/*
 * Copyright (C) 2016-2017 Red Hat, Inc. All rights reserved.
 * Copyright (C) 2016-2017 Milan Broz
 * Copyright (C) 2016-2017 Mikulas Patocka
 *
 * This file is released under the GPL.
 */

#include "dm-bio-record.h"

#include <linux/compiler.h>
#include <linux/module.h>
#include <linux/device-mapper.h>
#include <linux/dm-io.h>
#include <linux/vmalloc.h>
#include <linux/sort.h>
#include <linux/rbtree.h>
#include <linux/delay.h>
#include <linux/random.h>
#include <linux/reboot.h>
#include <crypto/hash.h>
#include <crypto/skcipher.h>
#include <linux/async_tx.h>
#include <linux/dm-bufio.h>

#define DM_MSG_PREFIX "integrity"

#define DEFAULT_INTERLEAVE_SECTORS      32768
#define DEFAULT_JOURNAL_SIZE_FACTOR     7
#define DEFAULT_SECTORS_PER_BITMAP_BIT  32768
#define DEFAULT_BUFFER_SECTORS          128
#define DEFAULT_JOURNAL_WATERMARK       50
#define DEFAULT_SYNC_MSEC               10000
#define DEFAULT_MAX_JOURNAL_SECTORS     131072
#define MIN_LOG2_INTERLEAVE_SECTORS     3
#define MAX_LOG2_INTERLEAVE_SECTORS     31
#define METADATA_WORKQUEUE_MAX_ACTIVE   16
#define RECALC_SECTORS                  32768
#define RECALC_WRITE_SUPER              16
#define BITMAP_BLOCK_SIZE               4096    /* don't change it */
#define BITMAP_FLUSH_INTERVAL           (10 * HZ)
#define DISCARD_FILLER                  0xf6
#define SALT_SIZE                       16

/*
 * Warning - DEBUG_PRINT prints security-sensitive data to the log,
 * so it should not be enabled in the official kernel
 */
//#define DEBUG_PRINT
//#define INTERNAL_VERIFY

/*
 * On disk structures
 */

#define SB_MAGIC                        "integrt"
#define SB_VERSION_1                    1
#define SB_VERSION_2                    2
#define SB_VERSION_3                    3
#define SB_VERSION_4                    4
#define SB_VERSION_5                    5
#define SB_SECTORS                      8
#define MAX_SECTORS_PER_BLOCK           8

struct superblock {
        __u8 magic[8];
        __u8 version;
        __u8 log2_interleave_sectors;
        __le16 integrity_tag_size;
        __le32 journal_sections;
        __le64 provided_data_sectors;   /* userspace uses this value */
        __le32 flags;
        __u8 log2_sectors_per_block;
        __u8 log2_blocks_per_bitmap_bit;
        __u8 pad[2];
        __le64 recalc_sector;
        __u8 pad2[8];
        __u8 salt[SALT_SIZE];
};

#define SB_FLAG_HAVE_JOURNAL_MAC        0x1
#define SB_FLAG_RECALCULATING           0x2
#define SB_FLAG_DIRTY_BITMAP            0x4
#define SB_FLAG_FIXED_PADDING           0x8
#define SB_FLAG_FIXED_HMAC              0x10

#define JOURNAL_ENTRY_ROUNDUP           8

typedef __le64 commit_id_t;
#define JOURNAL_MAC_PER_SECTOR          8

struct journal_entry {
        union {
                struct {
                        __le32 sector_lo;
                        __le32 sector_hi;
                } s;
                __le64 sector;
        } u;
        commit_id_t last_bytes[];
        /* __u8 tag[0]; */
};

#define journal_entry_tag(ic, je)               ((__u8 *)&(je)->last_bytes[(ic)->sectors_per_block])

#if BITS_PER_LONG == 64
#define journal_entry_set_sector(je, x)         do { smp_wmb(); WRITE_ONCE((je)->u.sector, cpu_to_le64(x)); } while (0)
#else
#define journal_entry_set_sector(je, x)         do { (je)->u.s.sector_lo = cpu_to_le32(x); smp_wmb(); WRITE_ONCE((je)->u.s.sector_hi, cpu_to_le32((x) >> 32)); } while (0)
#endif
#define journal_entry_get_sector(je)            le64_to_cpu((je)->u.sector)
#define journal_entry_is_unused(je)             ((je)->u.s.sector_hi == cpu_to_le32(-1))
#define journal_entry_set_unused(je)            do { ((je)->u.s.sector_hi = cpu_to_le32(-1)); } while (0)
#define journal_entry_is_inprogress(je)         ((je)->u.s.sector_hi == cpu_to_le32(-2))
#define journal_entry_set_inprogress(je)        do { ((je)->u.s.sector_hi = cpu_to_le32(-2)); } while (0)

#define JOURNAL_BLOCK_SECTORS           8
#define JOURNAL_SECTOR_DATA             ((1 << SECTOR_SHIFT) - sizeof(commit_id_t))
#define JOURNAL_MAC_SIZE                (JOURNAL_MAC_PER_SECTOR * JOURNAL_BLOCK_SECTORS)

struct journal_sector {
        __u8 entries[JOURNAL_SECTOR_DATA - JOURNAL_MAC_PER_SECTOR];
        __u8 mac[JOURNAL_MAC_PER_SECTOR];
        commit_id_t commit_id;
};

#define MAX_TAG_SIZE                    (JOURNAL_SECTOR_DATA - JOURNAL_MAC_PER_SECTOR - offsetof(struct journal_entry, last_bytes[MAX_SECTORS_PER_BLOCK]))

#define METADATA_PADDING_SECTORS        8

#define N_COMMIT_IDS                    4

static unsigned char prev_commit_seq(unsigned char seq)
{
        return (seq + N_COMMIT_IDS - 1) % N_COMMIT_IDS;
}

static unsigned char next_commit_seq(unsigned char seq)
{
        return (seq + 1) % N_COMMIT_IDS;
}

/*
 * In-memory structures
 */

struct journal_node {
        struct rb_node node;
        sector_t sector;
};

struct alg_spec {
        char *alg_string;
        char *key_string;
        __u8 *key;
        unsigned key_size;
};

struct dm_integrity_c {
        struct dm_dev *dev;
        struct dm_dev *meta_dev;
        unsigned tag_size;
        __s8 log2_tag_size;
        sector_t start;
        mempool_t journal_io_mempool;
        struct dm_io_client *io;
        struct dm_bufio_client *bufio;
        struct workqueue_struct *metadata_wq;
        struct superblock *sb;
        unsigned journal_pages;
        unsigned n_bitmap_blocks;

        struct page_list *journal;
        struct page_list *journal_io;
        struct page_list *journal_xor;
        struct page_list *recalc_bitmap;
        struct page_list *may_write_bitmap;
        struct bitmap_block_status *bbs;
        unsigned bitmap_flush_interval;
        int synchronous_mode;
        struct bio_list synchronous_bios;
        struct delayed_work bitmap_flush_work;

        struct crypto_skcipher *journal_crypt;
        struct scatterlist **journal_scatterlist;
        struct scatterlist **journal_io_scatterlist;
        struct skcipher_request **sk_requests;

        struct crypto_shash *journal_mac;

        struct journal_node *journal_tree;
        struct rb_root journal_tree_root;

        sector_t provided_data_sectors;

        unsigned short journal_entry_size;
        unsigned char journal_entries_per_sector;
        unsigned char journal_section_entries;
        unsigned short journal_section_sectors;
        unsigned journal_sections;
        unsigned journal_entries;
        sector_t data_device_sectors;
        sector_t meta_device_sectors;
        unsigned initial_sectors;
        unsigned metadata_run;
        __s8 log2_metadata_run;
        __u8 log2_buffer_sectors;
        __u8 sectors_per_block;
        __u8 log2_blocks_per_bitmap_bit;

        unsigned char mode;

        int failed;

        struct crypto_shash *internal_hash;

        struct dm_target *ti;

        /* these variables are locked with endio_wait.lock */
        struct rb_root in_progress;
        struct list_head wait_list;
        wait_queue_head_t endio_wait;
        struct workqueue_struct *wait_wq;
        struct workqueue_struct *offload_wq;

        unsigned char commit_seq;
        commit_id_t commit_ids[N_COMMIT_IDS];

        unsigned committed_section;
        unsigned n_committed_sections;

        unsigned uncommitted_section;
        unsigned n_uncommitted_sections;

        unsigned free_section;
        unsigned char free_section_entry;
        unsigned free_sectors;

        unsigned free_sectors_threshold;

        struct workqueue_struct *commit_wq;
        struct work_struct commit_work;

        struct workqueue_struct *writer_wq;
        struct work_struct writer_work;

        struct workqueue_struct *recalc_wq;
        struct work_struct recalc_work;
        u8 *recalc_buffer;
        u8 *recalc_tags;

        struct bio_list flush_bio_list;

        unsigned long autocommit_jiffies;
        struct timer_list autocommit_timer;
        unsigned autocommit_msec;

        wait_queue_head_t copy_to_journal_wait;

        struct completion crypto_backoff;

        bool journal_uptodate;
        bool just_formatted;
        bool recalculate_flag;
        bool reset_recalculate_flag;
        bool discard;
        bool fix_padding;
        bool fix_hmac;
        bool legacy_recalculate;

        struct alg_spec internal_hash_alg;
        struct alg_spec journal_crypt_alg;
        struct alg_spec journal_mac_alg;

        atomic64_t number_of_mismatches;

        struct notifier_block reboot_notifier;
};

struct dm_integrity_range {
        sector_t logical_sector;
        sector_t n_sectors;
        bool waiting;
        union {
                struct rb_node node;
                struct {
                        struct task_struct *task;
                        struct list_head wait_entry;
                };
        };
};

struct dm_integrity_io {
        struct work_struct work;

        struct dm_integrity_c *ic;
        enum req_opf op;
        bool fua;

        struct dm_integrity_range range;

        sector_t metadata_block;
        unsigned metadata_offset;

        atomic_t in_flight;
        blk_status_t bi_status;

        struct completion *completion;

        struct dm_bio_details bio_details;
};

struct journal_completion {
        struct dm_integrity_c *ic;
        atomic_t in_flight;
        struct completion comp;
};

struct journal_io {
        struct dm_integrity_range range;
        struct journal_completion *comp;
};

struct bitmap_block_status {
        struct work_struct work;
        struct dm_integrity_c *ic;
        unsigned idx;
        unsigned long *bitmap;
        struct bio_list bio_queue;
        spinlock_t bio_queue_lock;

};

static struct kmem_cache *journal_io_cache;

#define JOURNAL_IO_MEMPOOL      32

#ifdef DEBUG_PRINT
#define DEBUG_print(x, ...)     printk(KERN_DEBUG x, ##__VA_ARGS__)
static void __DEBUG_bytes(__u8 *bytes, size_t len, const char *msg, ...)
{
        va_list args;
        va_start(args, msg);
        vprintk(msg, args);
        va_end(args);
        if (len)
                pr_cont(":");
        while (len) {
                pr_cont(" %02x", *bytes);
                bytes++;
                len--;
        }
        pr_cont("\n");
}
#define DEBUG_bytes(bytes, len, msg, ...)       __DEBUG_bytes(bytes, len, KERN_DEBUG msg, ##__VA_ARGS__)
#else
#define DEBUG_print(x, ...)                     do { } while (0)
#define DEBUG_bytes(bytes, len, msg, ...)       do { } while (0)
#endif

static void dm_integrity_prepare(struct request *rq)
{
}

static void dm_integrity_complete(struct request *rq, unsigned int nr_bytes)
{
}

/*
 * DM Integrity profile, protection is performed layer above (dm-crypt)
 */
static const struct blk_integrity_profile dm_integrity_profile = {
        .name                   = "DM-DIF-EXT-TAG",
        .generate_fn            = NULL,
        .verify_fn              = NULL,
        .prepare_fn             = dm_integrity_prepare,
        .complete_fn            = dm_integrity_complete,
};

static void dm_integrity_map_continue(struct dm_integrity_io *dio, bool from_map);
static void integrity_bio_wait(struct work_struct *w);
static void dm_integrity_dtr(struct dm_target *ti);

static void dm_integrity_io_error(struct dm_integrity_c *ic, const char *msg, int err)
{
        if (err == -EILSEQ)
                atomic64_inc(&ic->number_of_mismatches);
        if (!cmpxchg(&ic->failed, 0, err))
                DMERR("Error on %s: %d", msg, err);
}

static int dm_integrity_failed(struct dm_integrity_c *ic)
{
        return READ_ONCE(ic->failed);
}

static bool dm_integrity_disable_recalculate(struct dm_integrity_c *ic)
{
        if (ic->legacy_recalculate)
                return false;
        if (!(ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_HMAC)) ?
            ic->internal_hash_alg.key || ic->journal_mac_alg.key :
            ic->internal_hash_alg.key && !ic->journal_mac_alg.key)
                return true;
        return false;
}

static commit_id_t dm_integrity_commit_id(struct dm_integrity_c *ic, unsigned i,
                                          unsigned j, unsigned char seq)
{
        /*
         * Xor the number with section and sector, so that if a piece of
         * journal is written at wrong place, it is detected.
         */
        return ic->commit_ids[seq] ^ cpu_to_le64(((__u64)i << 32) ^ j);
}

static void get_area_and_offset(struct dm_integrity_c *ic, sector_t data_sector,
                                sector_t *area, sector_t *offset)
{
        if (!ic->meta_dev) {
                __u8 log2_interleave_sectors = ic->sb->log2_interleave_sectors;
                *area = data_sector >> log2_interleave_sectors;
                *offset = (unsigned)data_sector & ((1U << log2_interleave_sectors) - 1);
        } else {
                *area = 0;
                *offset = data_sector;
        }
}

