba_tbl;
+	spin_unlock(&ubi->volumes_lock);
 out_free:
 	ubi_eba_destroy_table(new_eba_tbl);
 	return err;
@@ -592,6 +640,7 @@ int ubi_add_volume(struct ubi_device *ubi, struct ubi_volume *vol)
 	vol->dev.class = &ubi_class;
 	vol->dev.groups = volume_dev_groups;
 	dev_set_name(&vol->dev, "%s_%d", ubi->ubi_name, vol->vol_id);
+	device_set_node(&vol->dev, find_volume_fwnode(vol));
 	err = device_register(&vol->dev);
 	if (err) {
 		cdev_del(&vol->cdev);

drivers/mtd/ubi/vtbl.c

@@ -791,6 +791,12 @@ int ubi_read_volume_table(struct ubi_device *ubi, struct ubi_attach_info *ai)
 	 * The number of supported volumes is limited by the eraseblock size
 	 * and by the UBI_MAX_VOLUMES constant.
 	 */
+
+	if (ubi->leb_size < UBI_VTBL_RECORD_SIZE) {
+		ubi_err(ubi, "LEB size too small for a volume record");
+		return -EINVAL;
+	}
+
 	ubi->vtbl_slots = ubi->leb_size / UBI_VTBL_RECORD_SIZE;
 	if (ubi->vtbl_slots > UBI_MAX_VOLUMES)
 		ubi->vtbl_slots = UBI_MAX_VOLUMES;

fs/ubifs/debug.c

@@ -1742,17 +1742,22 @@ int dbg_check_idx_size(struct ubifs_info *c, long long idx_size)
 	err = dbg_walk_index(c, NULL, add_size, &calc);
 	if (err) {
 		ubifs_err(c, "error %d while walking the index", err);
-		return err;
+		goto out_err;
 	}
 
 	if (calc != idx_size) {
 		ubifs_err(c, "index size check failed: calculated size is %lld, should be %lld",
 			  calc, idx_size);
 		dump_stack();
-		return -EINVAL;
+		err = -EINVAL;
+		goto out_err;
 	}
 
 	return 0;
+
+out_err:
+	ubifs_destroy_tnc_tree(c);
+	return err;
 }
 
 /**

fs/ubifs/dir.c

@@ -1133,6 +1133,8 @@ static int ubifs_mknod(struct mnt_idmap *idmap, struct inode *dir,
 	dir_ui->ui_size = dir->i_size;
 	mutex_unlock(&dir_ui->ui_mutex);
 out_inode:
+	/* Free inode->i_link before inode is marked as bad. */
+	fscrypt_free_inode(inode);
 	make_bad_inode(inode);
 	iput(inode);
 out_fname:

fs/ubifs/find.c

@@ -82,8 +82,9 @@ static int valuable(struct ubifs_info *c, const struct ubifs_lprops *lprops)
  */
 static int scan_for_dirty_cb(struct ubifs_info *c,
 			     const struct ubifs_lprops *lprops, int in_tree,
-			     struct scan_data *data)
+			     void *arg)
 {
+	struct scan_data *data = arg;
 	int ret = LPT_SCAN_CONTINUE;
 
 	/* Exclude LEBs that are currently in use */
@@ -166,8 +167,7 @@ static const struct ubifs_lprops *scan_for_dirty(struct ubifs_info *c,
 	data.pick_free = pick_free;
 	data.lnum = -1;
 	data.exclude_index = exclude_index;
-	err = ubifs_lpt_scan_nolock(c, -1, c->lscan_lnum,
-				    (ubifs_lpt_scan_callback)scan_for_dirty_cb,
+	err = ubifs_lpt_scan_nolock(c, -1, c->lscan_lnum, scan_for_dirty_cb,
 				    &data);
 	if (err)
 		return ERR_PTR(err);
@@ -349,8 +349,9 @@ int ubifs_find_dirty_leb(struct ubifs_info *c, struct ubifs_lprops *ret_lp,
  */
 static int scan_for_free_cb(struct ubifs_info *c,
 			    const struct ubifs_lprops *lprops, int in_tree,
-			    struct scan_data *data)
+			    void *arg)
 {
+	struct scan_data *data = arg;
 	int ret = LPT_SCAN_CONTINUE;
 
