firmware/br-ext-chip-allwinner/board/v83x/kernel/patches/00000-fs_pstore_blkzone.c.patch

diff -drupN a/fs/pstore/blkzone.c b/fs/pstore/blkzone.c
--- a/fs/pstore/blkzone.c	1970-01-01 03:00:00.000000000 +0300
+++ b/fs/pstore/blkzone.c	2022-06-12 05:28:14.000000000 +0300
@@ -0,0 +1,1314 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *
+ * blkzone.c: Block device Oops/Panic logger
+ *
+ * Copyright (C) 2019 liaoweixiong <liaoweixiong@gallwinnertech.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#define MODNAME "pstore-blk"
+#define pr_fmt(fmt) MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/blkdev.h>
+#include <linux/pstore.h>
+#include <linux/mount.h>
+#include <linux/printk.h>
+#include <linux/fs.h>
+#include <linux/pstore_blk.h>
+#include <linux/kdev_t.h>
+#include <linux/device.h>
+#include <linux/namei.h>
+#include <linux/fcntl.h>
+#include <linux/uio.h>
+#include <linux/writeback.h>
+
+/**
+ * struct blkz_head - head of zone to flush to storage
+ *
+ * @sig: signature to indicate header (BLK_SIG xor BLKZONE-type value)
+ * @datalen: length of data in @data
+ * @start: offset into @data where the beginning of the stored bytes begin
+ * @data: zone data.
+ */
+struct blkz_buffer {
+#define BLK_SIG (0x43474244) /* DBGC */
+	uint32_t sig;
+	atomic_t datalen;
+	atomic_t start;
+	uint8_t data[];
+};
+
+/**
+ * struct blkz_dmesg_header: dmesg information
+ *
+ * @magic: magic num for dmesg header
+ * @time: trigger time
+ * @compressed: whether conpressed
+ * @count: oops/panic counter
+ * @reason: identify oops or panic
+ */
+struct blkz_dmesg_header {
+#define DMESG_HEADER_MAGIC 0x4dfc3ae5
+	uint32_t magic;
+	struct timespec64 time;
+	bool compressed;
+	uint32_t counter;
+	enum kmsg_dump_reason reason;
+	uint8_t data[0];
+};
+
+/**
+ * struct blkz_zone - zone information
+ * @off:
+ *	zone offset of block device
+ * @type:
+ *	frontent type for this zone
+ * @name:
+ *	frontent name for this zone
+ * @buffer:
+ *	pointer to data buffer managed by this zone
+ * @oldbuf:
+ *	pointer to old data buffer. It is used for single zone such as pmsg,
+ *	saving the old buffer.
+ * @buffer_size:
+ *	bytes in @buffer->data
+ * @should_recover:
+ *	should recover from storage
+ * @dirty:
+ *	mark whether the data in @buffer are dirty (not flush to storage yet)
+ */
+struct blkz_zone {
+	unsigned long off;
+	const char *name;
+	enum pstore_type_id type;
+
+	struct blkz_buffer *buffer;
+	struct blkz_buffer *oldbuf;
+	size_t buffer_size;
+	bool should_recover;
+	atomic_t dirty;
+};
+
+struct blkz_context {
+	struct blkz_zone **dbzs;	/* dmesg block zones */
+	struct blkz_zone *pbz;		/* Pmsg block zone */
+	unsigned int dmesg_max_cnt;
+	unsigned int dmesg_read_cnt;
+	unsigned int pmsg_read_cnt;
+	unsigned int dmesg_write_cnt;
+	/*
+	 * the counter should be recovered when do recovery
+	 * It records the oops/panic times after burning rather than booting.
+	 */
+	unsigned int oops_counter;
+	unsigned int panic_counter;
+	unsigned int oom_counter;
+	atomic_t recovery;
+	atomic_t on_panic;
+
+	/*
+	 * bzinfo_lock just protects "bzinfo" during calls to
+	 * blkz_register/blkz_unregister
+	 */
+	spinlock_t bzinfo_lock;
+	struct blkz_info *bzinfo;
+	struct pstore_info pstore;
+	struct block_device *bdev;
+};
+static struct blkz_context blkz_cxt;
+
+enum blkz_flush_mode {
+	FLUSH_NONE = 0,
+	FLUSH_PART,
+	FLUSH_META,
+	FLUSH_ALL,
+};
+
+static inline int buffer_datalen(struct blkz_zone *zone)
+{
+	return atomic_read(&zone->buffer->datalen);
+}
+
+static inline int buffer_start(struct blkz_zone *zone)
+{
+	return atomic_read(&zone->buffer->start);
+}
+
+static inline bool is_on_panic(void)
+{
+	struct blkz_context *cxt = &blkz_cxt;
+
+	return atomic_read(&cxt->on_panic);
+}
+
+static int blkz_zone_read(struct blkz_zone *zone, char *buf,
+		size_t len, unsigned long off)
+{
+	if (!buf || !zone->buffer)
+		return -EINVAL;
+	if (off > zone->buffer_size)
+		return -EINVAL;
+	len = min_t(size_t, len, zone->buffer_size - off);
+	memcpy(buf, zone->buffer->data + off, len);
+	return 0;
+}
+
+static int blkz_zone_write(struct blkz_zone *zone,
+		enum blkz_flush_mode flush_mode, const char *buf,
+		size_t len, unsigned long off)
+{
+	struct blkz_info *info = blkz_cxt.bzinfo;
+	ssize_t wcnt;
