Merge tag 'upstream-4.9-rc1' of git://git.infradead.org/linux-ubifs

Pull UBI/UBIFS updates from Richard Weinberger:
 "This pull request contains:

   - Fixes for both UBI and UBIFS
   - overlayfs support (O_TMPFILE, RENAME_WHITEOUT/EXCHANGE)
   - Code refactoring for the upcoming MLC support"

[ Ugh, we just got rid of the "rename2()" naming for the extended rename
  functionality. And this re-introduces it in ubifs with the cross-
  renaming and whiteout support.

  But rather than do any re-organizations in the merge itself, the
  naming can be cleaned up later ]

* tag 'upstream-4.9-rc1' of git://git.infradead.org/linux-ubifs: (27 commits)
  UBIFS: improve function-level documentation
  ubifs: fix host xattr_len when changing xattr
  ubifs: Use move variable in ubifs_rename()
  ubifs: Implement RENAME_EXCHANGE
  ubifs: Implement RENAME_WHITEOUT
  ubifs: Implement O_TMPFILE
  ubi: Fix Fastmap's update_vol()
  ubi: Fix races around ubi_refill_pools()
  ubi: Deal with interrupted erasures in WL
  UBI: introduce the VID buffer concept
  UBI: hide EBA internals
  UBI: provide an helper to query LEB information
  UBI: provide an helper to check whether a LEB is mapped or not
  UBI: add an helper to check lnum validity
  UBI: simplify LEB write and atomic LEB change code
  UBI: simplify recover_peb() code
  UBI: move the global ech and vidh variables into struct ubi_attach_info
  UBI: provide helpers to allocate and free aeb elements
  UBI: fastmap: use ubi_io_{read, write}_data() instead of ubi_io_{read, write}()
  UBI: fastmap: use ubi_rb_for_each_entry() in unmap_peb()
  ...

drivers/mtd/ubi/attach.c

@@ -91,9 +91,132 @@
 
 static int self_check_ai(struct ubi_device *ubi, struct ubi_attach_info *ai);
 
-/* Temporary variables used during scanning */
-static struct ubi_ec_hdr *ech;
-static struct ubi_vid_hdr *vidh;
+#define AV_FIND		BIT(0)
+#define AV_ADD		BIT(1)
+#define AV_FIND_OR_ADD	(AV_FIND | AV_ADD)
+
+/**
+ * find_or_add_av - internal function to find a volume, add a volume or do
+ *		    both (find and add if missing).
+ * @ai: attaching information
+ * @vol_id: the requested volume ID
+ * @flags: a combination of the %AV_FIND and %AV_ADD flags describing the
+ *	   expected operation. If only %AV_ADD is set, -EEXIST is returned
+ *	   if the volume already exists. If only %AV_FIND is set, NULL is
+ *	   returned if the volume does not exist. And if both flags are
+ *	   set, the helper first tries to find an existing volume, and if
+ *	   it does not exist it creates a new one.
+ * @created: in value used to inform the caller whether it"s a newly created
+ *	     volume or not.
+ *
+ * This function returns a pointer to a volume description or an ERR_PTR if
+ * the operation failed. It can also return NULL if only %AV_FIND is set and
+ * the volume does not exist.
+ */
+static struct ubi_ainf_volume *find_or_add_av(struct ubi_attach_info *ai,
+					      int vol_id, unsigned int flags,
+					      bool *created)
+{
+	struct ubi_ainf_volume *av;
+	struct rb_node **p = &ai->volumes.rb_node, *parent = NULL;
+
+	/* Walk the volume RB-tree to look if this volume is already present */
+	while (*p) {
+		parent = *p;
+		av = rb_entry(parent, struct ubi_ainf_volume, rb);
+
+		if (vol_id == av->vol_id) {
+			*created = false;
+
+			if (!(flags & AV_FIND))
+				return ERR_PTR(-EEXIST);
+
+			return av;
+		}
+
+		if (vol_id > av->vol_id)
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+
+	if (!(flags & AV_ADD))
+		return NULL;
+
+	/* The volume is absent - add it */
+	av = kzalloc(sizeof(*av), GFP_KERNEL);
+	if (!av)
+		return ERR_PTR(-ENOMEM);
+
+	av->vol_id = vol_id;
+
+	if (vol_id > ai->highest_vol_id)
+		ai->highest_vol_id = vol_id;
+
+	rb_link_node(&av->rb, parent, p);
+	rb_insert_color(&av->rb, &ai->volumes);
+	ai->vols_found += 1;
+	*created = true;
+	dbg_bld("added volume %d", vol_id);
+	return av;
+}
+
+/**
+ * ubi_find_or_add_av - search for a volume in the attaching information and
+ *			add one if it does not exist.
+ * @ai: attaching information
+ * @vol_id: the requested volume ID
+ * @created: whether the volume has been created or not
+ *
+ * This function returns a pointer to the new volume description or an
+ * ERR_PTR if the operation failed.
+ */
+static struct ubi_ainf_volume *ubi_find_or_add_av(struct ubi_attach_info *ai,
+						  int vol_id, bool *created)
+{
+	return find_or_add_av(ai, vol_id, AV_FIND_OR_ADD, created);
+}
+
+/**
+ * ubi_alloc_aeb - allocate an aeb element
+ * @ai: attaching information
+ * @pnum: physical eraseblock number
+ * @ec: erase counter of the physical eraseblock
+ *
+ * Allocate an aeb object and initialize the pnum and ec information.
+ * vol_id and lnum are set to UBI_UNKNOWN, and the other fields are
+ * initialized to zero.
+ * Note that the element is not added in any list or RB tree.
+ */
+struct ubi_ainf_peb *ubi_alloc_aeb(struct ubi_attach_info *ai, int pnum,
+				   int ec)
+{
+	struct ubi_ainf_peb *aeb;
+
+	aeb = kmem_cache_zalloc(ai->aeb_slab_cache, GFP_KERNEL);
+	if (!aeb)
+		return NULL;
+
+	aeb->pnum = pnum;
+	aeb->ec = ec;
+	aeb->vol_id = UBI_UNKNOWN;
+	aeb->lnum = UBI_UNKNOWN;
+
+	return aeb;
+}
+
+/**
+ * ubi_free_aeb - free an aeb element
+ * @ai: attaching information
+ * @aeb: the element to free
+ *
+ * Free an aeb object. The caller must have removed the element from any list
+ * or RB tree.
+ */
+void ubi_free_aeb(struct ubi_attach_info *ai, struct ubi_ainf_peb *aeb)
+{
+	kmem_cache_free(ai->aeb_slab_cache, aeb);
+}
 
 /**
  * add_to_list - add physical eraseblock to a list.
@@ -131,14 +254,12 @@ static int add_to_list(struct ubi_attach_info *ai, int pnum, int vol_id,
 	} else
 		BUG();
 
-	aeb = kmem_cache_alloc(ai->aeb_slab_cache, GFP_KERNEL);
+	aeb = ubi_alloc_aeb(ai, pnum, ec);
 	if (!aeb)
 		return -ENOMEM;
 
-	aeb->pnum = pnum;
 	aeb->vol_id = vol_id;
 	aeb->lnum = lnum;
-	aeb->ec = ec;
 	if (to_head)
 		list_add(&aeb->u.list, list);
 	else
@@ -163,13 +284,11 @@ static int add_corrupted(struct ubi_attach_info *ai, int pnum, int ec)
 
 	dbg_bld("add to corrupted: PEB %d, EC %d", pnum, ec);
 
-	aeb = kmem_cache_alloc(ai->aeb_slab_cache, GFP_KERNEL);
+	aeb = ubi_alloc_aeb(ai, pnum, ec);
 	if (!aeb)
 		return -ENOMEM;
 
 	ai->corr_peb_count += 1;
-	aeb->pnum = pnum;
-	aeb->ec = ec;
 	list_add(&aeb->u.list, &ai->corr);
 	return 0;
 }
@@ -192,14 +311,12 @@ static int add_fastmap(struct ubi_attach_info *ai, int pnum,
 {
 	struct ubi_ainf_peb *aeb;
 
-	aeb = kmem_cache_alloc(ai->aeb_slab_cache, GFP_KERNEL);
+	aeb = ubi_alloc_aeb(ai, pnum, ec);
 	if (!aeb)
 		return -ENOMEM;
 
-	aeb->pnum = pnum;
-	aeb->vol_id = be32_to_cpu(vidh->vol_id);
-	aeb->sqnum = be64_to_cpu(vidh->sqnum);
-	aeb->ec = ec;
+	aeb->vol_id = be32_to_cpu(vid_hdr->vol_id);
+	aeb->sqnum = be64_to_cpu(vid_hdr->sqnum);
 	list_add(&aeb->u.list, &ai->fastmap);
 
 	dbg_bld("add to fastmap list: PEB %d, vol_id %d, sqnum: %llu", pnum,
@@ -294,44 +411,20 @@ static struct ubi_ainf_volume *add_volume(struct ubi_attach_info *ai,
 					  const struct ubi_vid_hdr *vid_hdr)
 {
 	struct ubi_ainf_volume *av;
-	struct rb_node **p = &ai->volumes.rb_node, *parent = NULL;
+	bool created;
 
 	ubi_assert(vol_id == be32_to_cpu(vid_hdr->vol_id));
 
-	/* Walk the volume RB-tree to look if this volume is already present */
-	while (*p) {
-		parent = *p;
-		av = rb_entry(parent, struct ubi_ainf_volume, rb);
-
-		if (vol_id == av->vol_id)
+	av = ubi_find_or_add_av(ai, vol_id, &created);
+	if (IS_ERR(av) || !created)
 		return av;
 
-		if (vol_id > av->vol_id)
-			p = &(*p)->rb_left;
-		else
-			p = &(*p)->rb_right;
-	}
-
-	/* The volume is absent - add it */
-	av = kmalloc(sizeof(struct ubi_ainf_volume), GFP_KERNEL);
-	if (!av)
-		return ERR_PTR(-ENOMEM);
-
-	av->highest_lnum = av->leb_count = 0;
-	av->vol_id = vol_id;
-	av->root = RB_ROOT;
 	av->used_ebs = be32_to_cpu(vid_hdr->used_ebs);
 	av->data_pad = be32_to_cpu(vid_hdr->data_pad);
 	av->compat = vid_hdr->compat;
 	av->vol_type = vid_hdr->vol_type == UBI_VID_DYNAMIC ? UBI_DYNAMIC_VOLUME
 							    : UBI_STATIC_VOLUME;
-	if (vol_id > ai->highest_vol_id)
-		ai->highest_vol_id = vol_id;
 
-	rb_link_node(&av->rb, parent, p);
-	rb_insert_color(&av->rb, &ai->volumes);
-	ai->vols_found += 1;
-	dbg_bld("added volume %d", vol_id);
 	return av;
 }
 
@@ -360,7 +453,7 @@ int ubi_compare_lebs(struct ubi_device *ubi, const struct ubi_ainf_peb *aeb,
 {
 	int len, err, second_is_newer, bitflips = 0, corrupted = 0;
 	uint32_t data_crc, crc;
-	struct ubi_vid_hdr *vh = NULL;
+	struct ubi_vid_io_buf *vidb = NULL;
 	unsigned long long sqnum2 = be64_to_cpu(vid_hdr->sqnum);
 
 	if (sqnum2 == aeb->sqnum) {
@@ -403,12 +496,12 @@ int ubi_compare_lebs(struct ubi_device *ubi, const struct ubi_ainf_peb *aeb,
 			return bitflips << 1;
 		}
 
-		vh = ubi_zalloc_vid_hdr(ubi, GFP_KERNEL);
-		if (!vh)
+		vidb = ubi_alloc_vid_buf(ubi, GFP_KERNEL);
+		if (!vidb)
 			return -ENOMEM;
 
 		pnum = aeb->pnum;
-		err = ubi_io_read_vid_hdr(ubi, pnum, vh, 0);
+		err = ubi_io_read_vid_hdr(ubi, pnum, vidb, 0);
 		if (err) {
 			if (err == UBI_IO_BITFLIPS)
 				bitflips = 1;
@@ -422,7 +515,7 @@ int ubi_compare_lebs(struct ubi_device *ubi, const struct ubi_ainf_peb *aeb,
 			}
 		}
 
-		vid_hdr = vh;
+		vid_hdr = ubi_get_vid_hdr(vidb);
 	}
 
 	/* Read the data of the copy and check the CRC */
@@ -448,7 +541,7 @@ int ubi_compare_lebs(struct ubi_device *ubi, const struct ubi_ainf_peb *aeb,
 	}
 	mutex_unlock(&ubi->buf_mutex);
 
-	ubi_free_vid_hdr(ubi, vh);
+	ubi_free_vid_buf(vidb);
 
 	if (second_is_newer)
 		dbg_bld("second PEB %d is newer, copy_flag is set", pnum);
@@ -460,7 +553,7 @@ int ubi_compare_lebs(struct ubi_device *ubi, const struct ubi_ainf_peb *aeb,
 out_unlock:
 	mutex_unlock(&ubi->buf_mutex);
 out_free_vidh:
-	ubi_free_vid_hdr(ubi, vh);
+	ubi_free_vid_buf(vidb);
 	return err;
 }
 
@@ -605,12 +698,10 @@ int ubi_add_to_av(struct ubi_device *ubi, struct ubi_attach_info *ai, int pnum,
 	if (err)
 		return err;
 
-	aeb = kmem_cache_alloc(ai->aeb_slab_cache, GFP_KERNEL);
+	aeb = ubi_alloc_aeb(ai, pnum, ec);
 	if (!aeb)
 		return -ENOMEM;
 
-	aeb->ec = ec;
-	aeb->pnum = pnum;
 	aeb->vol_id = vol_id;
 	aeb->lnum = lnum;
 	aeb->scrub = bitflips;
@@ -628,6 +719,21 @@ int ubi_add_to_av(struct ubi_device *ubi, struct ubi_attach_info *ai, int pnum,
 	return 0;
 }
 
+/**
+ * ubi_add_av - add volume to the attaching information.
+ * @ai: attaching information
+ * @vol_id: the requested volume ID
+ *
+ * This function returns a pointer to the new volume description or an
+ * ERR_PTR if the operation failed.
+ */
+struct ubi_ainf_volume *ubi_add_av(struct ubi_attach_info *ai, int vol_id)
+{
+	bool created;
+
+	return find_or_add_av(ai, vol_id, AV_ADD, &created);
+}
+
 /**
  * ubi_find_av - find volume in the attaching information.
  * @ai: attaching information
@@ -639,24 +745,15 @@ int ubi_add_to_av(struct ubi_device *ubi, struct ubi_attach_info *ai, int pnum,
 struct ubi_ainf_volume *ubi_find_av(const struct ubi_attach_info *ai,
 				    int vol_id)
 {
-	struct ubi_ainf_volume *av;
-	struct rb_node *p = ai->volumes.rb_node;
+	bool created;
 
-	while (p) {
-		av = rb_entry(p, struct ubi_ainf_volume, rb);
-
-		if (vol_id == av->vol_id)
-			return av;
-
-		if (vol_id > av->vol_id)
-			p = p->rb_left;
-		else
-			p = p->rb_right;
-	}
-
-	return NULL;
+	return find_or_add_av((struct ubi_attach_info *)ai, vol_id, AV_FIND,
+			      &created);
 }
 
+static void destroy_av(struct ubi_attach_info *ai, struct ubi_ainf_volume *av,
+		       struct list_head *list);
+
 /**
  * ubi_remove_av - delete attaching information about a volume.
  * @ai: attaching information
@@ -664,19 +761,10 @@ struct ubi_ainf_volume *ubi_find_av(const struct ubi_attach_info *ai,
  */
 void ubi_remove_av(struct ubi_attach_info *ai, struct ubi_ainf_volume *av)
 {
-	struct rb_node *rb;
-	struct ubi_ainf_peb *aeb;
-
 	dbg_bld("remove attaching information about volume %d", av->vol_id);
 
-	while ((rb = rb_first(&av->root))) {
-		aeb = rb_entry(rb, struct ubi_ainf_peb, u.rb);
-		rb_erase(&aeb->u.rb, &av->root);
-		list_add_tail(&aeb->u.list, &ai->erase);
-	}
-
 	rb_erase(&av->rb, &ai->volumes);
-	kfree(av);
+	destroy_av(ai, av, &ai->erase);
 	ai->vols_found -= 1;
 }
 
@@ -866,6 +954,9 @@ static bool vol_ignored(int vol_id)
 static int scan_peb(struct ubi_device *ubi, struct ubi_attach_info *ai,
 		    int pnum, bool fast)
 {
+	struct ubi_ec_hdr *ech = ai->ech;
+	struct ubi_vid_io_buf *vidb = ai->vidb;
+	struct ubi_vid_hdr *vidh = ubi_get_vid_hdr(vidb);
 	long long ec;
 	int err, bitflips = 0, vol_id = -1, ec_err = 0;
 
@@ -963,7 +1054,7 @@ static int scan_peb(struct ubi_device *ubi, struct ubi_attach_info *ai,
 
 	/* OK, we've done with the EC header, let's look at the VID header */
 
-	err = ubi_io_read_vid_hdr(ubi, pnum, vidh, 0);
+	err = ubi_io_read_vid_hdr(ubi, pnum, vidb, 0);
 	if (err < 0)
 		return err;
 	switch (err) {
@@ -1191,10 +1282,12 @@ static int late_analysis(struct ubi_device *ubi, struct ubi_attach_info *ai)
  * destroy_av - free volume attaching information.
  * @av: volume attaching information
  * @ai: attaching information
+ * @list: put the aeb elements in there if !NULL, otherwise free them
  *
  * This function destroys the volume attaching information.
  */
-static void destroy_av(struct ubi_attach_info *ai, struct ubi_ainf_volume *av)
+static void destroy_av(struct ubi_attach_info *ai, struct ubi_ainf_volume *av,
+		       struct list_head *list)
 {
 	struct ubi_ainf_peb *aeb;
 	struct rb_node *this = av->root.rb_node;
@@ -1214,7 +1307,10 @@ static void destroy_av(struct ubi_attach_info *ai, struct ubi_ainf_volume *av)
 					this->rb_right = NULL;
 			}
 
-			kmem_cache_free(ai->aeb_slab_cache, aeb);
+			if (list)
+				list_add_tail(&aeb->u.list, list);
+			else
+				ubi_free_aeb(ai, aeb);
 		}
 	}
 	kfree(av);
@@ -1232,23 +1328,23 @@ static void destroy_ai(struct ubi_attach_info *ai)
 
 	list_for_each_entry_safe(aeb, aeb_tmp, &ai->alien, u.list) {
 		list_del(&aeb->u.list);
-		kmem_cache_free(ai->aeb_slab_cache, aeb);
+		ubi_free_aeb(ai, aeb);
 	}
 	list_for_each_entry_safe(aeb, aeb_tmp, &ai->erase, u.list) {
 		list_del(&aeb->u.list);
-		kmem_cache_free(ai->aeb_slab_cache, aeb);
+		ubi_free_aeb(ai, aeb);
 	}
 	list_for_each_entry_safe(aeb, aeb_tmp, &ai->corr, u.list) {
 		list_del(&aeb->u.list);
-		kmem_cache_free(ai->aeb_slab_cache, aeb);
+		ubi_free_aeb(ai, aeb);
 	}
 	list_for_each_entry_safe(aeb, aeb_tmp, &ai->free, u.list) {
 		list_del(&aeb->u.list);
-		kmem_cache_free(ai->aeb_slab_cache, aeb);
+		ubi_free_aeb(ai, aeb);
 	}
 	list_for_each_entry_safe(aeb, aeb_tmp, &ai->fastmap, u.list) {
 		list_del(&aeb->u.list);
-		kmem_cache_free(ai->aeb_slab_cache, aeb);
+		ubi_free_aeb(ai, aeb);
 	}
 
