linux/mm/rmap.c

824 lines
22 KiB
C
Raw Normal View History

/*
* mm/rmap.c - physical to virtual reverse mappings
*
* Copyright 2001, Rik van Riel <riel@conectiva.com.br>
* Released under the General Public License (GPL).
*
* Simple, low overhead reverse mapping scheme.
* Please try to keep this thing as modular as possible.
*
* Provides methods for unmapping each kind of mapped page:
* the anon methods track anonymous pages, and
* the file methods track pages belonging to an inode.
*
* Original design by Rik van Riel <riel@conectiva.com.br> 2001
* File methods by Dave McCracken <dmccr@us.ibm.com> 2003, 2004
* Anonymous methods by Andrea Arcangeli <andrea@suse.de> 2004
* Contributions by Hugh Dickins <hugh@veritas.com> 2003, 2004
*/
/*
* Lock ordering in mm:
*
* inode->i_sem (while writing or truncating, not reading or faulting)
* inode->i_alloc_sem
*
* When a page fault occurs in writing from user to file, down_read
* of mmap_sem nests within i_sem; in sys_msync, i_sem nests within
* down_read of mmap_sem; i_sem and down_write of mmap_sem are never
* taken together; in truncation, i_sem is taken outermost.
*
* mm->mmap_sem
* page->flags PG_locked (lock_page)
* mapping->i_mmap_lock
* anon_vma->lock
* mm->page_table_lock
* zone->lru_lock (in mark_page_accessed)
* swap_lock (in swap_duplicate, swap_info_get)
* mmlist_lock (in mmput, drain_mmlist and others)
* mapping->private_lock (in __set_page_dirty_buffers)
* inode_lock (in set_page_dirty's __mark_inode_dirty)
* sb_lock (within inode_lock in fs/fs-writeback.c)
* mapping->tree_lock (widely used, in set_page_dirty,
* in arch-dependent flush_dcache_mmap_lock,
* within inode_lock in __sync_single_inode)
*/
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/rmap.h>
#include <linux/rcupdate.h>
#include <asm/tlbflush.h>
//#define RMAP_DEBUG /* can be enabled only for debugging */
kmem_cache_t *anon_vma_cachep;
static inline void validate_anon_vma(struct vm_area_struct *find_vma)
{
#ifdef RMAP_DEBUG
struct anon_vma *anon_vma = find_vma->anon_vma;
struct vm_area_struct *vma;
unsigned int mapcount = 0;
int found = 0;
list_for_each_entry(vma, &anon_vma->head, anon_vma_node) {
mapcount++;
BUG_ON(mapcount > 100000);
if (vma == find_vma)
found = 1;
}
BUG_ON(!found);
#endif
}
/* This must be called under the mmap_sem. */
int anon_vma_prepare(struct vm_area_struct *vma)
{
struct anon_vma *anon_vma = vma->anon_vma;
might_sleep();
if (unlikely(!anon_vma)) {
struct mm_struct *mm = vma->vm_mm;
struct anon_vma *allocated, *locked;
anon_vma = find_mergeable_anon_vma(vma);
if (anon_vma) {
allocated = NULL;
locked = anon_vma;
spin_lock(&locked->lock);
} else {
anon_vma = anon_vma_alloc();
if (unlikely(!anon_vma))
return -ENOMEM;
allocated = anon_vma;
locked = NULL;
}
/* page_table_lock to protect against threads */
spin_lock(&mm->page_table_lock);
if (likely(!vma->anon_vma)) {
vma->anon_vma = anon_vma;
list_add(&vma->anon_vma_node, &anon_vma->head);
allocated = NULL;
}
spin_unlock(&mm->page_table_lock);
if (locked)
spin_unlock(&locked->lock);
if (unlikely(allocated))
anon_vma_free(allocated);
}
return 0;
}
void __anon_vma_merge(struct vm_area_struct *vma, struct vm_area_struct *next)
{
BUG_ON(vma->anon_vma != next->anon_vma);
list_del(&next->anon_vma_node);
}
void __anon_vma_link(struct vm_area_struct *vma)
{
struct anon_vma *anon_vma = vma->anon_vma;
if (anon_vma) {
list_add(&vma->anon_vma_node, &anon_vma->head);
validate_anon_vma(vma);
}
}
void anon_vma_link(struct vm_area_struct *vma)
