if (!shmem_inode_acct_block(inode, pages))
return false;
+ /* nrpages adjustment first, then shmem_recalc_inode() when balanced */
+ inode->i_mapping->nrpages += pages;
+
spin_lock_irqsave(&info->lock, flags);
info->alloced += pages;
inode->i_blocks += pages * BLOCKS_PER_PAGE;
shmem_recalc_inode(inode);
spin_unlock_irqrestore(&info->lock, flags);
- inode->i_mapping->nrpages += pages;
return true;
}
struct shmem_inode_info *info = SHMEM_I(inode);
unsigned long flags;
+ /* nrpages adjustment done by __delete_from_page_cache() or caller */
+
spin_lock_irqsave(&info->lock, flags);
info->alloced -= pages;
inode->i_blocks -= pages * BLOCKS_PER_PAGE;
{
struct page *oldpage, *newpage;
struct address_space *swap_mapping;
+ swp_entry_t entry;
pgoff_t swap_index;
int error;
oldpage = *pagep;
- swap_index = page_private(oldpage);
+ entry.val = page_private(oldpage);
+ swap_index = swp_offset(entry);
swap_mapping = page_mapping(oldpage);
/*
__SetPageLocked(newpage);
__SetPageSwapBacked(newpage);
SetPageUptodate(newpage);
- set_page_private(newpage, swap_index);
+ set_page_private(newpage, entry.val);
SetPageSwapCache(newpage);
/*
/*
* Our priority is to support MAP_SHARED mapped hugely;
* and support MAP_PRIVATE mapped hugely too, until it is COWed.
- * But if caller specified an address hint, respect that as before.
+ * But if caller specified an address hint and we allocated area there
+ * successfully, respect that as before.
*/
- if (uaddr)
+ if (uaddr == addr)
return addr;
if (shmem_huge != SHMEM_HUGE_FORCE) {
if (inflated_len < len)
return addr;
- inflated_addr = get_area(NULL, 0, inflated_len, 0, flags);
+ inflated_addr = get_area(NULL, uaddr, inflated_len, 0, flags);
if (IS_ERR_VALUE(inflated_addr))
return addr;
if (inflated_addr & ~PAGE_MASK)
struct shmem_inode_info *info = SHMEM_I(inode);
int retval = -ENOMEM;
- spin_lock_irq(&info->lock);
+ /*
+ * What serializes the accesses to info->flags?
+ * ipc_lock_object() when called from shmctl_do_lock(),
+ * no serialization needed when called from shm_destroy().
+ */
if (lock && !(info->flags & VM_LOCKED)) {
if (!user_shm_lock(inode->i_size, user))
goto out_nomem;
retval = 0;
out_nomem:
- spin_unlock_irq(&info->lock);
return retval;
}
struct page *page;
pte_t _dst_pte, *dst_pte;
int ret;
+ pgoff_t offset, max_off;
ret = -ENOMEM;
if (!shmem_inode_acct_block(inode, 1))
*pagep = page;
shmem_inode_unacct_blocks(inode, 1);
/* don't free the page */
- return -EFAULT;
+ return -ENOENT;
}
} else { /* mfill_zeropage_atomic */
clear_highpage(page);
__SetPageSwapBacked(page);
__SetPageUptodate(page);
+ ret = -EFAULT;
+ offset = linear_page_index(dst_vma, dst_addr);
+ max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
+ if (unlikely(offset >= max_off))
+ goto out_release;
+
ret = mem_cgroup_try_charge(page, dst_mm, gfp, &memcg, false);
if (ret)
goto out_release;
_dst_pte = mk_pte(page, dst_vma->vm_page_prot);
if (dst_vma->vm_flags & VM_WRITE)
_dst_pte = pte_mkwrite(pte_mkdirty(_dst_pte));
+ else {
+ /*
+ * We don't set the pte dirty if the vma has no
+ * VM_WRITE permission, so mark the page dirty or it
+ * could be freed from under us. We could do it
+ * unconditionally before unlock_page(), but doing it
+ * only if VM_WRITE is not set is faster.
