* and ZONE_HIGHMEM.
*/
void * high_memory;
-unsigned long vmalloc_earlyreserve;
EXPORT_SYMBOL(num_physpages);
EXPORT_SYMBOL(high_memory);
-EXPORT_SYMBOL(vmalloc_earlyreserve);
int randomize_va_space __read_mostly = 1;
page = vm_normal_page(vma, addr, pte);
if (page) {
get_page(page);
- page_dup_rmap(page);
+ page_dup_rmap(page, vma, addr);
rss[!!PageAnon(page)]++;
}
if (pages)
foll_flags |= FOLL_GET;
if (!write && !(vma->vm_flags & VM_LOCKED) &&
- (!vma->vm_ops || !vma->vm_ops->nopage))
+ (!vma->vm_ops || (!vma->vm_ops->nopage &&
+ !vma->vm_ops->fault)))
foll_flags |= FOLL_ANON;
do {
struct page *page;
+ /*
+ * If tsk is ooming, cut off its access to large memory
+ * allocations. It has a pending SIGKILL, but it can't
+ * be processed until returning to user space.
+ */
+ if (unlikely(test_tsk_thread_flag(tsk, TIF_MEMDIE)))
+ return -ENOMEM;
+
if (write)
foll_flags |= FOLL_WRITE;
}
EXPORT_SYMBOL(remap_pfn_range);
+static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
+ unsigned long addr, unsigned long end,
+ pte_fn_t fn, void *data)
+{
+ pte_t *pte;
+ int err;
+ struct page *pmd_page;
+ spinlock_t *uninitialized_var(ptl);
+
+ pte = (mm == &init_mm) ?
+ pte_alloc_kernel(pmd, addr) :
+ pte_alloc_map_lock(mm, pmd, addr, &ptl);
+ if (!pte)
+ return -ENOMEM;
+
+ BUG_ON(pmd_huge(*pmd));
+
+ pmd_page = pmd_page(*pmd);
+
+ do {
+ err = fn(pte, pmd_page, addr, data);
+ if (err)
+ break;
+ } while (pte++, addr += PAGE_SIZE, addr != end);
+
+ if (mm != &init_mm)
+ pte_unmap_unlock(pte-1, ptl);
+ return err;
+}
+
+static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud,
+ unsigned long addr, unsigned long end,
+ pte_fn_t fn, void *data)
+{
+ pmd_t *pmd;
+ unsigned long next;
+ int err;
+
+ pmd = pmd_alloc(mm, pud, addr);
+ if (!pmd)
+ return -ENOMEM;
+ do {
+ next = pmd_addr_end(addr, end);
+ err = apply_to_pte_range(mm, pmd, addr, next, fn, data);
+ if (err)
+ break;
+ } while (pmd++, addr = next, addr != end);
+ return err;
+}
+
+static int apply_to_pud_range(struct mm_struct *mm, pgd_t *pgd,
+ unsigned long addr, unsigned long end,
+ pte_fn_t fn, void *data)
+{
+ pud_t *pud;
+ unsigned long next;
+ int err;
+
+ pud = pud_alloc(mm, pgd, addr);
+ if (!pud)
+ return -ENOMEM;
+ do {
+ next = pud_addr_end(addr, end);
+ err = apply_to_pmd_range(mm, pud, addr, next, fn, data);
+ if (err)
+ break;
+ } while (pud++, addr = next, addr != end);
+ return err;
+}
+
+/*
+ * Scan a region of virtual memory, filling in page tables as necessary
+ * and calling a provided function on each leaf page table.
+ */
+int apply_to_page_range(struct mm_struct *mm, unsigned long addr,
+ unsigned long size, pte_fn_t fn, void *data)
+{
+ pgd_t *pgd;
+ unsigned long next;
+ unsigned long end = addr + size;
+ int err;
+
+ BUG_ON(addr >= end);
+ pgd = pgd_offset(mm, addr);
+ do {
+ next = pgd_addr_end(addr, end);
+ err = apply_to_pud_range(mm, pgd, addr, next, fn, data);
+ if (err)
+ break;
+ } while (pgd++, addr = next, addr != end);
+ return err;
+}
+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
flush_cache_page(vma, address, pte_pfn(orig_pte));
entry = pte_mkyoung(orig_pte);
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
- ptep_set_access_flags(vma, address, page_table, entry, 1);
- update_mmu_cache(vma, address, entry);
- lazy_mmu_prot_update(entry);
+ if (ptep_set_access_flags(vma, address, page_table, entry,1)) {
+ update_mmu_cache(vma, address, entry);
+ lazy_mmu_prot_update(entry);
+ }
ret |= VM_FAULT_WRITE;
goto unlock;
}
if (unlikely(anon_vma_prepare(vma)))
goto oom;
if (old_page == ZERO_PAGE(address)) {
- new_page = alloc_zeroed_user_highpage(vma, address);
+ new_page = alloc_zeroed_user_highpage_movable(vma, address);
if (!new_page)
goto oom;
} else {
- new_page = alloc_page_vma(GFP_HIGHUSER, vma, address);
+ new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
if (!new_page)
goto oom;
cow_user_page(new_page, old_page, address, vma);
unsigned long restart_addr;
int need_break;
+ /*
+ * files that support invalidating or truncating portions of the
+ * file from under mmaped areas must set the VM_CAN_INVALIDATE flag, and
+ * have their .nopage function return the page locked.
