* 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.
*
- * Simple, low overhead pte-based reverse mapping scheme.
- * This is kept modular because we may want to experiment
- * with object-based reverse mapping schemes. 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
*/
/*
* Locking:
- * - the page->pte.chain is protected by the PG_maplock bit,
- * which nests within the the mm->page_table_lock,
+ * - the page->mapcount field is protected by the PG_maplock bit,
+ * which nests within the mm->page_table_lock,
* which nests within the page lock.
* - because swapout locking is opposite to the locking order
* in the page fault path, the swapout path uses trylocks
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/rmap.h>
-#include <linux/cache.h>
-#include <linux/percpu.h>
+#include <linux/vs_memory.h>
-#include <asm/pgalloc.h>
-#include <asm/rmap.h>
-#include <asm/tlb.h>
#include <asm/tlbflush.h>
-/*
- * Something oopsable to put for now in the page->mapping
- * of an anonymous page, to test that it is ignored.
- */
-#define ANON_MAPPING_DEBUG ((struct address_space *) 0)
+//#define RMAP_DEBUG /* can be enabled only for debugging */
-static inline void clear_page_anon(struct page *page)
+kmem_cache_t *anon_vma_cachep;
+
+static inline void validate_anon_vma(struct vm_area_struct *find_vma)
{
- BUG_ON(page->mapping != ANON_MAPPING_DEBUG);
- page->mapping = NULL;
- ClearPageAnon(page);
+#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
}
-/*
- * Shared pages have a chain of pte_chain structures, used to locate
- * all the mappings to this page. We only need a pointer to the pte
- * here, the page struct for the page table page contains the process
- * it belongs to and the offset within that process.
- *
- * We use an array of pte pointers in this structure to minimise cache misses
- * while traversing reverse maps.
- */
-#define NRPTE ((L1_CACHE_BYTES - sizeof(unsigned long))/sizeof(pte_addr_t))
+/* 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 = NULL;
+
+ anon_vma = find_mergeable_anon_vma(vma);
+ if (!anon_vma) {
+ anon_vma = anon_vma_alloc();
+ if (unlikely(!anon_vma))
+ return -ENOMEM;
+ allocated = anon_vma;
+ }
-/*
- * next_and_idx encodes both the address of the next pte_chain and the
- * offset of the lowest-index used pte in ptes[] (which is equal also
- * to the offset of the highest-index unused pte in ptes[], plus one).
- */
-struct pte_chain {
- unsigned long next_and_idx;
- pte_addr_t ptes[NRPTE];
-} ____cacheline_aligned;
+ /* 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 (unlikely(allocated))
+ anon_vma_free(allocated);
+ }
+ return 0;
+}
+
+void __anon_vma_merge(struct vm_area_struct *vma, struct vm_area_struct *next)
+{
+ if (!vma->anon_vma) {
+ BUG_ON(!next->anon_vma);
+ vma->anon_vma = next->anon_vma;
+ list_add(&vma->anon_vma_node, &next->anon_vma_node);
+ } else {
+ /* if they're both non-null they must be the same */
+ 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;
-kmem_cache_t *pte_chain_cache;
+ spin_lock(&anon_vma->lock);
+ validate_anon_vma(vma);
+ list_del(&vma->anon_vma_node);
-static inline struct pte_chain *pte_chain_next(struct pte_chain *pte_chain)
+ /* 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)
{
- return (struct pte_chain *)(pte_chain->next_and_idx & ~NRPTE);
+ 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);
+ }
}
-static inline struct pte_chain *pte_chain_ptr(unsigned long pte_chain_addr)
+void __init anon_vma_init(void)
{
- return (struct pte_chain *)(pte_chain_addr & ~NRPTE);
+ anon_vma_cachep = kmem_cache_create("anon_vma",
+ sizeof(struct anon_vma), 0, SLAB_PANIC, anon_vma_ctor, NULL);
}
-static inline int pte_chain_idx(struct pte_chain *pte_chain)
+/* this needs the page->flags PG_maplock held */
+static inline void clear_page_anon(struct page *page)
{
- return pte_chain->next_and_idx & NRPTE;
+ BUG_ON(!page->mapping);
+ page->mapping = NULL;
+ ClearPageAnon(page);
}
+/*
+ * At what user virtual address is page expected in vma?