+	ssize_t (*writeop)(const char *buf, size_t bytes, loff_t pos);
+	size_t wlen;
+
+	if (off > zone->buffer_size)
+		return -EINVAL;
+	wlen = min_t(size_t, len, zone->buffer_size - off);
+	if (flush_mode == FLUSH_PART || flush_mode == FLUSH_ALL) {
+		if (buf && wlen) {
+			memcpy(zone->buffer->data + off, buf, wlen);
+			atomic_set(&zone->buffer->datalen, wlen + off);
+		}
+	}
+
+	writeop = is_on_panic() ? info->panic_write : info->write;
+	if (!writeop)
+		return -EINVAL;
+
+	switch (flush_mode) {
+	case FLUSH_NONE:
+		return 0;
+	case FLUSH_PART:
+		wcnt = writeop((const char *)zone->buffer->data + off, wlen,
+				zone->off + sizeof(*zone->buffer) + off);
+		if (wcnt != wlen)
+			goto set_dirty;
+	case FLUSH_META:
+		wlen = sizeof(struct blkz_buffer);
+		wcnt = writeop((const char *)zone->buffer, wlen, zone->off);
+		if (wcnt != wlen)
+			goto set_dirty;
+		break;
+	case FLUSH_ALL:
+		wlen = buffer_datalen(zone) + sizeof(*zone->buffer);
+		wcnt = writeop((const char *)zone->buffer, wlen, zone->off);
+		if (wcnt != wlen)
+			goto set_dirty;
+		break;
+	}
+
+	return 0;
+set_dirty:
+	pr_err("write failed with %zd returned, set dirty\n", wcnt);
+	atomic_set(&zone->dirty, true);
+	return -EBUSY;
+}
+
+static int blkz_flush_dirty_zone(struct blkz_zone *zone)
+{
+	int ret;
+
+	if (!zone)
+		return -EINVAL;
+
+	if (!atomic_read(&zone->dirty))
+		return 0;
+
+	pr_info("try to flush dirty %s zone with offset %lu\n",
+			zone->name, zone->off);
+	ret = blkz_zone_write(zone, FLUSH_ALL, NULL, 0, 0);
+	if (!ret)
+		atomic_set(&zone->dirty, false);
+	return ret;
+}
+
+static int blkz_flush_dirty_zones(struct blkz_zone **zones, unsigned int cnt)
+{
+	int i, ret;
+	struct blkz_zone *zone;
+
+	if (!zones)
+		return -EINVAL;
+
+	for (i = 0; i < cnt; i++) {
+		zone = zones[i];
+		if (!zone)
+			return -EINVAL;
+		ret = blkz_flush_dirty_zone(zone);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
+/*
+ * blkz_move_zone: move data from a old zone to a new zone
+ *
+ * @old: the old zone
+ * @new: the new zone
+ *
+ * NOTE:
+ *	Call blkz_zone_write to copy and flush data. If it failed, we
+ *	should reset new->dirty, because the new zone not really dirty.
+ */
+static int blkz_move_zone(struct blkz_zone *old, struct blkz_zone *new)
+{
+	const char *data = (const char *)old->buffer->data;
+	int ret;
+
+	ret = blkz_zone_write(new, FLUSH_ALL, data, buffer_datalen(old), 0);
+	if (ret) {
+		atomic_set(&new->buffer->datalen, 0);
+		atomic_set(&new->dirty, false);
+		return ret;
+	}
+	atomic_set(&old->buffer->datalen, 0);
+	return 0;
+}
+
+static int blkz_recover_dmesg_data(struct blkz_context *cxt)
+{
+	struct blkz_info *info = cxt->bzinfo;
+	struct blkz_zone *zone = NULL;
+	struct blkz_buffer *buf;
+	unsigned long i;
+	ssize_t (*readop)(char *buf, size_t bytes, loff_t pos);
+	ssize_t rcnt;
+
+	readop = is_on_panic() ? info->panic_read : info->read;
+	if (!readop)
+		return -EINVAL;
+
+	for (i = 0; i < cxt->dmesg_max_cnt; i++) {
+		zone = cxt->dbzs[i];
+		if (unlikely(!zone))
+			return -EINVAL;
+		if (atomic_read(&zone->dirty)) {
+			unsigned int wcnt = cxt->dmesg_write_cnt;
+			struct blkz_zone *new = cxt->dbzs[wcnt];
+			int ret;
+
+			ret = blkz_move_zone(zone, new);
+			if (ret) {
+				pr_err("move zone from %lu to %d failed\n",
+						i, wcnt);
+				return ret;
+			}
+			cxt->dmesg_write_cnt = (wcnt + 1) % cxt->dmesg_max_cnt;
+		}
+		if (!zone->should_recover)
+			continue;
+		buf = zone->buffer;
+		rcnt = readop((char *)buf, zone->buffer_size + sizeof(*buf),
+				zone->off);
+		if (rcnt != zone->buffer_size + sizeof(*buf))
+			return (int)rcnt < 0 ? (int)rcnt : -EIO;
+	}
+	return 0;
+}
+
+/**
+ * blkz_recover_dmesg_meta: recover metadata of dmesg
+ *
+ * Recover metadata as follow:
+ * @cxt->dmesg_write_cnt
+ * @cxt->oops_counter
+ * @cxt->panic_counter
+ */
+static int blkz_recover_dmesg_meta(struct blkz_context *cxt)
+{
+	struct blkz_info *info = cxt->bzinfo;
+	struct blkz_zone *zone;
+	size_t rcnt, len;
+	struct blkz_buffer *buf;
+	struct blkz_dmesg_header *hdr;
+	ssize_t (*readop)(char *buf, size_t bytes, loff_t pos);
+	struct timespec64 time = {0};
+	unsigned long i;
+	/*
+	 * Recover may on panic, we can't allocate any memory by kmalloc.
+	 * So, we use local array instead.
