mirror of
https://github.com/edk2-porting/linux-next.git
synced 2024-12-26 22:24:09 +08:00
b45972265f
Page reclaim keeps track of dirty and under writeback pages and uses it to determine if wait_iff_congested() should stall or if kswapd should begin writing back pages. This fails to account for buffer pages that can be under writeback but not PageWriteback which is the case for filesystems like ext3 ordered mode. Furthermore, PageDirty buffer pages can have all the buffers clean and writepage does no IO so it should not be accounted as congested. This patch adds an address_space operation that filesystems may optionally use to check if a page is really dirty or really under writeback. An implementation is provided for for buffer_heads is added and used for block operations and ext3 in ordered mode. By default the page flags are obeyed. Credit goes to Jan Kara for identifying that the page flags alone are not sufficient for ext3 and sanity checking a number of ideas on how the problem could be addressed. Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: Rik van Riel <riel@redhat.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Jiri Slaby <jslaby@suse.cz> Cc: Valdis Kletnieks <Valdis.Kletnieks@vt.edu> Cc: Zlatko Calusic <zcalusic@bitsync.net> Cc: dormando <dormando@rydia.net> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
360 lines
12 KiB
C
360 lines
12 KiB
C
/*
|
|
* include/linux/buffer_head.h
|
|
*
|
|
* Everything to do with buffer_heads.
|
|
*/
|
|
|
|
#ifndef _LINUX_BUFFER_HEAD_H
|
|
#define _LINUX_BUFFER_HEAD_H
|
|
|
|
#include <linux/types.h>
|
|
#include <linux/fs.h>
|
|
#include <linux/linkage.h>
|
|
#include <linux/pagemap.h>
|
|
#include <linux/wait.h>
|
|
#include <linux/atomic.h>
|
|
|
|
#ifdef CONFIG_BLOCK
|
|
|
|
enum bh_state_bits {
|
|
BH_Uptodate, /* Contains valid data */
|
|
BH_Dirty, /* Is dirty */
|
|
BH_Lock, /* Is locked */
|
|
BH_Req, /* Has been submitted for I/O */
|
|
BH_Uptodate_Lock,/* Used by the first bh in a page, to serialise
|
|
* IO completion of other buffers in the page
|
|
*/
|
|
|
|
BH_Mapped, /* Has a disk mapping */
|
|
BH_New, /* Disk mapping was newly created by get_block */
|
|
BH_Async_Read, /* Is under end_buffer_async_read I/O */
|
|
BH_Async_Write, /* Is under end_buffer_async_write I/O */
|
|
BH_Delay, /* Buffer is not yet allocated on disk */
|
|
BH_Boundary, /* Block is followed by a discontiguity */
|
|
BH_Write_EIO, /* I/O error on write */
|
|
BH_Unwritten, /* Buffer is allocated on disk but not written */
|
|
BH_Quiet, /* Buffer Error Prinks to be quiet */
|
|
BH_Meta, /* Buffer contains metadata */
|
|
BH_Prio, /* Buffer should be submitted with REQ_PRIO */
|
|
|
|
BH_PrivateStart,/* not a state bit, but the first bit available
|
|
* for private allocation by other entities
|
|
*/
|
|
};
|
|
|
|
#define MAX_BUF_PER_PAGE (PAGE_CACHE_SIZE / 512)
|
|
|
|
struct page;
|
|
struct buffer_head;
|
|
struct address_space;
|
|
typedef void (bh_end_io_t)(struct buffer_head *bh, int uptodate);
|
|
|
|
/*
|
|
* Historically, a buffer_head was used to map a single block
|
|
* within a page, and of course as the unit of I/O through the
|
|
* filesystem and block layers. Nowadays the basic I/O unit
|
|
* is the bio, and buffer_heads are used for extracting block
|
|
* mappings (via a get_block_t call), for tracking state within
|
|
* a page (via a page_mapping) and for wrapping bio submission
|
|
* for backward compatibility reasons (e.g. submit_bh).
