| 
									
										
										
										
											2005-04-16 15:20:36 -07:00
										 |  |  | /*
 | 
					
						
							|  |  |  |  *  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>
 | 
					
						
							|  |  |  | 
 | 
					
						
							| 
									
										
										
										
											2005-10-07 07:46:04 +01:00
										 |  |  | static struct bio *get_swap_bio(gfp_t gfp_flags, pgoff_t index, | 
					
						
							| 
									
										
										
										
											2005-04-16 15:20:36 -07:00
										 |  |  | 				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; | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							| 
									
										
										
										
											2007-09-27 12:47:43 +02:00
										 |  |  | static void end_swap_bio_write(struct bio *bio, int err) | 
					
						
							| 
									
										
										
										
											2005-04-16 15:20:36 -07:00
										 |  |  | { | 
					
						
							|  |  |  | 	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); | 
					
						
							|  |  |  | 	struct page *page = bio->bi_io_vec[0].bv_page; | 
					
						
							|  |  |  | 
 | 
					
						
							| 
									
										
										
										
											2006-09-25 23:31:26 -07:00
										 |  |  | 	if (!uptodate) { | 
					
						
							| 
									
										
										
										
											2005-04-16 15:20:36 -07:00
										 |  |  | 		SetPageError(page); | 
					
						
							| 
									
										
										
										
											2006-09-25 23:31:26 -07:00
										 |  |  | 		/*
 | 
					
						
							|  |  |  | 		 * We failed to write the page out to swap-space. | 
					
						
							|  |  |  | 		 * Re-dirty the page in order to avoid it being reclaimed. | 
					
						
							|  |  |  | 		 * Also print a dire warning that things will go BAD (tm) | 
					
						
							|  |  |  | 		 * very quickly. | 
					
						
							|  |  |  | 		 * | 
					
						
							|  |  |  | 		 * Also clear PG_reclaim to avoid rotate_reclaimable_page() | 
					
						
							|  |  |  | 		 */ | 
					
						
							|  |  |  | 		set_page_dirty(page); | 
					
						
							|  |  |  | 		printk(KERN_ALERT "Write-error on swap-device (%u:%u:%Lu)\n", | 
					
						
							|  |  |  | 				imajor(bio->bi_bdev->bd_inode), | 
					
						
							|  |  |  | 				iminor(bio->bi_bdev->bd_inode), | 
					
						
							|  |  |  | 				(unsigned long long)bio->bi_sector); | 
					
						
							|  |  |  | 		ClearPageReclaim(page); | 
					
						
							|  |  |  | 	} | 
					
						
							| 
									
										
										
										
											2005-04-16 15:20:36 -07:00
										 |  |  | 	end_page_writeback(page); | 
					
						
							|  |  |  | 	bio_put(bio); | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							| 
									
										
										
										
											2007-09-27 12:47:43 +02:00
										 |  |  | void end_swap_bio_read(struct bio *bio, int err) | 
					
						
							| 
									
										
										
										
											2005-04-16 15:20:36 -07:00
										 |  |  | { | 
					
						
							|  |  |  | 	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); | 
					
						
							|  |  |  | 	struct page *page = bio->bi_io_vec[0].bv_page; | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | 	if (!uptodate) { | 
					
						
							|  |  |  | 		SetPageError(page); | 
					
						
							|  |  |  | 		ClearPageUptodate(page); | 
					
						
							| 
									
										
										
										
											2006-09-25 23:31:26 -07:00
										 |  |  | 		printk(KERN_ALERT "Read-error on swap-device (%u:%u:%Lu)\n", | 
					
						
							|  |  |  | 				imajor(bio->bi_bdev->bd_inode), | 
					
						
							|  |  |  | 				iminor(bio->bi_bdev->bd_inode), | 
					
						
							|  |  |  | 				(unsigned long long)bio->bi_sector); | 
					
						
							| 
									
										
										
										
											2005-04-16 15:20:36 -07:00
										 |  |  | 	} else { | 
					
						
							|  |  |  | 		SetPageUptodate(page); | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 	unlock_page(page); | 
					
						
							|  |  |  | 	bio_put(bio); | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | /*
 | 
					
						
							|  |  |  |  * 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; | 
					
						
							|  |  |  | 
 | 
					
						
							| 
									
										
										
										
											2009-01-06 14:39:36 -08:00
										 |  |  | 	if (try_to_free_swap(page)) { | 
					
						
							| 
									
										
										
										
											2005-04-16 15:20:36 -07:00
										 |  |  | 		unlock_page(page); | 
					
						
							|  |  |  | 		goto out; | 
					
						
							|  |  |  | 	} | 
					
						
							| 
									
										
											  
											
												[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>
											
										 
											2005-10-29 18:16:40 -07:00
										 |  |  | 	bio = get_swap_bio(GFP_NOIO, page_private(page), page, | 
					
						
							|  |  |  | 				end_swap_bio_write); | 
					
						
							| 
									
										
										
										
											2005-04-16 15:20:36 -07:00
										 |  |  | 	if (bio == NULL) { | 
					
						
							|  |  |  | 		set_page_dirty(page); | 
					
						
							|  |  |  | 		unlock_page(page); | 
					
						
							|  |  |  | 		ret = -ENOMEM; | 
					
						
							|  |  |  | 		goto out; | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 	if (wbc->sync_mode == WB_SYNC_ALL) | 
					
						
							| 
									
										
										
										
											2009-02-16 10:25:40 +01:00
										 |  |  | 		rw |= (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG); | 
					
						
							| 
									
										
										
										
											2006-06-30 01:55:45 -07:00
										 |  |  | 	count_vm_event(PSWPOUT); | 
					
						
							| 
									
										
										
										
											2005-04-16 15:20:36 -07:00
										 |  |  | 	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; | 
					
						
							|  |  |  | 
 | 
					
						
							| 
									
										
										
										
											2009-01-06 14:39:25 -08:00
										 |  |  | 	VM_BUG_ON(!PageLocked(page)); | 
					
						
							|  |  |  | 	VM_BUG_ON(PageUptodate(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>
											
										 
											2005-10-29 18:16:40 -07:00
										 |  |  | 	bio = get_swap_bio(GFP_KERNEL, page_private(page), page, | 
					
						
							|  |  |  | 				end_swap_bio_read); | 
					
						
							| 
									
										
										
										
											2005-04-16 15:20:36 -07:00
										 |  |  | 	if (bio == NULL) { | 
					
						
							|  |  |  | 		unlock_page(page); | 
					
						
							|  |  |  | 		ret = -ENOMEM; | 
					
						
							|  |  |  | 		goto out; | 
					
						
							|  |  |  | 	} | 
					
						
							| 
									
										
										
										
											2006-06-30 01:55:45 -07:00
										 |  |  | 	count_vm_event(PSWPIN); | 
					
						
							| 
									
										
										
										
											2005-04-16 15:20:36 -07:00
										 |  |  | 	submit_bio(READ, bio); | 
					
						
							|  |  |  | out: | 
					
						
							|  |  |  | 	return ret; | 
					
						
							|  |  |  | } |