mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-11-26 13:44:15 +08:00
f8891e5e1f
The remaining counters in page_state after the zoned VM counter patches have been applied are all just for show in /proc/vmstat. They have no essential function for the VM. We use a simple increment of per cpu variables. In order to avoid the most severe races we disable preempt. Preempt does not prevent the race between an increment and an interrupt handler incrementing the same statistics counter. However, that race is exceedingly rare, we may only loose one increment or so and there is no requirement (at least not in kernel) that the vm event counters have to be accurate. In the non preempt case this results in a simple increment for each counter. For many architectures this will be reduced by the compiler to a single instruction. This single instruction is atomic for i386 and x86_64. And therefore even the rare race condition in an interrupt is avoided for both architectures in most cases. The patchset also adds an off switch for embedded systems that allows a building of linux kernels without these counters. The implementation of these counters is through inline code that hopefully results in only a single instruction increment instruction being emitted (i386, x86_64) or in the increment being hidden though instruction concurrency (EPIC architectures such as ia64 can get that done). Benefits: - VM event counter operations usually reduce to a single inline instruction on i386 and x86_64. - No interrupt disable, only preempt disable for the preempt case. Preempt disable can also be avoided by moving the counter into a spinlock. - Handling is similar to zoned VM counters. - Simple and easily extendable. - Can be omitted to reduce memory use for embedded use. References: RFC http://marc.theaimsgroup.com/?l=linux-kernel&m=113512330605497&w=2 RFC http://marc.theaimsgroup.com/?l=linux-kernel&m=114988082814934&w=2 local_t http://marc.theaimsgroup.com/?l=linux-kernel&m=114991748606690&w=2 V2 http://marc.theaimsgroup.com/?t=115014808400007&r=1&w=2 V3 http://marc.theaimsgroup.com/?l=linux-kernel&m=115024767022346&w=2 V4 http://marc.theaimsgroup.com/?l=linux-kernel&m=115047968808926&w=2 Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
163 lines
3.6 KiB
C
163 lines
3.6 KiB
C
/*
|
|
* linux/mm/page_io.c
|
|
*
|
|
* Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
|
|
*
|
|
* Swap reorganised 29.12.95,
|
|
* Asynchronous swapping added 30.12.95. Stephen Tweedie
|
|
* Removed race in async swapping. 14.4.1996. Bruno Haible
|
|
* Add swap of shared pages through the page cache. 20.2.1998. Stephen Tweedie
|
|
* Always use brw_page, life becomes simpler. 12 May 1998 Eric Biederman
|
|
*/
|
|
|
|
#include <linux/mm.h>
|
|
#include <linux/kernel_stat.h>
|
|
#include <linux/pagemap.h>
|
|
#include <linux/swap.h>
|
|
#include <linux/bio.h>
|
|
#include <linux/swapops.h>
|
|
#include <linux/writeback.h>
|
|
#include <asm/pgtable.h>
|
|
|
|
static struct bio *get_swap_bio(gfp_t gfp_flags, pgoff_t index,
|
|
struct page *page, bio_end_io_t end_io)
|
|
{
|
|
struct bio *bio;
|
|
|
|
bio = bio_alloc(gfp_flags, 1);
|
|
if (bio) {
|
|
struct swap_info_struct *sis;
|
|
swp_entry_t entry = { .val = index, };
|
|
|
|
sis = get_swap_info_struct(swp_type(entry));
|
|
bio->bi_sector = map_swap_page(sis, swp_offset(entry)) *
|
|
(PAGE_SIZE >> 9);
|
|
bio->bi_bdev = sis->bdev;
|
|
bio->bi_io_vec[0].bv_page = page;
|
|
bio->bi_io_vec[0].bv_len = PAGE_SIZE;
|
|
bio->bi_io_vec[0].bv_offset = 0;
|
|
bio->bi_vcnt = 1;
|
|
bio->bi_idx = 0;
|
|
bio->bi_size = PAGE_SIZE;
|
|
bio->bi_end_io = end_io;
|
|
}
|
|
return bio;
|
|
}
|
|
|
|
static int end_swap_bio_write(struct bio *bio, unsigned int bytes_done, int err)
|
|
{
|
|
const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
|
|
struct page *page = bio->bi_io_vec[0].bv_page;
|
|
|
|
if (bio->bi_size)
|
|
return 1;
|
|
|
|
if (!uptodate)
|
|
SetPageError(page);
|
|
end_page_writeback(page);
|
|
bio_put(bio);
|
|
return 0;
|
|
}
|
|
|
|
static int end_swap_bio_read(struct bio *bio, unsigned int bytes_done, int err)
|
|
{
|
|
const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
|
|
struct page *page = bio->bi_io_vec[0].bv_page;
|
|
|
|
if (bio->bi_size)
|
|
return 1;
|
|
|
|
if (!uptodate) {
|
|
SetPageError(page);
|
|
ClearPageUptodate(page);
|
|
} else {
|
|
SetPageUptodate(page);
|
|
}
|
|
unlock_page(page);
|
|
bio_put(bio);
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* We may have stale swap cache pages in memory: notice
|
|
* them here and get rid of the unnecessary final write.
