/**
* nilfs_copy_page -- copy the page with buffers
* @dst: destination page
* @src: source page
* @copy_dirty: flag whether to copy dirty states on the page's buffer heads.
*
* This function is for both data pages and btnode pages. The dirty flag
* should be treated by caller. The page must not be under i/o.
* Both src and dst page must be locked
*/
static void nilfs_copy_page(struct page *dst, struct page *src, int copy_dirty)
{
struct buffer_head *dbh, *dbufs, *sbh, *sbufs;
unsigned long mask = NILFS_BUFFER_INHERENT_BITS;
BUG_ON(PageWriteback(dst));
sbh = sbufs = page_buffers(src);
if (!page_has_buffers(dst))
create_empty_buffers(dst, sbh->b_size, 0);
if (copy_dirty)
mask |= (1UL << BH_Dirty);
dbh = dbufs = page_buffers(dst);
do {
lock_buffer(sbh);
lock_buffer(dbh);
dbh->b_state = sbh->b_state & mask;
dbh->b_blocknr = sbh->b_blocknr;
dbh->b_bdev = sbh->b_bdev;
sbh = sbh->b_this_page;
dbh = dbh->b_this_page;
} while (dbh != dbufs);
copy_highpage(dst, src);
if (PageUptodate(src) && !PageUptodate(dst))
SetPageUptodate(dst);
else if (!PageUptodate(src) && PageUptodate(dst))
ClearPageUptodate(dst);
if (PageMappedToDisk(src) && !PageMappedToDisk(dst))
SetPageMappedToDisk(dst);
else if (!PageMappedToDisk(src) && PageMappedToDisk(dst))
ClearPageMappedToDisk(dst);
do {
unlock_buffer(sbh);
unlock_buffer(dbh);
sbh = sbh->b_this_page;
dbh = dbh->b_this_page;
} while (dbh != dbufs);
}
int ttm_tt_swapin(struct ttm_tt *ttm)
{
struct address_space *swap_space;
struct file *swap_storage;
struct page *from_page;
struct page *to_page;
int i;
int ret = -ENOMEM;
swap_storage = ttm->swap_storage;
BUG_ON(swap_storage == NULL);
swap_space = swap_storage->f_mapping;
for (i = 0; i < ttm->num_pages; ++i) {
gfp_t gfp_mask = mapping_gfp_mask(swap_space);
gfp_mask |= (ttm->page_flags & TTM_PAGE_FLAG_NO_RETRY ? __GFP_RETRY_MAYFAIL : 0);
from_page = shmem_read_mapping_page_gfp(swap_space, i, gfp_mask);
if (IS_ERR(from_page)) {
ret = PTR_ERR(from_page);
goto out_err;
}
to_page = ttm->pages[i];
if (unlikely(to_page == NULL))
goto out_err;
copy_highpage(to_page, from_page);
put_page(from_page);
}
if (!(ttm->page_flags & TTM_PAGE_FLAG_PERSISTENT_SWAP))
fput(swap_storage);
ttm->swap_storage = NULL;
ttm->page_flags &= ~TTM_PAGE_FLAG_SWAPPED;
return 0;
out_err:
return ret;
}
/*
* NOTE:
* Expect the breakpoint instruction to be the smallest size instruction for
* the architecture. If an arch has variable length instruction and the
* breakpoint instruction is not of the smallest length instruction
* supported by that architecture then we need to modify is_trap_at_addr and
* uprobe_write_opcode accordingly. This would never be a problem for archs
* that have fixed length instructions.
*
* uprobe_write_opcode - write the opcode at a given virtual address.
* @mm: the probed process address space.
* @vaddr: the virtual address to store the opcode.
* @opcode: opcode to be written at @vaddr.
*
* Called with mm->mmap_sem held for write.
* Return 0 (success) or a negative errno.
