blob: 6dcd36d7b84906bc4585c861ea7b55659d365fe3 [file] [log] [blame]
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 2011, 2012 STRATO. All rights reserved.
*/
#include <linux/blkdev.h>
#include <linux/ratelimit.h>
#include <linux/sched/mm.h>
#include "ctree.h"
#include "volumes.h"
#include "disk-io.h"
#include "ordered-data.h"
#include "transaction.h"
#include "backref.h"
#include "extent_io.h"
#include "dev-replace.h"
#include "check-integrity.h"
#include "rcu-string.h"
#include "raid56.h"
/*
* This is only the first step towards a full-features scrub. It reads all
* extent and super block and verifies the checksums. In case a bad checksum
* is found or the extent cannot be read, good data will be written back if
* any can be found.
*
* Future enhancements:
* - In case an unrepairable extent is encountered, track which files are
* affected and report them
* - track and record media errors, throw out bad devices
* - add a mode to also read unallocated space
*/
struct scrub_block;
struct scrub_ctx;
/*
* the following three values only influence the performance.
* The last one configures the number of parallel and outstanding I/O
* operations. The first two values configure an upper limit for the number
* of (dynamically allocated) pages that are added to a bio.
*/
#define SCRUB_PAGES_PER_RD_BIO 32 /* 128k per bio */
#define SCRUB_PAGES_PER_WR_BIO 32 /* 128k per bio */
#define SCRUB_BIOS_PER_SCTX 64 /* 8MB per device in flight */
/*
* the following value times PAGE_SIZE needs to be large enough to match the
* largest node/leaf/sector size that shall be supported.
* Values larger than BTRFS_STRIPE_LEN are not supported.
*/
#define SCRUB_MAX_PAGES_PER_BLOCK 16 /* 64k per node/leaf/sector */
struct scrub_recover {
refcount_t refs;
struct btrfs_bio *bbio;
u64 map_length;
};
struct scrub_page {
struct scrub_block *sblock;
struct page *page;
struct btrfs_device *dev;
struct list_head list;
u64 flags; /* extent flags */
u64 generation;
u64 logical;
u64 physical;
u64 physical_for_dev_replace;
atomic_t refs;
struct {
unsigned int mirror_num:8;
unsigned int have_csum:1;
unsigned int io_error:1;
};
u8 csum[BTRFS_CSUM_SIZE];
struct scrub_recover *recover;
};
struct scrub_bio {
int index;
struct scrub_ctx *sctx;
struct btrfs_device *dev;
struct bio *bio;
blk_status_t status;
u64 logical;
u64 physical;
#if SCRUB_PAGES_PER_WR_BIO >= SCRUB_PAGES_PER_RD_BIO
struct scrub_page *pagev[SCRUB_PAGES_PER_WR_BIO];
#else
struct scrub_page *pagev[SCRUB_PAGES_PER_RD_BIO];
#endif
int page_count;
int next_free;
struct btrfs_work work;
};
struct scrub_block {
struct scrub_page *pagev[SCRUB_MAX_PAGES_PER_BLOCK];
int page_count;
atomic_t outstanding_pages;
refcount_t refs; /* free mem on transition to zero */
struct scrub_ctx *sctx;
struct scrub_parity *sparity;
struct {
unsigned int header_error:1;
unsigned int checksum_error:1;
unsigned int no_io_error_seen:1;
unsigned int generation_error:1; /* also sets header_error */
/* The following is for the data used to check parity */
/* It is for the data with checksum */
unsigned int data_corrected:1;
};
struct btrfs_work work;
};
/* Used for the chunks with parity stripe such RAID5/6 */
struct scrub_parity {
struct scrub_ctx *sctx;
struct btrfs_device *scrub_dev;
u64 logic_start;
u64 logic_end;
int nsectors;
u64 stripe_len;
refcount_t refs;
struct list_head spages;
/* Work of parity check and repair */
struct btrfs_work work;
/* Mark the parity blocks which have data */
unsigned long *dbitmap;
/*
* Mark the parity blocks which have data, but errors happen when
* read data or check data
*/
unsigned long *ebitmap;
unsigned long bitmap[0];
};
struct scrub_ctx {
struct scrub_bio *bios[SCRUB_BIOS_PER_SCTX];
struct btrfs_fs_info *fs_info;
int first_free;
int curr;
atomic_t bios_in_flight;
atomic_t workers_pending;
spinlock_t list_lock;
wait_queue_head_t list_wait;
u16 csum_size;
struct list_head csum_list;
atomic_t cancel_req;
int readonly;
int pages_per_rd_bio;
int is_dev_replace;
struct scrub_bio *wr_curr_bio;
struct mutex wr_lock;
int pages_per_wr_bio; /* <= SCRUB_PAGES_PER_WR_BIO */
struct btrfs_device *wr_tgtdev;
bool flush_all_writes;
/*
* statistics
*/
struct btrfs_scrub_progress stat;
spinlock_t stat_lock;
/*
* Use a ref counter to avoid use-after-free issues. Scrub workers
* decrement bios_in_flight and workers_pending and then do a wakeup
* on the list_wait wait queue. We must ensure the main scrub task
* doesn't free the scrub context before or while the workers are
* doing the wakeup() call.
*/
refcount_t refs;
};
struct scrub_warning {
struct btrfs_path *path;
u64 extent_item_size;
const char *errstr;
u64 physical;
u64 logical;
struct btrfs_device *dev;
};
struct full_stripe_lock {
struct rb_node node;
u64 logical;
u64 refs;
struct mutex mutex;
};
static void scrub_pending_bio_inc(struct scrub_ctx *sctx);
static void scrub_pending_bio_dec(struct scrub_ctx *sctx);
static int scrub_handle_errored_block(struct scrub_block *sblock_to_check);
static int scrub_setup_recheck_block(struct scrub_block *original_sblock,
struct scrub_block *sblocks_for_recheck);
static void scrub_recheck_block(struct btrfs_fs_info *fs_info,
struct scrub_block *sblock,
int retry_failed_mirror);
static void scrub_recheck_block_checksum(struct scrub_block *sblock);
static int scrub_repair_block_from_good_copy(struct scrub_block *sblock_bad,
struct scrub_block *sblock_good);
static int scrub_repair_page_from_good_copy(struct scrub_block *sblock_bad,
struct scrub_block *sblock_good,
int page_num, int force_write);
static void scrub_write_block_to_dev_replace(struct scrub_block *sblock);
static int scrub_write_page_to_dev_replace(struct scrub_block *sblock,
int page_num);
static int scrub_checksum_data(struct scrub_block *sblock);
static int scrub_checksum_tree_block(struct scrub_block *sblock);
static int scrub_checksum_super(struct scrub_block *sblock);
static void scrub_block_get(struct scrub_block *sblock);
static void scrub_block_put(struct scrub_block *sblock);
static void scrub_page_get(struct scrub_page *spage);
static void scrub_page_put(struct scrub_page *spage);
static void scrub_parity_get(struct scrub_parity *sparity);
static void scrub_parity_put(struct scrub_parity *sparity);
static int scrub_add_page_to_rd_bio(struct scrub_ctx *sctx,
struct scrub_page *spage);
static int scrub_pages(struct scrub_ctx *sctx, u64 logical, u64 len,
u64 physical, struct btrfs_device *dev, u64 flags,
u64 gen, int mirror_num, u8 *csum, int force,
u64 physical_for_dev_replace);
static void scrub_bio_end_io(struct bio *bio);
static void scrub_bio_end_io_worker(struct btrfs_work *work);
static void scrub_block_complete(struct scrub_block *sblock);
static void scrub_remap_extent(struct btrfs_fs_info *fs_info,
u64 extent_logical, u64 extent_len,
u64 *extent_physical,
struct btrfs_device **extent_dev,
int *extent_mirror_num);
static int scrub_add_page_to_wr_bio(struct scrub_ctx *sctx,
struct scrub_page *spage);
static void scrub_wr_submit(struct scrub_ctx *sctx);
static void scrub_wr_bio_end_io(struct bio *bio);
static void scrub_wr_bio_end_io_worker(struct btrfs_work *work);
static void __scrub_blocked_if_needed(struct btrfs_fs_info *fs_info);
static void scrub_blocked_if_needed(struct btrfs_fs_info *fs_info);
static void scrub_put_ctx(struct scrub_ctx *sctx);
static inline int scrub_is_page_on_raid56(struct scrub_page *page)
{
return page->recover &&
(page->recover->bbio->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK);
}
static void scrub_pending_bio_inc(struct scrub_ctx *sctx)
{
refcount_inc(&sctx->refs);
atomic_inc(&sctx->bios_in_flight);
}
static void scrub_pending_bio_dec(struct scrub_ctx *sctx)
{
atomic_dec(&sctx->bios_in_flight);
wake_up(&sctx->list_wait);
scrub_put_ctx(sctx);
}
static void __scrub_blocked_if_needed(struct btrfs_fs_info *fs_info)
{
while (atomic_read(&fs_info->scrub_pause_req)) {
mutex_unlock(&fs_info->scrub_lock);
wait_event(fs_info->scrub_pause_wait,
atomic_read(&fs_info->scrub_pause_req) == 0);
mutex_lock(&fs_info->scrub_lock);
}
}
static void scrub_pause_on(struct btrfs_fs_info *fs_info)
{
atomic_inc(&fs_info->scrubs_paused);
wake_up(&fs_info->scrub_pause_wait);
}
static void scrub_pause_off(struct btrfs_fs_info *fs_info)
{
mutex_lock(&fs_info->scrub_lock);
__scrub_blocked_if_needed(fs_info);
atomic_dec(&fs_info->scrubs_paused);
mutex_unlock(&fs_info->scrub_lock);
wake_up(&fs_info->scrub_pause_wait);
}
static void scrub_blocked_if_needed(struct btrfs_fs_info *fs_info)
{
scrub_pause_on(fs_info);
scrub_pause_off(fs_info);
}
/*
* Insert new full stripe lock into full stripe locks tree
*
* Return pointer to existing or newly inserted full_stripe_lock structure if
* everything works well.
* Return ERR_PTR(-ENOMEM) if we failed to allocate memory
*
* NOTE: caller must hold full_stripe_locks_root->lock before calling this
* function
*/
static struct full_stripe_lock *insert_full_stripe_lock(
struct btrfs_full_stripe_locks_tree *locks_root,
u64 fstripe_logical)
{
struct rb_node **p;
struct rb_node *parent = NULL;
struct full_stripe_lock *entry;
struct full_stripe_lock *ret;
lockdep_assert_held(&locks_root->lock);
p = &locks_root->root.rb_node;
while (*p) {
parent = *p;
entry = rb_entry(parent, struct full_stripe_lock, node);
if (fstripe_logical < entry->logical) {
p = &(*p)->rb_left;
} else if (fstripe_logical > entry->logical) {
p = &(*p)->rb_right;
} else {
entry->refs++;
return entry;
}
}
/*
* Insert new lock.