|
|
*/
|
|
struct buffer_head {
|
|
unsigned long b_state; /* buffer state bitmap (see above) */
|
|
struct buffer_head *b_this_page;/* circular list of page's buffers */
|
|
struct page *b_page; /* the page this bh is mapped to */
|
|
|
|
sector_t b_blocknr; /* start block number */
|
|
size_t b_size; /* size of mapping */
|
|
char *b_data; /* pointer to data within the page */
|
|
|
|
struct block_device *b_bdev;
|
|
bh_end_io_t *b_end_io; /* I/O completion */
|
|
void *b_private; /* reserved for b_end_io */
|
|
struct list_head b_assoc_buffers; /* associated with another mapping */
|
|
struct address_space *b_assoc_map; /* mapping this buffer is
|
|
associated with */
|
|
atomic_t b_count; /* users using this buffer_head */
|
|
};
|
|
|
|
/*
|
|
* macro tricks to expand the set_buffer_foo(), clear_buffer_foo()
|
|
* and buffer_foo() functions.
|
|
*/
|
|
#define BUFFER_FNS(bit, name) \
|
|
static inline void set_buffer_##name(struct buffer_head *bh) \
|
|
{ \
|
|
set_bit(BH_##bit, &(bh)->b_state); \
|
|
} \
|
|
static inline void clear_buffer_##name(struct buffer_head *bh) \
|
|
{ \
|
|
clear_bit(BH_##bit, &(bh)->b_state); \
|
|
} \
|
|
static inline int buffer_##name(const struct buffer_head *bh) \
|
|
{ \
|
|
return test_bit(BH_##bit, &(bh)->b_state); \
|
|
}
|
|
|
|
/*
|
|
* test_set_buffer_foo() and test_clear_buffer_foo()
|
|
*/
|
|
#define TAS_BUFFER_FNS(bit, name) \
|
|
static inline int test_set_buffer_##name(struct buffer_head *bh) \
|
|
{ \
|
|
return test_and_set_bit(BH_##bit, &(bh)->b_state); \
|
|
} \
|
|
static inline int test_clear_buffer_##name(struct buffer_head *bh) \
|
|
{ \
|
|
return test_and_clear_bit(BH_##bit, &(bh)->b_state); \
|
|
} \
|
|
|
|
/*
|
|
* Emit the buffer bitops functions. Note that there are also functions
|
|
* of the form "mark_buffer_foo()". These are higher-level functions which
|
|
* do something in addition to setting a b_state bit.
|
|
*/
|
|
BUFFER_FNS(Uptodate, uptodate)
|
|
BUFFER_FNS(Dirty, dirty)
|
|
TAS_BUFFER_FNS(Dirty, dirty)
|
|
BUFFER_FNS(Lock, locked)
|
|
BUFFER_FNS(Req, req)
|
|
TAS_BUFFER_FNS(Req, req)
|
|
BUFFER_FNS(Mapped, mapped)
|
|
BUFFER_FNS(New, new)
|
|
BUFFER_FNS(Async_Read, async_read)
|
|
BUFFER_FNS(Async_Write, async_write)
|
|
BUFFER_FNS(Delay, delay)
|
|
BUFFER_FNS(Boundary, boundary)
|
|
BUFFER_FNS(Write_EIO, write_io_error)
|
|
BUFFER_FNS(Unwritten, unwritten)
|
|
BUFFER_FNS(Meta, meta)
|
|
BUFFER_FNS(Prio, prio)
|
|
|
|
#define bh_offset(bh) ((unsigned long)(bh)->b_data & ~PAGE_MASK)
|
|
|
|
/* If we *know* page->private refers to buffer_heads */
|
|
#define page_buffers(page) \
|
|
({ \
|
|
BUG_ON(!PagePrivate(page)); \
|
|
((struct buffer_head *)page_private(page)); \
|
|
})
|
|
#define page_has_buffers(page) PagePrivate(page)
|
|
|
|
void buffer_check_dirty_writeback(struct page *page,
|
|
bool *dirty, bool *writeback);
|
|
|
|
/*
|
|
* Declarations
|
|
*/
|
|
|
|
void mark_buffer_dirty(struct buffer_head *bh);
|
|
void init_buffer(struct buffer_head *, bh_end_io_t *, void *);
|
|
void touch_buffer(struct buffer_head *bh);
|
|
void set_bh_page(struct buffer_head *bh,
|
|
struct page *page, unsigned long offset);
|
|
int try_to_free_buffers(struct page *);
|
|
struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size,
|
|
int retry);
|
|
void create_empty_buffers(struct page *, unsigned long,
|
|
unsigned long b_state);
|
|
void end_buffer_read_sync(struct buffer_head *bh, int uptodate);
|
|
void end_buffer_write_sync(struct buffer_head *bh, int uptodate);
|
|
void end_buffer_async_write(struct buffer_head *bh, int uptodate);
|
|
|
|