{
struct anon_vma *anon_vma = vma->anon_vma;
if (anon_vma) {
spin_lock(&anon_vma->lock);
list_add(&vma->anon_vma_node, &anon_vma->head);
validate_anon_vma(vma);
spin_unlock(&anon_vma->lock);
}
}
void anon_vma_unlink(struct vm_area_struct *vma)
{
struct anon_vma *anon_vma = vma->anon_vma;
int empty;
if (!anon_vma)
return;
spin_lock(&anon_vma->lock);
validate_anon_vma(vma);
list_del(&vma->anon_vma_node);
/* We must garbage collect the anon_vma if it's empty */
empty = list_empty(&anon_vma->head);
spin_unlock(&anon_vma->lock);
if (empty)
anon_vma_free(anon_vma);
}
static void anon_vma_ctor(void *data, kmem_cache_t *cachep, unsigned long flags)
{
if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) ==
SLAB_CTOR_CONSTRUCTOR) {
struct anon_vma *anon_vma = data;
spin_lock_init(&anon_vma->lock);
INIT_LIST_HEAD(&anon_vma->head);
}
}
void __init anon_vma_init(void)
{
anon_vma_cachep = kmem_cache_create("anon_vma", sizeof(struct anon_vma),
0, SLAB_DESTROY_BY_RCU|SLAB_PANIC, anon_vma_ctor, NULL);
}
/*
* Getting a lock on a stable anon_vma from a page off the LRU is
* tricky: page_lock_anon_vma rely on RCU to guard against the races.
*/
static struct anon_vma *page_lock_anon_vma(struct page *page)
{
struct anon_vma *anon_vma = NULL;
unsigned long anon_mapping;
rcu_read_lock();
anon_mapping = (unsigned long) page->mapping;
if (!(anon_mapping & PAGE_MAPPING_ANON))
goto out;
if (!page_mapped(page))
goto out;
anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON);
spin_lock(&anon_vma->lock);
out:
rcu_read_unlock();
return anon_vma;
}
/*
* At what user virtual address is page expected in vma?
*/
static inline unsigned long
vma_address(struct page *page, struct vm_area_struct *vma)
{
pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
unsigned long address;
address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
if (unlikely(address < vma->vm_start || address >= vma->vm_end)) {
/* page should be within any vma from prio_tree_next */
BUG_ON(!PageAnon(page));
return -EFAULT;
}
return address;
}
/*
* At what user virtual address is page expected in vma? checking that the
* page matches the vma: currently only used by unuse_process, on anon pages.
*/
unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma)
{
if (PageAnon(page)) {
if ((void *)vma->anon_vma !=
(void *)page->mapping - PAGE_MAPPING_ANON)
return -EFAULT;
} else if (page->mapping && !(vma->vm_flags & VM_NONLINEAR)) {
if (vma->vm_file->f_mapping != page->mapping)
return -EFAULT;
} else
return -EFAULT;
return vma_address(page, vma);
}
/*
* Check that @page is mapped at @address into @mm.
*
* On success returns with mapped pte and locked mm->page_table_lock.
*/
pte_t *page_check_address(struct page *page, struct mm_struct *mm,
unsigned long address)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
/*
* We need the page_table_lock to protect us from page faults,
* munmap, fork, etc...
*/
spin_lock(&mm->page_table_lock);
pgd = pgd_offset(mm, address);
if (likely(pgd_present(*pgd))) {
pud = pud_offset(pgd, address);
if (likely(pud_present(*pud))) {
pmd = pmd_offset(pud, address);
if (likely(pmd_present(*pmd))) {
pte = pte_offset_map(pmd, address);
if (likely(pte_present(*pte) &&
page_to_pfn(page) == pte_pfn(*pte)))
return pte;
pte_unmap(pte);
}
}
}
spin_unlock(&mm->page_table_lock);
return ERR_PTR(-ENOENT);
}
/*
* Subfunctions of page_referenced: page_referenced_one called
* repeatedly from either page_referenced_anon or page_referenced_file.