*/
int uprobe_write_opcode(struct mm_struct *mm, unsigned long vaddr,
uprobe_opcode_t opcode)
{
struct page *old_page, *new_page;
struct vm_area_struct *vma;
int ret;
retry:
/* Read the page with vaddr into memory */
ret = get_user_pages_remote(NULL, mm, vaddr, 1, FOLL_FORCE, &old_page,
&vma);
if (ret <= 0)
return ret;
ret = verify_opcode(old_page, vaddr, &opcode);
if (ret <= 0)
goto put_old;
ret = anon_vma_prepare(vma);
if (ret)
goto put_old;
ret = -ENOMEM;
new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vaddr);
if (!new_page)
goto put_old;
__SetPageUptodate(new_page);
copy_highpage(new_page, old_page);
copy_to_page(new_page, vaddr, &opcode, UPROBE_SWBP_INSN_SIZE);
ret = __replace_page(vma, vaddr, old_page, new_page);
put_page(new_page);
put_old:
put_page(old_page);
if (unlikely(ret == -EAGAIN))
goto retry;
return ret;
}
int ttm_tt_swapin(struct ttm_tt *ttm)
{
struct address_space *swap_space;
struct file *swap_storage;
struct page *from_page;
struct page *to_page;
int i;
int ret = -ENOMEM;
swap_storage = ttm->swap_storage;
BUG_ON(swap_storage == NULL);
swap_space = swap_storage->f_path.dentry->d_inode->i_mapping;
for (i = 0; i < ttm->num_pages; ++i) {
from_page = shmem_read_mapping_page(swap_space, i);
if (IS_ERR(from_page)) {
ret = PTR_ERR(from_page);
goto out_err;
}
to_page = ttm->pages[i];
if (unlikely(to_page == NULL))
goto out_err;
preempt_disable();
copy_highpage(to_page, from_page);
preempt_enable();
page_cache_release(from_page);
}
if (!(ttm->page_flags & TTM_PAGE_FLAG_PERSISTENT_SWAP))
fput(swap_storage);
ttm->swap_storage = NULL;
ttm->page_flags &= ~TTM_PAGE_FLAG_SWAPPED;
return 0;
out_err:
return ret;
}
static int wrapfs_writepage(struct page *page, struct writeback_control *wbc)
{
int err = -EIO;
struct inode *inode;
struct inode *lower_inode;
struct page *lower_page;
struct address_space *lower_mapping; /* lower inode mapping */
gfp_t mask;
/*printk(KERN_ALERT "in writepage() \n");*/
BUG_ON(!PageUptodate(page));
inode = page->mapping->host;
/* if no lower inode, nothing to do */
if (!inode || !WRAPFS_I(inode) || WRAPFS_I(inode)->lower_inode) {
err = 0;
goto out;
}
lower_inode = wrapfs_lower_inode(inode);
lower_mapping = lower_inode->i_mapping;
/*
* find lower page (returns a locked page)
*
* We turn off __GFP_FS while we look for or create a new lower
* page. This prevents a recursion into the file system code, which
* under memory pressure conditions could lead to a deadlock. This
* is similar to how the loop driver behaves (see loop_set_fd in
* drivers/block/loop.c). If we can't find the lower page, we
* redirty our page and return "success" so that the VM will call us
* again in the (hopefully near) future.
*/
mask = mapping_gfp_mask(lower_mapping) & ~(__GFP_FS);
lower_page = find_or_create_page(lower_mapping, page->index, mask);
if (!lower_page) {
err = 0;
set_page_dirty(page);
goto out;
}
/* copy page data from our upper page to the lower page */
copy_highpage(lower_page, page);
flush_dcache_page(lower_page);
SetPageUptodate(lower_page);
set_page_dirty(lower_page);
/*
* Call lower writepage (expects locked page). However, if we are
* called with wbc->for_reclaim, then the VFS/VM just wants to
* reclaim our page. Therefore, we don't need to call the lower
* ->writepage: just copy our data to the lower page (already done
* above), then mark the lower page dirty and unlock it, and return
* success.