*/
ret = kmalloc(sizeof(*ret), GFP_KERNEL);
if (!ret)
return ERR_PTR(-ENOMEM);
ret->logical = fstripe_logical;
ret->refs = 1;
mutex_init(&ret->mutex);
rb_link_node(&ret->node, parent, p);
rb_insert_color(&ret->node, &locks_root->root);
return ret;
}
/*
* Search for a full stripe lock of a block group
*
* Return pointer to existing full stripe lock if found
* Return NULL if not found
*/
static struct full_stripe_lock *search_full_stripe_lock(
struct btrfs_full_stripe_locks_tree *locks_root,
u64 fstripe_logical)
{
struct rb_node *node;
struct full_stripe_lock *entry;
lockdep_assert_held(&locks_root->lock);
node = locks_root->root.rb_node;
while (node) {
entry = rb_entry(node, struct full_stripe_lock, node);
if (fstripe_logical < entry->logical)
node = node->rb_left;
else if (fstripe_logical > entry->logical)
node = node->rb_right;
else
return entry;
}
return NULL;
}
/*
* Helper to get full stripe logical from a normal bytenr.
*
* Caller must ensure @cache is a RAID56 block group.
*/
static u64 get_full_stripe_logical(struct btrfs_block_group_cache *cache,
u64 bytenr)
{
u64 ret;
/*
* Due to chunk item size limit, full stripe length should not be
* larger than U32_MAX. Just a sanity check here.
*/
WARN_ON_ONCE(cache->full_stripe_len >= U32_MAX);
/*
* round_down() can only handle power of 2, while RAID56 full
* stripe length can be 64KiB * n, so we need to manually round down.
*/
ret = div64_u64(bytenr - cache->key.objectid, cache->full_stripe_len) *
cache->full_stripe_len + cache->key.objectid;
return ret;
}
/*
* Lock a full stripe to avoid concurrency of recovery and read
*
* It's only used for profiles with parities (RAID5/6), for other profiles it
* does nothing.
*
* Return 0 if we locked full stripe covering @bytenr, with a mutex held.
* So caller must call unlock_full_stripe() at the same context.
*
* Return <0 if encounters error.
*/
static int lock_full_stripe(struct btrfs_fs_info *fs_info, u64 bytenr,
bool *locked_ret)
{
struct btrfs_block_group_cache *bg_cache;
struct btrfs_full_stripe_locks_tree *locks_root;
struct full_stripe_lock *existing;
u64 fstripe_start;
int ret = 0;
*locked_ret = false;
bg_cache = btrfs_lookup_block_group(fs_info, bytenr);
if (!bg_cache) {
ASSERT(0);
return -ENOENT;
}
/* Profiles not based on parity don't need full stripe lock */
if (!(bg_cache->flags & BTRFS_BLOCK_GROUP_RAID56_MASK))
goto out;
locks_root = &bg_cache->full_stripe_locks_root;
fstripe_start = get_full_stripe_logical(bg_cache, bytenr);
/* Now insert the full stripe lock */
mutex_lock(&locks_root->lock);
existing = insert_full_stripe_lock(locks_root, fstripe_start);
mutex_unlock(&locks_root->lock);
if (IS_ERR(existing)) {
ret = PTR_ERR(existing);
goto out;
}
mutex_lock(&existing->mutex);
*locked_ret = true;
out:
btrfs_put_block_group(bg_cache);
return ret;
}
/*
* Unlock a full stripe.
*
* NOTE: Caller must ensure it's the same context calling corresponding
* lock_full_stripe().
*
* Return 0 if we unlock full stripe without problem.
* Return <0 for error
*/
static int unlock_full_stripe(struct btrfs_fs_info *fs_info, u64 bytenr,
bool locked)
{
struct btrfs_block_group_cache *bg_cache;
struct btrfs_full_stripe_locks_tree *locks_root;
struct full_stripe_lock *fstripe_lock;
u64 fstripe_start;
bool freeit = false;
int ret = 0;
/* If we didn't acquire full stripe lock, no need to continue */
if (!locked)
return 0;
bg_cache = btrfs_lookup_block_group(fs_info, bytenr);
if (!bg_cache) {
ASSERT(0);
return -ENOENT;
}
if (!(bg_cache->flags & BTRFS_BLOCK_GROUP_RAID56_MASK))
goto out;
locks_root = &bg_cache->full_stripe_locks_root;
fstripe_start = get_full_stripe_logical(bg_cache, bytenr);
mutex_lock(&locks_root->lock);
fstripe_lock = search_full_stripe_lock(locks_root, fstripe_start);
/* Unpaired unlock_full_stripe() detected */
if (!fstripe_lock) {
WARN_ON(1);
ret = -ENOENT;
mutex_unlock(&locks_root->lock);
goto out;
}
if (fstripe_lock->refs == 0) {
WARN_ON(1);
btrfs_warn(fs_info, "full stripe lock at %llu refcount underflow",
fstripe_lock->logical);
} else {
fstripe_lock->refs--;
}
if (fstripe_lock->refs == 0) {
rb_erase(&fstripe_lock->node, &locks_root->root);
freeit = true;
}
mutex_unlock(&locks_root->lock);
mutex_unlock(&fstripe_lock->mutex);
if (freeit)
kfree(fstripe_lock);
out:
btrfs_put_block_group(bg_cache);
return ret;
}
static void scrub_free_csums(struct scrub_ctx *sctx)
{
while (!list_empty(&sctx->csum_list)) {
struct btrfs_ordered_sum *sum;
sum = list_first_entry(&sctx->csum_list,
struct btrfs_ordered_sum, list);
list_del(&sum->list);
kfree(sum);
}
}
static noinline_for_stack void scrub_free_ctx(struct scrub_ctx *sctx)
{
int i;
if (!sctx)
return;
/* this can happen when scrub is cancelled */
if (sctx->curr != -1) {
struct scrub_bio *sbio = sctx->bios[sctx->curr];
for (i = 0; i < sbio->page_count; i++) {
WARN_ON(!sbio->pagev[i]->page);
scrub_block_put(sbio->pagev[i]->sblock);
}
bio_put(sbio->bio);
}
for (i = 0; i < SCRUB_BIOS_PER_SCTX; ++i) {
struct scrub_bio *sbio = sctx->bios[i];
if (!sbio)
break;
kfree(sbio);
}
kfree(sctx->wr_curr_bio);
scrub_free_csums(sctx);
kfree(sctx);
}
static void scrub_put_ctx(struct scrub_ctx *sctx)
{
if (refcount_dec_and_test(&sctx->refs))
scrub_free_ctx(sctx);
}
static noinline_for_stack struct scrub_ctx *scrub_setup_ctx(
struct btrfs_fs_info *fs_info, int is_dev_replace)
{
struct scrub_ctx *sctx;
int i;
sctx = kzalloc(sizeof(*sctx), GFP_KERNEL);
if (!sctx)
goto nomem;
refcount_set(&sctx->refs, 1);
sctx->is_dev_replace = is_dev_replace;
sctx->pages_per_rd_bio = SCRUB_PAGES_PER_RD_BIO;
sctx->curr = -1;
sctx->fs_info = fs_info;
for (i = 0; i < SCRUB_BIOS_PER_SCTX; ++i) {
struct scrub_bio *sbio;
sbio = kzalloc(sizeof(*sbio), GFP_KERNEL);
if (!sbio)
goto nomem;
sctx->bios[i] = sbio;
sbio->index = i;
sbio->sctx = sctx;
sbio->page_count = 0;
btrfs_init_work(&sbio->work, btrfs_scrub_helper,
scrub_bio_end_io_worker, NULL, NULL);
if (i != SCRUB_BIOS_PER_SCTX - 1)
sctx->bios[i]->next_free = i + 1;
else
sctx->bios[i]->next_free = -1;
}
sctx->first_free = 0;
atomic_set(&sctx->bios_in_flight, 0);
atomic_set(&sctx->workers_pending, 0);
atomic_set(&sctx->cancel_req, 0);
sctx->csum_size = btrfs_super_csum_size(fs_info->super_copy);
INIT_LIST_HEAD(&sctx->csum_list);
spin_lock_init(&sctx->list_lock);
spin_lock_init(&sctx->stat_lock);
init_waitqueue_head(&sctx->list_wait);
WARN_ON(sctx->wr_curr_bio != NULL);
mutex_init(&sctx->wr_lock);
sctx->wr_curr_bio = NULL;
if (is_dev_replace) {
WARN_ON(!fs_info->dev_replace.tgtdev);
sctx->pages_per_wr_bio = SCRUB_PAGES_PER_WR_BIO;
sctx->wr_tgtdev = fs_info->dev_replace.tgtdev;
sctx->flush_all_writes = false;
}
return sctx;
nomem:
scrub_free_ctx(sctx);
return ERR_PTR(-ENOMEM);
}
static int scrub_print_warning_inode(u64 inum, u64 offset, u64 root,
void *warn_ctx)
{
u64 isize;
u32 nlink;
int ret;
int i;
unsigned nofs_flag;
struct extent_buffer *eb;
struct btrfs_inode_item *inode_item;
struct scrub_warning *swarn = warn_ctx;
struct btrfs_fs_info *fs_info = swarn->dev->fs_info;
struct inode_fs_paths *ipath = NULL;
struct btrfs_root *local_root;
struct btrfs_key root_key;
struct btrfs_key key;
root_key.objectid = root;
root_key.type = BTRFS_ROOT_ITEM_KEY;
root_key.offset = (u64)-1;
local_root = btrfs_read_fs_root_no_name(fs_info, &root_key);
if (IS_ERR(local_root)) {
ret = PTR_ERR(local_root);
goto err;
}
/*
* this makes the path point to (inum INODE_ITEM ioff)
*/
key.objectid = inum;
key.type = BTRFS_INODE_ITEM_KEY;
key.offset = 0;
ret = btrfs_search_slot(NULL, local_root, &key, swarn->path, 0, 0);
if (ret) {
btrfs_release_path(swarn->path);
goto err;
}
eb = swarn->path->nodes[0];
inode_item = btrfs_item_ptr(eb, swarn->path->slots[0],
struct btrfs_inode_item);
isize = btrfs_inode_size(eb, inode_item);
nlink = btrfs_inode_nlink(eb, inode_item);
btrfs_release_path(swarn->path);
/*
* init_path might indirectly call vmalloc, or use GFP_KERNEL. Scrub
* uses GFP_NOFS in this context, so we keep it consistent but it does
* not seem to be strictly necessary.
