^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1) // SPDX-License-Identifier: GPL-2.0-only
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2) #include "dm.h"
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 3) #include "persistent-data/dm-transaction-manager.h"
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 4) #include "persistent-data/dm-bitset.h"
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 5) #include "persistent-data/dm-space-map.h"
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 6)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 7) #include <linux/dm-io.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 8) #include <linux/dm-kcopyd.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 9) #include <linux/init.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 10) #include <linux/mempool.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 11) #include <linux/module.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 12) #include <linux/slab.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 13) #include <linux/vmalloc.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 14)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 15) #define DM_MSG_PREFIX "era"
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 16)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 17) #define SUPERBLOCK_LOCATION 0
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 18) #define SUPERBLOCK_MAGIC 2126579579
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 19) #define SUPERBLOCK_CSUM_XOR 146538381
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 20) #define MIN_ERA_VERSION 1
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 21) #define MAX_ERA_VERSION 1
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 22) #define INVALID_WRITESET_ROOT SUPERBLOCK_LOCATION
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 23) #define MIN_BLOCK_SIZE 8
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 24)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 25) /*----------------------------------------------------------------
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 26) * Writeset
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 27) *--------------------------------------------------------------*/
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 28) struct writeset_metadata {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 29) uint32_t nr_bits;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 30) dm_block_t root;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 31) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 32)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 33) struct writeset {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 34) struct writeset_metadata md;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 35)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 36) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 37) * An in core copy of the bits to save constantly doing look ups on
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 38) * disk.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 39) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 40) unsigned long *bits;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 41) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 42)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 43) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 44) * This does not free off the on disk bitset as this will normally be done
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 45) * after digesting into the era array.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 46) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 47) static void writeset_free(struct writeset *ws)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 48) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 49) vfree(ws->bits);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 50) ws->bits = NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 51) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 52)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 53) static int setup_on_disk_bitset(struct dm_disk_bitset *info,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 54) unsigned nr_bits, dm_block_t *root)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 55) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 56) int r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 57)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 58) r = dm_bitset_empty(info, root);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 59) if (r)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 60) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 61)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 62) return dm_bitset_resize(info, *root, 0, nr_bits, false, root);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 63) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 64)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 65) static size_t bitset_size(unsigned nr_bits)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 66) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 67) return sizeof(unsigned long) * dm_div_up(nr_bits, BITS_PER_LONG);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 68) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 69)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 70) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 71) * Allocates memory for the in core bitset.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 72) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 73) static int writeset_alloc(struct writeset *ws, dm_block_t nr_blocks)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 74) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 75) ws->bits = vzalloc(bitset_size(nr_blocks));
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 76) if (!ws->bits) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 77) DMERR("%s: couldn't allocate in memory bitset", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 78) return -ENOMEM;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 79) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 80)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 81) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 82) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 83)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 84) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 85) * Wipes the in-core bitset, and creates a new on disk bitset.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 86) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 87) static int writeset_init(struct dm_disk_bitset *info, struct writeset *ws,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 88) dm_block_t nr_blocks)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 89) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 90) int r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 91)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 92) memset(ws->bits, 0, bitset_size(nr_blocks));
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 93)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 94) ws->md.nr_bits = nr_blocks;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 95) r = setup_on_disk_bitset(info, ws->md.nr_bits, &ws->md.root);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 96) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 97) DMERR("%s: setup_on_disk_bitset failed", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 98) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 99) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 100)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 101) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 102) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 103)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 104) static bool writeset_marked(struct writeset *ws, dm_block_t block)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 105) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 106) return test_bit(block, ws->bits);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 107) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 108)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 109) static int writeset_marked_on_disk(struct dm_disk_bitset *info,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 110) struct writeset_metadata *m, dm_block_t block,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 111) bool *result)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 112) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 113) dm_block_t old = m->root;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 114)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 115) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 116) * The bitset was flushed when it was archived, so we know there'll
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 117) * be no change to the root.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 118) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 119) int r = dm_bitset_test_bit(info, m->root, block, &m->root, result);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 120) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 121) DMERR("%s: dm_bitset_test_bit failed", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 122) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 123) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 124)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 125) BUG_ON(m->root != old);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 126)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 127) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 128) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 129)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 130) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 131) * Returns < 0 on error, 0 if the bit wasn't previously set, 1 if it was.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 132) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 133) static int writeset_test_and_set(struct dm_disk_bitset *info,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 134) struct writeset *ws, uint32_t block)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 135) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 136) int r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 137)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 138) if (!test_bit(block, ws->bits)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 139) r = dm_bitset_set_bit(info, ws->md.root, block, &ws->md.root);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 140) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 141) /* FIXME: fail mode */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 142) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 143) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 144)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 145) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 146) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 147)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 148) return 1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 149) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 150)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 151) /*----------------------------------------------------------------
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 152) * On disk metadata layout
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 153) *--------------------------------------------------------------*/
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 154) #define SPACE_MAP_ROOT_SIZE 128
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 155) #define UUID_LEN 16
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 156)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 157) struct writeset_disk {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 158) __le32 nr_bits;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 159) __le64 root;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 160) } __packed;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 161)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 162) struct superblock_disk {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 163) __le32 csum;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 164) __le32 flags;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 165) __le64 blocknr;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 166)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 167) __u8 uuid[UUID_LEN];
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 168) __le64 magic;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 169) __le32 version;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 170)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 171) __u8 metadata_space_map_root[SPACE_MAP_ROOT_SIZE];
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 172)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 173) __le32 data_block_size;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 174) __le32 metadata_block_size;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 175) __le32 nr_blocks;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 176)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 177) __le32 current_era;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 178) struct writeset_disk current_writeset;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 179)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 180) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 181) * Only these two fields are valid within the metadata snapshot.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 182) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 183) __le64 writeset_tree_root;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 184) __le64 era_array_root;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 185)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 186) __le64 metadata_snap;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 187) } __packed;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 188)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 189) /*----------------------------------------------------------------
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 190) * Superblock validation
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 191) *--------------------------------------------------------------*/
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 192) static void sb_prepare_for_write(struct dm_block_validator *v,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 193) struct dm_block *b,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 194) size_t sb_block_size)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 195) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 196) struct superblock_disk *disk = dm_block_data(b);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 197)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 198) disk->blocknr = cpu_to_le64(dm_block_location(b));
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 199) disk->csum = cpu_to_le32(dm_bm_checksum(&disk->flags,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 200) sb_block_size - sizeof(__le32),
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 201) SUPERBLOCK_CSUM_XOR));
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 202) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 203)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 204) static int check_metadata_version(struct superblock_disk *disk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 205) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 206) uint32_t metadata_version = le32_to_cpu(disk->version);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 207) if (metadata_version < MIN_ERA_VERSION || metadata_version > MAX_ERA_VERSION) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 208) DMERR("Era metadata version %u found, but only versions between %u and %u supported.",
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 209) metadata_version, MIN_ERA_VERSION, MAX_ERA_VERSION);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 210) return -EINVAL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 211) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 212)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 213) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 214) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 215)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 216) static int sb_check(struct dm_block_validator *v,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 217) struct dm_block *b,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 218) size_t sb_block_size)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 219) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 220) struct superblock_disk *disk = dm_block_data(b);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 221) __le32 csum_le;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 222)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 223) if (dm_block_location(b) != le64_to_cpu(disk->blocknr)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 224) DMERR("sb_check failed: blocknr %llu: wanted %llu",
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 225) le64_to_cpu(disk->blocknr),
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 226) (unsigned long long)dm_block_location(b));