*/
static int page_referenced_one(struct page *page,
struct vm_area_struct *vma, unsigned int *mapcount, int ignore_token)
{
struct mm_struct *mm = vma->vm_mm;
unsigned long address;
pte_t *pte;
int referenced = 0;
address = vma_address(page, vma);
if (address == -EFAULT)
goto out;
pte = page_check_address(page, mm, address);
if (!IS_ERR(pte)) {
if (ptep_clear_flush_young(vma, address, pte))
referenced++;
[PATCH] swaptoken tuning It turns out that the original swap token implementation, by Song Jiang, only enforced the swap token while the task holding the token is handling a page fault. This patch approximates that, without adding an additional flag to the mm_struct, by checking whether the mm->mmap_sem is held for reading, like the page fault code does. This patch has the effect of automatically, and gradually, disabling the enforcement of the swap token when there is little or no paging going on, and "turning up" the intensity of the swap token code the more the task holding the token is thrashing. Thanks to Song Jiang for pointing out this aspect of the token based thrashing control concept. The new code shows a slight degradation over the old swap token code, but still a big win over running without the swap token. 2.6.12+ swap token disabled $ for i in `seq 10` ; do /usr/bin/time ./qsbench -n 30000000 -p 3 ; done 101.74user 23.13system 8:26.91elapsed 24%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+0outputs (38597major+430315minor)pagefaults 0swaps 101.98user 24.91system 8:03.06elapsed 26%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+0outputs (33939major+430457minor)pagefaults 0swaps 101.93user 22.12system 7:34.90elapsed 27%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+0outputs (33166major+421267minor)pagefaults 0swaps 101.82user 22.38system 8:31.40elapsed 24%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+0outputs (39338major+433262minor)pagefaults 0swaps 2.6.12+ swap token enabled, timeout 300 seconds $ for i in `seq 4` ; do /usr/bin/time ./qsbench -n 30000000 -p 3 ; done 102.58user 16.08system 3:41.44elapsed 53%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+0outputs (19707major+285786minor)pagefaults 0swaps 102.07user 19.56system 4:00.64elapsed 50%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+0outputs (19012major+299259minor)pagefaults 0swaps 102.64user 18.25system 4:07.31elapsed 48%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+0outputs (21990major+304831minor)pagefaults 0swaps 101.39user 19.41system 5:15.81elapsed 38%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+0outputs (24850major+323321minor)pagefaults 0swaps 2.6.12+ with new swap token code, timeout 300 seconds $ for i in `seq 4` ; do /usr/bin/time ./qsbench -n 30000000 -p 3 ; done 101.87user 24.66system 5:53.20elapsed 35%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+0outputs (26848major+363497minor)pagefaults 0swaps 102.83user 19.95system 4:17.25elapsed 47%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+0outputs (19946major+305722minor)pagefaults 0swaps 102.09user 19.46system 5:12.57elapsed 38%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+0outputs (25461major+334994minor)pagefaults 0swaps 101.67user 20.61system 4:52.97elapsed 41%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+0outputs (22190major+329508minor)pagefaults 0swaps Signed-off-by: Rik Van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-30 01:15:46 +00:00
/* Pretend the page is referenced if the task has the
swap token and is in the middle of a page fault. */
if (mm != current->mm && !ignore_token &&
has_swap_token(mm) &&
rwsem_is_locked(&mm->mmap_sem))
referenced++;
(*mapcount)--;
pte_unmap(pte);
spin_unlock(&mm->page_table_lock);
}
out:
return referenced;
}
static int page_referenced_anon(struct page *page, int ignore_token)
{
unsigned int mapcount;
struct anon_vma *anon_vma;
struct vm_area_struct *vma;
int referenced = 0;
anon_vma = page_lock_anon_vma(page);
if (!anon_vma)
return referenced;
mapcount = page_mapcount(page);
list_for_each_entry(vma, &anon_vma->head, anon_vma_node) {
referenced += page_referenced_one(page, vma, &mapcount,
ignore_token);
if (!mapcount)
break;
}
spin_unlock(&anon_vma->lock);
return referenced;
}
/**
* page_referenced_file - referenced check for object-based rmap
* @page: the page we're checking references on.
*
* For an object-based mapped page, find all the places it is mapped and
* check/clear the referenced flag. This is done by following the page->mapping
* pointer, then walking the chain of vmas it holds. It returns the number
* of references it found.
*
* This function is only called from page_referenced for object-based pages.
*/
static int page_referenced_file(struct page *page, int ignore_token)
{
unsigned int mapcount;
struct address_space *mapping = page->mapping;
pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
struct vm_area_struct *vma;
struct prio_tree_iter iter;
int referenced = 0;
/*
* The caller's checks on page->mapping and !PageAnon have made
* sure that this is a file page: the check for page->mapping
* excludes the case just before it gets set on an anon page.
