summaryrefslogtreecommitdiffstats
path: root/mm/memory.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2015-02-11 01:45:56 +0100
committerLinus Torvalds <torvalds@linux-foundation.org>2015-02-11 01:45:56 +0100
commit992de5a8eca7cbd3215e3eb2c439b2c11582a58b (patch)
tree863988f84c1dd57a02fa337ecbce49263a3b9511 /mm/memory.c
parentMerge tag 'gfs2-merge-window' of git://git.kernel.org/pub/scm/linux/kernel/gi... (diff)
parentmemcg: zap memcg_slab_caches and memcg_slab_mutex (diff)
downloadlinux-992de5a8eca7cbd3215e3eb2c439b2c11582a58b.tar.xz
linux-992de5a8eca7cbd3215e3eb2c439b2c11582a58b.zip
Merge branch 'akpm' (patches from Andrew)
Merge misc updates from Andrew Morton: "Bite-sized chunks this time, to avoid the MTA ratelimiting woes. - fs/notify updates - ocfs2 - some of MM" That laconic "some MM" is mainly the removal of remap_file_pages(), which is a big simplification of the VM, and which gets rid of a *lot* of random cruft and special cases because we no longer support the non-linear mappings that it used. From a user interface perspective, nothing has changed, because the remap_file_pages() syscall still exists, it's just done by emulating the old behavior by creating a lot of individual small mappings instead of one non-linear one. The emulation is slower than the old "native" non-linear mappings, but nobody really uses or cares about remap_file_pages(), and simplifying the VM is a big advantage. * emailed patches from Andrew Morton <akpm@linux-foundation.org>: (78 commits) memcg: zap memcg_slab_caches and memcg_slab_mutex memcg: zap memcg_name argument of memcg_create_kmem_cache memcg: zap __memcg_{charge,uncharge}_slab mm/page_alloc.c: place zone_id check before VM_BUG_ON_PAGE check mm: hugetlb: fix type of hugetlb_treat_as_movable variable mm, hugetlb: remove unnecessary lower bound on sysctl handlers"? mm: memory: merge shared-writable dirtying branches in do_wp_page() mm: memory: remove ->vm_file check on shared writable vmas xtensa: drop _PAGE_FILE and pte_file()-related helpers x86: drop _PAGE_FILE and pte_file()-related helpers unicore32: drop pte_file()-related helpers um: drop _PAGE_FILE and pte_file()-related helpers tile: drop pte_file()-related helpers sparc: drop pte_file()-related helpers sh: drop _PAGE_FILE and pte_file()-related helpers score: drop _PAGE_FILE and pte_file()-related helpers s390: drop pte_file()-related helpers parisc: drop _PAGE_FILE and pte_file()-related helpers openrisc: drop _PAGE_FILE and pte_file()-related helpers nios2: drop _PAGE_FILE and pte_file()-related helpers ...
Diffstat (limited to 'mm/memory.c')
-rw-r--r--mm/memory.c276
1 files changed, 84 insertions, 192 deletions
diff --git a/mm/memory.c b/mm/memory.c
index d707c4dfbbb4..d63849b5188f 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -813,42 +813,40 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
/* pte contains position in swap or file, so copy. */
if (unlikely(!pte_present(pte))) {
- if (!pte_file(pte)) {
- swp_entry_t entry = pte_to_swp_entry(pte);
-
- if (likely(!non_swap_entry(entry))) {
- if (swap_duplicate(entry) < 0)
- return entry.val;
-
- /* make sure dst_mm is on swapoff's mmlist. */
- if (unlikely(list_empty(&dst_mm->mmlist))) {
- spin_lock(&mmlist_lock);
- if (list_empty(&dst_mm->mmlist))
- list_add(&dst_mm->mmlist,
- &src_mm->mmlist);
- spin_unlock(&mmlist_lock);
- }
- rss[MM_SWAPENTS]++;
- } else if (is_migration_entry(entry)) {
- page = migration_entry_to_page(entry);
-
- if (PageAnon(page))
- rss[MM_ANONPAGES]++;
- else
- rss[MM_FILEPAGES]++;
-
- if (is_write_migration_entry(entry) &&
- is_cow_mapping(vm_flags)) {
- /*
- * COW mappings require pages in both
- * parent and child to be set to read.