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 227) return -ENOTBLK;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 228) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 229)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 230) if (le64_to_cpu(disk->magic) != SUPERBLOCK_MAGIC) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 231) DMERR("sb_check failed: magic %llu: wanted %llu",
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 232) le64_to_cpu(disk->magic),
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 233) (unsigned long long) SUPERBLOCK_MAGIC);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 234) return -EILSEQ;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 235) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 236)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 237) csum_le = cpu_to_le32(dm_bm_checksum(&disk->flags,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 238) sb_block_size - sizeof(__le32),
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 239) SUPERBLOCK_CSUM_XOR));
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 240) if (csum_le != disk->csum) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 241) DMERR("sb_check failed: csum %u: wanted %u",
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 242) le32_to_cpu(csum_le), le32_to_cpu(disk->csum));
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 243) return -EILSEQ;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 244) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 245)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 246) return check_metadata_version(disk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 247) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 248)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 249) static struct dm_block_validator sb_validator = {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 250) .name = "superblock",
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 251) .prepare_for_write = sb_prepare_for_write,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 252) .check = sb_check
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 253) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 254)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 255) /*----------------------------------------------------------------
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 256) * Low level metadata handling
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 257) *--------------------------------------------------------------*/
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 258) #define DM_ERA_METADATA_BLOCK_SIZE 4096
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 259) #define ERA_MAX_CONCURRENT_LOCKS 5
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 260)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 261) struct era_metadata {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 262) struct block_device *bdev;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 263) struct dm_block_manager *bm;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 264) struct dm_space_map *sm;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 265) struct dm_transaction_manager *tm;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 266)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 267) dm_block_t block_size;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 268) uint32_t nr_blocks;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 269)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 270) uint32_t current_era;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 271)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 272) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 273) * We preallocate 2 writesets. When an era rolls over we
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 274) * switch between them. This means the allocation is done at
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 275) * preresume time, rather than on the io path.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 276) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 277) struct writeset writesets[2];
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 278) struct writeset *current_writeset;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 279)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 280) dm_block_t writeset_tree_root;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 281) dm_block_t era_array_root;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 282)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 283) struct dm_disk_bitset bitset_info;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 284) struct dm_btree_info writeset_tree_info;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 285) struct dm_array_info era_array_info;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 286)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 287) dm_block_t metadata_snap;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 288)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 289) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 290) * A flag that is set whenever a writeset has been archived.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 291) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 292) bool archived_writesets;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 293)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 294) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 295) * Reading the space map root can fail, so we read it into this
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 296) * buffer before the superblock is locked and updated.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 297) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 298) __u8 metadata_space_map_root[SPACE_MAP_ROOT_SIZE];
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 299) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 300)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 301) static int superblock_read_lock(struct era_metadata *md,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 302) struct dm_block **sblock)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 303) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 304) return dm_bm_read_lock(md->bm, SUPERBLOCK_LOCATION,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 305) &sb_validator, sblock);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 306) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 307)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 308) static int superblock_lock_zero(struct era_metadata *md,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 309) struct dm_block **sblock)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 310) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 311) return dm_bm_write_lock_zero(md->bm, SUPERBLOCK_LOCATION,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 312) &sb_validator, sblock);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 313) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 314)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 315) static int superblock_lock(struct era_metadata *md,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 316) struct dm_block **sblock)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 317) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 318) return dm_bm_write_lock(md->bm, SUPERBLOCK_LOCATION,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 319) &sb_validator, sblock);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 320) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 321)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 322) /* FIXME: duplication with cache and thin */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 323) static int superblock_all_zeroes(struct dm_block_manager *bm, bool *result)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 324) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 325) int r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 326) unsigned i;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 327) struct dm_block *b;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 328) __le64 *data_le, zero = cpu_to_le64(0);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 329) unsigned sb_block_size = dm_bm_block_size(bm) / sizeof(__le64);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 330)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 331) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 332) * We can't use a validator here - it may be all zeroes.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 333) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 334) r = dm_bm_read_lock(bm, SUPERBLOCK_LOCATION, NULL, &b);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 335) if (r)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 336) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 337)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 338) data_le = dm_block_data(b);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 339) *result = true;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 340) for (i = 0; i < sb_block_size; i++) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 341) if (data_le[i] != zero) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 342) *result = false;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 343) break;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 344) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 345) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 346)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 347) dm_bm_unlock(b);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 348)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 349) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 350) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 351)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 352) /*----------------------------------------------------------------*/
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 353)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 354) static void ws_pack(const struct writeset_metadata *core, struct writeset_disk *disk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 355) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 356) disk->nr_bits = cpu_to_le32(core->nr_bits);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 357) disk->root = cpu_to_le64(core->root);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 358) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 359)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 360) static void ws_unpack(const struct writeset_disk *disk, struct writeset_metadata *core)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 361) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 362) core->nr_bits = le32_to_cpu(disk->nr_bits);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 363) core->root = le64_to_cpu(disk->root);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 364) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 365)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 366) static void ws_inc(void *context, const void *value)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 367) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 368) struct era_metadata *md = context;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 369) struct writeset_disk ws_d;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 370) dm_block_t b;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 371)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 372) memcpy(&ws_d, value, sizeof(ws_d));
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 373) b = le64_to_cpu(ws_d.root);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 374)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 375) dm_tm_inc(md->tm, b);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 376) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 377)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 378) static void ws_dec(void *context, const void *value)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 379) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 380) struct era_metadata *md = context;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 381) struct writeset_disk ws_d;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 382) dm_block_t b;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 383)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 384) memcpy(&ws_d, value, sizeof(ws_d));
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 385) b = le64_to_cpu(ws_d.root);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 386)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 387) dm_bitset_del(&md->bitset_info, b);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 388) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 389)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 390) static int ws_eq(void *context, const void *value1, const void *value2)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 391) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 392) return !memcmp(value1, value2, sizeof(struct writeset_disk));
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 393) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 394)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 395) /*----------------------------------------------------------------*/
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 396)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 397) static void setup_writeset_tree_info(struct era_metadata *md)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 398) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 399) struct dm_btree_value_type *vt = &md->writeset_tree_info.value_type;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 400) md->writeset_tree_info.tm = md->tm;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 401) md->writeset_tree_info.levels = 1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 402) vt->context = md;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 403) vt->size = sizeof(struct writeset_disk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 404) vt->inc = ws_inc;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 405) vt->dec = ws_dec;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 406) vt->equal = ws_eq;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 407) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 408)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 409) static void setup_era_array_info(struct era_metadata *md)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 410)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 411) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 412) struct dm_btree_value_type vt;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 413) vt.context = NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 414) vt.size = sizeof(__le32);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 415) vt.inc = NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 416) vt.dec = NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 417) vt.equal = NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 418)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 419) dm_array_info_init(&md->era_array_info, md->tm, &vt);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 420) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 421)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 422) static void setup_infos(struct era_metadata *md)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 423) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 424) dm_disk_bitset_init(md->tm, &md->bitset_info);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 425) setup_writeset_tree_info(md);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 426) setup_era_array_info(md);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 427) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 428)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 429) /*----------------------------------------------------------------*/
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 430)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 431) static int create_fresh_metadata(struct era_metadata *md)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 432) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 433) int r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 434)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 435) r = dm_tm_create_with_sm(md->bm, SUPERBLOCK_LOCATION,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 436) &md->tm, &md->sm);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 437) if (r < 0) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 438) DMERR("dm_tm_create_with_sm failed");
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 439) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 440) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 441)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 442) setup_infos(md);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 443)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 444) r = dm_btree_empty(&md->writeset_tree_info, &md->writeset_tree_root);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 445) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 446) DMERR("couldn't create new writeset tree");
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 447) goto bad;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 448) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 449)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 450) r = dm_array_empty(&md->era_array_info, &md->era_array_root);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 451) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 452) DMERR("couldn't create era array");