 	/* Destroy the volume RB-tree */
@@ -1269,7 +1365,7 @@ static void destroy_ai(struct ubi_attach_info *ai)
 					rb->rb_right = NULL;
 			}
 
-			destroy_av(ai, av);
+			destroy_av(ai, av, NULL);
 		}
 	}
 
@@ -1297,12 +1393,12 @@ static int scan_all(struct ubi_device *ubi, struct ubi_attach_info *ai,
 
 	err = -ENOMEM;
 
-	ech = kzalloc(ubi->ec_hdr_alsize, GFP_KERNEL);
-	if (!ech)
+	ai->ech = kzalloc(ubi->ec_hdr_alsize, GFP_KERNEL);
+	if (!ai->ech)
 		return err;
 
-	vidh = ubi_zalloc_vid_hdr(ubi, GFP_KERNEL);
-	if (!vidh)
+	ai->vidb = ubi_alloc_vid_buf(ubi, GFP_KERNEL);
+	if (!ai->vidb)
 		goto out_ech;
 
 	for (pnum = start; pnum < ubi->peb_count; pnum++) {
@@ -1351,15 +1447,15 @@ static int scan_all(struct ubi_device *ubi, struct ubi_attach_info *ai,
 	if (err)
 		goto out_vidh;
 
-	ubi_free_vid_hdr(ubi, vidh);
-	kfree(ech);
+	ubi_free_vid_buf(ai->vidb);
+	kfree(ai->ech);
 
 	return 0;
 
 out_vidh:
-	ubi_free_vid_hdr(ubi, vidh);
+	ubi_free_vid_buf(ai->vidb);
 out_ech:
-	kfree(ech);
+	kfree(ai->ech);
 	return err;
 }
 
@@ -1411,12 +1507,12 @@ static int scan_fast(struct ubi_device *ubi, struct ubi_attach_info **ai)
 	if (!scan_ai)
 		goto out;
 
-	ech = kzalloc(ubi->ec_hdr_alsize, GFP_KERNEL);
-	if (!ech)
+	scan_ai->ech = kzalloc(ubi->ec_hdr_alsize, GFP_KERNEL);
+	if (!scan_ai->ech)
 		goto out_ai;
 
-	vidh = ubi_zalloc_vid_hdr(ubi, GFP_KERNEL);
-	if (!vidh)
+	scan_ai->vidb = ubi_alloc_vid_buf(ubi, GFP_KERNEL);
+	if (!scan_ai->vidb)
 		goto out_ech;
 
 	for (pnum = 0; pnum < UBI_FM_MAX_START; pnum++) {
@@ -1428,8 +1524,8 @@ static int scan_fast(struct ubi_device *ubi, struct ubi_attach_info **ai)
 			goto out_vidh;
 	}
 
-	ubi_free_vid_hdr(ubi, vidh);
-	kfree(ech);
+	ubi_free_vid_buf(scan_ai->vidb);
+	kfree(scan_ai->ech);
 
 	if (scan_ai->force_full_scan)
 		err = UBI_NO_FASTMAP;
@@ -1449,9 +1545,9 @@ static int scan_fast(struct ubi_device *ubi, struct ubi_attach_info **ai)
 	return err;
 
 out_vidh:
-	ubi_free_vid_hdr(ubi, vidh);
+	ubi_free_vid_buf(scan_ai->vidb);
 out_ech:
-	kfree(ech);
+	kfree(scan_ai->ech);
 out_ai:
 	destroy_ai(scan_ai);
 out:
@@ -1573,6 +1669,8 @@ int ubi_attach(struct ubi_device *ubi, int force_scan)
  */
 static int self_check_ai(struct ubi_device *ubi, struct ubi_attach_info *ai)
 {
+	struct ubi_vid_io_buf *vidb = ai->vidb;
+	struct ubi_vid_hdr *vidh = ubi_get_vid_hdr(vidb);
 	int pnum, err, vols_found = 0;
 	struct rb_node *rb1, *rb2;
 	struct ubi_ainf_volume *av;
@@ -1708,7 +1806,7 @@ static int self_check_ai(struct ubi_device *ubi, struct ubi_attach_info *ai)
 
 			last_aeb = aeb;
 
-			err = ubi_io_read_vid_hdr(ubi, aeb->pnum, vidh, 1);
+			err = ubi_io_read_vid_hdr(ubi, aeb->pnum, vidb, 1);
 			if (err && err != UBI_IO_BITFLIPS) {
 				ubi_err(ubi, "VID header is not OK (%d)",
 					err);

drivers/mtd/ubi/build.c

@@ -574,7 +574,7 @@ void ubi_free_internal_volumes(struct ubi_device *ubi)
 
 	for (i = ubi->vtbl_slots;
 	     i < ubi->vtbl_slots + UBI_INT_VOL_COUNT; i++) {
-		kfree(ubi->volumes[i]->eba_tbl);
+		ubi_eba_replace_table(ubi->volumes[i], NULL);
 		kfree(ubi->volumes[i]);
 	}
 }

drivers/mtd/ubi/cdev.c

@@ -416,7 +416,7 @@ static long vol_cdev_ioctl(struct file *file, unsigned int cmd,
 		}
 
 		rsvd_bytes = (long long)vol->reserved_pebs *
-					ubi->leb_size-vol->data_pad;
+					vol->usable_leb_size;
 		if (bytes < 0 || bytes > rsvd_bytes) {
 			err = -EINVAL;
 			break;
@@ -454,7 +454,7 @@ static long vol_cdev_ioctl(struct file *file, unsigned int cmd,
 
 		/* Validate the request */
 		err = -EINVAL;
-		if (req.lnum < 0 || req.lnum >= vol->reserved_pebs ||
+		if (!ubi_leb_valid(vol, req.lnum) ||
 		    req.bytes < 0 || req.bytes > vol->usable_leb_size)
 			break;
 
@@ -485,7 +485,7 @@ static long vol_cdev_ioctl(struct file *file, unsigned int cmd,
 			break;
 		}
 
-		if (lnum < 0 || lnum >= vol->reserved_pebs) {
+		if (!ubi_leb_valid(vol, lnum)) {
 			err = -EINVAL;
 			break;
 		}

drivers/mtd/ubi/eba.c

@@ -49,6 +49,30 @@
 /* Number of physical eraseblocks reserved for atomic LEB change operation */
 #define EBA_RESERVED_PEBS 1
 
+/**
+ * struct ubi_eba_entry - structure encoding a single LEB -> PEB association
+ * @pnum: the physical eraseblock number attached to the LEB
+ *
+ * This structure is encoding a LEB -> PEB association. Note that the LEB
+ * number is not stored here, because it is the index used to access the
+ * entries table.
+ */
+struct ubi_eba_entry {
+	int pnum;
+};
+
+/**
+ * struct ubi_eba_table - LEB -> PEB association information
+ * @entries: the LEB to PEB mapping (one entry per LEB).
+ *
+ * This structure is private to the EBA logic and should be kept here.
+ * It is encoding the LEB to PEB association table, and is subject to
+ * changes.
+ */
+struct ubi_eba_table {
+	struct ubi_eba_entry *entries;
+};
+
 /**
  * next_sqnum - get next sequence number.
  * @ubi: UBI device description object
@@ -83,6 +107,110 @@ static int ubi_get_compat(const struct ubi_device *ubi, int vol_id)
 	return 0;
 }
 
+/**
+ * ubi_eba_get_ldesc - get information about a LEB
+ * @vol: volume description object
+ * @lnum: logical eraseblock number
+ * @ldesc: the LEB descriptor to fill
+ *
+ * Used to query information about a specific LEB.
+ * It is currently only returning the physical position of the LEB, but will be
+ * extended to provide more information.
+ */
+void ubi_eba_get_ldesc(struct ubi_volume *vol, int lnum,
+		       struct ubi_eba_leb_desc *ldesc)
+{
+	ldesc->lnum = lnum;
+	ldesc->pnum = vol->eba_tbl->entries[lnum].pnum;
+}
+
+/**
+ * ubi_eba_create_table - allocate a new EBA table and initialize it with all
+ *			  LEBs unmapped
+ * @vol: volume containing the EBA table to copy
+ * @nentries: number of entries in the table
+ *
+ * Allocate a new EBA table and initialize it with all LEBs unmapped.
+ * Returns a valid pointer if it succeed, an ERR_PTR() otherwise.
+ */
+struct ubi_eba_table *ubi_eba_create_table(struct ubi_volume *vol,
+					   int nentries)
+{
+	struct ubi_eba_table *tbl;
+	int err = -ENOMEM;
+	int i;
+
+	tbl = kzalloc(sizeof(*tbl), GFP_KERNEL);
+	if (!tbl)
+		return ERR_PTR(-ENOMEM);
+
+	tbl->entries = kmalloc_array(nentries, sizeof(*tbl->entries),
+				     GFP_KERNEL);
+	if (!tbl->entries)
+		goto err;
+
+	for (i = 0; i < nentries; i++)
+		tbl->entries[i].pnum = UBI_LEB_UNMAPPED;
+
+	return tbl;
+
+err:
+	kfree(tbl->entries);
+	kfree(tbl);
+
+	return ERR_PTR(err);
+}
+
+/**
+ * ubi_eba_destroy_table - destroy an EBA table
+ * @tbl: the table to destroy
+ *
+ * Destroy an EBA table.
+ */
+void ubi_eba_destroy_table(struct ubi_eba_table *tbl)
+{
+	if (!tbl)
+		return;
+
+	kfree(tbl->entries);
+	kfree(tbl);
+}
+
+/**
+ * ubi_eba_copy_table - copy the EBA table attached to vol into another table
+ * @vol: volume containing the EBA table to copy
+ * @dst: destination
+ * @nentries: number of entries to copy
+ *
+ * Copy the EBA table stored in vol into the one pointed by dst.
+ */
+void ubi_eba_copy_table(struct ubi_volume *vol, struct ubi_eba_table *dst,
+			int nentries)
+{
+	struct ubi_eba_table *src;
+	int i;
+
+	ubi_assert(dst && vol && vol->eba_tbl);
+
+	src = vol->eba_tbl;
+
+	for (i = 0; i < nentries; i++)
+		dst->entries[i].pnum = src->entries[i].pnum;
+}
+
+/**
+ * ubi_eba_replace_table - assign a new EBA table to a volume
+ * @vol: volume containing the EBA table to copy
+ * @tbl: new EBA table
+ *
+ * Assign a new EBA table to the volume and release the old one.
+ */
+void ubi_eba_replace_table(struct ubi_volume *vol, struct ubi_eba_table *tbl)
+{
+	ubi_eba_destroy_table(vol->eba_tbl);
+	vol->eba_tbl = tbl;
+}
+
 /**
  * ltree_lookup - look up the lock tree.
  * @ubi: UBI device description object
@@ -311,6 +439,18 @@ static void leb_write_unlock(struct ubi_device *ubi, int vol_id, int lnum)
 	spin_unlock(&ubi->ltree_lock);
 }
 
+/**
+ * ubi_eba_is_mapped - check if a LEB is mapped.
+ * @vol: volume description object
+ * @lnum: logical eraseblock number
+ *
+ * This function returns true if the LEB is mapped, false otherwise.
+ */
+bool ubi_eba_is_mapped(struct ubi_volume *vol, int lnum)
+{
+	return vol->eba_tbl->entries[lnum].pnum >= 0;
+}
+
 /**
  * ubi_eba_unmap_leb - un-map logical eraseblock.
  * @ubi: UBI device description object
@@ -333,7 +473,7 @@ int ubi_eba_unmap_leb(struct ubi_device *ubi, struct ubi_volume *vol,
 	if (err)
 		return err;
 
-	pnum = vol->eba_tbl[lnum];
+	pnum = vol->eba_tbl->entries[lnum].pnum;
 	if (pnum < 0)
 		/* This logical eraseblock is already unmapped */
 		goto out_unlock;
@@ -341,7 +481,7 @@ int ubi_eba_unmap_leb(struct ubi_device *ubi, struct ubi_volume *vol,
 	dbg_eba("erase LEB %d:%d, PEB %d", vol_id, lnum, pnum);
 
 	down_read(&ubi->fm_eba_sem);
-	vol->eba_tbl[lnum] = UBI_LEB_UNMAPPED;
+	vol->eba_tbl->entries[lnum].pnum = UBI_LEB_UNMAPPED;
 	up_read(&ubi->fm_eba_sem);
 	err = ubi_wl_put_peb(ubi, vol_id, lnum, pnum, 0);
 
@@ -373,6 +513,7 @@ int ubi_eba_read_leb(struct ubi_device *ubi, struct ubi_volume *vol, int lnum,
 		     void *buf, int offset, int len, int check)
 {
 	int err, pnum, scrub = 0, vol_id = vol->vol_id;
+	struct ubi_vid_io_buf *vidb;
 	struct ubi_vid_hdr *vid_hdr;
 	uint32_t uninitialized_var(crc);
 
@@ -380,7 +521,7 @@ int ubi_eba_read_leb(struct ubi_device *ubi, struct ubi_volume *vol, int lnum,
 	if (err)
 		return err;
 
-	pnum = vol->eba_tbl[lnum];
+	pnum = vol->eba_tbl->entries[lnum].pnum;
 	if (pnum < 0) {
 		/*
 		 * The logical eraseblock is not mapped, fill the whole buffer
@@ -403,13 +544,15 @@ int ubi_eba_read_leb(struct ubi_device *ubi, struct ubi_volume *vol, int lnum,
 
 retry:
 	if (check) {
-		vid_hdr = ubi_zalloc_vid_hdr(ubi, GFP_NOFS);
-		if (!vid_hdr) {
+		vidb = ubi_alloc_vid_buf(ubi, GFP_NOFS);
+		if (!vidb) {
 			err = -ENOMEM;
 			goto out_unlock;
 		}
 
-		err = ubi_io_read_vid_hdr(ubi, pnum, vid_hdr, 1);
+		vid_hdr = ubi_get_vid_hdr(vidb);
+
+		err = ubi_io_read_vid_hdr(ubi, pnum, vidb, 1);
 		if (err && err != UBI_IO_BITFLIPS) {
 			if (err > 0) {
 				/*
@@ -455,7 +598,7 @@ int ubi_eba_read_leb(struct ubi_device *ubi, struct ubi_volume *vol, int lnum,
 		ubi_assert(len == be32_to_cpu(vid_hdr->data_size));
 
 		crc = be32_to_cpu(vid_hdr->data_crc);
-		ubi_free_vid_hdr(ubi, vid_hdr);
+		ubi_free_vid_buf(vidb);
 	}
 
 	err = ubi_io_read_data(ubi, buf, pnum, offset, len);
@@ -492,7 +635,7 @@ int ubi_eba_read_leb(struct ubi_device *ubi, struct ubi_volume *vol, int lnum,
 	return err;
 
 out_free:
-	ubi_free_vid_hdr(ubi, vid_hdr);
+	ubi_free_vid_buf(vidb);
 out_unlock:
 	leb_read_unlock(ubi, vol_id, lnum);
 	return err;
@@ -554,49 +697,47 @@ int ubi_eba_read_leb_sg(struct ubi_device *ubi, struct ubi_volume *vol,
 }
 
 /**
- * recover_peb - recover from write failure.
- * @ubi: UBI device description object
+ * try_recover_peb - try to recover from write failure.
+ * @vol: volume description object
  * @pnum: the physical eraseblock to recover
- * @vol_id: volume ID
  * @lnum: logical eraseblock number
  * @buf: data which was not written because of the write failure
  * @offset: offset of the failed write
  * @len: how many bytes should have been written
+ * @vidb: VID buffer
+ * @retry: whether the caller should retry in case of failure
  *
  * This function is called in case of a write failure and moves all good data
  * from the potentially bad physical eraseblock to a good physical eraseblock.
  * This function also writes the data which was not written due to the failure.
- * Returns new physical eraseblock number in case of success, and a negative
- * error code in case of failure.
+ * Returns 0 in case of success, and a negative error code in case of failure.
+ * In case of failure, the %retry parameter is set to false if this is a fatal
+ * error (retrying won't help), and true otherwise.
  */
-static int recover_peb(struct ubi_device *ubi, int pnum, int vol_id, int lnum,
-		       const void *buf, int offset, int len)
+static int try_recover_peb(struct ubi_volume *vol, int pnum, int lnum,
+			   const void *buf, int offset, int len,
+			   struct ubi_vid_io_buf *vidb, bool *retry)
 {
-	int err, idx = vol_id2idx(ubi, vol_id), new_pnum, data_size, tries = 0;
-	struct ubi_volume *vol = ubi->volumes[idx];
+	struct ubi_device *ubi = vol->ubi;
 	struct ubi_vid_hdr *vid_hdr;
+	int new_pnum, err, vol_id = vol->vol_id, data_size;
 	uint32_t crc;
 
-	vid_hdr = ubi_zalloc_vid_hdr(ubi, GFP_NOFS);
-	if (!vid_hdr)
-		return -ENOMEM;
+	*retry = false;
 
-retry:
 	new_pnum = ubi_wl_get_peb(ubi);
 	if (new_pnum < 0) {
-		ubi_free_vid_hdr(ubi, vid_hdr);
-		up_read(&ubi->fm_eba_sem);
-		return new_pnum;
+		err = new_pnum;
+		goto out_put;
 	}
 
 	ubi_msg(ubi, "recover PEB %d, move data to PEB %d",
 		pnum, new_pnum);
 
-	err = ubi_io_read_vid_hdr(ubi, pnum, vid_hdr, 1);
+	err = ubi_io_read_vid_hdr(ubi, pnum, vidb, 1);
 	if (err && err != UBI_IO_BITFLIPS) {
 		if (err > 0)
 			err = -EIO;
-		up_read(&ubi->fm_eba_sem);
 		goto out_put;
 	}
 
@@ -608,11 +749,11 @@ static int recover_peb(struct ubi_device *ubi, int pnum, int vol_id, int lnum,
 	/* Read everything before the area where the write failure happened */
 	if (offset > 0) {
 		err = ubi_io_read_data(ubi, ubi->peb_buf, pnum, 0, offset);
-		if (err && err != UBI_IO_BITFLIPS) {
-			up_read(&ubi->fm_eba_sem);
+		if (err && err != UBI_IO_BITFLIPS)
 			goto out_unlock;
 	}
-	}
+
+	*retry = true;
 
 	memcpy(ubi->peb_buf + offset, buf, len);
 
@@ -622,50 +763,140 @@ static int recover_peb(struct ubi_device *ubi, int pnum, int vol_id, int lnum,
 	vid_hdr->copy_flag = 1;
 	vid_hdr->data_size = cpu_to_be32(data_size);
 	vid_hdr->data_crc = cpu_to_be32(crc);
-	err = ubi_io_write_vid_hdr(ubi, new_pnum, vid_hdr);
-	if (err) {
-		mutex_unlock(&ubi->buf_mutex);
-		up_read(&ubi->fm_eba_sem);
-		goto write_error;
-	}
+	err = ubi_io_write_vid_hdr(ubi, new_pnum, vidb);
+	if (err)
+		goto out_unlock;
 
 	err = ubi_io_write_data(ubi, ubi->peb_buf, new_pnum, 0, data_size);
-	if (err) {
-		mutex_unlock(&ubi->buf_mutex);
-		up_read(&ubi->fm_eba_sem);
-		goto write_error;
-	}
 
+out_unlock:
 	mutex_unlock(&ubi->buf_mutex);
-	ubi_free_vid_hdr(ubi, vid_hdr);
 
