2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
|
* 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>
|
|
|
|
|
|
[PATCH] BLOCK: Make it possible to disable the block layer [try #6]
Make it possible to disable the block layer. Not all embedded devices require
it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require
the block layer to be present.
This patch does the following:
(*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev
support.
(*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls
an item that uses the block layer. This includes:
(*) Block I/O tracing.
(*) Disk partition code.
(*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS.
(*) The SCSI layer. As far as I can tell, even SCSI chardevs use the
block layer to do scheduling. Some drivers that use SCSI facilities -
such as USB storage - end up disabled indirectly from this.
(*) Various block-based device drivers, such as IDE and the old CDROM
drivers.
(*) MTD blockdev handling and FTL.
(*) JFFS - which uses set_bdev_super(), something it could avoid doing by
taking a leaf out of JFFS2's book.
(*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and
linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is,
however, still used in places, and so is still available.
(*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and
parts of linux/fs.h.
(*) Makes a number of files in fs/ contingent on CONFIG_BLOCK.
(*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK.
(*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK
is not enabled.
(*) fs/no-block.c is created to hold out-of-line stubs and things that are
required when CONFIG_BLOCK is not set:
(*) Default blockdev file operations (to give error ENODEV on opening).
(*) Makes some /proc changes:
(*) /proc/devices does not list any blockdevs.
(*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK.
(*) Makes some compat ioctl handling contingent on CONFIG_BLOCK.
(*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if
given command other than Q_SYNC or if a special device is specified.
(*) In init/do_mounts.c, no reference is made to the blockdev routines if
CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2.
(*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return
error ENOSYS by way of cond_syscall if so).
(*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if
CONFIG_BLOCK is not set, since they can't then happen.
Signed-Off-By: David Howells <dhowells@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 02:45:40 +08:00
|
|
|
#ifdef CONFIG_BLOCK
|
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
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 */
|
2005-07-08 08:56:56 +08:00
|
|
|
BH_Uptodate_Lock,/* Used by the first bh in a page, to serialise
|
|
|
|
|
* IO completion of other buffers in the page
|
|
|
|
|
*/
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
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) */
|
2007-02-12 16:51:41 +08:00
|
|
|
BH_Unwritten, /* Buffer is allocated on disk but not written */
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
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);
|
|
|
|
|
|
|
|
|
|
/*
|
2006-03-26 17:38:00 +08:00
|
|
|
* 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).
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
|
|
|
|
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 */
|
|
|
|
|
|
2006-03-26 17:38:00 +08:00
|
|
|
sector_t b_blocknr; /* start block number */
|
|
|
|
|
size_t b_size; /* size of mapping */
|
|
|
|
|
char *b_data; /* pointer to data within the page */
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
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 */
|
2006-10-17 15:10:19 +08:00
|
|
|
struct address_space *b_assoc_map; /* mapping this buffer is
|
|
|
|
|
associated with */
|
2006-03-26 17:38:00 +08:00
|
|
|
atomic_t b_count; /* users using this buffer_head */
|
2005-04-17 06:20:36 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* 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(Ordered, ordered)