+	 */
+	char buffer_header[sizeof(*buf) + sizeof(*hdr)] = {0};
+
+	readop = is_on_panic() ? info->panic_read : info->read;
+	if (!readop)
+		return -EINVAL;
+
+	len = sizeof(*buf) + sizeof(*hdr);
+	buf = (struct blkz_buffer *)buffer_header;
+	for (i = 0; i < cxt->dmesg_max_cnt; i++) {
+		zone = cxt->dbzs[i];
+		if (unlikely(!zone))
+			return -EINVAL;
+
+		rcnt = readop((char *)buf, len, zone->off);
+		if (rcnt != len)
+			return (int)rcnt < 0 ? (int)rcnt : -EIO;
+
+		/*
+		 * If sig NOT match, it means this zone never used before,
+		 * because we write one by one, and we never modify sig even
+		 * when erase. So, we do not need to check next one.
+		 */
+		if (buf->sig != zone->buffer->sig) {
+			cxt->dmesg_write_cnt = i;
+			pr_debug("no valid data in dmesg zone %lu\n", i);
+			break;
+		}
+
+		if (zone->buffer_size < atomic_read(&buf->datalen)) {
+			pr_info("found overtop zone: %s: id %lu, off %lu, size %zu\n",
+					zone->name, i, zone->off,
+					zone->buffer_size);
+			continue;
+		}
+
+		hdr = (struct blkz_dmesg_header *)buf->data;
+		if (hdr->magic != DMESG_HEADER_MAGIC) {
+			pr_info("found invalid zone: %s: id %lu, off %lu, size %zu\n",
+					zone->name, i, zone->off,
+					zone->buffer_size);
+			continue;
+		}
+
+		/*
+		 * we get the newest zone, and the next one must be the oldest
+		 * or unused zone, because we do write one by one like a circle.
+		 */
+		if (hdr->time.tv_sec >= time.tv_sec) {
+			time.tv_sec = hdr->time.tv_sec;
+			cxt->dmesg_write_cnt = (i + 1) % cxt->dmesg_max_cnt;
+		}
+
+		if (hdr->reason == KMSG_DUMP_OOPS)
+			cxt->oops_counter =
+				max(cxt->oops_counter, hdr->counter);
+		else
+			cxt->panic_counter =
+				max(cxt->panic_counter, hdr->counter);
+
+		if (!atomic_read(&buf->datalen)) {
+			pr_debug("found erased zone: %s: id %ld, off %lu, size %zu, datalen %d\n",
+					zone->name, i, zone->off,
+					zone->buffer_size,
+					atomic_read(&buf->datalen));
+			continue;
+		}
+
+		if (!is_on_panic())
+			zone->should_recover = true;
+		pr_debug("found nice zone: %s: id %ld, off %lu, size %zu, datalen %d\n",
+				zone->name, i, zone->off,
+				zone->buffer_size, atomic_read(&buf->datalen));
+	}
+
+	return 0;
+}
+
+static int blkz_recover_dmesg(struct blkz_context *cxt)
+{
+	int ret;
+
+	if (!cxt->dbzs)
+		return 0;
+
+	ret = blkz_recover_dmesg_meta(cxt);
+	if (ret)
+		goto recover_fail;
+
+	ret = blkz_recover_dmesg_data(cxt);
+	if (ret)
+		goto recover_fail;
+
+	return 0;
+recover_fail:
+	pr_debug("recover dmesg failed\n");
+	return ret;
+}
+
+static int blkz_recover_pmsg(struct blkz_context *cxt)
+{
+	struct blkz_info *info = cxt->bzinfo;
+	struct blkz_buffer *oldbuf;
+	struct blkz_zone *zone = NULL;
+	ssize_t (*readop)(char *buf, size_t bytes, loff_t pos);
+	int ret = 0;
+	ssize_t rcnt, len;
+
+	zone = cxt->pbz;
+	if (!zone || zone->oldbuf)
+		return 0;
+
+	if (is_on_panic())
+		goto out;
+
+	readop = info->read;
+	if (unlikely(!readop))
+		return -EINVAL;
+
+	len = zone->buffer_size + sizeof(*oldbuf);
+	oldbuf = kzalloc(len, GFP_KERNEL);
+	if (!oldbuf)
+		return -ENOMEM;
+
+	rcnt = readop((char *)oldbuf, len, zone->off);
+	if (rcnt != len) {
+		pr_debug("recover pmsg failed\n");
+		ret = (int)rcnt < 0 ? (int)rcnt : -EIO;
+		goto free_oldbuf;
+	}
+
+	if (oldbuf->sig != zone->buffer->sig) {
+		pr_debug("no valid data in zone %s\n", zone->name);
+		goto free_oldbuf;
+	}
+
+	if (zone->buffer_size < atomic_read(&oldbuf->datalen) ||
+		zone->buffer_size < atomic_read(&oldbuf->start)) {
+		pr_info("found overtop zone: %s: off %lu, size %zu\n",
+				zone->name, zone->off, zone->buffer_size);
+		goto free_oldbuf;
+	}
+
+	if (!atomic_read(&oldbuf->datalen)) {
+		pr_debug("found erased zone: %s: id 0, off %lu, size %zu, datalen %d\n",
+				zone->name, zone->off, zone->buffer_size,
+				atomic_read(&oldbuf->datalen));
+		kfree(oldbuf);
+		goto out;
+	}
+
+	pr_debug("found nice zone: %s: id 0, off %lu, size %zu, datalen %d\n",
+			zone->name, zone->off, zone->buffer_size,
+			atomic_read(&oldbuf->datalen));
+	zone->oldbuf = oldbuf;
+out:
+	blkz_flush_dirty_zone(zone);
+	return 0;
+
+free_oldbuf:
+	kfree(oldbuf);
+	return ret;
+}
+
+static inline int blkz_recovery(struct blkz_context *cxt)
+{
+	int ret = -EBUSY;
+
+	if (atomic_read(&cxt->recovery))
+		return 0;
+
+	ret = blkz_recover_dmesg(cxt);
+	if (ret)
+		goto recover_fail;
+
+	ret = blkz_recover_pmsg(cxt);
+	if (ret)
+		goto recover_fail;
+
+	atomic_set(&cxt->recovery, 1);
+	pr_debug("recover end!\n");
+	return 0;
+
+recover_fail:
+	pr_debug("recovery failed, handle buffer\n");
+	return ret;
+}
+