 	/* Exclude LEBs that are currently in use */
@@ -446,7 +447,7 @@ const struct ubifs_lprops *do_find_free_space(struct ubifs_info *c,
 	data.pick_free = pick_free;
 	data.lnum = -1;
 	err = ubifs_lpt_scan_nolock(c, -1, c->lscan_lnum,
-				    (ubifs_lpt_scan_callback)scan_for_free_cb,
+				    scan_for_free_cb,
 				    &data);
 	if (err)
 		return ERR_PTR(err);
@@ -589,8 +590,9 @@ int ubifs_find_free_space(struct ubifs_info *c, int min_space, int *offs,
  */
 static int scan_for_idx_cb(struct ubifs_info *c,
 			   const struct ubifs_lprops *lprops, int in_tree,
-			   struct scan_data *data)
+			   void *arg)
 {
+	struct scan_data *data = arg;
 	int ret = LPT_SCAN_CONTINUE;
 
 	/* Exclude LEBs that are currently in use */
@@ -625,8 +627,7 @@ static const struct ubifs_lprops *scan_for_leb_for_idx(struct ubifs_info *c)
 	int err;
 
 	data.lnum = -1;
-	err = ubifs_lpt_scan_nolock(c, -1, c->lscan_lnum,
-				    (ubifs_lpt_scan_callback)scan_for_idx_cb,
+	err = ubifs_lpt_scan_nolock(c, -1, c->lscan_lnum, scan_for_idx_cb,
 				    &data);
 	if (err)
 		return ERR_PTR(err);
@@ -726,11 +727,10 @@ int ubifs_find_free_leb_for_idx(struct ubifs_info *c)
 	return err;
 }
 
-static int cmp_dirty_idx(const struct ubifs_lprops **a,
-			 const struct ubifs_lprops **b)
+static int cmp_dirty_idx(const void *a, const void *b)
 {
-	const struct ubifs_lprops *lpa = *a;
-	const struct ubifs_lprops *lpb = *b;
+	const struct ubifs_lprops *lpa = *(const struct ubifs_lprops **)a;
+	const struct ubifs_lprops *lpb = *(const struct ubifs_lprops **)b;
 
 	return lpa->dirty + lpa->free - lpb->dirty - lpb->free;
 }
@@ -754,7 +754,7 @@ int ubifs_save_dirty_idx_lnums(struct ubifs_info *c)
 	       sizeof(void *) * c->dirty_idx.cnt);
 	/* Sort it so that the dirtiest is now at the end */
 	sort(c->dirty_idx.arr, c->dirty_idx.cnt, sizeof(void *),
-	     (int (*)(const void *, const void *))cmp_dirty_idx, NULL);
+	     cmp_dirty_idx, NULL);
 	dbg_find("found %d dirty index LEBs", c->dirty_idx.cnt);
 	if (c->dirty_idx.cnt)
 		dbg_find("dirtiest index LEB is %d with dirty %d and free %d",
@@ -782,8 +782,9 @@ int ubifs_save_dirty_idx_lnums(struct ubifs_info *c)
  */
 static int scan_dirty_idx_cb(struct ubifs_info *c,
 			   const struct ubifs_lprops *lprops, int in_tree,
-			   struct scan_data *data)
+			   void *arg)
 {
+	struct scan_data *data = arg;
 	int ret = LPT_SCAN_CONTINUE;
 
 	/* Exclude LEBs that are currently in use */
@@ -842,8 +843,7 @@ static int find_dirty_idx_leb(struct ubifs_info *c)
 	if (c->pnodes_have >= c->pnode_cnt)
 		/* All pnodes are in memory, so skip scan */
 		return -ENOSPC;
-	err = ubifs_lpt_scan_nolock(c, -1, c->lscan_lnum,
-				    (ubifs_lpt_scan_callback)scan_dirty_idx_cb,
+	err = ubifs_lpt_scan_nolock(c, -1, c->lscan_lnum, scan_dirty_idx_cb,
 				    &data);
 	if (err)
 		return err;

fs/ubifs/journal.c

@@ -292,6 +292,96 @@ static int write_head(struct ubifs_info *c, int jhead, void *buf, int len,
 	return err;
 }
 