+ */
static inline unsigned long
-pte_chain_encode(struct pte_chain *pte_chain, int idx)
+vma_address(struct page *page, struct vm_area_struct *vma)
{
- return (unsigned long)pte_chain | idx;
+ 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;
}
/*
- * pte_chain list management policy:
- *
- * - If a page has a pte_chain list then it is shared by at least two processes,
- * because a single sharing uses PageDirect. (Well, this isn't true yet,
- * coz this code doesn't collapse singletons back to PageDirect on the remove
- * path).
- * - A pte_chain list has free space only in the head member - all succeeding
- * members are 100% full.
- * - If the head element has free space, it occurs in its leading slots.
- * - All free space in the pte_chain is at the start of the head member.
- * - Insertion into the pte_chain puts a pte pointer in the last free slot of
- * the head member.
- * - Removal from a pte chain moves the head pte of the head member onto the
- * victim pte and frees the head member if it became empty.
+ * 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;
+ pgd_t *pgd;
+ pmd_t *pmd;
+ pte_t *pte;
+ int referenced = 0;
+
+ if (!mm->rss)
+ goto out;
+ address = vma_address(page, vma);
+ if (address == -EFAULT)
+ goto out;
+
+ if (!spin_trylock(&mm->page_table_lock))
+ goto out;
+
+ pgd = pgd_offset(mm, address);
+ if (!pgd_present(*pgd))
+ goto out_unlock;
+
+ pmd = pmd_offset(pgd, address);
+ if (!pmd_present(*pmd))
+ goto out_unlock;
+
+ pte = pte_offset_map(pmd, address);
+ if (!pte_present(*pte))
+ goto out_unmap;
+
+ if (page_to_pfn(page) != pte_pfn(*pte))
+ goto out_unmap;
+
+ if (ptep_test_and_clear_young(pte))
+ referenced++;
+
+ (*mapcount)--;
+
+out_unmap:
+ pte_unmap(pte);
+out_unlock:
+ spin_unlock(&mm->page_table_lock);
+out:
+ return referenced;
+}
+
+static inline int page_referenced_anon(struct page *page)
+{
+ unsigned int mapcount = page->mapcount;
+ struct anon_vma *anon_vma = (struct anon_vma *) page->mapping;
+ struct vm_area_struct *vma;
+ int referenced = 0;
+
+ spin_lock(&anon_vma->lock);
+ BUG_ON(list_empty(&anon_vma->head));
+ list_for_each_entry(vma, &anon_vma->head, anon_vma_node) {
+ referenced += page_referenced_one(page, vma, &mapcount);
+ if (!mapcount)
+ break;
+ }
+ spin_unlock(&anon_vma->lock);
+ return referenced;
+}
/**
- ** VM stuff below this comment
- **/
+ * 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.
+ *
+ * The spinlock address_space->i_mmap_lock is tried. If it can't be gotten,
+ * assume a reference count of 0, so try_to_unmap will then have a go.
+ */
+static inline int page_referenced_file(struct page *page)
+{
+ unsigned int mapcount = page->mapcount;
+ struct address_space *mapping = page->mapping;
+ pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
+ struct vm_area_struct *vma = NULL;
+ struct prio_tree_iter iter;
+ int referenced = 0;
+
+ if (!spin_trylock(&mapping->i_mmap_lock))
+ return 0;
+
+ while ((vma = vma_prio_tree_next(vma, &mapping->i_mmap,
+ &iter, pgoff, pgoff)) != NULL) {
+ 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
*
* Quick test_and_clear_referenced for all mappings to a page,
- * returns the number of processes which referenced the page.
+ * returns the number of ptes which referenced the page.
* Caller needs to hold the rmap lock.
- *
- * If the page has a single-entry pte_chain, collapse that back to a PageDirect
- * representation. This way, it's only done under memory pressure.