|
|
|
|
|
BUFFER_FNS(Eopnotsupp, eopnotsupp)
|
2007-02-12 16:51:41 +08:00
|
|
|
BUFFER_FNS(Unwritten, unwritten)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
#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) \
|
|
|
|
|
({ \
|
[PATCH] mm: split page table lock
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>
2005-10-30 09:16:40 +08:00
|
|
|
BUG_ON(!PagePrivate(page)); \
|
|
|
|
|
((struct buffer_head *)page_private(page)); \
|
2005-04-17 06:20:36 +08:00
|
|
|
})
|
|
|
|
|
#define page_has_buffers(page) PagePrivate(page)
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Declarations
|
|
|
|
|
*/
|
|
|
|
|
|
2008-02-14 07:03:15 +08:00
|
|
|
void mark_buffer_dirty(struct buffer_head *bh);
|
2005-04-17 06:20:36 +08:00
|
|
|
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);
|
|
|
|
|
|
|
|
|
|
/* 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);
|
2007-05-07 05:49:54 +08:00
|
|
|
void invalidate_bdev(struct block_device *);
|
2005-04-17 06:20:36 +08:00
|
|
|
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 *);
|
2007-02-12 16:52:14 +08:00
|
|
|
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);
|
2005-04-17 06:20:36 +08:00
|
|
|
void __brelse(struct buffer_head *);
|
|
|
|
|
void __bforget(struct buffer_head *);
|
2007-02-12 16:52:14 +08:00
|
|
|
void __breadahead(struct block_device *, sector_t block, unsigned int size);
|
|
|
|
|
struct buffer_head *__bread(struct block_device *, sector_t block, unsigned size);
|
2007-05-07 05:49:55 +08:00
|
|
|
void invalidate_bh_lrus(void);
|
2005-10-07 14:46:04 +08:00
|
|
|
struct buffer_head *alloc_buffer_head(gfp_t gfp_flags);
|
2005-04-17 06:20:36 +08:00
|
|
|
void free_buffer_head(struct buffer_head * bh);
|
2008-02-14 07:03:15 +08:00
|
|
|
void unlock_buffer(struct buffer_head *bh);
|
|
|
|
|
void __lock_buffer(struct buffer_head *bh);
|
2005-04-17 06:20:36 +08:00
|
|
|
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);
|
2008-01-29 12:58:26 +08:00
|
|
|
int bh_uptodate_or_lock(struct buffer_head *bh);
|
|
|
|
|
int bh_submit_read(struct buffer_head *bh);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
extern int buffer_heads_over_limit;
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Generic address_space_operations implementations for buffer_head-backed
|
|
|
|
|
* address_spaces.
|
|
|
|
|
*/
|
2006-03-26 17:37:18 +08:00
|
|
|
void block_invalidatepage(struct page *page, unsigned long offset);
|
2005-04-17 06:20:36 +08:00
|
|
|
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*);
|
vfs: pagecache usage optimization for pagesize!=blocksize
When we read some part of a file through pagecache, if there is a
pagecache of corresponding index but this page is not uptodate, read IO
is issued and this page will be uptodate.
I think this is good for pagesize == blocksize environment but there is
room for improvement on pagesize != blocksize environment. Because in
this case a page can have multiple buffers and even if a page is not
uptodate, some buffers can be uptodate.
So I suggest that when all buffers which correspond to a part of a file
that we want to read are uptodate, use this pagecache and copy data from
this pagecache to user buffer even if a page is not uptodate. This can
reduce read IO and improve system throughput.
I wrote a benchmark program and got result number with this program.
This benchmark do:
1: mount and open a test file.
2: create a 512MB file.
3: close a file and umount.
4: mount and again open a test file.
5: pwrite randomly 300000 times on a test file. offset is aligned
by IO size(1024bytes).
6: measure time of preading randomly 100000 times on a test file.
The result was:
2.6.26
330 sec
2.6.26-patched
226 sec
Arch:i386
Filesystem:ext3
Blocksize:1024 bytes
Memory: 1GB
On ext3/4, a file is written through buffer/block. So random read/write
mixed workloads or random read after random write workloads are optimized
with this patch under pagesize != blocksize environment. This test result
showed this.
