struct dentry *f2fs_get_parent(struct dentry *child)
{
struct qstr dotdot = {.name = "..", .len = 2};
unsigned long ino = f2fs_inode_by_name(child->d_inode, &dotdot);
if (!ino)
return ERR_PTR(-ENOENT);
return d_obtain_alias(f2fs_iget(child->d_inode->i_sb, ino));
}
static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
struct nameidata *nd)
{
struct inode *inode = NULL;
struct f2fs_dir_entry *de;
struct page *page;
if (dentry->d_name.len > F2FS_NAME_LEN)
return ERR_PTR(-ENAMETOOLONG);
de = f2fs_find_entry(dir, &dentry->d_name, &page);
if (de) {
nid_t ino = le32_to_cpu(de->ino);
kunmap(page);
f2fs_put_page(page, 0);
inode = f2fs_iget(dir->i_sb, ino);
if (IS_ERR(inode))
return ERR_CAST(inode);
}
return d_splice_alias(inode, dentry);
}
static int f2fs_unlink(struct inode *dir, struct dentry *dentry)
{
struct super_block *sb = dir->i_sb;
struct f2fs_sb_info *sbi = F2FS_SB(sb);
struct inode *inode = dentry->d_inode;
struct f2fs_dir_entry *de;
struct page *page;
int err = -ENOENT;
trace_f2fs_unlink_enter(dir, dentry);
f2fs_balance_fs(sbi);
de = f2fs_find_entry(dir, &dentry->d_name, &page);
if (!de)
goto fail;
f2fs_lock_op(sbi);
err = acquire_orphan_inode(sbi);
if (err) {
f2fs_unlock_op(sbi);
kunmap(page);
f2fs_put_page(page, 0);
goto fail;
}
f2fs_delete_entry(de, page, inode);
f2fs_unlock_op(sbi);
/* In order to evict this inode, we set it dirty */
mark_inode_dirty(inode);
fail:
trace_f2fs_unlink_exit(inode, err);
return err;
}
static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
const char *symname)
{
struct super_block *sb = dir->i_sb;
struct f2fs_sb_info *sbi = F2FS_SB(sb);
struct inode *inode;
size_t symlen = strlen(symname) + 1;
int err;
f2fs_balance_fs(sbi);
inode = f2fs_new_inode(dir, S_IFLNK | S_IRWXUGO);
if (IS_ERR(inode))
return PTR_ERR(inode);
inode->i_op = &f2fs_symlink_inode_operations;
inode->i_mapping->a_ops = &f2fs_dblock_aops;
f2fs_lock_op(sbi);
err = f2fs_add_link(dentry, inode);
f2fs_unlock_op(sbi);
if (err)
goto out;
err = page_symlink(inode, symname, symlen);
alloc_nid_done(sbi, inode->i_ino);
d_instantiate(dentry, inode);
unlock_new_inode(inode);
return err;
out:
clear_nlink(inode);
unlock_new_inode(inode);
make_bad_inode(inode);
iput(inode);
alloc_nid_failed(sbi, inode->i_ino);
return err;
}
static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
{
struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
struct inode *inode;
int err;
f2fs_balance_fs(sbi);
inode = f2fs_new_inode(dir, S_IFDIR | mode);
if (IS_ERR(inode))
return PTR_ERR(inode);
inode->i_op = &f2fs_dir_inode_operations;
inode->i_fop = &f2fs_dir_operations;
inode->i_mapping->a_ops = &f2fs_dblock_aops;
mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_ZERO);
set_inode_flag(F2FS_I(inode), FI_INC_LINK);
f2fs_lock_op(sbi);
err = f2fs_add_link(dentry, inode);
f2fs_unlock_op(sbi);
if (err)
goto out_fail;
alloc_nid_done(sbi, inode->i_ino);
d_instantiate(dentry, inode);
unlock_new_inode(inode);
return 0;
out_fail:
clear_inode_flag(F2FS_I(inode), FI_INC_LINK);
clear_nlink(inode);
unlock_new_inode(inode);
make_bad_inode(inode);
iput(inode);
alloc_nid_failed(sbi, inode->i_ino);
return err;
}
static int f2fs_rmdir(struct inode *dir, struct dentry *dentry)
{
struct inode *inode = dentry->d_inode;
if (f2fs_empty_dir(inode))
return f2fs_unlink(dir, dentry);
return -ENOTEMPTY;
}
static int f2fs_mknod(struct inode *dir, struct dentry *dentry,
umode_t mode, dev_t rdev)
{
struct super_block *sb = dir->i_sb;
struct f2fs_sb_info *sbi = F2FS_SB(sb);
struct inode *inode;
int err = 0;
if (!new_valid_dev(rdev))
return -EINVAL;
f2fs_balance_fs(sbi);
inode = f2fs_new_inode(dir, mode);
if (IS_ERR(inode))
return PTR_ERR(inode);
init_special_inode(inode, inode->i_mode, rdev);
inode->i_op = &f2fs_special_inode_operations;
f2fs_lock_op(sbi);
err = f2fs_add_link(dentry, inode);
f2fs_unlock_op(sbi);
if (err)
goto out;
alloc_nid_done(sbi, inode->i_ino);
d_instantiate(dentry, inode);
unlock_new_inode(inode);
return 0;
out:
clear_nlink(inode);
unlock_new_inode(inode);
make_bad_inode(inode);
iput(inode);
alloc_nid_failed(sbi, inode->i_ino);
return err;
}
static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry)
{
struct super_block *sb = old_dir->i_sb;
struct f2fs_sb_info *sbi = F2FS_SB(sb);
struct inode *old_inode = old_dentry->d_inode;
struct inode *new_inode = new_dentry->d_inode;
struct page *old_dir_page;
struct page *old_page, *new_page;
struct f2fs_dir_entry *old_dir_entry = NULL;
struct f2fs_dir_entry *old_entry;
struct f2fs_dir_entry *new_entry;
int err = -ENOENT;
f2fs_balance_fs(sbi);
old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page);
if (!old_entry)
goto out;
if (S_ISDIR(old_inode->i_mode)) {
err = -EIO;
old_dir_entry = f2fs_parent_dir(old_inode, &old_dir_page);
if (!old_dir_entry)
goto out_old;
}
f2fs_lock_op(sbi);
if (new_inode) {
err = -ENOTEMPTY;
if (old_dir_entry && !f2fs_empty_dir(new_inode))
goto out_dir;
err = -ENOENT;
new_entry = f2fs_find_entry(new_dir, &new_dentry->d_name,
&new_page);
if (!new_entry)
goto out_dir;
err = acquire_orphan_inode(sbi);
if (err)
goto put_out_dir;
if (update_dent_inode(old_inode, &new_dentry->d_name)) {
release_orphan_inode(sbi);
goto put_out_dir;
}
f2fs_set_link(new_dir, new_entry, new_page, old_inode);
F2FS_I(old_inode)->i_pino = new_dir->i_ino;
new_inode->i_ctime = CURRENT_TIME;
if (old_dir_entry)
drop_nlink(new_inode);
drop_nlink(new_inode);
mark_inode_dirty(new_inode);
if (!new_inode->i_nlink)
add_orphan_inode(sbi, new_inode->i_ino);
else
release_orphan_inode(sbi);
update_inode_page(old_inode);
update_inode_page(new_inode);
} else {
err = f2fs_add_link(new_dentry, old_inode);
if (err)
goto out_dir;
if (old_dir_entry) {
inc_nlink(new_dir);
update_inode_page(new_dir);
}
}
old_inode->i_ctime = CURRENT_TIME;
mark_inode_dirty(old_inode);
f2fs_delete_entry(old_entry, old_page, NULL);
if (old_dir_entry) {
if (old_dir != new_dir) {
f2fs_set_link(old_inode, old_dir_entry,
old_dir_page, new_dir);
F2FS_I(old_inode)->i_pino = new_dir->i_ino;
update_inode_page(old_inode);
} else {
kunmap(old_dir_page);
f2fs_put_page(old_dir_page, 0);
}
drop_nlink(old_dir);
mark_inode_dirty(old_dir);
update_inode_page(old_dir);
}
f2fs_unlock_op(sbi);
return 0;
put_out_dir:
if (PageLocked(new_page))
f2fs_put_page(new_page, 1);
else
f2fs_put_page(new_page, 0);
out_dir:
if (old_dir_entry) {
kunmap(old_dir_page);
f2fs_put_page(old_dir_page, 0);
}
f2fs_unlock_op(sbi);
out_old:
kunmap(old_page);
f2fs_put_page(old_page, 0);
out:
return err;
}
const struct inode_operations f2fs_dir_inode_operations = {
.create = f2fs_create,
.lookup = f2fs_lookup,
.link = f2fs_link,
.unlink = f2fs_unlink,
.symlink = f2fs_symlink,
.mkdir = f2fs_mkdir,
.rmdir = f2fs_rmdir,
.mknod = f2fs_mknod,
.rename = f2fs_rename,
.getattr = f2fs_getattr,
.setattr = f2fs_setattr,
.get_acl = f2fs_get_acl,
#ifdef CONFIG_F2FS_FS_XATTR
.setxattr = generic_setxattr,
.getxattr = generic_getxattr,
.listxattr = f2fs_listxattr,
.removexattr = generic_removexattr,
#endif
};
const struct inode_operations f2fs_symlink_inode_operations = {
.readlink = generic_readlink,
.follow_link = page_follow_link_light,
.put_link = page_put_link,
.getattr = f2fs_getattr,
.setattr = f2fs_setattr,
#ifdef CONFIG_F2FS_FS_XATTR
.setxattr = generic_setxattr,
.getxattr = generic_getxattr,
.listxattr = f2fs_listxattr,
.removexattr = generic_removexattr,
#endif
};
const struct inode_operations f2fs_special_inode_operations = {
.getattr = f2fs_getattr,
.setattr = f2fs_setattr,
.get_acl = f2fs_get_acl,
#ifdef CONFIG_F2FS_FS_XATTR
.setxattr = generic_setxattr,
.getxattr = generic_getxattr,
.listxattr = f2fs_listxattr,
.removexattr = generic_removexattr,
#endif
};
static void __free_pages_ok (struct page *page, unsigned int order)
{
unsigned long index, page_idx, mask, flags;
free_area_t *area;
struct page *base;
zone_t *zone;
/*
* Yes, think what happens when other parts of the kernel take
* a reference to a page in order to pin it for io. -ben
*/
if (PageLRU(page)) {
if (unlikely(in_interrupt()))
BUG();
lru_cache_del(page);
}
if (page->buffers)
BUG();
if (page->mapping)
BUG();
if (!VALID_PAGE(page))
BUG();
if (PageLocked(page))
BUG();
if (PageActive(page))
BUG();
page->flags &= ~((1<<PG_referenced) | (1<<PG_dirty));
if (current->flags & PF_FREE_PAGES)
goto local_freelist;
back_local_freelist:
zone = page_zone(page);
mask = (~0UL) << order;
base = zone->zone_mem_map;
page_idx = page - base;
if (page_idx & ~mask)
BUG();
index = page_idx >> (1 + order);
area = zone->free_area + order;
spin_lock_irqsave(&zone->lock, flags);
zone->free_pages -= mask;
while (mask + (1 << (MAX_ORDER-1))) {
struct page *buddy1, *buddy2;
if (area >= zone->free_area + MAX_ORDER)
BUG();
if (!__test_and_change_bit(index, area->map))
/*
* the buddy page is still allocated.