+ */
+ set_page_dirty(page);
+ }
- ret = -EEXIST;
dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl);
+
+ ret = -EFAULT;
+ max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
+ if (unlikely(offset >= max_off))
+ goto out_release_uncharge_unlock;
+
+ ret = -EEXIST;
if (!pte_none(*dst_pte))
goto out_release_uncharge_unlock;
lru_cache_add_anon(page);
- spin_lock(&info->lock);
+ spin_lock_irq(&info->lock);
info->alloced++;
inode->i_blocks += BLOCKS_PER_PAGE;
shmem_recalc_inode(inode);
- spin_unlock(&info->lock);
+ spin_unlock_irq(&info->lock);
inc_mm_counter(dst_mm, mm_counter_file(page));
page_add_file_rmap(page, false);
/* No need to invalidate - it was non-present before */
update_mmu_cache(dst_vma, dst_addr, dst_pte);
- unlock_page(page);
pte_unmap_unlock(dst_pte, ptl);
+ unlock_page(page);
ret = 0;
out:
return ret;
out_release_uncharge_unlock:
pte_unmap_unlock(dst_pte, ptl);
+ ClearPageDirty(page);
+ delete_from_page_cache(page);
out_release_uncharge:
mem_cgroup_cancel_charge(page, memcg, false);
out_release:
inode_lock(inode);
/* We're holding i_mutex so we can access i_size directly */
- if (offset < 0)
- offset = -EINVAL;
- else if (offset >= inode->i_size)
+ if (offset < 0 || offset >= inode->i_size)
offset = -ENXIO;
else {
start = offset >> PAGE_SHIFT;
void **slot;
pgoff_t start;
struct page *page;
+ unsigned int tagged = 0;
lru_add_drain();
start = 0;
- rcu_read_lock();
+ spin_lock_irq(&mapping->tree_lock);
radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) {
- page = radix_tree_deref_slot(slot);
+ page = radix_tree_deref_slot_protected(slot, &mapping->tree_lock);
if (!page || radix_tree_exception(page)) {
if (radix_tree_deref_retry(page)) {
slot = radix_tree_iter_retry(&iter);
continue;
}
} else if (page_count(page) - page_mapcount(page) > 1) {
- spin_lock_irq(&mapping->tree_lock);
radix_tree_tag_set(&mapping->page_tree, iter.index,
SHMEM_TAG_PINNED);
- spin_unlock_irq(&mapping->tree_lock);
}
- if (need_resched()) {
- slot = radix_tree_iter_resume(slot, &iter);
- cond_resched_rcu();
- }
+ if (++tagged % 1024)
+ continue;
+
+ slot = radix_tree_iter_resume(slot, &iter);
+ spin_unlock_irq(&mapping->tree_lock);
+ cond_resched();
+ spin_lock_irq(&mapping->tree_lock);
}
- rcu_read_unlock();
+ spin_unlock_irq(&mapping->tree_lock);
}
/*
}
shmem_falloc.waitq = &shmem_falloc_waitq;
- shmem_falloc.start = unmap_start >> PAGE_SHIFT;
+ shmem_falloc.start = (u64)unmap_start >> PAGE_SHIFT;
shmem_falloc.next = (unmap_end + 1) >> PAGE_SHIFT;
spin_lock(&inode->i_lock);
inode->i_private = &shmem_falloc;
static int shmem_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry)
{
struct inode *inode = d_inode(old_dentry);
- int ret;
+ int ret = 0;
/*
* No ordinary (disk based) filesystem counts links as inodes;
* but each new link needs a new dentry, pinning lowmem, and
* tmpfs dentries cannot be pruned until they are unlinked.
+ * But if an O_TMPFILE file is linked into the tmpfs, the
+ * first link must skip that, to get the accounting right.
*/
- ret = shmem_reserve_inode(inode->i_sb);
- if (ret)
- goto out;
+ if (inode->i_nlink) {
+ ret = shmem_reserve_inode(inode->i_sb);
+ if (ret)
+ goto out;
+ }
dir->i_size += BOGO_DIRENT_SIZE;
inode->i_ctime = dir->i_ctime = dir->i_mtime = current_time(inode);