/* Things to do with buffers at mapping->private_list */
|
|
void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode);
|
|
int inode_has_buffers(struct inode *);
|
|
void invalidate_inode_buffers(struct inode *);
|
|
int remove_inode_buffers(struct inode *inode);
|
|
int sync_mapping_buffers(struct address_space *mapping);
|
|
void unmap_underlying_metadata(struct block_device *bdev, sector_t block);
|
|
|
|
void mark_buffer_async_write(struct buffer_head *bh);
|
|
void __wait_on_buffer(struct buffer_head *);
|
|
wait_queue_head_t *bh_waitq_head(struct buffer_head *bh);
|
|
struct buffer_head *__find_get_block(struct block_device *bdev, sector_t block,
|
|
unsigned size);
|
|
struct buffer_head *__getblk(struct block_device *bdev, sector_t block,
|
|
unsigned size);
|
|
void __brelse(struct buffer_head *);
|
|
void __bforget(struct buffer_head *);
|
|
void __breadahead(struct block_device *, sector_t block, unsigned int size);
|
|
struct buffer_head *__bread(struct block_device *, sector_t block, unsigned size);
|
|
void invalidate_bh_lrus(void);
|
|
struct buffer_head *alloc_buffer_head(gfp_t gfp_flags);
|
|
void free_buffer_head(struct buffer_head * bh);
|
|
void unlock_buffer(struct buffer_head *bh);
|
|
void __lock_buffer(struct buffer_head *bh);
|
|
void ll_rw_block(int, int, struct buffer_head * bh[]);
|
|
int sync_dirty_buffer(struct buffer_head *bh);
|
|
int __sync_dirty_buffer(struct buffer_head *bh, int rw);
|
|
void write_dirty_buffer(struct buffer_head *bh, int rw);
|
|
int _submit_bh(int rw, struct buffer_head *bh, unsigned long bio_flags);
|
|
int submit_bh(int, struct buffer_head *);
|
|
void write_boundary_block(struct block_device *bdev,
|
|
sector_t bblock, unsigned blocksize);
|
|
int bh_uptodate_or_lock(struct buffer_head *bh);
|
|
int bh_submit_read(struct buffer_head *bh);
|
|
|
|
extern int buffer_heads_over_limit;
|
|
|
|
/*
|
|
* Generic address_space_operations implementations for buffer_head-backed
|
|
* address_spaces.
|
|
*/
|
|
void block_invalidatepage(struct page *page, unsigned int offset,
|
|
unsigned int length);
|
|
int block_write_full_page(struct page *page, get_block_t *get_block,
|
|
struct writeback_control *wbc);
|
|
int block_write_full_page_endio(struct page *page, get_block_t *get_block,
|
|
struct writeback_control *wbc, bh_end_io_t *handler);
|
|
int block_read_full_page(struct page*, get_block_t*);
|
|
int block_is_partially_uptodate(struct page *page, read_descriptor_t *desc,
|
|
unsigned long from);
|
|
int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
|
|
unsigned flags, struct page **pagep, get_block_t *get_block);
|
|
int __block_write_begin(struct page *page, loff_t pos, unsigned len,
|
|
get_block_t *get_block);
|
|
int block_write_end(struct file *, struct address_space *,
|
|
loff_t, unsigned, unsigned,
|
|
struct page *, void *);
|
|
int generic_write_end(struct file *, struct address_space *,
|
|
loff_t, unsigned, unsigned,
|
|
struct page *, void *);
|
|
void page_zero_new_buffers(struct page *page, unsigned from, unsigned to);
|
|
int cont_write_begin(struct file *, struct address_space *, loff_t,
|
|
unsigned, unsigned, struct page **, void **,
|
|
get_block_t *, loff_t *);
|
|
int generic_cont_expand_simple(struct inode *inode, loff_t size);
|
|
int block_commit_write(struct page *page, unsigned from, unsigned to);
|
|
int __block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
|
|
get_block_t get_block);
|
|
int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
|
|
get_block_t get_block);
|
|
/* Convert errno to return value from ->page_mkwrite() call */