*/
-int fastcall page_referenced(struct page * page)
+int page_referenced(struct page *page)
{
- struct pte_chain *pc;
int referenced = 0;
if (page_test_and_clear_young(page))
if (TestClearPageReferenced(page))
referenced++;
- if (PageDirect(page)) {
- pte_t *pte = rmap_ptep_map(page->pte.direct);
- if (ptep_test_and_clear_young(pte))
- referenced++;
- rmap_ptep_unmap(pte);
- } else {
- int nr_chains = 0;
-
- /* Check all the page tables mapping this page. */
- for (pc = page->pte.chain; pc; pc = pte_chain_next(pc)) {
- int i;
-
- for (i = pte_chain_idx(pc); i < NRPTE; i++) {
- pte_addr_t pte_paddr = pc->ptes[i];
- pte_t *p;
-
- p = rmap_ptep_map(pte_paddr);
- if (ptep_test_and_clear_young(p))
- referenced++;
- rmap_ptep_unmap(p);
- nr_chains++;
- }
- }
- if (nr_chains == 1) {
- pc = page->pte.chain;
- page->pte.direct = pc->ptes[NRPTE-1];
- SetPageDirect(page);
- pc->ptes[NRPTE-1] = 0;
- __pte_chain_free(pc);
- }
+ if (page->mapcount && page->mapping) {
+ if (PageAnon(page))
+ referenced += page_referenced_anon(page);
+ else
+ referenced += page_referenced_file(page);
}
return referenced;
}
/**
- * page_add_rmap - add reverse mapping entry to a page
- * @page: the page to add the mapping to
- * @ptep: the page table entry mapping this page
+ * 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
*
- * Add a new pte reverse mapping to a page.
* The caller needs to hold the mm->page_table_lock.
*/
-struct pte_chain * fastcall
-page_add_rmap(struct page *page, pte_t *ptep, struct pte_chain *pte_chain)
+void page_add_anon_rmap(struct page *page,
+ struct vm_area_struct *vma, unsigned long address)
{
- pte_addr_t pte_paddr = ptep_to_paddr(ptep);
- struct pte_chain *cur_pte_chain;
+ struct anon_vma *anon_vma = vma->anon_vma;
+ pgoff_t index;
- if (PageReserved(page))
- return pte_chain;
+ BUG_ON(PageReserved(page));
+ BUG_ON(!anon_vma);
- rmap_lock(page);
+ index = (address - vma->vm_start) >> PAGE_SHIFT;
+ index += vma->vm_pgoff;
+ index >>= PAGE_CACHE_SHIFT - PAGE_SHIFT;
- if (page->pte.direct == 0) {
- page->pte.direct = pte_paddr;
- SetPageDirect(page);
- if (!page->mapping) {
- SetPageAnon(page);
- page->mapping = ANON_MAPPING_DEBUG;
- }
+ /*
+ * Setting and clearing PG_anon must always happen inside
+ * page_map_lock to avoid races between mapping and
+ * unmapping on different processes of the same
+ * shared cow swapcache page. And while we take the
+ * page_map_lock PG_anon cannot change from under us.
+ * Actually PG_anon cannot change under fork either
+ * since fork holds a reference on the page so it cannot
+ * be unmapped under fork and in turn copy_page_range is
+ * allowed to read PG_anon outside the page_map_lock.
+ */
+ page_map_lock(page);
+ if (!page->mapcount) {
+ BUG_ON(PageAnon(page));
+ BUG_ON(page->mapping);
+ SetPageAnon(page);
+ page->index = index;
+ page->mapping = (struct address_space *) anon_vma;
inc_page_state(nr_mapped);
- goto out;
- }
-
- if (PageDirect(page)) {
- /* Convert a direct pointer into a pte_chain */
- ClearPageDirect(page);
- pte_chain->ptes[NRPTE-1] = page->pte.direct;
- pte_chain->ptes[NRPTE-2] = pte_paddr;
- pte_chain->next_and_idx = pte_chain_encode(NULL, NRPTE-2);
- page->pte.direct = 0;
- page->pte.chain = pte_chain;
- pte_chain = NULL; /* We consumed it */
- goto out;
- }
-
- cur_pte_chain = page->pte.chain;
- if (cur_pte_chain->ptes[0]) { /* It's full */
- pte_chain->next_and_idx = pte_chain_encode(cur_pte_chain,
- NRPTE - 1);
- page->pte.chain = pte_chain;
- pte_chain->ptes[NRPTE-1] = pte_paddr;
- pte_chain = NULL; /* We consumed it */
- goto out;
+ } else {
+ BUG_ON(!PageAnon(page));
+ BUG_ON(page->index != index);
+ BUG_ON(page->mapping != (struct address_space *) anon_vma);
}
- cur_pte_chain->ptes[pte_chain_idx(cur_pte_chain) - 1] = pte_paddr;
- cur_pte_chain->next_and_idx--;
-out:
- rmap_unlock(page);
- return pte_chain;
+ page->mapcount++;
+ page_map_unlock(page);
}
/**
- * page_remove_rmap - take down reverse mapping to a page
- * @page: page to remove mapping from
- * @ptep: page table entry to remove
+ * page_add_file_rmap - add pte mapping to a file page
+ * @page: the page to add the mapping to
*
- * Removes the reverse mapping from the pte_chain of the page,
- * after that the caller can clear the page table entry and free
- * the page.
