4c21e2f244
Christoph Lameter demonstrated very poor scalability on the SGI 512-way, with a many-threaded application which concurrently initializes different parts of a large anonymous area. This patch corrects that, by using a separate spinlock per page table page, to guard the page table entries in that page, instead of using the mm's single page_table_lock. (But even then, page_table_lock is still used to guard page table allocation, and anon_vma allocation.) In this implementation, the spinlock is tucked inside the struct page of the page table page: with a BUILD_BUG_ON in case it overflows - which it would in the case of 32-bit PA-RISC with spinlock debugging enabled. Splitting the lock is not quite for free: another cacheline access. Ideally, I suppose we would use split ptlock only for multi-threaded processes on multi-cpu machines; but deciding that dynamically would have its own costs. So for now enable it by config, at some number of cpus - since the Kconfig language doesn't support inequalities, let preprocessor compare that with NR_CPUS. But I don't think it's worth being user-configurable: for good testing of both split and unsplit configs, split now at 4 cpus, and perhaps change that to 8 later. There is a benefit even for singly threaded processes: kswapd can be attacking one part of the mm while another part is busy faulting. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
300 lines
9.4 KiB
C
300 lines
9.4 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 <asm/atomic.h>
|
|
|
|
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_Ordered, /* ordered write */
|
|
BH_Eopnotsupp, /* operation not supported (barrier) */
|
|
|
|
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);
|
|
|
|
/*
|
|
* Keep related fields in common cachelines. The most commonly accessed
|
|
* field (b_state) goes at the start so the compiler does not generate
|
|
* indexed addressing for it.
|
|
*/
|
|
struct buffer_head {
|
|
/* First cache line: */
|
|
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 */
|
|
atomic_t b_count; /* users using this block */
|
|
u32 b_size; /* block size */
|
|
|
|
sector_t b_blocknr; /* block number */
|
|
char *b_data; /* pointer to data block */
|
|
|
|
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 */
|
|
};
|
|
|
|
/*
|
|
* 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)
|
|
TAS_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(Ordered, ordered)
|
|
BUFFER_FNS(Eopnotsupp, eopnotsupp)
|
|
|
|
#define bh_offset(bh) ((unsigned long)(bh)->b_data & ~PAGE_MASK)
|
|
#define touch_buffer(bh) mark_page_accessed(bh->b_page)
|
|
|
|
/* 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)
|
|
|
|
/*
|
|
* Declarations
|
|
*/
|
|
|
|
void FASTCALL(mark_buffer_dirty(struct buffer_head *bh));
|
|
void init_buffer(struct buffer_head *, bh_end_io_t *, void *);
|
|
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 invalidate_bdev(struct block_device *, int);
|
|
int sync_blockdev(struct block_device *bdev);
|
|
void __wait_on_buffer(struct buffer_head *);
|
|
wait_queue_head_t *bh_waitq_head(struct buffer_head *bh);
|
|
int fsync_bdev(struct block_device *);
|
|
struct super_block *freeze_bdev(struct block_device *);
|
|
void thaw_bdev(struct block_device *, struct super_block *);
|
|
int fsync_super(struct super_block *);
|
|
int fsync_no_super(struct block_device *);
|
|
struct buffer_head *__find_get_block(struct block_device *, sector_t, int);
|
|
struct buffer_head * __getblk(struct block_device *, sector_t, int);
|
|
void __brelse(struct buffer_head *);
|
|
void __bforget(struct buffer_head *);
|
|
void __breadahead(struct block_device *, sector_t block, int size);
|
|
struct buffer_head *__bread(struct block_device *, sector_t block, int size);
|
|
struct buffer_head *alloc_buffer_head(gfp_t gfp_flags);
|
|
void free_buffer_head(struct buffer_head * bh);
|
|
void FASTCALL(unlock_buffer(struct buffer_head *bh));
|
|
void FASTCALL(__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 submit_bh(int, struct buffer_head *);
|
|
void write_boundary_block(struct block_device *bdev,
|
|
sector_t bblock, unsigned blocksize);
|
|
|
|
extern int buffer_heads_over_limit;
|
|
|
|
/*
|
|
* Generic address_space_operations implementations for buffer_head-backed
|
|
* address_spaces.
|
|
*/
|
|
int try_to_release_page(struct page * page, gfp_t gfp_mask);
|
|
int block_invalidatepage(struct page *page, unsigned long offset);
|
|
int block_write_full_page(struct page *page, get_block_t *get_block,
|
|
struct writeback_control *wbc);
|
|
int block_read_full_page(struct page*, get_block_t*);
|
|
int block_prepare_write(struct page*, unsigned, unsigned, get_block_t*);
|
|
int cont_prepare_write(struct page*, unsigned, unsigned, get_block_t*,
|
|
loff_t *);
|
|
int generic_cont_expand(struct inode *inode, loff_t size) ;
|
|
int block_commit_write(struct page *page, unsigned from, unsigned to);
|
|
int block_sync_page(struct page *);
|
|
sector_t generic_block_bmap(struct address_space *, sector_t, get_block_t *);
|
|
int generic_commit_write(struct file *, struct page *, unsigned, unsigned);
|
|
int block_truncate_page(struct address_space *, loff_t, get_block_t *);
|
|
int file_fsync(struct file *, struct dentry *, int);
|
|
int nobh_prepare_write(struct page*, unsigned, unsigned, get_block_t*);
|
|
int nobh_commit_write(struct file *, struct page *, unsigned, unsigned);
|
|
int nobh_truncate_page(struct address_space *, loff_t);
|
|
int nobh_writepage(struct page *page, get_block_t *get_block,
|
|
struct writeback_control *wbc);
|
|
|
|
|
|
/*
|
|
* 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;
|
|
}
|
|
|
|
/*
|
|
* Calling wait_on_buffer() for a zero-ref buffer is illegal, so we call into
|
|
* __wait_on_buffer() just to trip a debug check. Because debug code in inline
|
|
* functions is bloaty.
|
|
*/
|
|
static inline void wait_on_buffer(struct buffer_head *bh)
|
|
{
|
|
might_sleep();
|
|
if (buffer_locked(bh) || atomic_read(&bh->b_count) == 0)
|
|
__wait_on_buffer(bh);
|
|
}
|
|
|
|
static inline void lock_buffer(struct buffer_head *bh)
|
|
{
|
|
might_sleep();
|
|
if (test_set_buffer_locked(bh))
|
|
__lock_buffer(bh);
|
|
}
|
|
|
|
#endif /* _LINUX_BUFFER_HEAD_H */
|