+static int blkz_pstore_open(struct pstore_info *psi)
+{
+	struct blkz_context *cxt = psi->data;
+
+	cxt->dmesg_read_cnt = 0;
+	return 0;
+}
+
+static inline bool blkz_old_ok(struct blkz_zone *zone)
+{
+	if (zone && zone->oldbuf && atomic_read(&zone->oldbuf->datalen))
+		return true;
+	return false;
+}
+
+static inline bool blkz_ok(struct blkz_zone *zone)
+{
+	if (zone && zone->buffer && buffer_datalen(zone))
+		return true;
+	return false;
+}
+
+static int blkz_pstore_erase(struct pstore_record *record)
+{
+	struct blkz_context *cxt = record->psi->data;
+	struct blkz_zone *zone = NULL;
+
+	if (record->type == PSTORE_TYPE_DMESG) {
+		zone = cxt->dbzs[record->id];
+		if (unlikely(!blkz_ok(zone)))
+			return 0;
+
+		atomic_set(&zone->buffer->datalen, 0);
+		return blkz_zone_write(zone, FLUSH_META, NULL, 0, 0);
+	} else if (record->type == PSTORE_TYPE_PMSG) {
+		zone = cxt->pbz;
+		if (unlikely(!blkz_old_ok(zone)))
+			return 0;
+
+		kfree(zone->oldbuf);
+		zone->oldbuf = NULL;
+		/**
+		 * if there are new data in zone buffer, that means the old data
+		 * are already invalid. It is no need to flush 0 (erase) to
+		 * block device.
+		 */
+		if (!buffer_datalen(zone))
+			return blkz_zone_write(zone, FLUSH_META, NULL, 0, 0);
+		blkz_flush_dirty_zone(zone);
+		return 0;
+	}
+	return -EINVAL;
+}
+
+static void blkz_write_kmsg_hdr(struct blkz_zone *zone,
+		struct pstore_record *record)
+{
+	struct blkz_context *cxt = record->psi->data;
+	struct blkz_buffer *buffer = zone->buffer;
+	struct blkz_dmesg_header *hdr =
+		(struct blkz_dmesg_header *)buffer->data;
+
+	hdr->magic = DMESG_HEADER_MAGIC;
+	hdr->compressed = record->compressed;
+	hdr->time.tv_sec = record->time.tv_sec;
+	hdr->time.tv_nsec = record->time.tv_nsec;
+	hdr->reason = record->reason;
+	if (hdr->reason == KMSG_DUMP_OOPS)
+		hdr->counter = ++cxt->oops_counter;
+	else if (hdr->reason == KMSG_DUMP_PANIC)
+		hdr->counter = ++cxt->panic_counter;
+	else if (hdr->reason == KMSG_DUMP_OOM)
+		hdr->counter = ++cxt->oom_counter;
+	else
+		hdr->counter = 0;
+}
+
+static int notrace blkz_dmesg_write(struct blkz_context *cxt,
+		struct pstore_record *record)
+{
+	struct blkz_info *info = cxt->bzinfo;
+	struct blkz_zone *zone;
+	size_t size, hlen;
+	int ret;
+
+	/*
+	 * Out of the various dmesg dump types, pstore/blk is currently designed
+	 * to only store crash logs, rather than storing general kernel logs.
+	 */
+	if (record->reason != KMSG_DUMP_OOPS &&
+			record->reason != KMSG_DUMP_PANIC &&
+			record->reason != KMSG_DUMP_OOM)
+		return -EINVAL;
+
+	/* Skip Oopes when configured to do so. */
+	if (record->reason == KMSG_DUMP_OOPS && !info->dump_oops)
+		return -EINVAL;
+
+	/* Skip OOM when configured to do so. */
+	if (record->reason == KMSG_DUMP_OOM && !info->dump_oom)
+		return -EINVAL;
+
+	/*
+	 * Explicitly only take the first part of any new crash.
+	 * If our buffer is larger than kmsg_bytes, this can never happen,
+	 * and if our buffer is smaller than kmsg_bytes, we don't want the
+	 * report split across multiple records.
+	 */
+	if (record->part != 1)
+		return -ENOSPC;
+
+	if (!cxt->dbzs)
+		return -ENOSPC;
+
+	zone = cxt->dbzs[cxt->dmesg_write_cnt];
+	if (!zone)
+		return -ENOSPC;
+
+	blkz_write_kmsg_hdr(zone, record);
+	hlen = sizeof(struct blkz_dmesg_header);
+	size = record->size;
+	if (size + hlen > zone->buffer_size)
+		size = zone->buffer_size - hlen;
+	ret = blkz_zone_write(zone, FLUSH_ALL, record->buf, size, hlen);
+
+	pr_debug("write %s to zone id %d\n", zone->name, cxt->dmesg_write_cnt);
+	cxt->dmesg_write_cnt = (cxt->dmesg_write_cnt + 1) % cxt->dmesg_max_cnt;
+
+	if (!ret) {
+		pr_debug("try to flush dmesg dirty zones\n");
+		blkz_flush_dirty_zones(cxt->dbzs, cxt->dmesg_max_cnt);
+	}
+	return 0;
+}
+
+static int notrace blkz_pmsg_write(struct blkz_context *cxt,
+		struct pstore_record *record)
+{
+	struct blkz_zone *zone;
+	size_t start, rem;
+	int cnt = record->size;
+	bool is_full_data = false;
+	char *buf = record->buf;
+
+	zone = cxt->pbz;
+	if (!zone)
+		return -ENOSPC;
+
+	if (atomic_read(&zone->buffer->datalen) >= zone->buffer_size)
+		is_full_data = true;
+
+	if (unlikely(cnt > zone->buffer_size)) {
+		buf += cnt - zone->buffer_size;
+		cnt = zone->buffer_size;
+	}
+
+	start = buffer_start(zone);
+	rem = zone->buffer_size - start;
+	if (unlikely(rem < cnt)) {
+		blkz_zone_write(zone, FLUSH_PART, buf, rem, start);
+		buf += rem;
+		cnt -= rem;
+		start = 0;
+		is_full_data = true;
+	}
+
+	atomic_set(&zone->buffer->start, cnt + start);
+	blkz_zone_write(zone, FLUSH_PART, buf, cnt, start);
+
+	/**
+	 * blkz_zone_write will set datalen as start + cnt.