#define sector_to_block(ic, n)                                          \
do {                                                                    \
        BUG_ON((n) & (unsigned)((ic)->sectors_per_block - 1));          \
        (n) >>= (ic)->sb->log2_sectors_per_block;                       \
} while (0)

static __u64 get_metadata_sector_and_offset(struct dm_integrity_c *ic, sector_t area,
                                            sector_t offset, unsigned *metadata_offset)
{
        __u64 ms;
        unsigned mo;

        ms = area << ic->sb->log2_interleave_sectors;
        if (likely(ic->log2_metadata_run >= 0))
                ms += area << ic->log2_metadata_run;
        else
                ms += area * ic->metadata_run;
        ms >>= ic->log2_buffer_sectors;

        sector_to_block(ic, offset);

        if (likely(ic->log2_tag_size >= 0)) {
                ms += offset >> (SECTOR_SHIFT + ic->log2_buffer_sectors - ic->log2_tag_size);
                mo = (offset << ic->log2_tag_size) & ((1U << SECTOR_SHIFT << ic->log2_buffer_sectors) - 1);
        } else {
                ms += (__u64)offset * ic->tag_size >> (SECTOR_SHIFT + ic->log2_buffer_sectors);
                mo = (offset * ic->tag_size) & ((1U << SECTOR_SHIFT << ic->log2_buffer_sectors) - 1);
        }
        *metadata_offset = mo;
        return ms;
}

static sector_t get_data_sector(struct dm_integrity_c *ic, sector_t area, sector_t offset)
{
        sector_t result;

        if (ic->meta_dev)
                return offset;

        result = area << ic->sb->log2_interleave_sectors;
        if (likely(ic->log2_metadata_run >= 0))
                result += (area + 1) << ic->log2_metadata_run;
        else
                result += (area + 1) * ic->metadata_run;

        result += (sector_t)ic->initial_sectors + offset;
        result += ic->start;

        return result;
}

static void wraparound_section(struct dm_integrity_c *ic, unsigned *sec_ptr)
{
        if (unlikely(*sec_ptr >= ic->journal_sections))
                *sec_ptr -= ic->journal_sections;
}

static void sb_set_version(struct dm_integrity_c *ic)
{
        if (ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_HMAC))
                ic->sb->version = SB_VERSION_5;
        else if (ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_PADDING))
                ic->sb->version = SB_VERSION_4;
        else if (ic->mode == 'B' || ic->sb->flags & cpu_to_le32(SB_FLAG_DIRTY_BITMAP))
                ic->sb->version = SB_VERSION_3;
        else if (ic->meta_dev || ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING))
                ic->sb->version = SB_VERSION_2;
        else
                ic->sb->version = SB_VERSION_1;
}

static int sb_mac(struct dm_integrity_c *ic, bool wr)
{
        SHASH_DESC_ON_STACK(desc, ic->journal_mac);
        int r;
        unsigned size = crypto_shash_digestsize(ic->journal_mac);

        if (sizeof(struct superblock) + size > 1 << SECTOR_SHIFT) {
                dm_integrity_io_error(ic, "digest is too long", -EINVAL);
                return -EINVAL;
        }

        desc->tfm = ic->journal_mac;

        r = crypto_shash_init(desc);
        if (unlikely(r < 0)) {
                dm_integrity_io_error(ic, "crypto_shash_init", r);
                return r;
        }

        r = crypto_shash_update(desc, (__u8 *)ic->sb, (1 << SECTOR_SHIFT) - size);
        if (unlikely(r < 0)) {
                dm_integrity_io_error(ic, "crypto_shash_update", r);
                return r;
        }

        if (likely(wr)) {
                r = crypto_shash_final(desc, (__u8 *)ic->sb + (1 << SECTOR_SHIFT) - size);
                if (unlikely(r < 0)) {
                        dm_integrity_io_error(ic, "crypto_shash_final", r);
                        return r;
                }
        } else {
                __u8 result[HASH_MAX_DIGESTSIZE];
                r = crypto_shash_final(desc, result);
                if (unlikely(r < 0)) {
                        dm_integrity_io_error(ic, "crypto_shash_final", r);
                        return r;
                }
                if (memcmp((__u8 *)ic->sb + (1 << SECTOR_SHIFT) - size, result, size)) {
                        dm_integrity_io_error(ic, "superblock mac", -EILSEQ);
                        return -EILSEQ;
                }
        }

        return 0;
}

static int sync_rw_sb(struct dm_integrity_c *ic, int op, int op_flags)
{
        struct dm_io_request io_req;
        struct dm_io_region io_loc;
        int r;

        io_req.bi_op = op;
        io_req.bi_op_flags = op_flags;
        io_req.mem.type = DM_IO_KMEM;
        io_req.mem.ptr.addr = ic->sb;
        io_req.notify.fn = NULL;
        io_req.client = ic->io;
        io_loc.bdev = ic->meta_dev ? ic->meta_dev->bdev : ic->dev->bdev;
        io_loc.sector = ic->start;
        io_loc.count = SB_SECTORS;

        if (op == REQ_OP_WRITE) {
                sb_set_version(ic);
                if (ic->journal_mac && ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_HMAC)) {
                        r = sb_mac(ic, true);
                        if (unlikely(r))
                                return r;
                }
        }

        r = dm_io(&io_req, 1, &io_loc, NULL);
        if (unlikely(r))
                return r;

        if (op == REQ_OP_READ) {
                if (ic->mode != 'R' && ic->journal_mac && ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_HMAC)) {
                        r = sb_mac(ic, false);
                        if (unlikely(r))
                                return r;
                }
        }

        return 0;
}

#define BITMAP_OP_TEST_ALL_SET          0
#define BITMAP_OP_TEST_ALL_CLEAR        1
#define BITMAP_OP_SET                   2
#define BITMAP_OP_CLEAR                 3

static bool block_bitmap_op(struct dm_integrity_c *ic, struct page_list *bitmap,
                            sector_t sector, sector_t n_sectors, int mode)
{
        unsigned long bit, end_bit, this_end_bit, page, end_page;
        unsigned long *data;

        if (unlikely(((sector | n_sectors) & ((1 << ic->sb->log2_sectors_per_block) - 1)) != 0)) {
                DMCRIT("invalid bitmap access (%llx,%llx,%d,%d,%d)",
                        sector,
                        n_sectors,
                        ic->sb->log2_sectors_per_block,
                        ic->log2_blocks_per_bitmap_bit,
                        mode);
                BUG();
        }

        if (unlikely(!n_sectors))
                return true;

        bit = sector >> (ic->sb->log2_sectors_per_block + ic->log2_blocks_per_bitmap_bit);
        end_bit = (sector + n_sectors - 1) >>
                (ic->sb->log2_sectors_per_block + ic->log2_blocks_per_bitmap_bit);

        page = bit / (PAGE_SIZE * 8);
        bit %= PAGE_SIZE * 8;

        end_page = end_bit / (PAGE_SIZE * 8);
        end_bit %= PAGE_SIZE * 8;

repeat:
        if (page < end_page) {
                this_end_bit = PAGE_SIZE * 8 - 1;
        } else {
                this_end_bit = end_bit;
        }

        data = lowmem_page_address(bitmap[page].page);

        if (mode == BITMAP_OP_TEST_ALL_SET) {
                while (bit <= this_end_bit) {
                        if (!(bit % BITS_PER_LONG) && this_end_bit >= bit + BITS_PER_LONG - 1) {
                                do {
                                        if (data[bit / BITS_PER_LONG] != -1)
                                                return false;
                                        bit += BITS_PER_LONG;
                                } while (this_end_bit >= bit + BITS_PER_LONG - 1);
                                continue;
                        }
                        if (!test_bit(bit, data))
                                return false;
                        bit++;
                }
        } else if (mode == BITMAP_OP_TEST_ALL_CLEAR) {
                while (bit <= this_end_bit) {
                        if (!(bit % BITS_PER_LONG) && this_end_bit >= bit + BITS_PER_LONG - 1) {
                                do {
                                        if (data[bit / BITS_PER_LONG] != 0)
                                                return false;
                                        bit += BITS_PER_LONG;
                                } while (this_end_bit >= bit + BITS_PER_LONG - 1);
                                continue;
                        }
                        if (test_bit(bit, data))
                                return false;
                        bit++;
                }
        } else if (mode == BITMAP_OP_SET) {
                while (bit <= this_end_bit) {
                        if (!(bit % BITS_PER_LONG) && this_end_bit >= bit + BITS_PER_LONG - 1) {
                                do {
                                        data[bit / BITS_PER_LONG] = -1;
                                        bit += BITS_PER_LONG;
                                } while (this_end_bit >= bit + BITS_PER_LONG - 1);
                                continue;
                        }
                        __set_bit(bit, data);
                        bit++;
                }
        } else if (mode == BITMAP_OP_CLEAR) {
                if (!bit && this_end_bit == PAGE_SIZE * 8 - 1)
                        clear_page(data);
                else while (bit <= this_end_bit) {
                        if (!(bit % BITS_PER_LONG) && this_end_bit >= bit + BITS_PER_LONG - 1) {
                                do {
                                        data[bit / BITS_PER_LONG] = 0;
                                        bit += BITS_PER_LONG;
                                } while (this_end_bit >= bit + BITS_PER_LONG - 1);
                                continue;
                        }
                        __clear_bit(bit, data);
                        bit++;
                }
        } else {
                BUG();
        }

        if (unlikely(page < end_page)) {
                bit = 0;
                page++;
                goto repeat;
        }

        return true;
}

static void block_bitmap_copy(struct dm_integrity_c *ic, struct page_list *dst, struct page_list *src)
{
        unsigned n_bitmap_pages = DIV_ROUND_UP(ic->n_bitmap_blocks, PAGE_SIZE / BITMAP_BLOCK_SIZE);
        unsigned i;

        for (i = 0; i < n_bitmap_pages; i++) {
                unsigned long *dst_data = lowmem_page_address(dst[i].page);
                unsigned long *src_data = lowmem_page_address(src[i].page);
                copy_page(dst_data, src_data);
        }
}

static struct bitmap_block_status *sector_to_bitmap_block(struct dm_integrity_c *ic, sector_t sector)
{
        unsigned bit = sector >> (ic->sb->log2_sectors_per_block + ic->log2_blocks_per_bitmap_bit);
        unsigned bitmap_block = bit / (BITMAP_BLOCK_SIZE * 8);

        BUG_ON(bitmap_block >= ic->n_bitmap_blocks);
        return &ic->bbs[bitmap_block];
}

static void access_journal_check(struct dm_integrity_c *ic, unsigned section, unsigned offset,
                                 bool e, const char *function)
{
#if defined(CONFIG_DM_DEBUG) || defined(INTERNAL_VERIFY)
        unsigned limit = e ? ic->journal_section_entries : ic->journal_section_sectors;

        if (unlikely(section >= ic->journal_sections) ||
            unlikely(offset >= limit)) {
                DMCRIT("%s: invalid access at (%u,%u), limit (%u,%u)",
                       function, section, offset, ic->journal_sections, limit);
                BUG();
        }
#endif
}

static void page_list_location(struct dm_integrity_c *ic, unsigned section, unsigned offset,
                               unsigned *pl_index, unsigned *pl_offset)
{
        unsigned sector;

        access_journal_check(ic, section, offset, false, "page_list_location");

        sector = section * ic->journal_section_sectors + offset;

        *pl_index = sector >> (PAGE_SHIFT - SECTOR_SHIFT);
        *pl_offset = (sector << SECTOR_SHIFT) & (PAGE_SIZE - 1);
}

static struct journal_sector *access_page_list(struct dm_integrity_c *ic, struct page_list *pl,
                                               unsigned section, unsigned offset, unsigned *n_sectors)
{
        unsigned pl_index, pl_offset;
        char *va;

        page_list_location(ic, section, offset, &pl_index, &pl_offset);

        if (n_sectors)
                *n_sectors = (PAGE_SIZE - pl_offset) >> SECTOR_SHIFT;

        va = lowmem_page_address(pl[pl_index].page);

        return (struct journal_sector *)(va + pl_offset);
}

static struct journal_sector *access_journal(struct dm_integrity_c *ic, unsigned section, unsigned offset)
{
        return access_page_list(ic, ic->journal, section, offset, NULL);
}

static struct journal_entry *access_journal_entry(struct dm_integrity_c *ic, unsigned section, unsigned n)
{
        unsigned rel_sector, offset;
        struct journal_sector *js;

        access_journal_check(ic, section, n, true, "access_journal_entry");

        rel_sector = n % JOURNAL_BLOCK_SECTORS;
        offset = n / JOURNAL_BLOCK_SECTORS;

        js = access_journal(ic, section, rel_sector);
        return (struct journal_entry *)((char *)js + offset * ic->journal_entry_size);
}

static struct journal_sector *access_journal_data(struct dm_integrity_c *ic, unsigned section, unsigned n)
{
        n <<= ic->sb->log2_sectors_per_block;

        n += JOURNAL_BLOCK_SECTORS;

        access_journal_check(ic, section, n, false, "access_journal_data");

        return access_journal(ic, section, n);
}

static void section_mac(struct dm_integrity_c *ic, unsigned section, __u8 result[JOURNAL_MAC_SIZE])
{
        SHASH_DESC_ON_STACK(desc, ic->journal_mac);
        int r;
        unsigned j, size;

        desc->tfm = ic->journal_mac;

        r = crypto_shash_init(desc);
        if (unlikely(r < 0)) {
                dm_integrity_io_error(ic, "crypto_shash_init", r);
                goto err;
        }

        if (ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_HMAC)) {
                __le64 section_le;

                r = crypto_shash_update(desc, (__u8 *)&ic->sb->salt, SALT_SIZE);
                if (unlikely(r < 0)) {
                        dm_integrity_io_error(ic, "crypto_shash_update", r);
                        goto err;
                }

                section_le = cpu_to_le64(section);
                r = crypto_shash_update(desc, (__u8 *)&section_le, sizeof section_le);
                if (unlikely(r < 0)) {
                        dm_integrity_io_error(ic, "crypto_shash_update", r);
                        goto err;
                }
        }