*/
if (wbc->for_reclaim) {
unlock_page(lower_page);
goto out_release;
}
BUG_ON(!lower_mapping->a_ops->writepage);
wait_on_page_writeback(lower_page); /* prevent multiple writers */
clear_page_dirty_for_io(lower_page); /* emulate VFS behavior */
err = lower_mapping->a_ops->writepage(lower_page, wbc);
if (err < 0)
goto out_release;
/*
* Lower file systems such as ramfs and tmpfs, may return
* AOP_WRITEPAGE_ACTIVATE so that the VM won't try to (pointlessly)
* write the page again for a while. But those lower file systems
* also set the page dirty bit back again. Since we successfully
* copied our page data to the lower page, then the VM will come
* back to the lower page (directly) and try to flush it. So we can
* save the VM the hassle of coming back to our page and trying to
* flush too. Therefore, we don't re-dirty our own page, and we
* never return AOP_WRITEPAGE_ACTIVATE back to the VM (we consider
* this a success).
*
* We also unlock the lower page if the lower ->writepage returned
* AOP_WRITEPAGE_ACTIVATE. (This "anomalous" behaviour may be
* addressed in future shmem/VM code.)
*/
if (err == AOP_WRITEPAGE_ACTIVATE) {
err = 0;
unlock_page(lower_page);
}
/* all is well */
/* lower mtimes have changed: update ours */
/* fsstack_copy_inode_size(dentry->d_inode,
lower_file->f_path.dentry->d_inode);
fsstack_copy_attr_times(dentry->d_inode,
lower_file->f_path.dentry->d_inode);
*/
out_release:
/* b/c find_or_create_page increased refcnt */
page_cache_release(lower_page);
out:
/*
* We unlock our page unconditionally, because we never return
* AOP_WRITEPAGE_ACTIVATE.
*/
unlock_page(page);
return err;
}
/*
* do_no_page() 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.
*
* As this is called only for pages that do not currently exist, we
* do not need to flush old virtual caches or the TLB.
*
* This is called with the MM semaphore held and the page table
* spinlock held. Exit with the spinlock released.
*/
static int do_no_page(struct mm_struct * mm, struct vm_area_struct * vma,
unsigned long address, int write_access, pte_t *page_table)
{
struct page * new_page;
pte_t entry;
if (!vma->vm_ops || !vma->vm_ops->nopage)
return do_anonymous_page(mm, vma, page_table, write_access, address);
spin_unlock(&mm->page_table_lock);
new_page = vma->vm_ops->nopage(vma, address & PAGE_MASK, 0);
if (new_page == NULL) /* no page was available -- SIGBUS */
return 0;
if (new_page == NOPAGE_OOM)
return -1;
/*
* Should we do an early C-O-W break?
*/
if (write_access && !(vma->vm_flags & VM_SHARED)) {
struct page * page = alloc_page(GFP_HIGHUSER);
if (!page) {
page_cache_release(new_page);
return -1;
}
copy_highpage(page, new_page);
page_cache_release(new_page);
lru_cache_add(page);
new_page = page;
}
spin_lock(&mm->page_table_lock);
/*
* This silly early PAGE_DIRTY setting removes a race
* due to the bad i386 page protection. But it's valid
* for other architectures too.
*
* Note that if write_access is true, we either now have
* an exclusive copy of the page, or this is a shared mapping,
* so we can make it writable and dirty to avoid having to
* handle that later.
*/
/* Only go through if we didn't race with anybody else... */
if (pte_none(*page_table)) {
++mm->rss;
flush_page_to_ram(new_page);
flush_icache_page(vma, new_page);
entry = mk_pte(new_page, vma->vm_page_prot);
if (write_access)
entry = pte_mkwrite(pte_mkdirty(entry));
set_pte(page_table, entry);
} else {
/* One of our sibling threads was faster, back out. */
page_cache_release(new_page);
spin_unlock(&mm->page_table_lock);
return 1;
}
/* no need to invalidate: a not-present page shouldn't be cached */
update_mmu_cache(vma, address, entry);
spin_unlock(&mm->page_table_lock);
return 2; /* Major fault */
}
static int wrapfs_writepage(struct page *page, struct writeback_control *wbc)
{
int err = -EIO;
struct inode *inode;
struct inode *lower_inode;
struct page *lower_page;
struct address_space *lower_mapping; /* lower inode mapping */
gfp_t mask;
char *lower_page_data = NULL;
/*#ifdef WRAPFS_CRYPTO
char *enc_buf = NULL;
#endif*/
wrapfs_debug_aops(
WRAPFS_SB(page->mapping->host->i_sb)->wrapfs_debug_a_ops, "");
wrapfs_debug("");
BUG_ON(!PageUptodate(page));
wrapfs_debug("");
inode = page->mapping->host;
/* if no lower inode, nothing to do */
if (!inode || !WRAPFS_I(inode) || WRAPFS_I(inode)->lower_inode) {
err = 0;
goto out;
}
lower_inode = wrapfs_lower_inode(inode);
lower_mapping = lower_inode->i_mapping;
/*
* find lower page (returns a locked page)
*
* We turn off __GFP_FS while we look for or create a new lower
* page. This prevents a recursion into the file system code, which
* under memory pressure conditions could lead to a deadlock. This
* is similar to how the loop driver behaves (see loop_set_fd in
* drivers/block/loop.c). If we can't find the lower page, we
* redirty our page and return "success" so that the VM will call us
* again in the (hopefully near) future.