+	 * It work if actual data length lesser than buffer size.
+	 * If data length greater than buffer size, pmsg will rewrite to
+	 * beginning of zone, which make buffer->datalen wrongly.
+	 * So we should reset datalen as buffer size once actual data length
+	 * greater than buffer size.
+	 */
+	if (is_full_data) {
+		atomic_set(&zone->buffer->datalen, zone->buffer_size);
+		blkz_zone_write(zone, FLUSH_META, NULL, 0, 0);
+	}
+	return 0;
+}
+
+static int notrace blkz_pstore_write(struct pstore_record *record)
+{
+	struct blkz_context *cxt = record->psi->data;
+
+	if (record->type == PSTORE_TYPE_DMESG &&
+			record->reason == KMSG_DUMP_PANIC)
+		atomic_set(&cxt->on_panic, 1);
+
+	/*
+	 * before write, we must recover from storage.
+	 * if recover failed, handle buffer
+	 */
+	blkz_recovery(cxt);
+
+	switch (record->type) {
+	case PSTORE_TYPE_DMESG:
+		return blkz_dmesg_write(cxt, record);
+	case PSTORE_TYPE_PMSG:
+		return blkz_pmsg_write(cxt, record);
+	default:
+		return -EINVAL;
+	}
+}
+
+#define READ_NEXT_ZONE ((ssize_t)(-1024))
+static struct blkz_zone *blkz_read_next_zone(struct blkz_context *cxt)
+{
+	struct blkz_zone *zone = NULL;
+
+	while (cxt->dmesg_read_cnt < cxt->dmesg_max_cnt) {
+		zone = cxt->dbzs[cxt->dmesg_read_cnt++];
+		if (blkz_ok(zone))
+			return zone;
+	}
+
+	if (cxt->pmsg_read_cnt == 0) {
+		cxt->pmsg_read_cnt++;
+		zone = cxt->pbz;
+		if (blkz_old_ok(zone))
+			return zone;
+	}
+
+	return NULL;
+}
+
+static int blkz_read_dmesg_hdr(struct blkz_zone *zone,
+		struct pstore_record *record)
+{
+	struct blkz_buffer *buffer = zone->buffer;
+	struct blkz_dmesg_header *hdr =
+		(struct blkz_dmesg_header *)buffer->data;
+
+	if (hdr->magic != DMESG_HEADER_MAGIC)
+		return -EINVAL;
+	record->compressed = hdr->compressed;
+	record->time.tv_sec = hdr->time.tv_sec;
+	record->time.tv_nsec = hdr->time.tv_nsec;
+	record->reason = hdr->reason;
+	record->count = hdr->counter;
+	return 0;
+}
+
+static ssize_t blkz_dmesg_read(struct blkz_zone *zone,
+		struct pstore_record *record)
+{
+	size_t size, hlen = 0;
+
+	size = buffer_datalen(zone);
+	/* Clear and skip this DMESG record if it has no valid header */
+	if (blkz_read_dmesg_hdr(zone, record)) {
+		atomic_set(&zone->buffer->datalen, 0);
+		atomic_set(&zone->dirty, 0);
+		return READ_NEXT_ZONE;
+	}
+	size -= sizeof(struct blkz_dmesg_header);
+
+	if (!record->compressed) {
+		char *buf = kasprintf(GFP_KERNEL,
+				"%s: Total %d times\n",
+				record->reason == KMSG_DUMP_OOPS ? "Oops" :
+				record->reason == KMSG_DUMP_PANIC ? "Panic" :
+				record->reason == KMSG_DUMP_OOM ? "OOM" :
+				"Unknown", record->count);
+		hlen = strlen(buf);
+		record->buf = krealloc(buf, hlen + size, GFP_KERNEL);
+		if (!record->buf) {
+			kfree(buf);
+			return -ENOMEM;
+		}
+	} else {
+		record->buf = kmalloc(size, GFP_KERNEL);
+		if (!record->buf)
+			return -ENOMEM;
+	}
+
+	if (unlikely(blkz_zone_read(zone, record->buf + hlen, size,
+				sizeof(struct blkz_dmesg_header)) < 0)) {
+		kfree(record->buf);
+		return READ_NEXT_ZONE;
+	}
+
+	return size + hlen;
+}
+
+static ssize_t blkz_pmsg_read(struct blkz_zone *zone,
+		struct pstore_record *record)
+{
+	size_t size, start;
+	struct blkz_buffer *buf;
+
+	buf = (struct blkz_buffer *)zone->oldbuf;
+	if (!buf)
+		return READ_NEXT_ZONE;
+
+	size = atomic_read(&buf->datalen);
+	start = atomic_read(&buf->start);
+
+	record->buf = kmalloc(size, GFP_KERNEL);
+	if (!record->buf)
+		return -ENOMEM;
+
+	memcpy(record->buf, buf->data + start, size - start);
+	memcpy(record->buf + size - start, buf->data, start);
+
+	return size;
+}
+
+static ssize_t blkz_pstore_read(struct pstore_record *record)
+{
+	struct blkz_context *cxt = record->psi->data;
+	ssize_t (*blkz_read)(struct blkz_zone *zone,
+			struct pstore_record *record);
+	struct blkz_zone *zone;
+	ssize_t ret;
+
+	/*
+	 * before read, we must recover from storage.