        for (j = 0; j < ic->journal_section_entries; j++) {
                struct journal_entry *je = access_journal_entry(ic, section, j);
                r = crypto_shash_update(desc, (__u8 *)&je->u.sector, sizeof je->u.sector);
                if (unlikely(r < 0)) {
                        dm_integrity_io_error(ic, "crypto_shash_update", r);
                        goto err;
                }
        }

        size = crypto_shash_digestsize(ic->journal_mac);

        if (likely(size <= JOURNAL_MAC_SIZE)) {
                r = crypto_shash_final(desc, result);
                if (unlikely(r < 0)) {
                        dm_integrity_io_error(ic, "crypto_shash_final", r);
                        goto err;
                }
                memset(result + size, 0, JOURNAL_MAC_SIZE - size);
        } else {
                __u8 digest[HASH_MAX_DIGESTSIZE];

                if (WARN_ON(size > sizeof(digest))) {
                        dm_integrity_io_error(ic, "digest_size", -EINVAL);
                        goto err;
                }
                r = crypto_shash_final(desc, digest);
                if (unlikely(r < 0)) {
                        dm_integrity_io_error(ic, "crypto_shash_final", r);
                        goto err;
                }
                memcpy(result, digest, JOURNAL_MAC_SIZE);
        }

        return;
err:
        memset(result, 0, JOURNAL_MAC_SIZE);
}

static void rw_section_mac(struct dm_integrity_c *ic, unsigned section, bool wr)
{
        __u8 result[JOURNAL_MAC_SIZE];
        unsigned j;

        if (!ic->journal_mac)
                return;

        section_mac(ic, section, result);

        for (j = 0; j < JOURNAL_BLOCK_SECTORS; j++) {
                struct journal_sector *js = access_journal(ic, section, j);

                if (likely(wr))
                        memcpy(&js->mac, result + (j * JOURNAL_MAC_PER_SECTOR), JOURNAL_MAC_PER_SECTOR);
                else {
                        if (memcmp(&js->mac, result + (j * JOURNAL_MAC_PER_SECTOR), JOURNAL_MAC_PER_SECTOR))
                                dm_integrity_io_error(ic, "journal mac", -EILSEQ);
                }
        }
}

static void complete_journal_op(void *context)
{
        struct journal_completion *comp = context;
        BUG_ON(!atomic_read(&comp->in_flight));
        if (likely(atomic_dec_and_test(&comp->in_flight)))
                complete(&comp->comp);
}

static void xor_journal(struct dm_integrity_c *ic, bool encrypt, unsigned section,
                        unsigned n_sections, struct journal_completion *comp)
{
        struct async_submit_ctl submit;
        size_t n_bytes = (size_t)(n_sections * ic->journal_section_sectors) << SECTOR_SHIFT;
        unsigned pl_index, pl_offset, section_index;
        struct page_list *source_pl, *target_pl;

        if (likely(encrypt)) {
                source_pl = ic->journal;
                target_pl = ic->journal_io;
        } else {
                source_pl = ic->journal_io;
                target_pl = ic->journal;
        }

        page_list_location(ic, section, 0, &pl_index, &pl_offset);

        atomic_add(roundup(pl_offset + n_bytes, PAGE_SIZE) >> PAGE_SHIFT, &comp->in_flight);

        init_async_submit(&submit, ASYNC_TX_XOR_ZERO_DST, NULL, complete_journal_op, comp, NULL);

        section_index = pl_index;

        do {
                size_t this_step;
                struct page *src_pages[2];
                struct page *dst_page;

                while (unlikely(pl_index == section_index)) {
                        unsigned dummy;
                        if (likely(encrypt))
                                rw_section_mac(ic, section, true);
                        section++;
                        n_sections--;
                        if (!n_sections)
                                break;
                        page_list_location(ic, section, 0, &section_index, &dummy);
                }

                this_step = min(n_bytes, (size_t)PAGE_SIZE - pl_offset);
                dst_page = target_pl[pl_index].page;
                src_pages[0] = source_pl[pl_index].page;
                src_pages[1] = ic->journal_xor[pl_index].page;

                async_xor(dst_page, src_pages, pl_offset, 2, this_step, &submit);

                pl_index++;
                pl_offset = 0;
                n_bytes -= this_step;
        } while (n_bytes);

        BUG_ON(n_sections);

        async_tx_issue_pending_all();
}

static void complete_journal_encrypt(struct crypto_async_request *req, int err)
{
        struct journal_completion *comp = req->data;
        if (unlikely(err)) {
                if (likely(err == -EINPROGRESS)) {
                        complete(&comp->ic->crypto_backoff);
                        return;
                }
                dm_integrity_io_error(comp->ic, "asynchronous encrypt", err);
        }
        complete_journal_op(comp);
}

static bool do_crypt(bool encrypt, struct skcipher_request *req, struct journal_completion *comp)
{
        int r;
        skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
                                      complete_journal_encrypt, comp);
        if (likely(encrypt))
                r = crypto_skcipher_encrypt(req);
        else
                r = crypto_skcipher_decrypt(req);
        if (likely(!r))
                return false;
        if (likely(r == -EINPROGRESS))
                return true;
        if (likely(r == -EBUSY)) {
                wait_for_completion(&comp->ic->crypto_backoff);
                reinit_completion(&comp->ic->crypto_backoff);
                return true;
        }
        dm_integrity_io_error(comp->ic, "encrypt", r);
        return false;
}

static void crypt_journal(struct dm_integrity_c *ic, bool encrypt, unsigned section,
                          unsigned n_sections, struct journal_completion *comp)
{
        struct scatterlist **source_sg;
        struct scatterlist **target_sg;

        atomic_add(2, &comp->in_flight);

        if (likely(encrypt)) {
                source_sg = ic->journal_scatterlist;
                target_sg = ic->journal_io_scatterlist;
        } else {
                source_sg = ic->journal_io_scatterlist;
                target_sg = ic->journal_scatterlist;
        }

        do {
                struct skcipher_request *req;
                unsigned ivsize;
                char *iv;

                if (likely(encrypt))
                        rw_section_mac(ic, section, true);

                req = ic->sk_requests[section];
                ivsize = crypto_skcipher_ivsize(ic->journal_crypt);
                iv = req->iv;

                memcpy(iv, iv + ivsize, ivsize);

                req->src = source_sg[section];
                req->dst = target_sg[section];

                if (unlikely(do_crypt(encrypt, req, comp)))
                        atomic_inc(&comp->in_flight);

                section++;
                n_sections--;
        } while (n_sections);

        atomic_dec(&comp->in_flight);
        complete_journal_op(comp);
}

static void encrypt_journal(struct dm_integrity_c *ic, bool encrypt, unsigned section,
                            unsigned n_sections, struct journal_completion *comp)
{
        if (ic->journal_xor)
                return xor_journal(ic, encrypt, section, n_sections, comp);
        else
                return crypt_journal(ic, encrypt, section, n_sections, comp);
}

static void complete_journal_io(unsigned long error, void *context)
{
        struct journal_completion *comp = context;
        if (unlikely(error != 0))
                dm_integrity_io_error(comp->ic, "writing journal", -EIO);
        complete_journal_op(comp);
}

static void rw_journal_sectors(struct dm_integrity_c *ic, int op, int op_flags,
                               unsigned sector, unsigned n_sectors, struct journal_completion *comp)
{
        struct dm_io_request io_req;
        struct dm_io_region io_loc;
        unsigned pl_index, pl_offset;
        int r;

        if (unlikely(dm_integrity_failed(ic))) {
                if (comp)
                        complete_journal_io(-1UL, comp);
                return;
        }

        pl_index = sector >> (PAGE_SHIFT - SECTOR_SHIFT);
        pl_offset = (sector << SECTOR_SHIFT) & (PAGE_SIZE - 1);

        io_req.bi_op = op;
        io_req.bi_op_flags = op_flags;
        io_req.mem.type = DM_IO_PAGE_LIST;
        if (ic->journal_io)
                io_req.mem.ptr.pl = &ic->journal_io[pl_index];
        else
                io_req.mem.ptr.pl = &ic->journal[pl_index];
        io_req.mem.offset = pl_offset;
        if (likely(comp != NULL)) {
                io_req.notify.fn = complete_journal_io;
                io_req.notify.context = comp;
        } else {
                io_req.notify.fn = NULL;
        }
        io_req.client = ic->io;
        io_loc.bdev = ic->meta_dev ? ic->meta_dev->bdev : ic->dev->bdev;
        io_loc.sector = ic->start + SB_SECTORS + sector;
        io_loc.count = n_sectors;

        r = dm_io(&io_req, 1, &io_loc, NULL);
        if (unlikely(r)) {
                dm_integrity_io_error(ic, op == REQ_OP_READ ? "reading journal" : "writing journal", r);
                if (comp) {
                        WARN_ONCE(1, "asynchronous dm_io failed: %d", r);
                        complete_journal_io(-1UL, comp);
                }
        }
}

static void rw_journal(struct dm_integrity_c *ic, int op, int op_flags, unsigned section,
                       unsigned n_sections, struct journal_completion *comp)
{
        unsigned sector, n_sectors;

        sector = section * ic->journal_section_sectors;
        n_sectors = n_sections * ic->journal_section_sectors;

        rw_journal_sectors(ic, op, op_flags, sector, n_sectors, comp);
}

static void write_journal(struct dm_integrity_c *ic, unsigned commit_start, unsigned commit_sections)
{
        struct journal_completion io_comp;
        struct journal_completion crypt_comp_1;
        struct journal_completion crypt_comp_2;
        unsigned i;

        io_comp.ic = ic;
        init_completion(&io_comp.comp);

        if (commit_start + commit_sections <= ic->journal_sections) {
                io_comp.in_flight = (atomic_t)ATOMIC_INIT(1);
                if (ic->journal_io) {
                        crypt_comp_1.ic = ic;
                        init_completion(&crypt_comp_1.comp);
                        crypt_comp_1.in_flight = (atomic_t)ATOMIC_INIT(0);
                        encrypt_journal(ic, true, commit_start, commit_sections, &crypt_comp_1);
                        wait_for_completion_io(&crypt_comp_1.comp);
                } else {
                        for (i = 0; i < commit_sections; i++)
                                rw_section_mac(ic, commit_start + i, true);
                }
                rw_journal(ic, REQ_OP_WRITE, REQ_FUA | REQ_SYNC, commit_start,
                           commit_sections, &io_comp);
        } else {
                unsigned to_end;
                io_comp.in_flight = (atomic_t)ATOMIC_INIT(2);
                to_end = ic->journal_sections - commit_start;
                if (ic->journal_io) {
                        crypt_comp_1.ic = ic;
                        init_completion(&crypt_comp_1.comp);
                        crypt_comp_1.in_flight = (atomic_t)ATOMIC_INIT(0);
                        encrypt_journal(ic, true, commit_start, to_end, &crypt_comp_1);
                        if (try_wait_for_completion(&crypt_comp_1.comp)) {
                                rw_journal(ic, REQ_OP_WRITE, REQ_FUA, commit_start, to_end, &io_comp);
                                reinit_completion(&crypt_comp_1.comp);
                                crypt_comp_1.in_flight = (atomic_t)ATOMIC_INIT(0);
                                encrypt_journal(ic, true, 0, commit_sections - to_end, &crypt_comp_1);
                                wait_for_completion_io(&crypt_comp_1.comp);
                        } else {
                                crypt_comp_2.ic = ic;
                                init_completion(&crypt_comp_2.comp);
                                crypt_comp_2.in_flight = (atomic_t)ATOMIC_INIT(0);
                                encrypt_journal(ic, true, 0, commit_sections - to_end, &crypt_comp_2);
                                wait_for_completion_io(&crypt_comp_1.comp);
                                rw_journal(ic, REQ_OP_WRITE, REQ_FUA, commit_start, to_end, &io_comp);
                                wait_for_completion_io(&crypt_comp_2.comp);
                        }
                } else {
                        for (i = 0; i < to_end; i++)
                                rw_section_mac(ic, commit_start + i, true);
                        rw_journal(ic, REQ_OP_WRITE, REQ_FUA, commit_start, to_end, &io_comp);
                        for (i = 0; i < commit_sections - to_end; i++)
                                rw_section_mac(ic, i, true);
                }
                rw_journal(ic, REQ_OP_WRITE, REQ_FUA, 0, commit_sections - to_end, &io_comp);
        }

        wait_for_completion_io(&io_comp.comp);
}

static void copy_from_journal(struct dm_integrity_c *ic, unsigned section, unsigned offset,
                              unsigned n_sectors, sector_t target, io_notify_fn fn, void *data)
{
        struct dm_io_request io_req;
        struct dm_io_region io_loc;
        int r;
        unsigned sector, pl_index, pl_offset;

        BUG_ON((target | n_sectors | offset) & (unsigned)(ic->sectors_per_block - 1));

        if (unlikely(dm_integrity_failed(ic))) {
                fn(-1UL, data);
                return;
        }

        sector = section * ic->journal_section_sectors + JOURNAL_BLOCK_SECTORS + offset;

        pl_index = sector >> (PAGE_SHIFT - SECTOR_SHIFT);
        pl_offset = (sector << SECTOR_SHIFT) & (PAGE_SIZE - 1);

        io_req.bi_op = REQ_OP_WRITE;
        io_req.bi_op_flags = 0;
        io_req.mem.type = DM_IO_PAGE_LIST;
        io_req.mem.ptr.pl = &ic->journal[pl_index];
        io_req.mem.offset = pl_offset;
        io_req.notify.fn = fn;
        io_req.notify.context = data;
        io_req.client = ic->io;
        io_loc.bdev = ic->dev->bdev;
        io_loc.sector = target;
        io_loc.count = n_sectors;

        r = dm_io(&io_req, 1, &io_loc, NULL);
        if (unlikely(r)) {
                WARN_ONCE(1, "asynchronous dm_io failed: %d", r);
                fn(-1UL, data);
        }
}

static bool ranges_overlap(struct dm_integrity_range *range1, struct dm_integrity_range *range2)
{
        return range1->logical_sector < range2->logical_sector + range2->n_sectors &&
               range1->logical_sector + range1->n_sectors > range2->logical_sector;
}

static bool add_new_range(struct dm_integrity_c *ic, struct dm_integrity_range *new_range, bool check_waiting)
{
        struct rb_node **n = &ic->in_progress.rb_node;
        struct rb_node *parent;