*/
BUG_ON(PageAnon(page));
/*
* The page lock not only makes sure that page->mapping cannot
* suddenly be NULLified by truncation, it makes sure that the
* structure at mapping cannot be freed and reused yet,
* so we can safely take mapping->i_mmap_lock.
*/
BUG_ON(!PageLocked(page));
spin_lock(&mapping->i_mmap_lock);
/*
* i_mmap_lock does not stabilize mapcount at all, but mapcount
* is more likely to be accurate if we note it after spinning.
*/
mapcount = page_mapcount(page);
vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
if ((vma->vm_flags & (VM_LOCKED|VM_MAYSHARE))
== (VM_LOCKED|VM_MAYSHARE)) {
referenced++;
break;
}
referenced += page_referenced_one(page, vma, &mapcount,
ignore_token);
if (!mapcount)
break;
}
spin_unlock(&mapping->i_mmap_lock);
return referenced;
}
/**
* page_referenced - test if the page was referenced
* @page: the page to test
* @is_locked: caller holds lock on the page
*
* Quick test_and_clear_referenced for all mappings to a page,
* returns the number of ptes which referenced the page.
*/
int page_referenced(struct page *page, int is_locked, int ignore_token)
{
int referenced = 0;
if (!swap_token_default_timeout)
ignore_token = 1;
if (page_test_and_clear_young(page))
referenced++;
if (TestClearPageReferenced(page))
referenced++;
if (page_mapped(page) && page->mapping) {
if (PageAnon(page))
referenced += page_referenced_anon(page, ignore_token);
else if (is_locked)
referenced += page_referenced_file(page, ignore_token);
else if (TestSetPageLocked(page))
referenced++;
else {
if (page->mapping)
referenced += page_referenced_file(page,
ignore_token);
unlock_page(page);
}
}
return referenced;
}
/**
* page_add_anon_rmap - add pte mapping to an anonymous page
* @page: the page to add the mapping to
* @vma: the vm area in which the mapping is added
* @address: the user virtual address mapped
*
* The caller needs to hold the mm->page_table_lock.
*/
void page_add_anon_rmap(struct page *page,
struct vm_area_struct *vma, unsigned long address)
{
if (atomic_inc_and_test(&page->_mapcount)) {
struct anon_vma *anon_vma = vma->anon_vma;
BUG_ON(!anon_vma);
anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON;
page->mapping = (struct address_space *) anon_vma;
page->index = linear_page_index(vma, address);
inc_page_state(nr_mapped);
}
/* else checking page index and mapping is racy */
}
/**
* page_add_file_rmap - add pte mapping to a file page
* @page: the page to add the mapping to
*
* The caller needs to hold the mm->page_table_lock.
*/
void page_add_file_rmap(struct page *page)
{
BUG_ON(PageAnon(page));
2005-10-30 01:16:12 +00:00
BUG_ON(!pfn_valid(page_to_pfn(page)));
if (atomic_inc_and_test(&page->_mapcount))
inc_page_state(nr_mapped);
}
/**
* page_remove_rmap - take down pte mapping from a page
* @page: page to remove mapping from
*
* Caller needs to hold the mm->page_table_lock.
*/
void page_remove_rmap(struct page *page)
{
if (atomic_add_negative(-1, &page->_mapcount)) {
BUG_ON(page_mapcount(page) < 0);
/*
* It would be tidy to reset the PageAnon mapping here,
* but that might overwrite a racing page_add_anon_rmap
* which increments mapcount after us but sets mapping
* before us: so leave the reset to free_hot_cold_page,
* and remember that it's only reliable while mapped.
* Leaving it set also helps swapoff to reinstate ptes
* faster for those pages still in swapcache.
*/
if (page_test_and_clear_dirty(page))
set_page_dirty(page);
dec_page_state(nr_mapped);
}
}
/*
* Subfunctions of try_to_unmap: try_to_unmap_one called
* repeatedly from either try_to_unmap_anon or try_to_unmap_file.
*/
static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma)
{
struct mm_struct *mm = vma->vm_mm;
unsigned long address;
pte_t *pte;
pte_t pteval;
int ret = SWAP_AGAIN;
address = vma_address(page, vma);
if (address == -EFAULT)
goto out;
pte = page_check_address(page, mm, address);
if (IS_ERR(pte))
goto out;
/*
* If the page is mlock()d, we cannot swap it out.