+	 * if recover failed, handle buffer
+	 */
+	blkz_recovery(cxt);
+
+next_zone:
+	zone = blkz_read_next_zone(cxt);
+	if (!zone)
+		return 0;
+
+	record->type = zone->type;
+	switch (record->type) {
+	case PSTORE_TYPE_DMESG:
+		blkz_read = blkz_dmesg_read;
+		record->id = cxt->dmesg_read_cnt - 1;
+		break;
+	case PSTORE_TYPE_PMSG:
+		blkz_read = blkz_pmsg_read;
+		break;
+	default:
+		goto next_zone;
+	}
+
+	ret = blkz_read(zone, record);
+	if (ret == READ_NEXT_ZONE)
+		goto next_zone;
+	return ret;
+}
+
+static struct blkz_context blkz_cxt = {
+	.bzinfo_lock = __SPIN_LOCK_UNLOCKED(blkz_cxt.bzinfo_lock),
+	.recovery = ATOMIC_INIT(0),
+	.on_panic = ATOMIC_INIT(0),
+	.pstore = {
+		.owner = THIS_MODULE,
+		.name = MODNAME,
+		.open = blkz_pstore_open,
+		.read = blkz_pstore_read,
+		.write = blkz_pstore_write,
+		.erase = blkz_pstore_erase,
+	},
+};
+
+static long long blkz_blkdev_size(struct blkz_context *cxt)
+{
+	struct block_device *bdev = cxt->bdev;
+
+	if (!bdev)
+		return -EINVAL;
+
+	return (long long)part_nr_sects_read(bdev->bd_part) * SECTOR_SIZE;
+}
+
+/**
+ * blkz_get_bdev: initialize block device
+ *
+ * It uses name_to_dev_t to get dev_t, so it accpet the following variants:
+ *	1) <hex_major><hex_minor> device number in hexadecimal represents itself
+ *	   no leading 0x, for example b302.
+ *	2) /dev/<disk_name> represents the device number of disk
+ *	3) /dev/<disk_name><decimal> represents the device number
+ *	   of partition - device number of disk plus the partition number
+ *	4) /dev/<disk_name>p<decimal> - same as the above, that form is
+ *	   used when disk name of partitioned disk ends on a digit.
+ *	5) PARTUUID=00112233-4455-6677-8899-AABBCCDDEEFF representing the
+ *	   unique id of a partition if the partition table provides it.
+ *	   The UUID may be either an EFI/GPT UUID, or refer to an MSDOS
+ *	   partition using the format SSSSSSSS-PP, where SSSSSSSS is a zero-
+ *	   filled hex representation of the 32-bit "NT disk signature", and PP
+ *	   is a zero-filled hex representation of the 1-based partition number.
+ *	6) PARTUUID=<UUID>/PARTNROFF=<int> to select a partition in relation to
+ *	   a partition with a known unique id.
+ *	7) <major>:<minor> major and minor number of the device separated by
+ *	   a colon.
+ */
+static int blkz_get_bdev(struct blkz_context *cxt, const char *dev)
+{
+	dev_t devt;
+	struct block_device *bdev;
+	const fmode_t mode = FMODE_READ | FMODE_WRITE | FMODE_EXCL;
+
+	if (!dev)
+		return -EINVAL;
+
+	devt = name_to_dev_t(dev);
+	if (!devt) {
+		pr_err("not found dev_t from %s\n", dev);
+		return -ENODEV;
+	}
+
+	bdev = blkdev_get_by_dev(devt, mode, cxt);
+	if (IS_ERR(bdev)) {
+		pr_err("get block_device by %u:%u failed\n",
+				MAJOR(devt), MINOR(devt));
+		return PTR_ERR(bdev);
+	}
+
+	cxt->bdev = bdev;
+	return 0;
+}
+
+static void blkz_put_bdev(struct blkz_context *cxt)
+{
+	const fmode_t mode = FMODE_READ | FMODE_WRITE | FMODE_EXCL;
+
+	if (cxt->bdev) {
+		blkdev_put(cxt->bdev, mode);
+		cxt->bdev = NULL;
+	}
+}
+
+static ssize_t blkz_default_general_read(char *buf, size_t bytes, loff_t pos)
+{
+	ssize_t ret;
+	struct blkz_context *cxt = &blkz_cxt;
+	struct file filp;
+	struct kiocb kiocb;
+	struct iov_iter iter;
+	struct iovec iov = {
+		.iov_base = (void __user *)buf,
+		.iov_len = bytes
+	};
+
+	if (!cxt->bdev) {
+		struct blkz_info *info = cxt->bzinfo;
+
+		if (!info->blkdev)
+			return -ENODEV;
+		ret = blkz_get_bdev(cxt, info->blkdev);
+		if (ret)
+			return ret;
+	}
+
+	filp.f_mapping = cxt->bdev->bd_inode->i_mapping;
+	filp.f_flags = O_DSYNC | __O_SYNC | O_NOATIME;
+
+	init_sync_kiocb(&kiocb, &filp);
+	kiocb.ki_pos = pos;
+	iov_iter_init(&iter, READ, &iov, 1, bytes);
+
+	return generic_file_read_iter(&kiocb, &iter);
+}
+
+static ssize_t blkz_default_general_write(const char *buf, size_t bytes,
+		loff_t pos)
+{
+	struct blkz_context *cxt = &blkz_cxt;
+	struct iov_iter iter;
+	struct file filp;
+	ssize_t ret, written;