*/
mask = mapping_gfp_mask(lower_mapping) & ~(__GFP_FS);
lower_page = find_or_create_page(lower_mapping, page->index, mask);
if (!lower_page) {
err = 0;
set_page_dirty(page);
goto out;
}
lower_page_data = (char *)kmap(lower_page);
/* copy page data from our upper page to the lower page */
copy_highpage(lower_page, page);
flush_dcache_page(lower_page);
SetPageUptodate(lower_page);
set_page_dirty(lower_page);
/*#ifdef WRAPFS_CRYPTO
enc_buf = kmalloc(PAGE_CACHE_SIZE, GFP_KERNEL);
if (enc_buf == NULL) {
wrapfs_debug("No memory!!");
err = -ENOMEM;
goto out_release;
}
err = my_encrypt(lower_page_data, PAGE_CACHE_SIZE, enc_buf,
PAGE_CACHE_SIZE,
WRAPFS_SB(inode->i_sb)->key,
WRAPFS_CRYPTO_KEY_LEN);
if (err < 0) {
wrapfs_debug("encrypt error!!");
kfree(enc_buf);
err = -EINVAL;
goto out_release;
}
memcpy(lower_page_data, enc_buf, PAGE_CACHE_SIZE);
kfree(enc_buf);
#endif*/
/*
* Call lower writepage (expects locked page). However, if we are
* called with wbc->for_reclaim, then the VFS/VM just wants to
* reclaim our page. Therefore, we don't need to call the lower
* ->writepage: just copy our data to the lower page (already done
* above), then mark the lower page dirty and unlock it, and return
* success.
*/
/*if (wbc->for_reclaim) {
unlock_page(lower_page);
goto out_release;
}*/
BUG_ON(!lower_mapping->a_ops->writepage);
wait_on_page_writeback(lower_page); /* prevent multiple writers */
clear_page_dirty_for_io(lower_page); /* emulate VFS behavior */
err = lower_mapping->a_ops->writepage(lower_page, wbc);
if (err < 0)
goto out_release;
/*
* Lower file systems such as ramfs and tmpfs, may return
* AOP_WRITEPAGE_ACTIVATE so that the VM won't try to (pointlessly)
* write the page again for a while. But those lower file systems
* also set the page dirty bit back again. Since we successfully
* copied our page data to the lower page, then the VM will come
* back to the lower page (directly) and try to flush it. So we can
* save the VM the hassle of coming back to our page and trying to
* flush too. Therefore, we don't re-dirty our own page, and we
* never return AOP_WRITEPAGE_ACTIVATE back to the VM (we consider
* this a success).
*
* We also unlock the lower page if the lower ->writepage returned
* AOP_WRITEPAGE_ACTIVATE. (This "anomalous" behaviour may be
* addressed in future shmem/VM code.)
*/
if (err == AOP_WRITEPAGE_ACTIVATE) {
err = 0;
unlock_page(lower_page);
}
out_release:
kunmap(lower_page);
/* b/c find_or_create_page increased refcnt */
page_cache_release(lower_page);
out:
/*
* We unlock our page unconditionally, because we never return
* AOP_WRITEPAGE_ACTIVATE.
*/
unlock_page(page);
wrapfs_debug_aops(WRAPFS_SB(inode->i_sb)->wrapfs_debug_a_ops,
"err : %d", err);
return err;
}