- */
- make_migration_entry_read(&entry);
- pte = swp_entry_to_pte(entry);
- if (pte_swp_soft_dirty(*src_pte))
- pte = pte_swp_mksoft_dirty(pte);
- set_pte_at(src_mm, addr, src_pte, pte);
- }
+ swp_entry_t entry = pte_to_swp_entry(pte);
+
+ if (likely(!non_swap_entry(entry))) {
+ if (swap_duplicate(entry) < 0)
+ return entry.val;
+
+ /* make sure dst_mm is on swapoff's mmlist. */
+ if (unlikely(list_empty(&dst_mm->mmlist))) {
+ spin_lock(&mmlist_lock);
+ if (list_empty(&dst_mm->mmlist))
+ list_add(&dst_mm->mmlist,
+ &src_mm->mmlist);
+ spin_unlock(&mmlist_lock);
+ }
+ rss[MM_SWAPENTS]++;
+ } else if (is_migration_entry(entry)) {
+ page = migration_entry_to_page(entry);
+
+ if (PageAnon(page))
+ rss[MM_ANONPAGES]++;
+ else
+ rss[MM_FILEPAGES]++;
+
+ if (is_write_migration_entry(entry) &&
+ is_cow_mapping(vm_flags)) {
+ /*
+ * COW mappings require pages in both
+ * parent and child to be set to read.
+ */
+ make_migration_entry_read(&entry);
+ pte = swp_entry_to_pte(entry);
+ if (pte_swp_soft_dirty(*src_pte))
+ pte = pte_swp_mksoft_dirty(pte);
+ set_pte_at(src_mm, addr, src_pte, pte);
}
}
goto out_set_pte;
@@ -1022,11 +1020,9 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
* readonly mappings. The tradeoff is that copy_page_range is more
* efficient than faulting.
*/
- if (!(vma->vm_flags & (VM_HUGETLB | VM_NONLINEAR |
- VM_PFNMAP | VM_MIXEDMAP))) {
- if (!vma->anon_vma)
- return 0;
- }
+ if (!(vma->vm_flags & (VM_HUGETLB | VM_PFNMAP | VM_MIXEDMAP)) &&
+ !vma->anon_vma)
+ return 0;
if (is_vm_hugetlb_page(vma))
return copy_hugetlb_page_range(dst_mm, src_mm, vma);
@@ -1084,6 +1080,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
spinlock_t *ptl;
pte_t *start_pte;
pte_t *pte;
+ swp_entry_t entry;
again:
init_rss_vec(rss);
@@ -1109,28 +1106,12 @@ again:
if (details->check_mapping &&
details->check_mapping != page->mapping)
continue;
- /*
- * Each page->index must be checked when
- * invalidating or truncating nonlinear.
- */
- if (details->nonlinear_vma &&
- (page->index < details->first_index ||
- page->index > details->last_index))
- continue;
}
ptent = ptep_get_and_clear_full(mm, addr, pte,
tlb->fullmm);
tlb_remove_tlb_entry(tlb, pte, addr);
if (unlikely(!page))
continue;
- if (unlikely(details) && details->nonlinear_vma
- && linear_page_index(details->nonlinear_vma,
- addr) != page->index) {
- pte_t ptfile = pgoff_to_pte(page->index);
- if (pte_soft_dirty(ptent))
- ptfile = pte_file_mksoft_dirty(ptfile);
- set_pte_at(mm, addr, pte, ptfile);
- }
if (PageAnon(page))
rss[MM_ANONPAGES]--;
else {
@@ -1153,33 +1134,25 @@ again:
}
continue;
}
- /*
- * If details->check_mapping, we leave swap entries;
- * if details->nonlinear_vma, we leave file entries.