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 453) goto bad;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 454) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 455)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 456) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 457)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 458) bad:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 459) dm_sm_destroy(md->sm);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 460) dm_tm_destroy(md->tm);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 461)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 462) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 463) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 464)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 465) static int save_sm_root(struct era_metadata *md)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 466) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 467) int r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 468) size_t metadata_len;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 469)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 470) r = dm_sm_root_size(md->sm, &metadata_len);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 471) if (r < 0)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 472) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 473)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 474) return dm_sm_copy_root(md->sm, &md->metadata_space_map_root,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 475) metadata_len);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 476) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 477)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 478) static void copy_sm_root(struct era_metadata *md, struct superblock_disk *disk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 479) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 480) memcpy(&disk->metadata_space_map_root,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 481) &md->metadata_space_map_root,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 482) sizeof(md->metadata_space_map_root));
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 483) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 484)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 485) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 486) * Writes a superblock, including the static fields that don't get updated
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 487) * with every commit (possible optimisation here). 'md' should be fully
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 488) * constructed when this is called.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 489) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 490) static void prepare_superblock(struct era_metadata *md, struct superblock_disk *disk)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 491) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 492) disk->magic = cpu_to_le64(SUPERBLOCK_MAGIC);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 493) disk->flags = cpu_to_le32(0ul);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 494)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 495) /* FIXME: can't keep blanking the uuid (uuid is currently unused though) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 496) memset(disk->uuid, 0, sizeof(disk->uuid));
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 497) disk->version = cpu_to_le32(MAX_ERA_VERSION);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 498)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 499) copy_sm_root(md, disk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 500)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 501) disk->data_block_size = cpu_to_le32(md->block_size);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 502) disk->metadata_block_size = cpu_to_le32(DM_ERA_METADATA_BLOCK_SIZE >> SECTOR_SHIFT);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 503) disk->nr_blocks = cpu_to_le32(md->nr_blocks);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 504) disk->current_era = cpu_to_le32(md->current_era);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 505)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 506) ws_pack(&md->current_writeset->md, &disk->current_writeset);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 507) disk->writeset_tree_root = cpu_to_le64(md->writeset_tree_root);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 508) disk->era_array_root = cpu_to_le64(md->era_array_root);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 509) disk->metadata_snap = cpu_to_le64(md->metadata_snap);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 510) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 511)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 512) static int write_superblock(struct era_metadata *md)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 513) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 514) int r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 515) struct dm_block *sblock;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 516) struct superblock_disk *disk;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 517)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 518) r = save_sm_root(md);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 519) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 520) DMERR("%s: save_sm_root failed", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 521) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 522) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 523)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 524) r = superblock_lock_zero(md, &sblock);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 525) if (r)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 526) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 527)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 528) disk = dm_block_data(sblock);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 529) prepare_superblock(md, disk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 530)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 531) return dm_tm_commit(md->tm, sblock);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 532) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 533)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 534) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 535) * Assumes block_size and the infos are set.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 536) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 537) static int format_metadata(struct era_metadata *md)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 538) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 539) int r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 540)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 541) r = create_fresh_metadata(md);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 542) if (r)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 543) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 544)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 545) r = write_superblock(md);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 546) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 547) dm_sm_destroy(md->sm);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 548) dm_tm_destroy(md->tm);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 549) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 550) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 551)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 552) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 553) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 554)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 555) static int open_metadata(struct era_metadata *md)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 556) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 557) int r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 558) struct dm_block *sblock;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 559) struct superblock_disk *disk;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 560)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 561) r = superblock_read_lock(md, &sblock);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 562) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 563) DMERR("couldn't read_lock superblock");
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 564) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 565) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 566)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 567) disk = dm_block_data(sblock);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 568)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 569) /* Verify the data block size hasn't changed */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 570) if (le32_to_cpu(disk->data_block_size) != md->block_size) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 571) DMERR("changing the data block size (from %u to %llu) is not supported",
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 572) le32_to_cpu(disk->data_block_size), md->block_size);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 573) r = -EINVAL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 574) goto bad;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 575) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 576)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 577) r = dm_tm_open_with_sm(md->bm, SUPERBLOCK_LOCATION,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 578) disk->metadata_space_map_root,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 579) sizeof(disk->metadata_space_map_root),
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 580) &md->tm, &md->sm);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 581) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 582) DMERR("dm_tm_open_with_sm failed");
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 583) goto bad;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 584) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 585)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 586) setup_infos(md);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 587)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 588) md->nr_blocks = le32_to_cpu(disk->nr_blocks);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 589) md->current_era = le32_to_cpu(disk->current_era);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 590)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 591) ws_unpack(&disk->current_writeset, &md->current_writeset->md);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 592) md->writeset_tree_root = le64_to_cpu(disk->writeset_tree_root);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 593) md->era_array_root = le64_to_cpu(disk->era_array_root);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 594) md->metadata_snap = le64_to_cpu(disk->metadata_snap);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 595) md->archived_writesets = true;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 596)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 597) dm_bm_unlock(sblock);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 598)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 599) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 600)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 601) bad:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 602) dm_bm_unlock(sblock);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 603) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 604) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 605)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 606) static int open_or_format_metadata(struct era_metadata *md,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 607) bool may_format)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 608) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 609) int r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 610) bool unformatted = false;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 611)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 612) r = superblock_all_zeroes(md->bm, &unformatted);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 613) if (r)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 614) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 615)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 616) if (unformatted)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 617) return may_format ? format_metadata(md) : -EPERM;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 618)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 619) return open_metadata(md);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 620) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 621)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 622) static int create_persistent_data_objects(struct era_metadata *md,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 623) bool may_format)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 624) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 625) int r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 626)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 627) md->bm = dm_block_manager_create(md->bdev, DM_ERA_METADATA_BLOCK_SIZE,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 628) ERA_MAX_CONCURRENT_LOCKS);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 629) if (IS_ERR(md->bm)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 630) DMERR("could not create block manager");
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 631) return PTR_ERR(md->bm);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 632) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 633)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 634) r = open_or_format_metadata(md, may_format);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 635) if (r)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 636) dm_block_manager_destroy(md->bm);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 637)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 638) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 639) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 640)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 641) static void destroy_persistent_data_objects(struct era_metadata *md)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 642) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 643) dm_sm_destroy(md->sm);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 644) dm_tm_destroy(md->tm);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 645) dm_block_manager_destroy(md->bm);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 646) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 647)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 648) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 649) * This waits until all era_map threads have picked up the new filter.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 650) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 651) static void swap_writeset(struct era_metadata *md, struct writeset *new_writeset)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 652) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 653) rcu_assign_pointer(md->current_writeset, new_writeset);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 654) synchronize_rcu();
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 655) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 656)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 657) /*----------------------------------------------------------------
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 658) * Writesets get 'digested' into the main era array.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 659) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 660) * We're using a coroutine here so the worker thread can do the digestion,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 661) * thus avoiding synchronisation of the metadata. Digesting a whole
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 662) * writeset in one go would cause too much latency.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 663) *--------------------------------------------------------------*/