The benchmark program is as follows:
#include <stdio.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <unistd.h>
#include <time.h>
#include <stdlib.h>
#include <string.h>
#include <sys/mount.h>
#define LEN 1024
#define LOOP 1024*512 /* 512MB */
main(void)
{
unsigned long i, offset, filesize;
int fd;
char buf[LEN];
time_t t1, t2;
if (mount("/dev/sda1", "/root/test1/", "ext3", 0, 0) < 0) {
perror("cannot mount\n");
exit(1);
}
memset(buf, 0, LEN);
fd = open("/root/test1/testfile", O_CREAT|O_RDWR|O_TRUNC);
if (fd < 0) {
perror("cannot open file\n");
exit(1);
}
for (i = 0; i < LOOP; i++)
write(fd, buf, LEN);
close(fd);
if (umount("/root/test1/") < 0) {
perror("cannot umount\n");
exit(1);
}
if (mount("/dev/sda1", "/root/test1/", "ext3", 0, 0) < 0) {
perror("cannot mount\n");
exit(1);
}
fd = open("/root/test1/testfile", O_RDWR);
if (fd < 0) {
perror("cannot open file\n");
exit(1);
}
filesize = LEN * LOOP;
for (i = 0; i < 300000; i++){
offset = (random() % filesize) & (~(LEN - 1));
pwrite(fd, buf, LEN, offset);
}
printf("start test\n");
time(&t1);
for (i = 0; i < 100000; i++){
offset = (random() % filesize) & (~(LEN - 1));
pread(fd, buf, LEN, offset);
}
time(&t2);
printf("%ld sec\n", t2-t1);
close(fd);
if (umount("/root/test1/") < 0) {
perror("cannot umount\n");
exit(1);
}
}
Signed-off-by: Hisashi Hifumi <hifumi.hisashi@oss.ntt.co.jp>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Jan Kara <jack@ucw.cz>
Cc: <linux-ext4@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-29 06:46:36 +08:00
|
|
|
int block_is_partially_uptodate(struct page *page, read_descriptor_t *desc,
|
|
|
|
|
unsigned long from);
|
2007-10-16 16:25:01 +08:00
|
|
|
int block_write_begin(struct file *, struct address_space *,
|
|
|
|
|
loff_t, unsigned, unsigned,
|
|
|
|
|
struct page **, void **, get_block_t*);
|
|
|
|
|
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);
|
2005-04-17 06:20:36 +08:00
|
|
|
int block_prepare_write(struct page*, unsigned, unsigned, get_block_t*);
|
2007-10-16 16:25:07 +08:00
|
|
|
int cont_write_begin(struct file *, struct address_space *, loff_t,
|
|
|
|
|
unsigned, unsigned, struct page **, void **,
|
|
|
|
|
get_block_t *, loff_t *);
|
2006-01-08 17:02:13 +08:00
|
|
|
int generic_cont_expand_simple(struct inode *inode, loff_t size);
|
2005-04-17 06:20:36 +08:00
|
|
|
int block_commit_write(struct page *page, unsigned from, unsigned to);
|
2007-07-19 15:39:55 +08:00
|
|
|
int block_page_mkwrite(struct vm_area_struct *vma, struct page *page,
|
|
|
|
|
get_block_t get_block);
|
2006-03-26 17:37:17 +08:00
|
|
|
void block_sync_page(struct page *);
|
2005-04-17 06:20:36 +08:00
|
|
|
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 file_fsync(struct file *, struct dentry *, int);
|
2007-10-16 16:25:25 +08:00
|
|
|
int nobh_write_begin(struct file *, 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 *);
|
2005-04-17 06:20:36 +08:00
|
|
|
int nobh_writepage(struct page *page, get_block_t *get_block,
|
|
|
|
|
struct writeback_control *wbc);
|
|
|
|
|
|
2006-06-27 17:53:54 +08:00
|
|
|
void buffer_init(void);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* inline definitions
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
static inline void attach_page_buffers(struct page *page,
|
|
|
|
|
struct buffer_head *head)
|
|
|
|
|
{
|
|
|
|
|
page_cache_get(page);
|
|
|
|
|
SetPagePrivate(page);
|
[PATCH] mm: split page table lock
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>
2005-10-30 09:16:40 +08:00
|
|
|
set_page_private(page, (unsigned long)head);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
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;
|
2006-03-26 17:38:00 +08:00
|
|
|
bh->b_size = sb->s_blocksize;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* 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);
|
|
|
|
|
}
|
|
|
|
|
|
2008-08-02 18:02:13 +08:00
|
|
|
static inline int trylock_buffer(struct buffer_head *bh)
|
|
|
|
|
{
|
|
|
|
|
return likely(!test_and_set_bit(BH_Lock, &bh->b_state));
|
|
|
|
|
}
|
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
static inline void lock_buffer(struct buffer_head *bh)
|
|
|
|
|
{
|
|
|
|
|
might_sleep();
|
2008-08-02 18:02:13 +08:00
|
|
|
if (!trylock_buffer(bh))
|
2005-04-17 06:20:36 +08:00
|
|
|
__lock_buffer(bh);
|
|
|
|
|
}
|
|
|
|
|
|
2006-08-30 02:05:54 +08:00
|
|
|
extern int __set_page_dirty_buffers(struct page *page);
|
[PATCH] BLOCK: Make it possible to disable the block layer [try #6]
Make it possible to disable the block layer. Not all embedded devices require
it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require
the block layer to be present.