-	vol->eba_tbl[lnum] = new_pnum;
+	if (!err)
+		vol->eba_tbl->entries[lnum].pnum = new_pnum;
+
+out_put:
 	up_read(&ubi->fm_eba_sem);
-	ubi_wl_put_peb(ubi, vol_id, lnum, pnum, 1);
 
+	if (!err) {
+		ubi_wl_put_peb(ubi, vol_id, lnum, pnum, 1);
 		ubi_msg(ubi, "data was successfully recovered");
-	return 0;
-
-out_unlock:
-	mutex_unlock(&ubi->buf_mutex);
-out_put:
+	} else if (new_pnum >= 0) {
+		/*
+		 * Bad luck? This physical eraseblock is bad too? Crud. Let's
+		 * try to get another one.
+		 */
 		ubi_wl_put_peb(ubi, vol_id, lnum, new_pnum, 1);
-	ubi_free_vid_hdr(ubi, vid_hdr);
+		ubi_warn(ubi, "failed to write to PEB %d", new_pnum);
+	}
+
 	return err;
+}
 
-write_error:
-	/*
-	 * Bad luck? This physical eraseblock is bad too? Crud. Let's try to
-	 * get another one.
+/**
+ * recover_peb - recover from write failure.
+ * @ubi: UBI device description object
+ * @pnum: the physical eraseblock to recover
+ * @vol_id: volume ID
+ * @lnum: logical eraseblock number
+ * @buf: data which was not written because of the write failure
+ * @offset: offset of the failed write
+ * @len: how many bytes should have been written
+ *
+ * This function is called in case of a write failure and moves all good data
+ * from the potentially bad physical eraseblock to a good physical eraseblock.
+ * This function also writes the data which was not written due to the failure.
+ * Returns 0 in case of success, and a negative error code in case of failure.
+ * This function tries %UBI_IO_RETRIES before giving up.
  */
-	ubi_warn(ubi, "failed to write to PEB %d", new_pnum);
-	ubi_wl_put_peb(ubi, vol_id, lnum, new_pnum, 1);
-	if (++tries > UBI_IO_RETRIES) {
-		ubi_free_vid_hdr(ubi, vid_hdr);
+static int recover_peb(struct ubi_device *ubi, int pnum, int vol_id, int lnum,
+		       const void *buf, int offset, int len)
+{
+	int err, idx = vol_id2idx(ubi, vol_id), tries;
+	struct ubi_volume *vol = ubi->volumes[idx];
+	struct ubi_vid_io_buf *vidb;
+
+	vidb = ubi_alloc_vid_buf(ubi, GFP_NOFS);
+	if (!vidb)
+		return -ENOMEM;
+
+	for (tries = 0; tries <= UBI_IO_RETRIES; tries++) {
+		bool retry;
+
+		err = try_recover_peb(vol, pnum, lnum, buf, offset, len, vidb,
+				      &retry);
+		if (!err || !retry)
+			break;
+
+		ubi_msg(ubi, "try again");
+	}
+
+	ubi_free_vid_buf(vidb);
+
 	return err;
+}
+
+/**
+ * try_write_vid_and_data - try to write VID header and data to a new PEB.
+ * @vol: volume description object
+ * @lnum: logical eraseblock number
+ * @vidb: the VID buffer to write
+ * @buf: buffer containing the data
+ * @offset: where to start writing data
+ * @len: how many bytes should be written
+ *
+ * This function tries to write VID header and data belonging to logical
+ * eraseblock @lnum of volume @vol to a new physical eraseblock. Returns zero
+ * in case of success and a negative error code in case of failure.
+ * In case of error, it is possible that something was still written to the
+ * flash media, but may be some garbage.
+ */
+static int try_write_vid_and_data(struct ubi_volume *vol, int lnum,
+				  struct ubi_vid_io_buf *vidb, const void *buf,
+				  int offset, int len)
+{
+	struct ubi_device *ubi = vol->ubi;
+	int pnum, opnum, err, vol_id = vol->vol_id;
+
+	pnum = ubi_wl_get_peb(ubi);
+	if (pnum < 0) {
+		err = pnum;
+		goto out_put;
 	}
-	ubi_msg(ubi, "try again");
-	goto retry;
+
+	opnum = vol->eba_tbl->entries[lnum].pnum;
+
+	dbg_eba("write VID hdr and %d bytes at offset %d of LEB %d:%d, PEB %d",
+		len, offset, vol_id, lnum, pnum);
+
+	err = ubi_io_write_vid_hdr(ubi, pnum, vidb);
+	if (err) {
+		ubi_warn(ubi, "failed to write VID header to LEB %d:%d, PEB %d",
+			 vol_id, lnum, pnum);
+		goto out_put;
+	}
+
+	if (len) {
+		err = ubi_io_write_data(ubi, buf, pnum, offset, len);
+		if (err) {
+			ubi_warn(ubi,
+				 "failed to write %d bytes at offset %d of LEB %d:%d, PEB %d",
+				 len, offset, vol_id, lnum, pnum);
+			goto out_put;
+		}
+	}
+
+	vol->eba_tbl->entries[lnum].pnum = pnum;
+
+out_put:
+	up_read(&ubi->fm_eba_sem);
+
+	if (err && pnum >= 0)
+		err = ubi_wl_put_peb(ubi, vol_id, lnum, pnum, 1);
+	else if (!err && opnum >= 0)
+		err = ubi_wl_put_peb(ubi, vol_id, lnum, opnum, 0);
+
+	return err;
 }
 
 /**
@@ -681,11 +912,13 @@ static int recover_peb(struct ubi_device *ubi, int pnum, int vol_id, int lnum,
  * @vol. Returns zero in case of success and a negative error code in case
  * of failure. In case of error, it is possible that something was still
  * written to the flash media, but may be some garbage.
+ * This function retries %UBI_IO_RETRIES times before giving up.
  */
 int ubi_eba_write_leb(struct ubi_device *ubi, struct ubi_volume *vol, int lnum,
 		      const void *buf, int offset, int len)
 {
-	int err, pnum, tries = 0, vol_id = vol->vol_id;
+	int err, pnum, tries, vol_id = vol->vol_id;
+	struct ubi_vid_io_buf *vidb;
 	struct ubi_vid_hdr *vid_hdr;
 
 	if (ubi->ro_mode)
@@ -695,7 +928,7 @@ int ubi_eba_write_leb(struct ubi_device *ubi, struct ubi_volume *vol, int lnum,
 	if (err)
 		return err;
 
-	pnum = vol->eba_tbl[lnum];
+	pnum = vol->eba_tbl->entries[lnum].pnum;
 	if (pnum >= 0) {
 		dbg_eba("write %d bytes at offset %d of LEB %d:%d, PEB %d",
 			len, offset, vol_id, lnum, pnum);
@@ -706,23 +939,23 @@ int ubi_eba_write_leb(struct ubi_device *ubi, struct ubi_volume *vol, int lnum,
 			if (err == -EIO && ubi->bad_allowed)
 				err = recover_peb(ubi, pnum, vol_id, lnum, buf,
 						  offset, len);
-			if (err)
-				ubi_ro_mode(ubi);
 		}
-		leb_write_unlock(ubi, vol_id, lnum);
-		return err;
+
+		goto out;
 	}
 
 	/*
 	 * The logical eraseblock is not mapped. We have to get a free physical
 	 * eraseblock and write the volume identifier header there first.
 	 */
-	vid_hdr = ubi_zalloc_vid_hdr(ubi, GFP_NOFS);
-	if (!vid_hdr) {
+	vidb = ubi_alloc_vid_buf(ubi, GFP_NOFS);
+	if (!vidb) {
 		leb_write_unlock(ubi, vol_id, lnum);
 		return -ENOMEM;
 	}
 
+	vid_hdr = ubi_get_vid_hdr(vidb);
+
 	vid_hdr->vol_type = UBI_VID_DYNAMIC;
 	vid_hdr->sqnum = cpu_to_be64(ubi_next_sqnum(ubi));
 	vid_hdr->vol_id = cpu_to_be32(vol_id);
@@ -730,67 +963,30 @@ int ubi_eba_write_leb(struct ubi_device *ubi, struct ubi_volume *vol, int lnum,
 	vid_hdr->compat = ubi_get_compat(ubi, vol_id);
 	vid_hdr->data_pad = cpu_to_be32(vol->data_pad);
 
-retry:
-	pnum = ubi_wl_get_peb(ubi);
-	if (pnum < 0) {
-		ubi_free_vid_hdr(ubi, vid_hdr);
-		leb_write_unlock(ubi, vol_id, lnum);
-		up_read(&ubi->fm_eba_sem);
-		return pnum;
-	}
-
-	dbg_eba("write VID hdr and %d bytes at offset %d of LEB %d:%d, PEB %d",
-		len, offset, vol_id, lnum, pnum);
-
-	err = ubi_io_write_vid_hdr(ubi, pnum, vid_hdr);
-	if (err) {
-		ubi_warn(ubi, "failed to write VID header to LEB %d:%d, PEB %d",
-			 vol_id, lnum, pnum);
-		up_read(&ubi->fm_eba_sem);
-		goto write_error;
-	}
+	for (tries = 0; tries <= UBI_IO_RETRIES; tries++) {
+		err = try_write_vid_and_data(vol, lnum, vidb, buf, offset, len);
+		if (err != -EIO || !ubi->bad_allowed)
+			break;
 
-	if (len) {
-		err = ubi_io_write_data(ubi, buf, pnum, offset, len);
-		if (err) {
-			ubi_warn(ubi, "failed to write %d bytes at offset %d of LEB %d:%d, PEB %d",
-				 len, offset, vol_id, lnum, pnum);
-			up_read(&ubi->fm_eba_sem);
-			goto write_error;
-		}
+		/*
+		 * Fortunately, this is the first write operation to this
+		 * physical eraseblock, so just put it and request a new one.
+		 * We assume that if this physical eraseblock went bad, the
+		 * erase code will handle that.
+		 */
+		vid_hdr->sqnum = cpu_to_be64(ubi_next_sqnum(ubi));
+		ubi_msg(ubi, "try another PEB");
 	}
 
-	vol->eba_tbl[lnum] = pnum;
-	up_read(&ubi->fm_eba_sem);
-
-	leb_write_unlock(ubi, vol_id, lnum);
-	ubi_free_vid_hdr(ubi, vid_hdr);
-	return 0;
+	ubi_free_vid_buf(vidb);
 
-write_error:
-	if (err != -EIO || !ubi->bad_allowed) {
+out:
+	if (err)
 		ubi_ro_mode(ubi);
-		leb_write_unlock(ubi, vol_id, lnum);
-		ubi_free_vid_hdr(ubi, vid_hdr);
-		return err;
-	}
 
-	/*
-	 * Fortunately, this is the first write operation to this physical
-	 * eraseblock, so just put it and request a new one. We assume that if
-	 * this physical eraseblock went bad, the erase code will handle that.
-	 */
-	err = ubi_wl_put_peb(ubi, vol_id, lnum, pnum, 1);
-	if (err || ++tries > UBI_IO_RETRIES) {
-		ubi_ro_mode(ubi);
 	leb_write_unlock(ubi, vol_id, lnum);
-		ubi_free_vid_hdr(ubi, vid_hdr);
-		return err;
-	}
 
-	vid_hdr->sqnum = cpu_to_be64(ubi_next_sqnum(ubi));
-	ubi_msg(ubi, "try another PEB");
-	goto retry;
+	return err;
 }
 
 /**
@@ -818,7 +1014,8 @@ int ubi_eba_write_leb(struct ubi_device *ubi, struct ubi_volume *vol, int lnum,
 int ubi_eba_write_leb_st(struct ubi_device *ubi, struct ubi_volume *vol,
 			 int lnum, const void *buf, int len, int used_ebs)
 {
-	int err, pnum, tries = 0, data_size = len, vol_id = vol->vol_id;
+	int err, tries, data_size = len, vol_id = vol->vol_id;
+	struct ubi_vid_io_buf *vidb;
 	struct ubi_vid_hdr *vid_hdr;
 	uint32_t crc;
 
@@ -831,15 +1028,15 @@ int ubi_eba_write_leb_st(struct ubi_device *ubi, struct ubi_volume *vol,
 	else
 		ubi_assert(!(len & (ubi->min_io_size - 1)));
 
-	vid_hdr = ubi_zalloc_vid_hdr(ubi, GFP_NOFS);
-	if (!vid_hdr)
+	vidb = ubi_alloc_vid_buf(ubi, GFP_NOFS);
+	if (!vidb)
 		return -ENOMEM;
 
+	vid_hdr = ubi_get_vid_hdr(vidb);
+
 	err = leb_write_lock(ubi, vol_id, lnum);
-	if (err) {
-		ubi_free_vid_hdr(ubi, vid_hdr);
-		return err;
-	}
+	if (err)
+		goto out;
 
 	vid_hdr->sqnum = cpu_to_be64(ubi_next_sqnum(ubi));
 	vid_hdr->vol_id = cpu_to_be32(vol_id);
@@ -853,66 +1050,26 @@ int ubi_eba_write_leb_st(struct ubi_device *ubi, struct ubi_volume *vol,
 	vid_hdr->used_ebs = cpu_to_be32(used_ebs);
 	vid_hdr->data_crc = cpu_to_be32(crc);
 
-retry:
-	pnum = ubi_wl_get_peb(ubi);
-	if (pnum < 0) {
-		ubi_free_vid_hdr(ubi, vid_hdr);
-		leb_write_unlock(ubi, vol_id, lnum);
-		up_read(&ubi->fm_eba_sem);
-		return pnum;
-	}
-
-	dbg_eba("write VID hdr and %d bytes at LEB %d:%d, PEB %d, used_ebs %d",
-		len, vol_id, lnum, pnum, used_ebs);
+	ubi_assert(vol->eba_tbl->entries[lnum].pnum < 0);
 
-	err = ubi_io_write_vid_hdr(ubi, pnum, vid_hdr);
-	if (err) {
-		ubi_warn(ubi, "failed to write VID header to LEB %d:%d, PEB %d",
-			 vol_id, lnum, pnum);
-		up_read(&ubi->fm_eba_sem);
-		goto write_error;
-	}
+	for (tries = 0; tries <= UBI_IO_RETRIES; tries++) {
+		err = try_write_vid_and_data(vol, lnum, vidb, buf, 0, len);
+		if (err != -EIO || !ubi->bad_allowed)
+			break;
 
-	err = ubi_io_write_data(ubi, buf, pnum, 0, len);
-	if (err) {
-		ubi_warn(ubi, "failed to write %d bytes of data to PEB %d",
-			 len, pnum);
-		up_read(&ubi->fm_eba_sem);
-		goto write_error;
+		vid_hdr->sqnum = cpu_to_be64(ubi_next_sqnum(ubi));
+		ubi_msg(ubi, "try another PEB");
 	}
 
-	ubi_assert(vol->eba_tbl[lnum] < 0);
-	vol->eba_tbl[lnum] = pnum;
-	up_read(&ubi->fm_eba_sem);
+	if (err)
+		ubi_ro_mode(ubi);
 
 	leb_write_unlock(ubi, vol_id, lnum);
-	ubi_free_vid_hdr(ubi, vid_hdr);
-	return 0;
 
-write_error:
-	if (err != -EIO || !ubi->bad_allowed) {
-		/*
-		 * This flash device does not admit of bad eraseblocks or
-		 * something nasty and unexpected happened. Switch to read-only
-		 * mode just in case.
-		 */
-		ubi_ro_mode(ubi);
-		leb_write_unlock(ubi, vol_id, lnum);
-		ubi_free_vid_hdr(ubi, vid_hdr);
-		return err;
-	}
+out:
+	ubi_free_vid_buf(vidb);
 
-	err = ubi_wl_put_peb(ubi, vol_id, lnum, pnum, 1);
-	if (err || ++tries > UBI_IO_RETRIES) {
-		ubi_ro_mode(ubi);
-		leb_write_unlock(ubi, vol_id, lnum);
-		ubi_free_vid_hdr(ubi, vid_hdr);
 	return err;
-	}
-
-	vid_hdr->sqnum = cpu_to_be64(ubi_next_sqnum(ubi));
-	ubi_msg(ubi, "try another PEB");
-	goto retry;
 }
 
 /*
@@ -935,7 +1092,8 @@ int ubi_eba_write_leb_st(struct ubi_device *ubi, struct ubi_volume *vol,
 int ubi_eba_atomic_leb_change(struct ubi_device *ubi, struct ubi_volume *vol,
 			      int lnum, const void *buf, int len)
 {
-	int err, pnum, old_pnum, tries = 0, vol_id = vol->vol_id;
+	int err, tries, vol_id = vol->vol_id;
+	struct ubi_vid_io_buf *vidb;
 	struct ubi_vid_hdr *vid_hdr;
 	uint32_t crc;
 
@@ -953,10 +1111,12 @@ int ubi_eba_atomic_leb_change(struct ubi_device *ubi, struct ubi_volume *vol,
 		return ubi_eba_write_leb(ubi, vol, lnum, NULL, 0, 0);
 	}
 
-	vid_hdr = ubi_zalloc_vid_hdr(ubi, GFP_NOFS);
-	if (!vid_hdr)
+	vidb = ubi_alloc_vid_buf(ubi, GFP_NOFS);
+	if (!vidb)
 		return -ENOMEM;
 
+	vid_hdr = ubi_get_vid_hdr(vidb);
+
 	mutex_lock(&ubi->alc_mutex);
 	err = leb_write_lock(ubi, vol_id, lnum);
 	if (err)
@@ -974,70 +1134,31 @@ int ubi_eba_atomic_leb_change(struct ubi_device *ubi, struct ubi_volume *vol,
 	vid_hdr->copy_flag = 1;
 	vid_hdr->data_crc = cpu_to_be32(crc);
 
-retry:
-	pnum = ubi_wl_get_peb(ubi);
-	if (pnum < 0) {
-		err = pnum;
-		up_read(&ubi->fm_eba_sem);
-		goto out_leb_unlock;
-	}
-
-	dbg_eba("change LEB %d:%d, PEB %d, write VID hdr to PEB %d",
-		vol_id, lnum, vol->eba_tbl[lnum], pnum);
+	dbg_eba("change LEB %d:%d", vol_id, lnum);
 
-	err = ubi_io_write_vid_hdr(ubi, pnum, vid_hdr);
-	if (err) {
-		ubi_warn(ubi, "failed to write VID header to LEB %d:%d, PEB %d",
-			 vol_id, lnum, pnum);
-		up_read(&ubi->fm_eba_sem);
-		goto write_error;
-	}
-
-	err = ubi_io_write_data(ubi, buf, pnum, 0, len);
-	if (err) {
-		ubi_warn(ubi, "failed to write %d bytes of data to PEB %d",
-			 len, pnum);
-		up_read(&ubi->fm_eba_sem);
-		goto write_error;
-	}
-
-	old_pnum = vol->eba_tbl[lnum];
-	vol->eba_tbl[lnum] = pnum;
-	up_read(&ubi->fm_eba_sem);
+	for (tries = 0; tries <= UBI_IO_RETRIES; tries++) {
+		err = try_write_vid_and_data(vol, lnum, vidb, buf, 0, len);
+		if (err != -EIO || !ubi->bad_allowed)
+			break;
 
-	if (old_pnum >= 0) {
-		err = ubi_wl_put_peb(ubi, vol_id, lnum, old_pnum, 0);
-		if (err)
-			goto out_leb_unlock;
+		vid_hdr->sqnum = cpu_to_be64(ubi_next_sqnum(ubi));
+		ubi_msg(ubi, "try another PEB");
 	}
 