* If it's recently referenced (perhaps page_referenced
* skipped over this mm) then we should reactivate it.
*
* Pages belonging to VM_RESERVED regions should not happen here.
*/
if ((vma->vm_flags & (VM_LOCKED|VM_RESERVED)) ||
ptep_clear_flush_young(vma, address, pte)) {
ret = SWAP_FAIL;
goto out_unmap;
}
/* Nuke the page table entry. */
flush_cache_page(vma, address, page_to_pfn(page));
pteval = ptep_clear_flush(vma, address, pte);
/* Move the dirty bit to the physical page now the pte is gone. */
if (pte_dirty(pteval))
set_page_dirty(page);
[PATCH] mm: update_hiwaters just in time update_mem_hiwater has attracted various criticisms, in particular from those concerned with mm scalability. Originally it was called whenever rss or total_vm got raised. Then many of those callsites were replaced by a timer tick call from account_system_time. Now Frank van Maarseveen reports that to be found inadequate. How about this? Works for Frank. Replace update_mem_hiwater, a poor combination of two unrelated ops, by macros update_hiwater_rss and update_hiwater_vm. Don't attempt to keep mm->hiwater_rss up to date at timer tick, nor every time we raise rss (usually by 1): those are hot paths. Do the opposite, update only when about to lower rss (usually by many), or just before final accounting in do_exit. Handle mm->hiwater_vm in the same way, though it's much less of an issue. Demand that whoever collects these hiwater statistics do the work of taking the maximum with rss or total_vm. And there has been no collector of these hiwater statistics in the tree. The new convention needs an example, so match Frank's usage by adding a VmPeak line above VmSize to /proc/<pid>/status, and also a VmHWM line above VmRSS (High-Water-Mark or High-Water-Memory). There was a particular anomaly during mremap move, that hiwater_vm might be captured too high. A fleeting such anomaly remains, but it's quickly corrected now, whereas before it would stick. What locking? None: if the app is racy then these statistics will be racy, it's not worth any overhead to make them exact. But whenever it suits, hiwater_vm is updated under exclusive mmap_sem, and hiwater_rss under page_table_lock (for now) or with preemption disabled (later on): without going to any trouble, minimize the time between reading current values and updating, to minimize those occasions when a racing thread bumps a count up and back down in between. 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 01:16:18 +00:00
/* Update high watermark before we lower rss */
update_hiwater_rss(mm);
if (PageAnon(page)) {
swp_entry_t entry = { .val = page->private };
/*
* Store the swap location in the pte.
* See handle_pte_fault() ...
*/
BUG_ON(!PageSwapCache(page));
swap_duplicate(entry);
if (list_empty(&mm->mmlist)) {
spin_lock(&mmlist_lock);
list_add(&mm->mmlist, &init_mm.mmlist);
spin_unlock(&mmlist_lock);
}
set_pte_at(mm, address, pte, swp_entry_to_pte(entry));
BUG_ON(pte_file(*pte));
dec_mm_counter(mm, anon_rss);
} else
dec_mm_counter(mm, file_rss);
page_remove_rmap(page);
page_cache_release(page);
out_unmap:
pte_unmap(pte);
spin_unlock(&mm->page_table_lock);
out:
return ret;
}
/*
* objrmap doesn't work for nonlinear VMAs because the assumption that
* offset-into-file correlates with offset-into-virtual-addresses does not hold.
* Consequently, given a particular page and its ->index, we cannot locate the
* ptes which are mapping that page without an exhaustive linear search.
*
* So what this code does is a mini "virtual scan" of each nonlinear VMA which
* maps the file to which the target page belongs. The ->vm_private_data field
* holds the current cursor into that scan. Successive searches will circulate
* around the vma's virtual address space.
*
* So as more replacement pressure is applied to the pages in a nonlinear VMA,
* more scanning pressure is placed against them as well. Eventually pages
* will become fully unmapped and are eligible for eviction.
*
* For very sparsely populated VMAs this is a little inefficient - chances are
* there there won't be many ptes located within the scan cluster. In this case
* maybe we could scan further - to the end of the pte page, perhaps.