        BUG_ON((new_range->logical_sector | new_range->n_sectors) & (unsigned)(ic->sectors_per_block - 1));

        if (likely(check_waiting)) {
                struct dm_integrity_range *range;
                list_for_each_entry(range, &ic->wait_list, wait_entry) {
                        if (unlikely(ranges_overlap(range, new_range)))
                                return false;
                }
        }

        parent = NULL;

        while (*n) {
                struct dm_integrity_range *range = container_of(*n, struct dm_integrity_range, node);

                parent = *n;
                if (new_range->logical_sector + new_range->n_sectors <= range->logical_sector) {
                        n = &range->node.rb_left;
                } else if (new_range->logical_sector >= range->logical_sector + range->n_sectors) {
                        n = &range->node.rb_right;
                } else {
                        return false;
                }
        }

        rb_link_node(&new_range->node, parent, n);
        rb_insert_color(&new_range->node, &ic->in_progress);

        return true;
}

static void remove_range_unlocked(struct dm_integrity_c *ic, struct dm_integrity_range *range)
{
        rb_erase(&range->node, &ic->in_progress);
        while (unlikely(!list_empty(&ic->wait_list))) {
                struct dm_integrity_range *last_range =
                        list_first_entry(&ic->wait_list, struct dm_integrity_range, wait_entry);
                struct task_struct *last_range_task;
                last_range_task = last_range->task;
                list_del(&last_range->wait_entry);
                if (!add_new_range(ic, last_range, false)) {
                        last_range->task = last_range_task;
                        list_add(&last_range->wait_entry, &ic->wait_list);
                        break;
                }
                last_range->waiting = false;
                wake_up_process(last_range_task);
        }
}

static void remove_range(struct dm_integrity_c *ic, struct dm_integrity_range *range)
{
        unsigned long flags;

        spin_lock_irqsave(&ic->endio_wait.lock, flags);
        remove_range_unlocked(ic, range);
        spin_unlock_irqrestore(&ic->endio_wait.lock, flags);
}

static void wait_and_add_new_range(struct dm_integrity_c *ic, struct dm_integrity_range *new_range)
{
        new_range->waiting = true;
        list_add_tail(&new_range->wait_entry, &ic->wait_list);
        new_range->task = current;
        do {
                __set_current_state(TASK_UNINTERRUPTIBLE);
                spin_unlock_irq(&ic->endio_wait.lock);
                io_schedule();
                spin_lock_irq(&ic->endio_wait.lock);
        } while (unlikely(new_range->waiting));
}

static void add_new_range_and_wait(struct dm_integrity_c *ic, struct dm_integrity_range *new_range)
{
        if (unlikely(!add_new_range(ic, new_range, true)))
                wait_and_add_new_range(ic, new_range);
}

static void init_journal_node(struct journal_node *node)
{
        RB_CLEAR_NODE(&node->node);
        node->sector = (sector_t)-1;
}

static void add_journal_node(struct dm_integrity_c *ic, struct journal_node *node, sector_t sector)
{
        struct rb_node **link;
        struct rb_node *parent;

        node->sector = sector;
        BUG_ON(!RB_EMPTY_NODE(&node->node));

        link = &ic->journal_tree_root.rb_node;
        parent = NULL;

        while (*link) {
                struct journal_node *j;
                parent = *link;
                j = container_of(parent, struct journal_node, node);
                if (sector < j->sector)
                        link = &j->node.rb_left;
                else
                        link = &j->node.rb_right;
        }

        rb_link_node(&node->node, parent, link);
        rb_insert_color(&node->node, &ic->journal_tree_root);
}

static void remove_journal_node(struct dm_integrity_c *ic, struct journal_node *node)
{
        BUG_ON(RB_EMPTY_NODE(&node->node));
        rb_erase(&node->node, &ic->journal_tree_root);
        init_journal_node(node);
}

#define NOT_FOUND       (-1U)

static unsigned find_journal_node(struct dm_integrity_c *ic, sector_t sector, sector_t *next_sector)
{
        struct rb_node *n = ic->journal_tree_root.rb_node;
        unsigned found = NOT_FOUND;
        *next_sector = (sector_t)-1;
        while (n) {
                struct journal_node *j = container_of(n, struct journal_node, node);
                if (sector == j->sector) {
                        found = j - ic->journal_tree;
                }
                if (sector < j->sector) {
                        *next_sector = j->sector;
                        n = j->node.rb_left;
                } else {
                        n = j->node.rb_right;
                }
        }

        return found;
}

static bool test_journal_node(struct dm_integrity_c *ic, unsigned pos, sector_t sector)
{
        struct journal_node *node, *next_node;
        struct rb_node *next;

        if (unlikely(pos >= ic->journal_entries))
                return false;
        node = &ic->journal_tree[pos];
        if (unlikely(RB_EMPTY_NODE(&node->node)))
                return false;
        if (unlikely(node->sector != sector))
                return false;

        next = rb_next(&node->node);
        if (unlikely(!next))
                return true;

        next_node = container_of(next, struct journal_node, node);
        return next_node->sector != sector;
}

static bool find_newer_committed_node(struct dm_integrity_c *ic, struct journal_node *node)
{
        struct rb_node *next;
        struct journal_node *next_node;
        unsigned next_section;

        BUG_ON(RB_EMPTY_NODE(&node->node));

        next = rb_next(&node->node);
        if (unlikely(!next))
                return false;

        next_node = container_of(next, struct journal_node, node);

        if (next_node->sector != node->sector)
                return false;

        next_section = (unsigned)(next_node - ic->journal_tree) / ic->journal_section_entries;
        if (next_section >= ic->committed_section &&
            next_section < ic->committed_section + ic->n_committed_sections)
                return true;
        if (next_section + ic->journal_sections < ic->committed_section + ic->n_committed_sections)
                return true;

        return false;
}

#define TAG_READ        0
#define TAG_WRITE       1
#define TAG_CMP         2

static int dm_integrity_rw_tag(struct dm_integrity_c *ic, unsigned char *tag, sector_t *metadata_block,
                               unsigned *metadata_offset, unsigned total_size, int op)
{
#define MAY_BE_FILLER           1
#define MAY_BE_HASH             2
        unsigned hash_offset = 0;
        unsigned may_be = MAY_BE_HASH | (ic->discard ? MAY_BE_FILLER : 0);

        do {
                unsigned char *data, *dp;
                struct dm_buffer *b;
                unsigned to_copy;
                int r;

                r = dm_integrity_failed(ic);
                if (unlikely(r))
                        return r;

                data = dm_bufio_read(ic->bufio, *metadata_block, &b);
                if (IS_ERR(data))
                        return PTR_ERR(data);

                to_copy = min((1U << SECTOR_SHIFT << ic->log2_buffer_sectors) - *metadata_offset, total_size);
                dp = data + *metadata_offset;
                if (op == TAG_READ) {
                        memcpy(tag, dp, to_copy);
                } else if (op == TAG_WRITE) {
                        if (memcmp(dp, tag, to_copy)) {
                                memcpy(dp, tag, to_copy);
                                dm_bufio_mark_partial_buffer_dirty(b, *metadata_offset, *metadata_offset + to_copy);
                        }
                } else {
                        /* e.g.: op == TAG_CMP */

                        if (likely(is_power_of_2(ic->tag_size))) {
                                if (unlikely(memcmp(dp, tag, to_copy)))
                                        if (unlikely(!ic->discard) ||
                                            unlikely(memchr_inv(dp, DISCARD_FILLER, to_copy) != NULL)) {
                                                goto thorough_test;
                                }
                        } else {
                                unsigned i, ts;
thorough_test:
                                ts = total_size;

                                for (i = 0; i < to_copy; i++, ts--) {
                                        if (unlikely(dp[i] != tag[i]))
                                                may_be &= ~MAY_BE_HASH;
                                        if (likely(dp[i] != DISCARD_FILLER))
                                                may_be &= ~MAY_BE_FILLER;
                                        hash_offset++;
                                        if (unlikely(hash_offset == ic->tag_size)) {
                                                if (unlikely(!may_be)) {
                                                        dm_bufio_release(b);
                                                        return ts;
                                                }
                                                hash_offset = 0;
                                                may_be = MAY_BE_HASH | (ic->discard ? MAY_BE_FILLER : 0);
                                        }
                                }
                        }
                }
                dm_bufio_release(b);

                tag += to_copy;
                *metadata_offset += to_copy;
                if (unlikely(*metadata_offset == 1U << SECTOR_SHIFT << ic->log2_buffer_sectors)) {
                        (*metadata_block)++;
                        *metadata_offset = 0;
                }

                if (unlikely(!is_power_of_2(ic->tag_size))) {
                        hash_offset = (hash_offset + to_copy) % ic->tag_size;
                }

                total_size -= to_copy;
        } while (unlikely(total_size));

        return 0;
#undef MAY_BE_FILLER
#undef MAY_BE_HASH
}

struct flush_request {
        struct dm_io_request io_req;
        struct dm_io_region io_reg;
        struct dm_integrity_c *ic;
        struct completion comp;
};

static void flush_notify(unsigned long error, void *fr_)
{
        struct flush_request *fr = fr_;
        if (unlikely(error != 0))
                dm_integrity_io_error(fr->ic, "flushing disk cache", -EIO);
        complete(&fr->comp);
}

static void dm_integrity_flush_buffers(struct dm_integrity_c *ic, bool flush_data)
{
        int r;

        struct flush_request fr;

        if (!ic->meta_dev)
                flush_data = false;
        if (flush_data) {
                fr.io_req.bi_op = REQ_OP_WRITE,
                fr.io_req.bi_op_flags = REQ_PREFLUSH | REQ_SYNC,
                fr.io_req.mem.type = DM_IO_KMEM,
                fr.io_req.mem.ptr.addr = NULL,
                fr.io_req.notify.fn = flush_notify,
                fr.io_req.notify.context = &fr;
                fr.io_req.client = dm_bufio_get_dm_io_client(ic->bufio),
                fr.io_reg.bdev = ic->dev->bdev,
                fr.io_reg.sector = 0,
                fr.io_reg.count = 0,
                fr.ic = ic;
                init_completion(&fr.comp);
                r = dm_io(&fr.io_req, 1, &fr.io_reg, NULL);
                BUG_ON(r);
        }

        r = dm_bufio_write_dirty_buffers(ic->bufio);
        if (unlikely(r))
                dm_integrity_io_error(ic, "writing tags", r);

        if (flush_data)
                wait_for_completion(&fr.comp);
}

static void sleep_on_endio_wait(struct dm_integrity_c *ic)
{
        DECLARE_WAITQUEUE(wait, current);
        __add_wait_queue(&ic->endio_wait, &wait);
        __set_current_state(TASK_UNINTERRUPTIBLE);
        spin_unlock_irq(&ic->endio_wait.lock);
        io_schedule();
        spin_lock_irq(&ic->endio_wait.lock);
        __remove_wait_queue(&ic->endio_wait, &wait);
}

static void autocommit_fn(struct timer_list *t)
{
        struct dm_integrity_c *ic = from_timer(ic, t, autocommit_timer);

        if (likely(!dm_integrity_failed(ic)))
                queue_work(ic->commit_wq, &ic->commit_work);
}

static void schedule_autocommit(struct dm_integrity_c *ic)
{
        if (!timer_pending(&ic->autocommit_timer))
                mod_timer(&ic->autocommit_timer, jiffies + ic->autocommit_jiffies);
}

static void submit_flush_bio(struct dm_integrity_c *ic, struct dm_integrity_io *dio)
{
        struct bio *bio;
        unsigned long flags;

        spin_lock_irqsave(&ic->endio_wait.lock, flags);
        bio = dm_bio_from_per_bio_data(dio, sizeof(struct dm_integrity_io));
        bio_list_add(&ic->flush_bio_list, bio);
        spin_unlock_irqrestore(&ic->endio_wait.lock, flags);

        queue_work(ic->commit_wq, &ic->commit_work);
}

static void do_endio(struct dm_integrity_c *ic, struct bio *bio)
{
        int r = dm_integrity_failed(ic);
        if (unlikely(r) && !bio->bi_status)
                bio->bi_status = errno_to_blk_status(r);
        if (unlikely(ic->synchronous_mode) && bio_op(bio) == REQ_OP_WRITE) {
                unsigned long flags;
                spin_lock_irqsave(&ic->endio_wait.lock, flags);
                bio_list_add(&ic->synchronous_bios, bio);
                queue_delayed_work(ic->commit_wq, &ic->bitmap_flush_work, 0);
                spin_unlock_irqrestore(&ic->endio_wait.lock, flags);
                return;
        }
        bio_endio(bio);
}

static void do_endio_flush(struct dm_integrity_c *ic, struct dm_integrity_io *dio)
{
        struct bio *bio = dm_bio_from_per_bio_data(dio, sizeof(struct dm_integrity_io));

        if (unlikely(dio->fua) && likely(!bio->bi_status) && likely(!dm_integrity_failed(ic)))
                submit_flush_bio(ic, dio);
        else
                do_endio(ic, bio);
}

static void dec_in_flight(struct dm_integrity_io *dio)
{
        if (atomic_dec_and_test(&dio->in_flight)) {
                struct dm_integrity_c *ic = dio->ic;
                struct bio *bio;

                remove_range(ic, &dio->range);

                if (dio->op == REQ_OP_WRITE || unlikely(dio->op == REQ_OP_DISCARD))
                        schedule_autocommit(ic);