|
|
*/
|
|
int swap_writepage(struct page *page, struct writeback_control *wbc)
|
|
{
|
|
struct bio *bio;
|
|
int ret = 0, rw = WRITE;
|
|
|
|
if (remove_exclusive_swap_page(page)) {
|
|
unlock_page(page);
|
|
goto out;
|
|
}
|
|
bio = get_swap_bio(GFP_NOIO, page_private(page), page,
|
|
end_swap_bio_write);
|
|
if (bio == NULL) {
|
|
set_page_dirty(page);
|
|
unlock_page(page);
|
|
ret = -ENOMEM;
|
|
goto out;
|
|
}
|
|
if (wbc->sync_mode == WB_SYNC_ALL)
|
|
rw |= (1 << BIO_RW_SYNC);
|
|
count_vm_event(PSWPOUT);
|
|
set_page_writeback(page);
|
|
unlock_page(page);
|
|
submit_bio(rw, bio);
|
|
out:
|
|
return ret;
|
|
}
|
|
|
|
int swap_readpage(struct file *file, struct page *page)
|
|
{
|
|
struct bio *bio;
|
|
int ret = 0;
|
|
|
|
BUG_ON(!PageLocked(page));
|
|
ClearPageUptodate(page);
|
|
bio = get_swap_bio(GFP_KERNEL, page_private(page), page,
|
|
end_swap_bio_read);
|
|
if (bio == NULL) {
|
|
unlock_page(page);
|
|
ret = -ENOMEM;
|
|
goto out;
|
|
}
|
|
count_vm_event(PSWPIN);
|
|
submit_bio(READ, bio);
|
|
out:
|
|
return ret;
|
|
}
|
|
|
|
#ifdef CONFIG_SOFTWARE_SUSPEND
|
|
/*
|
|
* A scruffy utility function to read or write an arbitrary swap page
|
|
* and wait on the I/O. The caller must have a ref on the page.
|
|
*
|
|
* We use end_swap_bio_read() even for writes, because it happens to do what
|
|
* we want.
|
|
*/
|
|
int rw_swap_page_sync(int rw, swp_entry_t entry, struct page *page)
|
|
{
|
|
struct bio *bio;
|
|
int ret = 0;
|
|
|
|
lock_page(page);
|
|
|
|
bio = get_swap_bio(GFP_KERNEL, entry.val, page, end_swap_bio_read);
|
|
if (bio == NULL) {
|
|
unlock_page(page);
|
|
ret = -ENOMEM;
|
|
goto out;
|
|
}
|
|
|
|
submit_bio(rw | (1 << BIO_RW_SYNC), bio);
|
|
wait_on_page_locked(page);
|
|
|
|
if (!PageUptodate(page) || PageError(page))
|
|
ret = -EIO;
|
|
out:
|
|
return ret;
|
|
}
|
|
#endif
|