*/
#define CLUSTER_SIZE min(32*PAGE_SIZE, PMD_SIZE)
#define CLUSTER_MASK (~(CLUSTER_SIZE - 1))
static void try_to_unmap_cluster(unsigned long cursor,
unsigned int *mapcount, struct vm_area_struct *vma)
{
struct mm_struct *mm = vma->vm_mm;
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *pte, *original_pte;
pte_t pteval;
struct page *page;
unsigned long address;
unsigned long end;
unsigned long pfn;
/*
* We need the page_table_lock to protect us from page faults,
* munmap, fork, etc...
*/
spin_lock(&mm->page_table_lock);
address = (vma->vm_start + cursor) & CLUSTER_MASK;
end = address + CLUSTER_SIZE;
if (address < vma->vm_start)
address = vma->vm_start;
if (end > vma->vm_end)
end = vma->vm_end;
pgd = pgd_offset(mm, address);
if (!pgd_present(*pgd))
goto out_unlock;
pud = pud_offset(pgd, address);
if (!pud_present(*pud))
goto out_unlock;
pmd = pmd_offset(pud, address);
if (!pmd_present(*pmd))
goto out_unlock;
[PATCH] mm: update_hiwaters just in time update_mem_hiwater has attracted various criticisms, in particular from those concerned with mm scalability. Originally it was called whenever rss or total_vm got raised. Then many of those callsites were replaced by a timer tick call from account_system_time. Now Frank van Maarseveen reports that to be found inadequate. How about this? Works for Frank. Replace update_mem_hiwater, a poor combination of two unrelated ops, by macros update_hiwater_rss and update_hiwater_vm. Don't attempt to keep mm->hiwater_rss up to date at timer tick, nor every time we raise rss (usually by 1): those are hot paths. Do the opposite, update only when about to lower rss (usually by many), or just before final accounting in do_exit. Handle mm->hiwater_vm in the same way, though it's much less of an issue. Demand that whoever collects these hiwater statistics do the work of taking the maximum with rss or total_vm. And there has been no collector of these hiwater statistics in the tree. The new convention needs an example, so match Frank's usage by adding a VmPeak line above VmSize to /proc/<pid>/status, and also a VmHWM line above VmRSS (High-Water-Mark or High-Water-Memory). There was a particular anomaly during mremap move, that hiwater_vm might be captured too high. A fleeting such anomaly remains, but it's quickly corrected now, whereas before it would stick. What locking? None: if the app is racy then these statistics will be racy, it's not worth any overhead to make them exact. But whenever it suits, hiwater_vm is updated under exclusive mmap_sem, and hiwater_rss under page_table_lock (for now) or with preemption disabled (later on): without going to any trouble, minimize the time between reading current values and updating, to minimize those occasions when a racing thread bumps a count up and back down in between. 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 01:16:18 +00:00
/* Update high watermark before we lower rss */
update_hiwater_rss(mm);
for (original_pte = pte = pte_offset_map(pmd, address);
address < end; pte++, address += PAGE_SIZE) {
if (!pte_present(*pte))
continue;
pfn = pte_pfn(*pte);
2005-10-30 01:16:12 +00:00
if (unlikely(!pfn_valid(pfn))) {
print_bad_pte(vma, *pte, address);
continue;
2005-10-30 01:16:12 +00:00
}
page = pfn_to_page(pfn);
BUG_ON(PageAnon(page));
if (ptep_clear_flush_young(vma, address, pte))
continue;
/* Nuke the page table entry. */
flush_cache_page(vma, address, pfn);
pteval = ptep_clear_flush(vma, address, pte);
/* If nonlinear, store the file page offset in the pte. */
if (page->index != linear_page_index(vma, address))
set_pte_at(mm, address, pte, pgoff_to_pte(page->index));
/* Move the dirty bit to the physical page now the pte is gone. */
if (pte_dirty(pteval))
set_page_dirty(page);
page_remove_rmap(page);
page_cache_release(page);
dec_mm_counter(mm, file_rss);
(*mapcount)--;
}
pte_unmap(original_pte);
out_unlock:
spin_unlock(&mm->page_table_lock);
}
static int try_to_unmap_anon(struct page *page)
{
struct anon_vma *anon_vma;
struct vm_area_struct *vma;
int ret = SWAP_AGAIN;
anon_vma = page_lock_anon_vma(page);
if (!anon_vma)
return ret;
list_for_each_entry(vma, &anon_vma->head, anon_vma_node) {
ret = try_to_unmap_one(page, vma);
if (ret == SWAP_FAIL || !page_mapped(page))
break;
}
spin_unlock(&anon_vma->lock);
return ret;
}
/**
* try_to_unmap_file - unmap file page using the object-based rmap method
* @page: the page to unmap
*
* Find all the mappings of a page using the mapping pointer and the vma chains
* contained in the address_space struct it points to.