- * Caller needs to hold the mm->page_table_lock.
+ * The caller needs to hold the mm->page_table_lock.
*/
-void fastcall page_remove_rmap(struct page *page, pte_t *ptep)
+void page_add_file_rmap(struct page *page)
{
- pte_addr_t pte_paddr = ptep_to_paddr(ptep);
- struct pte_chain *pc;
-
+ BUG_ON(PageAnon(page));
if (!pfn_valid(page_to_pfn(page)) || PageReserved(page))
return;
- rmap_lock(page);
+ page_map_lock(page);
+ if (!page->mapcount)
+ inc_page_state(nr_mapped);
+ page->mapcount++;
+ page_map_unlock(page);
+}
- if (!page_mapped(page))
- goto out_unlock; /* remap_page_range() from a driver? */
+/**
+ * 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)
+{
+ BUG_ON(PageReserved(page));
+ BUG_ON(!page->mapcount);
- if (PageDirect(page)) {
- if (page->pte.direct == pte_paddr) {
- page->pte.direct = 0;
- ClearPageDirect(page);
- goto out;
- }
- } else {
- struct pte_chain *start = page->pte.chain;
- struct pte_chain *next;
- int victim_i = pte_chain_idx(start);
-
- for (pc = start; pc; pc = next) {
- int i;
-
- next = pte_chain_next(pc);
- if (next)
- prefetch(next);
- for (i = pte_chain_idx(pc); i < NRPTE; i++) {
- pte_addr_t pa = pc->ptes[i];
-
- if (pa != pte_paddr)
- continue;
- pc->ptes[i] = start->ptes[victim_i];
- start->ptes[victim_i] = 0;
- if (victim_i == NRPTE-1) {
- /* Emptied a pte_chain */
- page->pte.chain = pte_chain_next(start);
- __pte_chain_free(start);
- } else {
- start->next_and_idx++;
- }
- goto out;
- }
- }
- }
-out:
- if (!page_mapped(page)) {
+ page_map_lock(page);
+ page->mapcount--;
+ if (!page->mapcount) {
if (page_test_and_clear_dirty(page))
set_page_dirty(page);
if (PageAnon(page))
clear_page_anon(page);
dec_page_state(nr_mapped);
}
-out_unlock:
- rmap_unlock(page);
+ page_map_unlock(page);
}
-/**
- * try_to_unmap_one - worker function for try_to_unmap
- * @page: page to unmap
- * @ptep: page table entry to unmap from page
- *
- * Internal helper function for try_to_unmap, called for each page
- * table entry mapping a page. Because locking order here is opposite
- * to the locking order used by the page fault path, we use trylocks.
- * Locking:
- * page lock shrink_list(), trylock
- * rmap lock shrink_list()
- * mm->page_table_lock try_to_unmap_one(), trylock
+/*
+ * Subfunctions of try_to_unmap: try_to_unmap_one called
+ * repeatedly from either try_to_unmap_anon or try_to_unmap_file.
*/
-static int fastcall try_to_unmap_one(struct page * page, pte_addr_t paddr)
+static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma)
{
- pte_t *ptep = rmap_ptep_map(paddr);
- unsigned long address = ptep_to_address(ptep);
- struct mm_struct * mm = ptep_to_mm(ptep);
- struct vm_area_struct * vma;
- pte_t pte;
- int ret;
-
- if (!mm)
- BUG();
+ struct mm_struct *mm = vma->vm_mm;
+ unsigned long address;
+ pgd_t *pgd;
+ pmd_t *pmd;
+ pte_t *pte;
+ pte_t pteval;
+ int ret = SWAP_AGAIN;
+
+ if (!mm->rss)
+ goto out;
+ address = vma_address(page, vma);
+ if (address == -EFAULT)
+ goto out;
/*
* We need the page_table_lock to protect us from page faults,
* munmap, fork, etc...
