kernel-ark/mm/rmap.c
Andrea Arcangeli cddb8a5c14 mmu-notifiers: core
With KVM/GFP/XPMEM there isn't just the primary CPU MMU pointing to pages.
 There are secondary MMUs (with secondary sptes and secondary tlbs) too.
sptes in the kvm case are shadow pagetables, but when I say spte in
mmu-notifier context, I mean "secondary pte".  In GRU case there's no
actual secondary pte and there's only a secondary tlb because the GRU
secondary MMU has no knowledge about sptes and every secondary tlb miss
event in the MMU always generates a page fault that has to be resolved by
the CPU (this is not the case of KVM where the a secondary tlb miss will
walk sptes in hardware and it will refill the secondary tlb transparently
to software if the corresponding spte is present).  The same way
zap_page_range has to invalidate the pte before freeing the page, the spte
(and secondary tlb) must also be invalidated before any page is freed and
reused.

Currently we take a page_count pin on every page mapped by sptes, but that
means the pages can't be swapped whenever they're mapped by any spte
because they're part of the guest working set.  Furthermore a spte unmap
event can immediately lead to a page to be freed when the pin is released
(so requiring the same complex and relatively slow tlb_gather smp safe
logic we have in zap_page_range and that can be avoided completely if the
spte unmap event doesn't require an unpin of the page previously mapped in
the secondary MMU).

The mmu notifiers allow kvm/GRU/XPMEM to attach to the tsk->mm and know
when the VM is swapping or freeing or doing anything on the primary MMU so
that the secondary MMU code can drop sptes before the pages are freed,
avoiding all page pinning and allowing 100% reliable swapping of guest
physical address space.  Furthermore it avoids the code that teardown the
mappings of the secondary MMU, to implement a logic like tlb_gather in
zap_page_range that would require many IPI to flush other cpu tlbs, for
each fixed number of spte unmapped.

To make an example: if what happens on the primary MMU is a protection
downgrade (from writeable to wrprotect) the secondary MMU mappings will be
invalidated, and the next secondary-mmu-page-fault will call
get_user_pages and trigger a do_wp_page through get_user_pages if it
called get_user_pages with write=1, and it'll re-establishing an updated
spte or secondary-tlb-mapping on the copied page.  Or it will setup a
readonly spte or readonly tlb mapping if it's a guest-read, if it calls
get_user_pages with write=0.  This is just an example.

This allows to map any page pointed by any pte (and in turn visible in the
primary CPU MMU), into a secondary MMU (be it a pure tlb like GRU, or an
full MMU with both sptes and secondary-tlb like the shadow-pagetable layer
with kvm), or a remote DMA in software like XPMEM (hence needing of
schedule in XPMEM code to send the invalidate to the remote node, while no
need to schedule in kvm/gru as it's an immediate event like invalidating
primary-mmu pte).

At least for KVM without this patch it's impossible to swap guests
reliably.  And having this feature and removing the page pin allows
several other optimizations that simplify life considerably.

Dependencies:

1) mm_take_all_locks() to register the mmu notifier when the whole VM
   isn't doing anything with "mm".  This allows mmu notifier users to keep
   track if the VM is in the middle of the invalidate_range_begin/end
   critical section with an atomic counter incraese in range_begin and
   decreased in range_end.  No secondary MMU page fault is allowed to map
   any spte or secondary tlb reference, while the VM is in the middle of
   range_begin/end as any page returned by get_user_pages in that critical
   section could later immediately be freed without any further
   ->invalidate_page notification (invalidate_range_begin/end works on
   ranges and ->invalidate_page isn't called immediately before freeing
   the page).  To stop all page freeing and pagetable overwrites the
   mmap_sem must be taken in write mode and all other anon_vma/i_mmap
   locks must be taken too.

2) It'd be a waste to add branches in the VM if nobody could possibly
   run KVM/GRU/XPMEM on the kernel, so mmu notifiers will only enabled if
   CONFIG_KVM=m/y.  In the current kernel kvm won't yet take advantage of
   mmu notifiers, but this already allows to compile a KVM external module
   against a kernel with mmu notifiers enabled and from the next pull from
   kvm.git we'll start using them.  And GRU/XPMEM will also be able to
   continue the development by enabling KVM=m in their config, until they
   submit all GRU/XPMEM GPLv2 code to the mainline kernel.  Then they can
   also enable MMU_NOTIFIERS in the same way KVM does it (even if KVM=n).
   This guarantees nobody selects MMU_NOTIFIER=y if KVM and GRU and XPMEM
   are all =n.