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 664) struct digest {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 665) uint32_t era;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 666) unsigned nr_bits, current_bit;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 667) struct writeset_metadata writeset;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 668) __le32 value;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 669) struct dm_disk_bitset info;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 670)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 671) int (*step)(struct era_metadata *, struct digest *);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 672) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 673)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 674) static int metadata_digest_lookup_writeset(struct era_metadata *md,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 675) struct digest *d);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 676)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 677) static int metadata_digest_remove_writeset(struct era_metadata *md,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 678) struct digest *d)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 679) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 680) int r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 681) uint64_t key = d->era;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 682)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 683) r = dm_btree_remove(&md->writeset_tree_info, md->writeset_tree_root,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 684) &key, &md->writeset_tree_root);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 685) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 686) DMERR("%s: dm_btree_remove failed", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 687) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 688) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 689)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 690) d->step = metadata_digest_lookup_writeset;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 691) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 692) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 693)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 694) #define INSERTS_PER_STEP 100
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 695)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 696) static int metadata_digest_transcribe_writeset(struct era_metadata *md,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 697) struct digest *d)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 698) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 699) int r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 700) bool marked;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 701) unsigned b, e = min(d->current_bit + INSERTS_PER_STEP, d->nr_bits);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 702)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 703) for (b = d->current_bit; b < e; b++) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 704) r = writeset_marked_on_disk(&d->info, &d->writeset, b, &marked);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 705) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 706) DMERR("%s: writeset_marked_on_disk failed", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 707) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 708) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 709)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 710) if (!marked)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 711) continue;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 712)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 713) __dm_bless_for_disk(&d->value);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 714) r = dm_array_set_value(&md->era_array_info, md->era_array_root,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 715) b, &d->value, &md->era_array_root);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 716) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 717) DMERR("%s: dm_array_set_value failed", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 718) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 719) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 720) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 721)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 722) if (b == d->nr_bits)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 723) d->step = metadata_digest_remove_writeset;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 724) else
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 725) d->current_bit = b;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 726)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 727) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 728) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 729)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 730) static int metadata_digest_lookup_writeset(struct era_metadata *md,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 731) struct digest *d)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 732) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 733) int r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 734) uint64_t key;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 735) struct writeset_disk disk;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 736)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 737) r = dm_btree_find_lowest_key(&md->writeset_tree_info,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 738) md->writeset_tree_root, &key);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 739) if (r < 0)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 740) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 741)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 742) d->era = key;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 743)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 744) r = dm_btree_lookup(&md->writeset_tree_info,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 745) md->writeset_tree_root, &key, &disk);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 746) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 747) if (r == -ENODATA) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 748) d->step = NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 749) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 750) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 751)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 752) DMERR("%s: dm_btree_lookup failed", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 753) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 754) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 755)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 756) ws_unpack(&disk, &d->writeset);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 757) d->value = cpu_to_le32(key);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 758)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 759) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 760) * We initialise another bitset info to avoid any caching side effects
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 761) * with the previous one.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 762) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 763) dm_disk_bitset_init(md->tm, &d->info);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 764)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 765) d->nr_bits = min(d->writeset.nr_bits, md->nr_blocks);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 766) d->current_bit = 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 767) d->step = metadata_digest_transcribe_writeset;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 768)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 769) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 770) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 771)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 772) static int metadata_digest_start(struct era_metadata *md, struct digest *d)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 773) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 774) if (d->step)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 775) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 776)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 777) memset(d, 0, sizeof(*d));
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 778) d->step = metadata_digest_lookup_writeset;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 779)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 780) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 781) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 782)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 783) /*----------------------------------------------------------------
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 784) * High level metadata interface. Target methods should use these, and not
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 785) * the lower level ones.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 786) *--------------------------------------------------------------*/
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 787) static struct era_metadata *metadata_open(struct block_device *bdev,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 788) sector_t block_size,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 789) bool may_format)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 790) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 791) int r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 792) struct era_metadata *md = kzalloc(sizeof(*md), GFP_KERNEL);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 793)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 794) if (!md)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 795) return NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 796)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 797) md->bdev = bdev;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 798) md->block_size = block_size;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 799)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 800) md->writesets[0].md.root = INVALID_WRITESET_ROOT;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 801) md->writesets[1].md.root = INVALID_WRITESET_ROOT;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 802) md->current_writeset = &md->writesets[0];
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 803)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 804) r = create_persistent_data_objects(md, may_format);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 805) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 806) kfree(md);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 807) return ERR_PTR(r);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 808) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 809)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 810) return md;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 811) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 812)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 813) static void metadata_close(struct era_metadata *md)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 814) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 815) writeset_free(&md->writesets[0]);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 816) writeset_free(&md->writesets[1]);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 817) destroy_persistent_data_objects(md);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 818) kfree(md);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 819) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 820)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 821) static bool valid_nr_blocks(dm_block_t n)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 822) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 823) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 824) * dm_bitset restricts us to 2^32. test_bit & co. restrict us
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 825) * further to 2^31 - 1
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 826) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 827) return n < (1ull << 31);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 828) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 829)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 830) static int metadata_resize(struct era_metadata *md, void *arg)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 831) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 832) int r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 833) dm_block_t *new_size = arg;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 834) __le32 value;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 835)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 836) if (!valid_nr_blocks(*new_size)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 837) DMERR("Invalid number of origin blocks %llu",
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 838) (unsigned long long) *new_size);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 839) return -EINVAL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 840) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 841)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 842) writeset_free(&md->writesets[0]);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 843) writeset_free(&md->writesets[1]);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 844)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 845) r = writeset_alloc(&md->writesets[0], *new_size);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 846) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 847) DMERR("%s: writeset_alloc failed for writeset 0", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 848) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 849) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 850)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 851) r = writeset_alloc(&md->writesets[1], *new_size);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 852) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 853) DMERR("%s: writeset_alloc failed for writeset 1", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 854) writeset_free(&md->writesets[0]);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 855) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 856) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 857)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 858) value = cpu_to_le32(0u);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 859) __dm_bless_for_disk(&value);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 860) r = dm_array_resize(&md->era_array_info, md->era_array_root,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 861) md->nr_blocks, *new_size,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 862) &value, &md->era_array_root);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 863) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 864) DMERR("%s: dm_array_resize failed", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 865) writeset_free(&md->writesets[0]);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 866) writeset_free(&md->writesets[1]);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 867) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 868) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 869)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 870) md->nr_blocks = *new_size;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 871) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 872) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 873)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 874) static int metadata_era_archive(struct era_metadata *md)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 875) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 876) int r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 877) uint64_t keys[1];
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 878) struct writeset_disk value;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 879)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 880) r = dm_bitset_flush(&md->bitset_info, md->current_writeset->md.root,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 881) &md->current_writeset->md.root);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 882) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 883) DMERR("%s: dm_bitset_flush failed", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 884) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 885) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 886)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 887) ws_pack(&md->current_writeset->md, &value);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 888)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 889) keys[0] = md->current_era;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 890) __dm_bless_for_disk(&value);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 891) r = dm_btree_insert(&md->writeset_tree_info, md->writeset_tree_root,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 892) keys, &value, &md->writeset_tree_root);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 893) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 894) DMERR("%s: couldn't insert writeset into btree", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 895) /* FIXME: fail mode */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 896) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 897) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 898)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 899) md->current_writeset->md.root = INVALID_WRITESET_ROOT;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 900) md->archived_writesets = true;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 901)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 902) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 903) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 904)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 905) static struct writeset *next_writeset(struct era_metadata *md)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 906) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 907) return (md->current_writeset == &md->writesets[0]) ?