+/**
+ * __queue_and_wait - queue a task and wait until the task is waked up.
+ * @c: UBIFS file-system description object
+ *
+ * This function adds current task in queue and waits until the task is waked
+ * up. This function should be called with @c->reserve_space_wq locked.
+ */
+static void __queue_and_wait(struct ubifs_info *c)
+{
+	DEFINE_WAIT(wait);
+
+	__add_wait_queue_entry_tail_exclusive(&c->reserve_space_wq, &wait);
+	set_current_state(TASK_UNINTERRUPTIBLE);
+	spin_unlock(&c->reserve_space_wq.lock);
+
+	schedule();
+	finish_wait(&c->reserve_space_wq, &wait);
+}
+
+/**
+ * wait_for_reservation - try queuing current task to wait until waked up.
+ * @c: UBIFS file-system description object
+ *
+ * This function queues current task to wait until waked up, if queuing is
+ * started(@c->need_wait_space is not %0). Returns %true if current task is
+ * added in queue, otherwise %false is returned.
+ */
+static bool wait_for_reservation(struct ubifs_info *c)
+{
+	if (likely(atomic_read(&c->need_wait_space) == 0))
+		/* Quick path to check whether queuing is started. */
+		return false;
+
+	spin_lock(&c->reserve_space_wq.lock);
+	if (atomic_read(&c->need_wait_space) == 0) {
+		/* Queuing is not started, don't queue current task. */
+		spin_unlock(&c->reserve_space_wq.lock);
+		return false;
+	}
+
+	__queue_and_wait(c);
+	return true;
+}
+
+/**
+ * wake_up_reservation - wake up first task in queue or stop queuing.
+ * @c: UBIFS file-system description object
+ *
+ * This function wakes up the first task in queue if it exists, or stops
+ * queuing if no tasks in queue.
+ */
+static void wake_up_reservation(struct ubifs_info *c)
+{
+	spin_lock(&c->reserve_space_wq.lock);
+	if (waitqueue_active(&c->reserve_space_wq))
+		wake_up_locked(&c->reserve_space_wq);
+	else
+		/*
+		 * Compared with wait_for_reservation(), set @c->need_wait_space
+		 * under the protection of wait queue lock, which can avoid that
+		 * @c->need_wait_space is set to 0 after new task queued.
+		 */
+		atomic_set(&c->need_wait_space, 0);
+	spin_unlock(&c->reserve_space_wq.lock);
+}
+
+/**
+ * wake_up_reservation - add current task in queue or start queuing.
+ * @c: UBIFS file-system description object
+ *
+ * This function starts queuing if queuing is not started, otherwise adds
+ * current task in queue.
+ */
+static void add_or_start_queue(struct ubifs_info *c)
+{
+	spin_lock(&c->reserve_space_wq.lock);
+	if (atomic_cmpxchg(&c->need_wait_space, 0, 1) == 0) {
+		/* Starts queuing, task can go on directly. */
+		spin_unlock(&c->reserve_space_wq.lock);
+		return;
+	}
+
+	/*
+	 * There are at least two tasks have retried more than 32 times
+	 * at certain point, first task has started queuing, just queue
+	 * the left tasks.
+	 */
+	__queue_and_wait(c);
+}
+
 /**
  * make_reservation - reserve journal space.
  * @c: UBIFS file-system description object
@@ -311,33 +401,27 @@ static int write_head(struct ubifs_info *c, int jhead, void *buf, int len,
 static int make_reservation(struct ubifs_info *c, int jhead, int len)
 {
 	int err, cmt_retries = 0, nospc_retries = 0;
+	bool blocked = wait_for_reservation(c);
 
 again:
 	down_read(&c->commit_sem);
 	err = reserve_space(c, jhead, len);
-	if (!err)
+	if (!err) {
 		/* c->commit_sem will get released via finish_reservation(). */
-		return 0;
+		goto out_wake_up;
+	}
 	up_read(&c->commit_sem);
 
 	if (err == -ENOSPC) {
 		/*
 		 * GC could not make any progress. We should try to commit
-		 * once because it could make some dirty space and GC would
-		 * make progress, so make the error -EAGAIN so that the below
+		 * because it could make some dirty space and GC would make
+		 * progress, so make the error -EAGAIN so that the below
 		 * will commit and re-try.
 		 */
-		if (nospc_retries++ < 2) {
-			dbg_jnl("no space, retry");
-			err = -EAGAIN;
-		}
-
-		/*
-		 * This means that the budgeting is incorrect. We always have
-		 * to be able to write to the media, because all operations are
-		 * budgeted. Deletions are not budgeted, though, but we reserve
-		 * an extra LEB for them.
-		 */
+		nospc_retries++;
+		dbg_jnl("no space, retry");
+		err = -EAGAIN;
 	}
 