                bio = dm_bio_from_per_bio_data(dio, sizeof(struct dm_integrity_io));

                if (unlikely(dio->bi_status) && !bio->bi_status)
                        bio->bi_status = dio->bi_status;
                if (likely(!bio->bi_status) && unlikely(bio_sectors(bio) != dio->range.n_sectors)) {
                        dio->range.logical_sector += dio->range.n_sectors;
                        bio_advance(bio, dio->range.n_sectors << SECTOR_SHIFT);
                        INIT_WORK(&dio->work, integrity_bio_wait);
                        queue_work(ic->offload_wq, &dio->work);
                        return;
                }
                do_endio_flush(ic, dio);
        }
}

static void integrity_end_io(struct bio *bio)
{
        struct dm_integrity_io *dio = dm_per_bio_data(bio, sizeof(struct dm_integrity_io));

        dm_bio_restore(&dio->bio_details, bio);
        if (bio->bi_integrity)
                bio->bi_opf |= REQ_INTEGRITY;

        if (dio->completion)
                complete(dio->completion);

        dec_in_flight(dio);
}

static void integrity_sector_checksum(struct dm_integrity_c *ic, sector_t sector,
                                      const char *data, char *result)
{
        __le64 sector_le = cpu_to_le64(sector);
        SHASH_DESC_ON_STACK(req, ic->internal_hash);
        int r;
        unsigned digest_size;

        req->tfm = ic->internal_hash;

        r = crypto_shash_init(req);
        if (unlikely(r < 0)) {
                dm_integrity_io_error(ic, "crypto_shash_init", r);
                goto failed;
        }

        if (ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_HMAC)) {
                r = crypto_shash_update(req, (__u8 *)&ic->sb->salt, SALT_SIZE);
                if (unlikely(r < 0)) {
                        dm_integrity_io_error(ic, "crypto_shash_update", r);
                        goto failed;
                }
        }

        r = crypto_shash_update(req, (const __u8 *)&sector_le, sizeof sector_le);
        if (unlikely(r < 0)) {
                dm_integrity_io_error(ic, "crypto_shash_update", r);
                goto failed;
        }

        r = crypto_shash_update(req, data, ic->sectors_per_block << SECTOR_SHIFT);
        if (unlikely(r < 0)) {
                dm_integrity_io_error(ic, "crypto_shash_update", r);
                goto failed;
        }

        r = crypto_shash_final(req, result);
        if (unlikely(r < 0)) {
                dm_integrity_io_error(ic, "crypto_shash_final", r);
                goto failed;
        }

        digest_size = crypto_shash_digestsize(ic->internal_hash);
        if (unlikely(digest_size < ic->tag_size))
                memset(result + digest_size, 0, ic->tag_size - digest_size);

        return;

failed:
        /* this shouldn't happen anyway, the hash functions have no reason to fail */
        get_random_bytes(result, ic->tag_size);
}

static void integrity_metadata(struct work_struct *w)
{
        struct dm_integrity_io *dio = container_of(w, struct dm_integrity_io, work);
        struct dm_integrity_c *ic = dio->ic;

        int r;

        if (ic->internal_hash) {
                struct bvec_iter iter;
                struct bio_vec bv;
                unsigned digest_size = crypto_shash_digestsize(ic->internal_hash);
                struct bio *bio = dm_bio_from_per_bio_data(dio, sizeof(struct dm_integrity_io));
                char *checksums;
                unsigned extra_space = unlikely(digest_size > ic->tag_size) ? digest_size - ic->tag_size : 0;
                char checksums_onstack[max((size_t)HASH_MAX_DIGESTSIZE, MAX_TAG_SIZE)];
                sector_t sector;
                unsigned sectors_to_process;

                if (unlikely(ic->mode == 'R'))
                        goto skip_io;

                if (likely(dio->op != REQ_OP_DISCARD))
                        checksums = kmalloc((PAGE_SIZE >> SECTOR_SHIFT >> ic->sb->log2_sectors_per_block) * ic->tag_size + extra_space,
                                            GFP_NOIO | __GFP_NORETRY | __GFP_NOWARN);
                else
                        checksums = kmalloc(PAGE_SIZE, GFP_NOIO | __GFP_NORETRY | __GFP_NOWARN);
                if (!checksums) {
                        checksums = checksums_onstack;
                        if (WARN_ON(extra_space &&
                                    digest_size > sizeof(checksums_onstack))) {
                                r = -EINVAL;
                                goto error;
                        }
                }

                if (unlikely(dio->op == REQ_OP_DISCARD)) {
                        sector_t bi_sector = dio->bio_details.bi_iter.bi_sector;
                        unsigned bi_size = dio->bio_details.bi_iter.bi_size;
                        unsigned max_size = likely(checksums != checksums_onstack) ? PAGE_SIZE : HASH_MAX_DIGESTSIZE;
                        unsigned max_blocks = max_size / ic->tag_size;
                        memset(checksums, DISCARD_FILLER, max_size);

                        while (bi_size) {
                                unsigned this_step_blocks = bi_size >> (SECTOR_SHIFT + ic->sb->log2_sectors_per_block);
                                this_step_blocks = min(this_step_blocks, max_blocks);
                                r = dm_integrity_rw_tag(ic, checksums, &dio->metadata_block, &dio->metadata_offset,
                                                        this_step_blocks * ic->tag_size, TAG_WRITE);
                                if (unlikely(r)) {
                                        if (likely(checksums != checksums_onstack))
                                                kfree(checksums);
                                        goto error;
                                }

                                /*if (bi_size < this_step_blocks << (SECTOR_SHIFT + ic->sb->log2_sectors_per_block)) {
                                        printk("BUGG: bi_sector: %llx, bi_size: %u\n", bi_sector, bi_size);
                                        printk("BUGG: this_step_blocks: %u\n", this_step_blocks);
                                        BUG();
                                }*/
                                bi_size -= this_step_blocks << (SECTOR_SHIFT + ic->sb->log2_sectors_per_block);
                                bi_sector += this_step_blocks << ic->sb->log2_sectors_per_block;
                        }

                        if (likely(checksums != checksums_onstack))
                                kfree(checksums);
                        goto skip_io;
                }

                sector = dio->range.logical_sector;
                sectors_to_process = dio->range.n_sectors;

                __bio_for_each_segment(bv, bio, iter, dio->bio_details.bi_iter) {
                        unsigned pos;
                        char *mem, *checksums_ptr;

again:
                        mem = (char *)kmap_atomic(bv.bv_page) + bv.bv_offset;
                        pos = 0;
                        checksums_ptr = checksums;
                        do {
                                integrity_sector_checksum(ic, sector, mem + pos, checksums_ptr);
                                checksums_ptr += ic->tag_size;
                                sectors_to_process -= ic->sectors_per_block;
                                pos += ic->sectors_per_block << SECTOR_SHIFT;
                                sector += ic->sectors_per_block;
                        } while (pos < bv.bv_len && sectors_to_process && checksums != checksums_onstack);
                        kunmap_atomic(mem);

                        r = dm_integrity_rw_tag(ic, checksums, &dio->metadata_block, &dio->metadata_offset,
                                                checksums_ptr - checksums, dio->op == REQ_OP_READ ? TAG_CMP : TAG_WRITE);
                        if (unlikely(r)) {
                                if (r > 0) {
                                        char b[BDEVNAME_SIZE];
                                        DMERR_LIMIT("%s: Checksum failed at sector 0x%llx", bio_devname(bio, b),
                                                    (sector - ((r + ic->tag_size - 1) / ic->tag_size)));
                                        r = -EILSEQ;
                                        atomic64_inc(&ic->number_of_mismatches);
                                }
                                if (likely(checksums != checksums_onstack))
                                        kfree(checksums);
                                goto error;
                        }

                        if (!sectors_to_process)
                                break;

                        if (unlikely(pos < bv.bv_len)) {
                                bv.bv_offset += pos;
                                bv.bv_len -= pos;
                                goto again;
                        }
                }

                if (likely(checksums != checksums_onstack))
                        kfree(checksums);
        } else {
                struct bio_integrity_payload *bip = dio->bio_details.bi_integrity;

                if (bip) {
                        struct bio_vec biv;
                        struct bvec_iter iter;
                        unsigned data_to_process = dio->range.n_sectors;
                        sector_to_block(ic, data_to_process);
                        data_to_process *= ic->tag_size;

                        bip_for_each_vec(biv, bip, iter) {
                                unsigned char *tag;
                                unsigned this_len;

                                BUG_ON(PageHighMem(biv.bv_page));
                                tag = lowmem_page_address(biv.bv_page) + biv.bv_offset;
                                this_len = min(biv.bv_len, data_to_process);
                                r = dm_integrity_rw_tag(ic, tag, &dio->metadata_block, &dio->metadata_offset,
                                                        this_len, dio->op == REQ_OP_READ ? TAG_READ : TAG_WRITE);
                                if (unlikely(r))
                                        goto error;
                                data_to_process -= this_len;
                                if (!data_to_process)
                                        break;
                        }
                }
        }
skip_io:
        dec_in_flight(dio);
        return;
error:
        dio->bi_status = errno_to_blk_status(r);
        dec_in_flight(dio);
}

static int dm_integrity_map(struct dm_target *ti, struct bio *bio)
{
        struct dm_integrity_c *ic = ti->private;
        struct dm_integrity_io *dio = dm_per_bio_data(bio, sizeof(struct dm_integrity_io));
        struct bio_integrity_payload *bip;

        sector_t area, offset;

        dio->ic = ic;
        dio->bi_status = 0;
        dio->op = bio_op(bio);

        if (unlikely(dio->op == REQ_OP_DISCARD)) {
                if (ti->max_io_len) {
                        sector_t sec = dm_target_offset(ti, bio->bi_iter.bi_sector);
                        unsigned log2_max_io_len = __fls(ti->max_io_len);
                        sector_t start_boundary = sec >> log2_max_io_len;
                        sector_t end_boundary = (sec + bio_sectors(bio) - 1) >> log2_max_io_len;
                        if (start_boundary < end_boundary) {
                                sector_t len = ti->max_io_len - (sec & (ti->max_io_len - 1));
                                dm_accept_partial_bio(bio, len);
                        }
                }
        }

        if (unlikely(bio->bi_opf & REQ_PREFLUSH)) {
                submit_flush_bio(ic, dio);
                return DM_MAPIO_SUBMITTED;
        }

        dio->range.logical_sector = dm_target_offset(ti, bio->bi_iter.bi_sector);
        dio->fua = dio->op == REQ_OP_WRITE && bio->bi_opf & REQ_FUA;
        if (unlikely(dio->fua)) {
                /*
                 * Don't pass down the FUA flag because we have to flush
                 * disk cache anyway.
                 */
                bio->bi_opf &= ~REQ_FUA;
        }
        if (unlikely(dio->range.logical_sector + bio_sectors(bio) > ic->provided_data_sectors)) {
                DMERR("Too big sector number: 0x%llx + 0x%x > 0x%llx",
                      dio->range.logical_sector, bio_sectors(bio),
                      ic->provided_data_sectors);
                return DM_MAPIO_KILL;
        }
        if (unlikely((dio->range.logical_sector | bio_sectors(bio)) & (unsigned)(ic->sectors_per_block - 1))) {
                DMERR("Bio not aligned on %u sectors: 0x%llx, 0x%x",
                      ic->sectors_per_block,
                      dio->range.logical_sector, bio_sectors(bio));
                return DM_MAPIO_KILL;
        }

        if (ic->sectors_per_block > 1 && likely(dio->op != REQ_OP_DISCARD)) {
                struct bvec_iter iter;
                struct bio_vec bv;
                bio_for_each_segment(bv, bio, iter) {
                        if (unlikely(bv.bv_len & ((ic->sectors_per_block << SECTOR_SHIFT) - 1))) {
                                DMERR("Bio vector (%u,%u) is not aligned on %u-sector boundary",
                                        bv.bv_offset, bv.bv_len, ic->sectors_per_block);
                                return DM_MAPIO_KILL;
                        }
                }
        }

        bip = bio_integrity(bio);
        if (!ic->internal_hash) {
                if (bip) {
                        unsigned wanted_tag_size = bio_sectors(bio) >> ic->sb->log2_sectors_per_block;
                        if (ic->log2_tag_size >= 0)
                                wanted_tag_size <<= ic->log2_tag_size;
                        else
                                wanted_tag_size *= ic->tag_size;
                        if (unlikely(wanted_tag_size != bip->bip_iter.bi_size)) {
                                DMERR("Invalid integrity data size %u, expected %u",
                                      bip->bip_iter.bi_size, wanted_tag_size);
                                return DM_MAPIO_KILL;
                        }
                }
        } else {
                if (unlikely(bip != NULL)) {
                        DMERR("Unexpected integrity data when using internal hash");
                        return DM_MAPIO_KILL;
                }
        }

        if (unlikely(ic->mode == 'R') && unlikely(dio->op != REQ_OP_READ))
                return DM_MAPIO_KILL;

        get_area_and_offset(ic, dio->range.logical_sector, &area, &offset);
        dio->metadata_block = get_metadata_sector_and_offset(ic, area, offset, &dio->metadata_offset);
        bio->bi_iter.bi_sector = get_data_sector(ic, area, offset);

        dm_integrity_map_continue(dio, true);
        return DM_MAPIO_SUBMITTED;
}

static bool __journal_read_write(struct dm_integrity_io *dio, struct bio *bio,
                                 unsigned journal_section, unsigned journal_entry)
{
        struct dm_integrity_c *ic = dio->ic;
        sector_t logical_sector;
        unsigned n_sectors;

        logical_sector = dio->range.logical_sector;
        n_sectors = dio->range.n_sectors;
        do {
                struct bio_vec bv = bio_iovec(bio);
                char *mem;

                if (unlikely(bv.bv_len >> SECTOR_SHIFT > n_sectors))
                        bv.bv_len = n_sectors << SECTOR_SHIFT;
                n_sectors -= bv.bv_len >> SECTOR_SHIFT;
                bio_advance_iter(bio, &bio->bi_iter, bv.bv_len);
retry_kmap:
                mem = kmap_atomic(bv.bv_page);
                if (likely(dio->op == REQ_OP_WRITE))
                        flush_dcache_page(bv.bv_page);

                do {
                        struct journal_entry *je = access_journal_entry(ic, journal_section, journal_entry);