*/
break;
/*
* Move the buddy up one level.
* This code is taking advantage of the identity:
* -mask = 1+~mask
*/
buddy1 = base + (page_idx ^ -mask);
buddy2 = base + page_idx;
if (BAD_RANGE(zone,buddy1))
BUG();
if (BAD_RANGE(zone,buddy2))
BUG();
list_del(&buddy1->list);
mask <<= 1;
area++;
index >>= 1;
page_idx &= mask;
}
list_add(&(base + page_idx)->list, &area->free_list);
spin_unlock_irqrestore(&zone->lock, flags);
return;
local_freelist:
if (current->nr_local_pages)
goto back_local_freelist;
if (in_interrupt())
goto back_local_freelist;
list_add(&page->list, ¤t->local_pages);
page->index = order;
current->nr_local_pages++;
}
/*
* AFS read page from file, directory or symlink
*/
static int afs_readpage(struct file *file, struct page *page)
{
struct afs_vnode *vnode;
struct inode *inode;
struct key *key;
size_t len;
off_t offset;
int ret;
inode = page->mapping->host;
if (file) {
key = file->private_data;
ASSERT(key != NULL);
} else {
key = afs_request_key(AFS_FS_S(inode->i_sb)->volume->cell);
if (IS_ERR(key)) {
ret = PTR_ERR(key);
goto error_nokey;
}
}
_enter("{%x},{%lu},{%lu}", key_serial(key), inode->i_ino, page->index);
vnode = AFS_FS_I(inode);
BUG_ON(!PageLocked(page));
ret = -ESTALE;
if (test_bit(AFS_VNODE_DELETED, &vnode->flags))
goto error;
/* is it cached? */
#ifdef CONFIG_AFS_FSCACHE
ret = fscache_read_or_alloc_page(vnode->cache,
page,
afs_file_readpage_read_complete,
NULL,
GFP_KERNEL);
#else
ret = -ENOBUFS;
#endif
switch (ret) {
/* read BIO submitted (page in cache) */
case 0:
break;
/* page not yet cached */
case -ENODATA:
_debug("cache said ENODATA");
goto go_on;
/* page will not be cached */
case -ENOBUFS:
_debug("cache said ENOBUFS");
default:
go_on:
offset = page->index << PAGE_CACHE_SHIFT;
len = min_t(size_t, i_size_read(inode) - offset, PAGE_SIZE);
/* read the contents of the file from the server into the
* page */
ret = afs_vnode_fetch_data(vnode, key, offset, len, page);
if (ret < 0) {
if (ret == -ENOENT) {
_debug("got NOENT from server"
" - marking file deleted and stale");
set_bit(AFS_VNODE_DELETED, &vnode->flags);
ret = -ESTALE;
}
#ifdef CONFIG_AFS_FSCACHE
fscache_uncache_page(vnode->cache, page);
#endif
BUG_ON(PageFsCache(page));
goto error;
}
SetPageUptodate(page);
/* send the page to the cache */
#ifdef CONFIG_AFS_FSCACHE
if (PageFsCache(page) &&
fscache_write_page(vnode->cache, page, GFP_KERNEL) != 0) {
fscache_uncache_page(vnode->cache, page);
BUG_ON(PageFsCache(page));
}
#endif
unlock_page(page);
}
if (!file)
key_put(key);
_leave(" = 0");
return 0;
error:
SetPageError(page);
unlock_page(page);
if (!file)
key_put(key);
error_nokey:
_leave(" = %d", ret);
return ret;
}
int jffs2_do_readpage_nolock (struct inode *inode, struct page *pg)
{
struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode);
struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb);
struct jffs2_node_frag *frag = f->fraglist;
__u32 offset = pg->index << PAGE_CACHE_SHIFT;
__u32 end = offset + PAGE_CACHE_SIZE;
unsigned char *pg_buf;
int ret;
D1(printk(KERN_DEBUG "jffs2_do_readpage_nolock(): ino #%lu, page at offset 0x%x\n", inode->i_ino, offset));
if (!PageLocked(pg))
PAGE_BUG(pg);
while(frag && frag->ofs + frag->size <= offset) {
// D1(printk(KERN_DEBUG "skipping frag %d-%d; before the region we care about\n", frag->ofs, frag->ofs + frag->size));
frag = frag->next;
}
pg_buf = kmap(pg);
/* XXX FIXME: Where a single physical node actually shows up in two
frags, we read it twice. Don't do that. */
/* Now we're pointing at the first frag which overlaps our page */
while(offset < end) {
D2(printk(KERN_DEBUG "jffs2_readpage: offset %d, end %d\n", offset, end));
if (!frag || frag->ofs > offset) {
__u32 holesize = end - offset;
if (frag) {
D1(printk(KERN_NOTICE "Eep. Hole in ino %ld fraglist. frag->ofs = 0x%08x, offset = 0x%08x\n", inode->i_ino, frag->ofs, offset));
holesize = min(holesize, frag->ofs - offset);
D1(jffs2_print_frag_list(f));
}
D1(printk(KERN_DEBUG "Filling non-frag hole from %d-%d\n", offset, offset+holesize));
memset(pg_buf, 0, holesize);
pg_buf += holesize;
offset += holesize;
continue;
} else if (frag->ofs < offset && (offset & (PAGE_CACHE_SIZE-1)) != 0) {
D1(printk(KERN_NOTICE "Eep. Overlap in ino #%ld fraglist. frag->ofs = 0x%08x, offset = 0x%08x\n",
inode->i_ino, frag->ofs, offset));
D1(jffs2_print_frag_list(f));
memset(pg_buf, 0, end - offset);
ClearPageUptodate(pg);
SetPageError(pg);
kunmap(pg);
return -EIO;
} else if (!frag->node) {
__u32 holeend = min(end, frag->ofs + frag->size);
D1(printk(KERN_DEBUG "Filling frag hole from %d-%d (frag 0x%x 0x%x)\n", offset, holeend, frag->ofs, frag->ofs + frag->size));
memset(pg_buf, 0, holeend - offset);
pg_buf += holeend - offset;
offset = holeend;
frag = frag->next;
continue;
} else {
__u32 readlen;
__u32 fragofs; /* offset within the frag to start reading */
fragofs = offset - frag->ofs;
readlen = min(frag->size - fragofs, end - offset);
D1(printk(KERN_DEBUG "Reading %d-%d from node at 0x%x\n", frag->ofs+fragofs,
fragofs+frag->ofs+readlen, frag->node->raw->flash_offset & ~3));
ret = jffs2_read_dnode(c, frag->node, pg_buf, fragofs + frag->ofs - frag->node->ofs, readlen);
D2(printk(KERN_DEBUG "node read done\n"));
if (ret) {
D1(printk(KERN_DEBUG"jffs2_readpage error %d\n",ret));
memset(pg_buf, 0, readlen);
ClearPageUptodate(pg);
SetPageError(pg);
kunmap(pg);
return ret;
}
pg_buf += readlen;
offset += readlen;
frag = frag->next;
D2(printk(KERN_DEBUG "node read was OK. Looping\n"));
}
}
D2(printk(KERN_DEBUG "readpage finishing\n"));
SetPageUptodate(pg);
ClearPageError(pg);
flush_dcache_page(pg);
kunmap(pg);
D1(printk(KERN_DEBUG "readpage finished\n"));
return 0;
}
int lock_kiovec(int nr, struct kiobuf *iovec[], int wait)
{
struct kiobuf *iobuf;
int i, j;
struct page *page, **ppage;
int doublepage = 0;
int repeat = 0;
repeat:
for (i = 0; i < nr; i++) {
iobuf = iovec[i];
if (iobuf->locked)
continue;
iobuf->locked = 1;
ppage = iobuf->maplist;
for (j = 0; j < iobuf->nr_pages; ppage++, j++) {
page = *ppage;
if (!page)
continue;
if (TryLockPage(page))
goto retry;
}
}
return 0;
retry:
/*
* We couldn't lock one of the pages. Undo the locking so far,
* wait on the page we got to, and try again.
*/
unlock_kiovec(nr, iovec);
if (!wait)
return -EAGAIN;
/*
* Did the release also unlock the page we got stuck on?
*/
if (!PageLocked(page)) {
/*
* If so, we may well have the page mapped twice
* in the IO address range. Bad news. Of
* course, it _might_ just be a coincidence,
* but if it happens more than once, chances
* are we have a double-mapped page.
*/
if (++doublepage >= 3)
return -EINVAL;
/* Try again... */
wait_on_page(page);
}
if (++repeat < 16)
goto repeat;
return -EAGAIN;
}
/*
* AFS read page from file, directory or symlink
*/
static int afs_readpage(struct file *file, struct page *page)
{
struct afs_vnode *vnode;
struct inode *inode;
struct key *key;
size_t len;
off_t offset;
int ret;
inode = page->mapping->host;
ASSERT(file != NULL);
key = file->private_data;
ASSERT(key != NULL);
_enter("{%x},{%lu},{%lu}", key_serial(key), inode->i_ino, page->index);
vnode = AFS_FS_I(inode);
BUG_ON(!PageLocked(page));
ret = -ESTALE;
if (test_bit(AFS_VNODE_DELETED, &vnode->flags))
goto error;
#ifdef AFS_CACHING_SUPPORT
/* is it cached? */
ret = cachefs_read_or_alloc_page(vnode->cache,
page,
afs_file_readpage_read_complete,
NULL,
GFP_KERNEL);
#else
ret = -ENOBUFS;
#endif
switch (ret) {
/* read BIO submitted and wb-journal entry found */
case 1:
BUG(); // TODO - handle wb-journal match
/* read BIO submitted (page in cache) */
case 0:
break;
/* no page available in cache */
case -ENOBUFS:
case -ENODATA:
default:
offset = page->index << PAGE_CACHE_SHIFT;
len = min_t(size_t, i_size_read(inode) - offset, PAGE_SIZE);
/* read the contents of the file from the server into the
* page */
ret = afs_vnode_fetch_data(vnode, key, offset, len, page);
if (ret < 0) {
if (ret == -ENOENT) {
_debug("got NOENT from server"
" - marking file deleted and stale");
set_bit(AFS_VNODE_DELETED, &vnode->flags);
ret = -ESTALE;
}
#ifdef AFS_CACHING_SUPPORT
cachefs_uncache_page(vnode->cache, page);
#endif
goto error;
}
SetPageUptodate(page);
#ifdef AFS_CACHING_SUPPORT
if (cachefs_write_page(vnode->cache,
page,
afs_file_readpage_write_complete,
NULL,
GFP_KERNEL) != 0
) {
cachefs_uncache_page(vnode->cache, page);
unlock_page(page);
}
#else
unlock_page(page);
#endif
}
_leave(" = 0");
return 0;
error:
SetPageError(page);
unlock_page(page);
_leave(" = %d", ret);
return ret;
}
/* Sharing code of page_mkwrite method for rhel5 and rhel6 */
static int ll_page_mkwrite0(struct vm_area_struct *vma, struct page *vmpage,
bool *retry)
{
struct lu_env *env;
struct cl_io *io;
struct vvp_io *vio;
struct cl_env_nest nest;
int result;
sigset_t set;
struct inode *inode;
struct ll_inode_info *lli;
io = ll_fault_io_init(vma, &env, &nest, vmpage->index, NULL);
if (IS_ERR(io)) {
result = PTR_ERR(io);
goto out;
}
result = io->ci_result;
if (result < 0)
goto out_io;
io->u.ci_fault.ft_mkwrite = 1;
io->u.ci_fault.ft_writable = 1;
vio = vvp_env_io(env);
vio->u.fault.ft_vma = vma;
vio->u.fault.ft_vmpage = vmpage;
set = cfs_block_sigsinv(sigmask(SIGKILL) | sigmask(SIGTERM));
/* we grab lli_trunc_sem to exclude truncate case.