- */
+ /* If details->check_mapping, we leave swap entries. */
if (unlikely(details))
continue;
- if (pte_file(ptent)) {
- if (unlikely(!(vma->vm_flags & VM_NONLINEAR)))
- print_bad_pte(vma, addr, ptent, NULL);
- } else {
- swp_entry_t entry = pte_to_swp_entry(ptent);
- if (!non_swap_entry(entry))
- rss[MM_SWAPENTS]--;
- else if (is_migration_entry(entry)) {
- struct page *page;
+ entry = pte_to_swp_entry(ptent);
+ if (!non_swap_entry(entry))
+ rss[MM_SWAPENTS]--;
+ else if (is_migration_entry(entry)) {
+ struct page *page;
- page = migration_entry_to_page(entry);
+ page = migration_entry_to_page(entry);
- if (PageAnon(page))
- rss[MM_ANONPAGES]--;
- else
- rss[MM_FILEPAGES]--;
- }
- if (unlikely(!free_swap_and_cache(entry)))
- print_bad_pte(vma, addr, ptent, NULL);
+ if (PageAnon(page))
+ rss[MM_ANONPAGES]--;
+ else
+ rss[MM_FILEPAGES]--;
}
+ if (unlikely(!free_swap_and_cache(entry)))
+ print_bad_pte(vma, addr, ptent, NULL);
pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
} while (pte++, addr += PAGE_SIZE, addr != end);
@@ -1279,7 +1252,7 @@ static void unmap_page_range(struct mmu_gather *tlb,
pgd_t *pgd;
unsigned long next;
- if (details && !details->check_mapping && !details->nonlinear_vma)
+ if (details && !details->check_mapping)
details = NULL;
BUG_ON(addr >= end);
@@ -1373,7 +1346,7 @@ void unmap_vmas(struct mmu_gather *tlb,
* @vma: vm_area_struct holding the applicable pages
* @start: starting address of pages to zap
* @size: number of bytes to zap
- * @details: details of nonlinear truncation or shared cache invalidation
+ * @details: details of shared cache invalidation
*
* Caller must protect the VMA list
*/
@@ -1399,7 +1372,7 @@ void zap_page_range(struct vm_area_struct *vma, unsigned long start,
* @vma: vm_area_struct holding the applicable pages
* @address: starting address of pages to zap
* @size: number of bytes to zap
- * @details: details of nonlinear truncation or shared cache invalidation
+ * @details: details of shared cache invalidation
*
* The range must fit into one VMA.
*/
@@ -1924,12 +1897,11 @@ int apply_to_page_range(struct mm_struct *mm, unsigned long addr,
EXPORT_SYMBOL_GPL(apply_to_page_range);
/*
- * handle_pte_fault chooses page fault handler according to an entry
- * which was read non-atomically. Before making any commitment, on
- * those architectures or configurations (e.g. i386 with PAE) which
- * might give a mix of unmatched parts, do_swap_page and do_nonlinear_fault
- * must check under lock before unmapping the pte and proceeding
- * (but do_wp_page is only called after already making such a check;
+ * handle_pte_fault chooses page fault handler according to an entry which was
+ * read non-atomically. Before making any commitment, on those architectures
+ * or configurations (e.g. i386 with PAE) which might give a mix of unmatched
+ * parts, do_swap_page must check under lock before unmapping the pte and
+ * proceeding (but do_wp_page is only called after already making such a check;
* and do_anonymous_page can safely check later on).