                        if (unlikely(dio->op == REQ_OP_READ)) {
                                struct journal_sector *js;
                                char *mem_ptr;
                                unsigned s;

                                if (unlikely(journal_entry_is_inprogress(je))) {
                                        flush_dcache_page(bv.bv_page);
                                        kunmap_atomic(mem);

                                        __io_wait_event(ic->copy_to_journal_wait, !journal_entry_is_inprogress(je));
                                        goto retry_kmap;
                                }
                                smp_rmb();
                                BUG_ON(journal_entry_get_sector(je) != logical_sector);
                                js = access_journal_data(ic, journal_section, journal_entry);
                                mem_ptr = mem + bv.bv_offset;
                                s = 0;
                                do {
                                        memcpy(mem_ptr, js, JOURNAL_SECTOR_DATA);
                                        *(commit_id_t *)(mem_ptr + JOURNAL_SECTOR_DATA) = je->last_bytes[s];
                                        js++;
                                        mem_ptr += 1 << SECTOR_SHIFT;
                                } while (++s < ic->sectors_per_block);
#ifdef INTERNAL_VERIFY
                                if (ic->internal_hash) {
                                        char checksums_onstack[max((size_t)HASH_MAX_DIGESTSIZE, MAX_TAG_SIZE)];

                                        integrity_sector_checksum(ic, logical_sector, mem + bv.bv_offset, checksums_onstack);
                                        if (unlikely(memcmp(checksums_onstack, journal_entry_tag(ic, je), ic->tag_size))) {
                                                DMERR_LIMIT("Checksum failed when reading from journal, at sector 0x%llx",
                                                            logical_sector);
                                        }
                                }
#endif
                        }

                        if (!ic->internal_hash) {
                                struct bio_integrity_payload *bip = bio_integrity(bio);

                                unsigned tag_todo = ic->tag_size;
                                char *tag_ptr = journal_entry_tag(ic, je);

                                if (bip) do {
                                        struct bio_vec biv = bvec_iter_bvec(bip->bip_vec, bip->bip_iter);
                                        unsigned tag_now = min(biv.bv_len, tag_todo);
                                        char *tag_addr;
                                        BUG_ON(PageHighMem(biv.bv_page));
                                        tag_addr = lowmem_page_address(biv.bv_page) + biv.bv_offset;
                                        if (likely(dio->op == REQ_OP_WRITE))
                                                memcpy(tag_ptr, tag_addr, tag_now);
                                        else
                                                memcpy(tag_addr, tag_ptr, tag_now);
                                        bvec_iter_advance(bip->bip_vec, &bip->bip_iter, tag_now);
                                        tag_ptr += tag_now;
                                        tag_todo -= tag_now;
                                } while (unlikely(tag_todo)); else {
                                        if (likely(dio->op == REQ_OP_WRITE))
                                                memset(tag_ptr, 0, tag_todo);
                                }
                        }

                        if (likely(dio->op == REQ_OP_WRITE)) {
                                struct journal_sector *js;
                                unsigned s;

                                js = access_journal_data(ic, journal_section, journal_entry);
                                memcpy(js, mem + bv.bv_offset, ic->sectors_per_block << SECTOR_SHIFT);

                                s = 0;
                                do {
                                        je->last_bytes[s] = js[s].commit_id;
                                } while (++s < ic->sectors_per_block);

                                if (ic->internal_hash) {
                                        unsigned digest_size = crypto_shash_digestsize(ic->internal_hash);
                                        if (unlikely(digest_size > ic->tag_size)) {
                                                char checksums_onstack[HASH_MAX_DIGESTSIZE];
                                                integrity_sector_checksum(ic, logical_sector, (char *)js, checksums_onstack);
                                                memcpy(journal_entry_tag(ic, je), checksums_onstack, ic->tag_size);
                                        } else
                                                integrity_sector_checksum(ic, logical_sector, (char *)js, journal_entry_tag(ic, je));
                                }

                                journal_entry_set_sector(je, logical_sector);
                        }
                        logical_sector += ic->sectors_per_block;

                        journal_entry++;
                        if (unlikely(journal_entry == ic->journal_section_entries)) {
                                journal_entry = 0;
                                journal_section++;
                                wraparound_section(ic, &journal_section);
                        }

                        bv.bv_offset += ic->sectors_per_block << SECTOR_SHIFT;
                } while (bv.bv_len -= ic->sectors_per_block << SECTOR_SHIFT);

                if (unlikely(dio->op == REQ_OP_READ))
                        flush_dcache_page(bv.bv_page);
                kunmap_atomic(mem);
        } while (n_sectors);

        if (likely(dio->op == REQ_OP_WRITE)) {
                smp_mb();
                if (unlikely(waitqueue_active(&ic->copy_to_journal_wait)))
                        wake_up(&ic->copy_to_journal_wait);
                if (READ_ONCE(ic->free_sectors) <= ic->free_sectors_threshold) {
                        queue_work(ic->commit_wq, &ic->commit_work);
                } else {
                        schedule_autocommit(ic);
                }
        } else {
                remove_range(ic, &dio->range);
        }

        if (unlikely(bio->bi_iter.bi_size)) {
                sector_t area, offset;

                dio->range.logical_sector = logical_sector;
                get_area_and_offset(ic, dio->range.logical_sector, &area, &offset);
                dio->metadata_block = get_metadata_sector_and_offset(ic, area, offset, &dio->metadata_offset);
                return true;
        }

        return false;
}

static void dm_integrity_map_continue(struct dm_integrity_io *dio, bool from_map)
{
        struct dm_integrity_c *ic = dio->ic;
        struct bio *bio = dm_bio_from_per_bio_data(dio, sizeof(struct dm_integrity_io));
        unsigned journal_section, journal_entry;
        unsigned journal_read_pos;
        struct completion read_comp;
        bool discard_retried = false;
        bool need_sync_io = ic->internal_hash && dio->op == REQ_OP_READ;
        if (unlikely(dio->op == REQ_OP_DISCARD) && ic->mode != 'D')
                need_sync_io = true;

        if (need_sync_io && from_map) {
                INIT_WORK(&dio->work, integrity_bio_wait);
                queue_work(ic->offload_wq, &dio->work);
                return;
        }

lock_retry:
        spin_lock_irq(&ic->endio_wait.lock);
retry:
        if (unlikely(dm_integrity_failed(ic))) {
                spin_unlock_irq(&ic->endio_wait.lock);
                do_endio(ic, bio);
                return;
        }
        dio->range.n_sectors = bio_sectors(bio);
        journal_read_pos = NOT_FOUND;
        if (ic->mode == 'J' && likely(dio->op != REQ_OP_DISCARD)) {
                if (dio->op == REQ_OP_WRITE) {
                        unsigned next_entry, i, pos;
                        unsigned ws, we, range_sectors;

                        dio->range.n_sectors = min(dio->range.n_sectors,
                                                   (sector_t)ic->free_sectors << ic->sb->log2_sectors_per_block);
                        if (unlikely(!dio->range.n_sectors)) {
                                if (from_map)
                                        goto offload_to_thread;
                                sleep_on_endio_wait(ic);
                                goto retry;
                        }
                        range_sectors = dio->range.n_sectors >> ic->sb->log2_sectors_per_block;
                        ic->free_sectors -= range_sectors;
                        journal_section = ic->free_section;
                        journal_entry = ic->free_section_entry;

                        next_entry = ic->free_section_entry + range_sectors;
                        ic->free_section_entry = next_entry % ic->journal_section_entries;
                        ic->free_section += next_entry / ic->journal_section_entries;
                        ic->n_uncommitted_sections += next_entry / ic->journal_section_entries;
                        wraparound_section(ic, &ic->free_section);

                        pos = journal_section * ic->journal_section_entries + journal_entry;
                        ws = journal_section;
                        we = journal_entry;
                        i = 0;
                        do {
                                struct journal_entry *je;

                                add_journal_node(ic, &ic->journal_tree[pos], dio->range.logical_sector + i);
                                pos++;
                                if (unlikely(pos >= ic->journal_entries))
                                        pos = 0;

                                je = access_journal_entry(ic, ws, we);
                                BUG_ON(!journal_entry_is_unused(je));
                                journal_entry_set_inprogress(je);
                                we++;
                                if (unlikely(we == ic->journal_section_entries)) {
                                        we = 0;
                                        ws++;
                                        wraparound_section(ic, &ws);
                                }
                        } while ((i += ic->sectors_per_block) < dio->range.n_sectors);

                        spin_unlock_irq(&ic->endio_wait.lock);
                        goto journal_read_write;
                } else {
                        sector_t next_sector;
                        journal_read_pos = find_journal_node(ic, dio->range.logical_sector, &next_sector);
                        if (likely(journal_read_pos == NOT_FOUND)) {
                                if (unlikely(dio->range.n_sectors > next_sector - dio->range.logical_sector))
                                        dio->range.n_sectors = next_sector - dio->range.logical_sector;
                        } else {
                                unsigned i;
                                unsigned jp = journal_read_pos + 1;
                                for (i = ic->sectors_per_block; i < dio->range.n_sectors; i += ic->sectors_per_block, jp++) {
                                        if (!test_journal_node(ic, jp, dio->range.logical_sector + i))
                                                break;
                                }
                                dio->range.n_sectors = i;
                        }
                }
        }
        if (unlikely(!add_new_range(ic, &dio->range, true))) {
                /*
                 * We must not sleep in the request routine because it could
                 * stall bios on current->bio_list.
                 * So, we offload the bio to a workqueue if we have to sleep.
                 */
                if (from_map) {
offload_to_thread:
                        spin_unlock_irq(&ic->endio_wait.lock);
                        INIT_WORK(&dio->work, integrity_bio_wait);
                        queue_work(ic->wait_wq, &dio->work);
                        return;
                }
                if (journal_read_pos != NOT_FOUND)
                        dio->range.n_sectors = ic->sectors_per_block;
                wait_and_add_new_range(ic, &dio->range);
                /*
                 * wait_and_add_new_range drops the spinlock, so the journal
                 * may have been changed arbitrarily. We need to recheck.
                 * To simplify the code, we restrict I/O size to just one block.
                 */
                if (journal_read_pos != NOT_FOUND) {
                        sector_t next_sector;
                        unsigned new_pos = find_journal_node(ic, dio->range.logical_sector, &next_sector);
                        if (unlikely(new_pos != journal_read_pos)) {
                                remove_range_unlocked(ic, &dio->range);
                                goto retry;
                        }
                }
        }
        if (ic->mode == 'J' && likely(dio->op == REQ_OP_DISCARD) && !discard_retried) {
                sector_t next_sector;
                unsigned new_pos = find_journal_node(ic, dio->range.logical_sector, &next_sector);
                if (unlikely(new_pos != NOT_FOUND) ||
                    unlikely(next_sector < dio->range.logical_sector - dio->range.n_sectors)) {
                        remove_range_unlocked(ic, &dio->range);
                        spin_unlock_irq(&ic->endio_wait.lock);
                        queue_work(ic->commit_wq, &ic->commit_work);
                        flush_workqueue(ic->commit_wq);
                        queue_work(ic->writer_wq, &ic->writer_work);
                        flush_workqueue(ic->writer_wq);
                        discard_retried = true;
                        goto lock_retry;
                }
        }
        spin_unlock_irq(&ic->endio_wait.lock);

        if (unlikely(journal_read_pos != NOT_FOUND)) {
                journal_section = journal_read_pos / ic->journal_section_entries;
                journal_entry = journal_read_pos % ic->journal_section_entries;
                goto journal_read_write;
        }

        if (ic->mode == 'B' && (dio->op == REQ_OP_WRITE || unlikely(dio->op == REQ_OP_DISCARD))) {
                if (!block_bitmap_op(ic, ic->may_write_bitmap, dio->range.logical_sector,
                                     dio->range.n_sectors, BITMAP_OP_TEST_ALL_SET)) {
                        struct bitmap_block_status *bbs;

                        bbs = sector_to_bitmap_block(ic, dio->range.logical_sector);
                        spin_lock(&bbs->bio_queue_lock);
                        bio_list_add(&bbs->bio_queue, bio);
                        spin_unlock(&bbs->bio_queue_lock);
                        queue_work(ic->writer_wq, &bbs->work);
                        return;
                }
        }

        dio->in_flight = (atomic_t)ATOMIC_INIT(2);

        if (need_sync_io) {
                init_completion(&read_comp);
                dio->completion = &read_comp;
        } else
                dio->completion = NULL;

        dm_bio_record(&dio->bio_details, bio);
        bio_set_dev(bio, ic->dev->bdev);
        bio->bi_integrity = NULL;
        bio->bi_opf &= ~REQ_INTEGRITY;
        bio->bi_end_io = integrity_end_io;
        bio->bi_iter.bi_size = dio->range.n_sectors << SECTOR_SHIFT;

        if (unlikely(dio->op == REQ_OP_DISCARD) && likely(ic->mode != 'D')) {
                integrity_metadata(&dio->work);
                dm_integrity_flush_buffers(ic, false);

                dio->in_flight = (atomic_t)ATOMIC_INIT(1);
                dio->completion = NULL;

                submit_bio_noacct(bio);

                return;
        }

        submit_bio_noacct(bio);

        if (need_sync_io) {
                wait_for_completion_io(&read_comp);
                if (ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING) &&
                    dio->range.logical_sector + dio->range.n_sectors > le64_to_cpu(ic->sb->recalc_sector))
                        goto skip_check;
                if (ic->mode == 'B') {
                        if (!block_bitmap_op(ic, ic->recalc_bitmap, dio->range.logical_sector,
                                             dio->range.n_sectors, BITMAP_OP_TEST_ALL_CLEAR))
                                goto skip_check;
                }

                if (likely(!bio->bi_status))
                        integrity_metadata(&dio->work);
                else
skip_check:
                        dec_in_flight(dio);