* Otherwise, we could add dirty pages into osc cache
* while truncate is on-going.
*/
inode = ccc_object_inode(io->ci_obj);
lli = ll_i2info(inode);
down_read(&lli->lli_trunc_sem);
result = cl_io_loop(env, io);
up_read(&lli->lli_trunc_sem);
cfs_restore_sigs(set);
if (result == 0) {
struct inode *inode = file_inode(vma->vm_file);
struct ll_inode_info *lli = ll_i2info(inode);
lock_page(vmpage);
if (!vmpage->mapping) {
unlock_page(vmpage);
/* page was truncated and lock was cancelled, return
* ENODATA so that VM_FAULT_NOPAGE will be returned
* to handle_mm_fault().
*/
if (result == 0)
result = -ENODATA;
} else if (!PageDirty(vmpage)) {
/* race, the page has been cleaned by ptlrpcd after
* it was unlocked, it has to be added into dirty
* cache again otherwise this soon-to-dirty page won't
* consume any grants, even worse if this page is being
* transferred because it will break RPC checksum.
*/
unlock_page(vmpage);
CDEBUG(D_MMAP, "Race on page_mkwrite %p/%lu, page has been written out, retry.\n",
vmpage, vmpage->index);
*retry = true;
result = -EAGAIN;
}
if (result == 0) {
spin_lock(&lli->lli_lock);
lli->lli_flags |= LLIF_DATA_MODIFIED;
spin_unlock(&lli->lli_lock);
}
}
out_io:
cl_io_fini(env, io);
cl_env_nested_put(&nest, env);
out:
CDEBUG(D_MMAP, "%s mkwrite with %d\n", current->comm, result);
LASSERT(ergo(result == 0, PageLocked(vmpage)));
return result;
}
static void page_cache_tree_delete(struct address_space *mapping,
struct page *page, void *shadow)
{
struct radix_tree_node *node;
unsigned long index;
unsigned int offset;
unsigned int tag;
void **slot;
VM_BUG_ON(!PageLocked(page));
__radix_tree_lookup(&mapping->page_tree, page->index, &node, &slot);
if (shadow) {
mapping->nrshadows++;
/*
* Make sure the nrshadows update is committed before
* the nrpages update so that final truncate racing
* with reclaim does not see both counters 0 at the
* same time and miss a shadow entry.
*/
smp_wmb();
}
mapping->nrpages--;
if (!node) {
/* Clear direct pointer tags in root node */
mapping->page_tree.gfp_mask &= __GFP_BITS_MASK;
radix_tree_replace_slot(slot, shadow);
return;
}
/* Clear tree tags for the removed page */
index = page->index;
offset = index & RADIX_TREE_MAP_MASK;
for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) {
if (test_bit(offset, node->tags[tag]))
radix_tree_tag_clear(&mapping->page_tree, index, tag);
}
/* Delete page, swap shadow entry */
radix_tree_replace_slot(slot, shadow);
workingset_node_pages_dec(node);
if (shadow)
workingset_node_shadows_inc(node);
else
if (__radix_tree_delete_node(&mapping->page_tree, node))
return;
/*
* Track node that only contains shadow entries.
*
* Avoid acquiring the list_lru lock if already tracked. The
* list_empty() test is safe as node->private_list is
* protected by mapping->tree_lock.
*/
if (!workingset_node_pages(node) &&
list_empty(&node->private_list)) {
node->private_data = mapping;
list_lru_add(&workingset_shadow_nodes, &node->private_list);
}
}
/* Sharing code of page_mkwrite method for rhel5 and rhel6 */
static int ll_page_mkwrite0(struct vm_area_struct *vma, struct page *vmpage,
bool *retry)
{
struct lu_env *env;
struct cl_io *io;
struct vvp_io *vio;
int result;
__u16 refcheck;
sigset_t set;
struct inode *inode;
struct ll_inode_info *lli;
ENTRY;
LASSERT(vmpage != NULL);
env = cl_env_get(&refcheck);
if (IS_ERR(env))
RETURN(PTR_ERR(env));
io = ll_fault_io_init(env, vma, vmpage->index, NULL);
if (IS_ERR(io))
GOTO(out, result = PTR_ERR(io));
result = io->ci_result;
if (result < 0)
GOTO(out_io, result);
io->u.ci_fault.ft_mkwrite = 1;
io->u.ci_fault.ft_writable = 1;
vio = vvp_env_io(env);
vio->u.fault.ft_vma = vma;
vio->u.fault.ft_vmpage = vmpage;
set = cfs_block_sigsinv(sigmask(SIGKILL) | sigmask(SIGTERM));
inode = vvp_object_inode(io->ci_obj);
lli = ll_i2info(inode);
result = cl_io_loop(env, io);
cfs_restore_sigs(set);
if (result == 0) {
lock_page(vmpage);
if (vmpage->mapping == NULL) {
unlock_page(vmpage);
/* page was truncated and lock was cancelled, return
* ENODATA so that VM_FAULT_NOPAGE will be returned
* to handle_mm_fault(). */
if (result == 0)
result = -ENODATA;
} else if (!PageDirty(vmpage)) {
/* race, the page has been cleaned by ptlrpcd after
* it was unlocked, it has to be added into dirty
* cache again otherwise this soon-to-dirty page won't
* consume any grants, even worse if this page is being
* transferred because it will break RPC checksum.
*/
unlock_page(vmpage);
CDEBUG(D_MMAP, "Race on page_mkwrite %p/%lu, page has "
"been written out, retry.\n",
vmpage, vmpage->index);
*retry = true;
result = -EAGAIN;
}
if (result == 0)
ll_file_set_flag(lli, LLIF_DATA_MODIFIED);
}
EXIT;
out_io:
cl_io_fini(env, io);
out:
cl_env_put(env, &refcheck);
CDEBUG(D_MMAP, "%s mkwrite with %d\n", current->comm, result);
LASSERT(ergo(result == 0, PageLocked(vmpage)));
return result;
}
int ext4_bio_write_page(struct ext4_io_submit *io,
struct page *page,
int len,
struct writeback_control *wbc)
{
struct inode *inode = page->mapping->host;
unsigned block_start, block_end, blocksize;
struct ext4_io_page *io_page;
struct buffer_head *bh, *head;
int ret = 0;
blocksize = 1 << inode->i_blkbits;
BUG_ON(!PageLocked(page));
BUG_ON(PageWriteback(page));
io_page = kmem_cache_alloc(io_page_cachep, GFP_NOFS);
if (!io_page) {
set_page_dirty(page);
unlock_page(page);
return -ENOMEM;
}
io_page->p_page = page;
atomic_set(&io_page->p_count, 1);
get_page(page);
set_page_writeback(page);
ClearPageError(page);
for (bh = head = page_buffers(page), block_start = 0;
bh != head || !block_start;
block_start = block_end, bh = bh->b_this_page) {
block_end = block_start + blocksize;
if (block_start >= len) {
/*
* Comments copied from block_write_full_page_endio:
*
* The page straddles i_size. It must be zeroed out on
* each and every writepage invocation because it may
* be mmapped. "A file is mapped in multiples of the
* page size. For a file that is not a multiple of
* the page size, the remaining memory is zeroed when
* mapped, and writes to that region are not written
* out to the file."
*/
zero_user_segment(page, block_start, block_end);
clear_buffer_dirty(bh);
set_buffer_uptodate(bh);
continue;
}
clear_buffer_dirty(bh);
ret = io_submit_add_bh(io, io_page, inode, wbc, bh);
if (ret) {
set_page_dirty(page);
break;
}
}
unlock_page(page);
put_io_page(io_page);
return ret;
}
void bd_put_page(struct page *page)
{
if(PageLocked(page))
unlock_page(page);
page_cache_release(page);
}
static void __free_pages_ok (struct page *page, unsigned int order)
{
unsigned long index, page_idx, mask, flags;
free_area_t *area;
struct page *base;
zone_t *zone;
if (PageLRU(page))
lru_cache_del(page);
if (page->buffers)
BUG();
if (page->mapping)
BUG();
if (!VALID_PAGE(page))
BUG();
if (PageSwapCache(page))
BUG();
if (PageLocked(page))
BUG();
if (PageLRU(page))
BUG();
if (PageActive(page))
BUG();
TRACE_MEMORY(TRACE_EV_MEMORY_PAGE_FREE, order);
page->flags &= ~((1<<PG_referenced) | (1<<PG_dirty));
if (current->flags & PF_FREE_PAGES)
goto local_freelist;
back_local_freelist:
zone = page->zone;
mask = (~0UL) << order;
base = zone->zone_mem_map;
page_idx = page - base;
if (page_idx & ~mask)
BUG();
index = page_idx >> (1 + order);
area = zone->free_area + order;
spin_lock_irqsave(&zone->lock, flags);
zone->free_pages -= mask;
while (mask + (1 << (MAX_ORDER-1))) {
struct page *buddy1, *buddy2;
if (area >= zone->free_area + MAX_ORDER)
BUG();
if (!__test_and_change_bit(index, area->map))
/*
* the buddy page is still allocated.
*/
break;
/*
* Move the buddy up one level.
*/
buddy1 = base + (page_idx ^ -mask);
buddy2 = base + page_idx;
if (BAD_RANGE(zone,buddy1))
BUG();
if (BAD_RANGE(zone,buddy2))
BUG();
memlist_del(&buddy1->list);
mask <<= 1;
area++;
index >>= 1;
page_idx &= mask;
}
memlist_add_head(&(base + page_idx)->list, &area->free_list);
spin_unlock_irqrestore(&zone->lock, flags);
return;
local_freelist:
if (current->nr_local_pages)
goto back_local_freelist;
if (in_interrupt())
goto back_local_freelist;
list_add(&page->list, ¤t->local_pages);
page->index = order;
current->nr_local_pages++;
}
/*
* "Get" data from cleancache associated with the poolid/inode/index
* that were specified when the data was put to cleanache and, if
* successful, use it to fill the specified page with data and return 0.
* The pageframe is unchanged and returns -1 if the get fails.
* Page must be locked by caller.
*/
int __cleancache_get_page(struct page *page)
{
int ret = -1;
int pool_id;
struct cleancache_filekey key = { .u.key = { 0 } };
VM_BUG_ON(!PageLocked(page));
pool_id = page->mapping->host->i_sb->cleancache_poolid;
if (pool_id < 0)
goto out;
if (cleancache_get_key(page->mapping->host, &key) < 0)
goto out;
ret = (*cleancache_ops.get_page)(pool_id, key, page->index, page);
if (ret == 0)
cleancache_succ_gets++;
else
cleancache_failed_gets++;
out:
return ret;
}
EXPORT_SYMBOL(__cleancache_get_page);
/*
* "Put" data from a page to cleancache and associate it with the
* (previously-obtained per-filesystem) poolid and the page's,
* inode and page index. Page must be locked. Note that a put_page
* always "succeeds", though a subsequent get_page may succeed or fail.
*/
void __cleancache_put_page(struct page *page)
{
int pool_id;
struct cleancache_filekey key = { .u.key = { 0 } };
VM_BUG_ON(!PageLocked(page));
pool_id = page->mapping->host->i_sb->cleancache_poolid;
if (pool_id >= 0 &&
cleancache_get_key(page->mapping->host, &key) >= 0) {
(*cleancache_ops.put_page)(pool_id, key, page->index, page);
cleancache_puts++;
}
}
EXPORT_SYMBOL(__cleancache_put_page);
/*
* Flush any data from cleancache associated with the poolid and the
* page's inode and page index so that a subsequent "get" will fail.
*/
void __cleancache_flush_page(struct address_space *mapping, struct page *page)
{
/* careful... page->mapping is NULL sometimes when this is called */
int pool_id = mapping->host->i_sb->cleancache_poolid;
struct cleancache_filekey key = { .u.key = { 0 } };
if (pool_id >= 0) {
VM_BUG_ON(!PageLocked(page));
if (cleancache_get_key(mapping->host, &key) >= 0) {
(*cleancache_ops.flush_page)(pool_id, key, page->index);
cleancache_flushes++;
}
}
}
EXPORT_SYMBOL(__cleancache_flush_page);
/*
* Flush all data from cleancache associated with the poolid and the
* mappings's inode so that all subsequent gets to this poolid/inode
* will fail.
*/
void __cleancache_flush_inode(struct address_space *mapping)
{
int pool_id = mapping->host->i_sb->cleancache_poolid;
struct cleancache_filekey key = { .u.key = { 0 } };
if (pool_id >= 0 && cleancache_get_key(mapping->host, &key) >= 0)
(*cleancache_ops.flush_inode)(pool_id, key);
}
EXPORT_SYMBOL(__cleancache_flush_inode);
/*
* Called by any cleancache-enabled filesystem at time of unmount;
* note that pool_id is surrendered and may be reutrned by a subsequent
* cleancache_init_fs or cleancache_init_shared_fs
*/
void __cleancache_flush_fs(struct super_block *sb)
{
if (sb->cleancache_poolid >= 0) {
int old_poolid = sb->cleancache_poolid;
sb->cleancache_poolid = -1;
(*cleancache_ops.flush_fs)(old_poolid);
}
}
EXPORT_SYMBOL(__cleancache_flush_fs);
#ifdef CONFIG_SYSFS
/* see Documentation/ABI/xxx/sysfs-kernel-mm-cleancache */
#define CLEANCACHE_SYSFS_RO(_name) \
static ssize_t cleancache_##_name##_show(struct kobject *kobj, \
struct kobj_attribute *attr, char *buf) \
{ \
return sprintf(buf, "%lu\n", cleancache_##_name); \
} \
static struct kobj_attribute cleancache_##_name##_attr = { \
.attr = { .name = __stringify(_name), .mode = 0444 }, \
.show = cleancache_##_name##_show, \
}
CLEANCACHE_SYSFS_RO(succ_gets);
CLEANCACHE_SYSFS_RO(failed_gets);
CLEANCACHE_SYSFS_RO(puts);
CLEANCACHE_SYSFS_RO(flushes);
static struct attribute *cleancache_attrs[] = {
&cleancache_succ_gets_attr.attr,
&cleancache_failed_gets_attr.attr,
&cleancache_puts_attr.attr,
&cleancache_flushes_attr.attr,
NULL,
};
static struct attribute_group cleancache_attr_group = {
.attrs = cleancache_attrs,
.name = "cleancache",
};
#endif /* CONFIG_SYSFS */
static int __init init_cleancache(void)
{
#ifdef CONFIG_SYSFS
int err;
err = sysfs_create_group(mm_kobj, &cleancache_attr_group);
#endif /* CONFIG_SYSFS */
return 0;
}
module_init(init_cleancache)
static void rw_swap_page_base(int rw, unsigned long entry, struct page *page, int wait)
{
unsigned long type, offset;
struct swap_info_struct * p;
int zones[PAGE_SIZE/512];
int zones_used;
kdev_t dev = 0;
int block_size;
#ifdef DEBUG_SWAP
printk ("DebugVM: %s_swap_page entry %08lx, page %p (count %d), %s\n",
(rw == READ) ? "read" : "write",
entry, (char *) page_address(page), atomic_read(&page->count),
wait ? "wait" : "nowait");
#endif
type = SWP_TYPE(entry);
if (type >= nr_swapfiles) {
printk("Internal error: bad swap-device\n");
return;
}
/* Don't allow too many pending pages in flight.. */
if (atomic_read(&nr_async_pages) > pager_daemon.swap_cluster)
wait = 1;
p = &swap_info[type];
offset = SWP_OFFSET(entry);
if (offset >= p->max) {
printk("rw_swap_page: weirdness\n");
return;
}
if (p->swap_map && !p->swap_map[offset]) {
printk(KERN_ERR "rw_swap_page: "
"Trying to %s unallocated swap (%08lx)\n",
(rw == READ) ? "read" : "write", entry);
return;
}
if (!(p->flags & SWP_USED)) {
printk(KERN_ERR "rw_swap_page: "
"Trying to swap to unused swap-device\n");
return;
}
if (!PageLocked(page)) {
printk(KERN_ERR "VM: swap page is unlocked\n");
return;
}
if (PageSwapCache(page)) {
/* Make sure we are the only process doing I/O with this swap page. */
if (test_and_set_bit(offset, p->swap_lockmap))
{
struct wait_queue __wait;
__wait.task = current;
add_wait_queue(&lock_queue, &__wait);
for (;;) {
current->state = TASK_UNINTERRUPTIBLE;
mb();
if (!test_and_set_bit(offset, p->swap_lockmap))
break;
run_task_queue(&tq_disk);
schedule();
}
current->state = TASK_RUNNING;
remove_wait_queue(&lock_queue, &__wait);
}
/*
* Make sure that we have a swap cache association for this
* page. We need this to find which swap page to unlock once
* the swap IO has completed to the physical page. If the page
* is not already in the cache, just overload the offset entry
* as if it were: we are not allowed to manipulate the inode
* hashing for locked pages.
*/
if (page->offset != entry) {
printk ("swap entry mismatch");
return;
}
}
if (rw == READ) {
clear_bit(PG_uptodate, &page->flags);
kstat.pswpin++;
} else
kstat.pswpout++;
atomic_inc(&page->count);
if (p->swap_device) {
zones[0] = offset;
zones_used = 1;
dev = p->swap_device;
block_size = PAGE_SIZE;
} else if (p->swap_file) {
struct inode *swapf = p->swap_file->d_inode;
int i;
if (swapf->i_op->bmap == NULL
&& swapf->i_op->smap != NULL){
/*
With MS-DOS, we use msdos_smap which returns
a sector number (not a cluster or block number).
It is a patch to enable the UMSDOS project.
Other people are working on better solution.
It sounds like ll_rw_swap_file defined
its operation size (sector size) based on
PAGE_SIZE and the number of blocks to read.
So using bmap or smap should work even if
smap will require more blocks.
*/
int j;
unsigned int block = offset << 3;
for (i=0, j=0; j< PAGE_SIZE ; i++, j += 512){
if (!(zones[i] = swapf->i_op->smap(swapf,block++))) {
printk("rw_swap_page: bad swap file\n");
return;
}
}
block_size = 512;
}else{
int j;
unsigned int block = offset
<< (PAGE_SHIFT - swapf->i_sb->s_blocksize_bits);
block_size = swapf->i_sb->s_blocksize;
for (i=0, j=0; j< PAGE_SIZE ; i++, j += block_size)
if (!(zones[i] = bmap(swapf,block++))) {
printk("rw_swap_page: bad swap file\n");
return;
}
zones_used = i;
dev = swapf->i_dev;
}
} else {
printk(KERN_ERR "rw_swap_page: no swap file or device\n");
/* Do some cleaning up so if this ever happens we can hopefully
* trigger controlled shutdown.
*/
if (PageSwapCache(page)) {
if (!test_and_clear_bit(offset,p->swap_lockmap))
printk("swap_after_unlock_page: lock already cleared\n");
wake_up(&lock_queue);
}
atomic_dec(&page->count);
return;
}
if (!wait) {
set_bit(PG_decr_after, &page->flags);
atomic_inc(&nr_async_pages);
}
if (PageSwapCache(page)) {
/* only lock/unlock swap cache pages! */
set_bit(PG_swap_unlock_after, &page->flags);
}
set_bit(PG_free_after, &page->flags);
/* block_size == PAGE_SIZE/zones_used */
brw_page(rw, page, dev, zones, block_size, 0);
/* Note! For consistency we do all of the logic,
* decrementing the page count, and unlocking the page in the
* swap lock map - in the IO completion handler.
*/
if (!wait)
return;
wait_on_page(page);
/* This shouldn't happen, but check to be sure. */
if (atomic_read(&page->count) == 0)
printk(KERN_ERR "rw_swap_page: page unused while waiting!\n");
#ifdef DEBUG_SWAP
printk ("DebugVM: %s_swap_page finished on page %p (count %d)\n",
(rw == READ) ? "read" : "write",
(char *) page_adddress(page),
atomic_read(&page->count));
#endif
}
int ext4_bio_write_page(struct ext4_io_submit *io,
struct page *page,
int len,
struct writeback_control *wbc)
{
struct inode *inode = page->mapping->host;
unsigned block_start, block_end, blocksize;
struct ext4_io_page *io_page;
struct buffer_head *bh, *head;
int ret = 0;
blocksize = 1 << inode->i_blkbits;
BUG_ON(!PageLocked(page));
BUG_ON(PageWriteback(page));
io_page = kmem_cache_alloc(io_page_cachep, GFP_NOFS);
if (!io_page) {
set_page_dirty(page);
unlock_page(page);
return -ENOMEM;
}
io_page->p_page = page;
atomic_set(&io_page->p_count, 1);
get_page(page);
set_page_writeback(page);
ClearPageError(page);
for (bh = head = page_buffers(page), block_start = 0;
bh != head || !block_start;
block_start = block_end, bh = bh->b_this_page) {
block_end = block_start + blocksize;
if (block_start >= len) {
clear_buffer_dirty(bh);
set_buffer_uptodate(bh);
continue;
}
clear_buffer_dirty(bh);
ret = io_submit_add_bh(io, io_page, inode, wbc, bh);
if (ret) {
/*
* We only get here on ENOMEM. Not much else
* we can do but mark the page as dirty, and
* better luck next time.
*/
set_page_dirty(page);
break;
}
}
unlock_page(page);
/*
* If the page was truncated before we could do the writeback,
* or we had a memory allocation error while trying to write
* the first buffer head, we won't have submitted any pages for
* I/O. In that case we need to make sure we've cleared the
* PageWriteback bit from the page to prevent the system from
* wedging later on.
*/
put_io_page(io_page);
return ret;
}
/*
* "Get" data from cleancache associated with the poolid/inode/index
* that were specified when the data was put to cleanache and, if
* successful, use it to fill the specified page with data and return 0.
* The pageframe is unchanged and returns -1 if the get fails.
* Page must be locked by caller.
*/
int __cleancache_get_page(struct page *page)
{
int ret = -1;
int pool_id;
struct cleancache_filekey key = { .u.key = { 0 } };
VM_BUG_ON(!PageLocked(page));
pool_id = page->mapping->host->i_sb->cleancache_poolid;
if (pool_id < 0)
goto out;
if (cleancache_get_key(page->mapping->host, &key) < 0)
goto out;
ret = (*cleancache_ops.get_page)(pool_id, key, page->index, page);
if (ret == 0)
cleancache_succ_gets++;
else
cleancache_failed_gets++;
out:
return ret;
}
EXPORT_SYMBOL(__cleancache_get_page);
/*
* "Put" data from a page to cleancache and associate it with the
* (previously-obtained per-filesystem) poolid and the page's,
* inode and page index. Page must be locked. Note that a put_page
* always "succeeds", though a subsequent get_page may succeed or fail.
*/
void __cleancache_put_page(struct page *page)
{
int pool_id;
struct cleancache_filekey key = { .u.key = { 0 } };
VM_BUG_ON(!PageLocked(page));
pool_id = page->mapping->host->i_sb->cleancache_poolid;
if (pool_id >= 0 &&
cleancache_get_key(page->mapping->host, &key) >= 0) {
(*cleancache_ops.put_page)(pool_id, key, page->index, page);
cleancache_puts++;
}
}
EXPORT_SYMBOL(__cleancache_put_page);
/*
* Invalidate any data from cleancache associated with the poolid and the
* page's inode and page index so that a subsequent "get" will fail.
*/
void __cleancache_invalidate_page(struct address_space *mapping,
struct page *page)
{
/* careful... page->mapping is NULL sometimes when this is called */
int pool_id = mapping->host->i_sb->cleancache_poolid;
struct cleancache_filekey key = { .u.key = { 0 } };
if (pool_id >= 0) {
VM_BUG_ON(!PageLocked(page));
if (cleancache_get_key(mapping->host, &key) >= 0) {
(*cleancache_ops.invalidate_page)(pool_id,
key, page->index);
cleancache_invalidates++;
}
}
}
EXPORT_SYMBOL(__cleancache_invalidate_page);
/*
* Invalidate all data from cleancache associated with the poolid and the
* mappings's inode so that all subsequent gets to this poolid/inode
* will fail.
*/
void __cleancache_invalidate_inode(struct address_space *mapping)
{
int pool_id = mapping->host->i_sb->cleancache_poolid;
struct cleancache_filekey key = { .u.key = { 0 } };
if (pool_id >= 0 && cleancache_get_key(mapping->host, &key) >= 0)
(*cleancache_ops.invalidate_inode)(pool_id, key);
}
EXPORT_SYMBOL(__cleancache_invalidate_inode);
/*
* Called by any cleancache-enabled filesystem at time of unmount;
* note that pool_id is surrendered and may be reutrned by a subsequent
* cleancache_init_fs or cleancache_init_shared_fs
*/
void __cleancache_invalidate_fs(struct super_block *sb)
{
if (sb->cleancache_poolid >= 0) {
int old_poolid = sb->cleancache_poolid;
sb->cleancache_poolid = -1;
(*cleancache_ops.invalidate_fs)(old_poolid);
}
}
EXPORT_SYMBOL(__cleancache_invalidate_fs);
static int __init init_cleancache(void)
{
#ifdef CONFIG_DEBUG_FS
struct dentry *root = debugfs_create_dir("cleancache", NULL);
if (root == NULL)
return -ENXIO;
debugfs_create_u64("succ_gets", S_IRUGO, root, &cleancache_succ_gets);
debugfs_create_u64("failed_gets", S_IRUGO,
root, &cleancache_failed_gets);
debugfs_create_u64("puts", S_IRUGO, root, &cleancache_puts);
debugfs_create_u64("invalidates", S_IRUGO,
root, &cleancache_invalidates);
#endif
return 0;
}
module_init(init_cleancache)
int ext4_bio_write_page(struct ext4_io_submit *io,
struct page *page,
int len,
struct writeback_control *wbc)
{
struct inode *inode = page->mapping->host;
unsigned block_start, block_end, blocksize;
struct ext4_io_page *io_page;
struct buffer_head *bh, *head;
int ret = 0;
blocksize = 1 << inode->i_blkbits;
BUG_ON(!PageLocked(page));
BUG_ON(PageWriteback(page));
io_page = kmem_cache_alloc(io_page_cachep, GFP_NOFS);
if (!io_page) {
set_page_dirty(page);
unlock_page(page);
return -ENOMEM;
}
io_page->p_page = page;
atomic_set(&io_page->p_count, 1);
get_page(page);
set_page_writeback(page);
ClearPageError(page);
/*
* Comments copied from block_write_full_page_endio:
*
* The page straddles i_size. It must be zeroed out on each and every
* writepage invocation because it may be mmapped. "A file is mapped
* in multiples of the page size. For a file that is not a multiple of
* the page size, the remaining memory is zeroed when mapped, and
* writes to that region are not written out to the file."
*/
if (len < PAGE_CACHE_SIZE)
zero_user_segment(page, len, PAGE_CACHE_SIZE);
for (bh = head = page_buffers(page), block_start = 0;
bh != head || !block_start;
block_start = block_end, bh = bh->b_this_page) {
block_end = block_start + blocksize;
if (block_start >= len) {
clear_buffer_dirty(bh);
set_buffer_uptodate(bh);
continue;
}
clear_buffer_dirty(bh);
ret = io_submit_add_bh(io, io_page, inode, wbc, bh);
if (ret) {
/*
* We only get here on ENOMEM. Not much else
* we can do but mark the page as dirty, and
* better luck next time.
*/
set_page_dirty(page);
break;
}
}
unlock_page(page);
/*
* If the page was truncated before we could do the writeback,
* or we had a memory allocation error while trying to write
* the first buffer head, we won't have submitted any pages for
* I/O. In that case we need to make sure we've cleared the
* PageWriteback bit from the page to prevent the system from
* wedging later on.
*/
put_io_page(io_page);
return ret;
}
/*
* Try to free buffers if "page" has them.
*/
static int
remap_preparepage(struct page *page, int fastmode)
{
struct address_space *mapping;
int waitcnt = fastmode ? 0 : 10;
BUG_ON(!PageLocked(page));
mapping = page_mapping(page);
if (PageWriteback(page) && !PagePrivate(page) && !PageSwapCache(page)) {
printk("remap: mapping %p page %p\n", page->mapping, page);
return -REMAPPREP_WB;
}
if (PageWriteback(page))
wait_on_page_writeback(page);
if (PagePrivate(page)) {
#ifdef DEBUG_MSG
printk("rmap: process page with buffers...\n");
#endif
/* XXX copied from shrink_list() */
if (PageDirty(page) &&
is_page_cache_freeable(page) &&
mapping != NULL &&
mapping->a_ops->writepage != NULL) {
spin_lock_irq(&mapping->tree_lock);
if (clear_page_dirty_for_io(page)) {
int res;
struct writeback_control wbc = {
.sync_mode = WB_SYNC_NONE,
.nr_to_write = SWAP_CLUSTER_MAX,
.nonblocking = 1,
.for_reclaim = 1,
};
spin_unlock_irq(&mapping->tree_lock);
SetPageReclaim(page);
res = mapping->a_ops->writepage(page, &wbc);
if (res < 0)
/* not implemented. help */
BUG();
if (res == WRITEPAGE_ACTIVATE) {
ClearPageReclaim(page);
return -REMAPPREP_WB;
}
if (!PageWriteback(page)) {
/* synchronous write or broken a_ops? */
ClearPageReclaim(page);
}
lock_page(page);
if (!PagePrivate(page))
return 0;
} else
spin_unlock_irq(&mapping->tree_lock);
}
while (1) {
if (try_to_release_page(page, GFP_KERNEL))
break;
if (!waitcnt)
return -REMAPPREP_BUFFER;
msleep(10);
waitcnt--;
if (!waitcnt)
print_buffer(page);
}
}
/*
* Modify inode page cache in such way:
* have - blocks with b_blocknr equal to oldb...oldb+count-1
* get - blocks with b_blocknr equal to newb...newb+count-1
* also we suppose that oldb...oldb+count-1 blocks
* situated at the end of file.
*
* We can come here from ufs_writepage or ufs_prepare_write,
* locked_page is argument of these functions, so we already lock it.
*/
static void ufs_change_blocknr(struct inode *inode, sector_t beg,
unsigned int count, sector_t oldb,
sector_t newb, struct page *locked_page)
{
const unsigned blks_per_page =
1 << (PAGE_CACHE_SHIFT - inode->i_blkbits);
const unsigned mask = blks_per_page - 1;
struct address_space * const mapping = inode->i_mapping;
pgoff_t index, cur_index, last_index;
unsigned pos, j, lblock;
sector_t end, i;
struct page *page;
struct buffer_head *head, *bh;
UFSD("ENTER, ino %lu, count %u, oldb %llu, newb %llu\n",
inode->i_ino, count,
(unsigned long long)oldb, (unsigned long long)newb);
BUG_ON(!locked_page);
BUG_ON(!PageLocked(locked_page));
cur_index = locked_page->index;
end = count + beg;
last_index = end >> (PAGE_CACHE_SHIFT - inode->i_blkbits);
for (i = beg; i < end; i = (i | mask) + 1) {
index = i >> (PAGE_CACHE_SHIFT - inode->i_blkbits);
if (likely(cur_index != index)) {
page = ufs_get_locked_page(mapping, index);
if (!page)/* it was truncated */
continue;
if (IS_ERR(page)) {/* or EIO */
ufs_error(inode->i_sb, __func__,
"read of page %llu failed\n",
(unsigned long long)index);
continue;
}
} else
page = locked_page;
head = page_buffers(page);
bh = head;
pos = i & mask;
for (j = 0; j < pos; ++j)
bh = bh->b_this_page;
if (unlikely(index == last_index))
lblock = end & mask;
else
lblock = blks_per_page;
do {
if (j >= lblock)
break;
pos = (i - beg) + j;
if (!buffer_mapped(bh))
map_bh(bh, inode->i_sb, oldb + pos);
if (!buffer_uptodate(bh)) {
ll_rw_block(READ, 1, &bh);
wait_on_buffer(bh);
if (!buffer_uptodate(bh)) {
ufs_error(inode->i_sb, __func__,
"read of block failed\n");
break;
}
}
UFSD(" change from %llu to %llu, pos %u\n",
(unsigned long long)(pos + oldb),
(unsigned long long)(pos + newb), pos);
bh->b_blocknr = newb + pos;
unmap_underlying_metadata(bh->b_bdev,
bh->b_blocknr);
mark_buffer_dirty(bh);
++j;
bh = bh->b_this_page;
} while (bh != head);
if (likely(cur_index != index))
ufs_put_locked_page(page);
}
UFSD("EXIT\n");
}
static int vvp_io_fault_start(const struct lu_env *env,
const struct cl_io_slice *ios)
{
struct vvp_io *vio = cl2vvp_io(env, ios);
struct cl_io *io = ios->cis_io;
struct cl_object *obj = io->ci_obj;
struct inode *inode = ccc_object_inode(obj);
struct cl_fault_io *fio = &io->u.ci_fault;
struct vvp_fault_io *cfio = &vio->u.fault;
loff_t offset;
int result = 0;
struct page *vmpage = NULL;
struct cl_page *page;
loff_t size;
pgoff_t last; /* last page in a file data region */
if (fio->ft_executable &&
LTIME_S(inode->i_mtime) != vio->u.fault.ft_mtime)
CWARN("binary "DFID
" changed while waiting for the page fault lock\n",
PFID(lu_object_fid(&obj->co_lu)));
/* offset of the last byte on the page */
offset = cl_offset(obj, fio->ft_index + 1) - 1;
LASSERT(cl_index(obj, offset) == fio->ft_index);
result = ccc_prep_size(env, obj, io, 0, offset + 1, NULL);
if (result != 0)
return result;
/* must return locked page */
if (fio->ft_mkwrite) {
LASSERT(cfio->ft_vmpage != NULL);
lock_page(cfio->ft_vmpage);
} else {
result = vvp_io_kernel_fault(cfio);
if (result != 0)
return result;
}
vmpage = cfio->ft_vmpage;
LASSERT(PageLocked(vmpage));
if (OBD_FAIL_CHECK(OBD_FAIL_LLITE_FAULT_TRUNC_RACE))
ll_invalidate_page(vmpage);
size = i_size_read(inode);
/* Though we have already held a cl_lock upon this page, but
* it still can be truncated locally. */
if (unlikely((vmpage->mapping != inode->i_mapping) ||
(page_offset(vmpage) > size))) {
CDEBUG(D_PAGE, "llite: fault and truncate race happened!\n");
/* return +1 to stop cl_io_loop() and ll_fault() will catch
* and retry. */
GOTO(out, result = +1);
}
if (fio->ft_mkwrite ) {
pgoff_t last_index;
/*
* Capture the size while holding the lli_trunc_sem from above
* we want to make sure that we complete the mkwrite action
* while holding this lock. We need to make sure that we are
* not past the end of the file.
*/
last_index = cl_index(obj, size - 1);
if (last_index < fio->ft_index) {
CDEBUG(D_PAGE,
"llite: mkwrite and truncate race happened: "
"%p: 0x%lx 0x%lx\n",
vmpage->mapping,fio->ft_index,last_index);
/*
* We need to return if we are
* passed the end of the file. This will propagate
* up the call stack to ll_page_mkwrite where
* we will return VM_FAULT_NOPAGE. Any non-negative
* value returned here will be silently
* converted to 0. If the vmpage->mapping is null
* the error code would be converted back to ENODATA
* in ll_page_mkwrite0. Thus we return -ENODATA
* to handle both cases
*/
GOTO(out, result = -ENODATA);
}
}
page = cl_page_find(env, obj, fio->ft_index, vmpage, CPT_CACHEABLE);
if (IS_ERR(page))
GOTO(out, result = PTR_ERR(page));
/* if page is going to be written, we should add this page into cache
* earlier. */
if (fio->ft_mkwrite) {
wait_on_page_writeback(vmpage);
if (set_page_dirty(vmpage)) {
struct ccc_page *cp;
/* vvp_page_assume() calls wait_on_page_writeback(). */
cl_page_assume(env, io, page);
cp = cl2ccc_page(cl_page_at(page, &vvp_device_type));
vvp_write_pending(cl2ccc(obj), cp);
/* Do not set Dirty bit here so that in case IO is
* started before the page is really made dirty, we
* still have chance to detect it. */
result = cl_page_cache_add(env, io, page, CRT_WRITE);
LASSERT(cl_page_is_owned(page, io));
vmpage = NULL;
if (result < 0) {
cl_page_unmap(env, io, page);
cl_page_discard(env, io, page);
cl_page_disown(env, io, page);
cl_page_put(env, page);
/* we're in big trouble, what can we do now? */
if (result == -EDQUOT)
result = -ENOSPC;
GOTO(out, result);
} else
cl_page_disown(env, io, page);
}
}
last = cl_index(obj, size - 1);
/*
* The ft_index is only used in the case of
* a mkwrite action. We need to check
* our assertions are correct, since
* we should have caught this above
*/
LASSERT(!fio->ft_mkwrite || fio->ft_index <= last);
if (fio->ft_index == last)
/*
* Last page is mapped partially.
*/
fio->ft_nob = size - cl_offset(obj, fio->ft_index);
else
fio->ft_nob = cl_page_size(obj);
lu_ref_add(&page->cp_reference, "fault", io);
fio->ft_page = page;
EXIT;
out:
/* return unlocked vmpage to avoid deadlocking */
if (vmpage != NULL)
unlock_page(vmpage);
cfio->fault.ft_flags &= ~VM_FAULT_LOCKED;
return result;
}
static int ext4_destroy_inline_data_nolock(handle_t *handle,
struct inode *inode)
{
struct ext4_inode_info *ei = EXT4_I(inode);
struct ext4_xattr_ibody_find is = {
.s = { .not_found = 0, },
};
struct ext4_xattr_info i = {
.name_index = EXT4_XATTR_INDEX_SYSTEM,
.name = EXT4_XATTR_SYSTEM_DATA,
.value = NULL,
.value_len = 0,
};
int error;
if (!ei->i_inline_off)
return 0;
error = ext4_get_inode_loc(inode, &is.iloc);
if (error)
return error;
error = ext4_xattr_ibody_find(inode, &i, &is);
if (error)
goto out;
BUFFER_TRACE(is.iloc.bh, "get_write_access");
error = ext4_journal_get_write_access(handle, is.iloc.bh);
if (error)
goto out;
error = ext4_xattr_ibody_inline_set(handle, inode, &i, &is);
if (error)
goto out;
memset((void *)ext4_raw_inode(&is.iloc)->i_block,
0, EXT4_MIN_INLINE_DATA_SIZE);
if (ext4_has_feature_extents(inode->i_sb)) {
if (S_ISDIR(inode->i_mode) ||
S_ISREG(inode->i_mode) || S_ISLNK(inode->i_mode)) {
ext4_set_inode_flag(inode, EXT4_INODE_EXTENTS);
ext4_ext_tree_init(handle, inode);
}
}
ext4_clear_inode_flag(inode, EXT4_INODE_INLINE_DATA);
get_bh(is.iloc.bh);
error = ext4_mark_iloc_dirty(handle, inode, &is.iloc);
EXT4_I(inode)->i_inline_off = 0;
EXT4_I(inode)->i_inline_size = 0;
ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
out:
brelse(is.iloc.bh);
if (error == -ENODATA)
error = 0;
return error;
}
static int ext4_read_inline_page(struct inode *inode, struct page *page)
{
void *kaddr;
int ret = 0;
size_t len;
struct ext4_iloc iloc;
BUG_ON(!PageLocked(page));
BUG_ON(!ext4_has_inline_data(inode));
BUG_ON(page->index);
if (!EXT4_I(inode)->i_inline_off) {
ext4_warning(inode->i_sb, "inode %lu doesn't have inline data.",
inode->i_ino);
goto out;
}
ret = ext4_get_inode_loc(inode, &iloc);
if (ret)
goto out;
len = min_t(size_t, ext4_get_inline_size(inode), i_size_read(inode));
kaddr = kmap_atomic(page);
ret = ext4_read_inline_data(inode, kaddr, len, &iloc);
flush_dcache_page(page);
kunmap_atomic(kaddr);
zero_user_segment(page, len, PAGE_CACHE_SIZE);
SetPageUptodate(page);
brelse(iloc.bh);
out:
return ret;
}
static void kcdfsd_process_request(void){
struct list_head * tmp;
struct kcdfsd_req * req;
struct page * page;
struct inode * inode;
unsigned request;
while (!list_empty (&kcdfsd_req_list)){
/* Grab the next entry from the beginning of the list */
tmp = kcdfsd_req_list.next;
req = list_entry (tmp, struct kcdfsd_req, req_list);
list_del (tmp);
page = req->page;
inode = req->dentry->d_inode;
request = req->request_type;
if (!PageLocked(page))
#if (LINUX_VERSION_CODE < KERNEL_VERSION(2,6,12))
PAGE_BUG(page);
#else
BUG();
#endif
switch (request){
case CDDA_REQUEST:
case CDDA_RAW_REQUEST:
{
cd *this_cd = cdfs_info (inode->i_sb);
char *p;
track_info *this_track = &(this_cd->track[inode->i_ino]);
cdfs_cdda_file_read (inode,
p = (char *) kmap (page),
1 << PAGE_CACHE_SHIFT,
(page->index << PAGE_CACHE_SHIFT) +
((this_track->avi) ? this_track->
avi_offset : 0),
(request == CDDA_RAW_REQUEST));
if ((this_track->avi) && (this_track->avi_swab)){
int k;
for (k=0; k<(1 << PAGE_CACHE_SHIFT); k+=2){
char c;
c = p[k];
p[k] = p[k + 1];
p[k + 1] = c;
}
}
}
break;
case CDXA_REQUEST:
cdfs_copy_from_cdXA(inode->i_sb,
inode->i_ino,
page->index << PAGE_CACHE_SHIFT,
(page->index + 1) << PAGE_CACHE_SHIFT,
(char *)kmap(page));
break;
case CDDATA_REQUEST:
cdfs_copy_from_cddata(inode->i_sb,
inode->i_ino,
page->index << PAGE_CACHE_SHIFT,
(page->index + 1) << PAGE_CACHE_SHIFT,
(char *)kmap(page));
break;
case CDHFS_REQUEST:
cdfs_copy_from_cdhfs(inode->i_sb,
inode->i_ino,
page->index << PAGE_CACHE_SHIFT,
(page->index + 1) << PAGE_CACHE_SHIFT,
(char *)kmap(page));
break;
}
SetPageUptodate (page);
kunmap (page);
unlock_page (page);
kfree (req);
}
}
/*
* AFS read page from file (or symlink)
*/
static int afs_file_readpage(struct file *file, struct page *page)
{
struct afs_rxfs_fetch_descriptor desc;
#ifdef AFS_CACHING_SUPPORT
struct cachefs_page *pageio;
#endif
struct afs_vnode *vnode;
struct inode *inode;
int ret;
inode = page->mapping->host;
_enter("{%lu},{%lu}", inode->i_ino, page->index);
vnode = AFS_FS_I(inode);
BUG_ON(!PageLocked(page));
ret = -ESTALE;
if (vnode->flags & AFS_VNODE_DELETED)
goto error;
#ifdef AFS_CACHING_SUPPORT
ret = cachefs_page_get_private(page, &pageio, GFP_NOIO);
if (ret < 0)
goto error;
/* is it cached? */
ret = cachefs_read_or_alloc_page(vnode->cache,
page,
afs_file_readpage_read_complete,
NULL,
GFP_KERNEL);
#else
ret = -ENOBUFS;
#endif
switch (ret) {
/* read BIO submitted and wb-journal entry found */
case 1:
BUG(); // TODO - handle wb-journal match
/* read BIO submitted (page in cache) */
case 0:
break;
/* no page available in cache */
case -ENOBUFS:
case -ENODATA:
default:
desc.fid = vnode->fid;
desc.offset = page->index << PAGE_CACHE_SHIFT;
desc.size = min((size_t) (inode->i_size - desc.offset),
(size_t) PAGE_SIZE);
desc.buffer = kmap(page);
clear_page(desc.buffer);
/* read the contents of the file from the server into the
* page */
ret = afs_vnode_fetch_data(vnode, &desc);
kunmap(page);
if (ret < 0) {
if (ret==-ENOENT) {
_debug("got NOENT from server"
" - marking file deleted and stale");
vnode->flags |= AFS_VNODE_DELETED;
ret = -ESTALE;
}
#ifdef AFS_CACHING_SUPPORT
cachefs_uncache_page(vnode->cache, page);
#endif
goto error;
}
SetPageUptodate(page);
#ifdef AFS_CACHING_SUPPORT
if (cachefs_write_page(vnode->cache,
page,
afs_file_readpage_write_complete,
NULL,
GFP_KERNEL) != 0
) {
cachefs_uncache_page(vnode->cache, page);
unlock_page(page);
}
#else
unlock_page(page);
#endif
}
_leave(" = 0");
return 0;
error:
SetPageError(page);
unlock_page(page);
_leave(" = %d", ret);
return ret;
} /* end afs_file_readpage() */
/* Two pass sync: first using WB_SYNC_NONE, then WB_SYNC_ALL */
static int nfs_write_mapping(struct address_space *mapping, int how)
{
struct writeback_control wbc = {
.bdi = mapping->backing_dev_info,
.sync_mode = WB_SYNC_ALL,
.nr_to_write = LONG_MAX,
.range_start = 0,
.range_end = LLONG_MAX,
};
return __nfs_write_mapping(mapping, &wbc, how);
}
/*
* flush the inode to disk.
*/
int nfs_wb_all(struct inode *inode)
{
return nfs_write_mapping(inode->i_mapping, 0);
}
int nfs_wb_nocommit(struct inode *inode)
{
return nfs_write_mapping(inode->i_mapping, FLUSH_NOCOMMIT);
}
int nfs_wb_page_cancel(struct inode *inode, struct page *page)
{
struct nfs_page *req;
loff_t range_start = page_offset(page);
loff_t range_end = range_start + (loff_t)(PAGE_CACHE_SIZE - 1);
struct writeback_control wbc = {
.bdi = page->mapping->backing_dev_info,
.sync_mode = WB_SYNC_ALL,
.nr_to_write = LONG_MAX,
.range_start = range_start,
.range_end = range_end,
};
int ret = 0;
BUG_ON(!PageLocked(page));
for (;;) {
req = nfs_page_find_request(page);
if (req == NULL)
goto out;
if (test_bit(PG_CLEAN, &req->wb_flags)) {
nfs_release_request(req);
break;
}
if (nfs_lock_request_dontget(req)) {
nfs_inode_remove_request(req);
/*
* In case nfs_inode_remove_request has marked the
* page as being dirty
*/
cancel_dirty_page(page, PAGE_CACHE_SIZE);
nfs_unlock_request(req);
break;
}
ret = nfs_wait_on_request(req);
if (ret < 0)
goto out;
}
if (!PagePrivate(page))
return 0;
ret = nfs_sync_mapping_wait(page->mapping, &wbc, FLUSH_INVALIDATE);
out:
return ret;
}
static int nfs_wb_page_priority(struct inode *inode, struct page *page,
int how)
{
loff_t range_start = page_offset(page);
loff_t range_end = range_start + (loff_t)(PAGE_CACHE_SIZE - 1);
struct writeback_control wbc = {
.bdi = page->mapping->backing_dev_info,
.sync_mode = WB_SYNC_ALL,
.nr_to_write = LONG_MAX,
.range_start = range_start,
.range_end = range_end,
};
int ret;
do {
if (clear_page_dirty_for_io(page)) {
ret = nfs_writepage_locked(page, &wbc);
if (ret < 0)
goto out_error;
} else if (!PagePrivate(page))
break;
ret = nfs_sync_mapping_wait(page->mapping, &wbc, how);
if (ret < 0)
goto out_error;
} while (PagePrivate(page));
return 0;
out_error:
__mark_inode_dirty(inode, I_DIRTY_PAGES);
return ret;
}
/*
* Write back all requests on one page - we do this before reading it.
*/
int nfs_wb_page(struct inode *inode, struct page* page)
{
return nfs_wb_page_priority(inode, page, FLUSH_STABLE);
}
#ifdef CONFIG_MIGRATION
int nfs_migrate_page(struct address_space *mapping, struct page *newpage,
struct page *page)
{
struct nfs_page *req;
int ret;
if (PageFsCache(page))
nfs_fscache_release_page(page, GFP_KERNEL);
req = nfs_find_and_lock_request(page);
ret = PTR_ERR(req);
if (IS_ERR(req))
goto out;
ret = migrate_page(mapping, newpage, page);
if (!req)
goto out;
if (ret)
goto out_unlock;
page_cache_get(newpage);
req->wb_page = newpage;
SetPagePrivate(newpage);
set_page_private(newpage, page_private(page));
ClearPagePrivate(page);
set_page_private(page, 0);
page_cache_release(page);
out_unlock:
nfs_clear_page_tag_locked(req);
nfs_release_request(req);
out:
return ret;
}
#endif
int __init nfs_init_writepagecache(void)
{
nfs_wdata_cachep = kmem_cache_create("nfs_write_data",
sizeof(struct nfs_write_data),
0, SLAB_HWCACHE_ALIGN,
NULL);
if (nfs_wdata_cachep == NULL)
return -ENOMEM;
nfs_wdata_mempool = mempool_create_slab_pool(MIN_POOL_WRITE,
nfs_wdata_cachep);
if (nfs_wdata_mempool == NULL)
return -ENOMEM;
nfs_commit_mempool = mempool_create_slab_pool(MIN_POOL_COMMIT,
nfs_wdata_cachep);
if (nfs_commit_mempool == NULL)
return -ENOMEM;
/*
* NFS congestion size, scale with available memory.
*
* 64MB: 8192k
* 128MB: 11585k
* 256MB: 16384k
* 512MB: 23170k
* 1GB: 32768k
* 2GB: 46340k
* 4GB: 65536k
* 8GB: 92681k
* 16GB: 131072k
*
* This allows larger machines to have larger/more transfers.
* Limit the default to 256M
*/
nfs_congestion_kb = (16*int_sqrt(totalram_pages)) << (PAGE_SHIFT-10);
if (nfs_congestion_kb > 256*1024)
nfs_congestion_kb = 256*1024;
return 0;
}
void nfs_destroy_writepagecache(void)
{
mempool_destroy(nfs_commit_mempool);
mempool_destroy(nfs_wdata_mempool);
kmem_cache_destroy(nfs_wdata_cachep);
}
/**
* write_one_page - write out a single page and optionally wait on I/O
* @page: the page to write
* @wait: if true, wait on writeout
*
* The page must be locked by the caller and will be unlocked upon return.
*
* write_one_page() returns a negative error code if I/O failed.
*/
int write_one_page(struct page *page, int wait)
{
struct address_space *mapping = page->mapping;
int ret = 0;
struct writeback_control wbc = {
.sync_mode = WB_SYNC_ALL,
.nr_to_write = 1,
};
BUG_ON(!PageLocked(page));
if (wait)
wait_on_page_writeback(page);
if (clear_page_dirty_for_io(page)) {
page_cache_get(page);
ret = mapping->a_ops->writepage(page, &wbc);
if (ret == 0 && wait) {
wait_on_page_writeback(page);
if (PageError(page))
ret = -EIO;
}
page_cache_release(page);
} else {
unlock_page(page);
}
return ret;
}
EXPORT_SYMBOL(write_one_page);
/*
* For address_spaces which do not use buffers nor write back.
*/
int __set_page_dirty_no_writeback(struct page *page)
{
if (!PageDirty(page))
SetPageDirty(page);
return 0;
}
/*
* Helper function for set_page_dirty family.
* NOTE: This relies on being atomic wrt interrupts.
*/
void account_page_dirtied(struct page *page, struct address_space *mapping)
{
if (mapping_cap_account_dirty(mapping)) {
__inc_zone_page_state(page, NR_FILE_DIRTY);
__inc_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE);
task_dirty_inc(current);
task_io_account_write(PAGE_CACHE_SIZE);
}
}
/*
* For address_spaces which do not use buffers. Just tag the page as dirty in
* its radix tree.
*
* This is also used when a single buffer is being dirtied: we want to set the
* page dirty in that case, but not all the buffers. This is a "bottom-up"
* dirtying, whereas __set_page_dirty_buffers() is a "top-down" dirtying.
*
* Most callers have locked the page, which pins the address_space in memory.
* But zap_pte_range() does not lock the page, however in that case the
* mapping is pinned by the vma's ->vm_file reference.
*
* We take care to handle the case where the page was truncated from the
* mapping by re-checking page_mapping() inside tree_lock.
*/
int __set_page_dirty_nobuffers(struct page *page)
{
if (!TestSetPageDirty(page)) {
struct address_space *mapping = page_mapping(page);
struct address_space *mapping2;
if (!mapping)
return 1;
spin_lock_irq(&mapping->tree_lock);
mapping2 = page_mapping(page);
if (mapping2) { /* Race with truncate? */
BUG_ON(mapping2 != mapping);
WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page));
account_page_dirtied(page, mapping);
radix_tree_tag_set(&mapping->page_tree,
page_index(page), PAGECACHE_TAG_DIRTY);
}
spin_unlock_irq(&mapping->tree_lock);
if (mapping->host) {
/* !PageAnon && !swapper_space */
__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
}
return 1;
}
return 0;
}
EXPORT_SYMBOL(__set_page_dirty_nobuffers);
/*
* When a writepage implementation decides that it doesn't want to write this
* page for some reason, it should redirty the locked page via
* redirty_page_for_writepage() and it should then unlock the page and return 0
*/
int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page)
{
wbc->pages_skipped++;
return __set_page_dirty_nobuffers(page);
}
static int ptpfs_file_readpage(struct file *filp, struct page *page)
{
//printk(KERN_INFO "%s\n", __FUNCTION__);
struct inode *inode;
int ret;
struct ptp_data_buffer *data=(struct ptp_data_buffer*)filp->private_data;
inode = page->mapping->host;
if (!PageLocked(page))
PAGE_BUG(page);
ret = -ESTALE;
/* work out how much to get and from where */
int offset = page->index << PAGE_CACHE_SHIFT;
int size = min((size_t)(inode->i_size - offset),(size_t)PAGE_SIZE);
char *buffer = kmap(page);
clear_page(buffer);
/* read the contents of the file from the server into the page */
int block = 0;
while (block < data->num_blocks && offset > data->blocks[block].block_size)
{
offset -= data->blocks[block].block_size;
block++;
}
if (block == data->num_blocks)
{
kunmap(page);
ret = -ESTALE;
goto error;
}
int toCopy = min(size,data->blocks[block].block_size-offset);
memcpy(buffer,&data->blocks[block].block[offset],toCopy);
size -= toCopy;
int pos = toCopy;
block++;
while (size && block < data->num_blocks)
{
toCopy = min(size,data->blocks[block].block_size);
memcpy(&buffer[pos],data->blocks[block].block,toCopy);
size -= toCopy;
pos += toCopy;
block++;
}
if (block == data->num_blocks && size > 0)
{
kunmap(page);
ret = -ESTALE;
goto error;
}
kunmap(page);
flush_dcache_page(page);
SetPageUptodate(page);
unlock_page(page);
return 0;
error:
SetPageError(page);
unlock_page(page);
return ret;
}
/*
* "Get" data from cleancache associated with the poolid/inode/index
* that were specified when the data was put to cleanache and, if
* successful, use it to fill the specified page with data and return 0.