*/
static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd,
@@ -2035,7 +2007,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
pte_t entry;
int ret = 0;
int page_mkwrite = 0;
- struct page *dirty_page = NULL;
+ bool dirty_shared = false;
unsigned long mmun_start = 0; /* For mmu_notifiers */
unsigned long mmun_end = 0; /* For mmu_notifiers */
struct mem_cgroup *memcg;
@@ -2086,6 +2058,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
unlock_page(old_page);
} else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) ==
(VM_WRITE|VM_SHARED))) {
+ page_cache_get(old_page);
/*
* Only catch write-faults on shared writable pages,
* read-only shared pages can get COWed by
@@ -2093,7 +2066,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
*/
if (vma->vm_ops && vma->vm_ops->page_mkwrite) {
int tmp;
- page_cache_get(old_page);
+
pte_unmap_unlock(page_table, ptl);
tmp = do_page_mkwrite(vma, old_page, address);
if (unlikely(!tmp || (tmp &
@@ -2113,11 +2086,10 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
unlock_page(old_page);
goto unlock;
}
-
page_mkwrite = 1;
}
- dirty_page = old_page;
- get_page(dirty_page);
+
+ dirty_shared = true;
reuse:
/*
@@ -2136,20 +2108,20 @@ reuse:
pte_unmap_unlock(page_table, ptl);
ret |= VM_FAULT_WRITE;
- if (!dirty_page)
- return ret;
-
- if (!page_mkwrite) {
+ if (dirty_shared) {
struct address_space *mapping;
int dirtied;
- lock_page(dirty_page);
- dirtied = set_page_dirty(dirty_page);
- VM_BUG_ON_PAGE(PageAnon(dirty_page), dirty_page);
- mapping = dirty_page->mapping;
- unlock_page(dirty_page);
+ if (!page_mkwrite)
+ lock_page(old_page);
- if (dirtied && mapping) {
+ dirtied = set_page_dirty(old_page);
+ VM_BUG_ON_PAGE(PageAnon(old_page), old_page);
+ mapping = old_page->mapping;
+ unlock_page(old_page);
+ page_cache_release(old_page);
+
+ if ((dirtied || page_mkwrite) && mapping) {
/*
* Some device drivers do not set page.mapping
* but still dirty their pages
@@ -2157,25 +2129,9 @@ reuse:
balance_dirty_pages_ratelimited(mapping);
}
- /* file_update_time outside page_lock */
- if (vma->vm_file)
+ if (!page_mkwrite)
file_update_time(vma->vm_file);
}
- put_page(dirty_page);
- if (page_mkwrite) {
- struct address_space *mapping = dirty_page->mapping;
-
- set_page_dirty(dirty_page);
- unlock_page(dirty_page);
- page_cache_release(dirty_page);
- if (mapping) {
- /*
- * Some device drivers do not set page.mapping
- * but still dirty their pages
- */
- balance_dirty_pages_ratelimited(mapping);
- }
- }
return ret;
}
@@ -2333,25 +2289,11 @@ static inline void unmap_mapping_range_tree(struct rb_root *root,
}
}
-static inline void unmap_mapping_range_list(struct list_head *head,
- struct zap_details *details)
-{
- struct vm_area_struct *vma;
-
- /*
- * In nonlinear VMAs there is no correspondence between virtual address
- * offset and file offset. So we must perform an exhaustive search
- * across *all* the pages in each nonlinear VMA, not just the pages
- * whose virtual address lies outside the file truncation point.
- */
- list_for_each_entry(vma, head, shared.nonlinear) {
- details->nonlinear_vma = vma;
- unmap_mapping_range_vma(vma, vma->vm_start, vma->vm_end, details);
- }
-}
-
/**
- * unmap_mapping_range - unmap the portion of all mmaps in the specified address_space corresponding to the specified page range in the underlying file.
+ * unmap_mapping_range - unmap the portion of all mmaps in the specified
+ * address_space corresponding to the specified page range in the underlying
+ * file.
+ *
* @mapping: the address space containing mmaps to be unmapped.
* @holebegin: byte in first page to unmap, relative to the start of
* the underlying file. This will be rounded down to a PAGE_SIZE
@@ -2380,7 +2322,6 @@ void unmap_mapping_range(struct address_space *mapping,
}
details.check_mapping = even_cows? NULL: mapping;
- details.nonlinear_vma = NULL;
details.first_index = hba;
details.last_index = hba + hlen - 1;
if (details.last_index < details.first_index)
@@ -2390,8 +2331,6 @@ void unmap_mapping_range(struct address_space *mapping,
i_mmap_lock_write(mapping);
if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap)))
unmap_mapping_range_tree(&mapping->i_mmap, &details);
- if (unlikely(!list_empty(&mapping->i_mmap_nonlinear)))
- unmap_mapping_range_list(&mapping->i_mmap_nonlinear, &details);
i_mmap_unlock_write(mapping);
}
EXPORT_SYMBOL(unmap_mapping_range);
@@ -2752,8 +2691,6 @@ void do_set_pte(struct vm_area_struct *vma, unsigned long address,
entry = mk_pte(page, vma->vm_page_prot);
if (write)
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
- else if (pte_file(*pte) && pte_file_soft_dirty(*pte))
- entry = pte_mksoft_dirty(entry);
if (anon) {
inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
page_add_new_anon_rmap(page, vma, address);
@@ -2888,8 +2825,7 @@ static int do_read_fault(struct mm_struct *mm, struct vm_area_struct *vma,
* if page by the offset is not ready to be mapped (cold cache or
* something).