-out_leb_unlock:
-	leb_write_unlock(ubi, vol_id, lnum);
-out_mutex:
-	mutex_unlock(&ubi->alc_mutex);
-	ubi_free_vid_hdr(ubi, vid_hdr);
-	return err;
-
-write_error:
-	if (err != -EIO || !ubi->bad_allowed) {
 	/*
 	 * This flash device does not admit of bad eraseblocks or
 	 * something nasty and unexpected happened. Switch to read-only
 	 * mode just in case.
 	 */
+	if (err)
 		ubi_ro_mode(ubi);
-		goto out_leb_unlock;
-	}
 
-	err = ubi_wl_put_peb(ubi, vol_id, lnum, pnum, 1);
-	if (err || ++tries > UBI_IO_RETRIES) {
-		ubi_ro_mode(ubi);
-		goto out_leb_unlock;
-	}
+	leb_write_unlock(ubi, vol_id, lnum);
 
-	vid_hdr->sqnum = cpu_to_be64(ubi_next_sqnum(ubi));
-	ubi_msg(ubi, "try another PEB");
-	goto retry;
+out_mutex:
+	mutex_unlock(&ubi->alc_mutex);
+	ubi_free_vid_buf(vidb);
+	return err;
 }
 
 /**
@@ -1082,12 +1203,15 @@ static int is_error_sane(int err)
  *   o a negative error code in case of failure.
  */
 int ubi_eba_copy_leb(struct ubi_device *ubi, int from, int to,
-		     struct ubi_vid_hdr *vid_hdr)
+		     struct ubi_vid_io_buf *vidb)
 {
 	int err, vol_id, lnum, data_size, aldata_size, idx;
+	struct ubi_vid_hdr *vid_hdr = ubi_get_vid_hdr(vidb);
 	struct ubi_volume *vol;
 	uint32_t crc;
 
+	ubi_assert(rwsem_is_locked(&ubi->fm_eba_sem));
+
 	vol_id = be32_to_cpu(vid_hdr->vol_id);
 	lnum = be32_to_cpu(vid_hdr->lnum);
 
@@ -1142,9 +1266,9 @@ int ubi_eba_copy_leb(struct ubi_device *ubi, int from, int to,
 	 * probably waiting on @ubi->move_mutex. No need to continue the work,
 	 * cancel it.
 	 */
-	if (vol->eba_tbl[lnum] != from) {
+	if (vol->eba_tbl->entries[lnum].pnum != from) {
 		dbg_wl("LEB %d:%d is no longer mapped to PEB %d, mapped to PEB %d, cancel",
-		       vol_id, lnum, from, vol->eba_tbl[lnum]);
+		       vol_id, lnum, from, vol->eba_tbl->entries[lnum].pnum);
 		err = MOVE_CANCEL_RACE;
 		goto out_unlock_leb;
 	}
@@ -1196,7 +1320,7 @@ int ubi_eba_copy_leb(struct ubi_device *ubi, int from, int to,
 	}
 	vid_hdr->sqnum = cpu_to_be64(ubi_next_sqnum(ubi));
 
-	err = ubi_io_write_vid_hdr(ubi, to, vid_hdr);
+	err = ubi_io_write_vid_hdr(ubi, to, vidb);
 	if (err) {
 		if (err == -EIO)
 			err = MOVE_TARGET_WR_ERR;
@@ -1206,7 +1330,7 @@ int ubi_eba_copy_leb(struct ubi_device *ubi, int from, int to,
 	cond_resched();
 
 	/* Read the VID header back and check if it was written correctly */
-	err = ubi_io_read_vid_hdr(ubi, to, vid_hdr, 1);
+	err = ubi_io_read_vid_hdr(ubi, to, vidb, 1);
 	if (err) {
 		if (err != UBI_IO_BITFLIPS) {
 			ubi_warn(ubi, "error %d while reading VID header back from PEB %d",
@@ -1229,10 +1353,8 @@ int ubi_eba_copy_leb(struct ubi_device *ubi, int from, int to,
 		cond_resched();
 	}
 
-	ubi_assert(vol->eba_tbl[lnum] == from);
-	down_read(&ubi->fm_eba_sem);
-	vol->eba_tbl[lnum] = to;
-	up_read(&ubi->fm_eba_sem);
+	ubi_assert(vol->eba_tbl->entries[lnum].pnum == from);
+	vol->eba_tbl->entries[lnum].pnum = to;
 
 out_unlock_buf:
 	mutex_unlock(&ubi->buf_mutex);
@@ -1388,7 +1510,7 @@ int self_check_eba(struct ubi_device *ubi, struct ubi_attach_info *ai_fastmap,
  */
 int ubi_eba_init(struct ubi_device *ubi, struct ubi_attach_info *ai)
 {
-	int i, j, err, num_volumes;
+	int i, err, num_volumes;
 	struct ubi_ainf_volume *av;
 	struct ubi_volume *vol;
 	struct ubi_ainf_peb *aeb;
@@ -1404,35 +1526,39 @@ int ubi_eba_init(struct ubi_device *ubi, struct ubi_attach_info *ai)
 	num_volumes = ubi->vtbl_slots + UBI_INT_VOL_COUNT;
 
 	for (i = 0; i < num_volumes; i++) {
+		struct ubi_eba_table *tbl;
+
 		vol = ubi->volumes[i];
 		if (!vol)
 			continue;
 
 		cond_resched();
 
-		vol->eba_tbl = kmalloc(vol->reserved_pebs * sizeof(int),
-				       GFP_KERNEL);
-		if (!vol->eba_tbl) {
-			err = -ENOMEM;
+		tbl = ubi_eba_create_table(vol, vol->reserved_pebs);
+		if (IS_ERR(tbl)) {
+			err = PTR_ERR(tbl);
 			goto out_free;
 		}
 
-		for (j = 0; j < vol->reserved_pebs; j++)
-			vol->eba_tbl[j] = UBI_LEB_UNMAPPED;
+		ubi_eba_replace_table(vol, tbl);
 
 		av = ubi_find_av(ai, idx2vol_id(ubi, i));
 		if (!av)
 			continue;
 
 		ubi_rb_for_each_entry(rb, aeb, &av->root, u.rb) {
-			if (aeb->lnum >= vol->reserved_pebs)
+			if (aeb->lnum >= vol->reserved_pebs) {
 				/*
 				 * This may happen in case of an unclean reboot
 				 * during re-size.
 				 */
 				ubi_move_aeb_to_list(av, aeb, &ai->erase);
-			else
-				vol->eba_tbl[aeb->lnum] = aeb->pnum;
+			} else {
+				struct ubi_eba_entry *entry;
+
+				entry = &vol->eba_tbl->entries[aeb->lnum];
+				entry->pnum = aeb->pnum;
+			}
 		}
 	}
 
@@ -1469,8 +1595,7 @@ int ubi_eba_init(struct ubi_device *ubi, struct ubi_attach_info *ai)
 	for (i = 0; i < num_volumes; i++) {
 		if (!ubi->volumes[i])
 			continue;
-		kfree(ubi->volumes[i]->eba_tbl);
-		ubi->volumes[i]->eba_tbl = NULL;
+		ubi_eba_replace_table(ubi->volumes[i], NULL);
 	}
 	return err;
 }

drivers/mtd/ubi/fastmap-wl.c

@@ -262,6 +262,8 @@ static struct ubi_wl_entry *get_peb_for_wl(struct ubi_device *ubi)
 	struct ubi_fm_pool *pool = &ubi->fm_wl_pool;
 	int pnum;
 
+	ubi_assert(rwsem_is_locked(&ubi->fm_eba_sem));
+
 	if (pool->used == pool->size) {
 		/* We cannot update the fastmap here because this
 		 * function is called in atomic context.
@@ -303,7 +305,7 @@ int ubi_ensure_anchor_pebs(struct ubi_device *ubi)
 
 	wrk->anchor = 1;
 	wrk->func = &wear_leveling_worker;
-	schedule_ubi_work(ubi, wrk);
+	__schedule_ubi_work(ubi, wrk);
 	return 0;
 }
 
@@ -344,7 +346,7 @@ int ubi_wl_put_fm_peb(struct ubi_device *ubi, struct ubi_wl_entry *fm_e,
 	spin_unlock(&ubi->wl_lock);
 
 	vol_id = lnum ? UBI_FM_DATA_VOLUME_ID : UBI_FM_SB_VOLUME_ID;
-	return schedule_erase(ubi, e, vol_id, lnum, torture);
+	return schedule_erase(ubi, e, vol_id, lnum, torture, true);
 }
 
 /**

drivers/mtd/ubi/fastmap.c

@@ -110,21 +110,23 @@ size_t ubi_calc_fm_size(struct ubi_device *ubi)
  * Returns a new struct ubi_vid_hdr on success.
  * NULL indicates out of memory.
  */
-static struct ubi_vid_hdr *new_fm_vhdr(struct ubi_device *ubi, int vol_id)
+static struct ubi_vid_io_buf *new_fm_vbuf(struct ubi_device *ubi, int vol_id)
 {
-	struct ubi_vid_hdr *new;
+	struct ubi_vid_io_buf *new;
+	struct ubi_vid_hdr *vh;
 
-	new = ubi_zalloc_vid_hdr(ubi, GFP_KERNEL);
+	new = ubi_alloc_vid_buf(ubi, GFP_KERNEL);
 	if (!new)
 		goto out;
 
-	new->vol_type = UBI_VID_DYNAMIC;
-	new->vol_id = cpu_to_be32(vol_id);
+	vh = ubi_get_vid_hdr(new);
+	vh->vol_type = UBI_VID_DYNAMIC;
+	vh->vol_id = cpu_to_be32(vol_id);
 
 	/* UBI implementations without fastmap support have to delete the
 	 * fastmap.
 	 */
-	new->compat = UBI_COMPAT_DELETE;
+	vh->compat = UBI_COMPAT_DELETE;
 
 out:
 	return new;
@@ -145,12 +147,10 @@ static int add_aeb(struct ubi_attach_info *ai, struct list_head *list,
 {
 	struct ubi_ainf_peb *aeb;
 
-	aeb = kmem_cache_alloc(ai->aeb_slab_cache, GFP_KERNEL);
+	aeb = ubi_alloc_aeb(ai, pnum, ec);
 	if (!aeb)
 		return -ENOMEM;
 
-	aeb->pnum = pnum;
-	aeb->ec = ec;
 	aeb->lnum = -1;
 	aeb->scrub = scrub;
 	aeb->copy_flag = aeb->sqnum = 0;
@@ -186,40 +186,19 @@ static struct ubi_ainf_volume *add_vol(struct ubi_attach_info *ai, int vol_id,
 				       int last_eb_bytes)
 {
 	struct ubi_ainf_volume *av;
-	struct rb_node **p = &ai->volumes.rb_node, *parent = NULL;
-
-	while (*p) {
-		parent = *p;
-		av = rb_entry(parent, struct ubi_ainf_volume, rb);
-
-		if (vol_id > av->vol_id)
-			p = &(*p)->rb_left;
-		else if (vol_id < av->vol_id)
-			p = &(*p)->rb_right;
-		else
-			return ERR_PTR(-EINVAL);
-	}
 
-	av = kmalloc(sizeof(struct ubi_ainf_volume), GFP_KERNEL);
-	if (!av)
-		goto out;
+	av = ubi_add_av(ai, vol_id);
+	if (IS_ERR(av))
+		return av;
 
-	av->highest_lnum = av->leb_count = av->used_ebs = 0;
-	av->vol_id = vol_id;
 	av->data_pad = data_pad;
 	av->last_data_size = last_eb_bytes;
 	av->compat = 0;
 	av->vol_type = vol_type;
-	av->root = RB_ROOT;
 	if (av->vol_type == UBI_STATIC_VOLUME)
 		av->used_ebs = used_ebs;
 
 	dbg_bld("found volume (ID %i)", vol_id);
-
-	rb_link_node(&av->rb, parent, p);
-	rb_insert_color(&av->rb, &ai->volumes);
-
-out:
 	return av;
 }
 
@@ -297,7 +276,7 @@ static int update_vol(struct ubi_device *ubi, struct ubi_attach_info *ai,
 		 */
 		if (aeb->pnum == new_aeb->pnum) {
 			ubi_assert(aeb->lnum == new_aeb->lnum);
-			kmem_cache_free(ai->aeb_slab_cache, new_aeb);
+			ubi_free_aeb(ai, new_aeb);
 
 			return 0;
 		}
@@ -308,13 +287,10 @@ static int update_vol(struct ubi_device *ubi, struct ubi_attach_info *ai,
 
 		/* new_aeb is newer */
 		if (cmp_res & 1) {
-			victim = kmem_cache_alloc(ai->aeb_slab_cache,
-				GFP_KERNEL);
+			victim = ubi_alloc_aeb(ai, aeb->ec, aeb->pnum);
 			if (!victim)
 				return -ENOMEM;
 
-			victim->ec = aeb->ec;
-			victim->pnum = aeb->pnum;
 			list_add_tail(&victim->u.list, &ai->erase);
 
 			if (av->highest_lnum == be32_to_cpu(new_vh->lnum))
@@ -328,7 +304,8 @@ static int update_vol(struct ubi_device *ubi, struct ubi_attach_info *ai,
 			aeb->pnum = new_aeb->pnum;
 			aeb->copy_flag = new_vh->copy_flag;
 			aeb->scrub = new_aeb->scrub;
-			kmem_cache_free(ai->aeb_slab_cache, new_aeb);
+			aeb->sqnum = new_aeb->sqnum;
+			ubi_free_aeb(ai, new_aeb);
 
 		/* new_aeb is older */
 		} else {
@@ -370,41 +347,24 @@ static int process_pool_aeb(struct ubi_device *ubi, struct ubi_attach_info *ai,
 			    struct ubi_vid_hdr *new_vh,
 			    struct ubi_ainf_peb *new_aeb)
 {
-	struct ubi_ainf_volume *av, *tmp_av = NULL;
-	struct rb_node **p = &ai->volumes.rb_node, *parent = NULL;
-	int found = 0;
+	int vol_id = be32_to_cpu(new_vh->vol_id);
+	struct ubi_ainf_volume *av;
 
-	if (be32_to_cpu(new_vh->vol_id) == UBI_FM_SB_VOLUME_ID ||
-		be32_to_cpu(new_vh->vol_id) == UBI_FM_DATA_VOLUME_ID) {
-		kmem_cache_free(ai->aeb_slab_cache, new_aeb);
+	if (vol_id == UBI_FM_SB_VOLUME_ID || vol_id == UBI_FM_DATA_VOLUME_ID) {
+		ubi_free_aeb(ai, new_aeb);
 
 		return 0;
 	}
 
 	/* Find the volume this SEB belongs to */
-	while (*p) {
-		parent = *p;
-		tmp_av = rb_entry(parent, struct ubi_ainf_volume, rb);
-
-		if (be32_to_cpu(new_vh->vol_id) > tmp_av->vol_id)
-			p = &(*p)->rb_left;
-		else if (be32_to_cpu(new_vh->vol_id) < tmp_av->vol_id)
-			p = &(*p)->rb_right;
-		else {
-			found = 1;
-			break;
-		}
-	}
-
-	if (found)
-		av = tmp_av;
-	else {
+	av = ubi_find_av(ai, vol_id);
+	if (!av) {
 		ubi_err(ubi, "orphaned volume in fastmap pool!");
-		kmem_cache_free(ai->aeb_slab_cache, new_aeb);
+		ubi_free_aeb(ai, new_aeb);
 		return UBI_BAD_FASTMAP;
 	}
 
-	ubi_assert(be32_to_cpu(new_vh->vol_id) == av->vol_id);
+	ubi_assert(vol_id == av->vol_id);
 
 	return update_vol(ubi, ai, av, new_vh, new_aeb);
 }
@@ -423,16 +383,12 @@ static void unmap_peb(struct ubi_attach_info *ai, int pnum)
 	struct rb_node *node, *node2;
 	struct ubi_ainf_peb *aeb;
 
-	for (node = rb_first(&ai->volumes); node; node = rb_next(node)) {
-		av = rb_entry(node, struct ubi_ainf_volume, rb);
-
-		for (node2 = rb_first(&av->root); node2;
-		     node2 = rb_next(node2)) {
-			aeb = rb_entry(node2, struct ubi_ainf_peb, u.rb);
+	ubi_rb_for_each_entry(node, av, &ai->volumes, rb) {
+		ubi_rb_for_each_entry(node2, aeb, &av->root, u.rb) {
 			if (aeb->pnum == pnum) {
 				rb_erase(&aeb->u.rb, &av->root);
 				av->leb_count--;
-				kmem_cache_free(ai->aeb_slab_cache, aeb);
+				ubi_free_aeb(ai, aeb);
 				return;
 			}
 		}
@@ -455,6 +411,7 @@ static int scan_pool(struct ubi_device *ubi, struct ubi_attach_info *ai,
 		     __be32 *pebs, int pool_size, unsigned long long *max_sqnum,
 		     struct list_head *free)
 {
+	struct ubi_vid_io_buf *vb;
 	struct ubi_vid_hdr *vh;
 	struct ubi_ec_hdr *ech;
 	struct ubi_ainf_peb *new_aeb;
@@ -464,12 +421,14 @@ static int scan_pool(struct ubi_device *ubi, struct ubi_attach_info *ai,
 	if (!ech)
 		return -ENOMEM;
 
-	vh = ubi_zalloc_vid_hdr(ubi, GFP_KERNEL);
-	if (!vh) {
+	vb = ubi_alloc_vid_buf(ubi, GFP_KERNEL);
+	if (!vb) {
 		kfree(ech);
 		return -ENOMEM;
 	}
 
+	vh = ubi_get_vid_hdr(vb);
+
 	dbg_bld("scanning fastmap pool: size = %i", pool_size);
 
 	/*
@@ -510,15 +469,16 @@ static int scan_pool(struct ubi_device *ubi, struct ubi_attach_info *ai,
 			goto out;
 		}
 
-		err = ubi_io_read_vid_hdr(ubi, pnum, vh, 0);
+		err = ubi_io_read_vid_hdr(ubi, pnum, vb, 0);
 		if (err == UBI_IO_FF || err == UBI_IO_FF_BITFLIPS) {
 			unsigned long long ec = be64_to_cpu(ech->ec);
 			unmap_peb(ai, pnum);
 			dbg_bld("Adding PEB to free: %i", pnum);
+
 			if (err == UBI_IO_FF_BITFLIPS)
-				add_aeb(ai, free, pnum, ec, 1);
-			else
-				add_aeb(ai, free, pnum, ec, 0);
+				scrub = 1;
+
+			add_aeb(ai, free, pnum, ec, scrub);
 			continue;
 		} else if (err == 0 || err == UBI_IO_BITFLIPS) {
 			dbg_bld("Found non empty PEB:%i in pool", pnum);
@@ -526,15 +486,12 @@ static int scan_pool(struct ubi_device *ubi, struct ubi_attach_info *ai,
 			if (err == UBI_IO_BITFLIPS)
 				scrub = 1;
 
-			new_aeb = kmem_cache_alloc(ai->aeb_slab_cache,
-						   GFP_KERNEL);
+			new_aeb = ubi_alloc_aeb(ai, pnum, be64_to_cpu(ech->ec));
 			if (!new_aeb) {
 				ret = -ENOMEM;
 				goto out;
 			}
 