*/
nofs_flag = memalloc_nofs_save();
ipath = init_ipath(4096, local_root, swarn->path);
memalloc_nofs_restore(nofs_flag);
if (IS_ERR(ipath)) {
ret = PTR_ERR(ipath);
ipath = NULL;
goto err;
}
ret = paths_from_inode(inum, ipath);
if (ret < 0)
goto err;
/*
* we deliberately ignore the bit ipath might have been too small to
* hold all of the paths here
*/
for (i = 0; i < ipath->fspath->elem_cnt; ++i)
btrfs_warn_in_rcu(fs_info,
"%s at logical %llu on dev %s, physical %llu, root %llu, inode %llu, offset %llu, length %llu, links %u (path: %s)",
swarn->errstr, swarn->logical,
rcu_str_deref(swarn->dev->name),
swarn->physical,
root, inum, offset,
min(isize - offset, (u64)PAGE_SIZE), nlink,
(char *)(unsigned long)ipath->fspath->val[i]);
free_ipath(ipath);
return 0;
err:
btrfs_warn_in_rcu(fs_info,
"%s at logical %llu on dev %s, physical %llu, root %llu, inode %llu, offset %llu: path resolving failed with ret=%d",
swarn->errstr, swarn->logical,
rcu_str_deref(swarn->dev->name),
swarn->physical,
root, inum, offset, ret);
free_ipath(ipath);
return 0;
}
static void scrub_print_warning(const char *errstr, struct scrub_block *sblock)
{
struct btrfs_device *dev;
struct btrfs_fs_info *fs_info;
struct btrfs_path *path;
struct btrfs_key found_key;
struct extent_buffer *eb;
struct btrfs_extent_item *ei;
struct scrub_warning swarn;
unsigned long ptr = 0;
u64 extent_item_pos;
u64 flags = 0;
u64 ref_root;
u32 item_size;
u8 ref_level = 0;
int ret;
WARN_ON(sblock->page_count < 1);
dev = sblock->pagev[0]->dev;
fs_info = sblock->sctx->fs_info;
path = btrfs_alloc_path();
if (!path)
return;
swarn.physical = sblock->pagev[0]->physical;
swarn.logical = sblock->pagev[0]->logical;
swarn.errstr = errstr;
swarn.dev = NULL;
ret = extent_from_logical(fs_info, swarn.logical, path, &found_key,
&flags);
if (ret < 0)
goto out;
extent_item_pos = swarn.logical - found_key.objectid;
swarn.extent_item_size = found_key.offset;
eb = path->nodes[0];
ei = btrfs_item_ptr(eb, path->slots[0], struct btrfs_extent_item);
item_size = btrfs_item_size_nr(eb, path->slots[0]);
if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
do {
ret = tree_backref_for_extent(&ptr, eb, &found_key, ei,
item_size, &ref_root,
&ref_level);
btrfs_warn_in_rcu(fs_info,
"%s at logical %llu on dev %s, physical %llu: metadata %s (level %d) in tree %llu",
errstr, swarn.logical,
rcu_str_deref(dev->name),
swarn.physical,
ref_level ? "node" : "leaf",
ret < 0 ? -1 : ref_level,
ret < 0 ? -1 : ref_root);
} while (ret != 1);
btrfs_release_path(path);
} else {
btrfs_release_path(path);
swarn.path = path;
swarn.dev = dev;
iterate_extent_inodes(fs_info, found_key.objectid,
extent_item_pos, 1,
scrub_print_warning_inode, &swarn, false);
}
out:
btrfs_free_path(path);
}
static inline void scrub_get_recover(struct scrub_recover *recover)
{
refcount_inc(&recover->refs);
}
static inline void scrub_put_recover(struct btrfs_fs_info *fs_info,
struct scrub_recover *recover)
{
if (refcount_dec_and_test(&recover->refs)) {
btrfs_bio_counter_dec(fs_info);
btrfs_put_bbio(recover->bbio);
kfree(recover);
}
}
/*
* scrub_handle_errored_block gets called when either verification of the
* pages failed or the bio failed to read, e.g. with EIO. In the latter
* case, this function handles all pages in the bio, even though only one
* may be bad.
* The goal of this function is to repair the errored block by using the
* contents of one of the mirrors.
*/
static int scrub_handle_errored_block(struct scrub_block *sblock_to_check)
{
struct scrub_ctx *sctx = sblock_to_check->sctx;
struct btrfs_device *dev;
struct btrfs_fs_info *fs_info;
u64 logical;
unsigned int failed_mirror_index;
unsigned int is_metadata;
unsigned int have_csum;
struct scrub_block *sblocks_for_recheck; /* holds one for each mirror */
struct scrub_block *sblock_bad;
int ret;
int mirror_index;
int page_num;
int success;
bool full_stripe_locked;
unsigned int nofs_flag;
static DEFINE_RATELIMIT_STATE(_rs, DEFAULT_RATELIMIT_INTERVAL,
DEFAULT_RATELIMIT_BURST);
BUG_ON(sblock_to_check->page_count < 1);
fs_info = sctx->fs_info;
if (sblock_to_check->pagev[0]->flags & BTRFS_EXTENT_FLAG_SUPER) {
/*
* if we find an error in a super block, we just report it.
* They will get written with the next transaction commit
* anyway
*/
spin_lock(&sctx->stat_lock);
++sctx->stat.super_errors;
spin_unlock(&sctx->stat_lock);
return 0;
}
logical = sblock_to_check->pagev[0]->logical;
BUG_ON(sblock_to_check->pagev[0]->mirror_num < 1);
failed_mirror_index = sblock_to_check->pagev[0]->mirror_num - 1;
is_metadata = !(sblock_to_check->pagev[0]->flags &
BTRFS_EXTENT_FLAG_DATA);
have_csum = sblock_to_check->pagev[0]->have_csum;
dev = sblock_to_check->pagev[0]->dev;
/*
* We must use GFP_NOFS because the scrub task might be waiting for a
* worker task executing this function and in turn a transaction commit
* might be waiting the scrub task to pause (which needs to wait for all
* the worker tasks to complete before pausing).
* We do allocations in the workers through insert_full_stripe_lock()
* and scrub_add_page_to_wr_bio(), which happens down the call chain of
* this function.
*/
nofs_flag = memalloc_nofs_save();
/*
* For RAID5/6, race can happen for a different device scrub thread.
* For data corruption, Parity and Data threads will both try
* to recovery the data.
* Race can lead to doubly added csum error, or even unrecoverable
* error.
*/
ret = lock_full_stripe(fs_info, logical, &full_stripe_locked);
if (ret < 0) {
memalloc_nofs_restore(nofs_flag);
spin_lock(&sctx->stat_lock);
if (ret == -ENOMEM)
sctx->stat.malloc_errors++;
sctx->stat.read_errors++;
sctx->stat.uncorrectable_errors++;
spin_unlock(&sctx->stat_lock);
return ret;
}
/*
* read all mirrors one after the other. This includes to
* re-read the extent or metadata block that failed (that was
* the cause that this fixup code is called) another time,
* page by page this time in order to know which pages
* caused I/O errors and which ones are good (for all mirrors).
* It is the goal to handle the situation when more than one
* mirror contains I/O errors, but the errors do not
* overlap, i.e. the data can be repaired by selecting the
* pages from those mirrors without I/O error on the
* particular pages. One example (with blocks >= 2 * PAGE_SIZE)
* would be that mirror #1 has an I/O error on the first page,
* the second page is good, and mirror #2 has an I/O error on
* the second page, but the first page is good.
* Then the first page of the first mirror can be repaired by
* taking the first page of the second mirror, and the
* second page of the second mirror can be repaired by
* copying the contents of the 2nd page of the 1st mirror.
* One more note: if the pages of one mirror contain I/O
* errors, the checksum cannot be verified. In order to get
* the best data for repairing, the first attempt is to find
* a mirror without I/O errors and with a validated checksum.
* Only if this is not possible, the pages are picked from
* mirrors with I/O errors without considering the checksum.
* If the latter is the case, at the end, the checksum of the
* repaired area is verified in order to correctly maintain
* the statistics.
*/
sblocks_for_recheck = kcalloc(BTRFS_MAX_MIRRORS,
sizeof(*sblocks_for_recheck), GFP_KERNEL);
if (!sblocks_for_recheck) {
spin_lock(&sctx->stat_lock);
sctx->stat.malloc_errors++;
sctx->stat.read_errors++;
sctx->stat.uncorrectable_errors++;
spin_unlock(&sctx->stat_lock);
btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_READ_ERRS);
goto out;
}
/* setup the context, map the logical blocks and alloc the pages */
ret = scrub_setup_recheck_block(sblock_to_check, sblocks_for_recheck);
if (ret) {
spin_lock(&sctx->stat_lock);
sctx->stat.read_errors++;
sctx->stat.uncorrectable_errors++;
spin_unlock(&sctx->stat_lock);
btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_READ_ERRS);
goto out;
}
BUG_ON(failed_mirror_index >= BTRFS_MAX_MIRRORS);
sblock_bad = sblocks_for_recheck + failed_mirror_index;
/* build and submit the bios for the failed mirror, check checksums */
scrub_recheck_block(fs_info, sblock_bad, 1);
if (!sblock_bad->header_error && !sblock_bad->checksum_error &&
sblock_bad->no_io_error_seen) {
/*
* the error disappeared after reading page by page, or
* the area was part of a huge bio and other parts of the
* bio caused I/O errors, or the block layer merged several
* read requests into one and the error is caused by a
* different bio (usually one of the two latter cases is
* the cause)
*/
spin_lock(&sctx->stat_lock);
sctx->stat.unverified_errors++;
sblock_to_check->data_corrected = 1;
spin_unlock(&sctx->stat_lock);
if (sctx->is_dev_replace)
scrub_write_block_to_dev_replace(sblock_bad);
goto out;
}
if (!sblock_bad->no_io_error_seen) {
spin_lock(&sctx->stat_lock);
sctx->stat.read_errors++;
spin_unlock(&sctx->stat_lock);
if (__ratelimit(&_rs))
scrub_print_warning("i/o error", sblock_to_check);
btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_READ_ERRS);
} else if (sblock_bad->checksum_error) {
spin_lock(&sctx->stat_lock);
sctx->stat.csum_errors++;
spin_unlock(&sctx->stat_lock);
if (__ratelimit(&_rs))
scrub_print_warning("checksum error", sblock_to_check);
btrfs_dev_stat_inc_and_print(dev,
BTRFS_DEV_STAT_CORRUPTION_ERRS);
} else if (sblock_bad->header_error) {
spin_lock(&sctx->stat_lock);
sctx->stat.verify_errors++;
spin_unlock(&sctx->stat_lock);
if (__ratelimit(&_rs))
scrub_print_warning("checksum/header error",
sblock_to_check);
if (sblock_bad->generation_error)
btrfs_dev_stat_inc_and_print(dev,
BTRFS_DEV_STAT_GENERATION_ERRS);
else
btrfs_dev_stat_inc_and_print(dev,
BTRFS_DEV_STAT_CORRUPTION_ERRS);
}
if (sctx->readonly) {
ASSERT(!sctx->is_dev_replace);
goto out;
}
/*
* now build and submit the bios for the other mirrors, check
* checksums.