*/
- if (!spin_trylock(&mm->page_table_lock)) {
- rmap_ptep_unmap(ptep);
- return SWAP_AGAIN;
- }
+ if (!spin_trylock(&mm->page_table_lock))
+ goto out;
- /* unmap_vmas drops page_table_lock with vma unlinked */
- vma = find_vma(mm, address);
- if (!vma) {
- ret = SWAP_FAIL;
+ pgd = pgd_offset(mm, address);
+ if (!pgd_present(*pgd))
goto out_unlock;
+
+ pmd = pmd_offset(pgd, address);
+ if (!pmd_present(*pmd))
+ goto out_unlock;
+
+ pte = pte_offset_map(pmd, address);
+ if (!pte_present(*pte))
+ goto out_unmap;
+
+ if (page_to_pfn(page) != pte_pfn(*pte))
+ goto out_unmap;
+
+ /*
+ * 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 ((vma->vm_flags & (VM_LOCKED|VM_RESERVED)) ||
+ ptep_test_and_clear_young(pte)) {
+ ret = SWAP_FAIL;
+ goto out_unmap;
}
- /* The page is mlock()d, we cannot swap it out. */
- if (vma->vm_flags & VM_LOCKED) {
+ /*
+ * Don't pull an anonymous page out from under get_user_pages.
+ * GUP carefully breaks COW and raises page count (while holding
+ * page_table_lock, as we have here) to make sure that the page
+ * cannot be freed. If we unmap that page here, a user write
+ * access to the virtual address will bring back the page, but
+ * its raised count will (ironically) be taken to mean it's not
+ * an exclusive swap page, do_wp_page will replace it by a copy
+ * page, and the user never get to see the data GUP was holding
+ * the original page for.
+ */
+ if (PageSwapCache(page) &&
+ page_count(page) != page->mapcount + 2) {
ret = SWAP_FAIL;
- goto out_unlock;
+ goto out_unmap;
}
/* Nuke the page table entry. */
flush_cache_page(vma, address);
- pte = ptep_clear_flush(vma, address, ptep);
+ 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);
if (PageAnon(page)) {
swp_entry_t entry = { .val = page->private };
*/
BUG_ON(!PageSwapCache(page));
swap_duplicate(entry);
- set_pte(ptep, swp_entry_to_pte(entry));
- BUG_ON(pte_file(*ptep));
- } else {
- /*
- * If a nonlinear mapping then store the file page offset
- * in the pte.
- */
- BUG_ON(!page->mapping);
- if (page->index != linear_page_index(vma, address)) {
- set_pte(ptep, pgoff_to_pte(page->index));
- BUG_ON(!pte_file(*ptep));
- }
+ set_pte(pte, swp_entry_to_pte(entry));
+ BUG_ON(pte_file(*pte));
}
- /* Move the dirty bit to the physical page now the pte is gone. */
- if (pte_dirty(pte))
- set_page_dirty(page);
-
// mm->rss--;
vx_rsspages_dec(mm);
+ BUG_ON(!page->mapcount);
+ page->mapcount--;
page_cache_release(page);
- ret = SWAP_SUCCESS;
+out_unmap:
+ pte_unmap(pte);
out_unlock:
- rmap_ptep_unmap(ptep);
spin_unlock(&mm->page_table_lock);
+out:
return ret;
}
-/**
- * try_to_unmap - try to remove all page table mappings to a page
- * @page: the page to get unmapped
+/*
+ * 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.
*
- * Tries to remove all the page table entries which are mapping this
- * page, used in the pageout path. Caller must hold the page lock
- * and its rmap lock. Return values are:
+ * 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.
*
- * SWAP_SUCCESS - we succeeded in removing all mappings
- * SWAP_AGAIN - we missed a trylock, try again later
- * SWAP_FAIL - the page is unswappable
+ * 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.