The mmu_notifier_register call can fail because mm_take_all_locks may be
interrupted by a signal and return -EINTR.  Because mmu_notifier_reigster
is used when a driver startup, a failure can be gracefully handled.  Here
an example of the change applied to kvm to register the mmu notifiers.
Usually when a driver startups other allocations are required anyway and
-ENOMEM failure paths exists already.

 struct  kvm *kvm_arch_create_vm(void)
 {
        struct kvm *kvm = kzalloc(sizeof(struct kvm), GFP_KERNEL);
+       int err;

        if (!kvm)
                return ERR_PTR(-ENOMEM);

        INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);

+       kvm->arch.mmu_notifier.ops = &kvm_mmu_notifier_ops;
+       err = mmu_notifier_register(&kvm->arch.mmu_notifier, current->mm);
+       if (err) {
+               kfree(kvm);
+               return ERR_PTR(err);
+       }
+
        return kvm;
 }

mmu_notifier_unregister returns void and it's reliable.

The patch also adds a few needed but missing includes that would prevent
kernel to compile after these changes on non-x86 archs (x86 didn't need
them by luck).

[akpm@linux-foundation.org: coding-style fixes]
[akpm@linux-foundation.org: fix mm/filemap_xip.c build]
[akpm@linux-foundation.org: fix mm/mmu_notifier.c build]
Signed-off-by: Andrea Arcangeli <andrea@qumranet.com>
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Jack Steiner <steiner@sgi.com>
Cc: Robin Holt <holt@sgi.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Kanoj Sarcar <kanojsarcar@yahoo.com>
Cc: Roland Dreier <rdreier@cisco.com>
Cc: Steve Wise <swise@opengridcomputing.com>
Cc: Avi Kivity <avi@qumranet.com>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Anthony Liguori <aliguori@us.ibm.com>
Cc: Chris Wright <chrisw@redhat.com>
Cc: Marcelo Tosatti <marcelo@kvack.org>
Cc: Eric Dumazet <dada1@cosmosbay.com>
Cc: "Paul E. McKenney" <paulmck@us.ibm.com>
Cc: Izik Eidus <izike@qumranet.com>
Cc: Anthony Liguori <aliguori@us.ibm.com>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-28 16:30:21 -07:00