 	if (err != -EAGAIN)
@@ -349,15 +433,37 @@ static int make_reservation(struct ubifs_info *c, int jhead, int len)
 	 */
 	if (cmt_retries > 128) {
 		/*
-		 * This should not happen unless the journal size limitations
-		 * are too tough.
+		 * This should not happen unless:
+		 * 1. The journal size limitations are too tough.
+		 * 2. The budgeting is incorrect. We always have to be able to
+		 *    write to the media, because all operations are budgeted.
+		 *    Deletions are not budgeted, though, but we reserve an
+		 *    extra LEB for them.
 		 */
-		ubifs_err(c, "stuck in space allocation");
+		ubifs_err(c, "stuck in space allocation, nospc_retries %d",
+			  nospc_retries);
 		err = -ENOSPC;
 		goto out;
-	} else if (cmt_retries > 32)
-		ubifs_warn(c, "too many space allocation re-tries (%d)",
-			   cmt_retries);
+	} else if (cmt_retries > 32) {
+		/*
+		 * It's almost impossible to happen, unless there are many tasks
+		 * making reservation concurrently and someone task has retried
+		 * gc + commit for many times, generated available space during
+		 * this period are grabbed by other tasks.
+		 * But if it happens, start queuing up all tasks that will make
+		 * space reservation, then there is only one task making space
+		 * reservation at any time, and it can always make success under
+		 * the premise of correct budgeting.
+		 */
+		ubifs_warn(c, "too many space allocation cmt_retries (%d) "
+			   "nospc_retries (%d), start queuing tasks",
+			   cmt_retries, nospc_retries);
+
+		if (!blocked) {
+			blocked = true;
+			add_or_start_queue(c);
+		}
+	}
 
 	dbg_jnl("-EAGAIN, commit and retry (retried %d times)",
 		cmt_retries);
@@ -365,7 +471,7 @@ static int make_reservation(struct ubifs_info *c, int jhead, int len)
 
 	err = ubifs_run_commit(c);
 	if (err)
-		return err;
+		goto out_wake_up;
 	goto again;
 
 out:
@@ -380,6 +486,27 @@ static int make_reservation(struct ubifs_info *c, int jhead, int len)
 		cmt_retries = dbg_check_lprops(c);
 		up_write(&c->commit_sem);
 	}
+out_wake_up:
+	if (blocked) {
+		/*
+		 * Only tasks that have ever started queuing or ever been queued
+		 * can wake up other queued tasks, which can make sure that
+		 * there is only one task waked up to make space reservation.
+		 * For example:
+		 *      task A          task B           task C
+		 *                 make_reservation  make_reservation
+		 * reserve_space // 0
+		 * wake_up_reservation
+		 *                  atomic_cmpxchg // 0, start queuing
+		 *                  reserve_space
+		 *                                    wait_for_reservation
+		 *                                     __queue_and_wait
+		 *                                      add_wait_queue
+		 *  if (blocked) // false
+		 *  // So that task C won't be waked up to race with task B
+		 */
+		wake_up_reservation(c);
+	}
 	return err;
 }
 

fs/ubifs/lprops.c

@@ -1014,8 +1014,9 @@ void dbg_check_heap(struct ubifs_info *c, struct ubifs_lpt_heap *heap, int cat,
  */
 static int scan_check_cb(struct ubifs_info *c,
 			 const struct ubifs_lprops *lp, int in_tree,
-			 struct ubifs_lp_stats *lst)
+			 void *arg)
 {
+	struct ubifs_lp_stats *lst = arg;
 	struct ubifs_scan_leb *sleb;
 	struct ubifs_scan_node *snod;
 	int cat, lnum = lp->lnum, is_idx = 0, used = 0, free, dirty, ret;
@@ -1269,8 +1270,7 @@ int dbg_check_lprops(struct ubifs_info *c)
 
 	memset(&lst, 0, sizeof(struct ubifs_lp_stats));
 	err = ubifs_lpt_scan_nolock(c, c->main_first, c->leb_cnt - 1,
-				    (ubifs_lpt_scan_callback)scan_check_cb,
-				    &lst);
+				    scan_check_cb, &lst);
 	if (err && err != -ENOSPC)
 		goto out;
 

fs/ubifs/lpt_commit.c

@@ -1646,7 +1646,6 @@ static int dbg_check_ltab_lnum(struct ubifs_info *c, int lnum)
 		len -= node_len;
 	}
 