+	struct iovec iov = {
+		.iov_base = (void __user *)buf,
+		.iov_len = bytes
+	};
+	struct writeback_control wbc = {
+		.nr_to_write = LONG_MAX,
+		.sync_mode = WB_SYNC_ALL,
+		.range_start = 0,
+		.range_end = LONG_MAX,
+	};
+
+	if (!cxt->bdev) {
+		struct blkz_info *info = cxt->bzinfo;
+
+		if (!info->blkdev)
+			return -ENODEV;
+		ret = blkz_get_bdev(cxt, info->blkdev);
+		if (ret)
+			return ret;
+	}
+
+	filp.f_mapping = cxt->bdev->bd_inode->i_mapping;
+	iov_iter_init(&iter, WRITE, &iov, 1, bytes);
+
+	written = generic_perform_write(&filp, &iter, pos);
+	ret = generic_writepages(filp.f_mapping, &wbc);
+
+	return ret < 0 ? ret : written;
+}
+
+static struct blkz_zone *blkz_init_zone(enum pstore_type_id type,
+		unsigned long *off, size_t size)
+{
+	struct blkz_info *info = blkz_cxt.bzinfo;
+	struct blkz_zone *zone;
+	const char *name = pstore_type_to_name(type);
+
+	if (!size)
+		return NULL;
+
+	if (*off + size > info->total_size) {
+		pr_err("no room for %s (0x%zx@0x%lx over 0x%lx)\n",
+			name, size, *off, info->total_size);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	zone = kzalloc(sizeof(struct blkz_zone), GFP_KERNEL);
+	if (!zone)
+		return ERR_PTR(-ENOMEM);
+
+	/*
+	 * NOTE: allocate buffer for blk zones for two reasons:
+	 * 1. It can temporarily hold the data before
+	 *    blkz_default_general_read/write are useable.
+	 * 2. It makes pstore usable even if no persistent storage. Most
+	 *    events of pstore except panic are suitable!!
+	 */
+	zone->buffer = kmalloc(size, GFP_KERNEL);
+	if (!zone->buffer) {
+		kfree(zone);
+		return ERR_PTR(-ENOMEM);
+	}
+	memset(zone->buffer, 0xFF, size);
+	zone->off = *off;
+	zone->name = name;
+	zone->type = type;
+	zone->buffer_size = size - sizeof(struct blkz_buffer);
+	zone->buffer->sig = type ^ BLK_SIG;
+	zone->oldbuf = NULL;
+	atomic_set(&zone->dirty, 0);
+	atomic_set(&zone->buffer->datalen, 0);
+	atomic_set(&zone->buffer->start, 0);
+
+	*off += size;
+
+	pr_debug("blkzone %s: off 0x%lx, %zu header, %zu data\n", zone->name,
+			zone->off, sizeof(*zone->buffer), zone->buffer_size);
+	return zone;
+}
+
+static struct blkz_zone **blkz_init_zones(enum pstore_type_id type,
+	unsigned long *off, size_t total_size, ssize_t record_size,
+	unsigned int *cnt)
+{
+	struct blkz_info *info = blkz_cxt.bzinfo;
+	struct blkz_zone **zones, *zone;
+	const char *name = pstore_type_to_name(type);
+	int c, i;
+
+	if (!total_size || !record_size)
+		return NULL;
+
+	if (*off + total_size > info->total_size) {
+		pr_err("no room for zones %s (0x%zx@0x%lx over 0x%lx)\n",
+			name, total_size, *off, info->total_size);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	c = total_size / record_size;
+	zones = kcalloc(c, sizeof(*zones), GFP_KERNEL);
+	if (!zones) {
+		pr_err("allocate for zones %s failed\n", name);
+		return ERR_PTR(-ENOMEM);
+	}
+	memset(zones, 0, c * sizeof(*zones));
+
+	for (i = 0; i < c; i++) {
+		zone = blkz_init_zone(type, off, record_size);
+		if (!zone || IS_ERR(zone)) {
+			pr_err("initialize zones %s failed\n", name);
+			while (--i >= 0) {
+				kfree(zones[i]->buffer);
+				kfree(zones[i]);
+			}
+			kfree(zones);
+			return (void *)zone;
+		}
+		zones[i] = zone;
+	}
+
+	*cnt = c;
+	return zones;
+}
+
+static void blkz_free_zone(struct blkz_zone **blkzone)
+{
+	struct blkz_zone *zone = *blkzone;
+
+	if (!zone)
+		return;
+
+	kfree(zone->buffer);
+	kfree(zone);
+	*blkzone = NULL;
+}
+
+static void blkz_free_zones(struct blkz_zone ***blkzones, unsigned int *cnt)
+{
+	struct blkz_zone **zones = *blkzones;
+
+	if (!zones)
+		return;
+
+	while (*cnt > 0) {
+		blkz_free_zone(&zones[*cnt]);
+		(*cnt)--;
+	}
+	kfree(zones);
+	*blkzones = NULL;
+}
+
+static int blkz_cut_zones(struct blkz_context *cxt)
+{
+	struct blkz_info *info = cxt->bzinfo;
+	unsigned long off = 0;
+	int err;
+	size_t size;
+
+	size = info->total_size - info->pmsg_size;
+	cxt->dbzs = blkz_init_zones(PSTORE_TYPE_DMESG, &off, size,
+			info->dmesg_size, &cxt->dmesg_max_cnt);