1010 lines
27 KiB
C

/*
* 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_mutex (while writing or truncating, not reading or faulting)
* inode->i_alloc_sem (vmtruncate_range)
* mm->mmap_sem
* page->flags PG_locked (lock_page)
* mapping->i_mmap_lock
* anon_vma->lock
* mm->page_table_lock or pte_lock
* zone->lru_lock (in mark_page_accessed, isolate_lru_page)
* 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 <linux/module.h>
#include <linux/kallsyms.h>
#include <linux/memcontrol.h>
#include <linux/mmu_notifier.h>
#include <asm/tlbflush.h>
struct kmem_cache *anon_vma_cachep;
/* 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_tail(&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_tail(&vma->anon_vma_node, &anon_vma->head);
}
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_tail(&vma->anon_vma_node, &anon_vma->head);
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);
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)
{
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);
}
/*
* 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;
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);
return anon_vma;
out:
rcu_read_unlock();
return NULL;
}
static void page_unlock_anon_vma(struct anon_vma *anon_vma)
{
spin_unlock(&anon_vma->lock);
rcu_read_unlock();
}
/*
* At what user virtual address is page expected in @vma?
* Returns virtual address or -EFAULT if page's index/offset is not
* within the range mapped the @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 @vma mapping range */
return -EFAULT;
}
return address;
}
/*
* At what user virtual address is page expected in vma? checking that the
* page matches the vma: currently only used on anon pages, by unuse_vma;
*/
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 ||
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 pte mapped and locked.
*/
pte_t *page_check_address(struct page *page, struct mm_struct *mm,
unsigned long address, spinlock_t **ptlp)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
spinlock_t *ptl;
pgd = pgd_offset(mm, address);
if (!pgd_present(*pgd))
return NULL;
pud = pud_offset(pgd, address);
if (!pud_present(*pud))
return NULL;
pmd = pmd_offset(pud, address);
if (!pmd_present(*pmd))
return NULL;
pte = pte_offset_map(pmd, address);
/* Make a quick check before getting the lock */
if (!pte_present(*pte)) {
pte_unmap(pte);
return NULL;
}
ptl = pte_lockptr(mm, pmd);
spin_lock(ptl);
if (pte_present(*pte) && page_to_pfn(page) == pte_pfn(*pte)) {
*ptlp = ptl;
return pte;
}
pte_unmap_unlock(pte, ptl);
return NULL;
}
/*
* 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)
{
struct mm_struct *mm = vma->vm_mm;
unsigned long address;
pte_t *pte;
spinlock_t *ptl;
int referenced = 0;
address = vma_address(page, vma);
if (address == -EFAULT)
goto out;
pte = page_check_address(page, mm, address, &ptl);
if (!pte)
goto out;
if (vma->vm_flags & VM_LOCKED) {
referenced++;
*mapcount = 1; /* break early from loop */
} else if (ptep_clear_flush_young_notify(vma, address, pte))
referenced++;
/* 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 && has_swap_token(mm) &&
rwsem_is_locked(&mm->mmap_sem))
referenced++;
(*mapcount)--;
pte_unmap_unlock(pte, ptl);
out:
return referenced;
}
static int page_referenced_anon(struct page *page,
struct mem_cgroup *mem_cont)
{
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) {
/*
* If we are reclaiming on behalf of a cgroup, skip
* counting on behalf of references from different
* cgroups
*/
if (mem_cont && !mm_match_cgroup(vma->vm_mm, mem_cont))
continue;
referenced += page_referenced_one(page, vma, &mapcount);
if (!mapcount)
break;
}
page_unlock_anon_vma(anon_vma);
return referenced;
}
/**
* page_referenced_file - referenced check for object-based rmap
* @page: the page we're checking references on.
* @mem_cont: target memory controller
*
* 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,
struct mem_cgroup *mem_cont)
{
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 we are reclaiming on behalf of a cgroup, skip
* counting on behalf of references from different
* cgroups
*/
if (mem_cont && !mm_match_cgroup(vma->vm_mm, mem_cont))
continue;
if ((vma->vm_flags & (VM_LOCKED|VM_MAYSHARE))
== (VM_LOCKED|VM_MAYSHARE)) {
referenced++;
break;
}
referenced += page_referenced_one(page, vma, &mapcount);
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
* @mem_cont: target memory controller
*
* 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,
struct mem_cgroup *mem_cont)
{
int referenced = 0;
if (TestClearPageReferenced(page))
referenced++;
if (page_mapped(page) && page->mapping) {
if (PageAnon(page))
referenced += page_referenced_anon(page, mem_cont);
else if (is_locked)
referenced += page_referenced_file(page, mem_cont);
else if (TestSetPageLocked(page))
referenced++;
else {
if (page->mapping)
referenced +=
page_referenced_file(page, mem_cont);
unlock_page(page);
}
}
if (page_test_and_clear_young(page))