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 908) &md->writesets[1] : &md->writesets[0];
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 909) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 910)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 911) static int metadata_new_era(struct era_metadata *md)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 912) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 913) int r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 914) struct writeset *new_writeset = next_writeset(md);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 915)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 916) r = writeset_init(&md->bitset_info, new_writeset, md->nr_blocks);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 917) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 918) DMERR("%s: writeset_init failed", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 919) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 920) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 921)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 922) swap_writeset(md, new_writeset);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 923) md->current_era++;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 924)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 925) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 926) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 927)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 928) static int metadata_era_rollover(struct era_metadata *md)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 929) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 930) int r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 931)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 932) if (md->current_writeset->md.root != INVALID_WRITESET_ROOT) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 933) r = metadata_era_archive(md);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 934) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 935) DMERR("%s: metadata_archive_era failed", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 936) /* FIXME: fail mode? */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 937) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 938) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 939) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 940)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 941) r = metadata_new_era(md);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 942) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 943) DMERR("%s: new era failed", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 944) /* FIXME: fail mode */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 945) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 946) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 947)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 948) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 949) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 950)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 951) static bool metadata_current_marked(struct era_metadata *md, dm_block_t block)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 952) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 953) bool r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 954) struct writeset *ws;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 955)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 956) rcu_read_lock();
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 957) ws = rcu_dereference(md->current_writeset);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 958) r = writeset_marked(ws, block);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 959) rcu_read_unlock();
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 960)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 961) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 962) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 963)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 964) static int metadata_commit(struct era_metadata *md)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 965) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 966) int r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 967) struct dm_block *sblock;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 968)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 969) if (md->current_writeset->md.root != INVALID_WRITESET_ROOT) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 970) r = dm_bitset_flush(&md->bitset_info, md->current_writeset->md.root,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 971) &md->current_writeset->md.root);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 972) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 973) DMERR("%s: bitset flush failed", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 974) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 975) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 976) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 977)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 978) r = dm_tm_pre_commit(md->tm);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 979) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 980) DMERR("%s: pre commit failed", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 981) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 982) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 983)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 984) r = save_sm_root(md);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 985) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 986) DMERR("%s: save_sm_root failed", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 987) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 988) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 989)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 990) r = superblock_lock(md, &sblock);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 991) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 992) DMERR("%s: superblock lock failed", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 993) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 994) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 995)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 996) prepare_superblock(md, dm_block_data(sblock));
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 997)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 998) return dm_tm_commit(md->tm, sblock);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 999) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1000)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1001) static int metadata_checkpoint(struct era_metadata *md)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1002) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1003) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1004) * For now we just rollover, but later I want to put a check in to
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1005) * avoid this if the filter is still pretty fresh.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1006) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1007) return metadata_era_rollover(md);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1008) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1009)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1010) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1011) * Metadata snapshots allow userland to access era data.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1012) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1013) static int metadata_take_snap(struct era_metadata *md)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1014) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1015) int r, inc;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1016) struct dm_block *clone;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1017)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1018) if (md->metadata_snap != SUPERBLOCK_LOCATION) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1019) DMERR("%s: metadata snapshot already exists", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1020) return -EINVAL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1021) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1022)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1023) r = metadata_era_rollover(md);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1024) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1025) DMERR("%s: era rollover failed", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1026) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1027) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1028)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1029) r = metadata_commit(md);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1030) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1031) DMERR("%s: pre commit failed", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1032) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1033) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1034)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1035) r = dm_sm_inc_block(md->sm, SUPERBLOCK_LOCATION);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1036) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1037) DMERR("%s: couldn't increment superblock", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1038) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1039) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1040)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1041) r = dm_tm_shadow_block(md->tm, SUPERBLOCK_LOCATION,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1042) &sb_validator, &clone, &inc);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1043) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1044) DMERR("%s: couldn't shadow superblock", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1045) dm_sm_dec_block(md->sm, SUPERBLOCK_LOCATION);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1046) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1047) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1048) BUG_ON(!inc);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1049)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1050) r = dm_sm_inc_block(md->sm, md->writeset_tree_root);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1051) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1052) DMERR("%s: couldn't inc writeset tree root", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1053) dm_tm_unlock(md->tm, clone);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1054) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1055) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1056)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1057) r = dm_sm_inc_block(md->sm, md->era_array_root);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1058) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1059) DMERR("%s: couldn't inc era tree root", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1060) dm_sm_dec_block(md->sm, md->writeset_tree_root);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1061) dm_tm_unlock(md->tm, clone);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1062) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1063) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1064)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1065) md->metadata_snap = dm_block_location(clone);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1066)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1067) dm_tm_unlock(md->tm, clone);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1068)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1069) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1070) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1071)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1072) static int metadata_drop_snap(struct era_metadata *md)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1073) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1074) int r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1075) dm_block_t location;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1076) struct dm_block *clone;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1077) struct superblock_disk *disk;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1078)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1079) if (md->metadata_snap == SUPERBLOCK_LOCATION) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1080) DMERR("%s: no snap to drop", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1081) return -EINVAL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1082) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1083)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1084) r = dm_tm_read_lock(md->tm, md->metadata_snap, &sb_validator, &clone);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1085) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1086) DMERR("%s: couldn't read lock superblock clone", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1087) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1088) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1089)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1090) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1091) * Whatever happens now we'll commit with no record of the metadata
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1092) * snap.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1093) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1094) md->metadata_snap = SUPERBLOCK_LOCATION;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1095)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1096) disk = dm_block_data(clone);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1097) r = dm_btree_del(&md->writeset_tree_info,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1098) le64_to_cpu(disk->writeset_tree_root));
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1099) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1100) DMERR("%s: error deleting writeset tree clone", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1101) dm_tm_unlock(md->tm, clone);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1102) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1103) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1104)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1105) r = dm_array_del(&md->era_array_info, le64_to_cpu(disk->era_array_root));