+ */
+ BUG_ON(!(vma->vm_flags & VM_CAN_INVALIDATE));
+
again:
restart_addr = vma->vm_truncate_count;
if (is_restart_addr(restart_addr) && start_addr < restart_addr) {
spin_lock(&mapping->i_mmap_lock);
- /* serialize i_size write against truncate_count write */
- smp_wmb();
- /* Protect against page faults, and endless unmapping loops */
+ /* Protect against endless unmapping loops */
mapping->truncate_count++;
- /*
- * For archs where spin_lock has inclusive semantics like ia64
- * this smp_mb() will prevent to read pagetable contents
- * before the truncate_count increment is visible to
- * other cpus.
- */
- smp_mb();
if (unlikely(is_restart_addr(mapping->truncate_count))) {
if (mapping->truncate_count == 0)
reset_vma_truncate_counts(mapping);
if (IS_SWAPFILE(inode))
goto out_busy;
i_size_write(inode, offset);
+
+ /*
+ * unmap_mapping_range is called twice, first simply for efficiency
+ * so that truncate_inode_pages does fewer single-page unmaps. However
+ * after this first call, and before truncate_inode_pages finishes,
+ * it is possible for private pages to be COWed, which remain after
+ * truncate_inode_pages finishes, hence the second unmap_mapping_range
+ * call must be made for correctness.
+ */
unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
truncate_inode_pages(mapping, offset);
+ unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
goto out_truncate;
do_expand:
down_write(&inode->i_alloc_sem);
unmap_mapping_range(mapping, offset, (end - offset), 1);
truncate_inode_pages_range(mapping, offset, end);
+ unmap_mapping_range(mapping, offset, (end - offset), 1);
inode->i_op->truncate_range(inode, offset, end);
up_write(&inode->i_alloc_sem);
mutex_unlock(&inode->i_mutex);
/* No need to invalidate - it was non-present before */
update_mmu_cache(vma, address, pte);
- lazy_mmu_prot_update(pte);
unlock:
pte_unmap_unlock(page_table, ptl);
out:
if (unlikely(anon_vma_prepare(vma)))
goto oom;
- page = alloc_zeroed_user_highpage(vma, address);
+ page = alloc_zeroed_user_highpage_movable(vma, address);
if (!page)
goto oom;
}
/*
- * do_no_page() tries to create a new page mapping. It aggressively
+ * __do_fault() tries to create a new page mapping. It aggressively
* tries to share with existing pages, but makes a separate copy if
- * the "write_access" parameter is true in order to avoid the next
- * page fault.
+ * the FAULT_FLAG_WRITE is set in the flags parameter in order to avoid
+ * the next page fault.
*
* As this is called only for pages that do not currently exist, we
* do not need to flush old virtual caches or the TLB.
* but allow concurrent faults), and pte mapped but not yet locked.
* We return with mmap_sem still held, but pte unmapped and unlocked.
*/
-static int do_no_page(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,
- int write_access)
+ pgoff_t pgoff, unsigned int flags, pte_t orig_pte)
{
spinlock_t *ptl;
- struct page *new_page;
- struct address_space *mapping = NULL;
+ struct page *page, *faulted_page;
pte_t entry;
- unsigned int sequence = 0;
- int ret = VM_FAULT_MINOR;
int anon = 0;
struct page *dirty_page = NULL;
+ struct fault_data fdata;
+
+ fdata.address = address & PAGE_MASK;
+ fdata.pgoff = pgoff;
+ fdata.flags = flags;
pte_unmap(page_table);
BUG_ON(vma->vm_flags & VM_PFNMAP);
- if (vma->vm_file) {
- mapping = vma->vm_file->f_mapping;
- sequence = mapping->truncate_count;
- smp_rmb(); /* serializes i_size against truncate_count */
+ if (likely(vma->vm_ops->fault)) {
+ fdata.type = -1;
+ faulted_page = vma->vm_ops->fault(vma, &fdata);
+ WARN_ON(fdata.type == -1);
+ if (unlikely(!faulted_page))
+ return fdata.type;
+ } else {
+ /* Legacy ->nopage path */
+ fdata.type = VM_FAULT_MINOR;
+ faulted_page = vma->vm_ops->nopage(vma, address & PAGE_MASK,
+ &fdata.type);
+ /* no page was available -- either SIGBUS or OOM */
+ if (unlikely(faulted_page == NOPAGE_SIGBUS))
+ return VM_FAULT_SIGBUS;
+ else if (unlikely(faulted_page == NOPAGE_OOM))
+ return VM_FAULT_OOM;
}
-retry:
- new_page = vma->vm_ops->nopage(vma, address & PAGE_MASK, &ret);
+
/*
- * No smp_rmb is needed here as long as there's a full
- * spin_lock/unlock sequence inside the ->nopage callback
- * (for the pagecache lookup) that acts as an implicit
- * smp_mb() and prevents the i_size read to happen
- * after the next truncate_count read.