-			new_aeb->ec = be64_to_cpu(ech->ec);
-			new_aeb->pnum = pnum;
 			new_aeb->lnum = be32_to_cpu(vh->lnum);
 			new_aeb->sqnum = be64_to_cpu(vh->sqnum);
 			new_aeb->copy_flag = vh->copy_flag;
@@ -558,7 +515,7 @@ static int scan_pool(struct ubi_device *ubi, struct ubi_attach_info *ai,
 	}
 
 out:
-	ubi_free_vid_hdr(ubi, vh);
+	ubi_free_vid_buf(vb);
 	kfree(ech);
 	return ret;
 }
@@ -841,11 +798,11 @@ static int ubi_attach_fastmap(struct ubi_device *ubi,
 fail:
 	list_for_each_entry_safe(tmp_aeb, _tmp_aeb, &used, u.list) {
 		list_del(&tmp_aeb->u.list);
-		kmem_cache_free(ai->aeb_slab_cache, tmp_aeb);
+		ubi_free_aeb(ai, tmp_aeb);
 	}
 	list_for_each_entry_safe(tmp_aeb, _tmp_aeb, &free, u.list) {
 		list_del(&tmp_aeb->u.list);
-		kmem_cache_free(ai->aeb_slab_cache, tmp_aeb);
+		ubi_free_aeb(ai, tmp_aeb);
 	}
 
 	return ret;
@@ -886,6 +843,7 @@ int ubi_scan_fastmap(struct ubi_device *ubi, struct ubi_attach_info *ai,
 		     struct ubi_attach_info *scan_ai)
 {
 	struct ubi_fm_sb *fmsb, *fmsb2;
+	struct ubi_vid_io_buf *vb;
 	struct ubi_vid_hdr *vh;
 	struct ubi_ec_hdr *ech;
 	struct ubi_fastmap_layout *fm;
@@ -919,7 +877,7 @@ int ubi_scan_fastmap(struct ubi_device *ubi, struct ubi_attach_info *ai,
 		goto out;
 	}
 
-	ret = ubi_io_read(ubi, fmsb, fm_anchor, ubi->leb_start, sizeof(*fmsb));
+	ret = ubi_io_read_data(ubi, fmsb, fm_anchor, 0, sizeof(*fmsb));
 	if (ret && ret != UBI_IO_BITFLIPS)
 		goto free_fm_sb;
 	else if (ret == UBI_IO_BITFLIPS)
@@ -961,12 +919,14 @@ int ubi_scan_fastmap(struct ubi_device *ubi, struct ubi_attach_info *ai,
 		goto free_fm_sb;
 	}
 
-	vh = ubi_zalloc_vid_hdr(ubi, GFP_KERNEL);
-	if (!vh) {
+	vb = ubi_alloc_vid_buf(ubi, GFP_KERNEL);
+	if (!vb) {
 		ret = -ENOMEM;
 		goto free_hdr;
 	}
 
+	vh = ubi_get_vid_hdr(vb);
+
 	for (i = 0; i < used_blocks; i++) {
 		int image_seq;
 
@@ -1009,7 +969,7 @@ int ubi_scan_fastmap(struct ubi_device *ubi, struct ubi_attach_info *ai,
 			goto free_hdr;
 		}
 
-		ret = ubi_io_read_vid_hdr(ubi, pnum, vh, 0);
+		ret = ubi_io_read_vid_hdr(ubi, pnum, vb, 0);
 		if (ret && ret != UBI_IO_BITFLIPS) {
 			ubi_err(ubi, "unable to read fastmap block# %i (PEB: %i)",
 				i, pnum);
@@ -1037,8 +997,8 @@ int ubi_scan_fastmap(struct ubi_device *ubi, struct ubi_attach_info *ai,
 		if (sqnum < be64_to_cpu(vh->sqnum))
 			sqnum = be64_to_cpu(vh->sqnum);
 
-		ret = ubi_io_read(ubi, ubi->fm_buf + (ubi->leb_size * i), pnum,
-				  ubi->leb_start, ubi->leb_size);
+		ret = ubi_io_read_data(ubi, ubi->fm_buf + (ubi->leb_size * i),
+				       pnum, 0, ubi->leb_size);
 		if (ret && ret != UBI_IO_BITFLIPS) {
 			ubi_err(ubi, "unable to read fastmap block# %i (PEB: %i, "
 				"err: %i)", i, pnum, ret);
@@ -1099,7 +1059,7 @@ int ubi_scan_fastmap(struct ubi_device *ubi, struct ubi_attach_info *ai,
 	ubi->fm_disabled = 0;
 	ubi->fast_attach = 1;
 
-	ubi_free_vid_hdr(ubi, vh);
+	ubi_free_vid_buf(vb);
 	kfree(ech);
 out:
 	up_write(&ubi->fm_protect);
@@ -1108,7 +1068,7 @@ int ubi_scan_fastmap(struct ubi_device *ubi, struct ubi_attach_info *ai,
 	return ret;
 
 free_hdr:
-	ubi_free_vid_hdr(ubi, vh);
+	ubi_free_vid_buf(vb);
 	kfree(ech);
 free_fm_sb:
 	kfree(fmsb);
@@ -1136,6 +1096,7 @@ static int ubi_write_fastmap(struct ubi_device *ubi,
 	struct ubi_fm_eba *feba;
 	struct ubi_wl_entry *wl_e;
 	struct ubi_volume *vol;
+	struct ubi_vid_io_buf *avbuf, *dvbuf;
 	struct ubi_vid_hdr *avhdr, *dvhdr;
 	struct ubi_work *ubi_wrk;
 	struct rb_node *tmp_rb;
@@ -1146,18 +1107,21 @@ static int ubi_write_fastmap(struct ubi_device *ubi,
 	fm_raw = ubi->fm_buf;
 	memset(ubi->fm_buf, 0, ubi->fm_size);
 
-	avhdr = new_fm_vhdr(ubi, UBI_FM_SB_VOLUME_ID);
-	if (!avhdr) {
+	avbuf = new_fm_vbuf(ubi, UBI_FM_SB_VOLUME_ID);
+	if (!avbuf) {
 		ret = -ENOMEM;
 		goto out;
 	}
 
-	dvhdr = new_fm_vhdr(ubi, UBI_FM_DATA_VOLUME_ID);
-	if (!dvhdr) {
+	dvbuf = new_fm_vbuf(ubi, UBI_FM_DATA_VOLUME_ID);
+	if (!dvbuf) {
 		ret = -ENOMEM;
 		goto out_kfree;
 	}
 
+	avhdr = ubi_get_vid_hdr(avbuf);
+	dvhdr = ubi_get_vid_hdr(dvbuf);
+
 	seen_pebs = init_seen(ubi);
 	if (IS_ERR(seen_pebs)) {
 		ret = PTR_ERR(seen_pebs);
@@ -1306,8 +1270,12 @@ static int ubi_write_fastmap(struct ubi_device *ubi,
 		fm_pos += sizeof(*feba) + (sizeof(__be32) * vol->reserved_pebs);
 		ubi_assert(fm_pos <= ubi->fm_size);
 
-		for (j = 0; j < vol->reserved_pebs; j++)
-			feba->pnum[j] = cpu_to_be32(vol->eba_tbl[j]);
+		for (j = 0; j < vol->reserved_pebs; j++) {
+			struct ubi_eba_leb_desc ldesc;
+
+			ubi_eba_get_ldesc(vol, j, &ldesc);
+			feba->pnum[j] = cpu_to_be32(ldesc.pnum);
+		}
 
 		feba->reserved_pebs = cpu_to_be32(j);
 		feba->magic = cpu_to_be32(UBI_FM_EBA_MAGIC);
@@ -1322,7 +1290,7 @@ static int ubi_write_fastmap(struct ubi_device *ubi,
 	spin_unlock(&ubi->volumes_lock);
 
 	dbg_bld("writing fastmap SB to PEB %i", new_fm->e[0]->pnum);
-	ret = ubi_io_write_vid_hdr(ubi, new_fm->e[0]->pnum, avhdr);
+	ret = ubi_io_write_vid_hdr(ubi, new_fm->e[0]->pnum, avbuf);
 	if (ret) {
 		ubi_err(ubi, "unable to write vid_hdr to fastmap SB!");
 		goto out_kfree;
@@ -1343,7 +1311,7 @@ static int ubi_write_fastmap(struct ubi_device *ubi,
 		dvhdr->lnum = cpu_to_be32(i);
 		dbg_bld("writing fastmap data to PEB %i sqnum %llu",
 			new_fm->e[i]->pnum, be64_to_cpu(dvhdr->sqnum));
-		ret = ubi_io_write_vid_hdr(ubi, new_fm->e[i]->pnum, dvhdr);
+		ret = ubi_io_write_vid_hdr(ubi, new_fm->e[i]->pnum, dvbuf);
 		if (ret) {
 			ubi_err(ubi, "unable to write vid_hdr to PEB %i!",
 				new_fm->e[i]->pnum);
@@ -1352,8 +1320,8 @@ static int ubi_write_fastmap(struct ubi_device *ubi,
 	}
 
 	for (i = 0; i < new_fm->used_blocks; i++) {
-		ret = ubi_io_write(ubi, fm_raw + (i * ubi->leb_size),
-			new_fm->e[i]->pnum, ubi->leb_start, ubi->leb_size);
+		ret = ubi_io_write_data(ubi, fm_raw + (i * ubi->leb_size),
+					new_fm->e[i]->pnum, 0, ubi->leb_size);
 		if (ret) {
 			ubi_err(ubi, "unable to write fastmap to PEB %i!",
 				new_fm->e[i]->pnum);
@@ -1368,8 +1336,8 @@ static int ubi_write_fastmap(struct ubi_device *ubi,
 	dbg_bld("fastmap written!");
 
 out_kfree:
-	ubi_free_vid_hdr(ubi, avhdr);
-	ubi_free_vid_hdr(ubi, dvhdr);
+	ubi_free_vid_buf(avbuf);
+	ubi_free_vid_buf(dvbuf);
 	free_seen(seen_pebs);
 out:
 	return ret;
@@ -1439,7 +1407,8 @@ static int invalidate_fastmap(struct ubi_device *ubi)
 	int ret;
 	struct ubi_fastmap_layout *fm;
 	struct ubi_wl_entry *e;
-	struct ubi_vid_hdr *vh = NULL;
+	struct ubi_vid_io_buf *vb = NULL;
+	struct ubi_vid_hdr *vh;
 
 	if (!ubi->fm)
 		return 0;
@@ -1451,10 +1420,12 @@ static int invalidate_fastmap(struct ubi_device *ubi)
 	if (!fm)
 		goto out;
 
-	vh = new_fm_vhdr(ubi, UBI_FM_SB_VOLUME_ID);
-	if (!vh)
+	vb = new_fm_vbuf(ubi, UBI_FM_SB_VOLUME_ID);
+	if (!vb)
 		goto out_free_fm;
 
+	vh = ubi_get_vid_hdr(vb);
+
 	ret = -ENOSPC;
 	e = ubi_wl_get_fm_peb(ubi, 1);
 	if (!e)
@@ -1465,7 +1436,7 @@ static int invalidate_fastmap(struct ubi_device *ubi)
 	 * to scanning mode.
 	 */
 	vh->sqnum = cpu_to_be64(ubi_next_sqnum(ubi));
-	ret = ubi_io_write_vid_hdr(ubi, e->pnum, vh);
+	ret = ubi_io_write_vid_hdr(ubi, e->pnum, vb);
 	if (ret < 0) {
 		ubi_wl_put_fm_peb(ubi, e, 0, 0);
 		goto out_free_fm;
@@ -1477,7 +1448,7 @@ static int invalidate_fastmap(struct ubi_device *ubi)
 	ubi->fm = fm;
 
 out:
-	ubi_free_vid_hdr(ubi, vh);
+	ubi_free_vid_buf(vb);
 	return ret;
 
 out_free_fm:
@@ -1522,22 +1493,30 @@ int ubi_update_fastmap(struct ubi_device *ubi)
 	struct ubi_wl_entry *tmp_e;
 
 	down_write(&ubi->fm_protect);
+	down_write(&ubi->work_sem);
+	down_write(&ubi->fm_eba_sem);
 
 	ubi_refill_pools(ubi);
 
 	if (ubi->ro_mode || ubi->fm_disabled) {
+		up_write(&ubi->fm_eba_sem);
+		up_write(&ubi->work_sem);
 		up_write(&ubi->fm_protect);
 		return 0;
 	}
 
 	ret = ubi_ensure_anchor_pebs(ubi);
 	if (ret) {
+		up_write(&ubi->fm_eba_sem);
+		up_write(&ubi->work_sem);
 		up_write(&ubi->fm_protect);
 		return ret;
 	}
 
 	new_fm = kzalloc(sizeof(*new_fm), GFP_KERNEL);
 	if (!new_fm) {
+		up_write(&ubi->fm_eba_sem);
+		up_write(&ubi->work_sem);
 		up_write(&ubi->fm_protect);
 		return -ENOMEM;
 	}
@@ -1646,16 +1625,14 @@ int ubi_update_fastmap(struct ubi_device *ubi)
 		new_fm->e[0] = tmp_e;
 	}
 
-	down_write(&ubi->work_sem);
-	down_write(&ubi->fm_eba_sem);
 	ret = ubi_write_fastmap(ubi, new_fm);
-	up_write(&ubi->fm_eba_sem);
-	up_write(&ubi->work_sem);
 
 	if (ret)
 		goto err;
 
 out_unlock:
+	up_write(&ubi->fm_eba_sem);
+	up_write(&ubi->work_sem);
 	up_write(&ubi->fm_protect);
 	kfree(old_fm);
 	return ret;

drivers/mtd/ubi/io.c

@@ -502,6 +502,7 @@ static int nor_erase_prepare(struct ubi_device *ubi, int pnum)
 	loff_t addr;
 	uint32_t data = 0;
 	struct ubi_ec_hdr ec_hdr;
+	struct ubi_vid_io_buf vidb;
 
 	/*
 	 * Note, we cannot generally define VID header buffers on stack,
@@ -528,7 +529,10 @@ static int nor_erase_prepare(struct ubi_device *ubi, int pnum)
 			goto error;
 	}
 
-	err = ubi_io_read_vid_hdr(ubi, pnum, &vid_hdr, 0);
+	ubi_init_vid_buf(ubi, &vidb, &vid_hdr);
+	ubi_assert(&vid_hdr == ubi_get_vid_hdr(&vidb));
+
+	err = ubi_io_read_vid_hdr(ubi, pnum, &vidb, 0);
 	if (err != UBI_IO_BAD_HDR_EBADMSG && err != UBI_IO_BAD_HDR &&
 	    err != UBI_IO_FF){
 		addr += ubi->vid_hdr_aloffset;
@@ -995,12 +999,11 @@ static int validate_vid_hdr(const struct ubi_device *ubi,
  * ubi_io_read_vid_hdr - read and check a volume identifier header.
  * @ubi: UBI device description object
  * @pnum: physical eraseblock number to read from
- * @vid_hdr: &struct ubi_vid_hdr object where to store the read volume
- * identifier header
+ * @vidb: the volume identifier buffer to store data in
  * @verbose: be verbose if the header is corrupted or wasn't found
  *
  * This function reads the volume identifier header from physical eraseblock
- * @pnum and stores it in @vid_hdr. It also checks CRC checksum of the read
+ * @pnum and stores it in @vidb. It also checks CRC checksum of the read
  * volume identifier header. The error codes are the same as in
  * 'ubi_io_read_ec_hdr()'.
  *
@@ -1008,16 +1011,16 @@ static int validate_vid_hdr(const struct ubi_device *ubi,
  * 'ubi_io_read_ec_hdr()', so refer commentaries in 'ubi_io_read_ec_hdr()'.
  */
 int ubi_io_read_vid_hdr(struct ubi_device *ubi, int pnum,
-			struct ubi_vid_hdr *vid_hdr, int verbose)
+			struct ubi_vid_io_buf *vidb, int verbose)
 {
 	int err, read_err;
 	uint32_t crc, magic, hdr_crc;
-	void *p;
+	struct ubi_vid_hdr *vid_hdr = ubi_get_vid_hdr(vidb);
+	void *p = vidb->buffer;
 
 	dbg_io("read VID header from PEB %d", pnum);
 	ubi_assert(pnum >= 0 &&  pnum < ubi->peb_count);
 
-	p = (char *)vid_hdr - ubi->vid_hdr_shift;
 	read_err = ubi_io_read(ubi, p, pnum, ubi->vid_hdr_aloffset,
 			  ubi->vid_hdr_shift + UBI_VID_HDR_SIZE);
 	if (read_err && read_err != UBI_IO_BITFLIPS && !mtd_is_eccerr(read_err))
@@ -1080,23 +1083,24 @@ int ubi_io_read_vid_hdr(struct ubi_device *ubi, int pnum,
  * ubi_io_write_vid_hdr - write a volume identifier header.
  * @ubi: UBI device description object
  * @pnum: the physical eraseblock number to write to
- * @vid_hdr: the volume identifier header to write
+ * @vidb: the volume identifier buffer to write
  *
  * This function writes the volume identifier header described by @vid_hdr to
  * physical eraseblock @pnum. This function automatically fills the
- * @vid_hdr->magic and the @vid_hdr->version fields, as well as calculates
- * header CRC checksum and stores it at vid_hdr->hdr_crc.
+ * @vidb->hdr->magic and the @vidb->hdr->version fields, as well as calculates
+ * header CRC checksum and stores it at vidb->hdr->hdr_crc.
  *
  * This function returns zero in case of success and a negative error code in
  * case of failure. If %-EIO is returned, the physical eraseblock probably went
  * bad.
  */
 int ubi_io_write_vid_hdr(struct ubi_device *ubi, int pnum,
-			 struct ubi_vid_hdr *vid_hdr)
+			 struct ubi_vid_io_buf *vidb)
 {
+	struct ubi_vid_hdr *vid_hdr = ubi_get_vid_hdr(vidb);
 	int err;
 	uint32_t crc;
-	void *p;
+	void *p = vidb->buffer;
 
 	dbg_io("write VID header to PEB %d", pnum);
 	ubi_assert(pnum >= 0 &&  pnum < ubi->peb_count);
@@ -1117,7 +1121,6 @@ int ubi_io_write_vid_hdr(struct ubi_device *ubi, int pnum,
 	if (ubi_dbg_power_cut(ubi, POWER_CUT_VID_WRITE))
 		return -EROFS;
 
-	p = (char *)vid_hdr - ubi->vid_hdr_shift;
 	err = ubi_io_write(ubi, p, pnum, ubi->vid_hdr_aloffset,
 			   ubi->vid_hdr_alsize);
 	return err;
@@ -1283,17 +1286,19 @@ static int self_check_peb_vid_hdr(const struct ubi_device *ubi, int pnum)
 {
 	int err;
 	uint32_t crc, hdr_crc;
+	struct ubi_vid_io_buf *vidb;
 	struct ubi_vid_hdr *vid_hdr;
 	void *p;
 
 	if (!ubi_dbg_chk_io(ubi))
 		return 0;
 
-	vid_hdr = ubi_zalloc_vid_hdr(ubi, GFP_NOFS);
-	if (!vid_hdr)
+	vidb = ubi_alloc_vid_buf(ubi, GFP_NOFS);
+	if (!vidb)
 		return -ENOMEM;
 
-	p = (char *)vid_hdr - ubi->vid_hdr_shift;
+	vid_hdr = ubi_get_vid_hdr(vidb);
+	p = vidb->buffer;
 	err = ubi_io_read(ubi, p, pnum, ubi->vid_hdr_aloffset,
 			  ubi->vid_hdr_alsize);
 	if (err && err != UBI_IO_BITFLIPS && !mtd_is_eccerr(err))
@@ -1314,7 +1319,7 @@ static int self_check_peb_vid_hdr(const struct ubi_device *ubi, int pnum)
 	err = self_check_vid_hdr(ubi, pnum, vid_hdr);
 
 exit:
-	ubi_free_vid_hdr(ubi, vid_hdr);
+	ubi_free_vid_buf(vidb);
 	return err;
 }
 

drivers/mtd/ubi/kapi.c

@@ -538,7 +538,7 @@ int ubi_leb_write(struct ubi_volume_desc *desc, int lnum, const void *buf,
 	if (desc->mode == UBI_READONLY || vol->vol_type == UBI_STATIC_VOLUME)
 		return -EROFS;
 