|
|
static inline int block_page_mkwrite_return(int err)
|
|
{
|
|
if (err == 0)
|
|
return VM_FAULT_LOCKED;
|
|
if (err == -EFAULT)
|
|
return VM_FAULT_NOPAGE;
|
|
if (err == -ENOMEM)
|
|
return VM_FAULT_OOM;
|
|
if (err == -EAGAIN)
|
|
return VM_FAULT_RETRY;
|
|
/* -ENOSPC, -EDQUOT, -EIO ... */
|
|
return VM_FAULT_SIGBUS;
|
|
}
|
|
sector_t generic_block_bmap(struct address_space *, sector_t, get_block_t *);
|
|
int block_truncate_page(struct address_space *, loff_t, get_block_t *);
|
|
int nobh_write_begin(struct address_space *, loff_t, unsigned, unsigned,
|
|
struct page **, void **, get_block_t*);
|
|
int nobh_write_end(struct file *, struct address_space *,
|
|
loff_t, unsigned, unsigned,
|
|
struct page *, void *);
|
|
int nobh_truncate_page(struct address_space *, loff_t, get_block_t *);
|
|
int nobh_writepage(struct page *page, get_block_t *get_block,
|
|
struct writeback_control *wbc);
|
|
|
|
void buffer_init(void);
|
|
|
|
/*
|
|
* inline definitions
|
|
*/
|
|
|
|
static inline void attach_page_buffers(struct page *page,
|
|
struct buffer_head *head)
|
|
{
|
|
page_cache_get(page);
|
|
SetPagePrivate(page);
|
|
set_page_private(page, (unsigned long)head);
|
|
}
|
|
|
|
static inline void get_bh(struct buffer_head *bh)
|
|
{
|
|
atomic_inc(&bh->b_count);
|
|
}
|
|
|
|
static inline void put_bh(struct buffer_head *bh)
|
|
{
|
|
smp_mb__before_atomic_dec();
|
|
atomic_dec(&bh->b_count);
|
|
}
|
|
|
|
static inline void brelse(struct buffer_head *bh)
|
|
{
|
|
if (bh)
|
|
__brelse(bh);
|
|
}
|
|
|
|
static inline void bforget(struct buffer_head *bh)
|
|
{
|
|
if (bh)
|
|
__bforget(bh);
|
|
}
|
|
|
|
static inline struct buffer_head *
|
|
sb_bread(struct super_block *sb, sector_t block)
|
|
{
|
|
return __bread(sb->s_bdev, block, sb->s_blocksize);
|
|
}
|
|
|
|
static inline void
|
|
sb_breadahead(struct super_block *sb, sector_t block)
|
|
{
|
|
__breadahead(sb->s_bdev, block, sb->s_blocksize);
|
|
}
|
|
|
|
static inline struct buffer_head *
|
|
sb_getblk(struct super_block *sb, sector_t block)
|
|
{
|
|
return __getblk(sb->s_bdev, block, sb->s_blocksize);
|
|
}
|
|
|
|
static inline struct buffer_head *
|
|
sb_find_get_block(struct super_block *sb, sector_t block)
|
|
{
|
|
return __find_get_block(sb->s_bdev, block, sb->s_blocksize);
|
|
}
|
|
|
|
static inline void
|
|
map_bh(struct buffer_head *bh, struct super_block *sb, sector_t block)
|
|
{
|
|
set_buffer_mapped(bh);
|
|
bh->b_bdev = sb->s_bdev;
|
|
bh->b_blocknr = block;
|
|
bh->b_size = sb->s_blocksize;
|
|
}
|
|
|
|
static inline void wait_on_buffer(struct buffer_head *bh)
|
|
{
|
|
might_sleep();
|
|
if (buffer_locked(bh))
|
|
__wait_on_buffer(bh);
|
|
}
|
|
|
|
static inline int trylock_buffer(struct buffer_head *bh)
|
|
{
|
|
return likely(!test_and_set_bit_lock(BH_Lock, &bh->b_state));
|
|
}
|
|
|
|
static inline void lock_buffer(struct buffer_head *bh)
|
|
{
|
|
might_sleep();
|
|
if (!trylock_buffer(bh))
|
|
__lock_buffer(bh);
|
|
}
|
|
|
|
extern int __set_page_dirty_buffers(struct page *page);
|
|
|
|
#else /* CONFIG_BLOCK */
|
|
|
|
static inline void buffer_init(void) {}
|
|
static inline int try_to_free_buffers(struct page *page) { return 1; }
|
|
static inline int inode_has_buffers(struct inode *inode) { return 0; }
|
|
static inline void invalidate_inode_buffers(struct inode *inode) {}
|
|
static inline int remove_inode_buffers(struct inode *inode) { return 1; }
|
|
static inline int sync_mapping_buffers(struct address_space *mapping) { return 0; }
|
|
|
|
#endif /* CONFIG_BLOCK */
|
|
#endif /* _LINUX_BUFFER_HEAD_H */
|