+ * For consistency in subsequent calls, make the faulted_page always
+ * locked.
*/
-
- /* no page was available -- either SIGBUS, OOM or REFAULT */
- if (unlikely(new_page == NOPAGE_SIGBUS))
- return VM_FAULT_SIGBUS;
- else if (unlikely(new_page == NOPAGE_OOM))
- return VM_FAULT_OOM;
- else if (unlikely(new_page == NOPAGE_REFAULT))
- return VM_FAULT_MINOR;
+ if (unlikely(!(vma->vm_flags & VM_CAN_INVALIDATE)))
+ lock_page(faulted_page);
+ else
+ BUG_ON(!PageLocked(faulted_page));
/*
* Should we do an early C-O-W break?
*/
- if (write_access) {
+ page = faulted_page;
+ if (flags & FAULT_FLAG_WRITE) {
if (!(vma->vm_flags & VM_SHARED)) {
- struct page *page;
-
- if (unlikely(anon_vma_prepare(vma)))
- goto oom;
- page = alloc_page_vma(GFP_HIGHUSER, vma, address);
- if (!page)
- goto oom;
- copy_user_highpage(page, new_page, address, vma);
- page_cache_release(new_page);
- new_page = page;
anon = 1;
-
+ if (unlikely(anon_vma_prepare(vma))) {
+ fdata.type = VM_FAULT_OOM;
+ goto out;
+ }
+ page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
+ if (!page) {
+ fdata.type = VM_FAULT_OOM;
+ goto out;
+ }
+ copy_user_highpage(page, faulted_page, address, vma);
} else {
- /* if the page will be shareable, see if the backing
+ /*
+ * If the page will be shareable, see if the backing
* address space wants to know that the page is about
- * to become writable */
- if (vma->vm_ops->page_mkwrite &&
- vma->vm_ops->page_mkwrite(vma, new_page) < 0
- ) {
- page_cache_release(new_page);
- return VM_FAULT_SIGBUS;
+ * to become writable
+ */
+ if (vma->vm_ops->page_mkwrite) {
+ unlock_page(page);
+ if (vma->vm_ops->page_mkwrite(vma, page) < 0) {
+ fdata.type = VM_FAULT_SIGBUS;
+ anon = 1; /* no anon but release faulted_page */
+ goto out_unlocked;
+ }
+ lock_page(page);
}
}
+
}
page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
- /*
- * For a file-backed vma, someone could have truncated or otherwise
- * invalidated this page. If unmap_mapping_range got called,
- * retry getting the page.
- */
- if (mapping && unlikely(sequence != mapping->truncate_count)) {
- pte_unmap_unlock(page_table, ptl);
- page_cache_release(new_page);
- cond_resched();
- sequence = mapping->truncate_count;
- smp_rmb();
- goto retry;
- }
/*
* This silly early PAGE_DIRTY setting removes a race
* handle that later.