-	if (lnum < 0 || lnum >= vol->reserved_pebs || offset < 0 || len < 0 ||
+	if (!ubi_leb_valid(vol, lnum) || offset < 0 || len < 0 ||
 	    offset + len > vol->usable_leb_size ||
 	    offset & (ubi->min_io_size - 1) || len & (ubi->min_io_size - 1))
 		return -EINVAL;
@@ -583,7 +583,7 @@ int ubi_leb_change(struct ubi_volume_desc *desc, int lnum, const void *buf,
 	if (desc->mode == UBI_READONLY || vol->vol_type == UBI_STATIC_VOLUME)
 		return -EROFS;
 
-	if (lnum < 0 || lnum >= vol->reserved_pebs || len < 0 ||
+	if (!ubi_leb_valid(vol, lnum) || len < 0 ||
 	    len > vol->usable_leb_size || len & (ubi->min_io_size - 1))
 		return -EINVAL;
 
@@ -620,7 +620,7 @@ int ubi_leb_erase(struct ubi_volume_desc *desc, int lnum)
 	if (desc->mode == UBI_READONLY || vol->vol_type == UBI_STATIC_VOLUME)
 		return -EROFS;
 
-	if (lnum < 0 || lnum >= vol->reserved_pebs)
+	if (!ubi_leb_valid(vol, lnum))
 		return -EINVAL;
 
 	if (vol->upd_marker)
@@ -680,7 +680,7 @@ int ubi_leb_unmap(struct ubi_volume_desc *desc, int lnum)
 	if (desc->mode == UBI_READONLY || vol->vol_type == UBI_STATIC_VOLUME)
 		return -EROFS;
 
-	if (lnum < 0 || lnum >= vol->reserved_pebs)
+	if (!ubi_leb_valid(vol, lnum))
 		return -EINVAL;
 
 	if (vol->upd_marker)
@@ -716,13 +716,13 @@ int ubi_leb_map(struct ubi_volume_desc *desc, int lnum)
 	if (desc->mode == UBI_READONLY || vol->vol_type == UBI_STATIC_VOLUME)
 		return -EROFS;
 
-	if (lnum < 0 || lnum >= vol->reserved_pebs)
+	if (!ubi_leb_valid(vol, lnum))
 		return -EINVAL;
 
 	if (vol->upd_marker)
 		return -EBADF;
 
-	if (vol->eba_tbl[lnum] >= 0)
+	if (ubi_eba_is_mapped(vol, lnum))
 		return -EBADMSG;
 
 	return ubi_eba_write_leb(ubi, vol, lnum, NULL, 0, 0);
@@ -751,13 +751,13 @@ int ubi_is_mapped(struct ubi_volume_desc *desc, int lnum)
 
 	dbg_gen("test LEB %d:%d", vol->vol_id, lnum);
 
-	if (lnum < 0 || lnum >= vol->reserved_pebs)
+	if (!ubi_leb_valid(vol, lnum))
 		return -EINVAL;
 
 	if (vol->upd_marker)
 		return -EBADF;
 
-	return vol->eba_tbl[lnum] >= 0;
+	return ubi_eba_is_mapped(vol, lnum);
 }
 EXPORT_SYMBOL_GPL(ubi_is_mapped);
 

drivers/mtd/ubi/ubi.h

@@ -166,6 +166,17 @@ enum {
 	POWER_CUT_VID_WRITE = 0x02,
 };
 
+/**
+ * struct ubi_vid_io_buf - VID buffer used to read/write VID info to/from the
+ *			   flash.
+ * @hdr: a pointer to the VID header stored in buffer
+ * @buffer: underlying buffer
+ */
+struct ubi_vid_io_buf {
+	struct ubi_vid_hdr *hdr;
+	void *buffer;
+};
+
 /**
  * struct ubi_wl_entry - wear-leveling entry.
  * @u.rb: link in the corresponding (free/used) RB-tree
@@ -266,6 +277,21 @@ struct ubi_fm_pool {
 	int max_size;
 };
 
+/**
+ * struct ubi_eba_leb_desc - EBA logical eraseblock descriptor
+ * @lnum: the logical eraseblock number
+ * @pnum: the physical eraseblock where the LEB can be found
+ *
+ * This structure is here to hide EBA's internal from other part of the
+ * UBI implementation.
+ *
+ * One can query the position of a LEB by calling ubi_eba_get_ldesc().
+ */
+struct ubi_eba_leb_desc {
+	int lnum;
+	int pnum;
+};
+
 /**
  * struct ubi_volume - UBI volume description data structure.
  * @dev: device object to make use of the the Linux device model
@@ -344,7 +370,7 @@ struct ubi_volume {
 	long long upd_received;
 	void *upd_buf;
 
-	int *eba_tbl;
+	struct ubi_eba_table *eba_tbl;
 	unsigned int checked:1;
 	unsigned int corrupted:1;
 	unsigned int upd_marker:1;
@@ -724,6 +750,8 @@ struct ubi_ainf_volume {
  * @ec_sum: a temporary variable used when calculating @mean_ec
  * @ec_count: a temporary variable used when calculating @mean_ec
  * @aeb_slab_cache: slab cache for &struct ubi_ainf_peb objects
+ * @ech: temporary EC header. Only available during scan
+ * @vidh: temporary VID buffer. Only available during scan
  *
  * This data structure contains the result of attaching an MTD device and may
  * be used by other UBI sub-systems to build final UBI data structures, further
@@ -752,6 +780,8 @@ struct ubi_attach_info {
 	uint64_t ec_sum;
 	int ec_count;
 	struct kmem_cache *aeb_slab_cache;
+	struct ubi_ec_hdr *ech;
+	struct ubi_vid_io_buf *vidb;
 };
 
 /**
@@ -792,8 +822,12 @@ extern struct mutex ubi_devices_mutex;
 extern struct blocking_notifier_head ubi_notifiers;
 
 /* attach.c */
+struct ubi_ainf_peb *ubi_alloc_aeb(struct ubi_attach_info *ai, int pnum,
+				   int ec);
+void ubi_free_aeb(struct ubi_attach_info *ai, struct ubi_ainf_peb *aeb);
 int ubi_add_to_av(struct ubi_device *ubi, struct ubi_attach_info *ai, int pnum,
 		  int ec, const struct ubi_vid_hdr *vid_hdr, int bitflips);
+struct ubi_ainf_volume *ubi_add_av(struct ubi_attach_info *ai, int vol_id);
 struct ubi_ainf_volume *ubi_find_av(const struct ubi_attach_info *ai,
 				    int vol_id);
 void ubi_remove_av(struct ubi_attach_info *ai, struct ubi_ainf_volume *av);
@@ -835,7 +869,21 @@ void ubi_update_reserved(struct ubi_device *ubi);
 void ubi_calculate_reserved(struct ubi_device *ubi);
 int ubi_check_pattern(const void *buf, uint8_t patt, int size);
 
+static inline bool ubi_leb_valid(struct ubi_volume *vol, int lnum)
+{
+	return lnum >= 0 && lnum < vol->reserved_pebs;
+}
+
 /* eba.c */
+struct ubi_eba_table *ubi_eba_create_table(struct ubi_volume *vol,
+					   int nentries);
+void ubi_eba_destroy_table(struct ubi_eba_table *tbl);
+void ubi_eba_copy_table(struct ubi_volume *vol, struct ubi_eba_table *dst,
+			int nentries);
+void ubi_eba_replace_table(struct ubi_volume *vol, struct ubi_eba_table *tbl);
+void ubi_eba_get_ldesc(struct ubi_volume *vol, int lnum,
+		       struct ubi_eba_leb_desc *ldesc);
+bool ubi_eba_is_mapped(struct ubi_volume *vol, int lnum);
 int ubi_eba_unmap_leb(struct ubi_device *ubi, struct ubi_volume *vol,
 		      int lnum);
 int ubi_eba_read_leb(struct ubi_device *ubi, struct ubi_volume *vol, int lnum,
@@ -850,7 +898,7 @@ int ubi_eba_write_leb_st(struct ubi_device *ubi, struct ubi_volume *vol,
 int ubi_eba_atomic_leb_change(struct ubi_device *ubi, struct ubi_volume *vol,
 			      int lnum, const void *buf, int len);
 int ubi_eba_copy_leb(struct ubi_device *ubi, int from, int to,
-		     struct ubi_vid_hdr *vid_hdr);
+		     struct ubi_vid_io_buf *vidb);
 int ubi_eba_init(struct ubi_device *ubi, struct ubi_attach_info *ai);
 unsigned long long ubi_next_sqnum(struct ubi_device *ubi);
 int self_check_eba(struct ubi_device *ubi, struct ubi_attach_info *ai_fastmap,
@@ -885,9 +933,9 @@ int ubi_io_read_ec_hdr(struct ubi_device *ubi, int pnum,
 int ubi_io_write_ec_hdr(struct ubi_device *ubi, int pnum,
 			struct ubi_ec_hdr *ec_hdr);
 int ubi_io_read_vid_hdr(struct ubi_device *ubi, int pnum,
-			struct ubi_vid_hdr *vid_hdr, int verbose);
+			struct ubi_vid_io_buf *vidb, int verbose);
 int ubi_io_write_vid_hdr(struct ubi_device *ubi, int pnum,
-			 struct ubi_vid_hdr *vid_hdr);
+			 struct ubi_vid_io_buf *vidb);
 
 /* build.c */
 int ubi_attach_mtd_dev(struct mtd_info *mtd, int ubi_num,
@@ -1008,44 +1056,68 @@ static inline void ubi_move_aeb_to_list(struct ubi_ainf_volume *av,
 }
 
 /**
- * ubi_zalloc_vid_hdr - allocate a volume identifier header object.
- * @ubi: UBI device description object
- * @gfp_flags: GFP flags to allocate with
- *
- * This function returns a pointer to the newly allocated and zero-filled
- * volume identifier header object in case of success and %NULL in case of
- * failure.
+ * ubi_init_vid_buf - Initialize a VID buffer
+ * @ubi: the UBI device
+ * @vidb: the VID buffer to initialize
+ * @buf: the underlying buffer
  */
-static inline struct ubi_vid_hdr *
-ubi_zalloc_vid_hdr(const struct ubi_device *ubi, gfp_t gfp_flags)
+static inline void ubi_init_vid_buf(const struct ubi_device *ubi,
+				    struct ubi_vid_io_buf *vidb,
+				    void *buf)
 {
-	void *vid_hdr;
+	if (buf)
+		memset(buf, 0, ubi->vid_hdr_alsize);
 
-	vid_hdr = kzalloc(ubi->vid_hdr_alsize, gfp_flags);
-	if (!vid_hdr)
-		return NULL;
+	vidb->buffer = buf;
+	vidb->hdr = buf + ubi->vid_hdr_shift;
+}
 
-	/*
-	 * VID headers may be stored at un-aligned flash offsets, so we shift
-	 * the pointer.
+/**
+ * ubi_init_vid_buf - Allocate a VID buffer
+ * @ubi: the UBI device
+ * @gfp_flags: GFP flags to use for the allocation
  */
-	return vid_hdr + ubi->vid_hdr_shift;
+static inline struct ubi_vid_io_buf *
+ubi_alloc_vid_buf(const struct ubi_device *ubi, gfp_t gfp_flags)
+{
+	struct ubi_vid_io_buf *vidb;
+	void *buf;
+
+	vidb = kzalloc(sizeof(*vidb), gfp_flags);
+	if (!vidb)
+		return NULL;
+
+	buf = kmalloc(ubi->vid_hdr_alsize, gfp_flags);
+	if (!buf) {
+		kfree(vidb);
+		return NULL;
+	}
+
+	ubi_init_vid_buf(ubi, vidb, buf);
+
+	return vidb;
 }
 
 /**
- * ubi_free_vid_hdr - free a volume identifier header object.
- * @ubi: UBI device description object
- * @vid_hdr: the object to free
+ * ubi_free_vid_buf - Free a VID buffer
+ * @vidb: the VID buffer to free
  */
-static inline void ubi_free_vid_hdr(const struct ubi_device *ubi,
-				    struct ubi_vid_hdr *vid_hdr)
+static inline void ubi_free_vid_buf(struct ubi_vid_io_buf *vidb)
 {
-	void *p = vid_hdr;
-
-	if (!p)
+	if (!vidb)
 		return;
 
-	kfree(p - ubi->vid_hdr_shift);
+	kfree(vidb->buffer);
+	kfree(vidb);
+}
+
+/**
+ * ubi_get_vid_hdr - Get the VID header attached to a VID buffer
+ * @vidb: VID buffer
+ */
+static inline struct ubi_vid_hdr *ubi_get_vid_hdr(struct ubi_vid_io_buf *vidb)
+{
+	return vidb->hdr;
 }
 
 /*

drivers/mtd/ubi/vmt.c

@@ -138,7 +138,7 @@ static void vol_release(struct device *dev)
 {
 	struct ubi_volume *vol = container_of(dev, struct ubi_volume, dev);
 
-	kfree(vol->eba_tbl);
+	ubi_eba_replace_table(vol, NULL);
 	kfree(vol);
 }
 
@@ -158,6 +158,7 @@ int ubi_create_volume(struct ubi_device *ubi, struct ubi_mkvol_req *req)
 	int i, err, vol_id = req->vol_id, do_free = 1;
 	struct ubi_volume *vol;
 	struct ubi_vtbl_record vtbl_rec;
+	struct ubi_eba_table *eba_tbl = NULL;
 	dev_t dev;
 
 	if (ubi->ro_mode)
@@ -241,14 +242,13 @@ int ubi_create_volume(struct ubi_device *ubi, struct ubi_mkvol_req *req)
 	if (err)
 		goto out_acc;
 
-	vol->eba_tbl = kmalloc(vol->reserved_pebs * sizeof(int), GFP_KERNEL);
-	if (!vol->eba_tbl) {
-		err = -ENOMEM;
+	eba_tbl = ubi_eba_create_table(vol, vol->reserved_pebs);
+	if (IS_ERR(eba_tbl)) {
+		err = PTR_ERR(eba_tbl);
 		goto out_acc;
 	}
 
-	for (i = 0; i < vol->reserved_pebs; i++)
-		vol->eba_tbl[i] = UBI_LEB_UNMAPPED;
+	ubi_eba_replace_table(vol, eba_tbl);
 
 	if (vol->vol_type == UBI_DYNAMIC_VOLUME) {
 		vol->used_ebs = vol->reserved_pebs;
@@ -329,7 +329,7 @@ int ubi_create_volume(struct ubi_device *ubi, struct ubi_mkvol_req *req)
 	cdev_del(&vol->cdev);
 out_mapping:
 	if (do_free)
-		kfree(vol->eba_tbl);
+		ubi_eba_destroy_table(eba_tbl);
 out_acc:
 	spin_lock(&ubi->volumes_lock);
 	ubi->rsvd_pebs -= vol->reserved_pebs;
@@ -427,10 +427,11 @@ int ubi_remove_volume(struct ubi_volume_desc *desc, int no_vtbl)
  */
 int ubi_resize_volume(struct ubi_volume_desc *desc, int reserved_pebs)
 {
-	int i, err, pebs, *new_mapping;
+	int i, err, pebs;
 	struct ubi_volume *vol = desc->vol;
 	struct ubi_device *ubi = vol->ubi;
 	struct ubi_vtbl_record vtbl_rec;
+	struct ubi_eba_table *new_eba_tbl = NULL;
 	int vol_id = vol->vol_id;
 
 	if (ubi->ro_mode)
@@ -450,12 +451,9 @@ int ubi_resize_volume(struct ubi_volume_desc *desc, int reserved_pebs)
 	if (reserved_pebs == vol->reserved_pebs)
 		return 0;
 
-	new_mapping = kmalloc(reserved_pebs * sizeof(int), GFP_KERNEL);
-	if (!new_mapping)
-		return -ENOMEM;
-
-	for (i = 0; i < reserved_pebs; i++)
-		new_mapping[i] = UBI_LEB_UNMAPPED;
+	new_eba_tbl = ubi_eba_create_table(vol, reserved_pebs);
+	if (IS_ERR(new_eba_tbl))
+		return PTR_ERR(new_eba_tbl);
 
 	spin_lock(&ubi->volumes_lock);
 	if (vol->ref_count > 1) {
@@ -481,10 +479,8 @@ int ubi_resize_volume(struct ubi_volume_desc *desc, int reserved_pebs)
 		}
 		ubi->avail_pebs -= pebs;
 		ubi->rsvd_pebs += pebs;
-		for (i = 0; i < vol->reserved_pebs; i++)
-			new_mapping[i] = vol->eba_tbl[i];
-		kfree(vol->eba_tbl);
-		vol->eba_tbl = new_mapping;
+		ubi_eba_copy_table(vol, new_eba_tbl, vol->reserved_pebs);
+		ubi_eba_replace_table(vol, new_eba_tbl);
 		spin_unlock(&ubi->volumes_lock);
 	}
 
@@ -498,10 +494,8 @@ int ubi_resize_volume(struct ubi_volume_desc *desc, int reserved_pebs)
 		ubi->rsvd_pebs += pebs;
 		ubi->avail_pebs -= pebs;
 		ubi_update_reserved(ubi);
-		for (i = 0; i < reserved_pebs; i++)
-			new_mapping[i] = vol->eba_tbl[i];
-		kfree(vol->eba_tbl);
-		vol->eba_tbl = new_mapping;
+		ubi_eba_copy_table(vol, new_eba_tbl, reserved_pebs);
+		ubi_eba_replace_table(vol, new_eba_tbl);
 		spin_unlock(&ubi->volumes_lock);
 	}
 
@@ -543,7 +537,7 @@ int ubi_resize_volume(struct ubi_volume_desc *desc, int reserved_pebs)
 		spin_unlock(&ubi->volumes_lock);
 	}
 out_free:
-	kfree(new_mapping);
+	kfree(new_eba_tbl);
 	return err;
 }
 

drivers/mtd/ubi/vtbl.c

@@ -299,15 +299,18 @@ static int create_vtbl(struct ubi_device *ubi, struct ubi_attach_info *ai,
 		       int copy, void *vtbl)
 {
 	int err, tries = 0;
+	struct ubi_vid_io_buf *vidb;
 	struct ubi_vid_hdr *vid_hdr;
 	struct ubi_ainf_peb *new_aeb;
 
 	dbg_gen("create volume table (copy #%d)", copy + 1);
 
-	vid_hdr = ubi_zalloc_vid_hdr(ubi, GFP_KERNEL);
-	if (!vid_hdr)
+	vidb = ubi_alloc_vid_buf(ubi, GFP_KERNEL);
+	if (!vidb)
 		return -ENOMEM;
 
+	vid_hdr = ubi_get_vid_hdr(vidb);
+
 retry:
 	new_aeb = ubi_early_get_peb(ubi, ai);
 	if (IS_ERR(new_aeb)) {
@@ -324,7 +327,7 @@ static int create_vtbl(struct ubi_device *ubi, struct ubi_attach_info *ai,
 	vid_hdr->sqnum = cpu_to_be64(++ai->max_sqnum);
 
 	/* The EC header is already there, write the VID header */
-	err = ubi_io_write_vid_hdr(ubi, new_aeb->pnum, vid_hdr);
+	err = ubi_io_write_vid_hdr(ubi, new_aeb->pnum, vidb);
 	if (err)
 		goto write_error;
 