        } else {
                INIT_WORK(&dio->work, integrity_metadata);
                queue_work(ic->metadata_wq, &dio->work);
        }

        return;

journal_read_write:
        if (unlikely(__journal_read_write(dio, bio, journal_section, journal_entry)))
                goto lock_retry;

        do_endio_flush(ic, dio);
}


static void integrity_bio_wait(struct work_struct *w)
{
        struct dm_integrity_io *dio = container_of(w, struct dm_integrity_io, work);

        dm_integrity_map_continue(dio, false);
}

static void pad_uncommitted(struct dm_integrity_c *ic)
{
        if (ic->free_section_entry) {
                ic->free_sectors -= ic->journal_section_entries - ic->free_section_entry;
                ic->free_section_entry = 0;
                ic->free_section++;
                wraparound_section(ic, &ic->free_section);
                ic->n_uncommitted_sections++;
        }
        if (WARN_ON(ic->journal_sections * ic->journal_section_entries !=
                    (ic->n_uncommitted_sections + ic->n_committed_sections) *
                    ic->journal_section_entries + ic->free_sectors)) {
                DMCRIT("journal_sections %u, journal_section_entries %u, "
                       "n_uncommitted_sections %u, n_committed_sections %u, "
                       "journal_section_entries %u, free_sectors %u",
                       ic->journal_sections, ic->journal_section_entries,
                       ic->n_uncommitted_sections, ic->n_committed_sections,
                       ic->journal_section_entries, ic->free_sectors);
        }
}

static void integrity_commit(struct work_struct *w)
{
        struct dm_integrity_c *ic = container_of(w, struct dm_integrity_c, commit_work);
        unsigned commit_start, commit_sections;
        unsigned i, j, n;
        struct bio *flushes;

        del_timer(&ic->autocommit_timer);

        spin_lock_irq(&ic->endio_wait.lock);
        flushes = bio_list_get(&ic->flush_bio_list);
        if (unlikely(ic->mode != 'J')) {
                spin_unlock_irq(&ic->endio_wait.lock);
                dm_integrity_flush_buffers(ic, true);
                goto release_flush_bios;
        }

        pad_uncommitted(ic);
        commit_start = ic->uncommitted_section;
        commit_sections = ic->n_uncommitted_sections;
        spin_unlock_irq(&ic->endio_wait.lock);

        if (!commit_sections)
                goto release_flush_bios;

        i = commit_start;
        for (n = 0; n < commit_sections; n++) {
                for (j = 0; j < ic->journal_section_entries; j++) {
                        struct journal_entry *je;
                        je = access_journal_entry(ic, i, j);
                        io_wait_event(ic->copy_to_journal_wait, !journal_entry_is_inprogress(je));
                }
                for (j = 0; j < ic->journal_section_sectors; j++) {
                        struct journal_sector *js;
                        js = access_journal(ic, i, j);
                        js->commit_id = dm_integrity_commit_id(ic, i, j, ic->commit_seq);
                }
                i++;
                if (unlikely(i >= ic->journal_sections))
                        ic->commit_seq = next_commit_seq(ic->commit_seq);
                wraparound_section(ic, &i);
        }
        smp_rmb();

        write_journal(ic, commit_start, commit_sections);

        spin_lock_irq(&ic->endio_wait.lock);
        ic->uncommitted_section += commit_sections;
        wraparound_section(ic, &ic->uncommitted_section);
        ic->n_uncommitted_sections -= commit_sections;
        ic->n_committed_sections += commit_sections;
        spin_unlock_irq(&ic->endio_wait.lock);

        if (READ_ONCE(ic->free_sectors) <= ic->free_sectors_threshold)
                queue_work(ic->writer_wq, &ic->writer_work);

release_flush_bios:
        while (flushes) {
                struct bio *next = flushes->bi_next;
                flushes->bi_next = NULL;
                do_endio(ic, flushes);
                flushes = next;
        }
}

static void complete_copy_from_journal(unsigned long error, void *context)
{
        struct journal_io *io = context;
        struct journal_completion *comp = io->comp;
        struct dm_integrity_c *ic = comp->ic;
        remove_range(ic, &io->range);
        mempool_free(io, &ic->journal_io_mempool);
        if (unlikely(error != 0))
                dm_integrity_io_error(ic, "copying from journal", -EIO);
        complete_journal_op(comp);
}

static void restore_last_bytes(struct dm_integrity_c *ic, struct journal_sector *js,
                               struct journal_entry *je)
{
        unsigned s = 0;
        do {
                js->commit_id = je->last_bytes[s];
                js++;
        } while (++s < ic->sectors_per_block);
}

static void do_journal_write(struct dm_integrity_c *ic, unsigned write_start,
                             unsigned write_sections, bool from_replay)
{
        unsigned i, j, n;
        struct journal_completion comp;
        struct blk_plug plug;

        blk_start_plug(&plug);

        comp.ic = ic;
        comp.in_flight = (atomic_t)ATOMIC_INIT(1);
        init_completion(&comp.comp);

        i = write_start;
        for (n = 0; n < write_sections; n++, i++, wraparound_section(ic, &i)) {
#ifndef INTERNAL_VERIFY
                if (unlikely(from_replay))
#endif
                        rw_section_mac(ic, i, false);
                for (j = 0; j < ic->journal_section_entries; j++) {
                        struct journal_entry *je = access_journal_entry(ic, i, j);
                        sector_t sec, area, offset;
                        unsigned k, l, next_loop;
                        sector_t metadata_block;
                        unsigned metadata_offset;
                        struct journal_io *io;

                        if (journal_entry_is_unused(je))
                                continue;
                        BUG_ON(unlikely(journal_entry_is_inprogress(je)) && !from_replay);
                        sec = journal_entry_get_sector(je);
                        if (unlikely(from_replay)) {
                                if (unlikely(sec & (unsigned)(ic->sectors_per_block - 1))) {
                                        dm_integrity_io_error(ic, "invalid sector in journal", -EIO);
                                        sec &= ~(sector_t)(ic->sectors_per_block - 1);
                                }
                        }
                        if (unlikely(sec >= ic->provided_data_sectors))
                                continue;
                        get_area_and_offset(ic, sec, &area, &offset);
                        restore_last_bytes(ic, access_journal_data(ic, i, j), je);
                        for (k = j + 1; k < ic->journal_section_entries; k++) {
                                struct journal_entry *je2 = access_journal_entry(ic, i, k);
                                sector_t sec2, area2, offset2;
                                if (journal_entry_is_unused(je2))
                                        break;
                                BUG_ON(unlikely(journal_entry_is_inprogress(je2)) && !from_replay);
                                sec2 = journal_entry_get_sector(je2);
                                if (unlikely(sec2 >= ic->provided_data_sectors))
                                        break;
                                get_area_and_offset(ic, sec2, &area2, &offset2);
                                if (area2 != area || offset2 != offset + ((k - j) << ic->sb->log2_sectors_per_block))
                                        break;
                                restore_last_bytes(ic, access_journal_data(ic, i, k), je2);
                        }
                        next_loop = k - 1;

                        io = mempool_alloc(&ic->journal_io_mempool, GFP_NOIO);
                        io->comp = &comp;
                        io->range.logical_sector = sec;
                        io->range.n_sectors = (k - j) << ic->sb->log2_sectors_per_block;

                        spin_lock_irq(&ic->endio_wait.lock);
                        add_new_range_and_wait(ic, &io->range);

                        if (likely(!from_replay)) {
                                struct journal_node *section_node = &ic->journal_tree[i * ic->journal_section_entries];

                                /* don't write if there is newer committed sector */
                                while (j < k && find_newer_committed_node(ic, &section_node[j])) {
                                        struct journal_entry *je2 = access_journal_entry(ic, i, j);

                                        journal_entry_set_unused(je2);
                                        remove_journal_node(ic, &section_node[j]);
                                        j++;
                                        sec += ic->sectors_per_block;
                                        offset += ic->sectors_per_block;
                                }
                                while (j < k && find_newer_committed_node(ic, &section_node[k - 1])) {
                                        struct journal_entry *je2 = access_journal_entry(ic, i, k - 1);

                                        journal_entry_set_unused(je2);
                                        remove_journal_node(ic, &section_node[k - 1]);
                                        k--;
                                }
                                if (j == k) {
                                        remove_range_unlocked(ic, &io->range);
                                        spin_unlock_irq(&ic->endio_wait.lock);
                                        mempool_free(io, &ic->journal_io_mempool);
                                        goto skip_io;
                                }
                                for (l = j; l < k; l++) {
                                        remove_journal_node(ic, &section_node[l]);
                                }
                        }
                        spin_unlock_irq(&ic->endio_wait.lock);

                        metadata_block = get_metadata_sector_and_offset(ic, area, offset, &metadata_offset);
                        for (l = j; l < k; l++) {
                                int r;
                                struct journal_entry *je2 = access_journal_entry(ic, i, l);

                                if (
#ifndef INTERNAL_VERIFY
                                    unlikely(from_replay) &&
#endif
                                    ic->internal_hash) {
                                        char test_tag[max_t(size_t, HASH_MAX_DIGESTSIZE, MAX_TAG_SIZE)];

                                        integrity_sector_checksum(ic, sec + ((l - j) << ic->sb->log2_sectors_per_block),
                                                                  (char *)access_journal_data(ic, i, l), test_tag);
                                        if (unlikely(memcmp(test_tag, journal_entry_tag(ic, je2), ic->tag_size)))
                                                dm_integrity_io_error(ic, "tag mismatch when replaying journal", -EILSEQ);
                                }

                                journal_entry_set_unused(je2);
                                r = dm_integrity_rw_tag(ic, journal_entry_tag(ic, je2), &metadata_block, &metadata_offset,
                                                        ic->tag_size, TAG_WRITE);
                                if (unlikely(r)) {
                                        dm_integrity_io_error(ic, "reading tags", r);
                                }
                        }

                        atomic_inc(&comp.in_flight);
                        copy_from_journal(ic, i, j << ic->sb->log2_sectors_per_block,
                                          (k - j) << ic->sb->log2_sectors_per_block,
                                          get_data_sector(ic, area, offset),
                                          complete_copy_from_journal, io);
skip_io:
                        j = next_loop;
                }
        }

        dm_bufio_write_dirty_buffers_async(ic->bufio);

        blk_finish_plug(&plug);

        complete_journal_op(&comp);
        wait_for_completion_io(&comp.comp);

        dm_integrity_flush_buffers(ic, true);
}

static void integrity_writer(struct work_struct *w)
{
        struct dm_integrity_c *ic = container_of(w, struct dm_integrity_c, writer_work);
        unsigned write_start, write_sections;

        unsigned prev_free_sectors;

        /* the following test is not needed, but it tests the replay code */
        if (unlikely(dm_post_suspending(ic->ti)) && !ic->meta_dev)
                return;

        spin_lock_irq(&ic->endio_wait.lock);
        write_start = ic->committed_section;
        write_sections = ic->n_committed_sections;
        spin_unlock_irq(&ic->endio_wait.lock);

        if (!write_sections)
                return;

        do_journal_write(ic, write_start, write_sections, false);

        spin_lock_irq(&ic->endio_wait.lock);

        ic->committed_section += write_sections;
        wraparound_section(ic, &ic->committed_section);
        ic->n_committed_sections -= write_sections;

        prev_free_sectors = ic->free_sectors;
        ic->free_sectors += write_sections * ic->journal_section_entries;
        if (unlikely(!prev_free_sectors))
                wake_up_locked(&ic->endio_wait);

        spin_unlock_irq(&ic->endio_wait.lock);
}

static void recalc_write_super(struct dm_integrity_c *ic)
{
        int r;

        dm_integrity_flush_buffers(ic, false);
        if (dm_integrity_failed(ic))
                return;

        r = sync_rw_sb(ic, REQ_OP_WRITE, 0);
        if (unlikely(r))
                dm_integrity_io_error(ic, "writing superblock", r);
}

static void integrity_recalc(struct work_struct *w)
{
        struct dm_integrity_c *ic = container_of(w, struct dm_integrity_c, recalc_work);
        struct dm_integrity_range range;
        struct dm_io_request io_req;
        struct dm_io_region io_loc;
        sector_t area, offset;
        sector_t metadata_block;
        unsigned metadata_offset;
        sector_t logical_sector, n_sectors;
        __u8 *t;
        unsigned i;
        int r;
        unsigned super_counter = 0;