* First try to pick the mirror which is completely without I/O
* errors and also does not have a checksum error.
* If one is found, and if a checksum is present, the full block
* that is known to contain an error is rewritten. Afterwards
* the block is known to be corrected.
* If a mirror is found which is completely correct, and no
* checksum is present, only those pages are rewritten that had
* an I/O error in the block to be repaired, since it cannot be
* determined, which copy of the other pages is better (and it
* could happen otherwise that a correct page would be
* overwritten by a bad one).
*/
for (mirror_index = 0; ;mirror_index++) {
struct scrub_block *sblock_other;
if (mirror_index == failed_mirror_index)
continue;
/* raid56's mirror can be more than BTRFS_MAX_MIRRORS */
if (!scrub_is_page_on_raid56(sblock_bad->pagev[0])) {
if (mirror_index >= BTRFS_MAX_MIRRORS)
break;
if (!sblocks_for_recheck[mirror_index].page_count)
break;
sblock_other = sblocks_for_recheck + mirror_index;
} else {
struct scrub_recover *r = sblock_bad->pagev[0]->recover;
int max_allowed = r->bbio->num_stripes -
r->bbio->num_tgtdevs;
if (mirror_index >= max_allowed)
break;
if (!sblocks_for_recheck[1].page_count)
break;
ASSERT(failed_mirror_index == 0);
sblock_other = sblocks_for_recheck + 1;
sblock_other->pagev[0]->mirror_num = 1 + mirror_index;
}
/* build and submit the bios, check checksums */
scrub_recheck_block(fs_info, sblock_other, 0);
if (!sblock_other->header_error &&
!sblock_other->checksum_error &&
sblock_other->no_io_error_seen) {
if (sctx->is_dev_replace) {
scrub_write_block_to_dev_replace(sblock_other);
goto corrected_error;
} else {
ret = scrub_repair_block_from_good_copy(
sblock_bad, sblock_other);
if (!ret)
goto corrected_error;
}
}
}
if (sblock_bad->no_io_error_seen && !sctx->is_dev_replace)
goto did_not_correct_error;
/*
* In case of I/O errors in the area that is supposed to be
* repaired, continue by picking good copies of those pages.
* Select the good pages from mirrors to rewrite bad pages from
* the area to fix. Afterwards verify the checksum of the block
* that is supposed to be repaired. This verification step is
* only done for the purpose of statistic counting and for the
* final scrub report, whether errors remain.
* A perfect algorithm could make use of the checksum and try
* all possible combinations of pages from the different mirrors
* until the checksum verification succeeds. For example, when
* the 2nd page of mirror #1 faces I/O errors, and the 2nd page
* of mirror #2 is readable but the final checksum test fails,
* then the 2nd page of mirror #3 could be tried, whether now
* the final checksum succeeds. But this would be a rare
* exception and is therefore not implemented. At least it is
* avoided that the good copy is overwritten.
* A more useful improvement would be to pick the sectors
* without I/O error based on sector sizes (512 bytes on legacy
* disks) instead of on PAGE_SIZE. Then maybe 512 byte of one
* mirror could be repaired by taking 512 byte of a different
* mirror, even if other 512 byte sectors in the same PAGE_SIZE
* area are unreadable.
*/
success = 1;
for (page_num = 0; page_num < sblock_bad->page_count;
page_num++) {
struct scrub_page *page_bad = sblock_bad->pagev[page_num];
struct scrub_block *sblock_other = NULL;
/* skip no-io-error page in scrub */
if (!page_bad->io_error && !sctx->is_dev_replace)
continue;
if (scrub_is_page_on_raid56(sblock_bad->pagev[0])) {
/*
* In case of dev replace, if raid56 rebuild process
* didn't work out correct data, then copy the content
* in sblock_bad to make sure target device is identical
* to source device, instead of writing garbage data in
* sblock_for_recheck array to target device.
*/
sblock_other = NULL;
} else if (page_bad->io_error) {
/* try to find no-io-error page in mirrors */
for (mirror_index = 0;
mirror_index < BTRFS_MAX_MIRRORS &&
sblocks_for_recheck[mirror_index].page_count > 0;
mirror_index++) {
if (!sblocks_for_recheck[mirror_index].
pagev[page_num]->io_error) {
sblock_other = sblocks_for_recheck +
mirror_index;
break;
}
}
if (!sblock_other)
success = 0;
}
if (sctx->is_dev_replace) {
/*
* did not find a mirror to fetch the page
* from. scrub_write_page_to_dev_replace()
* handles this case (page->io_error), by
* filling the block with zeros before
* submitting the write request
*/
if (!sblock_other)
sblock_other = sblock_bad;
if (scrub_write_page_to_dev_replace(sblock_other,
page_num) != 0) {
atomic64_inc(
&fs_info->dev_replace.num_write_errors);
success = 0;
}
} else if (sblock_other) {
ret = scrub_repair_page_from_good_copy(sblock_bad,
sblock_other,
page_num, 0);
if (0 == ret)
page_bad->io_error = 0;
else
success = 0;
}
}
if (success && !sctx->is_dev_replace) {
if (is_metadata || have_csum) {
/*
* need to verify the checksum now that all
* sectors on disk are repaired (the write
* request for data to be repaired is on its way).
* Just be lazy and use scrub_recheck_block()
* which re-reads the data before the checksum
* is verified, but most likely the data comes out
* of the page cache.
*/
scrub_recheck_block(fs_info, sblock_bad, 1);
if (!sblock_bad->header_error &&
!sblock_bad->checksum_error &&
sblock_bad->no_io_error_seen)
goto corrected_error;
else
goto did_not_correct_error;
} else {
corrected_error:
spin_lock(&sctx->stat_lock);
sctx->stat.corrected_errors++;
sblock_to_check->data_corrected = 1;
spin_unlock(&sctx->stat_lock);
btrfs_err_rl_in_rcu(fs_info,
"fixed up error at logical %llu on dev %s",
logical, rcu_str_deref(dev->name));
}
} else {
did_not_correct_error:
spin_lock(&sctx->stat_lock);
sctx->stat.uncorrectable_errors++;
spin_unlock(&sctx->stat_lock);
btrfs_err_rl_in_rcu(fs_info,
"unable to fixup (regular) error at logical %llu on dev %s",
logical, rcu_str_deref(dev->name));
}
out:
if (sblocks_for_recheck) {
for (mirror_index = 0; mirror_index < BTRFS_MAX_MIRRORS;
mirror_index++) {
struct scrub_block *sblock = sblocks_for_recheck +
mirror_index;
struct scrub_recover *recover;
int page_index;
for (page_index = 0; page_index < sblock->page_count;
page_index++) {
sblock->pagev[page_index]->sblock = NULL;
recover = sblock->pagev[page_index]->recover;
if (recover) {
scrub_put_recover(fs_info, recover);
sblock->pagev[page_index]->recover =
NULL;
}
scrub_page_put(sblock->pagev[page_index]);
}
}
kfree(sblocks_for_recheck);
}
ret = unlock_full_stripe(fs_info, logical, full_stripe_locked);
memalloc_nofs_restore(nofs_flag);
if (ret < 0)
return ret;
return 0;
}
static inline int scrub_nr_raid_mirrors(struct btrfs_bio *bbio)
{
if (bbio->map_type & BTRFS_BLOCK_GROUP_RAID5)
return 2;
else if (bbio->map_type & BTRFS_BLOCK_GROUP_RAID6)
return 3;
else
return (int)bbio->num_stripes;
}
static inline void scrub_stripe_index_and_offset(u64 logical, u64 map_type,
u64 *raid_map,
u64 mapped_length,
int nstripes, int mirror,
int *stripe_index,
u64 *stripe_offset)
{
int i;
if (map_type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
/* RAID5/6 */
for (i = 0; i < nstripes; i++) {
if (raid_map[i] == RAID6_Q_STRIPE ||
raid_map[i] == RAID5_P_STRIPE)
continue;
if (logical >= raid_map[i] &&
logical < raid_map[i] + mapped_length)
break;
}
*stripe_index = i;
*stripe_offset = logical - raid_map[i];
} else {
/* The other RAID type */
*stripe_index = mirror;
*stripe_offset = 0;
}
}
static int scrub_setup_recheck_block(struct scrub_block *original_sblock,
struct scrub_block *sblocks_for_recheck)
{
struct scrub_ctx *sctx = original_sblock->sctx;
struct btrfs_fs_info *fs_info = sctx->fs_info;
u64 length = original_sblock->page_count * PAGE_SIZE;
u64 logical = original_sblock->pagev[0]->logical;
u64 generation = original_sblock->pagev[0]->generation;
u64 flags = original_sblock->pagev[0]->flags;
u64 have_csum = original_sblock->pagev[0]->have_csum;
struct scrub_recover *recover;
struct btrfs_bio *bbio;
u64 sublen;
u64 mapped_length;
u64 stripe_offset;
int stripe_index;
int page_index = 0;
int mirror_index;
int nmirrors;
int ret;
/*
* note: the two members refs and outstanding_pages
* are not used (and not set) in the blocks that are used for
* the recheck procedure
*/
while (length > 0) {
sublen = min_t(u64, length, PAGE_SIZE);
mapped_length = sublen;
bbio = NULL;
/*
* with a length of PAGE_SIZE, each returned stripe
* represents one mirror
*/
btrfs_bio_counter_inc_blocked(fs_info);
ret = btrfs_map_sblock(fs_info, BTRFS_MAP_GET_READ_MIRRORS,
logical, &mapped_length, &bbio);
if (ret || !bbio || mapped_length < sublen) {
btrfs_put_bbio(bbio);
btrfs_bio_counter_dec(fs_info);
return -EIO;
}
recover = kzalloc(sizeof(struct scrub_recover), GFP_NOFS);
if (!recover) {
btrfs_put_bbio(bbio);
btrfs_bio_counter_dec(fs_info);
return -ENOMEM;
}
refcount_set(&recover->refs, 1);
recover->bbio = bbio;
recover->map_length = mapped_length;
BUG_ON(page_index >= SCRUB_MAX_PAGES_PER_BLOCK);
nmirrors = min(scrub_nr_raid_mirrors(bbio), BTRFS_MAX_MIRRORS);
for (mirror_index = 0; mirror_index < nmirrors;
mirror_index++) {
struct scrub_block *sblock;
struct scrub_page *page;
sblock = sblocks_for_recheck + mirror_index;
sblock->sctx = sctx;
page = kzalloc(sizeof(*page), GFP_NOFS);
if (!page) {
leave_nomem:
spin_lock(&sctx->stat_lock);
sctx->stat.malloc_errors++;
spin_unlock(&sctx->stat_lock);
scrub_put_recover(fs_info, recover);
return -ENOMEM;
}
scrub_page_get(page);
sblock->pagev[page_index] = page;
page->sblock = sblock;
page->flags = flags;
page->generation = generation;
page->logical = logical;
page->have_csum = have_csum;
if (have_csum)
memcpy(page->csum,
original_sblock->pagev[0]->csum,
sctx->csum_size);
scrub_stripe_index_and_offset(logical,
bbio->map_type,
bbio->raid_map,
mapped_length,
bbio->num_stripes -
bbio->num_tgtdevs,
mirror_index,
&stripe_index,
&stripe_offset);
page->physical = bbio->stripes[stripe_index].physical +
stripe_offset;
page->dev = bbio->stripes[stripe_index].dev;
BUG_ON(page_index >= original_sblock->page_count);
page->physical_for_dev_replace =
original_sblock->pagev[page_index]->
physical_for_dev_replace;
/* for missing devices, dev->bdev is NULL */
page->mirror_num = mirror_index + 1;
sblock->page_count++;
page->page = alloc_page(GFP_NOFS);
if (!page->page)
goto leave_nomem;
scrub_get_recover(recover);
page->recover = recover;
}
scrub_put_recover(fs_info, recover);
length -= sublen;
logical += sublen;
page_index++;
}
return 0;
}
static void scrub_bio_wait_endio(struct bio *bio)
{
complete(bio->bi_private);
}
static int scrub_submit_raid56_bio_wait(struct btrfs_fs_info *fs_info,
struct bio *bio,
struct scrub_page *page)
{
DECLARE_COMPLETION_ONSTACK(done);
int ret;
int mirror_num;
bio->bi_iter.bi_sector = page->logical >> 9;
bio->bi_private = &done;
bio->bi_end_io = scrub_bio_wait_endio;
mirror_num = page->sblock->pagev[0]->mirror_num;
ret = raid56_parity_recover(fs_info, bio, page->recover->bbio,
page->recover->map_length,
mirror_num, 0);
if (ret)
return ret;
wait_for_completion_io(&done);
return blk_status_to_errno(bio->bi_status);
}
static void scrub_recheck_block_on_raid56(struct btrfs_fs_info *fs_info,
struct scrub_block *sblock)
{
struct scrub_page *first_page = sblock->pagev[0];
struct bio *bio;
int page_num;
/* All pages in sblock belong to the same stripe on the same device. */
ASSERT(first_page->dev);
if (!first_page->dev->bdev)
goto out;
bio = btrfs_io_bio_alloc(BIO_MAX_PAGES);
bio_set_dev(bio, first_page->dev->bdev);
for (page_num = 0; page_num < sblock->page_count; page_num++) {
struct scrub_page *page = sblock->pagev[page_num];
WARN_ON(!page->page);
bio_add_page(bio, page->page, PAGE_SIZE, 0);
}
if (scrub_submit_raid56_bio_wait(fs_info, bio, first_page)) {
bio_put(bio);
goto out;
}
bio_put(bio);
scrub_recheck_block_checksum(sblock);
return;
out:
for (page_num = 0; page_num < sblock->page_count; page_num++)
sblock->pagev[page_num]->io_error = 1;
sblock->no_io_error_seen = 0;
}
/*
* this function will check the on disk data for checksum errors, header
* errors and read I/O errors. If any I/O errors happen, the exact pages
* which are errored are marked as being bad. The goal is to enable scrub
* to take those pages that are not errored from all the mirrors so that
* the pages that are errored in the just handled mirror can be repaired.
*/
static void scrub_recheck_block(struct btrfs_fs_info *fs_info,
struct scrub_block *sblock,
int retry_failed_mirror)
{
int page_num;
sblock->no_io_error_seen = 1;
/* short cut for raid56 */
if (!retry_failed_mirror && scrub_is_page_on_raid56(sblock->pagev[0]))
return scrub_recheck_block_on_raid56(fs_info, sblock);
for (page_num = 0; page_num < sblock->page_count; page_num++) {
struct bio *bio;
struct scrub_page *page = sblock->pagev[page_num];
if (page->dev->bdev == NULL) {
page->io_error = 1;
sblock->no_io_error_seen = 0;
continue;
}
WARN_ON(!page->page);
bio = btrfs_io_bio_alloc(1);
bio_set_dev(bio, page->dev->bdev);
bio_add_page(bio, page->page, PAGE_SIZE, 0);
bio->bi_iter.bi_sector = page->physical >> 9;
bio->bi_opf = REQ_OP_READ;
if (btrfsic_submit_bio_wait(bio)) {
page->io_error = 1;
sblock->no_io_error_seen = 0;
}
bio_put(bio);
}
if (sblock->no_io_error_seen)
scrub_recheck_block_checksum(sblock);
}
static inline int scrub_check_fsid(u8 fsid[],
struct scrub_page *spage)
{
struct btrfs_fs_devices *fs_devices = spage->dev->fs_devices;
int ret;
ret = memcmp(fsid, fs_devices->fsid, BTRFS_FSID_SIZE);
return !ret;
}
static void scrub_recheck_block_checksum(struct scrub_block *sblock)
{
sblock->header_error = 0;
sblock->checksum_error = 0;
sblock->generation_error = 0;
if (sblock->pagev[0]->flags & BTRFS_EXTENT_FLAG_DATA)
scrub_checksum_data(sblock);
else
scrub_checksum_tree_block(sblock);
}
static int scrub_repair_block_from_good_copy(struct scrub_block *sblock_bad,
struct scrub_block *sblock_good)
{
int page_num;
int ret = 0;
for (page_num = 0; page_num < sblock_bad->page_count; page_num++) {
int ret_sub;
ret_sub = scrub_repair_page_from_good_copy(sblock_bad,
sblock_good,
page_num, 1);
if (ret_sub)
ret = ret_sub;
}
return ret;
}
static int scrub_repair_page_from_good_copy(struct scrub_block *sblock_bad,
struct scrub_block *sblock_good,
int page_num, int force_write)
{
struct scrub_page *page_bad = sblock_bad->pagev[page_num];
struct scrub_page *page_good = sblock_good->pagev[page_num];
struct btrfs_fs_info *fs_info = sblock_bad->sctx->fs_info;
BUG_ON(page_bad->page == NULL);
BUG_ON(page_good->page == NULL);
if (force_write || sblock_bad->header_error ||
sblock_bad->checksum_error || page_bad->io_error) {
struct bio *bio;
int ret;
if (!page_bad->dev->bdev) {
btrfs_warn_rl(fs_info,
"scrub_repair_page_from_good_copy(bdev == NULL) is unexpected");
return -EIO;
}
bio = btrfs_io_bio_alloc(1);
bio_set_dev(bio, page_bad->dev->bdev);
bio->bi_iter.bi_sector = page_bad->physical >> 9;
bio->bi_opf = REQ_OP_WRITE;
ret = bio_add_page(bio, page_good->page, PAGE_SIZE, 0);
if (PAGE_SIZE != ret) {
bio_put(bio);
return -EIO;
}
if (btrfsic_submit_bio_wait(bio)) {
btrfs_dev_stat_inc_and_print(page_bad->dev,
BTRFS_DEV_STAT_WRITE_ERRS);
atomic64_inc(&fs_info->dev_replace.num_write_errors);
bio_put(bio);
return -EIO;
}
bio_put(bio);
}
return 0;
}
static void scrub_write_block_to_dev_replace(struct scrub_block *sblock)
{
struct btrfs_fs_info *fs_info = sblock->sctx->fs_info;
int page_num;
/*
* This block is used for the check of the parity on the source device,
* so the data needn't be written into the destination device.
*/
if (sblock->sparity)
return;
for (page_num = 0; page_num < sblock->page_count; page_num++) {
int ret;
ret = scrub_write_page_to_dev_replace(sblock, page_num);
if (ret)
atomic64_inc(&fs_info->dev_replace.num_write_errors);
}
}
static int scrub_write_page_to_dev_replace(struct scrub_block *sblock,
int page_num)
{
struct scrub_page *spage = sblock->pagev[page_num];
BUG_ON(spage->page == NULL);
if (spage->io_error) {
void *mapped_buffer = kmap_atomic(spage->page);
clear_page(mapped_buffer);
flush_dcache_page(spage->page);
kunmap_atomic(mapped_buffer);
}
return scrub_add_page_to_wr_bio(sblock->sctx, spage);
}
static int scrub_add_page_to_wr_bio(struct scrub_ctx *sctx,
struct scrub_page *spage)
{
struct scrub_bio *sbio;
int ret;
mutex_lock(&sctx->wr_lock);
again:
if (!sctx->wr_curr_bio) {
sctx->wr_curr_bio = kzalloc(sizeof(*sctx->wr_curr_bio),
GFP_KERNEL);
if (!sctx->wr_curr_bio) {
mutex_unlock(&sctx->wr_lock);
return -ENOMEM;
}
sctx->wr_curr_bio->sctx = sctx;
sctx->wr_curr_bio->page_count = 0;
}
sbio = sctx->wr_curr_bio;
if (sbio->page_count == 0) {
struct bio *bio;
sbio->physical = spage->physical_for_dev_replace;
sbio->logical = spage->logical;
sbio->dev = sctx->wr_tgtdev;
bio = sbio->bio;
if (!bio) {
bio = btrfs_io_bio_alloc(sctx->pages_per_wr_bio);
sbio->bio = bio;
}
bio->bi_private = sbio;
bio->bi_end_io = scrub_wr_bio_end_io;
bio_set_dev(bio, sbio->dev->bdev);
bio->bi_iter.bi_sector = sbio->physical >> 9;
bio->bi_opf = REQ_OP_WRITE;
sbio->status = 0;
} else if (sbio->physical + sbio->page_count * PAGE_SIZE !=
spage->physical_for_dev_replace ||
sbio->logical + sbio->page_count * PAGE_SIZE !=
spage->logical) {
scrub_wr_submit(sctx);
goto again;
}
ret = bio_add_page(sbio->bio, spage->page, PAGE_SIZE, 0);
if (ret != PAGE_SIZE) {
if (sbio->page_count < 1) {
bio_put(sbio->bio);
sbio->bio = NULL;
mutex_unlock(&sctx->wr_lock);
return -EIO;
}
scrub_wr_submit(sctx);
goto again;
}
sbio->pagev[sbio->page_count] = spage;
scrub_page_get(spage);
sbio->page_count++;
if (sbio->page_count == sctx->pages_per_wr_bio)
scrub_wr_submit(sctx);
mutex_unlock(&sctx->wr_lock);
return 0;
}
static void scrub_wr_submit(struct scrub_ctx *sctx)
{
struct scrub_bio *sbio;
if (!sctx->wr_curr_bio)
return;
sbio = sctx->wr_curr_bio;
sctx->wr_curr_bio = NULL;
WARN_ON(!sbio->bio->bi_disk);
scrub_pending_bio_inc(sctx);
/* process all writes in a single worker thread. Then the block layer
* orders the requests before sending them to the driver which
* doubled the write performance on spinning disks when measured
* with Linux 3.5 */
btrfsic_submit_bio(sbio->bio);
}
static void scrub_wr_bio_end_io(struct bio *bio)
{
struct scrub_bio *sbio = bio->bi_private;
struct btrfs_fs_info *fs_info = sbio->dev->fs_info;
sbio->status = bio->bi_status;
sbio->bio = bio;
btrfs_init_work(&sbio->work, btrfs_scrubwrc_helper,
scrub_wr_bio_end_io_worker, NULL, NULL);
btrfs_queue_work(fs_info->scrub_wr_completion_workers, &sbio->work);
}
static void scrub_wr_bio_end_io_worker(struct btrfs_work *work)
{
struct scrub_bio *sbio = container_of(work, struct scrub_bio, work);
struct scrub_ctx *sctx = sbio->sctx;
int i;
WARN_ON(sbio->page_count > SCRUB_PAGES_PER_WR_BIO);
if (sbio->status) {
struct btrfs_dev_replace *dev_replace =
&sbio->sctx->fs_info->dev_replace;
for (i = 0; i < sbio->page_count; i++) {
struct scrub_page *spage = sbio->pagev[i];
spage->io_error = 1;
atomic64_inc(&dev_replace->num_write_errors);
}
}
for (i = 0; i < sbio->page_count; i++)
scrub_page_put(sbio->pagev[i]);
bio_put(sbio->bio);
kfree(sbio);
scrub_pending_bio_dec(sctx);
}
static int scrub_checksum(struct scrub_block *sblock)
{
u64 flags;
int ret;
/*
* No need to initialize these stats currently,
* because this function only use return value
* instead of these stats value.
*
* Todo:
* always use stats
*/
sblock->header_error = 0;
sblock->generation_error = 0;
sblock->checksum_error = 0;
WARN_ON(sblock->page_count < 1);
flags = sblock->pagev[0]->flags;
ret = 0;
if (flags & BTRFS_EXTENT_FLAG_DATA)
ret = scrub_checksum_data(sblock);
else if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK)
ret = scrub_checksum_tree_block(sblock);
else if (flags & BTRFS_EXTENT_FLAG_SUPER)
(void)scrub_checksum_super(sblock);
else
WARN_ON(1);
if (ret)
scrub_handle_errored_block(sblock);
return ret;
}
static int scrub_checksum_data(struct scrub_block *sblock)
{
struct scrub_ctx *sctx = sblock->sctx;
u8 csum[BTRFS_CSUM_SIZE];
u8 *on_disk_csum;
struct page *page;
void *buffer;
u32 crc = ~(u32)0;
u64 len;
int index;
BUG_ON(sblock->page_count < 1);
if (!sblock->pagev[0]->have_csum)
return 0;
on_disk_csum = sblock->pagev[0]->csum;
page = sblock->pagev[0]->page;
buffer = kmap_atomic(page);
len = sctx->fs_info->sectorsize;
index = 0;
for (;;) {
u64 l = min_t(u64, len, PAGE_SIZE);
crc = btrfs_csum_data(buffer, crc, l);
kunmap_atomic(buffer);
len -= l;
if (len == 0)
break;
index++;
BUG_ON(index >= sblock->page_count);
BUG_ON(!sblock->pagev[index]->page);
page = sblock->pagev[index]->page;
buffer = kmap_atomic(page);
}
btrfs_csum_final(crc, csum);
if (memcmp(csum, on_disk_csum, sctx->csum_size))
sblock->checksum_error = 1;
return sblock->checksum_error;
}
static int scrub_checksum_tree_block(struct scrub_block *sblock)
{
struct scrub_ctx *sctx = sblock->sctx;
struct btrfs_header *h;
struct btrfs_fs_info *fs_info = sctx->fs_info;
u8 calculated_csum[BTRFS_CSUM_SIZE];
u8 on_disk_csum[BTRFS_CSUM_SIZE];
struct page *page;
void *mapped_buffer;
u64 mapped_size;
void *p;
u32 crc = ~(u32)0;
u64 len;
int index;
BUG_ON(sblock->page_count < 1);
page = sblock->pagev[0]->page;
mapped_buffer = kmap_atomic(page);
h = (struct btrfs_header *)mapped_buffer;
memcpy(on_disk_csum, h->csum, sctx->csum_size);
/*
* we don't use the getter functions here, as we
* a) don't have an extent buffer and
* b) the page is already kmapped
*/
if (sblock->pagev[0]->logical != btrfs_stack_header_bytenr(h))
sblock->header_error = 1;
if (sblock->pagev[0]->generation != btrfs_stack_header_generation(h)) {
sblock->header_error = 1;
sblock->generation_error = 1;
}
if (!scrub_check_fsid(h->fsid, sblock->pagev[0]))
sblock->header_error = 1;
if (memcmp(h->chunk_tree_uuid, fs_info->chunk_tree_uuid,
BTRFS_UUID_SIZE))
sblock->header_error = 1;
len = sctx->fs_info->nodesize - BTRFS_CSUM_SIZE;
mapped_size = PAGE_SIZE - BTRFS_CSUM_SIZE;
p = ((u8 *)mapped_buffer) + BTRFS_CSUM_SIZE;
index = 0;
for (;;) {
u64 l = min_t(u64, len, mapped_size);
crc = btrfs_csum_data(p, crc, l);
kunmap_atomic(mapped_buffer);
len -= l;
if (len == 0)
break;
index++;
BUG_ON(index >= sblock->page_count);
BUG_ON(!sblock->pagev[index]->page);
page = sblock->pagev[index]->page;
mapped_buffer = kmap_atomic(page);
mapped_size = PAGE_SIZE;
p = mapped_buffer;
}
btrfs_csum_final(crc, calculated_csum);
if (memcmp(calculated_csum, on_disk_csum, sctx->csum_size))
sblock->checksum_error = 1;
return sblock->header_error || sblock->checksum_error;
}
static int scrub_checksum_super(struct scrub_block *sblock)
{
struct btrfs_super_block *s;
struct scrub_ctx *sctx = sblock->sctx;
u8 calculated_csum[BTRFS_CSUM_SIZE];
u8 on_disk_csum[BTRFS_CSUM_SIZE];
struct page *page;
void *mapped_buffer;
u64 mapped_size;
void *p;
u32 crc = ~(u32)0;
int fail_gen = 0;
int fail_cor = 0;
u64 len;
int index;
BUG_ON(sblock->page_count < 1);
page = sblock->pagev[0]->page;
mapped_buffer = kmap_atomic(page);
s = (struct btrfs_super_block *)mapped_buffer;
memcpy(on_disk_csum, s->csum, sctx->csum_size);
if (sblock->pagev[0]->logical != btrfs_super_bytenr(s))
++fail_cor;
if (sblock->pagev[0]->generation != btrfs_super_generation(s))
++fail_gen;
if (!scrub_check_fsid(s->fsid, sblock->pagev[0]))
++fail_cor;
len = BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE;
mapped_size = PAGE_SIZE - BTRFS_CSUM_SIZE;
p = ((u8 *)mapped_buffer) + BTRFS_CSUM_SIZE;
index = 0;
for (;;) {
u64 l = min_t(u64, len, mapped_size);
crc = btrfs_csum_data(p, crc, l);
kunmap_atomic(mapped_buffer);
len -= l;
if (len == 0)
break;
index++;
BUG_ON(index >= sblock->page_count);
BUG_ON(!sblock->pagev[index]->page);
page = sblock->pagev[index]->page;
mapped_buffer = kmap_atomic(page);
mapped_size = PAGE_SIZE;
p = mapped_buffer;
}
btrfs_csum_final(crc, calculated_csum);
if (memcmp(calculated_csum, on_disk_csum, sctx->csum_size))
++fail_cor;
if (fail_cor + fail_gen) {
/*
* if we find an error in a super block, we just report it.
* They will get written with the next transaction commit
* anyway
*/
spin_lock(&sctx->stat_lock);
++sctx->stat.super_errors;
spin_unlock(&sctx->stat_lock);
if (fail_cor)
btrfs_dev_stat_inc_and_print(sblock->pagev[0]->dev,
BTRFS_DEV_STAT_CORRUPTION_ERRS);
else
btrfs_dev_stat_inc_and_print(sblock->pagev[0]->dev,
BTRFS_DEV_STAT_GENERATION_ERRS);
}
return fail_cor + fail_gen;
}
static void scrub_block_get(struct scrub_block *sblock)
{
refcount_inc(&sblock->refs);
}
static void scrub_block_put(struct scrub_block *sblock)
{
if (refcount_dec_and_test(&sblock->refs)) {
int i;
if (sblock->sparity)
scrub_parity_put(sblock->sparity);
for (i = 0; i < sblock->page_count; i++)
scrub_page_put(sblock->pagev[i]);
kfree(sblock);
}
}
static void scrub_page_get(struct scrub_page *spage)
{
atomic_inc(&spage->refs);
}
static void scrub_page_put(struct scrub_page *spage)
{
if (atomic_dec_and_test(&spage->refs)) {
if (spage->page)
__free_page(spage->page);
kfree(spage);
}
}
static void scrub_submit(struct scrub_ctx *sctx)
{
struct scrub_bio *sbio;
if (sctx->curr == -1)
return;
sbio = sctx->bios[sctx->curr];
sctx->curr = -1;
scrub_pending_bio_inc(sctx);
btrfsic_submit_bio(sbio->bio);
}
static int scrub_add_page_to_rd_bio(struct scrub_ctx *sctx,
struct scrub_page *spage)
{
struct scrub_block *sblock = spage->sblock;
struct scrub_bio *sbio;
int ret;
again:
/*
* grab a fresh bio or wait for one to become available
*/
while (sctx->curr == -1) {
spin_lock(&sctx->list_lock);
sctx->curr = sctx->first_free;
if (sctx->curr != -1) {
sctx->first_free = sctx->bios[sctx->curr]->next_free;
sctx->bios[sctx->curr]->next_free = -1;
sctx->bios[sctx->curr]->page_count = 0;
spin_unlock(&sctx->list_lock);
} else {
spin_unlock(&sctx->list_lock);
wait_event(sctx->list_wait, sctx->first_free != -1);
}
}
sbio = sctx->bios[sctx->curr];
if (sbio->page_count == 0) {
struct bio *bio;
sbio->physical = spage->physical;
sbio->logical = spage->logical;
sbio->dev = spage->dev;
bio = sbio->bio;
if (!bio) {
bio = btrfs_io_bio_alloc(sctx->pages_per_rd_bio);
sbio->bio = bio;
}
bio->bi_private = sbio;
bio->bi_end_io = scrub_bio_end_io;
bio_set_dev(bio, sbio->dev->bdev);
bio->bi_iter.bi_sector = sbio->physical >> 9;
bio->bi_opf = REQ_OP_READ;
sbio->status = 0;
} else if (sbio->physical + sbio->page_count * PAGE_SIZE !=
spage->physical ||
sbio->logical + sbio->page_count * PAGE_SIZE !=
spage->logical ||
sbio->dev != spage->dev) {
scrub_submit(sctx);
goto again;
}
sbio->pagev[sbio->page_count] = spage;
ret = bio_add_page(sbio->bio, spage->page, PAGE_SIZE, 0);
if (ret != PAGE_SIZE) {
if (sbio->page_count < 1) {
bio_put(sbio->bio);
sbio->bio = NULL;
return -EIO;
}
scrub_submit(sctx);
goto again;
}
scrub_block_get(sblock); /* one for the page added to the bio */
atomic_inc(&sblock->outstanding_pages);
sbio->page_count++;
if (sbio->page_count == sctx->pages_per_rd_bio)
scrub_submit(sctx);
return 0;
}
static void scrub_missing_raid56_end_io(struct bio *bio)
{
struct scrub_block *sblock = bio->bi_private;
struct btrfs_fs_info *fs_info = sblock->sctx->fs_info;
if (bio->bi_status)
sblock->no_io_error_seen = 0;
bio_put(bio);
btrfs_queue_work(fs_info->scrub_workers, &sblock->work);
}
static void scrub_missing_raid56_worker(struct btrfs_work *work)
{
struct scrub_block *sblock = container_of(work, struct scrub_block, work);
struct scrub_ctx *sctx = sblock->sctx;
struct btrfs_fs_info *fs_info = sctx->fs_info;
u64 logical;
struct btrfs_device *dev;
logical = sblock->pagev[0]->logical;
dev = sblock->pagev[0]->dev;
if (sblock->no_io_error_seen)
scrub_recheck_block_checksum(sblock);
if (!sblock->no_io_error_seen) {
spin_lock(&sctx->stat_lock);
sctx->stat.read_errors++;
spin_unlock(&sctx->stat_lock);
btrfs_err_rl_in_rcu(fs_info,
"IO error rebuilding logical %llu for dev %s",
logical, rcu_str_deref(dev->name));
} else if (sblock->header_error || sblock->checksum_error) {
spin_lock(&sctx->stat_lock);
sctx->stat.uncorrectable_errors++;
spin_unlock(&sctx->stat_lock);
btrfs_err_rl_in_rcu(fs_info,
"failed to rebuild valid logical %llu for dev %s",
logical, rcu_str_deref(dev->name));
} else {
scrub_write_block_to_dev_replace(sblock);
}
scrub_block_put(sblock);
if (sctx->is_dev_replace && sctx->flush_all_writes) {
mutex_lock(&sctx->wr_lock);
scrub_wr_submit(sctx);
mutex_unlock(&sctx->wr_lock);
}
scrub_pending_bio_dec(sctx);
}
static void scrub_missing_raid56_pages(struct scrub_block *sblock)
{
struct scrub_ctx *sctx = sblock->sctx;
struct btrfs_fs_info *fs_info = sctx->fs_info;
u64 length = sblock->page_count * PAGE_SIZE;
u64 logical = sblock->pagev[0]->logical;
struct btrfs_bio *bbio = NULL;
struct bio *bio;
struct btrfs_raid_bio *rbio;
int ret;
int i;
btrfs_bio_counter_inc_blocked(fs_info);
ret = btrfs_map_sblock(fs_info, BTRFS_MAP_GET_READ_MIRRORS, logical,
&length, &bbio);
if (ret || !bbio || !bbio->raid_map)
goto bbio_out;
if (WARN_ON(!sctx->is_dev_replace ||
!(bbio->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK))) {
/*
* We shouldn't be scrubbing a missing device. Even for dev
* replace, we should only get here for RAID 5/6. We either
* managed to mount something with no mirrors remaining or
* there's a bug in scrub_remap_extent()/btrfs_map_block().
*/
goto bbio_out;
}
bio = btrfs_io_bio_alloc(0);
bio->bi_iter.bi_sector = logical >> 9;
bio->bi_private = sblock;
bio->bi_end_io = scrub_missing_raid56_end_io;
rbio = raid56_alloc_missing_rbio(fs_info, bio, bbio, length);
if (!rbio)
goto rbio_out;
for (i = 0; i < sblock->page_count; i++) {
struct scrub_page *spage = sblock->pagev[i];
raid56_add_scrub_pages(rbio, spage->page, spage->logical);
}
btrfs_init_work(&sblock->work, btrfs_scrub_helper,
scrub_missing_raid56_worker, NULL, NULL);
scrub_block_get(sblock);
scrub_pending_bio_inc(sctx);
raid56_submit_missing_rbio(rbio);
return;
rbio_out:
bio_put(bio);
bbio_out:
btrfs_bio_counter_dec(fs_info);
btrfs_put_bbio(bbio);
spin_lock(&sctx->stat_lock);
sctx->stat.malloc_errors++;
spin_unlock(&sctx->stat_lock);
}
static int scrub_pages(struct scrub_ctx *sctx, u64 logical, u64 len,
u64 physical, struct btrfs_device *dev, u64 flags,
u64 gen, int mirror_num, u8 *csum, int force,
u64 physical_for_dev_replace)
{
struct scrub_block *sblock;
int index;
sblock = kzalloc(sizeof(*sblock), GFP_KERNEL);
if (!sblock) {
spin_lock(&sctx->stat_lock);
sctx->stat.malloc_errors++;
spin_unlock(&sctx->stat_lock);
return -ENOMEM;
}
/* one ref inside this function, plus one for each page added to
* a bio later on */
refcount_set(&sblock->refs, 1);
sblock->sctx = sctx;
sblock->no_io_error_seen = 1;
for (index = 0; len > 0; index++) {
struct scrub_page *spage;
u64 l = min_t(u64, len, PAGE_SIZE);
spage = kzalloc(sizeof(*spage), GFP_KERNEL);
if (!spage) {
leave_nomem:
spin_lock(&sctx->stat_lock);
sctx->stat.malloc_errors++;
spin_unlock(&sctx->stat_lock);
scrub_block_put(sblock);
return -ENOMEM;
}
BUG_ON(index >= SCRUB_MAX_PAGES_PER_BLOCK);
scrub_page_get(spage);
sblock->pagev[index] = spage;
spage->sblock = sblock;
spage->dev = dev;
spage->flags = flags;
spage->generation = gen;
spage->logical = logical;
spage->physical = physical;
spage->physical_for_dev_replace = physical_for_dev_replace;
spage->mirror_num = mirror_num;
if (csum) {
spage->have_csum = 1;
memcpy(spage->csum, csum, sctx->csum_size);
} else {
spage->have_csum = 0;
}
sblock->page_count++;
spage->page = alloc_page(GFP_KERNEL);
if (!spage->page)
goto leave_nomem;
len -= l;
logical += l;
physical += l;
physical_for_dev_replace += l;
}
WARN_ON(sblock->page_count == 0);
if (test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state)) {
/*
* This case should only be hit for RAID 5/6 device replace. See
* the comment in scrub_missing_raid56_pages() for details.
*/
scrub_missing_raid56_pages(sblock);
} else {
for (index = 0; index < sblock->page_count; index++) {
struct scrub_page *spage = sblock->pagev[index];
int ret;
ret = scrub_add_page_to_rd_bio(sctx, spage);
if (ret) {
scrub_block_put(sblock);
return ret;
}
}
if (force)
scrub_submit(sctx);
}
/* last one frees, either here or in bio completion for last page */
scrub_block_put(sblock);
return 0;
}
static void scrub_bio_end_io(struct bio *bio)
{
struct scrub_bio *sbio = bio->bi_private;
struct btrfs_fs_info *fs_info = sbio->dev->fs_info;
sbio->status = bio->bi_status;
sbio->bio = bio;
btrfs_queue_work(fs_info->scrub_workers, &sbio->work);
}
static void scrub_bio_end_io_worker(struct btrfs_work *work)
{
struct scrub_bio *sbio = container_of(work, struct scrub_bio, work);
struct scrub_ctx *sctx = sbio->sctx;
int i;
BUG_ON(sbio->page_count > SCRUB_PAGES_PER_RD_BIO);
if (sbio->status) {
for (i = 0; i < sbio->page_count; i++) {
struct scrub_page *spage = sbio->pagev[i];
spage->io_error = 1;
spage->sblock->no_io_error_seen = 0;
}
}
/* now complete the scrub_block items that have all pages completed */
for (i = 0; i < sbio->page_count; i++) {
struct scrub_page *spage = sbio->pagev[i];
struct scrub_block *sblock = spage->sblock;
if (atomic_dec_and_test(&sblock->outstanding_pages))
scrub_block_complete(sblock);
scrub_block_put(sblock);
}
bio_put(sbio->bio);
sbio->bio = NULL;
spin_lock(&sctx->list_lock);
sbio->next_free = sctx->first_free;
sctx->first_free = sbio->index;
spin_unlock(&sctx->list_lock);
if (sctx->is_dev_replace && sctx->flush_all_writes) {
mutex_lock(&sctx->wr_lock);
scrub_wr_submit(sctx);
mutex_unlock(&sctx->wr_lock);
}
scrub_pending_bio_dec(sctx);
}
static inline void __scrub_mark_bitmap(struct scrub_parity *sparity,
unsigned long *bitmap,
u64 start, u64 len)
{
u64 offset;
u64 nsectors64;
u32 nsectors;
int sectorsize = sparity->sctx->fs_info->sectorsize;
if (len >= sparity->stripe_len) {
bitmap_set(bitmap, 0, sparity->nsectors);
return;
}
start -= sparity->logic_start;
start = div64_u64_rem(start, sparity->stripe_len, &offset);
offset = div_u64(offset, sectorsize);
nsectors64 = div_u64(len, sectorsize);
ASSERT(nsectors64 < UINT_MAX);
nsectors = (u32)nsectors64;
if (offset + nsectors <= sparity->nsectors) {
bitmap_set(bitmap, offset, nsectors);
return;
}
bitmap_set(bitmap, offset, sparity->nsectors - offset);
bitmap_set(bitmap, 0, nsectors - (sparity->nsectors - offset));
}
static inline void scrub_parity_mark_sectors_error(struct scrub_parity *sparity,
u64 start, u64 len)
{
__scrub_mark_bitmap(sparity, sparity->ebitmap, start, len);
}
static inline void scrub_parity_mark_sectors_data(struct scrub_parity *sparity,
u64 start, u64 len)
{
__scrub_mark_bitmap(sparity, sparity->dbitmap, start, len);
}
static void scrub_block_complete(struct scrub_block *sblock)
{
int corrupted = 0;
if (!sblock->no_io_error_seen) {
corrupted = 1;
scrub_handle_errored_block(sblock);
} else {
/*
* if has checksum error, write via repair mechanism in
* dev replace case, otherwise write here in dev replace
* case.