@@ -338,8 +341,8 @@ static int create_vtbl(struct ubi_device *ubi, struct ubi_attach_info *ai,
 	 * of this LEB as it will be deleted and freed in 'ubi_add_to_av()'.
 	 */
 	err = ubi_add_to_av(ubi, ai, new_aeb->pnum, new_aeb->ec, vid_hdr, 0);
-	kmem_cache_free(ai->aeb_slab_cache, new_aeb);
-	ubi_free_vid_hdr(ubi, vid_hdr);
+	ubi_free_aeb(ai, new_aeb);
+	ubi_free_vid_buf(vidb);
 	return err;
 
 write_error:
@@ -351,9 +354,9 @@ static int create_vtbl(struct ubi_device *ubi, struct ubi_attach_info *ai,
 		list_add(&new_aeb->u.list, &ai->erase);
 		goto retry;
 	}
-	kmem_cache_free(ai->aeb_slab_cache, new_aeb);
+	ubi_free_aeb(ai, new_aeb);
 out_free:
-	ubi_free_vid_hdr(ubi, vid_hdr);
+	ubi_free_vid_buf(vidb);
 	return err;
 
 }

drivers/mtd/ubi/wl.c

@@ -580,7 +580,7 @@ static int erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk,
  * failure.
  */
 static int schedule_erase(struct ubi_device *ubi, struct ubi_wl_entry *e,
-			  int vol_id, int lnum, int torture)
+			  int vol_id, int lnum, int torture, bool nested)
 {
 	struct ubi_work *wl_wrk;
 
@@ -599,6 +599,9 @@ static int schedule_erase(struct ubi_device *ubi, struct ubi_wl_entry *e,
 	wl_wrk->lnum = lnum;
 	wl_wrk->torture = torture;
 
+	if (nested)
+		__schedule_ubi_work(ubi, wl_wrk);
+	else
 		schedule_ubi_work(ubi, wl_wrk);
 	return 0;
 }
@@ -644,11 +647,12 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk,
 				int shutdown)
 {
 	int err, scrubbing = 0, torture = 0, protect = 0, erroneous = 0;
-	int vol_id = -1, lnum = -1;
+	int erase = 0, keep = 0, vol_id = -1, lnum = -1;
 #ifdef CONFIG_MTD_UBI_FASTMAP
 	int anchor = wrk->anchor;
 #endif
 	struct ubi_wl_entry *e1, *e2;
+	struct ubi_vid_io_buf *vidb;
 	struct ubi_vid_hdr *vid_hdr;
 	int dst_leb_clean = 0;
 
@@ -656,10 +660,13 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk,
 	if (shutdown)
 		return 0;
 
-	vid_hdr = ubi_zalloc_vid_hdr(ubi, GFP_NOFS);
-	if (!vid_hdr)
+	vidb = ubi_alloc_vid_buf(ubi, GFP_NOFS);
+	if (!vidb)
 		return -ENOMEM;
 
+	vid_hdr = ubi_get_vid_hdr(vidb);
+
+	down_read(&ubi->fm_eba_sem);
 	mutex_lock(&ubi->move_mutex);
 	spin_lock(&ubi->wl_lock);
 	ubi_assert(!ubi->move_from && !ubi->move_to);
@@ -753,7 +760,7 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk,
 	 * which is being moved was unmapped.
 	 */
 
-	err = ubi_io_read_vid_hdr(ubi, e1->pnum, vid_hdr, 0);
+	err = ubi_io_read_vid_hdr(ubi, e1->pnum, vidb, 0);
 	if (err && err != UBI_IO_BITFLIPS) {
 		dst_leb_clean = 1;
 		if (err == UBI_IO_FF) {
@@ -780,6 +787,16 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk,
 			       e1->pnum);
 			scrubbing = 1;
 			goto out_not_moved;
+		} else if (ubi->fast_attach && err == UBI_IO_BAD_HDR_EBADMSG) {
+			/*
+			 * While a full scan would detect interrupted erasures
+			 * at attach time we can face them here when attached from
+			 * Fastmap.
+			 */
+			dbg_wl("PEB %d has ECC errors, maybe from an interrupted erasure",
+			       e1->pnum);
+			erase = 1;
+			goto out_not_moved;
 		}
 
 		ubi_err(ubi, "error %d while reading VID header from PEB %d",
@@ -790,7 +807,7 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk,
 	vol_id = be32_to_cpu(vid_hdr->vol_id);
 	lnum = be32_to_cpu(vid_hdr->lnum);
 
-	err = ubi_eba_copy_leb(ubi, e1->pnum, e2->pnum, vid_hdr);
+	err = ubi_eba_copy_leb(ubi, e1->pnum, e2->pnum, vidb);
 	if (err) {
 		if (err == MOVE_CANCEL_RACE) {
 			/*
@@ -815,6 +832,7 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk,
 			 * Target PEB had bit-flips or write error - torture it.
 			 */
 			torture = 1;
+			keep = 1;
 			goto out_not_moved;
 		}
 
@@ -847,7 +865,7 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk,
 	if (scrubbing)
 		ubi_msg(ubi, "scrubbed PEB %d (LEB %d:%d), data moved to PEB %d",
 			e1->pnum, vol_id, lnum, e2->pnum);
-	ubi_free_vid_hdr(ubi, vid_hdr);
+	ubi_free_vid_buf(vidb);
 
 	spin_lock(&ubi->wl_lock);
 	if (!ubi->move_to_put) {
@@ -879,6 +897,7 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk,
 
 	dbg_wl("done");
 	mutex_unlock(&ubi->move_mutex);
+	up_read(&ubi->fm_eba_sem);
 	return 0;
 
 	/*
@@ -901,7 +920,7 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk,
 		ubi->erroneous_peb_count += 1;
 	} else if (scrubbing)
 		wl_tree_add(e1, &ubi->scrub);
-	else
+	else if (keep)
 		wl_tree_add(e1, &ubi->used);
 	if (dst_leb_clean) {
 		wl_tree_add(e2, &ubi->free);
@@ -913,7 +932,7 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk,
 	ubi->wl_scheduled = 0;
 	spin_unlock(&ubi->wl_lock);
 
-	ubi_free_vid_hdr(ubi, vid_hdr);
+	ubi_free_vid_buf(vidb);
 	if (dst_leb_clean) {
 		ensure_wear_leveling(ubi, 1);
 	} else {
@@ -922,7 +941,14 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk,
 			goto out_ro;
 	}
 
+	if (erase) {
+		err = do_sync_erase(ubi, e1, vol_id, lnum, 1);
+		if (err)
+			goto out_ro;
+	}
+
 	mutex_unlock(&ubi->move_mutex);
+	up_read(&ubi->fm_eba_sem);
 	return 0;
 
 out_error:
@@ -937,13 +963,14 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk,
 	ubi->move_to_put = ubi->wl_scheduled = 0;
 	spin_unlock(&ubi->wl_lock);
 
-	ubi_free_vid_hdr(ubi, vid_hdr);
+	ubi_free_vid_buf(vidb);
 	wl_entry_destroy(ubi, e1);
 	wl_entry_destroy(ubi, e2);
 
 out_ro:
 	ubi_ro_mode(ubi);
 	mutex_unlock(&ubi->move_mutex);
+	up_read(&ubi->fm_eba_sem);
 	ubi_assert(err != 0);
 	return err < 0 ? err : -EIO;
 
@@ -951,7 +978,8 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk,
 	ubi->wl_scheduled = 0;
 	spin_unlock(&ubi->wl_lock);
 	mutex_unlock(&ubi->move_mutex);
-	ubi_free_vid_hdr(ubi, vid_hdr);
+	up_read(&ubi->fm_eba_sem);
+	ubi_free_vid_buf(vidb);
 	return 0;
 }
 
@@ -1073,7 +1101,7 @@ static int __erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk)
 		int err1;
 
 		/* Re-schedule the LEB for erasure */
-		err1 = schedule_erase(ubi, e, vol_id, lnum, 0);
+		err1 = schedule_erase(ubi, e, vol_id, lnum, 0, false);
 		if (err1) {
 			wl_entry_destroy(ubi, e);
 			err = err1;
@@ -1254,7 +1282,7 @@ int ubi_wl_put_peb(struct ubi_device *ubi, int vol_id, int lnum,
 	}
 	spin_unlock(&ubi->wl_lock);
 
-	err = schedule_erase(ubi, e, vol_id, lnum, torture);
+	err = schedule_erase(ubi, e, vol_id, lnum, torture, false);
 	if (err) {
 		spin_lock(&ubi->wl_lock);
 		wl_tree_add(e, &ubi->used);
@@ -1545,7 +1573,7 @@ int ubi_wl_init(struct ubi_device *ubi, struct ubi_attach_info *ai)
 		e->pnum = aeb->pnum;
 		e->ec = aeb->ec;
 		ubi->lookuptbl[e->pnum] = e;
-		if (schedule_erase(ubi, e, aeb->vol_id, aeb->lnum, 0)) {
+		if (schedule_erase(ubi, e, aeb->vol_id, aeb->lnum, 0, false)) {
 			wl_entry_destroy(ubi, e);
 			goto out_free;
 		}
@@ -1624,7 +1652,7 @@ int ubi_wl_init(struct ubi_device *ubi, struct ubi_attach_info *ai)
 			e->ec = aeb->ec;
 			ubi_assert(!ubi->lookuptbl[e->pnum]);
 			ubi->lookuptbl[e->pnum] = e;
-			if (schedule_erase(ubi, e, aeb->vol_id, aeb->lnum, 0)) {
+			if (schedule_erase(ubi, e, aeb->vol_id, aeb->lnum, 0, false)) {
 				wl_entry_destroy(ubi, e);
 				goto out_free;
 			}

fs/ubifs/dir.c

@@ -301,6 +301,95 @@ static int ubifs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 	return err;
 }
 
+static int do_tmpfile(struct inode *dir, struct dentry *dentry,
+		      umode_t mode, struct inode **whiteout)
+{
+	struct inode *inode;
+	struct ubifs_info *c = dir->i_sb->s_fs_info;
+	struct ubifs_budget_req req = { .new_ino = 1, .new_dent = 1};
+	struct ubifs_budget_req ino_req = { .dirtied_ino = 1 };
+	struct ubifs_inode *ui, *dir_ui = ubifs_inode(dir);
+	int err, instantiated = 0;
+
+	/*
+	 * Budget request settings: new dirty inode, new direntry,
+	 * budget for dirtied inode will be released via writeback.
+	 */
+
+	dbg_gen("dent '%pd', mode %#hx in dir ino %lu",
+		dentry, mode, dir->i_ino);
+
+	err = ubifs_budget_space(c, &req);
+	if (err)
+		return err;
+
+	err = ubifs_budget_space(c, &ino_req);
+	if (err) {
+		ubifs_release_budget(c, &req);
+		return err;
+	}
+
+	inode = ubifs_new_inode(c, dir, mode);
+	if (IS_ERR(inode)) {
+		err = PTR_ERR(inode);
+		goto out_budg;
+	}
+	ui = ubifs_inode(inode);
+
+	if (whiteout) {
+		init_special_inode(inode, inode->i_mode, WHITEOUT_DEV);
+		ubifs_assert(inode->i_op == &ubifs_file_inode_operations);
+	}
+
+	err = ubifs_init_security(dir, inode, &dentry->d_name);
+	if (err)
+		goto out_inode;
+
+	mutex_lock(&ui->ui_mutex);
+	insert_inode_hash(inode);
+
+	if (whiteout) {
+		mark_inode_dirty(inode);
+		drop_nlink(inode);
+		*whiteout = inode;
+	} else {
+		d_tmpfile(dentry, inode);
+	}
+	ubifs_assert(ui->dirty);
+
+	instantiated = 1;
+	mutex_unlock(&ui->ui_mutex);
+
+	mutex_lock(&dir_ui->ui_mutex);
+	err = ubifs_jnl_update(c, dir, &dentry->d_name, inode, 1, 0);
+	if (err)
+		goto out_cancel;
+	mutex_unlock(&dir_ui->ui_mutex);
+
+	ubifs_release_budget(c, &req);
+
+	return 0;
+
+out_cancel:
+	mutex_unlock(&dir_ui->ui_mutex);
+out_inode:
+	make_bad_inode(inode);
+	if (!instantiated)
+		iput(inode);
+out_budg:
+	ubifs_release_budget(c, &req);
+	if (!instantiated)
+		ubifs_release_budget(c, &ino_req);
+	ubifs_err(c, "cannot create temporary file, error %d", err);
+	return err;
+}
+
+static int ubifs_tmpfile(struct inode *dir, struct dentry *dentry,
+			 umode_t mode)
+{
+	return do_tmpfile(dir, dentry, mode, NULL);
+}
+
 /**
  * vfs_dent_type - get VFS directory entry type.
  * @type: UBIFS directory entry type
@@ -927,37 +1016,43 @@ static int ubifs_symlink(struct inode *dir, struct dentry *dentry,
 }
 
 /**
- * lock_3_inodes - a wrapper for locking three UBIFS inodes.
+ * lock_4_inodes - a wrapper for locking three UBIFS inodes.
  * @inode1: first inode
  * @inode2: second inode
  * @inode3: third inode
+ * @inode4: fouth inode
  *
  * This function is used for 'ubifs_rename()' and @inode1 may be the same as
- * @inode2 whereas @inode3 may be %NULL.
+ * @inode2 whereas @inode3 and @inode4 may be %NULL.
  *
  * We do not implement any tricks to guarantee strict lock ordering, because
  * VFS has already done it for us on the @i_mutex. So this is just a simple
  * wrapper function.
  */
-static void lock_3_inodes(struct inode *inode1, struct inode *inode2,
-			  struct inode *inode3)
+static void lock_4_inodes(struct inode *inode1, struct inode *inode2,
+			  struct inode *inode3, struct inode *inode4)
 {
 	mutex_lock_nested(&ubifs_inode(inode1)->ui_mutex, WB_MUTEX_1);
 	if (inode2 != inode1)
 		mutex_lock_nested(&ubifs_inode(inode2)->ui_mutex, WB_MUTEX_2);
 	if (inode3)
 		mutex_lock_nested(&ubifs_inode(inode3)->ui_mutex, WB_MUTEX_3);
+	if (inode4)
+		mutex_lock_nested(&ubifs_inode(inode4)->ui_mutex, WB_MUTEX_4);
 }
 
 /**
- * unlock_3_inodes - a wrapper for unlocking three UBIFS inodes for rename.
+ * unlock_4_inodes - a wrapper for unlocking three UBIFS inodes for rename.
  * @inode1: first inode
  * @inode2: second inode
  * @inode3: third inode
+ * @inode4: fouth inode
  */
-static void unlock_3_inodes(struct inode *inode1, struct inode *inode2,
-			    struct inode *inode3)
+static void unlock_4_inodes(struct inode *inode1, struct inode *inode2,
+			    struct inode *inode3, struct inode *inode4)
 {
+	if (inode4)
+		mutex_unlock(&ubifs_inode(inode4)->ui_mutex);
 	if (inode3)
 		mutex_unlock(&ubifs_inode(inode3)->ui_mutex);
 	if (inode1 != inode2)
@@ -972,7 +1067,9 @@ static int ubifs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	struct ubifs_info *c = old_dir->i_sb->s_fs_info;
 	struct inode *old_inode = d_inode(old_dentry);
 	struct inode *new_inode = d_inode(new_dentry);
+	struct inode *whiteout = NULL;
 	struct ubifs_inode *old_inode_ui = ubifs_inode(old_inode);
+	struct ubifs_inode *whiteout_ui = NULL;
 	int err, release, sync = 0, move = (new_dir != old_dir);
 	int is_dir = S_ISDIR(old_inode->i_mode);
 	int unlink = !!new_inode;
@@ -997,15 +1094,13 @@ static int ubifs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	 * separately.
 	 */
 
-	dbg_gen("dent '%pd' ino %lu in dir ino %lu to dent '%pd' in dir ino %lu",
+	dbg_gen("dent '%pd' ino %lu in dir ino %lu to dent '%pd' in dir ino %lu flags 0x%x",
 		old_dentry, old_inode->i_ino, old_dir->i_ino,
-		new_dentry, new_dir->i_ino);
-	ubifs_assert(inode_is_locked(old_dir));
-	ubifs_assert(inode_is_locked(new_dir));
+		new_dentry, new_dir->i_ino, flags);
+
 	if (unlink)
 		ubifs_assert(inode_is_locked(new_inode));
 
-
 	if (unlink && is_dir) {
 		err = check_dir_empty(c, new_inode);
 		if (err)
@@ -1021,7 +1116,32 @@ static int ubifs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		return err;
 	}
 
-	lock_3_inodes(old_dir, new_dir, new_inode);
+	if (flags & RENAME_WHITEOUT) {
+		union ubifs_dev_desc *dev = NULL;
+
+		dev = kmalloc(sizeof(union ubifs_dev_desc), GFP_NOFS);
+		if (!dev) {
+			ubifs_release_budget(c, &req);
+			ubifs_release_budget(c, &ino_req);
+			return -ENOMEM;
+		}
+
+		err = do_tmpfile(old_dir, old_dentry, S_IFCHR | WHITEOUT_MODE, &whiteout);
+		if (err) {
+			ubifs_release_budget(c, &req);
+			ubifs_release_budget(c, &ino_req);
+			kfree(dev);
+			return err;
+		}
+
+		whiteout->i_state |= I_LINKABLE;
+		whiteout_ui = ubifs_inode(whiteout);
+		whiteout_ui->data = dev;
+		whiteout_ui->data_len = ubifs_encode_dev(dev, MKDEV(0, 0));
+		ubifs_assert(!whiteout_ui->dirty);
+	}
+
+	lock_4_inodes(old_dir, new_dir, new_inode, whiteout);
 
 	/*
 	 * Like most other Unix systems, set the @i_ctime for inodes on a
@@ -1091,12 +1211,34 @@ static int ubifs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		if (unlink && IS_SYNC(new_inode))
 			sync = 1;
 	}
-	err = ubifs_jnl_rename(c, old_dir, old_dentry, new_dir, new_dentry,
+
+	if (whiteout) {
+		struct ubifs_budget_req wht_req = { .dirtied_ino = 1,
+				.dirtied_ino_d = \
+				ALIGN(ubifs_inode(whiteout)->data_len, 8) };
+
+		err = ubifs_budget_space(c, &wht_req);
+		if (err) {
+			ubifs_release_budget(c, &req);
+			ubifs_release_budget(c, &ino_req);
+			kfree(whiteout_ui->data);
+			whiteout_ui->data_len = 0;
+			iput(whiteout);
+			return err;
+		}
+
+		inc_nlink(whiteout);
+		mark_inode_dirty(whiteout);
+		whiteout->i_state &= ~I_LINKABLE;
+		iput(whiteout);
+	}
+
+	err = ubifs_jnl_rename(c, old_dir, old_dentry, new_dir, new_dentry, whiteout,
 			       sync);
 	if (err)
 		goto out_cancel;
 
-	unlock_3_inodes(old_dir, new_dir, new_inode);
+	unlock_4_inodes(old_dir, new_dir, new_inode, whiteout);
 	ubifs_release_budget(c, &req);
 
 	mutex_lock(&old_inode_ui->ui_mutex);
@@ -1129,12 +1271,74 @@ static int ubifs_rename(struct inode *old_dir, struct dentry *old_dentry,
 				inc_nlink(old_dir);
 		}
 	}
-	unlock_3_inodes(old_dir, new_dir, new_inode);
+	if (whiteout) {
+		drop_nlink(whiteout);
+		iput(whiteout);
+	}
+	unlock_4_inodes(old_dir, new_dir, new_inode, whiteout);
 	ubifs_release_budget(c, &ino_req);
 	ubifs_release_budget(c, &req);
 	return err;
 }
 