+	if (IS_ERR(cxt->dbzs)) {
+		err = PTR_ERR(cxt->dbzs);
+		goto fail_out;
+	}
+
+	size = info->pmsg_size;
+	cxt->pbz = blkz_init_zone(PSTORE_TYPE_PMSG, &off, size);
+	if (IS_ERR(cxt->pbz)) {
+		err = PTR_ERR(cxt->pbz);
+		goto free_dmesg_zones;
+	}
+
+	return 0;
+free_dmesg_zones:
+	blkz_free_zones(&cxt->dbzs, &cxt->dmesg_max_cnt);
+fail_out:
+	return err;
+}
+
+int blkz_register(struct blkz_info *info)
+{
+	int err = -EINVAL;
+	struct blkz_context *cxt = &blkz_cxt;
+	struct module *owner = info->owner;
+
+	if (info->blkdev && !blkz_get_bdev(cxt, info->blkdev)) {
+		long long size;
+
+		size = blkz_blkdev_size(cxt);
+		if (size > 0 && (!info->total_size || info->total_size > size)) {
+			info->total_size = (unsigned long)size;
+			pr_info("total size %ld from block device %s\n",
+					info->total_size, info->blkdev);
+		}
+		pr_info("using block device %s\n", info->blkdev);
+	}
+
+	if (!info->total_size || (!info->dmesg_size && !info->pmsg_size)) {
+		pr_warn("The total size and the dmesg size must be non-zero\n");
+		return -EINVAL;
+	}
+
+	if (info->total_size < 4096) {
+		pr_err("total size must be over 4096 bytes\n");
+		return -EINVAL;
+	}
+
+#define check_size(name, size) {					\
+		if (info->name & (size - 1)) {				\
+			pr_err(#name " must be a multiple of %d\n",	\
+					(size));			\
+			return -EINVAL;					\
+		}							\
+	}
+
+	check_size(total_size, 4096);
+	check_size(dmesg_size, SECTOR_SIZE);
+	check_size(pmsg_size, SECTOR_SIZE);
+
+#undef check_size
+
+	if (!info->read)
+		info->read = blkz_default_general_read;
+	if (!info->write)
+		info->write = blkz_default_general_write;
+
+	if (owner && !try_module_get(owner))
+		return -EINVAL;
+
+	spin_lock(&cxt->bzinfo_lock);
+	if (cxt->bzinfo) {
+		pr_warn("blk '%s' already loaded: ignoring '%s'\n",
+				cxt->bzinfo->name, info->name);
+		spin_unlock(&cxt->bzinfo_lock);
+		return -EBUSY;
+	}
+	cxt->bzinfo = info;
+	spin_unlock(&cxt->bzinfo_lock);
+
+	pr_debug("register %s with properties:\n", info->name);
+	pr_debug("\tblkdev : %s\n", info->blkdev);
+	pr_debug("\ttotal size : %ld Bytes\n", info->total_size);
+	pr_debug("\tdmesg size : %ld Bytes\n", info->dmesg_size);
+	pr_debug("\tpmsg size : %ld Bytes\n", info->pmsg_size);
+
+	if (blkz_cut_zones(cxt)) {
+		pr_err("cut zones fialed\n");
+		goto fail_out;
+	}
+
+	if (info->dmesg_size) {
+		cxt->pstore.bufsize = cxt->dbzs[0]->buffer_size -
+			sizeof(struct blkz_dmesg_header);
+		cxt->pstore.buf = kzalloc(cxt->pstore.bufsize, GFP_KERNEL);
+		if (!cxt->pstore.buf) {
+			err = -ENOMEM;
+			goto fail_out;
+		}
+	}
+	cxt->pstore.data = cxt;
+	if (info->dmesg_size)
+		cxt->pstore.flags |= PSTORE_FLAGS_DMESG;
+	if (info->pmsg_size)
+		cxt->pstore.flags |= PSTORE_FLAGS_PMSG;
+
+	pr_info("Registered %s as blkzone backend for %s%s%s%s\n", info->name,
+			cxt->dbzs && cxt->bzinfo->dump_oops ? "Oops " : "",
+			cxt->dbzs && cxt->bzinfo->panic_write ? "Panic " : "",
+			cxt->dbzs && cxt->bzinfo->dump_oom ? "OOM " : "",
+			cxt->pbz ? "Pmsg" : "");
+
+	err = pstore_register(&cxt->pstore);
+	if (err) {
+		pr_err("registering with pstore failed\n");
+		goto free_pstore_buf;
+	}
+
+	module_put(owner);
+	return 0;
+
+free_pstore_buf:
+	kfree(cxt->pstore.buf);
+fail_out:
+	spin_lock(&blkz_cxt.bzinfo_lock);
+	blkz_cxt.bzinfo = NULL;
+	spin_unlock(&blkz_cxt.bzinfo_lock);
+	return err;
+}
+EXPORT_SYMBOL_GPL(blkz_register);
+
+void blkz_unregister(struct blkz_info *info)
+{
+	struct blkz_context *cxt = &blkz_cxt;
+
+	pstore_unregister(&cxt->pstore);
+	kfree(cxt->pstore.buf);
+	cxt->pstore.bufsize = 0;
+
+	spin_lock(&cxt->bzinfo_lock);
+	blkz_cxt.bzinfo = NULL;
+	spin_unlock(&cxt->bzinfo_lock);
+
+	blkz_free_zones(&cxt->dbzs, &cxt->dmesg_max_cnt);
+	blkz_free_zone(&cxt->pbz);
+	blkz_put_bdev(cxt);
+}
+EXPORT_SYMBOL_GPL(blkz_unregister);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("liaoweixiong <liaoweixiong@allwinnertech.com>");
+MODULE_DESCRIPTION("Block device Oops/Panic logger");