referenced++;
return referenced;
}
static int page_mkclean_one(struct page *page, struct vm_area_struct *vma)
{
struct mm_struct *mm = vma->vm_mm;
unsigned long address;
pte_t *pte;
spinlock_t *ptl;
int ret = 0;
address = vma_address(page, vma);
if (address == -EFAULT)
goto out;
pte = page_check_address(page, mm, address, &ptl);
if (!pte)
goto out;
if (pte_dirty(*pte) || pte_write(*pte)) {
pte_t entry;
flush_cache_page(vma, address, pte_pfn(*pte));
entry = ptep_clear_flush_notify(vma, address, pte);
entry = pte_wrprotect(entry);
entry = pte_mkclean(entry);
set_pte_at(mm, address, pte, entry);
ret = 1;
}
pte_unmap_unlock(pte, ptl);
out:
return ret;
}
static int page_mkclean_file(struct address_space *mapping, struct page *page)
{
pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
struct vm_area_struct *vma;
struct prio_tree_iter iter;
int ret = 0;
BUG_ON(PageAnon(page));
spin_lock(&mapping->i_mmap_lock);
vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
if (vma->vm_flags & VM_SHARED)
ret += page_mkclean_one(page, vma);
}
spin_unlock(&mapping->i_mmap_lock);
return ret;
}
int page_mkclean(struct page *page)
{
int ret = 0;
BUG_ON(!PageLocked(page));
if (page_mapped(page)) {
struct address_space *mapping = page_mapping(page);
if (mapping) {
ret = page_mkclean_file(mapping, page);
if (page_test_dirty(page)) {
page_clear_dirty(page);
ret = 1;
}
}
}
return ret;
}
EXPORT_SYMBOL_GPL(page_mkclean);
/**
* __page_set_anon_rmap - setup new anonymous rmap
* @page: the page to add the mapping to
* @vma: the vm area in which the mapping is added
* @address: the user virtual address mapped
*/
static void __page_set_anon_rmap(struct page *page,
struct vm_area_struct *vma, unsigned long address)
{
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);
/*
* nr_mapped state can be updated without turning off
* interrupts because it is not modified via interrupt.
*/
__inc_zone_page_state(page, NR_ANON_PAGES);
}
/**
* __page_check_anon_rmap - sanity check anonymous rmap addition
* @page: the page to add the mapping to
* @vma: the vm area in which the mapping is added
* @address: the user virtual address mapped
*/
static void __page_check_anon_rmap(struct page *page,
struct vm_area_struct *vma, unsigned long address)
{
#ifdef CONFIG_DEBUG_VM
/*
* The page's anon-rmap details (mapping and index) are guaranteed to
* be set up correctly at this point.
*
* We have exclusion against page_add_anon_rmap because the caller
* always holds the page locked, except if called from page_dup_rmap,
* in which case the page is already known to be setup.
*
* We have exclusion against page_add_new_anon_rmap because those pages
* are initially only visible via the pagetables, and the pte is locked
* over the call to page_add_new_anon_rmap.
*/
struct anon_vma *anon_vma = vma->anon_vma;
anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON;
BUG_ON(page->mapping != (struct address_space *)anon_vma);
BUG_ON(page->index != linear_page_index(vma, address));
#endif
}
/**
* 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 pte lock and the page must be locked.
*/
void page_add_anon_rmap(struct page *page,
struct vm_area_struct *vma, unsigned long address)
{
VM_BUG_ON(!PageLocked(page));
VM_BUG_ON(address < vma->vm_start || address >= vma->vm_end);
if (atomic_inc_and_test(&page->_mapcount))
__page_set_anon_rmap(page, vma, address);
else
__page_check_anon_rmap(page, vma, address);
}
/**
* page_add_new_anon_rmap - add pte mapping to a new 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
*
* Same as page_add_anon_rmap but must only be called on *new* pages.
* This means the inc-and-test can be bypassed.
* Page does not have to be locked.
*/
void page_add_new_anon_rmap(struct page *page,
struct vm_area_struct *vma, unsigned long address)
{
BUG_ON(address < vma->vm_start || address >= vma->vm_end);
atomic_set(&page->_mapcount, 0); /* elevate count by 1 (starts at -1) */
__page_set_anon_rmap(page, vma, address);
}
/**
* 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 pte lock.
*/
void page_add_file_rmap(struct page *page)
{
if (atomic_inc_and_test(&page->_mapcount))
__inc_zone_page_state(page, NR_FILE_MAPPED);
}
#ifdef CONFIG_DEBUG_VM
/**
* page_dup_rmap - duplicate pte mapping to a page
* @page: the page to add the mapping to
* @vma: the vm area being duplicated
* @address: the user virtual address mapped
*
* For copy_page_range only: minimal extract from page_add_file_rmap /
* page_add_anon_rmap, avoiding unnecessary tests (already checked) so it's
* quicker.
*
* The caller needs to hold the pte lock.
*/
void page_dup_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address)
{
BUG_ON(page_mapcount(page) == 0);
if (PageAnon(page))
__page_check_anon_rmap(page, vma, address);
atomic_inc(&page->_mapcount);
}
#endif
/**
* page_remove_rmap - take down pte mapping from a page
* @page: page to remove mapping from
* @vma: the vm area in which the mapping is removed
*