-	err = 0;
 out:
 	vfree(buf);
 	return err;

fs/ubifs/super.c

@@ -2151,6 +2151,8 @@ static struct ubifs_info *alloc_ubifs_info(struct ubi_volume_desc *ubi)
 		mutex_init(&c->bu_mutex);
 		mutex_init(&c->write_reserve_mutex);
 		init_waitqueue_head(&c->cmt_wq);
+		init_waitqueue_head(&c->reserve_space_wq);
+		atomic_set(&c->need_wait_space, 0);
 		c->buds = RB_ROOT;
 		c->old_idx = RB_ROOT;
 		c->size_tree = RB_ROOT;

fs/ubifs/tnc.c

@@ -3116,14 +3116,7 @@ static void tnc_destroy_cnext(struct ubifs_info *c)
 void ubifs_tnc_close(struct ubifs_info *c)
 {
 	tnc_destroy_cnext(c);
-	if (c->zroot.znode) {
-		long n, freed;
-
-		n = atomic_long_read(&c->clean_zn_cnt);
-		freed = ubifs_destroy_tnc_subtree(c, c->zroot.znode);
-		ubifs_assert(c, freed == n);
-		atomic_long_sub(n, &ubifs_clean_zn_cnt);
-	}
+	ubifs_destroy_tnc_tree(c);
 	kfree(c->gap_lebs);
 	kfree(c->ilebs);
 	destroy_old_idx(c);

fs/ubifs/tnc_misc.c

@@ -250,6 +250,28 @@ long ubifs_destroy_tnc_subtree(const struct ubifs_info *c,
 	}
 }
 
+/**
+ * ubifs_destroy_tnc_tree - destroy all znodes connected to the TNC tree.
+ * @c: UBIFS file-system description object
+ *
+ * This function destroys the whole TNC tree and updates clean global znode
+ * count.
+ */
+void ubifs_destroy_tnc_tree(struct ubifs_info *c)
+{
+	long n, freed;
+
+	if (!c->zroot.znode)
+		return;
+
+	n = atomic_long_read(&c->clean_zn_cnt);
+	freed = ubifs_destroy_tnc_subtree(c, c->zroot.znode);
+	ubifs_assert(c, freed == n);
+	atomic_long_sub(n, &ubifs_clean_zn_cnt);
+
+	c->zroot.znode = NULL;
+}
+
 /**
  * read_znode - read an indexing node from flash and fill znode.
  * @c: UBIFS file-system description object

fs/ubifs/ubifs.h

@@ -1047,6 +1047,8 @@ struct ubifs_debug_info;
  * @bg_bud_bytes: number of bud bytes when background commit is initiated
  * @old_buds: buds to be released after commit ends
  * @max_bud_cnt: maximum number of buds
+ * @need_wait_space: Non %0 means space reservation tasks need to wait in queue
+ * @reserve_space_wq: wait queue to sleep on if @need_wait_space is not %0
  *
  * @commit_sem: synchronizes committer with other processes
  * @cmt_state: commit state
@@ -1305,6 +1307,8 @@ struct ubifs_info {
 	long long bg_bud_bytes;
 	struct list_head old_buds;
 	int max_bud_cnt;
+	atomic_t need_wait_space;
+	wait_queue_head_t reserve_space_wq;
 
 	struct rw_semaphore commit_sem;
 	int cmt_state;
@@ -1903,6 +1907,7 @@ struct ubifs_znode *ubifs_tnc_postorder_next(const struct ubifs_info *c,
 					     struct ubifs_znode *znode);
 long ubifs_destroy_tnc_subtree(const struct ubifs_info *c,
 			       struct ubifs_znode *zr);
+void ubifs_destroy_tnc_tree(struct ubifs_info *c);
 struct ubifs_znode *ubifs_load_znode(struct ubifs_info *c,
 				     struct ubifs_zbranch *zbr,
 				     struct ubifs_znode *parent, int iip);

include/linux/mtd/ubi.h

@@ -192,6 +192,7 @@ struct ubi_device_info {
  *			or a volume was removed)
  * @UBI_VOLUME_RESIZED: a volume has been re-sized
  * @UBI_VOLUME_RENAMED: a volume has been re-named
+ * @UBI_VOLUME_SHUTDOWN: a volume is going to removed, shutdown users
  * @UBI_VOLUME_UPDATED: data has been written to a volume
  *
  * These constants define which type of event has happened when a volume
@@ -202,6 +203,7 @@ enum {
 	UBI_VOLUME_REMOVED,
 	UBI_VOLUME_RESIZED,
 	UBI_VOLUME_RENAMED,
+	UBI_VOLUME_SHUTDOWN,
 	UBI_VOLUME_UPDATED,
 };