        DEBUG_print("start recalculation... (position %llx)\n", le64_to_cpu(ic->sb->recalc_sector));

        spin_lock_irq(&ic->endio_wait.lock);

next_chunk:

        if (unlikely(dm_post_suspending(ic->ti)))
                goto unlock_ret;

        range.logical_sector = le64_to_cpu(ic->sb->recalc_sector);
        if (unlikely(range.logical_sector >= ic->provided_data_sectors)) {
                if (ic->mode == 'B') {
                        block_bitmap_op(ic, ic->recalc_bitmap, 0, ic->provided_data_sectors, BITMAP_OP_CLEAR);
                        DEBUG_print("queue_delayed_work: bitmap_flush_work\n");
                        queue_delayed_work(ic->commit_wq, &ic->bitmap_flush_work, 0);
                }
                goto unlock_ret;
        }

        get_area_and_offset(ic, range.logical_sector, &area, &offset);
        range.n_sectors = min((sector_t)RECALC_SECTORS, ic->provided_data_sectors - range.logical_sector);
        if (!ic->meta_dev)
                range.n_sectors = min(range.n_sectors, ((sector_t)1U << ic->sb->log2_interleave_sectors) - (unsigned)offset);

        add_new_range_and_wait(ic, &range);
        spin_unlock_irq(&ic->endio_wait.lock);
        logical_sector = range.logical_sector;
        n_sectors = range.n_sectors;

        if (ic->mode == 'B') {
                if (block_bitmap_op(ic, ic->recalc_bitmap, logical_sector, n_sectors, BITMAP_OP_TEST_ALL_CLEAR)) {
                        goto advance_and_next;
                }
                while (block_bitmap_op(ic, ic->recalc_bitmap, logical_sector,
                                       ic->sectors_per_block, BITMAP_OP_TEST_ALL_CLEAR)) {
                        logical_sector += ic->sectors_per_block;
                        n_sectors -= ic->sectors_per_block;
                        cond_resched();
                }
                while (block_bitmap_op(ic, ic->recalc_bitmap, logical_sector + n_sectors - ic->sectors_per_block,
                                       ic->sectors_per_block, BITMAP_OP_TEST_ALL_CLEAR)) {
                        n_sectors -= ic->sectors_per_block;
                        cond_resched();
                }
                get_area_and_offset(ic, logical_sector, &area, &offset);
        }

        DEBUG_print("recalculating: %llx, %llx\n", logical_sector, n_sectors);

        if (unlikely(++super_counter == RECALC_WRITE_SUPER)) {
                recalc_write_super(ic);
                if (ic->mode == 'B') {
                        queue_delayed_work(ic->commit_wq, &ic->bitmap_flush_work, ic->bitmap_flush_interval);
                }
                super_counter = 0;
        }

        if (unlikely(dm_integrity_failed(ic)))
                goto err;

        io_req.bi_op = REQ_OP_READ;
        io_req.bi_op_flags = 0;
        io_req.mem.type = DM_IO_VMA;
        io_req.mem.ptr.addr = ic->recalc_buffer;
        io_req.notify.fn = NULL;
        io_req.client = ic->io;
        io_loc.bdev = ic->dev->bdev;
        io_loc.sector = get_data_sector(ic, area, offset);
        io_loc.count = n_sectors;

        r = dm_io(&io_req, 1, &io_loc, NULL);
        if (unlikely(r)) {
                dm_integrity_io_error(ic, "reading data", r);
                goto err;
        }

        t = ic->recalc_tags;
        for (i = 0; i < n_sectors; i += ic->sectors_per_block) {
                integrity_sector_checksum(ic, logical_sector + i, ic->recalc_buffer + (i << SECTOR_SHIFT), t);
                t += ic->tag_size;
        }

        metadata_block = get_metadata_sector_and_offset(ic, area, offset, &metadata_offset);

        r = dm_integrity_rw_tag(ic, ic->recalc_tags, &metadata_block, &metadata_offset, t - ic->recalc_tags, TAG_WRITE);
        if (unlikely(r)) {
                dm_integrity_io_error(ic, "writing tags", r);
                goto err;
        }

        if (ic->mode == 'B') {
                sector_t start, end;
                start = (range.logical_sector >>
                         (ic->sb->log2_sectors_per_block + ic->log2_blocks_per_bitmap_bit)) <<
                        (ic->sb->log2_sectors_per_block + ic->log2_blocks_per_bitmap_bit);
                end = ((range.logical_sector + range.n_sectors) >>
                       (ic->sb->log2_sectors_per_block + ic->log2_blocks_per_bitmap_bit)) <<
                        (ic->sb->log2_sectors_per_block + ic->log2_blocks_per_bitmap_bit);
                block_bitmap_op(ic, ic->recalc_bitmap, start, end - start, BITMAP_OP_CLEAR);
        }

advance_and_next:
        cond_resched();

        spin_lock_irq(&ic->endio_wait.lock);
        remove_range_unlocked(ic, &range);
        ic->sb->recalc_sector = cpu_to_le64(range.logical_sector + range.n_sectors);
        goto next_chunk;

err:
        remove_range(ic, &range);
        return;

unlock_ret:
        spin_unlock_irq(&ic->endio_wait.lock);

        recalc_write_super(ic);
}

static void bitmap_block_work(struct work_struct *w)
{
        struct bitmap_block_status *bbs = container_of(w, struct bitmap_block_status, work);
        struct dm_integrity_c *ic = bbs->ic;
        struct bio *bio;
        struct bio_list bio_queue;
        struct bio_list waiting;

        bio_list_init(&waiting);

        spin_lock(&bbs->bio_queue_lock);
        bio_queue = bbs->bio_queue;
        bio_list_init(&bbs->bio_queue);
        spin_unlock(&bbs->bio_queue_lock);

        while ((bio = bio_list_pop(&bio_queue))) {
                struct dm_integrity_io *dio;

                dio = dm_per_bio_data(bio, sizeof(struct dm_integrity_io));

                if (block_bitmap_op(ic, ic->may_write_bitmap, dio->range.logical_sector,
                                    dio->range.n_sectors, BITMAP_OP_TEST_ALL_SET)) {
                        remove_range(ic, &dio->range);
                        INIT_WORK(&dio->work, integrity_bio_wait);
                        queue_work(ic->offload_wq, &dio->work);
                } else {
                        block_bitmap_op(ic, ic->journal, dio->range.logical_sector,
                                        dio->range.n_sectors, BITMAP_OP_SET);
                        bio_list_add(&waiting, bio);
                }
        }

        if (bio_list_empty(&waiting))
                return;

        rw_journal_sectors(ic, REQ_OP_WRITE, REQ_FUA | REQ_SYNC,
                           bbs->idx * (BITMAP_BLOCK_SIZE >> SECTOR_SHIFT),
                           BITMAP_BLOCK_SIZE >> SECTOR_SHIFT, NULL);

        while ((bio = bio_list_pop(&waiting))) {
                struct dm_integrity_io *dio = dm_per_bio_data(bio, sizeof(struct dm_integrity_io));

                block_bitmap_op(ic, ic->may_write_bitmap, dio->range.logical_sector,
                                dio->range.n_sectors, BITMAP_OP_SET);

                remove_range(ic, &dio->range);
                INIT_WORK(&dio->work, integrity_bio_wait);
                queue_work(ic->offload_wq, &dio->work);
        }

        queue_delayed_work(ic->commit_wq, &ic->bitmap_flush_work, ic->bitmap_flush_interval);
}

static void bitmap_flush_work(struct work_struct *work)
{
        struct dm_integrity_c *ic = container_of(work, struct dm_integrity_c, bitmap_flush_work.work);
        struct dm_integrity_range range;
        unsigned long limit;
        struct bio *bio;

        dm_integrity_flush_buffers(ic, false);

        range.logical_sector = 0;
        range.n_sectors = ic->provided_data_sectors;

        spin_lock_irq(&ic->endio_wait.lock);
        add_new_range_and_wait(ic, &range);
        spin_unlock_irq(&ic->endio_wait.lock);

        dm_integrity_flush_buffers(ic, true);

        limit = ic->provided_data_sectors;
        if (ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING)) {
                limit = le64_to_cpu(ic->sb->recalc_sector)
                        >> (ic->sb->log2_sectors_per_block + ic->log2_blocks_per_bitmap_bit)
                        << (ic->sb->log2_sectors_per_block + ic->log2_blocks_per_bitmap_bit);
        }
        /*DEBUG_print("zeroing journal\n");*/
        block_bitmap_op(ic, ic->journal, 0, limit, BITMAP_OP_CLEAR);
        block_bitmap_op(ic, ic->may_write_bitmap, 0, limit, BITMAP_OP_CLEAR);

        rw_journal_sectors(ic, REQ_OP_WRITE, REQ_FUA | REQ_SYNC, 0,
                           ic->n_bitmap_blocks * (BITMAP_BLOCK_SIZE >> SECTOR_SHIFT), NULL);

        spin_lock_irq(&ic->endio_wait.lock);
        remove_range_unlocked(ic, &range);
        while (unlikely((bio = bio_list_pop(&ic->synchronous_bios)) != NULL)) {
                bio_endio(bio);
                spin_unlock_irq(&ic->endio_wait.lock);
                spin_lock_irq(&ic->endio_wait.lock);
        }
        spin_unlock_irq(&ic->endio_wait.lock);
}


static void init_journal(struct dm_integrity_c *ic, unsigned start_section,
                         unsigned n_sections, unsigned char commit_seq)
{
        unsigned i, j, n;

        if (!n_sections)
                return;

        for (n = 0; n < n_sections; n++) {
                i = start_section + n;
                wraparound_section(ic, &i);
                for (j = 0; j < ic->journal_section_sectors; j++) {
                        struct journal_sector *js = access_journal(ic, i, j);
                        memset(&js->entries, 0, JOURNAL_SECTOR_DATA);
                        js->commit_id = dm_integrity_commit_id(ic, i, j, commit_seq);
                }
                for (j = 0; j < ic->journal_section_entries; j++) {
                        struct journal_entry *je = access_journal_entry(ic, i, j);
                        journal_entry_set_unused(je);
                }
        }

        write_journal(ic, start_section, n_sections);
}

static int find_commit_seq(struct dm_integrity_c *ic, unsigned i, unsigned j, commit_id_t id)
{
        unsigned char k;
        for (k = 0; k < N_COMMIT_IDS; k++) {
                if (dm_integrity_commit_id(ic, i, j, k) == id)
                        return k;
        }
        dm_integrity_io_error(ic, "journal commit id", -EIO);
        return -EIO;
}

static void replay_journal(struct dm_integrity_c *ic)
{
        unsigned i, j;
        bool used_commit_ids[N_COMMIT_IDS];
        unsigned max_commit_id_sections[N_COMMIT_IDS];
        unsigned write_start, write_sections;
        unsigned continue_section;
        bool journal_empty;
        unsigned char unused, last_used, want_commit_seq;

        if (ic->mode == 'R')
                return;

        if (ic->journal_uptodate)
                return;

        last_used = 0;
        write_start = 0;

        if (!ic->just_formatted) {
                DEBUG_print("reading journal\n");
                rw_journal(ic, REQ_OP_READ, 0, 0, ic->journal_sections, NULL);
                if (ic->journal_io)
                        DEBUG_bytes(lowmem_page_address(ic->journal_io[0].page), 64, "read journal");
                if (ic->journal_io) {
                        struct journal_completion crypt_comp;
                        crypt_comp.ic = ic;
                        init_completion(&crypt_comp.comp);
                        crypt_comp.in_flight = (atomic_t)ATOMIC_INIT(0);
                        encrypt_journal(ic, false, 0, ic->journal_sections, &crypt_comp);
                        wait_for_completion(&crypt_comp.comp);
                }
                DEBUG_bytes(lowmem_page_address(ic->journal[0].page), 64, "decrypted journal");
        }

        if (dm_integrity_failed(ic))
                goto clear_journal;

        journal_empty = true;
        memset(used_commit_ids, 0, sizeof used_commit_ids);
        memset(max_commit_id_sections, 0, sizeof max_commit_id_sections);
        for (i = 0; i < ic->journal_sections; i++) {
                for (j = 0; j < ic->journal_section_sectors; j++) {
                        int k;
                        struct journal_sector *js = access_journal(ic, i, j);
                        k = find_commit_seq(ic, i, j, js->commit_id);
                        if (k < 0)
                                goto clear_journal;
                        used_commit_ids[k] = true;
                        max_commit_id_sections[k] = i;
                }
                if (journal_empty) {
                        for (j = 0; j < ic->journal_section_entries; j++) {
                                struct journal_entry *je = access_journal_entry(ic, i, j);
                                if (!journal_entry_is_unused(je)) {
                                        journal_empty = false;
                                        break;
                                }
                        }
                }
        }

        if (!used_commit_ids[N_COMMIT_IDS - 1]) {
                unused = N_COMMIT_IDS - 1;
                while (unused && !used_commit_ids[unused - 1])
                        unused--;
        } else {
                for (unused = 0; unused < N_COMMIT_IDS; unused++)
                        if (!used_commit_ids[unused])
                                break;
                if (unused == N_COMMIT_IDS) {
                        dm_integrity_io_error(ic, "journal commit ids", -EIO);
                        goto clear_journal;
                }
        }
        DEBUG_print("first unused commit seq %d [%d,%d,%d,%d]\n",
                    unused, used_commit_ids[0], used_commit_ids[1],
                    used_commit_ids[2], used_commit_ids[3]);

        last_used = prev_commit_seq(unused);
        want_commit_seq = prev_commit_seq(last_used);

        if (!used_commit_ids[want_commit_seq] && used_commit_ids[prev_commit_seq(want_commit_seq)])
                journal_empty = true;

        write_start = max_commit_id_sections[last_used] + 1;
        if (unlikely(write_start >= ic->journal_sections))
                want_commit_seq = next_commit_seq(want_commit_seq);
        wraparound_section(ic, &write_start);

        i = write_start;
        for (write_sections = 0; write_sections < ic->journal_sections; write_sections++) {
                for (j = 0; j < ic->journal_section_sectors; j++) {
                        struct journal_sector *js = access_journal(ic, i, j);

                        if (js->commit_id != dm_integrity_commit_id(ic, i, j, want_commit_seq)) {
                                /*
                                 * This could be caused by crash during writing.
                                 * We won't replay the inconsistent part of the
                                 * journal.
                                 */
                                DEBUG_print("commit id mismatch at position (%u, %u): %d != %d\n",
                                            i, j, find_commit_seq(ic, i, j, js->commit_id), want_commit_seq);
                                goto brk;
                        }
                }
                i++;
                if (unlikely(i >= ic->journal_sections))
                        want_commit_seq = next_commit_seq(want_commit_seq);
                wraparound_section(ic, &i);
        }
brk:

        if (!journal_empty) {
                DEBUG_print("replaying %u sections, starting at %u, commit seq %d\n",
                            write_sections, write_start, want_commit_seq);
                do_journal_write(ic, write_start, write_sections, true);
        }