*/
- if (vma->vm_ops->map_pages && !(flags & FAULT_FLAG_NONLINEAR) &&
- fault_around_bytes >> PAGE_SHIFT > 1) {
+ if (vma->vm_ops->map_pages && fault_around_bytes >> PAGE_SHIFT > 1) {
pte = pte_offset_map_lock(mm, pmd, address, &ptl);
do_fault_around(vma, address, pte, pgoff, flags);
if (!pte_same(*pte, orig_pte))
@@ -3021,8 +2957,7 @@ static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma,
balance_dirty_pages_ratelimited(mapping);
}
- /* file_update_time outside page_lock */
- if (vma->vm_file && !vma->vm_ops->page_mkwrite)
+ if (!vma->vm_ops->page_mkwrite)
file_update_time(vma->vm_file);
return ret;
@@ -3034,7 +2969,7 @@ static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma,
* The mmap_sem may have been released depending on flags and our
* return value. See filemap_fault() and __lock_page_or_retry().
*/
-static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
+static int do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, pte_t *page_table, pmd_t *pmd,
unsigned int flags, pte_t orig_pte)
{
@@ -3051,46 +2986,6 @@ static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
return do_shared_fault(mm, vma, address, pmd, pgoff, flags, orig_pte);
}
-/*
- * Fault of a previously existing named mapping. Repopulate the pte
- * from the encoded file_pte if possible. This enables swappable
- * nonlinear vmas.
- *
- * We enter with non-exclusive mmap_sem (to exclude vma changes,
- * but allow concurrent faults), and pte mapped but not yet locked.
- * We return with pte unmapped and unlocked.
- * The mmap_sem may have been released depending on flags and our
- * return value. See filemap_fault() and __lock_page_or_retry().
- */
-static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
- unsigned long address, pte_t *page_table, pmd_t *pmd,
- unsigned int flags, pte_t orig_pte)
-{
- pgoff_t pgoff;
-
- flags |= FAULT_FLAG_NONLINEAR;
-
- if (!pte_unmap_same(mm, pmd, page_table, orig_pte))
- return 0;
-
- if (unlikely(!(vma->vm_flags & VM_NONLINEAR))) {
- /*
- * Page table corrupted: show pte and kill process.
- */
- print_bad_pte(vma, address, orig_pte, NULL);
- return VM_FAULT_SIGBUS;
- }
-
- pgoff = pte_to_pgoff(orig_pte);
- if (!(flags & FAULT_FLAG_WRITE))
- return do_read_fault(mm, vma, address, pmd, pgoff, flags,
- orig_pte);
- if (!(vma->vm_flags & VM_SHARED))
- return do_cow_fault(mm, vma, address, pmd, pgoff, flags,
- orig_pte);
- return do_shared_fault(mm, vma, address, pmd, pgoff, flags, orig_pte);
-}
-
static int numa_migrate_prep(struct page *page, struct vm_area_struct *vma,
unsigned long addr, int page_nid,
int *flags)
@@ -3218,15 +3113,12 @@ static int handle_pte_fault(struct mm_struct *mm,
if (pte_none(entry)) {
if (vma->vm_ops) {
if (likely(vma->vm_ops->fault))
- return do_linear_fault(mm, vma, address,
- pte, pmd, flags, entry);
+ return do_fault(mm, vma, address, pte,
+ pmd, flags, entry);
}
return do_anonymous_page(mm, vma, address,
pte, pmd, flags);
}
- if (pte_file(entry))
- return do_nonlinear_fault(mm, vma, address,
- pte, pmd, flags, entry);
return do_swap_page(mm, vma, address,
pte, pmd, flags, entry);
}