*/
-int fastcall try_to_unmap(struct page * page)
+#define CLUSTER_SIZE min(32*PAGE_SIZE, PMD_SIZE)
+#define CLUSTER_MASK (~(CLUSTER_SIZE - 1))
+
+static int try_to_unmap_cluster(unsigned long cursor,
+ unsigned int *mapcount, struct vm_area_struct *vma)
{
- struct pte_chain *pc, *next_pc, *start;
- int ret = SWAP_SUCCESS;
- int victim_i;
-
- /* This page should not be on the pageout lists. */
- if (PageReserved(page))
- BUG();
- if (!PageLocked(page))
- BUG();
-
- if (PageDirect(page)) {
- ret = try_to_unmap_one(page, page->pte.direct);
- if (ret == SWAP_SUCCESS) {
- page->pte.direct = 0;
- ClearPageDirect(page);
- }
- goto out;
- }
+ struct mm_struct *mm = vma->vm_mm;
+ pgd_t *pgd;
+ pmd_t *pmd;
+ pte_t *pte;
+ pte_t pteval;
+ struct page *page;
+ unsigned long address;
+ unsigned long end;
+ unsigned long pfn;
- start = page->pte.chain;
- victim_i = pte_chain_idx(start);
- for (pc = start; pc; pc = next_pc) {
- int i;
-
- next_pc = pte_chain_next(pc);
- if (next_pc)
- prefetch(next_pc);
- for (i = pte_chain_idx(pc); i < NRPTE; i++) {
- pte_addr_t pte_paddr = pc->ptes[i];
-
- switch (try_to_unmap_one(page, pte_paddr)) {
- case SWAP_SUCCESS:
- /*
- * Release a slot. If we're releasing the
- * first pte in the first pte_chain then
- * pc->ptes[i] and start->ptes[victim_i] both
- * refer to the same thing. It works out.
- */
- pc->ptes[i] = start->ptes[victim_i];
- start->ptes[victim_i] = 0;
- victim_i++;
- if (victim_i == NRPTE) {
- page->pte.chain = pte_chain_next(start);
- __pte_chain_free(start);
- start = page->pte.chain;
- victim_i = 0;
- } else {
- start->next_and_idx++;
- }
- break;
- case SWAP_AGAIN:
- /* Skip this pte, remembering status. */
- ret = SWAP_AGAIN;
- continue;
- case SWAP_FAIL:
- ret = SWAP_FAIL;
- goto out;
- }
- }
- }
-out:
- if (!page_mapped(page)) {
- if (page_test_and_clear_dirty(page))
+ /*
+ * We need the page_table_lock to protect us from page faults,
+ * munmap, fork, etc...
+ */
+ if (!spin_trylock(&mm->page_table_lock))
+ return SWAP_FAIL;
+
+ 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;
+
+ pmd = pmd_offset(pgd, address);
+ if (!pmd_present(*pmd))
+ goto out_unlock;
+
+ for (pte = pte_offset_map(pmd, address);
+ address < end; pte++, address += PAGE_SIZE) {
+
+ if (!pte_present(*pte))
+ continue;
+
+ pfn = pte_pfn(*pte);
+ if (!pfn_valid(pfn))
+ continue;
+
+ page = pfn_to_page(pfn);
+ BUG_ON(PageAnon(page));
+ if (PageReserved(page))
+ continue;
+
+ if (ptep_test_and_clear_young(pte))
+ continue;
+
+ /* Nuke the page table entry. */
+ flush_cache_page(vma, address);
+ 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(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);
- if (PageAnon(page))
- clear_page_anon(page);
- dec_page_state(nr_mapped);
- ret = SWAP_SUCCESS;
- }
- return ret;
-}
-/**
- ** No more VM stuff below this comment, only pte_chain helper
- ** functions.
- **/
+ page_remove_rmap(page);
+ page_cache_release(page);
+ // mm->rss--;
+ vx_rsspages_dec(mm);
+ (*mapcount)--;
+ }
-static void pte_chain_ctor(void *p, kmem_cache_t *cachep, unsigned long flags)
-{
- struct pte_chain *pc = p;
+ pte_unmap(pte);
- memset(pc, 0, sizeof(*pc));
+out_unlock:
+ spin_unlock(&mm->page_table_lock);
+ return SWAP_AGAIN;
}
-DEFINE_PER_CPU(struct pte_chain *, local_pte_chain) = 0;
-
-/**
- * __pte_chain_free - free pte_chain structure
- * @pte_chain: pte_chain struct to free
- */
-void __pte_chain_free(struct pte_chain *pte_chain)
+static inline int try_to_unmap_anon(struct page *page)
{
- struct pte_chain **pte_chainp;
-
- pte_chainp = &get_cpu_var(local_pte_chain);
- if (pte_chain->next_and_idx)
- pte_chain->next_and_idx = 0;
- if (*pte_chainp)
- kmem_cache_free(pte_chain_cache, *pte_chainp);
- *pte_chainp = pte_chain;
- put_cpu_var(local_pte_chain);
+ struct anon_vma *anon_vma = (struct anon_vma *) page->mapping;
+ struct vm_area_struct *vma;
+ int ret = SWAP_AGAIN;
+
+ spin_lock(&anon_vma->lock);
+ BUG_ON(list_empty(&anon_vma->head));
+ list_for_each_entry(vma, &anon_vma->head, anon_vma_node) {
+ ret = try_to_unmap_one(page, vma);
+ if (ret == SWAP_FAIL || !page->mapcount)
+ break;
+ }
+ spin_unlock(&anon_vma->lock);
+ return ret;
}
-/*
- * pte_chain_alloc(): allocate a pte_chain structure for use by page_add_rmap().