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1106) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1107) DMERR("%s: error deleting era array clone", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1108) dm_tm_unlock(md->tm, clone);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1109) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1110) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1111)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1112) location = dm_block_location(clone);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1113) dm_tm_unlock(md->tm, clone);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1114)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1115) return dm_sm_dec_block(md->sm, location);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1116) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1117)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1118) struct metadata_stats {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1119) dm_block_t used;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1120) dm_block_t total;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1121) dm_block_t snap;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1122) uint32_t era;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1123) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1124)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1125) static int metadata_get_stats(struct era_metadata *md, void *ptr)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1126) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1127) int r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1128) struct metadata_stats *s = ptr;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1129) dm_block_t nr_free, nr_total;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1130)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1131) r = dm_sm_get_nr_free(md->sm, &nr_free);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1132) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1133) DMERR("dm_sm_get_nr_free returned %d", r);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1134) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1135) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1136)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1137) r = dm_sm_get_nr_blocks(md->sm, &nr_total);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1138) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1139) DMERR("dm_pool_get_metadata_dev_size returned %d", r);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1140) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1141) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1142)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1143) s->used = nr_total - nr_free;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1144) s->total = nr_total;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1145) s->snap = md->metadata_snap;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1146) s->era = md->current_era;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1147)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1148) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1149) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1150)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1151) /*----------------------------------------------------------------*/
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1152)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1153) struct era {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1154) struct dm_target *ti;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1155)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1156) struct dm_dev *metadata_dev;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1157) struct dm_dev *origin_dev;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1158)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1159) dm_block_t nr_blocks;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1160) uint32_t sectors_per_block;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1161) int sectors_per_block_shift;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1162) struct era_metadata *md;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1163)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1164) struct workqueue_struct *wq;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1165) struct work_struct worker;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1166)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1167) spinlock_t deferred_lock;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1168) struct bio_list deferred_bios;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1169)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1170) spinlock_t rpc_lock;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1171) struct list_head rpc_calls;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1172)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1173) struct digest digest;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1174) atomic_t suspended;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1175) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1176)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1177) struct rpc {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1178) struct list_head list;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1179)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1180) int (*fn0)(struct era_metadata *);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1181) int (*fn1)(struct era_metadata *, void *);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1182) void *arg;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1183) int result;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1184)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1185) struct completion complete;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1186) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1187)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1188) /*----------------------------------------------------------------
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1189) * Remapping.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1190) *---------------------------------------------------------------*/
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1191) static bool block_size_is_power_of_two(struct era *era)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1192) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1193) return era->sectors_per_block_shift >= 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1194) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1195)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1196) static dm_block_t get_block(struct era *era, struct bio *bio)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1197) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1198) sector_t block_nr = bio->bi_iter.bi_sector;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1199)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1200) if (!block_size_is_power_of_two(era))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1201) (void) sector_div(block_nr, era->sectors_per_block);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1202) else
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1203) block_nr >>= era->sectors_per_block_shift;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1204)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1205) return block_nr;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1206) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1207)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1208) static void remap_to_origin(struct era *era, struct bio *bio)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1209) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1210) bio_set_dev(bio, era->origin_dev->bdev);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1211) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1212)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1213) /*----------------------------------------------------------------
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1214) * Worker thread
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1215) *--------------------------------------------------------------*/
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1216) static void wake_worker(struct era *era)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1217) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1218) if (!atomic_read(&era->suspended))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1219) queue_work(era->wq, &era->worker);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1220) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1221)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1222) static void process_old_eras(struct era *era)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1223) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1224) int r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1225)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1226) if (!era->digest.step)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1227) return;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1228)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1229) r = era->digest.step(era->md, &era->digest);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1230) if (r < 0) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1231) DMERR("%s: digest step failed, stopping digestion", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1232) era->digest.step = NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1233)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1234) } else if (era->digest.step)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1235) wake_worker(era);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1236) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1237)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1238) static void process_deferred_bios(struct era *era)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1239) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1240) int r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1241) struct bio_list deferred_bios, marked_bios;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1242) struct bio *bio;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1243) struct blk_plug plug;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1244) bool commit_needed = false;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1245) bool failed = false;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1246) struct writeset *ws = era->md->current_writeset;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1247)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1248) bio_list_init(&deferred_bios);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1249) bio_list_init(&marked_bios);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1250)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1251) spin_lock(&era->deferred_lock);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1252) bio_list_merge(&deferred_bios, &era->deferred_bios);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1253) bio_list_init(&era->deferred_bios);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1254) spin_unlock(&era->deferred_lock);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1255)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1256) if (bio_list_empty(&deferred_bios))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1257) return;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1258)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1259) while ((bio = bio_list_pop(&deferred_bios))) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1260) r = writeset_test_and_set(&era->md->bitset_info, ws,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1261) get_block(era, bio));
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1262) if (r < 0) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1263) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1264) * This is bad news, we need to rollback.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1265) * FIXME: finish.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1266) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1267) failed = true;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1268) } else if (r == 0)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1269) commit_needed = true;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1270)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1271) bio_list_add(&marked_bios, bio);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1272) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1273)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1274) if (commit_needed) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1275) r = metadata_commit(era->md);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1276) if (r)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1277) failed = true;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1278) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1279)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1280) if (failed)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1281) while ((bio = bio_list_pop(&marked_bios)))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1282) bio_io_error(bio);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1283) else {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1284) blk_start_plug(&plug);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1285) while ((bio = bio_list_pop(&marked_bios))) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1286) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1287) * Only update the in-core writeset if the on-disk one
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1288) * was updated too.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1289) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1290) if (commit_needed)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1291) set_bit(get_block(era, bio), ws->bits);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1292) submit_bio_noacct(bio);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1293) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1294) blk_finish_plug(&plug);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1295) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1296) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1297)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1298) static void process_rpc_calls(struct era *era)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1299) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1300) int r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1301) bool need_commit = false;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1302) struct list_head calls;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1303) struct rpc *rpc, *tmp;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1304)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1305) INIT_LIST_HEAD(&calls);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1306) spin_lock(&era->rpc_lock);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1307) list_splice_init(&era->rpc_calls, &calls);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1308) spin_unlock(&era->rpc_lock);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1309)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1310) list_for_each_entry_safe(rpc, tmp, &calls, list) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1311) rpc->result = rpc->fn0 ? rpc->fn0(era->md) : rpc->fn1(era->md, rpc->arg);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1312) need_commit = true;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1313) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1314)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1315) if (need_commit) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1316) r = metadata_commit(era->md);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1317) if (r)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1318) list_for_each_entry_safe(rpc, tmp, &calls, list)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1319) rpc->result = r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1320) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1321)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1322) list_for_each_entry_safe(rpc, tmp, &calls, list)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1323) complete(&rpc->complete);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1324) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1325)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1326) static void kick_off_digest(struct era *era)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1327) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1328) if (era->md->archived_writesets) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1329) era->md->archived_writesets = false;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1330) metadata_digest_start(era->md, &era->digest);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1331) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1332) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1333)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1334) static void do_work(struct work_struct *ws)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1335) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1336) struct era *era = container_of(ws, struct era, worker);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1337)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1338) kick_off_digest(era);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1339) process_old_eras(era);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1340) process_deferred_bios(era);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1341) process_rpc_calls(era);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1342) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1343)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1344) static void defer_bio(struct era *era, struct bio *bio)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1345) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1346) spin_lock(&era->deferred_lock);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1347) bio_list_add(&era->deferred_bios, bio);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1348) spin_unlock(&era->deferred_lock);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1349)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1350) wake_worker(era);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1351) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1352)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1353) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1354) * Make an rpc call to the worker to change the metadata.