* The caller needs to hold the pte lock.
*/
void page_remove_rmap(struct page *page, struct vm_area_struct *vma)
{
if (atomic_add_negative(-1, &page->_mapcount)) {
if (unlikely(page_mapcount(page) < 0)) {
printk (KERN_EMERG "Eeek! page_mapcount(page) went negative! (%d)\n", page_mapcount(page));
printk (KERN_EMERG " page pfn = %lx\n", page_to_pfn(page));
printk (KERN_EMERG " page->flags = %lx\n", page->flags);
printk (KERN_EMERG " page->count = %x\n", page_count(page));
printk (KERN_EMERG " page->mapping = %p\n", page->mapping);
print_symbol (KERN_EMERG " vma->vm_ops = %s\n", (unsigned long)vma->vm_ops);
if (vma->vm_ops) {
print_symbol (KERN_EMERG " vma->vm_ops->fault = %s\n", (unsigned long)vma->vm_ops->fault);
}
if (vma->vm_file && vma->vm_file->f_op)
print_symbol (KERN_EMERG " vma->vm_file->f_op->mmap = %s\n", (unsigned long)vma->vm_file->f_op->mmap);
BUG();
}
/*
* 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_dirty(page)) {
page_clear_dirty(page);
set_page_dirty(page);
}
mem_cgroup_uncharge_page(page);
__dec_zone_page_state(page,
PageAnon(page) ? NR_ANON_PAGES : NR_FILE_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,
int migration)
{
struct mm_struct *mm = vma->vm_mm;
unsigned long address;
pte_t *pte;
pte_t pteval;
spinlock_t *ptl;
int ret = SWAP_AGAIN;
address = vma_address(page, vma);
if (address == -EFAULT)
goto out;
pte = page_check_address(page, mm, address, &ptl);
if (!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.
*/
if (!migration && ((vma->vm_flags & VM_LOCKED) ||
(ptep_clear_flush_young_notify(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_notify(vma, address, pte);
/* Move the dirty bit to the physical page now the pte is gone. */
if (pte_dirty(pteval))
set_page_dirty(page);
/* Update high watermark before we lower rss */
update_hiwater_rss(mm);
if (PageAnon(page)) {
swp_entry_t entry = { .val = page_private(page) };
if (PageSwapCache(page)) {
/*
* Store the swap location in the pte.
* See handle_pte_fault() ...
*/
swap_duplicate(entry);
if (list_empty(&mm->mmlist)) {
spin_lock(&mmlist_lock);
if (list_empty(&mm->mmlist))
list_add(&mm->mmlist, &init_mm.mmlist);
spin_unlock(&mmlist_lock);
}
dec_mm_counter(mm, anon_rss);
#ifdef CONFIG_MIGRATION
} else {
/*
* Store the pfn of the page in a special migration
* pte. do_swap_page() will wait until the migration
* pte is removed and then restart fault handling.
*/
BUG_ON(!migration);
entry = make_migration_entry(page, pte_write(pteval));
#endif
}
set_pte_at(mm, address, pte, swp_entry_to_pte(entry));
BUG_ON(pte_file(*pte));
} else
#ifdef CONFIG_MIGRATION
if (migration) {
/* Establish migration entry for a file page */
swp_entry_t entry;
entry = make_migration_entry(page, pte_write(pteval));
set_pte_at(mm, address, pte, swp_entry_to_pte(entry));
} else
#endif
dec_mm_counter(mm, file_rss);
page_remove_rmap(page, vma);
page_cache_release(page);
out_unmap:
pte_unmap_unlock(pte, ptl);
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;
pte_t pteval;
spinlock_t *ptl;
struct page *page;
unsigned long address;
unsigned long end;
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))
return;
pud = pud_offset(pgd, address);
if (!pud_present(*pud))
return;
pmd = pmd_offset(pud, address);
if (!pmd_present(*pmd))
return;
pte = pte_offset_map_lock(mm, pmd, address, &ptl);
/* Update high watermark before we lower rss */
update_hiwater_rss(mm);
for (; address < end; pte++, address += PAGE_SIZE) {
if (!pte_present(*pte))
continue;
page = vm_normal_page(vma, address, *pte);
BUG_ON(!page || PageAnon(page));
if (ptep_clear_flush_young_notify(vma, address, pte))
continue;
/* Nuke the page table entry. */
flush_cache_page(vma, address, pte_pfn(*pte));
pteval = ptep_clear_flush_notify(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, vma);
page_cache_release(page);
dec_mm_counter(mm, file_rss);
(*mapcount)--;
}
pte_unmap_unlock(pte - 1, ptl);
}
static int try_to_unmap_anon(struct page *page, int migration)
{
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, migration);
if (ret == SWAP_FAIL || !page_mapped(page))
break;
}
page_unlock_anon_vma(anon_vma);
return ret;
}
/**
* try_to_unmap_file - unmap file page using the object-based rmap method
* @page: the page to unmap
* @migration: migration flag
*
* 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, int migration)
{
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, migration);
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) && !migration)
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) && !migration)
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)
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
* @migration: migration flag
*
* 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 migration)
{
int ret;
BUG_ON(!PageLocked(page));
if (PageAnon(page))
ret = try_to_unmap_anon(page, migration);
else
ret = try_to_unmap_file(page, migration);
if (!page_mapped(page))
ret = SWAP_SUCCESS;
return ret;
}