+static int ubifs_xrename(struct inode *old_dir, struct dentry *old_dentry,
+			struct inode *new_dir, struct dentry *new_dentry)
+{
+	struct ubifs_info *c = old_dir->i_sb->s_fs_info;
+	struct ubifs_budget_req req = { .new_dent = 1, .mod_dent = 1,
+				.dirtied_ino = 2 };
+	int sync = IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir);
+	struct inode *fst_inode = d_inode(old_dentry);
+	struct inode *snd_inode = d_inode(new_dentry);
+	struct timespec time;
+	int err;
+
+	ubifs_assert(fst_inode && snd_inode);
+
+	lock_4_inodes(old_dir, new_dir, NULL, NULL);
+
+	time = ubifs_current_time(old_dir);
+	fst_inode->i_ctime = time;
+	snd_inode->i_ctime = time;
+	old_dir->i_mtime = old_dir->i_ctime = time;
+	new_dir->i_mtime = new_dir->i_ctime = time;
+
+	if (old_dir != new_dir) {
+		if (S_ISDIR(fst_inode->i_mode) && !S_ISDIR(snd_inode->i_mode)) {
+			inc_nlink(new_dir);
+			drop_nlink(old_dir);
+		}
+		else if (!S_ISDIR(fst_inode->i_mode) && S_ISDIR(snd_inode->i_mode)) {
+			drop_nlink(new_dir);
+			inc_nlink(old_dir);
+		}
+	}
+
+	err = ubifs_jnl_xrename(c, old_dir, old_dentry, new_dir, new_dentry,
+				sync);
+
+	unlock_4_inodes(old_dir, new_dir, NULL, NULL);
+	ubifs_release_budget(c, &req);
+
+	return err;
+}
+
+static int ubifs_rename2(struct inode *old_dir, struct dentry *old_dentry,
+			struct inode *new_dir, struct dentry *new_dentry,
+			unsigned int flags)
+{
+	if (flags & ~(RENAME_NOREPLACE | RENAME_WHITEOUT | RENAME_EXCHANGE))
+		return -EINVAL;
+
+	ubifs_assert(inode_is_locked(old_dir));
+	ubifs_assert(inode_is_locked(new_dir));
+
+	if (flags & RENAME_EXCHANGE)
+		return ubifs_xrename(old_dir, old_dentry, new_dir, new_dentry);
+
+	return ubifs_rename(old_dir, old_dentry, new_dir, new_dentry, flags);
+}
+
 int ubifs_getattr(struct vfsmount *mnt, struct dentry *dentry,
 		  struct kstat *stat)
 {
@@ -1183,13 +1387,14 @@ const struct inode_operations ubifs_dir_inode_operations = {
 	.mkdir       = ubifs_mkdir,
 	.rmdir       = ubifs_rmdir,
 	.mknod       = ubifs_mknod,
-	.rename     = ubifs_rename,
+	.rename      = ubifs_rename2,
 	.setattr     = ubifs_setattr,
 	.getattr     = ubifs_getattr,
 	.listxattr   = ubifs_listxattr,
 #ifdef CONFIG_UBIFS_ATIME_SUPPORT
 	.update_time = ubifs_update_time,
 #endif
+	.tmpfile     = ubifs_tmpfile,
 };
 
 const struct file_operations ubifs_dir_operations = {

fs/ubifs/file.c

@@ -1397,7 +1397,7 @@ int ubifs_update_time(struct inode *inode, struct timespec *time,
 #endif
 
 /**
- * update_ctime - update mtime and ctime of an inode.
+ * update_mctime - update mtime and ctime of an inode.
  * @inode: inode to update
  *
  * This function updates mtime and ctime of the inode if it is not equivalent to

fs/ubifs/gc.c

@@ -113,7 +113,7 @@ static int switch_gc_head(struct ubifs_info *c)
  * data_nodes_cmp - compare 2 data nodes.
  * @priv: UBIFS file-system description object
  * @a: first data node
- * @a: second data node
+ * @b: second data node
  *
  * This function compares data nodes @a and @b. Returns %1 if @a has greater
  * inode or block number, and %-1 otherwise.

fs/ubifs/journal.c

@@ -907,6 +907,147 @@ int ubifs_jnl_delete_inode(struct ubifs_info *c, const struct inode *inode)
 	return err;
 }
 
+/**
+ * ubifs_jnl_xrename - cross rename two directory entries.
+ * @c: UBIFS file-system description object
+ * @fst_dir: parent inode of 1st directory entry to exchange
+ * @fst_dentry: 1st directory entry to exchange
+ * @snd_dir: parent inode of 2nd directory entry to exchange
+ * @snd_dentry: 2nd directory entry to exchange
+ * @sync: non-zero if the write-buffer has to be synchronized
+ *
+ * This function implements the cross rename operation which may involve
+ * writing 2 inodes and 2 directory entries. It marks the written inodes as clean
+ * and returns zero on success. In case of failure, a negative error code is
+ * returned.
+ */
+int ubifs_jnl_xrename(struct ubifs_info *c, const struct inode *fst_dir,
+		      const struct dentry *fst_dentry,
+		      const struct inode *snd_dir,
+		      const struct dentry *snd_dentry, int sync)
+{
+	union ubifs_key key;
+	struct ubifs_dent_node *dent1, *dent2;
+	int err, dlen1, dlen2, lnum, offs, len, plen = UBIFS_INO_NODE_SZ;
+	int aligned_dlen1, aligned_dlen2;
+	int twoparents = (fst_dir != snd_dir);
+	const struct inode *fst_inode = d_inode(fst_dentry);
+	const struct inode *snd_inode = d_inode(snd_dentry);
+	void *p;
+
+	dbg_jnl("dent '%pd' in dir ino %lu between dent '%pd' in dir ino %lu",
+		fst_dentry, fst_dir->i_ino, snd_dentry, snd_dir->i_ino);
+
+	ubifs_assert(ubifs_inode(fst_dir)->data_len == 0);
+	ubifs_assert(ubifs_inode(snd_dir)->data_len == 0);
+	ubifs_assert(mutex_is_locked(&ubifs_inode(fst_dir)->ui_mutex));
+	ubifs_assert(mutex_is_locked(&ubifs_inode(snd_dir)->ui_mutex));
+
+	dlen1 = UBIFS_DENT_NODE_SZ + snd_dentry->d_name.len + 1;
+	dlen2 = UBIFS_DENT_NODE_SZ + fst_dentry->d_name.len + 1;
+	aligned_dlen1 = ALIGN(dlen1, 8);
+	aligned_dlen2 = ALIGN(dlen2, 8);
+
+	len = aligned_dlen1 + aligned_dlen2 + ALIGN(plen, 8);
+	if (twoparents)
+		len += plen;
+
+	dent1 = kmalloc(len, GFP_NOFS);
+	if (!dent1)
+		return -ENOMEM;
+
+	/* Make reservation before allocating sequence numbers */
+	err = make_reservation(c, BASEHD, len);
+	if (err)
+		goto out_free;
+
+	/* Make new dent for 1st entry */
+	dent1->ch.node_type = UBIFS_DENT_NODE;
+	dent_key_init_flash(c, &dent1->key, snd_dir->i_ino, &snd_dentry->d_name);
+	dent1->inum = cpu_to_le64(fst_inode->i_ino);
+	dent1->type = get_dent_type(fst_inode->i_mode);
+	dent1->nlen = cpu_to_le16(snd_dentry->d_name.len);
+	memcpy(dent1->name, snd_dentry->d_name.name, snd_dentry->d_name.len);
+	dent1->name[snd_dentry->d_name.len] = '\0';
+	zero_dent_node_unused(dent1);
+	ubifs_prep_grp_node(c, dent1, dlen1, 0);
+
+	/* Make new dent for 2nd entry */
+	dent2 = (void *)dent1 + aligned_dlen1;
+	dent2->ch.node_type = UBIFS_DENT_NODE;
+	dent_key_init_flash(c, &dent2->key, fst_dir->i_ino, &fst_dentry->d_name);
+	dent2->inum = cpu_to_le64(snd_inode->i_ino);
+	dent2->type = get_dent_type(snd_inode->i_mode);
+	dent2->nlen = cpu_to_le16(fst_dentry->d_name.len);
+	memcpy(dent2->name, fst_dentry->d_name.name, fst_dentry->d_name.len);
+	dent2->name[fst_dentry->d_name.len] = '\0';
+	zero_dent_node_unused(dent2);
+	ubifs_prep_grp_node(c, dent2, dlen2, 0);
+
+	p = (void *)dent2 + aligned_dlen2;
+	if (!twoparents)
+		pack_inode(c, p, fst_dir, 1);
+	else {
+		pack_inode(c, p, fst_dir, 0);
+		p += ALIGN(plen, 8);
+		pack_inode(c, p, snd_dir, 1);
+	}
+
+	err = write_head(c, BASEHD, dent1, len, &lnum, &offs, sync);
+	if (err)
+		goto out_release;
+	if (!sync) {
+		struct ubifs_wbuf *wbuf = &c->jheads[BASEHD].wbuf;
+
+		ubifs_wbuf_add_ino_nolock(wbuf, fst_dir->i_ino);
+		ubifs_wbuf_add_ino_nolock(wbuf, snd_dir->i_ino);
+	}
+	release_head(c, BASEHD);
+
+	dent_key_init(c, &key, snd_dir->i_ino, &snd_dentry->d_name);
+	err = ubifs_tnc_add_nm(c, &key, lnum, offs, dlen1, &snd_dentry->d_name);
+	if (err)
+		goto out_ro;
+
+	offs += aligned_dlen1;
+	dent_key_init(c, &key, fst_dir->i_ino, &fst_dentry->d_name);
+	err = ubifs_tnc_add_nm(c, &key, lnum, offs, dlen2, &fst_dentry->d_name);
+	if (err)
+		goto out_ro;
+
+	offs += aligned_dlen2;
+
+	ino_key_init(c, &key, fst_dir->i_ino);
+	err = ubifs_tnc_add(c, &key, lnum, offs, plen);
+	if (err)
+		goto out_ro;
+
+	if (twoparents) {
+		offs += ALIGN(plen, 8);
+		ino_key_init(c, &key, snd_dir->i_ino);
+		err = ubifs_tnc_add(c, &key, lnum, offs, plen);
+		if (err)
+			goto out_ro;
+	}
+
+	finish_reservation(c);
+
+	mark_inode_clean(c, ubifs_inode(fst_dir));
+	if (twoparents)
+		mark_inode_clean(c, ubifs_inode(snd_dir));
+	kfree(dent1);
+	return 0;
+
+out_release:
+	release_head(c, BASEHD);
+out_ro:
+	ubifs_ro_mode(c, err);
+	finish_reservation(c);
+out_free:
+	kfree(dent1);
+	return err;
+}
+
 /**
  * ubifs_jnl_rename - rename a directory entry.
  * @c: UBIFS file-system description object
@@ -917,14 +1058,15 @@ int ubifs_jnl_delete_inode(struct ubifs_info *c, const struct inode *inode)
  * @sync: non-zero if the write-buffer has to be synchronized
  *
  * This function implements the re-name operation which may involve writing up
- * to 3 inodes and 2 directory entries. It marks the written inodes as clean
+ * to 4 inodes and 2 directory entries. It marks the written inodes as clean
  * and returns zero on success. In case of failure, a negative error code is
  * returned.
  */
 int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir,
 		     const struct dentry *old_dentry,
 		     const struct inode *new_dir,
-		     const struct dentry *new_dentry, int sync)
+		     const struct dentry *new_dentry,
+		     const struct inode *whiteout, int sync)
 {
 	void *p;
 	union ubifs_key key;
@@ -958,7 +1100,7 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir,
 	aligned_dlen1 = ALIGN(dlen1, 8);
 	aligned_dlen2 = ALIGN(dlen2, 8);
 	len = aligned_dlen1 + aligned_dlen2 + ALIGN(ilen, 8) + ALIGN(plen, 8);
-	if (old_dir != new_dir)
+	if (move)
 		len += plen;
 	dent = kmalloc(len, GFP_NOFS);
 	if (!dent)
@@ -980,13 +1122,19 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir,
 	zero_dent_node_unused(dent);
 	ubifs_prep_grp_node(c, dent, dlen1, 0);
 
-	/* Make deletion dent */
 	dent2 = (void *)dent + aligned_dlen1;
 	dent2->ch.node_type = UBIFS_DENT_NODE;
 	dent_key_init_flash(c, &dent2->key, old_dir->i_ino,
 			    &old_dentry->d_name);
+
+	if (whiteout) {
+		dent2->inum = cpu_to_le64(whiteout->i_ino);
+		dent2->type = get_dent_type(whiteout->i_mode);
+	} else {
+		/* Make deletion dent */
 		dent2->inum = 0;
 		dent2->type = DT_UNKNOWN;
+	}
 	dent2->nlen = cpu_to_le16(old_dentry->d_name.len);
 	memcpy(dent2->name, old_dentry->d_name.name, old_dentry->d_name.len);
 	dent2->name[old_dentry->d_name.len] = '\0';
@@ -1035,6 +1183,15 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir,
 	if (err)
 		goto out_ro;
 
+	offs += aligned_dlen1;
+	if (whiteout) {
+		dent_key_init(c, &key, old_dir->i_ino, &old_dentry->d_name);
+		err = ubifs_tnc_add_nm(c, &key, lnum, offs, dlen2, &old_dentry->d_name);
+		if (err)
+			goto out_ro;
+
+		ubifs_delete_orphan(c, whiteout->i_ino);
+	} else {
 		err = ubifs_add_dirt(c, lnum, dlen2);
 		if (err)
 			goto out_ro;
@@ -1043,8 +1200,9 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir,
 		err = ubifs_tnc_remove_nm(c, &key, &old_dentry->d_name);
 		if (err)
 			goto out_ro;
+	}
 
-	offs += aligned_dlen1 + aligned_dlen2;
+	offs += aligned_dlen2;
 	if (new_inode) {
 		ino_key_init(c, &key, new_inode->i_ino);
 		err = ubifs_tnc_add(c, &key, lnum, offs, ilen);
@@ -1058,7 +1216,7 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir,
 	if (err)
 		goto out_ro;
 
-	if (old_dir != new_dir) {
+	if (move) {
 		offs += ALIGN(plen, 8);
 		ino_key_init(c, &key, new_dir->i_ino);
 		err = ubifs_tnc_add(c, &key, lnum, offs, plen);

fs/ubifs/lprops.c

@@ -636,7 +636,7 @@ const struct ubifs_lprops *ubifs_change_lp(struct ubifs_info *c,
 /**
  * ubifs_get_lp_stats - get lprops statistics.
  * @c: UBIFS file-system description object
- * @st: return statistics
+ * @lst: return statistics
  */
 void ubifs_get_lp_stats(struct ubifs_info *c, struct ubifs_lp_stats *lst)
 {

fs/ubifs/lpt_commit.c

@@ -34,7 +34,6 @@ static int dbg_populate_lsave(struct ubifs_info *c);
 
 /**
  * first_dirty_cnode - find first dirty cnode.
- * @c: UBIFS file-system description object
  * @nnode: nnode at which to start
  *
  * This function returns the first dirty cnode or %NULL if there is not one.
@@ -1623,7 +1622,6 @@ static int dbg_is_node_dirty(struct ubifs_info *c, int node_type, int lnum,
  * dbg_check_ltab_lnum - check the ltab for a LPT LEB number.
  * @c: the UBIFS file-system description object
  * @lnum: LEB number where node was written
- * @offs: offset where node was written
  *
  * This function returns %0 on success and a negative error code on failure.
  */
@@ -1870,7 +1868,7 @@ int dbg_chk_lpt_sz(struct ubifs_info *c, int action, int len)
 }
 
 /**
- * ubifs_dump_lpt_leb - dump an LPT LEB.
+ * dump_lpt_leb - dump an LPT LEB.
  * @c: UBIFS file-system description object
  * @lnum: LEB number to dump
  *

fs/ubifs/replay.c

@@ -267,7 +267,7 @@ static int apply_replay_entry(struct ubifs_info *c, struct replay_entry *r)
  * replay_entries_cmp - compare 2 replay entries.
  * @priv: UBIFS file-system description object
  * @a: first replay entry
- * @a: second replay entry
+ * @b: second replay entry
  *
  * This is a comparios function for 'list_sort()' which compares 2 replay
  * entries @a and @b by comparing their sequence numer.  Returns %1 if @a has

fs/ubifs/ubifs.h

@@ -157,6 +157,7 @@ enum {
 	WB_MUTEX_1 = 0,
 	WB_MUTEX_2 = 1,
 	WB_MUTEX_3 = 2,
+	WB_MUTEX_4 = 3,
 };
 
 /*
@@ -1520,10 +1521,15 @@ int ubifs_jnl_write_data(struct ubifs_info *c, const struct inode *inode,
 			 const union ubifs_key *key, const void *buf, int len);
 int ubifs_jnl_write_inode(struct ubifs_info *c, const struct inode *inode);
 int ubifs_jnl_delete_inode(struct ubifs_info *c, const struct inode *inode);
+int ubifs_jnl_xrename(struct ubifs_info *c, const struct inode *fst_dir,
+		      const struct dentry *fst_dentry,
+		      const struct inode *snd_dir,
+		      const struct dentry *snd_dentry, int sync);
 int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir,
 		     const struct dentry *old_dentry,
 		     const struct inode *new_dir,
-		     const struct dentry *new_dentry, int sync);
+		     const struct dentry *new_dentry,
+		     const struct inode *whiteout, int sync);
 int ubifs_jnl_truncate(struct ubifs_info *c, const struct inode *inode,
 		       loff_t old_size, loff_t new_size);
 int ubifs_jnl_delete_xattr(struct ubifs_info *c, const struct inode *host,

fs/ubifs/xattr.c

@@ -200,6 +200,7 @@ static int change_xattr(struct ubifs_info *c, struct inode *host,
 	struct ubifs_inode *host_ui = ubifs_inode(host);
 	struct ubifs_inode *ui = ubifs_inode(inode);
 	void *buf = NULL;
+	int old_size;
 	struct ubifs_budget_req req = { .dirtied_ino = 2,
 		.dirtied_ino_d = ALIGN(size, 8) + ALIGN(host_ui->data_len, 8) };
 
@@ -217,12 +218,13 @@ static int change_xattr(struct ubifs_info *c, struct inode *host,
 	kfree(ui->data);
 	ui->data = buf;
 	inode->i_size = ui->ui_size = size;
+	old_size = ui->data_len;
 	ui->data_len = size;
 	mutex_unlock(&ui->ui_mutex);
 
 	mutex_lock(&host_ui->ui_mutex);
 	host->i_ctime = ubifs_current_time(host);
-	host_ui->xattr_size -= CALC_XATTR_BYTES(ui->data_len);
+	host_ui->xattr_size -= CALC_XATTR_BYTES(old_size);
 	host_ui->xattr_size += CALC_XATTR_BYTES(size);
 
 	/*
@@ -241,7 +243,7 @@ static int change_xattr(struct ubifs_info *c, struct inode *host,
 
 out_cancel:
 	host_ui->xattr_size -= CALC_XATTR_BYTES(size);
-	host_ui->xattr_size += CALC_XATTR_BYTES(ui->data_len);
+	host_ui->xattr_size += CALC_XATTR_BYTES(old_size);
 	mutex_unlock(&host_ui->ui_mutex);
 	make_bad_inode(inode);
 out_free: