#include <linux/kernel.h>
#include <linux/sched/signal.h>
#include <linux/syscalls.h>
#include <linux/fs.h>
#include <linux/iomap.h>
#include <linux/mm.h>
#include <linux/percpu.h>
#include <linux/slab.h>
#include <linux/capability.h>
#include <linux/blkdev.h>
#include <linux/file.h>
#include <linux/quotaops.h>
#include <linux/highmem.h>
#include <linux/export.h>
#include <linux/backing-dev.h>
#include <linux/writeback.h>
#include <linux/hash.h>
#include <linux/suspend.h>
#include <linux/buffer_head.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/bio.h>
#include <linux/cpu.h>
#include <linux/bitops.h>
#include <linux/mpage.h>
#include <linux/bit_spinlock.h>
#include <linux/pagevec.h>
#include <linux/sched/mm.h>
#include <trace/events/block.h>
#include <linux/fscrypt.h>
#include "internal.h"
static int fsync_buffers_list(spinlock_t *lock, struct list_head *list);
static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh,
struct writeback_control *wbc);
#define BH_ENTRY(list) list_entry((list), struct buffer_head, b_assoc_buffers)
inline void touch_buffer(struct buffer_head *bh)
{
trace_block_touch_buffer(bh);
mark_page_accessed(bh->b_page);
}
EXPORT_SYMBOL(touch_buffer);
void __lock_buffer(struct buffer_head *bh)
{
wait_on_bit_lock_io(&bh->b_state, BH_Lock, TASK_UNINTERRUPTIBLE);
}
EXPORT_SYMBOL(__lock_buffer);
void unlock_buffer(struct buffer_head *bh)
{
clear_bit_unlock(BH_Lock, &bh->b_state);
smp_mb__after_atomic();
wake_up_bit(&bh->b_state, BH_Lock);
}
EXPORT_SYMBOL(unlock_buffer);
void buffer_check_dirty_writeback(struct folio *folio,
bool *dirty, bool *writeback)
{
struct buffer_head *head, *bh;
*dirty = false;
*writeback = false;
BUG_ON(!folio_test_locked(folio));
head = folio_buffers(folio);
if (!head)
return;
if (folio_test_writeback(folio))
*writeback = true;
bh = head;
do {
if (buffer_locked(bh))
*writeback = true;
if (buffer_dirty(bh))
*dirty = true;
bh = bh->b_this_page;
} while (bh != head);
}
EXPORT_SYMBOL(buffer_check_dirty_writeback);
void __wait_on_buffer(struct buffer_head * bh)
{
wait_on_bit_io(&bh->b_state, BH_Lock, TASK_UNINTERRUPTIBLE);
}
EXPORT_SYMBOL(__wait_on_buffer);
static void buffer_io_error(struct buffer_head *bh, char *msg)
{
if (!test_bit(BH_Quiet, &bh->b_state))
printk_ratelimited(KERN_ERR
"Buffer I/O error on dev %pg, logical block %llu%s\n",
bh->b_bdev, (unsigned long long)bh->b_blocknr, msg);
}
static void __end_buffer_read_notouch(struct buffer_head *bh, int uptodate)
{
if (uptodate) {
set_buffer_uptodate(bh);
} else {
clear_buffer_uptodate(bh);
}
unlock_buffer(bh);
}
void end_buffer_read_sync(struct buffer_head *bh, int uptodate)
{
__end_buffer_read_notouch(bh, uptodate);
put_bh(bh);
}
EXPORT_SYMBOL(end_buffer_read_sync);
void end_buffer_write_sync(struct buffer_head *bh, int uptodate)
{
if (uptodate) {
set_buffer_uptodate(bh);
} else {
buffer_io_error(bh, ", lost sync page write");
mark_buffer_write_io_error(bh);
clear_buffer_uptodate(bh);
}
unlock_buffer(bh);
put_bh(bh);
}
EXPORT_SYMBOL(end_buffer_write_sync);
static struct buffer_head *
__find_get_block_slow(struct block_device *bdev, sector_t block)
{
struct inode *bd_inode = bdev->bd_inode;
struct address_space *bd_mapping = bd_inode->i_mapping;
struct buffer_head *ret = NULL;
pgoff_t index;
struct buffer_head *bh;
struct buffer_head *head;
struct page *page;
int all_mapped = 1;
static DEFINE_RATELIMIT_STATE(last_warned, HZ, 1);
index = block >> (PAGE_SHIFT - bd_inode->i_blkbits);
page = find_get_page_flags(bd_mapping, index, FGP_ACCESSED);
if (!page)
goto out;
spin_lock(&bd_mapping->private_lock);
if (!page_has_buffers(page))
goto out_unlock;
head = page_buffers(page);
bh = head;
do {
if (!buffer_mapped(bh))
all_mapped = 0;
else if (bh->b_blocknr == block) {
ret = bh;
get_bh(bh);
goto out_unlock;
}
bh = bh->b_this_page;
} while (bh != head);
ratelimit_set_flags(&last_warned, RATELIMIT_MSG_ON_RELEASE);
if (all_mapped && __ratelimit(&last_warned)) {
printk("__find_get_block_slow() failed. block=%llu, "
"b_blocknr=%llu, b_state=0x%08lx, b_size=%zu, "
"device %pg blocksize: %d\n",
(unsigned long long)block,
(unsigned long long)bh->b_blocknr,
bh->b_state, bh->b_size, bdev,
1 << bd_inode->i_blkbits);
}
out_unlock:
spin_unlock(&bd_mapping->private_lock);
put_page(page);
out:
return ret;
}
static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
{
unsigned long flags;
struct buffer_head *first;
struct buffer_head *tmp;
struct page *page;
int page_uptodate = 1;
BUG_ON(!buffer_async_read(bh));
page = bh->b_page;
if (uptodate) {
set_buffer_uptodate(bh);
} else {
clear_buffer_uptodate(bh);
buffer_io_error(bh, ", async page read");
SetPageError(page);
}
first = page_buffers(page);
spin_lock_irqsave(&first->b_uptodate_lock, flags);
clear_buffer_async_read(bh);
unlock_buffer(bh);
tmp = bh;
do {
if (!buffer_uptodate(tmp))
page_uptodate = 0;
if (buffer_async_read(tmp)) {
BUG_ON(!buffer_locked(tmp));
goto still_busy;
}
tmp = tmp->b_this_page;
} while (tmp != bh);
spin_unlock_irqrestore(&first->b_uptodate_lock, flags);
if (page_uptodate && !PageError(page))
SetPageUptodate(page);
unlock_page(page);
return;
still_busy:
spin_unlock_irqrestore(&first->b_uptodate_lock, flags);
return;
}
struct decrypt_bh_ctx {
struct work_struct work;
struct buffer_head *bh;
};
static void decrypt_bh(struct work_struct *work)
{
struct decrypt_bh_ctx *ctx =
container_of(work, struct decrypt_bh_ctx, work);
struct buffer_head *bh = ctx->bh;
int err;
err = fscrypt_decrypt_pagecache_blocks(bh->b_page, bh->b_size,
bh_offset(bh));
end_buffer_async_read(bh, err == 0);
kfree(ctx);
}
static void end_buffer_async_read_io(struct buffer_head *bh, int uptodate)
{
if (uptodate &&
fscrypt_inode_uses_fs_layer_crypto(bh->b_page->mapping->host)) {
struct decrypt_bh_ctx *ctx = kmalloc(sizeof(*ctx), GFP_ATOMIC);
if (ctx) {
INIT_WORK(&ctx->work, decrypt_bh);
ctx->bh = bh;
fscrypt_enqueue_decrypt_work(&ctx->work);
return;
}
uptodate = 0;
}
end_buffer_async_read(bh, uptodate);
}
void end_buffer_async_write(struct buffer_head *bh, int uptodate)
{
unsigned long flags;
struct buffer_head *first;
struct buffer_head *tmp;
struct page *page;
BUG_ON(!buffer_async_write(bh));
page = bh->b_page;
if (uptodate) {
set_buffer_uptodate(bh);
} else {
buffer_io_error(bh, ", lost async page write");
mark_buffer_write_io_error(bh);
clear_buffer_uptodate(bh);
SetPageError(page);
}
first = page_buffers(page);
spin_lock_irqsave(&first->b_uptodate_lock, flags);
clear_buffer_async_write(bh);
unlock_buffer(bh);
tmp = bh->b_this_page;
while (tmp != bh) {
if (buffer_async_write(tmp)) {
BUG_ON(!buffer_locked(tmp));
goto still_busy;
}
tmp = tmp->b_this_page;
}
spin_unlock_irqrestore(&first->b_uptodate_lock, flags);
end_page_writeback(page);
return;
still_busy:
spin_unlock_irqrestore(&first->b_uptodate_lock, flags);
return;
}
EXPORT_SYMBOL(end_buffer_async_write);
static void mark_buffer_async_read(struct buffer_head *bh)
{
bh->b_end_io = end_buffer_async_read_io;
set_buffer_async_read(bh);
}
static void mark_buffer_async_write_endio(struct buffer_head *bh,
bh_end_io_t *handler)
{
bh->b_end_io = handler;
set_buffer_async_write(bh);
}
void mark_buffer_async_write(struct buffer_head *bh)
{
mark_buffer_async_write_endio(bh, end_buffer_async_write);
}
EXPORT_SYMBOL(mark_buffer_async_write);
static void __remove_assoc_queue(struct buffer_head *bh)
{
list_del_init(&bh->b_assoc_buffers);
WARN_ON(!bh->b_assoc_map);
bh->b_assoc_map = NULL;
}
int inode_has_buffers(struct inode *inode)
{
return !list_empty(&inode->i_data.private_list);
}
static int osync_buffers_list(spinlock_t *lock, struct list_head *list)
{
struct buffer_head *bh;
struct list_head *p;
int err = 0;
spin_lock(lock);
repeat:
list_for_each_prev(p, list) {
bh = BH_ENTRY(p);
if (buffer_locked(bh)) {
get_bh(bh);
spin_unlock(lock);
wait_on_buffer(bh);
if (!buffer_uptodate(bh))
err = -EIO;
brelse(bh);
spin_lock(lock);
goto repeat;
}
}
spin_unlock(lock);
return err;
}
void emergency_thaw_bdev(struct super_block *sb)
{
while (sb->s_bdev && !thaw_bdev(sb->s_bdev))
printk(KERN_WARNING "Emergency Thaw on %pg\n", sb->s_bdev);
}
int sync_mapping_buffers(struct address_space *mapping)
{
struct address_space *buffer_mapping = mapping->private_data;
if (buffer_mapping == NULL || list_empty(&mapping->private_list))
return 0;
return fsync_buffers_list(&buffer_mapping->private_lock,
&mapping->private_list);
}
EXPORT_SYMBOL(sync_mapping_buffers);
void write_boundary_block(struct block_device *bdev,
sector_t bblock, unsigned blocksize)
{
struct buffer_head *bh = __find_get_block(bdev, bblock + 1, blocksize);
if (bh) {
if (buffer_dirty(bh))
ll_rw_block(REQ_OP_WRITE, 0, 1, &bh);
put_bh(bh);
}
}
void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode)
{
struct address_space *mapping = inode->i_mapping;
struct address_space *buffer_mapping = bh->b_page->mapping;
mark_buffer_dirty(bh);
if (!mapping->private_data) {
mapping->private_data = buffer_mapping;
} else {
BUG_ON(mapping->private_data != buffer_mapping);
}
if (!bh->b_assoc_map) {
spin_lock(&buffer_mapping->private_lock);
list_move_tail(&bh->b_assoc_buffers,
&mapping->private_list);
bh->b_assoc_map = mapping;
spin_unlock(&buffer_mapping->private_lock);
}
}
EXPORT_SYMBOL(mark_buffer_dirty_inode);
bool block_dirty_folio(struct address_space *mapping, struct folio *folio)
{
struct buffer_head *head;
bool newly_dirty;
spin_lock(&mapping->private_lock);
head = folio_buffers(folio);
if (head) {
struct buffer_head *bh = head;
do {
set_buffer_dirty(bh);
bh = bh->b_this_page;
} while (bh != head);
}
folio_memcg_lock(folio);
newly_dirty = !folio_test_set_dirty(folio);
spin_unlock(&mapping->private_lock);
if (newly_dirty)
__folio_mark_dirty(folio, mapping, 1);
folio_memcg_unlock(folio);
if (newly_dirty)
__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
return newly_dirty;
}
EXPORT_SYMBOL(block_dirty_folio);
static int fsync_buffers_list(spinlock_t *lock, struct list_head *list)
{
struct buffer_head *bh;
struct list_head tmp;
struct address_space *mapping;
int err = 0, err2;
struct blk_plug plug;
INIT_LIST_HEAD(&tmp);
blk_start_plug(&plug);
spin_lock(lock);
while (!list_empty(list)) {
bh = BH_ENTRY(list->next);
mapping = bh->b_assoc_map;
__remove_assoc_queue(bh);
smp_mb();
if (buffer_dirty(bh) || buffer_locked(bh)) {
list_add(&bh->b_assoc_buffers, &tmp);
bh->b_assoc_map = mapping;
if (buffer_dirty(bh)) {
get_bh(bh);
spin_unlock(lock);
write_dirty_buffer(bh, REQ_SYNC);
brelse(bh);
spin_lock(lock);
}
}
}
spin_unlock(lock);
blk_finish_plug(&plug);
spin_lock(lock);
while (!list_empty(&tmp)) {
bh = BH_ENTRY(tmp.prev);
get_bh(bh);
mapping = bh->b_assoc_map;
__remove_assoc_queue(bh);
smp_mb();
if (buffer_dirty(bh)) {
list_add(&bh->b_assoc_buffers,
&mapping->private_list);
bh->b_assoc_map = mapping;
}
spin_unlock(lock);
wait_on_buffer(bh);
if (!buffer_uptodate(bh))
err = -EIO;
brelse(bh);
spin_lock(lock);
}
spin_unlock(lock);
err2 = osync_buffers_list(lock, list);
if (err)
return err;
else
return err2;
}
void invalidate_inode_buffers(struct inode *inode)
{
if (inode_has_buffers(inode)) {
struct address_space *mapping = &inode->i_data;
struct list_head *list = &mapping->private_list;
struct address_space *buffer_mapping = mapping->private_data;
spin_lock(&buffer_mapping->private_lock);
while (!list_empty(list))
__remove_assoc_queue(BH_ENTRY(list->next));
spin_unlock(&buffer_mapping->private_lock);
}
}
EXPORT_SYMBOL(invalidate_inode_buffers);
int remove_inode_buffers(struct inode *inode)
{
int ret = 1;
if (inode_has_buffers(inode)) {
struct address_space *mapping = &inode->i_data;
struct list_head *list = &mapping->private_list;
struct address_space *buffer_mapping = mapping->private_data;
spin_lock(&buffer_mapping->private_lock);
while (!list_empty(list)) {
struct buffer_head *bh = BH_ENTRY(list->next);
if (buffer_dirty(bh)) {
ret = 0;
break;
}
__remove_assoc_queue(bh);
}
spin_unlock(&buffer_mapping->private_lock);
}
return ret;
}
struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size,
bool retry)
{
struct buffer_head *bh, *head;
gfp_t gfp = GFP_NOFS | __GFP_ACCOUNT;
long offset;
struct mem_cgroup *memcg, *old_memcg;
if (retry)
gfp |= __GFP_NOFAIL;
memcg = page_memcg(page);
old_memcg = set_active_memcg(memcg);
head = NULL;
offset = PAGE_SIZE;
while ((offset -= size) >= 0) {
bh = alloc_buffer_head(gfp);
if (!bh)
goto no_grow;
bh->b_this_page = head;
bh->b_blocknr = -1;
head = bh;
bh->b_size = size;
set_bh_page(bh, page, offset);
}
out:
set_active_memcg(old_memcg);
return head;
no_grow:
if (head) {
do {
bh = head;
head = head->b_this_page;
free_buffer_head(bh);
} while (head);
}
goto out;
}
EXPORT_SYMBOL_GPL(alloc_page_buffers);
static inline void
link_dev_buffers(struct page *page, struct buffer_head *head)
{
struct buffer_head *bh, *tail;
bh = head;
do {
tail = bh;
bh = bh->b_this_page;
} while (bh);
tail->b_this_page = head;
attach_page_private(page, head);
}
static sector_t blkdev_max_block(struct block_device *bdev, unsigned int size)
{
sector_t retval = ~((sector_t)0);
loff_t sz = bdev_nr_bytes(bdev);
if (sz) {
unsigned int sizebits = blksize_bits(size);
retval = (sz >> sizebits);
}
return retval;
}
static sector_t
init_page_buffers(struct page *page, struct block_device *bdev,
sector_t block, int size)
{
struct buffer_head *head = page_buffers(page);
struct buffer_head *bh = head;
int uptodate = PageUptodate(page);
sector_t end_block = blkdev_max_block(bdev, size);
do {
if (!buffer_mapped(bh)) {
bh->b_end_io = NULL;
bh->b_private = NULL;
bh->b_bdev = bdev;
bh->b_blocknr = block;
if (uptodate)
set_buffer_uptodate(bh);
if (block < end_block)
set_buffer_mapped(bh);
}
block++;
bh = bh->b_this_page;
} while (bh != head);
return end_block;
}
static int
grow_dev_page(struct block_device *bdev, sector_t block,
pgoff_t index, int size, int sizebits, gfp_t gfp)
{
struct inode *inode = bdev->bd_inode;
struct page *page;
struct buffer_head *bh;
sector_t end_block;
int ret = 0;
gfp_t gfp_mask;
gfp_mask = mapping_gfp_constraint(inode->i_mapping, ~__GFP_FS) | gfp;
gfp_mask |= __GFP_NOFAIL;
page = find_or_create_page(inode->i_mapping, index, gfp_mask);
BUG_ON(!PageLocked(page));
if (page_has_buffers(page)) {
bh = page_buffers(page);
if (bh->b_size == size) {
end_block = init_page_buffers(page, bdev,
(sector_t)index << sizebits,
size);
goto done;
}
if (!try_to_free_buffers(page_folio(page)))
goto failed;
}
bh = alloc_page_buffers(page, size, true);
spin_lock(&inode->i_mapping->private_lock);
link_dev_buffers(page, bh);
end_block = init_page_buffers(page, bdev, (sector_t)index << sizebits,
size);
spin_unlock(&inode->i_mapping->private_lock);
done:
ret = (block < end_block) ? 1 : -ENXIO;
failed:
unlock_page(page);
put_page(page);
return ret;
}
static int
grow_buffers(struct block_device *bdev, sector_t block, int size, gfp_t gfp)
{
pgoff_t index;
int sizebits;
sizebits = PAGE_SHIFT - __ffs(size);
index = block >> sizebits;
if (unlikely(index != block >> sizebits)) {
printk(KERN_ERR "%s: requested out-of-range block %llu for "
"device %pg\n",
__func__, (unsigned long long)block,
bdev);
return -EIO;
}
return grow_dev_page(bdev, block, index, size, sizebits, gfp);
}
static struct buffer_head *
__getblk_slow(struct block_device *bdev, sector_t block,
unsigned size, gfp_t gfp)
{
if (unlikely(size & (bdev_logical_block_size(bdev)-1) ||
(size < 512 || size > PAGE_SIZE))) {
printk(KERN_ERR "getblk(): invalid block size %d requested\n",
size);
printk(KERN_ERR "logical block size: %d\n",
bdev_logical_block_size(bdev));
dump_stack();
return NULL;
}
for (;;) {
struct buffer_head *bh;
int ret;
bh = __find_get_block(bdev, block, size);
if (bh)
return bh;
ret = grow_buffers(bdev, block, size, gfp);
if (ret < 0)
return NULL;
}
}
void mark_buffer_dirty(struct buffer_head *bh)
{
WARN_ON_ONCE(!buffer_uptodate(bh));
trace_block_dirty_buffer(bh);
if (buffer_dirty(bh)) {
smp_mb();
if (buffer_dirty(bh))
return;
}
if (!test_set_buffer_dirty(bh)) {
struct page *page = bh->b_page;
struct address_space *mapping = NULL;
lock_page_memcg(page);
if (!TestSetPageDirty(page)) {
mapping = page_mapping(page);
if (mapping)
__set_page_dirty(page, mapping, 0);
}
unlock_page_memcg(page);
if (mapping)
__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
}
}
EXPORT_SYMBOL(mark_buffer_dirty);
void mark_buffer_write_io_error(struct buffer_head *bh)
{
struct super_block *sb;
set_buffer_write_io_error(bh);
if (bh->b_page && bh->b_page->mapping)
mapping_set_error(bh->b_page->mapping, -EIO);
if (bh->b_assoc_map)
mapping_set_error(bh->b_assoc_map, -EIO);
rcu_read_lock();
sb = READ_ONCE(bh->b_bdev->bd_super);
if (sb)
errseq_set(&sb->s_wb_err, -EIO);
rcu_read_unlock();
}
EXPORT_SYMBOL(mark_buffer_write_io_error);
void __brelse(struct buffer_head * buf)
{
if (atomic_read(&buf->b_count)) {
put_bh(buf);
return;
}
WARN(1, KERN_ERR "VFS: brelse: Trying to free free buffer\n");
}
EXPORT_SYMBOL(__brelse);
void __bforget(struct buffer_head *bh)
{
clear_buffer_dirty(bh);
if (bh->b_assoc_map) {
struct address_space *buffer_mapping = bh->b_page->mapping;
spin_lock(&buffer_mapping->private_lock);
list_del_init(&bh->b_assoc_buffers);
bh->b_assoc_map = NULL;
spin_unlock(&buffer_mapping->private_lock);
}
__brelse(bh);
}
EXPORT_SYMBOL(__bforget);
static struct buffer_head *__bread_slow(struct buffer_head *bh)
{
lock_buffer(bh);
if (buffer_uptodate(bh)) {
unlock_buffer(bh);
return bh;
} else {
get_bh(bh);
bh->b_end_io = end_buffer_read_sync;
submit_bh(REQ_OP_READ, 0, bh);
wait_on_buffer(bh);
if (buffer_uptodate(bh))
return bh;
}
brelse(bh);
return NULL;
}
#define BH_LRU_SIZE 16
struct bh_lru {
struct buffer_head *bhs[BH_LRU_SIZE];
};
static DEFINE_PER_CPU(struct bh_lru, bh_lrus) = {{ NULL }};
#ifdef CONFIG_SMP
#define bh_lru_lock() local_irq_disable()
#define bh_lru_unlock() local_irq_enable()
#else
#define bh_lru_lock() preempt_disable()
#define bh_lru_unlock() preempt_enable()
#endif
static inline void check_irqs_on(void)
{
#ifdef irqs_disabled
BUG_ON(irqs_disabled());
#endif
}
static void bh_lru_install(struct buffer_head *bh)
{
struct buffer_head *evictee = bh;
struct bh_lru *b;
int i;
check_irqs_on();
bh_lru_lock();
if (lru_cache_disabled()) {
bh_lru_unlock();
return;
}
b = this_cpu_ptr(&bh_lrus);
for (i = 0; i < BH_LRU_SIZE; i++) {
swap(evictee, b->bhs[i]);
if (evictee == bh) {
bh_lru_unlock();
return;
}
}
get_bh(bh);
bh_lru_unlock();
brelse(evictee);
}
static struct buffer_head *
lookup_bh_lru(struct block_device *bdev, sector_t block, unsigned size)
{
struct buffer_head *ret = NULL;
unsigned int i;
check_irqs_on();
bh_lru_lock();
for (i = 0; i < BH_LRU_SIZE; i++) {
struct buffer_head *bh = __this_cpu_read(bh_lrus.bhs[i]);
if (bh && bh->b_blocknr == block && bh->b_bdev == bdev &&
bh->b_size == size) {
if (i) {
while (i) {
__this_cpu_write(bh_lrus.bhs[i],
__this_cpu_read(bh_lrus.bhs[i - 1]));
i--;
}
__this_cpu_write(bh_lrus.bhs[0], bh);
}
get_bh(bh);
ret = bh;
break;
}
}
bh_lru_unlock();
return ret;
}
struct buffer_head *
__find_get_block(struct block_device *bdev, sector_t block, unsigned size)
{
struct buffer_head *bh = lookup_bh_lru(bdev, block, size);
if (bh == NULL) {
bh = __find_get_block_slow(bdev, block);
if (bh)
bh_lru_install(bh);
} else
touch_buffer(bh);
return bh;
}
EXPORT_SYMBOL(__find_get_block);
struct buffer_head *
__getblk_gfp(struct block_device *bdev, sector_t block,
unsigned size, gfp_t gfp)
{
struct buffer_head *bh = __find_get_block(bdev, block, size);
might_sleep();
if (bh == NULL)
bh = __getblk_slow(bdev, block, size, gfp);
return bh;
}
EXPORT_SYMBOL(__getblk_gfp);
void __breadahead(struct block_device *bdev, sector_t block, unsigned size)
{
struct buffer_head *bh = __getblk(bdev, block, size);
if (likely(bh)) {
ll_rw_block(REQ_OP_READ, REQ_RAHEAD, 1, &bh);
brelse(bh);
}
}
EXPORT_SYMBOL(__breadahead);
void __breadahead_gfp(struct block_device *bdev, sector_t block, unsigned size,
gfp_t gfp)
{
struct buffer_head *bh = __getblk_gfp(bdev, block, size, gfp);
if (likely(bh)) {
ll_rw_block(REQ_OP_READ, REQ_RAHEAD, 1, &bh);
brelse(bh);
}
}
EXPORT_SYMBOL(__breadahead_gfp);
struct buffer_head *
__bread_gfp(struct block_device *bdev, sector_t block,
unsigned size, gfp_t gfp)
{
struct buffer_head *bh = __getblk_gfp(bdev, block, size, gfp);
if (likely(bh) && !buffer_uptodate(bh))
bh = __bread_slow(bh);
return bh;
}
EXPORT_SYMBOL(__bread_gfp);
static void __invalidate_bh_lrus(struct bh_lru *b)
{
int i;
for (i = 0; i < BH_LRU_SIZE; i++) {
brelse(b->bhs[i]);
b->bhs[i] = NULL;
}
}
static void invalidate_bh_lru(void *arg)
{
struct bh_lru *b = &get_cpu_var(bh_lrus);
__invalidate_bh_lrus(b);
put_cpu_var(bh_lrus);
}
bool has_bh_in_lru(int cpu, void *dummy)
{
struct bh_lru *b = per_cpu_ptr(&bh_lrus, cpu);
int i;
for (i = 0; i < BH_LRU_SIZE; i++) {
if (b->bhs[i])
return true;
}
return false;
}
void invalidate_bh_lrus(void)
{
on_each_cpu_cond(has_bh_in_lru, invalidate_bh_lru, NULL, 1);
}
EXPORT_SYMBOL_GPL(invalidate_bh_lrus);
void invalidate_bh_lrus_cpu(void)
{
struct bh_lru *b;
bh_lru_lock();
b = this_cpu_ptr(&bh_lrus);
__invalidate_bh_lrus(b);
bh_lru_unlock();
}
void set_bh_page(struct buffer_head *bh,
struct page *page, unsigned long offset)
{
bh->b_page = page;
BUG_ON(offset >= PAGE_SIZE);
if (PageHighMem(page))
bh->b_data = (char *)(0 + offset);
else
bh->b_data = page_address(page) + offset;
}
EXPORT_SYMBOL(set_bh_page);
#define BUFFER_FLAGS_DISCARD \
(1 << BH_Mapped | 1 << BH_New | 1 << BH_Req | \
1 << BH_Delay | 1 << BH_Unwritten)
static void discard_buffer(struct buffer_head * bh)
{
unsigned long b_state, b_state_old;
lock_buffer(bh);
clear_buffer_dirty(bh);
bh->b_bdev = NULL;
b_state = bh->b_state;
for (;;) {
b_state_old = cmpxchg(&bh->b_state, b_state,
(b_state & ~BUFFER_FLAGS_DISCARD));
if (b_state_old == b_state)
break;
b_state = b_state_old;
}
unlock_buffer(bh);
}
void block_invalidate_folio(struct folio *folio, size_t offset, size_t length)
{
struct buffer_head *head, *bh, *next;
size_t curr_off = 0;
size_t stop = length + offset;
BUG_ON(!folio_test_locked(folio));
BUG_ON(stop > folio_size(folio) || stop < length);
head = folio_buffers(folio);
if (!head)
return;
bh = head;
do {
size_t next_off = curr_off + bh->b_size;
next = bh->b_this_page;
if (next_off > stop)
goto out;
if (offset <= curr_off)
discard_buffer(bh);
curr_off = next_off;
bh = next;
} while (bh != head);
if (length == folio_size(folio))
filemap_release_folio(folio, 0);
out:
return;
}
EXPORT_SYMBOL(block_invalidate_folio);
void create_empty_buffers(struct page *page,
unsigned long blocksize, unsigned long b_state)
{
struct buffer_head *bh, *head, *tail;
head = alloc_page_buffers(page, blocksize, true);
bh = head;
do {
bh->b_state |= b_state;
tail = bh;
bh = bh->b_this_page;
} while (bh);
tail->b_this_page = head;
spin_lock(&page->mapping->private_lock);
if (PageUptodate(page) || PageDirty(page)) {
bh = head;
do {
if (PageDirty(page))
set_buffer_dirty(bh);
if (PageUptodate(page))
set_buffer_uptodate(bh);
bh = bh->b_this_page;
} while (bh != head);
}
attach_page_private(page, head);
spin_unlock(&page->mapping->private_lock);
}
EXPORT_SYMBOL(create_empty_buffers);
void clean_bdev_aliases(struct block_device *bdev, sector_t block, sector_t len)
{
struct inode *bd_inode = bdev->bd_inode;
struct address_space *bd_mapping = bd_inode->i_mapping;
struct pagevec pvec;
pgoff_t index = block >> (PAGE_SHIFT - bd_inode->i_blkbits);
pgoff_t end;
int i, count;
struct buffer_head *bh;
struct buffer_head *head;
end = (block + len - 1) >> (PAGE_SHIFT - bd_inode->i_blkbits);
pagevec_init(&pvec);
while (pagevec_lookup_range(&pvec, bd_mapping, &index, end)) {
count = pagevec_count(&pvec);
for (i = 0; i < count; i++) {
struct page *page = pvec.pages[i];
if (!page_has_buffers(page))
continue;
lock_page(page);
if (!page_has_buffers(page))
goto unlock_page;
head = page_buffers(page);
bh = head;
do {
if (!buffer_mapped(bh) || (bh->b_blocknr < block))
goto next;
if (bh->b_blocknr >= block + len)
break;
clear_buffer_dirty(bh);
wait_on_buffer(bh);
clear_buffer_req(bh);
next:
bh = bh->b_this_page;
} while (bh != head);
unlock_page:
unlock_page(page);
}
pagevec_release(&pvec);
cond_resched();
if (index > end || !index)
break;
}
}
EXPORT_SYMBOL(clean_bdev_aliases);
static inline int block_size_bits(unsigned int blocksize)
{
return ilog2(blocksize);
}
static struct buffer_head *create_page_buffers(struct page *page, struct inode *inode, unsigned int b_state)
{
BUG_ON(!PageLocked(page));
if (!page_has_buffers(page))
create_empty_buffers(page, 1 << READ_ONCE(inode->i_blkbits),
b_state);
return page_buffers(page);
}
int __block_write_full_page(struct inode *inode, struct page *page,
get_block_t *get_block, struct writeback_control *wbc,
bh_end_io_t *handler)
{
int err;
sector_t block;
sector_t last_block;
struct buffer_head *bh, *head;
unsigned int blocksize, bbits;
int nr_underway = 0;
int write_flags = wbc_to_write_flags(wbc);
head = create_page_buffers(page, inode,
(1 << BH_Dirty)|(1 << BH_Uptodate));
bh = head;
blocksize = bh->b_size;
bbits = block_size_bits(blocksize);
block = (sector_t)page->index << (PAGE_SHIFT - bbits);
last_block = (i_size_read(inode) - 1) >> bbits;
do {
if (block > last_block) {
clear_buffer_dirty(bh);
set_buffer_uptodate(bh);
} else if ((!buffer_mapped(bh) || buffer_delay(bh)) &&
buffer_dirty(bh)) {
WARN_ON(bh->b_size != blocksize);
err = get_block(inode, block, bh, 1);
if (err)
goto recover;
clear_buffer_delay(bh);
if (buffer_new(bh)) {
clear_buffer_new(bh);
clean_bdev_bh_alias(bh);
}
}
bh = bh->b_this_page;
block++;
} while (bh != head);
do {
if (!buffer_mapped(bh))
continue;
if (wbc->sync_mode != WB_SYNC_NONE) {
lock_buffer(bh);
} else if (!trylock_buffer(bh)) {
redirty_page_for_writepage(wbc, page);
continue;
}
if (test_clear_buffer_dirty(bh)) {
mark_buffer_async_write_endio(bh, handler);
} else {
unlock_buffer(bh);
}
} while ((bh = bh->b_this_page) != head);
BUG_ON(PageWriteback(page));
set_page_writeback(page);
do {
struct buffer_head *next = bh->b_this_page;
if (buffer_async_write(bh)) {
submit_bh_wbc(REQ_OP_WRITE, write_flags, bh, wbc);
nr_underway++;
}
bh = next;
} while (bh != head);
unlock_page(page);
err = 0;
done:
if (nr_underway == 0) {
end_page_writeback(page);
}
return err;
recover:
bh = head;
do {
if (buffer_mapped(bh) && buffer_dirty(bh) &&
!buffer_delay(bh)) {
lock_buffer(bh);
mark_buffer_async_write_endio(bh, handler);
} else {
clear_buffer_dirty(bh);
}
} while ((bh = bh->b_this_page) != head);
SetPageError(page);
BUG_ON(PageWriteback(page));
mapping_set_error(page->mapping, err);
set_page_writeback(page);
do {
struct buffer_head *next = bh->b_this_page;
if (buffer_async_write(bh)) {
clear_buffer_dirty(bh);
submit_bh_wbc(REQ_OP_WRITE, write_flags, bh, wbc);
nr_underway++;
}
bh = next;
} while (bh != head);
unlock_page(page);
goto done;
}
EXPORT_SYMBOL(__block_write_full_page);
void page_zero_new_buffers(struct page *page, unsigned from, unsigned to)
{
unsigned int block_start, block_end;
struct buffer_head *head, *bh;
BUG_ON(!PageLocked(page));
if (!page_has_buffers(page))
return;
bh = head = page_buffers(page);
block_start = 0;
do {
block_end = block_start + bh->b_size;
if (buffer_new(bh)) {
if (block_end > from && block_start < to) {
if (!PageUptodate(page)) {
unsigned start, size;
start = max(from, block_start);
size = min(to, block_end) - start;
zero_user(page, start, size);
set_buffer_uptodate(bh);
}
clear_buffer_new(bh);
mark_buffer_dirty(bh);
}
}
block_start = block_end;
bh = bh->b_this_page;
} while (bh != head);
}
EXPORT_SYMBOL(page_zero_new_buffers);
static void
iomap_to_bh(struct inode *inode, sector_t block, struct buffer_head *bh,
const struct iomap *iomap)
{
loff_t offset = block << inode->i_blkbits;
bh->b_bdev = iomap->bdev;
BUG_ON(offset >= iomap->offset + iomap->length);
switch (iomap->type) {
case IOMAP_HOLE:
if (!buffer_uptodate(bh) ||
(offset >= i_size_read(inode)))
set_buffer_new(bh);
break;
case IOMAP_DELALLOC:
if (!buffer_uptodate(bh) ||
(offset >= i_size_read(inode)))
set_buffer_new(bh);
set_buffer_uptodate(bh);
set_buffer_mapped(bh);
set_buffer_delay(bh);
break;
case IOMAP_UNWRITTEN:
set_buffer_new(bh);
set_buffer_unwritten(bh);
fallthrough;
case IOMAP_MAPPED:
if ((iomap->flags & IOMAP_F_NEW) ||
offset >= i_size_read(inode))
set_buffer_new(bh);
bh->b_blocknr = (iomap->addr + offset - iomap->offset) >>
inode->i_blkbits;
set_buffer_mapped(bh);
break;
}
}
int __block_write_begin_int(struct folio *folio, loff_t pos, unsigned len,
get_block_t *get_block, const struct iomap *iomap)
{
unsigned from = pos & (PAGE_SIZE - 1);
unsigned to = from + len;
struct inode *inode = folio->mapping->host;
unsigned block_start, block_end;
sector_t block;
int err = 0;
unsigned blocksize, bbits;
struct buffer_head *bh, *head, *wait[2], **wait_bh=wait;
BUG_ON(!folio_test_locked(folio));
BUG_ON(from > PAGE_SIZE);
BUG_ON(to > PAGE_SIZE);
BUG_ON(from > to);
head = create_page_buffers(&folio->page, inode, 0);
blocksize = head->b_size;
bbits = block_size_bits(blocksize);
block = (sector_t)folio->index << (PAGE_SHIFT - bbits);
for(bh = head, block_start = 0; bh != head || !block_start;
block++, block_start=block_end, bh = bh->b_this_page) {
block_end = block_start + blocksize;
if (block_end <= from || block_start >= to) {
if (folio_test_uptodate(folio)) {
if (!buffer_uptodate(bh))
set_buffer_uptodate(bh);
}
continue;
}
if (buffer_new(bh))
clear_buffer_new(bh);
if (!buffer_mapped(bh)) {
WARN_ON(bh->b_size != blocksize);
if (get_block) {
err = get_block(inode, block, bh, 1);
if (err)
break;
} else {
iomap_to_bh(inode, block, bh, iomap);
}
if (buffer_new(bh)) {
clean_bdev_bh_alias(bh);
if (folio_test_uptodate(folio)) {
clear_buffer_new(bh);
set_buffer_uptodate(bh);
mark_buffer_dirty(bh);
continue;
}
if (block_end > to || block_start < from)
folio_zero_segments(folio,
to, block_end,
block_start, from);
continue;
}
}
if (folio_test_uptodate(folio)) {
if (!buffer_uptodate(bh))
set_buffer_uptodate(bh);
continue;
}
if (!buffer_uptodate(bh) && !buffer_delay(bh) &&
!buffer_unwritten(bh) &&
(block_start < from || block_end > to)) {
ll_rw_block(REQ_OP_READ, 0, 1, &bh);
*wait_bh++=bh;
}
}
while(wait_bh > wait) {
wait_on_buffer(*--wait_bh);
if (!buffer_uptodate(*wait_bh))
err = -EIO;
}
if (unlikely(err))
page_zero_new_buffers(&folio->page, from, to);
return err;
}
int __block_write_begin(struct page *page, loff_t pos, unsigned len,
get_block_t *get_block)
{
return __block_write_begin_int(page_folio(page), pos, len, get_block,
NULL);
}
EXPORT_SYMBOL(__block_write_begin);
static int __block_commit_write(struct inode *inode, struct page *page,
unsigned from, unsigned to)
{
unsigned block_start, block_end;
int partial = 0;
unsigned blocksize;
struct buffer_head *bh, *head;
bh = head = page_buffers(page);
blocksize = bh->b_size;
block_start = 0;
do {
block_end = block_start + blocksize;
if (block_end <= from || block_start >= to) {
if (!buffer_uptodate(bh))
partial = 1;
} else {
set_buffer_uptodate(bh);
mark_buffer_dirty(bh);
}
if (buffer_new(bh))
clear_buffer_new(bh);
block_start = block_end;
bh = bh->b_this_page;
} while (bh != head);
if (!partial)
SetPageUptodate(page);
return 0;
}
int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
struct page **pagep, get_block_t *get_block)
{
pgoff_t index = pos >> PAGE_SHIFT;
struct page *page;
int status;
page = grab_cache_page_write_begin(mapping, index);
if (!page)
return -ENOMEM;
status = __block_write_begin(page, pos, len, get_block);
if (unlikely(status)) {
unlock_page(page);
put_page(page);
page = NULL;
}
*pagep = page;
return status;
}
EXPORT_SYMBOL(block_write_begin);
int block_write_end(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata)
{
struct inode *inode = mapping->host;
unsigned start;
start = pos & (PAGE_SIZE - 1);
if (unlikely(copied < len)) {
if (!PageUptodate(page))
copied = 0;
page_zero_new_buffers(page, start+copied, start+len);
}
flush_dcache_page(page);
__block_commit_write(inode, page, start, start+copied);
return copied;
}
EXPORT_SYMBOL(block_write_end);
int generic_write_end(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata)
{
struct inode *inode = mapping->host;
loff_t old_size = inode->i_size;
bool i_size_changed = false;
copied = block_write_end(file, mapping, pos, len, copied, page, fsdata);
if (pos + copied > inode->i_size) {
i_size_write(inode, pos + copied);
i_size_changed = true;
}
unlock_page(page);
put_page(page);
if (old_size < pos)
pagecache_isize_extended(inode, old_size, pos);
if (i_size_changed)
mark_inode_dirty(inode);
return copied;
}
EXPORT_SYMBOL(generic_write_end);
bool block_is_partially_uptodate(struct folio *folio, size_t from, size_t count)
{
unsigned block_start, block_end, blocksize;
unsigned to;
struct buffer_head *bh, *head;
bool ret = true;
head = folio_buffers(folio);
if (!head)
return false;
blocksize = head->b_size;
to = min_t(unsigned, folio_size(folio) - from, count);
to = from + to;
if (from < blocksize && to > folio_size(folio) - blocksize)
return false;
bh = head;
block_start = 0;
do {
block_end = block_start + blocksize;
if (block_end > from && block_start < to) {
if (!buffer_uptodate(bh)) {
ret = false;
break;
}
if (block_end >= to)
break;
}
block_start = block_end;
bh = bh->b_this_page;
} while (bh != head);
return ret;
}
EXPORT_SYMBOL(block_is_partially_uptodate);
int block_read_full_folio(struct folio *folio, get_block_t *get_block)
{
struct inode *inode = folio->mapping->host;
sector_t iblock, lblock;
struct buffer_head *bh, *head, *arr[MAX_BUF_PER_PAGE];
unsigned int blocksize, bbits;
int nr, i;
int fully_mapped = 1;
VM_BUG_ON_FOLIO(folio_test_large(folio), folio);
head = create_page_buffers(&folio->page, inode, 0);
blocksize = head->b_size;
bbits = block_size_bits(blocksize);
iblock = (sector_t)folio->index << (PAGE_SHIFT - bbits);
lblock = (i_size_read(inode)+blocksize-1) >> bbits;
bh = head;
nr = 0;
i = 0;
do {
if (buffer_uptodate(bh))
continue;
if (!buffer_mapped(bh)) {
int err = 0;
fully_mapped = 0;
if (iblock < lblock) {
WARN_ON(bh->b_size != blocksize);
err = get_block(inode, iblock, bh, 0);
if (err)
folio_set_error(folio);
}
if (!buffer_mapped(bh)) {
folio_zero_range(folio, i * blocksize,
blocksize);
if (!err)
set_buffer_uptodate(bh);
continue;
}
if (buffer_uptodate(bh))
continue;
}
arr[nr++] = bh;
} while (i++, iblock++, (bh = bh->b_this_page) != head);
if (fully_mapped)
folio_set_mappedtodisk(folio);
if (!nr) {
if (!folio_test_error(folio))
folio_mark_uptodate(folio);
folio_unlock(folio);
return 0;
}
for (i = 0; i < nr; i++) {
bh = arr[i];
lock_buffer(bh);
mark_buffer_async_read(bh);
}
for (i = 0; i < nr; i++) {
bh = arr[i];
if (buffer_uptodate(bh))
end_buffer_async_read(bh, 1);
else
submit_bh(REQ_OP_READ, 0, bh);
}
return 0;
}
EXPORT_SYMBOL(block_read_full_folio);
int generic_cont_expand_simple(struct inode *inode, loff_t size)
{
struct address_space *mapping = inode->i_mapping;
const struct address_space_operations *aops = mapping->a_ops;
struct page *page;
void *fsdata;
int err;
err = inode_newsize_ok(inode, size);
if (err)
goto out;
err = aops->write_begin(NULL, mapping, size, 0, &page, &fsdata);
if (err)
goto out;
err = aops->write_end(NULL, mapping, size, 0, 0, page, fsdata);
BUG_ON(err > 0);
out:
return err;
}
EXPORT_SYMBOL(generic_cont_expand_simple);
static int cont_expand_zero(struct file *file, struct address_space *mapping,
loff_t pos, loff_t *bytes)
{
struct inode *inode = mapping->host;
const struct address_space_operations *aops = mapping->a_ops;
unsigned int blocksize = i_blocksize(inode);
struct page *page;
void *fsdata;
pgoff_t index, curidx;
loff_t curpos;
unsigned zerofrom, offset, len;
int err = 0;
index = pos >> PAGE_SHIFT;
offset = pos & ~PAGE_MASK;
while (index > (curidx = (curpos = *bytes)>>PAGE_SHIFT)) {
zerofrom = curpos & ~PAGE_MASK;
if (zerofrom & (blocksize-1)) {
*bytes |= (blocksize-1);
(*bytes)++;
}
len = PAGE_SIZE - zerofrom;
err = aops->write_begin(file, mapping, curpos, len,
&page, &fsdata);
if (err)
goto out;
zero_user(page, zerofrom, len);
err = aops->write_end(file, mapping, curpos, len, len,
page, fsdata);
if (err < 0)
goto out;
BUG_ON(err != len);
err = 0;
balance_dirty_pages_ratelimited(mapping);
if (fatal_signal_pending(current)) {
err = -EINTR;
goto out;
}
}
if (index == curidx) {
zerofrom = curpos & ~PAGE_MASK;
if (offset <= zerofrom) {
goto out;
}
if (zerofrom & (blocksize-1)) {
*bytes |= (blocksize-1);
(*bytes)++;
}
len = offset - zerofrom;
err = aops->write_begin(file, mapping, curpos, len,
&page, &fsdata);
if (err)
goto out;
zero_user(page, zerofrom, len);
err = aops->write_end(file, mapping, curpos, len, len,
page, fsdata);
if (err < 0)
goto out;
BUG_ON(err != len);
err = 0;
}
out:
return err;
}
int cont_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len,
struct page **pagep, void **fsdata,
get_block_t *get_block, loff_t *bytes)
{
struct inode *inode = mapping->host;
unsigned int blocksize = i_blocksize(inode);
unsigned int zerofrom;
int err;
err = cont_expand_zero(file, mapping, pos, bytes);
if (err)
return err;
zerofrom = *bytes & ~PAGE_MASK;
if (pos+len > *bytes && zerofrom & (blocksize-1)) {
*bytes |= (blocksize-1);
(*bytes)++;
}
return block_write_begin(mapping, pos, len, pagep, get_block);
}
EXPORT_SYMBOL(cont_write_begin);
int block_commit_write(struct page *page, unsigned from, unsigned to)
{
struct inode *inode = page->mapping->host;
__block_commit_write(inode,page,from,to);
return 0;
}
EXPORT_SYMBOL(block_commit_write);
int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
get_block_t get_block)
{
struct page *page = vmf->page;
struct inode *inode = file_inode(vma->vm_file);
unsigned long end;
loff_t size;
int ret;
lock_page(page);
size = i_size_read(inode);
if ((page->mapping != inode->i_mapping) ||
(page_offset(page) > size)) {
ret = -EFAULT;
goto out_unlock;
}
if (((page->index + 1) << PAGE_SHIFT) > size)
end = size & ~PAGE_MASK;
else
end = PAGE_SIZE;
ret = __block_write_begin(page, 0, end, get_block);
if (!ret)
ret = block_commit_write(page, 0, end);
if (unlikely(ret < 0))
goto out_unlock;
set_page_dirty(page);
wait_for_stable_page(page);
return 0;
out_unlock:
unlock_page(page);
return ret;
}
EXPORT_SYMBOL(block_page_mkwrite);
static void end_buffer_read_nobh(struct buffer_head *bh, int uptodate)
{
__end_buffer_read_notouch(bh, uptodate);
}
static void attach_nobh_buffers(struct page *page, struct buffer_head *head)
{
struct buffer_head *bh;
BUG_ON(!PageLocked(page));
spin_lock(&page->mapping->private_lock);
bh = head;
do {
if (PageDirty(page))
set_buffer_dirty(bh);
if (!bh->b_this_page)
bh->b_this_page = head;
bh = bh->b_this_page;
} while (bh != head);
attach_page_private(page, head);
spin_unlock(&page->mapping->private_lock);
}
int nobh_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
struct page **pagep, void **fsdata,
get_block_t *get_block)
{
struct inode *inode = mapping->host;
const unsigned blkbits = inode->i_blkbits;
const unsigned blocksize = 1 << blkbits;
struct buffer_head *head, *bh;
struct page *page;
pgoff_t index;
unsigned from, to;
unsigned block_in_page;
unsigned block_start, block_end;
sector_t block_in_file;
int nr_reads = 0;
int ret = 0;
int is_mapped_to_disk = 1;
index = pos >> PAGE_SHIFT;
from = pos & (PAGE_SIZE - 1);
to = from + len;
page = grab_cache_page_write_begin(mapping, index);
if (!page)
return -ENOMEM;
*pagep = page;
*fsdata = NULL;
if (page_has_buffers(page)) {
ret = __block_write_begin(page, pos, len, get_block);
if (unlikely(ret))
goto out_release;
return ret;
}
if (PageMappedToDisk(page))
return 0;
head = alloc_page_buffers(page, blocksize, false);
if (!head) {
ret = -ENOMEM;
goto out_release;
}
block_in_file = (sector_t)page->index << (PAGE_SHIFT - blkbits);
for (block_start = 0, block_in_page = 0, bh = head;
block_start < PAGE_SIZE;
block_in_page++, block_start += blocksize, bh = bh->b_this_page) {
int create;
block_end = block_start + blocksize;
bh->b_state = 0;
create = 1;
if (block_start >= to)
create = 0;
ret = get_block(inode, block_in_file + block_in_page,
bh, create);
if (ret)
goto failed;
if (!buffer_mapped(bh))
is_mapped_to_disk = 0;
if (buffer_new(bh))
clean_bdev_bh_alias(bh);
if (PageUptodate(page)) {
set_buffer_uptodate(bh);
continue;
}
if (buffer_new(bh) || !buffer_mapped(bh)) {
zero_user_segments(page, block_start, from,
to, block_end);
continue;
}
if (buffer_uptodate(bh))
continue;
if (block_start < from || block_end > to) {
lock_buffer(bh);
bh->b_end_io = end_buffer_read_nobh;
submit_bh(REQ_OP_READ, 0, bh);
nr_reads++;
}
}
if (nr_reads) {
for (bh = head; bh; bh = bh->b_this_page) {
wait_on_buffer(bh);
if (!buffer_uptodate(bh))
ret = -EIO;
}
if (ret)
goto failed;
}
if (is_mapped_to_disk)
SetPageMappedToDisk(page);
*fsdata = head;
return 0;
failed:
BUG_ON(!ret);
attach_nobh_buffers(page, head);
page_zero_new_buffers(page, from, to);
out_release:
unlock_page(page);
put_page(page);
*pagep = NULL;
return ret;
}
EXPORT_SYMBOL(nobh_write_begin);
int nobh_write_end(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata)
{
struct inode *inode = page->mapping->host;
struct buffer_head *head = fsdata;
struct buffer_head *bh;
BUG_ON(fsdata != NULL && page_has_buffers(page));
if (unlikely(copied < len) && head)
attach_nobh_buffers(page, head);
if (page_has_buffers(page))
return generic_write_end(file, mapping, pos, len,
copied, page, fsdata);
SetPageUptodate(page);
set_page_dirty(page);
if (pos+copied > inode->i_size) {
i_size_write(inode, pos+copied);
mark_inode_dirty(inode);
}
unlock_page(page);
put_page(page);
while (head) {
bh = head;
head = head->b_this_page;
free_buffer_head(bh);
}
return copied;
}
EXPORT_SYMBOL(nobh_write_end);
int nobh_writepage(struct page *page, get_block_t *get_block,
struct writeback_control *wbc)
{
struct inode * const inode = page->mapping->host;
loff_t i_size = i_size_read(inode);
const pgoff_t end_index = i_size >> PAGE_SHIFT;
unsigned offset;
int ret;
if (page->index < end_index)
goto out;
offset = i_size & (PAGE_SIZE-1);
if (page->index >= end_index+1 || !offset) {
unlock_page(page);
return 0;
}
zero_user_segment(page, offset, PAGE_SIZE);
out:
ret = mpage_writepage(page, get_block, wbc);
if (ret == -EAGAIN)
ret = __block_write_full_page(inode, page, get_block, wbc,
end_buffer_async_write);
return ret;
}
EXPORT_SYMBOL(nobh_writepage);
int nobh_truncate_page(struct address_space *mapping,
loff_t from, get_block_t *get_block)
{
pgoff_t index = from >> PAGE_SHIFT;
struct inode *inode = mapping->host;
unsigned blocksize = i_blocksize(inode);
struct folio *folio;
struct buffer_head map_bh;
size_t offset;
sector_t iblock;
int err;
if (!(from & (blocksize - 1)))
return 0;
folio = __filemap_get_folio(mapping, index, FGP_LOCK | FGP_CREAT,
mapping_gfp_mask(mapping));
err = -ENOMEM;
if (!folio)
goto out;
if (folio_buffers(folio))
goto has_buffers;
iblock = from >> inode->i_blkbits;
map_bh.b_size = blocksize;
map_bh.b_state = 0;
err = get_block(inode, iblock, &map_bh, 0);
if (err)
goto unlock;
if (!buffer_mapped(&map_bh))
goto unlock;
if (!folio_test_uptodate(folio)) {
err = mapping->a_ops->read_folio(NULL, folio);
if (err) {
folio_put(folio);
goto out;
}
folio_lock(folio);
if (!folio_test_uptodate(folio)) {
err = -EIO;
goto unlock;
}
if (folio_buffers(folio))
goto has_buffers;
}
offset = offset_in_folio(folio, from);
folio_zero_segment(folio, offset, round_up(offset, blocksize));
folio_mark_dirty(folio);
err = 0;
unlock:
folio_unlock(folio);
folio_put(folio);
out:
return err;
has_buffers:
folio_unlock(folio);
folio_put(folio);
return block_truncate_page(mapping, from, get_block);
}
EXPORT_SYMBOL(nobh_truncate_page);
int block_truncate_page(struct address_space *mapping,
loff_t from, get_block_t *get_block)
{
pgoff_t index = from >> PAGE_SHIFT;
unsigned offset = from & (PAGE_SIZE-1);
unsigned blocksize;
sector_t iblock;
unsigned length, pos;
struct inode *inode = mapping->host;
struct page *page;
struct buffer_head *bh;
int err;
blocksize = i_blocksize(inode);
length = offset & (blocksize - 1);
if (!length)
return 0;
length = blocksize - length;
iblock = (sector_t)index << (PAGE_SHIFT - inode->i_blkbits);
page = grab_cache_page(mapping, index);
err = -ENOMEM;
if (!page)
goto out;
if (!page_has_buffers(page))
create_empty_buffers(page, blocksize, 0);
bh = page_buffers(page);
pos = blocksize;
while (offset >= pos) {
bh = bh->b_this_page;
iblock++;
pos += blocksize;
}
err = 0;
if (!buffer_mapped(bh)) {
WARN_ON(bh->b_size != blocksize);
err = get_block(inode, iblock, bh, 0);
if (err)
goto unlock;
if (!buffer_mapped(bh))
goto unlock;
}
if (PageUptodate(page))
set_buffer_uptodate(bh);
if (!buffer_uptodate(bh) && !buffer_delay(bh) && !buffer_unwritten(bh)) {
err = -EIO;
ll_rw_block(REQ_OP_READ, 0, 1, &bh);
wait_on_buffer(bh);
if (!buffer_uptodate(bh))
goto unlock;
}
zero_user(page, offset, length);
mark_buffer_dirty(bh);
err = 0;
unlock:
unlock_page(page);
put_page(page);
out:
return err;
}
EXPORT_SYMBOL(block_truncate_page);
int block_write_full_page(struct page *page, get_block_t *get_block,
struct writeback_control *wbc)
{
struct inode * const inode = page->mapping->host;
loff_t i_size = i_size_read(inode);
const pgoff_t end_index = i_size >> PAGE_SHIFT;
unsigned offset;
if (page->index < end_index)
return __block_write_full_page(inode, page, get_block, wbc,
end_buffer_async_write);
offset = i_size & (PAGE_SIZE-1);
if (page->index >= end_index+1 || !offset) {
unlock_page(page);
return 0;
}
zero_user_segment(page, offset, PAGE_SIZE);
return __block_write_full_page(inode, page, get_block, wbc,
end_buffer_async_write);
}
EXPORT_SYMBOL(block_write_full_page);
sector_t generic_block_bmap(struct address_space *mapping, sector_t block,
get_block_t *get_block)
{
struct inode *inode = mapping->host;
struct buffer_head tmp = {
.b_size = i_blocksize(inode),
};
get_block(inode, block, &tmp, 0);
return tmp.b_blocknr;
}
EXPORT_SYMBOL(generic_block_bmap);
static void end_bio_bh_io_sync(struct bio *bio)
{
struct buffer_head *bh = bio->bi_private;
if (unlikely(bio_flagged(bio, BIO_QUIET)))
set_bit(BH_Quiet, &bh->b_state);
bh->b_end_io(bh, !bio->bi_status);
bio_put(bio);
}
static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh,
struct writeback_control *wbc)
{
struct bio *bio;
BUG_ON(!buffer_locked(bh));
BUG_ON(!buffer_mapped(bh));
BUG_ON(!bh->b_end_io);
BUG_ON(buffer_delay(bh));
BUG_ON(buffer_unwritten(bh));
if (test_set_buffer_req(bh) && (op == REQ_OP_WRITE))
clear_buffer_write_io_error(bh);
if (buffer_meta(bh))
op_flags |= REQ_META;
if (buffer_prio(bh))
op_flags |= REQ_PRIO;
bio = bio_alloc(bh->b_bdev, 1, op | op_flags, GFP_NOIO);
fscrypt_set_bio_crypt_ctx_bh(bio, bh, GFP_NOIO);
bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh));
BUG_ON(bio->bi_iter.bi_size != bh->b_size);
bio->bi_end_io = end_bio_bh_io_sync;
bio->bi_private = bh;
guard_bio_eod(bio);
if (wbc) {
wbc_init_bio(wbc, bio);
wbc_account_cgroup_owner(wbc, bh->b_page, bh->b_size);
}
submit_bio(bio);
return 0;
}
int submit_bh(int op, int op_flags, struct buffer_head *bh)
{
return submit_bh_wbc(op, op_flags, bh, NULL);
}
EXPORT_SYMBOL(submit_bh);
void ll_rw_block(int op, int op_flags, int nr, struct buffer_head *bhs[])
{
int i;
for (i = 0; i < nr; i++) {
struct buffer_head *bh = bhs[i];
if (!trylock_buffer(bh))
continue;
if (op == WRITE) {
if (test_clear_buffer_dirty(bh)) {
bh->b_end_io = end_buffer_write_sync;
get_bh(bh);
submit_bh(op, op_flags, bh);
continue;
}
} else {
if (!buffer_uptodate(bh)) {
bh->b_end_io = end_buffer_read_sync;
get_bh(bh);
submit_bh(op, op_flags, bh);
continue;
}
}
unlock_buffer(bh);
}
}
EXPORT_SYMBOL(ll_rw_block);
void write_dirty_buffer(struct buffer_head *bh, int op_flags)
{
lock_buffer(bh);
if (!test_clear_buffer_dirty(bh)) {
unlock_buffer(bh);
return;
}
bh->b_end_io = end_buffer_write_sync;
get_bh(bh);
submit_bh(REQ_OP_WRITE, op_flags, bh);
}
EXPORT_SYMBOL(write_dirty_buffer);
int __sync_dirty_buffer(struct buffer_head *bh, int op_flags)
{
int ret = 0;
WARN_ON(atomic_read(&bh->b_count) < 1);
lock_buffer(bh);
if (test_clear_buffer_dirty(bh)) {
if (!buffer_mapped(bh)) {
unlock_buffer(bh);
return -EIO;
}
get_bh(bh);
bh->b_end_io = end_buffer_write_sync;
ret = submit_bh(REQ_OP_WRITE, op_flags, bh);
wait_on_buffer(bh);
if (!ret && !buffer_uptodate(bh))
ret = -EIO;
} else {
unlock_buffer(bh);
}
return ret;
}
EXPORT_SYMBOL(__sync_dirty_buffer);
int sync_dirty_buffer(struct buffer_head *bh)
{
return __sync_dirty_buffer(bh, REQ_SYNC);
}
EXPORT_SYMBOL(sync_dirty_buffer);
static inline int buffer_busy(struct buffer_head *bh)
{
return atomic_read(&bh->b_count) |
(bh->b_state & ((1 << BH_Dirty) | (1 << BH_Lock)));
}
static bool
drop_buffers(struct folio *folio, struct buffer_head **buffers_to_free)
{
struct buffer_head *head = folio_buffers(folio);
struct buffer_head *bh;
bh = head;
do {
if (buffer_busy(bh))
goto failed;
bh = bh->b_this_page;
} while (bh != head);
do {
struct buffer_head *next = bh->b_this_page;
if (bh->b_assoc_map)
__remove_assoc_queue(bh);
bh = next;
} while (bh != head);
*buffers_to_free = head;
folio_detach_private(folio);
return true;
failed:
return false;
}
bool try_to_free_buffers(struct folio *folio)
{
struct address_space * const mapping = folio->mapping;
struct buffer_head *buffers_to_free = NULL;
bool ret = 0;
BUG_ON(!folio_test_locked(folio));
if (folio_test_writeback(folio))
return false;
if (mapping == NULL) {
ret = drop_buffers(folio, &buffers_to_free);
goto out;
}
spin_lock(&mapping->private_lock);
ret = drop_buffers(folio, &buffers_to_free);
if (ret)
folio_cancel_dirty(folio);
spin_unlock(&mapping->private_lock);
out:
if (buffers_to_free) {
struct buffer_head *bh = buffers_to_free;
do {
struct buffer_head *next = bh->b_this_page;
free_buffer_head(bh);
bh = next;
} while (bh != buffers_to_free);
}
return ret;
}
EXPORT_SYMBOL(try_to_free_buffers);
static struct kmem_cache *bh_cachep __read_mostly;
static unsigned long max_buffer_heads;
int buffer_heads_over_limit;
struct bh_accounting {
int nr;
int ratelimit;
};
static DEFINE_PER_CPU(struct bh_accounting, bh_accounting) = {0, 0};
static void recalc_bh_state(void)
{
int i;
int tot = 0;
if (__this_cpu_inc_return(bh_accounting.ratelimit) - 1 < 4096)
return;
__this_cpu_write(bh_accounting.ratelimit, 0);
for_each_online_cpu(i)
tot += per_cpu(bh_accounting, i).nr;
buffer_heads_over_limit = (tot > max_buffer_heads);
}
struct buffer_head *alloc_buffer_head(gfp_t gfp_flags)
{
struct buffer_head *ret = kmem_cache_zalloc(bh_cachep, gfp_flags);
if (ret) {
INIT_LIST_HEAD(&ret->b_assoc_buffers);
spin_lock_init(&ret->b_uptodate_lock);
preempt_disable();
__this_cpu_inc(bh_accounting.nr);
recalc_bh_state();
preempt_enable();
}
return ret;
}
EXPORT_SYMBOL(alloc_buffer_head);
void free_buffer_head(struct buffer_head *bh)
{
BUG_ON(!list_empty(&bh->b_assoc_buffers));
kmem_cache_free(bh_cachep, bh);
preempt_disable();
__this_cpu_dec(bh_accounting.nr);
recalc_bh_state();
preempt_enable();
}
EXPORT_SYMBOL(free_buffer_head);
static int buffer_exit_cpu_dead(unsigned int cpu)
{
int i;
struct bh_lru *b = &per_cpu(bh_lrus, cpu);
for (i = 0; i < BH_LRU_SIZE; i++) {
brelse(b->bhs[i]);
b->bhs[i] = NULL;
}
this_cpu_add(bh_accounting.nr, per_cpu(bh_accounting, cpu).nr);
per_cpu(bh_accounting, cpu).nr = 0;
return 0;
}
int bh_uptodate_or_lock(struct buffer_head *bh)
{
if (!buffer_uptodate(bh)) {
lock_buffer(bh);
if (!buffer_uptodate(bh))
return 0;
unlock_buffer(bh);
}
return 1;
}
EXPORT_SYMBOL(bh_uptodate_or_lock);
int bh_submit_read(struct buffer_head *bh)
{
BUG_ON(!buffer_locked(bh));
if (buffer_uptodate(bh)) {
unlock_buffer(bh);
return 0;
}
get_bh(bh);
bh->b_end_io = end_buffer_read_sync;
submit_bh(REQ_OP_READ, 0, bh);
wait_on_buffer(bh);
if (buffer_uptodate(bh))
return 0;
return -EIO;
}
EXPORT_SYMBOL(bh_submit_read);
void __init buffer_init(void)
{
unsigned long nrpages;
int ret;
bh_cachep = kmem_cache_create("buffer_head",
sizeof(struct buffer_head), 0,
(SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|
SLAB_MEM_SPREAD),
NULL);
nrpages = (nr_free_buffer_pages() * 10) / 100;
max_buffer_heads = nrpages * (PAGE_SIZE / sizeof(struct buffer_head));
ret = cpuhp_setup_state_nocalls(CPUHP_FS_BUFF_DEAD, "fs/buffer:dead",
NULL, buffer_exit_cpu_dead);
WARN_ON(ret < 0);
}