*/
/* Only go through if we didn't race with anybody else... */
- if (pte_none(*page_table)) {
- flush_icache_page(vma, new_page);
- entry = mk_pte(new_page, vma->vm_page_prot);
- if (write_access)
+ if (likely(pte_same(*page_table, orig_pte))) {
+ flush_icache_page(vma, page);
+ entry = mk_pte(page, vma->vm_page_prot);
+ if (flags & FAULT_FLAG_WRITE)
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
set_pte_at(mm, address, page_table, entry);
if (anon) {
- inc_mm_counter(mm, anon_rss);
- lru_cache_add_active(new_page);
- page_add_new_anon_rmap(new_page, vma, address);
+ inc_mm_counter(mm, anon_rss);
+ lru_cache_add_active(page);
+ page_add_new_anon_rmap(page, vma, address);
} else {
inc_mm_counter(mm, file_rss);
- page_add_file_rmap(new_page);
- if (write_access) {
- dirty_page = new_page;
+ page_add_file_rmap(page);
+ if (flags & FAULT_FLAG_WRITE) {
+ dirty_page = page;
get_page(dirty_page);
}
}
+
+ /* no need to invalidate: a not-present page won't be cached */
+ update_mmu_cache(vma, address, entry);
+ lazy_mmu_prot_update(entry);
} else {
- /* One of our sibling threads was faster, back out. */
- page_cache_release(new_page);
- goto unlock;
+ if (anon)
+ page_cache_release(page);
+ else
+ anon = 1; /* no anon but release faulted_page */
}
- /* no need to invalidate: a not-present page shouldn't be cached */
- update_mmu_cache(vma, address, entry);
- lazy_mmu_prot_update(entry);
-unlock:
pte_unmap_unlock(page_table, ptl);
- if (dirty_page) {
+
+out:
+ unlock_page(faulted_page);
+out_unlocked:
+ if (anon)
+ page_cache_release(faulted_page);
+ else if (dirty_page) {
set_page_dirty_balance(dirty_page);
put_page(dirty_page);
}
- return ret;
-oom:
- page_cache_release(new_page);
- return VM_FAULT_OOM;
+
+ return fdata.type;
+}
+
+static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long address, pte_t *page_table, pmd_t *pmd,
+ int write_access, pte_t orig_pte)
+{
+ pgoff_t pgoff = (((address & PAGE_MASK)
+ - vma->vm_start) >> PAGE_CACHE_SHIFT) + vma->vm_pgoff;
+ unsigned int flags = (write_access ? FAULT_FLAG_WRITE : 0);
+
+ return __do_fault(mm, vma, address, page_table, pmd, pgoff, flags, orig_pte);
+}
+
+static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long address, pte_t *page_table, pmd_t *pmd,
+ int write_access, pgoff_t pgoff, pte_t orig_pte)
+{
+ unsigned int flags = FAULT_FLAG_NONLINEAR |
+ (write_access ? FAULT_FLAG_WRITE : 0);
+
+ return __do_fault(mm, vma, address, page_table, pmd, pgoff, flags, orig_pte);
}
/*
print_bad_pte(vma, orig_pte, address);
return VM_FAULT_OOM;
}
- /* We can then assume vm->vm_ops && vma->vm_ops->populate */
pgoff = pte_to_pgoff(orig_pte);
+
+ if (vma->vm_ops && vma->vm_ops->fault)
+ return do_nonlinear_fault(mm, vma, address, page_table, pmd,
+ write_access, pgoff, orig_pte);
+
+ /* We can then assume vm->vm_ops && vma->vm_ops->populate */
err = vma->vm_ops->populate(vma, address & PAGE_MASK, PAGE_SIZE,
vma->vm_page_prot, pgoff, 0);
if (err == -ENOMEM)
pte_t *pte, pmd_t *pmd, int write_access)
{
pte_t entry;
- pte_t old_entry;
spinlock_t *ptl;
- old_entry = entry = *pte;
+ entry = *pte;
if (!pte_present(entry)) {
if (pte_none(entry)) {
if (vma->vm_ops) {
- if (vma->vm_ops->nopage)
- return do_no_page(mm, vma, address,
- pte, pmd,
- write_access);
+ if (vma->vm_ops->fault || vma->vm_ops->nopage)
+ return do_linear_fault(mm, vma, address,
+ pte, pmd, write_access, entry);
if (unlikely(vma->vm_ops->nopfn))
return do_no_pfn(mm, vma, address, pte,
pmd, write_access);
entry = pte_mkdirty(entry);
}
entry = pte_mkyoung(entry);
- if (!pte_same(old_entry, entry)) {
- ptep_set_access_flags(vma, address, pte, entry, write_access);
+ if (ptep_set_access_flags(vma, address, pte, entry, write_access)) {
update_mmu_cache(vma, address, entry);
lazy_mmu_prot_update(entry);
} else {
spin_unlock(&mm->page_table_lock);
return 0;
}
-#else
-/* Workaround for gcc 2.96 */
-int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
-{
- return 0;
-}
#endif /* __PAGETABLE_PUD_FOLDED */
#ifndef __PAGETABLE_PMD_FOLDED
spin_unlock(&mm->page_table_lock);
return 0;
}
-#else
-/* Workaround for gcc 2.96 */
-int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
-{
- return 0;
-}
#endif /* __PAGETABLE_PMD_FOLDED */
int make_pages_present(unsigned long addr, unsigned long end)
write = (vma->vm_flags & VM_WRITE) != 0;
BUG_ON(addr >= end);
BUG_ON(end > vma->vm_end);
- len = (end+PAGE_SIZE-1)/PAGE_SIZE-addr/PAGE_SIZE;
+ len = DIV_ROUND_UP(end, PAGE_SIZE) - addr/PAGE_SIZE;
ret = get_user_pages(current, current->mm, addr,
len, write, 0, NULL, NULL);
if (ret < 0)
projects / linux-2.6 / blobdiff