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1355) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1356) static int perform_rpc(struct era *era, struct rpc *rpc)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1357) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1358) rpc->result = 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1359) init_completion(&rpc->complete);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1360)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1361) spin_lock(&era->rpc_lock);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1362) list_add(&rpc->list, &era->rpc_calls);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1363) spin_unlock(&era->rpc_lock);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1364)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1365) wake_worker(era);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1366) wait_for_completion(&rpc->complete);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1367)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1368) return rpc->result;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1369) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1370)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1371) static int in_worker0(struct era *era, int (*fn)(struct era_metadata *))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1372) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1373) struct rpc rpc;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1374) rpc.fn0 = fn;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1375) rpc.fn1 = NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1376)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1377) return perform_rpc(era, &rpc);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1378) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1379)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1380) static int in_worker1(struct era *era,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1381) int (*fn)(struct era_metadata *, void *), void *arg)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1382) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1383) struct rpc rpc;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1384) rpc.fn0 = NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1385) rpc.fn1 = fn;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1386) rpc.arg = arg;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1387)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1388) return perform_rpc(era, &rpc);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1389) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1390)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1391) static void start_worker(struct era *era)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1392) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1393) atomic_set(&era->suspended, 0);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1394) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1395)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1396) static void stop_worker(struct era *era)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1397) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1398) atomic_set(&era->suspended, 1);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1399) flush_workqueue(era->wq);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1400) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1401)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1402) /*----------------------------------------------------------------
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1403) * Target methods
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1404) *--------------------------------------------------------------*/
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1405) static void era_destroy(struct era *era)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1406) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1407) if (era->md)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1408) metadata_close(era->md);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1409)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1410) if (era->wq)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1411) destroy_workqueue(era->wq);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1412)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1413) if (era->origin_dev)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1414) dm_put_device(era->ti, era->origin_dev);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1415)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1416) if (era->metadata_dev)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1417) dm_put_device(era->ti, era->metadata_dev);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1418)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1419) kfree(era);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1420) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1421)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1422) static dm_block_t calc_nr_blocks(struct era *era)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1423) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1424) return dm_sector_div_up(era->ti->len, era->sectors_per_block);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1425) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1426)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1427) static bool valid_block_size(dm_block_t block_size)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1428) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1429) bool greater_than_zero = block_size > 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1430) bool multiple_of_min_block_size = (block_size & (MIN_BLOCK_SIZE - 1)) == 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1431)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1432) return greater_than_zero && multiple_of_min_block_size;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1433) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1434)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1435) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1436) * <metadata dev> <data dev> <data block size (sectors)>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1437) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1438) static int era_ctr(struct dm_target *ti, unsigned argc, char **argv)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1439) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1440) int r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1441) char dummy;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1442) struct era *era;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1443) struct era_metadata *md;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1444)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1445) if (argc != 3) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1446) ti->error = "Invalid argument count";
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1447) return -EINVAL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1448) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1449)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1450) era = kzalloc(sizeof(*era), GFP_KERNEL);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1451) if (!era) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1452) ti->error = "Error allocating era structure";
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1453) return -ENOMEM;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1454) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1455)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1456) era->ti = ti;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1457)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1458) r = dm_get_device(ti, argv[0], FMODE_READ | FMODE_WRITE, &era->metadata_dev);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1459) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1460) ti->error = "Error opening metadata device";
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1461) era_destroy(era);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1462) return -EINVAL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1463) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1464)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1465) r = dm_get_device(ti, argv[1], FMODE_READ | FMODE_WRITE, &era->origin_dev);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1466) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1467) ti->error = "Error opening data device";
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1468) era_destroy(era);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1469) return -EINVAL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1470) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1471)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1472) r = sscanf(argv[2], "%u%c", &era->sectors_per_block, &dummy);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1473) if (r != 1) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1474) ti->error = "Error parsing block size";
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1475) era_destroy(era);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1476) return -EINVAL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1477) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1478)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1479) r = dm_set_target_max_io_len(ti, era->sectors_per_block);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1480) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1481) ti->error = "could not set max io len";
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1482) era_destroy(era);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1483) return -EINVAL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1484) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1485)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1486) if (!valid_block_size(era->sectors_per_block)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1487) ti->error = "Invalid block size";
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1488) era_destroy(era);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1489) return -EINVAL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1490) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1491) if (era->sectors_per_block & (era->sectors_per_block - 1))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1492) era->sectors_per_block_shift = -1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1493) else
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1494) era->sectors_per_block_shift = __ffs(era->sectors_per_block);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1495)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1496) md = metadata_open(era->metadata_dev->bdev, era->sectors_per_block, true);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1497) if (IS_ERR(md)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1498) ti->error = "Error reading metadata";
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1499) era_destroy(era);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1500) return PTR_ERR(md);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1501) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1502) era->md = md;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1503)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1504) era->wq = alloc_ordered_workqueue("dm-" DM_MSG_PREFIX, WQ_MEM_RECLAIM);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1505) if (!era->wq) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1506) ti->error = "could not create workqueue for metadata object";
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1507) era_destroy(era);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1508) return -ENOMEM;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1509) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1510) INIT_WORK(&era->worker, do_work);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1511)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1512) spin_lock_init(&era->deferred_lock);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1513) bio_list_init(&era->deferred_bios);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1514)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1515) spin_lock_init(&era->rpc_lock);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1516) INIT_LIST_HEAD(&era->rpc_calls);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1517)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1518) ti->private = era;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1519) ti->num_flush_bios = 1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1520) ti->flush_supported = true;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1521)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1522) ti->num_discard_bios = 1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1523)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1524) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1525) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1526)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1527) static void era_dtr(struct dm_target *ti)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1528) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1529) era_destroy(ti->private);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1530) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1531)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1532) static int era_map(struct dm_target *ti, struct bio *bio)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1533) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1534) struct era *era = ti->private;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1535) dm_block_t block = get_block(era, bio);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1536)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1537) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1538) * All bios get remapped to the origin device. We do this now, but