*/
corrupted = scrub_checksum(sblock);
if (!corrupted && sblock->sctx->is_dev_replace)
scrub_write_block_to_dev_replace(sblock);
}
if (sblock->sparity && corrupted && !sblock->data_corrected) {
u64 start = sblock->pagev[0]->logical;
u64 end = sblock->pagev[sblock->page_count - 1]->logical +
PAGE_SIZE;
scrub_parity_mark_sectors_error(sblock->sparity,
start, end - start);
}
}
static int scrub_find_csum(struct scrub_ctx *sctx, u64 logical, u8 *csum)
{
struct btrfs_ordered_sum *sum = NULL;
unsigned long index;
unsigned long num_sectors;
while (!list_empty(&sctx->csum_list)) {
sum = list_first_entry(&sctx->csum_list,
struct btrfs_ordered_sum, list);
if (sum->bytenr > logical)
return 0;
if (sum->bytenr + sum->len > logical)
break;
++sctx->stat.csum_discards;
list_del(&sum->list);
kfree(sum);
sum = NULL;
}
if (!sum)
return 0;
index = div_u64(logical - sum->bytenr, sctx->fs_info->sectorsize);
ASSERT(index < UINT_MAX);
num_sectors = sum->len / sctx->fs_info->sectorsize;
memcpy(csum, sum->sums + index, sctx->csum_size);
if (index == num_sectors - 1) {
list_del(&sum->list);
kfree(sum);
}
return 1;
}
/* scrub extent tries to collect up to 64 kB for each bio */
static int scrub_extent(struct scrub_ctx *sctx, struct map_lookup *map,
u64 logical, u64 len,
u64 physical, struct btrfs_device *dev, u64 flags,
u64 gen, int mirror_num, u64 physical_for_dev_replace)
{
int ret;
u8 csum[BTRFS_CSUM_SIZE];
u32 blocksize;
if (flags & BTRFS_EXTENT_FLAG_DATA) {
if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK)
blocksize = map->stripe_len;
else
blocksize = sctx->fs_info->sectorsize;
spin_lock(&sctx->stat_lock);
sctx->stat.data_extents_scrubbed++;
sctx->stat.data_bytes_scrubbed += len;
spin_unlock(&sctx->stat_lock);
} else if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK)
blocksize = map->stripe_len;
else
blocksize = sctx->fs_info->nodesize;
spin_lock(&sctx->stat_lock);
sctx->stat.tree_extents_scrubbed++;
sctx->stat.tree_bytes_scrubbed += len;
spin_unlock(&sctx->stat_lock);
} else {
blocksize = sctx->fs_info->sectorsize;
WARN_ON(1);
}
while (len) {
u64 l = min_t(u64, len, blocksize);
int have_csum = 0;
if (flags & BTRFS_EXTENT_FLAG_DATA) {
/* push csums to sbio */
have_csum = scrub_find_csum(sctx, logical, csum);
if (have_csum == 0)
++sctx->stat.no_csum;
}
ret = scrub_pages(sctx, logical, l, physical, dev, flags, gen,
mirror_num, have_csum ? csum : NULL, 0,
physical_for_dev_replace);
if (ret)
return ret;
len -= l;
logical += l;
physical += l;
physical_for_dev_replace += l;
}
return 0;
}
static int scrub_pages_for_parity(struct scrub_parity *sparity,
u64 logical, u64 len,
u64 physical, struct btrfs_device *dev,
u64 flags, u64 gen, int mirror_num, u8 *csum)
{
struct scrub_ctx *sctx = sparity->sctx;
struct scrub_block *sblock;
int index;
sblock = kzalloc(sizeof(*sblock), GFP_KERNEL);
if (!sblock) {
spin_lock(&sctx->stat_lock);
sctx->stat.malloc_errors++;
spin_unlock(&sctx->stat_lock);
return -ENOMEM;
}
/* one ref inside this function, plus one for each page added to
* a bio later on */
refcount_set(&sblock->refs, 1);
sblock->sctx = sctx;
sblock->no_io_error_seen = 1;
sblock->sparity = sparity;
scrub_parity_get(sparity);
for (index = 0; len > 0; index++) {
struct scrub_page *spage;
u64 l = min_t(u64, len, PAGE_SIZE);
spage = kzalloc(sizeof(*spage), GFP_KERNEL);
if (!spage) {
leave_nomem:
spin_lock(&sctx->stat_lock);
sctx->stat.malloc_errors++;
spin_unlock(&sctx->stat_lock);
scrub_block_put(sblock);
return -ENOMEM;
}
BUG_ON(index >= SCRUB_MAX_PAGES_PER_BLOCK);
/* For scrub block */
scrub_page_get(spage);
sblock->pagev[index] = spage;
/* For scrub parity */
scrub_page_get(spage);
list_add_tail(&spage->list, &sparity->spages);
spage->sblock = sblock;
spage->dev = dev;
spage->flags = flags;
spage->generation = gen;
spage->logical = logical;
spage->physical = physical;
spage->mirror_num = mirror_num;
if (csum) {
spage->have_csum = 1;
memcpy(spage->csum, csum, sctx->csum_size);
} else {
spage->have_csum = 0;
}
sblock->page_count++;
spage->page = alloc_page(GFP_KERNEL);
if (!spage->page)
goto leave_nomem;
len -= l;
logical += l;
physical += l;
}
WARN_ON(sblock->page_count == 0);
for (index = 0; index < sblock->page_count; index++) {
struct scrub_page *spage = sblock->pagev[index];
int ret;
ret = scrub_add_page_to_rd_bio(sctx, spage);
if (ret) {
scrub_block_put(sblock);
return ret;
}
}
/* last one frees, either here or in bio completion for last page */
scrub_block_put(sblock);
return 0;
}
static int scrub_extent_for_parity(struct scrub_parity *sparity,
u64 logical, u64 len,
u64 physical, struct btrfs_device *dev,
u64 flags, u64 gen, int mirror_num)
{
struct scrub_ctx *sctx = sparity->sctx;
int ret;
u8 csum[BTRFS_CSUM_SIZE];
u32 blocksize;
if (test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state)) {
scrub_parity_mark_sectors_error(sparity, logical, len);
return 0;
}
if (flags & BTRFS_EXTENT_FLAG_DATA) {
blocksize = sparity->stripe_len;
} else if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
blocksize = sparity->stripe_len;
} else {
blocksize = sctx->fs_info->sectorsize;
WARN_ON(1);
}
while (len) {
u64 l = min_t(u64, len, blocksize);
int have_csum = 0;
if (flags & BTRFS_EXTENT_FLAG_DATA) {
/* push csums to sbio */
have_csum = scrub_find_csum(sctx, logical, csum);
if (have_csum == 0)
goto skip;
}
ret = scrub_pages_for_parity(sparity, logical, l, physical, dev,
flags, gen, mirror_num,
have_csum ? csum : NULL);
if (ret)
return ret;
skip:
len -= l;
logical += l;
physical += l;
}
return 0;
}
/*
* Given a physical address, this will calculate it's
* logical offset. if this is a parity stripe, it will return
* the most left data stripe's logical offset.
*
* return 0 if it is a data stripe, 1 means parity stripe.
*/
static int get_raid56_logic_offset(u64 physical, int num,
struct map_lookup *map, u64 *offset,
u64 *stripe_start)
{
int i;
int j = 0;
u64 stripe_nr;
u64 last_offset;
u32 stripe_index;
u32 rot;
last_offset = (physical - map->stripes[num].physical) *
nr_data_stripes(map);
if (stripe_start)
*stripe_start = last_offset;
*offset = last_offset;
for (i = 0; i < nr_data_stripes(map); i++) {
*offset = last_offset + i * map->stripe_len;
stripe_nr = div64_u64(*offset, map->stripe_len);
stripe_nr = div_u64(stripe_nr, nr_data_stripes(map));
/* Work out the disk rotation on this stripe-set */
stripe_nr = div_u64_rem(stripe_nr, map->num_stripes, &rot);
/* calculate which stripe this data locates */
rot += i;
stripe_index = rot % map->num_stripes;
if (stripe_index == num)
return 0;
if (stripe_index < num)
j++;
}
*offset = last_offset + j * map->stripe_len;
return 1;
}
static void scrub_free_parity(struct scrub_parity *sparity)
{
struct scrub_ctx *sctx = sparity->sctx;
struct scrub_page *curr, *next;
int nbits;
nbits = bitmap_weight(sparity->ebitmap, sparity->nsectors);
if (nbits) {
spin_lock(&sctx->stat_lock);
sctx->stat.read_errors += nbits;
sctx->stat.uncorrectable_errors += nbits;
spin_unlock(&sctx->stat_lock);
}
list_for_each_entry_safe(curr, next, &sparity->spages, list) {
list_del_init(&curr->list);
scrub_page_put(curr);
}
kfree(sparity);
}
static void scrub_parity_bio_endio_worker(struct btrfs_work *work)
{
struct scrub_parity *sparity = container_of(work, struct scrub_parity,
work);
struct scrub_ctx *sctx = sparity->sctx;
scrub_free_parity(sparity);
scrub_pending_bio_dec(sctx);
}
static void scrub_parity_bio_endio(struct bio *bio)
{
struct scrub_parity *sparity = (struct scrub_parity *)bio->bi_private;
struct btrfs_fs_info *fs_info = sparity->sctx->fs_info;
if (bio->bi_status)
bitmap_or(sparity->ebitmap, sparity->ebitmap, sparity->dbitmap,
sparity->nsectors);
bio_put(bio);
btrfs_init_work(&sparity->work, btrfs_scrubparity_helper,
scrub_parity_bio_endio_worker, NULL, NULL);
btrfs_queue_work(fs_info->scrub_parity_workers, &sparity->work);
}
static void scrub_parity_check_and_repair(struct scrub_parity *sparity)
{
struct scrub_ctx *sctx = sparity->sctx;
struct btrfs_fs_info *fs_info = sctx->fs_info;
struct bio *bio;
struct btrfs_raid_bio *rbio;
struct btrfs_bio *bbio = NULL;
u64 length;
int ret;
if (!bitmap_andnot(sparity->dbitmap, sparity->dbitmap, sparity->ebitmap,
sparity->nsectors))
goto out;
length = sparity->logic_end - sparity->logic_start;
btrfs_bio_counter_inc_blocked(fs_info);
ret = btrfs_map_sblock(fs_info, BTRFS_MAP_WRITE, sparity->logic_start,
&length, &bbio);
if (ret || !bbio || !bbio->raid_map)
goto bbio_out;
bio = btrfs_io_bio_alloc(0);
bio->bi_iter.bi_sector = sparity->logic_start >> 9;
bio->bi_private = sparity;
bio->bi_end_io = scrub_parity_bio_endio;
rbio = raid56_parity_alloc_scrub_rbio(fs_info, bio, bbio,
length, sparity->scrub_dev,
sparity->dbitmap,
sparity->nsectors);
if