*
* This function is only called from try_to_unmap for object-based pages.
*/
static int try_to_unmap_file(struct page *page)
{
struct address_space *mapping = page->mapping;
pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
struct vm_area_struct *vma;
struct prio_tree_iter iter;
int ret = SWAP_AGAIN;
unsigned long cursor;
unsigned long max_nl_cursor = 0;
unsigned long max_nl_size = 0;
unsigned int mapcount;
spin_lock(&mapping->i_mmap_lock);
vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
ret = try_to_unmap_one(page, vma);
if (ret == SWAP_FAIL || !page_mapped(page))
goto out;
}
if (list_empty(&mapping->i_mmap_nonlinear))
goto out;
list_for_each_entry(vma, &mapping->i_mmap_nonlinear,
shared.vm_set.list) {
if (vma->vm_flags & (VM_LOCKED|VM_RESERVED))
continue;
cursor = (unsigned long) vma->vm_private_data;
if (cursor > max_nl_cursor)
max_nl_cursor = cursor;
cursor = vma->vm_end - vma->vm_start;
if (cursor > max_nl_size)
max_nl_size = cursor;
}
if (max_nl_size == 0) { /* any nonlinears locked or reserved */
ret = SWAP_FAIL;
goto out;
}
/*
* We don't try to search for this page in the nonlinear vmas,
* and page_referenced wouldn't have found it anyway. Instead
* just walk the nonlinear vmas trying to age and unmap some.
* The mapcount of the page we came in with is irrelevant,
* but even so use it as a guide to how hard we should try?
*/
mapcount = page_mapcount(page);
if (!mapcount)
goto out;
cond_resched_lock(&mapping->i_mmap_lock);
max_nl_size = (max_nl_size + CLUSTER_SIZE - 1) & CLUSTER_MASK;
if (max_nl_cursor == 0)
max_nl_cursor = CLUSTER_SIZE;
do {
list_for_each_entry(vma, &mapping->i_mmap_nonlinear,
shared.vm_set.list) {
if (vma->vm_flags & (VM_LOCKED|VM_RESERVED))
continue;
cursor = (unsigned long) vma->vm_private_data;
while ( cursor < max_nl_cursor &&
cursor < vma->vm_end - vma->vm_start) {
try_to_unmap_cluster(cursor, &mapcount, vma);
cursor += CLUSTER_SIZE;
vma->vm_private_data = (void *) cursor;
if ((int)mapcount <= 0)
goto out;
}
vma->vm_private_data = (void *) max_nl_cursor;
}
cond_resched_lock(&mapping->i_mmap_lock);
max_nl_cursor += CLUSTER_SIZE;
} while (max_nl_cursor <= max_nl_size);
/*
* Don't loop forever (perhaps all the remaining pages are
* in locked vmas). Reset cursor on all unreserved nonlinear
* vmas, now forgetting on which ones it had fallen behind.
*/
list_for_each_entry(vma, &mapping->i_mmap_nonlinear,
shared.vm_set.list) {
if (!(vma->vm_flags & VM_RESERVED))
vma->vm_private_data = NULL;
}
out:
spin_unlock(&mapping->i_mmap_lock);
return ret;
}
/**
* try_to_unmap - try to remove all page table mappings to a page
* @page: the page to get unmapped
*
* Tries to remove all the page table entries which are mapping this
* page, used in the pageout path. Caller must hold the page lock.
* Return values are:
*
* SWAP_SUCCESS - we succeeded in removing all mappings
* SWAP_AGAIN - we missed a mapping, try again later
* SWAP_FAIL - the page is unswappable
*/
int try_to_unmap(struct page *page)
{
int ret;
BUG_ON(!PageLocked(page));
if (PageAnon(page))
ret = try_to_unmap_anon(page);
else
ret = try_to_unmap_file(page);
if (!page_mapped(page))
ret = SWAP_SUCCESS;
return ret;
}