+/**
+ * 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.
*
- * The caller of page_add_rmap() must perform the allocation because
- * page_add_rmap() is invariably called under spinlock. Often, page_add_rmap()
- * will not actually use the pte_chain, because there is space available in one
- * of the existing pte_chains which are attached to the page. So the case of
- * allocating and then freeing a single pte_chain is specially optimised here,
- * with a one-deep per-cpu cache.
+ * The spinlock address_space->i_mmap_lock is tried. If it can't be gotten,
+ * return a temporary error.
*/
-struct pte_chain *pte_chain_alloc(int gfp_flags)
+static inline int try_to_unmap_file(struct page *page)
{
- struct pte_chain *ret;
- struct pte_chain **pte_chainp;
+ struct address_space *mapping = page->mapping;
+ pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
+ struct vm_area_struct *vma = NULL;
+ 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;
+
+ if (!spin_trylock(&mapping->i_mmap_lock))
+ return ret;
+
+ while ((vma = vma_prio_tree_next(vma, &mapping->i_mmap,
+ &iter, pgoff, pgoff)) != NULL) {
+ ret = try_to_unmap_one(page, vma);
+ if (ret == SWAP_FAIL || !page->mapcount)
+ goto out;
+ }
- might_sleep_if(gfp_flags & __GFP_WAIT);
+ if (list_empty(&mapping->i_mmap_nonlinear))
+ goto out;
- pte_chainp = &get_cpu_var(local_pte_chain);
- if (*pte_chainp) {
- ret = *pte_chainp;
- *pte_chainp = NULL;
- put_cpu_var(local_pte_chain);
- } else {
- put_cpu_var(local_pte_chain);
- ret = kmem_cache_alloc(pte_chain_cache, gfp_flags);
+ 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 */
+ 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_map_unlock(page);
+ 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 (vma->vm_mm->rss &&
+ cursor < max_nl_cursor &&
+ cursor < vma->vm_end - vma->vm_start) {
+ ret = try_to_unmap_cluster(
+ cursor, &mapcount, vma);
+ if (ret == SWAP_FAIL)
+ break;
+ cursor += CLUSTER_SIZE;
+ vma->vm_private_data = (void *) cursor;
+ if ((int)mapcount <= 0)
+ goto relock;
+ }
+ if (ret != SWAP_FAIL)
+ vma->vm_private_data =
+ (void *) max_nl_cursor;
+ ret = SWAP_AGAIN;
+ }
+ 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 = 0;
+ }
+relock:
+ page_map_lock(page);
+out:
+ spin_unlock(&mapping->i_mmap_lock);
return ret;
}
-void __init pte_chain_init(void)
+/**
+ * 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
+ * and its rmap lock. Return values are:
+ *
+ * SWAP_SUCCESS - we succeeded in removing all mappings
+ * SWAP_AGAIN - we missed a trylock, try again later
+ * SWAP_FAIL - the page is unswappable
+ */
+int try_to_unmap(struct page *page)
{
- pte_chain_cache = kmem_cache_create( "pte_chain",
- sizeof(struct pte_chain),
- sizeof(struct pte_chain),
- 0,
- pte_chain_ctor,
- NULL);
-
- if (!pte_chain_cache)
- panic("failed to create pte_chain cache!\n");
+ int ret;
+
+ BUG_ON(PageReserved(page));
+ BUG_ON(!PageLocked(page));
+ BUG_ON(!page->mapcount);
+
+ if (PageAnon(page))
+ ret = try_to_unmap_anon(page);
+ else
+ ret = try_to_unmap_file(page);
+
+ if (!page->mapcount) {
+ if (page_test_and_clear_dirty(page))
+ set_page_dirty(page);
+ if (PageAnon(page))
+ clear_page_anon(page);
+ dec_page_state(nr_mapped);
+ ret = SWAP_SUCCESS;
+ }
+ return ret;
}
git://git.onelab.eu / linux-2.6.git / blobdiff