This patch does the following:
(*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev
support.
(*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls
an item that uses the block layer. This includes:
(*) Block I/O tracing.
(*) Disk partition code.
(*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS.
(*) The SCSI layer. As far as I can tell, even SCSI chardevs use the
block layer to do scheduling. Some drivers that use SCSI facilities -
such as USB storage - end up disabled indirectly from this.
(*) Various block-based device drivers, such as IDE and the old CDROM
drivers.
(*) MTD blockdev handling and FTL.
(*) JFFS - which uses set_bdev_super(), something it could avoid doing by
taking a leaf out of JFFS2's book.
(*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and
linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is,
however, still used in places, and so is still available.
(*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and
parts of linux/fs.h.
(*) Makes a number of files in fs/ contingent on CONFIG_BLOCK.
(*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK.
(*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK
is not enabled.
(*) fs/no-block.c is created to hold out-of-line stubs and things that are
required when CONFIG_BLOCK is not set:
(*) Default blockdev file operations (to give error ENODEV on opening).
(*) Makes some /proc changes:
(*) /proc/devices does not list any blockdevs.
(*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK.
(*) Makes some compat ioctl handling contingent on CONFIG_BLOCK.
(*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if
given command other than Q_SYNC or if a special device is specified.
(*) In init/do_mounts.c, no reference is made to the blockdev routines if
CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2.
(*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return
error ENOSYS by way of cond_syscall if so).
(*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if
CONFIG_BLOCK is not set, since they can't then happen.
Signed-Off-By: David Howells <dhowells@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 02:45:40 +08:00
|
|
|
|
|
|
|
|
#else /* CONFIG_BLOCK */
|
|
|
|
|
|
|
|
|
|
static inline void buffer_init(void) {}
|
|
|
|
|
static inline int try_to_free_buffers(struct page *page) { return 1; }
|
|
|
|
|
static inline int sync_blockdev(struct block_device *bdev) { return 0; }
|
|
|
|
|
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; }
|
2007-05-07 05:49:54 +08:00
|
|
|
static inline void invalidate_bdev(struct block_device *bdev) {}
|
[PATCH] BLOCK: Make it possible to disable the block layer [try #6]
Make it possible to disable the block layer. Not all embedded devices require
it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require
the block layer to be present.
This patch does the following:
(*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev
support.
(*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls
an item that uses the block layer. This includes:
(*) Block I/O tracing.
(*) Disk partition code.
(*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS.
(*) The SCSI layer. As far as I can tell, even SCSI chardevs use the
block layer to do scheduling. Some drivers that use SCSI facilities -
such as USB storage - end up disabled indirectly from this.
(*) Various block-based device drivers, such as IDE and the old CDROM
drivers.
(*) MTD blockdev handling and FTL.
(*) JFFS - which uses set_bdev_super(), something it could avoid doing by
taking a leaf out of JFFS2's book.
(*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and
linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is,
however, still used in places, and so is still available.
(*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and
parts of linux/fs.h.
(*) Makes a number of files in fs/ contingent on CONFIG_BLOCK.
(*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK.
(*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK
is not enabled.
(*) fs/no-block.c is created to hold out-of-line stubs and things that are
required when CONFIG_BLOCK is not set:
(*) Default blockdev file operations (to give error ENODEV on opening).
(*) Makes some /proc changes:
(*) /proc/devices does not list any blockdevs.
(*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK.
(*) Makes some compat ioctl handling contingent on CONFIG_BLOCK.
(*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if
given command other than Q_SYNC or if a special device is specified.
(*) In init/do_mounts.c, no reference is made to the blockdev routines if
CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2.
(*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return
error ENOSYS by way of cond_syscall if so).
(*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if
CONFIG_BLOCK is not set, since they can't then happen.
Signed-Off-By: David Howells <dhowells@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 02:45:40 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
#endif /* CONFIG_BLOCK */
|
2005-04-17 06:20:36 +08:00
|
|
|
#endif /* _LINUX_BUFFER_HEAD_H */
|