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1539) * it may not get issued until later. Depending on whether the
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1540) * block is marked in this era.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1541) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1542) remap_to_origin(era, bio);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1543)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1544) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1545) * REQ_PREFLUSH bios carry no data, so we're not interested in them.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1546) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1547) if (!(bio->bi_opf & REQ_PREFLUSH) &&
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1548) (bio_data_dir(bio) == WRITE) &&
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1549) !metadata_current_marked(era->md, block)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1550) defer_bio(era, bio);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1551) return DM_MAPIO_SUBMITTED;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1552) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1553)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1554) return DM_MAPIO_REMAPPED;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1555) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1556)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1557) static void era_postsuspend(struct dm_target *ti)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1558) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1559) int r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1560) struct era *era = ti->private;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1561)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1562) r = in_worker0(era, metadata_era_archive);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1563) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1564) DMERR("%s: couldn't archive current era", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1565) /* FIXME: fail mode */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1566) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1567)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1568) stop_worker(era);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1569) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1570)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1571) static int era_preresume(struct dm_target *ti)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1572) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1573) int r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1574) struct era *era = ti->private;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1575) dm_block_t new_size = calc_nr_blocks(era);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1576)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1577) if (era->nr_blocks != new_size) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1578) r = metadata_resize(era->md, &new_size);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1579) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1580) DMERR("%s: metadata_resize failed", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1581) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1582) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1583)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1584) r = metadata_commit(era->md);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1585) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1586) DMERR("%s: metadata_commit failed", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1587) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1588) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1589)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1590) era->nr_blocks = new_size;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1591) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1592)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1593) start_worker(era);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1594)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1595) r = in_worker0(era, metadata_era_rollover);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1596) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1597) DMERR("%s: metadata_era_rollover failed", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1598) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1599) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1600)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1601) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1602) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1603)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1604) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1605) * Status format:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1606) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1607) * <metadata block size> <#used metadata blocks>/<#total metadata blocks>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1608) * <current era> <held metadata root | '-'>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1609) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1610) static void era_status(struct dm_target *ti, status_type_t type,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1611) unsigned status_flags, char *result, unsigned maxlen)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1612) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1613) int r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1614) struct era *era = ti->private;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1615) ssize_t sz = 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1616) struct metadata_stats stats;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1617) char buf[BDEVNAME_SIZE];
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1618)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1619) switch (type) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1620) case STATUSTYPE_INFO:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1621) r = in_worker1(era, metadata_get_stats, &stats);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1622) if (r)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1623) goto err;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1624)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1625) DMEMIT("%u %llu/%llu %u",
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1626) (unsigned) (DM_ERA_METADATA_BLOCK_SIZE >> SECTOR_SHIFT),
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1627) (unsigned long long) stats.used,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1628) (unsigned long long) stats.total,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1629) (unsigned) stats.era);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1630)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1631) if (stats.snap != SUPERBLOCK_LOCATION)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1632) DMEMIT(" %llu", stats.snap);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1633) else
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1634) DMEMIT(" -");
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1635) break;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1636)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1637) case STATUSTYPE_TABLE:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1638) format_dev_t(buf, era->metadata_dev->bdev->bd_dev);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1639) DMEMIT("%s ", buf);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1640) format_dev_t(buf, era->origin_dev->bdev->bd_dev);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1641) DMEMIT("%s %u", buf, era->sectors_per_block);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1642) break;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1643) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1644)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1645) return;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1646)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1647) err:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1648) DMEMIT("Error");
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1649) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1650)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1651) static int era_message(struct dm_target *ti, unsigned argc, char **argv,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1652) char *result, unsigned maxlen)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1653) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1654) struct era *era = ti->private;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1655)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1656) if (argc != 1) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1657) DMERR("incorrect number of message arguments");
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1658) return -EINVAL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1659) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1660)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1661) if (!strcasecmp(argv[0], "checkpoint"))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1662) return in_worker0(era, metadata_checkpoint);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1663)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1664) if (!strcasecmp(argv[0], "take_metadata_snap"))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1665) return in_worker0(era, metadata_take_snap);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1666)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1667) if (!strcasecmp(argv[0], "drop_metadata_snap"))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1668) return in_worker0(era, metadata_drop_snap);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1669)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1670) DMERR("unsupported message '%s'", argv[0]);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1671) return -EINVAL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1672) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1673)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1674) static sector_t get_dev_size(struct dm_dev *dev)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1675) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1676) return i_size_read(dev->bdev->bd_inode) >> SECTOR_SHIFT;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1677) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1678)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1679) static int era_iterate_devices(struct dm_target *ti,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1680) iterate_devices_callout_fn fn, void *data)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1681) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1682) struct era *era = ti->private;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1683) return fn(ti, era->origin_dev, 0, get_dev_size(era->origin_dev), data);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1684) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1685)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1686) static void era_io_hints(struct dm_target *ti, struct queue_limits *limits)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1687) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1688) struct era *era = ti->private;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1689) uint64_t io_opt_sectors = limits->io_opt >> SECTOR_SHIFT;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1690)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1691) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1692) * If the system-determined stacked limits are compatible with the
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1693) * era device's blocksize (io_opt is a factor) do not override them.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1694) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1695) if (io_opt_sectors < era->sectors_per_block ||
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1696) do_div(io_opt_sectors, era->sectors_per_block)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1697) blk_limits_io_min(limits, 0);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1698) blk_limits_io_opt(limits, era->sectors_per_block << SECTOR_SHIFT);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1699) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1700) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1701)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1702) /*----------------------------------------------------------------*/
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1703)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1704) static struct target_type era_target = {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1705) .name = "era",
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1706) .version = {1, 0, 0},
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1707) .module = THIS_MODULE,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1708) .ctr = era_ctr,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1709) .dtr = era_dtr,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1710) .map = era_map,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1711) .postsuspend = era_postsuspend,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1712) .preresume = era_preresume,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1713) .status = era_status,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1714) .message = era_message,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1715) .iterate_devices = era_iterate_devices,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1716) .io_hints = era_io_hints
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1717) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1718)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1719) static int __init dm_era_init(void)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1720) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1721) int r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1722)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1723) r = dm_register_target(&era_target);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1724) if (r) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1725) DMERR("era target registration failed: %d", r);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1726) return r;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1727) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1728)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1729) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1730) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1731)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1732) static void __exit dm_era_exit(void)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1733) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1734) dm_unregister_target(&era_target);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1735) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1736)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1737) module_init(dm_era_init);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1738) module_exit(dm_era_exit);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1739)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1740) MODULE_DESCRIPTION(DM_NAME " era target");
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1741) MODULE_AUTHOR("Joe Thornber <ejt@redhat.com>");
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1742) MODULE_LICENSE("GPL");
Orange Pi5 kernel
Deprecated Linux kernel 5.10.110 for OrangePi 5/5B/5+ boards
3 Commits
0 Branches
0 Tags