* The pageframe is unchanged and returns -1 if the get fails.
* Page must be locked by caller.
*
* The function has two checks before any action is taken - whether
* a backend is registered and whether the sb->cleancache_poolid
* is correct.
*/
int __cleancache_get_page(struct page *page)
{
int ret = -1;
int pool_id;
int fake_pool_id;
struct cleancache_filekey key = { .u.key = { 0 } };
if (!cleancache_ops) {
cleancache_failed_gets++;
goto out;
}
VM_BUG_ON_PAGE(!PageLocked(page), page);
fake_pool_id = page->mapping->host->i_sb->cleancache_poolid;
if (fake_pool_id < 0)
goto out;
pool_id = get_poolid_from_fake(fake_pool_id);
if (cleancache_get_key(page->mapping->host, &key) < 0)
goto out;
if (pool_id >= 0)
ret = cleancache_ops->get_page(pool_id,
key, page->index, page);
if (ret == 0)
cleancache_succ_gets++;
else
cleancache_failed_gets++;
out:
return ret;
}
EXPORT_SYMBOL(__cleancache_get_page);
/*
* "Put" data from a page to cleancache and associate it with the
* (previously-obtained per-filesystem) poolid and the page's,
* inode and page index. Page must be locked. Note that a put_page
* always "succeeds", though a subsequent get_page may succeed or fail.
*
* The function has two checks before any action is taken - whether
* a backend is registered and whether the sb->cleancache_poolid
* is correct.
*/
void __cleancache_put_page(struct page *page)
{
int pool_id;
int fake_pool_id;
struct cleancache_filekey key = { .u.key = { 0 } };
if (!cleancache_ops) {
cleancache_puts++;
return;
}
VM_BUG_ON_PAGE(!PageLocked(page), page);
fake_pool_id = page->mapping->host->i_sb->cleancache_poolid;
if (fake_pool_id < 0)
return;
pool_id = get_poolid_from_fake(fake_pool_id);
if (pool_id >= 0 &&
cleancache_get_key(page->mapping->host, &key) >= 0) {
cleancache_ops->put_page(pool_id, key, page->index, page);
cleancache_puts++;
}
}
EXPORT_SYMBOL(__cleancache_put_page);
/*
* Invalidate any data from cleancache associated with the poolid and the
* page's inode and page index so that a subsequent "get" will fail.
*
* The function has two checks before any action is taken - whether
* a backend is registered and whether the sb->cleancache_poolid
* is correct.
*/
void __cleancache_invalidate_page(struct address_space *mapping,
struct page *page)
{
/* careful... page->mapping is NULL sometimes when this is called */
int pool_id;
int fake_pool_id = mapping->host->i_sb->cleancache_poolid;
struct cleancache_filekey key = { .u.key = { 0 } };
if (!cleancache_ops)
return;
if (fake_pool_id >= 0) {
pool_id = get_poolid_from_fake(fake_pool_id);
if (pool_id < 0)
return;
VM_BUG_ON_PAGE(!PageLocked(page), page);
if (cleancache_get_key(mapping->host, &key) >= 0) {
cleancache_ops->invalidate_page(pool_id,
key, page->index);
cleancache_invalidates++;
}
}
}
EXPORT_SYMBOL(__cleancache_invalidate_page);
/*
* Invalidate all data from cleancache associated with the poolid and the
* mappings's inode so that all subsequent gets to this poolid/inode
* will fail.
*
* The function has two checks before any action is taken - whether
* a backend is registered and whether the sb->cleancache_poolid
* is correct.
*/
/*! 2017. 2.25 study -ing */
void __cleancache_invalidate_inode(struct address_space *mapping)
{
int pool_id;
int fake_pool_id = mapping->host->i_sb->cleancache_poolid;
struct cleancache_filekey key = { .u.key = { 0 } };
if (!cleancache_ops)
return;
if (fake_pool_id < 0)
return;
pool_id = get_poolid_from_fake(fake_pool_id);
if (pool_id >= 0 && cleancache_get_key(mapping->host, &key) >= 0)
cleancache_ops->invalidate_inode(pool_id, key);
}
EXPORT_SYMBOL(__cleancache_invalidate_inode);
/*
* Called by any cleancache-enabled filesystem at time of unmount;
* note that pool_id is surrendered and may be returned by a subsequent
* cleancache_init_fs or cleancache_init_shared_fs.
*/
void __cleancache_invalidate_fs(struct super_block *sb)
{
int index;
int fake_pool_id = sb->cleancache_poolid;
int old_poolid = fake_pool_id;
mutex_lock(&poolid_mutex);
if (fake_pool_id >= FAKE_SHARED_FS_POOLID_OFFSET) {
index = fake_pool_id - FAKE_SHARED_FS_POOLID_OFFSET;
old_poolid = shared_fs_poolid_map[index];
shared_fs_poolid_map[index] = FS_UNKNOWN;
uuids[index] = NULL;
} else if (fake_pool_id >= FAKE_FS_POOLID_OFFSET) {
index = fake_pool_id - FAKE_FS_POOLID_OFFSET;
old_poolid = fs_poolid_map[index];
fs_poolid_map[index] = FS_UNKNOWN;
}
sb->cleancache_poolid = -1;
if (cleancache_ops)
cleancache_ops->invalidate_fs(old_poolid);
mutex_unlock(&poolid_mutex);
}
ClearPageSwapCache(page);
page_cache_release(page);
}
}
return error;
}
/*
* This must be called only on pages that have
* been verified to be in the swap cache.
*/
void __delete_from_swap_cache(struct page *page)
{
swp_entry_t ent = {.val = page_private(page)};
VM_BUG_ON(!PageLocked(page));
VM_BUG_ON(!PageSwapCache(page));
VM_BUG_ON(PageWriteback(page));
radix_tree_delete(&swapper_space.page_tree, page_private(page));
set_page_private(page, 0);
ClearPageSwapCache(page);
total_swapcache_pages--;
__dec_zone_page_state(page, NR_FILE_PAGES);
INC_CACHE_INFO(del_total);
mem_cgroup_uncharge_swapcache(page, ent);
}
/**
* add_to_swap - allocate swap space for a page
* @page: page we want to move to swap
/**
* write_one_page - write out a single page and optionally wait on I/O
* @page: the page to write
* @wait: if true, wait on writeout
*
* The page must be locked by the caller and will be unlocked upon return.
*
* write_one_page() returns a negative error code if I/O failed.
*/
int write_one_page(struct page *page, int wait)
{
struct address_space *mapping = page->mapping;
int ret = 0;
struct writeback_control wbc = {
.sync_mode = WB_SYNC_ALL,
.nr_to_write = 1,
};
BUG_ON(!PageLocked(page));
if (wait)
wait_on_page_writeback(page);
if (clear_page_dirty_for_io(page)) {
page_cache_get(page);
ret = mapping->a_ops->writepage(page, &wbc);
if (ret == 0 && wait) {
wait_on_page_writeback(page);
if (PageError(page))
ret = -EIO;
}
page_cache_release(page);
} else {
unlock_page(page);
}
return ret;
}
EXPORT_SYMBOL(write_one_page);
/*
* For address_spaces which do not use buffers nor write back.
*/
int __set_page_dirty_no_writeback(struct page *page)
{
if (!PageDirty(page))
return !TestSetPageDirty(page);
return 0;
}
/*
* Helper function for set_page_dirty family.
* NOTE: This relies on being atomic wrt interrupts.
*/
void account_page_dirtied(struct page *page, struct address_space *mapping)
{
if (mapping_cap_account_dirty(mapping)) {
__inc_zone_page_state(page, NR_FILE_DIRTY);
__inc_zone_page_state(page, NR_DIRTIED);
__inc_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE);
task_dirty_inc(current);
task_io_account_write(PAGE_CACHE_SIZE);
}
}
EXPORT_SYMBOL(account_page_dirtied);
/*
* Helper function for set_page_writeback family.
* NOTE: Unlike account_page_dirtied this does not rely on being atomic
* wrt interrupts.
*/
void account_page_writeback(struct page *page)
{
inc_zone_page_state(page, NR_WRITEBACK);
inc_zone_page_state(page, NR_WRITTEN);
}
/*
* Inspired by write_cache_pages from /mm/page-writeback.c
*/
static int ecryptfs_writepages(struct address_space *mapping,
struct writeback_control *wbc)
{
int ret = 0;
int done = 0;
struct pagevec pvec;
int nr_pages;
pgoff_t uninitialized_var(writeback_index);
pgoff_t index;
pgoff_t end; /* Inclusive */
pgoff_t done_index;
int cycled;
int range_whole = 0;
int tag;
struct page **pgs;
int pgidx;
/* printk("[g-ecryptfs] Info: call writepages\n"); */
pgs = kmalloc(sizeof(struct page*)*PAGEVEC_SIZE, GFP_KERNEL);
if (!pgs) {
printk("[g-ecryptfs] Error: pgs alloc failed!\n");
return -EFAULT;
}
pagevec_init(&pvec, 0);
if (wbc->range_cyclic) {
writeback_index = mapping->writeback_index; /* prev offset */
index = writeback_index;
if (index == 0)
cycled = 1;
else
cycled = 0;
end = -1;
} else {
index = wbc->range_start >> PAGE_CACHE_SHIFT;
end = wbc->range_end >> PAGE_CACHE_SHIFT;
if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
range_whole = 1;
cycled = 1; /* ignore range_cyclic tests */
}
if (wbc->sync_mode == WB_SYNC_ALL)
tag = PAGECACHE_TAG_TOWRITE;
else
tag = PAGECACHE_TAG_DIRTY;
retry:
if (wbc->sync_mode == WB_SYNC_ALL)
tag_pages_for_writeback(mapping, index, end);
done_index = index;
while (!done && (index <= end)) {
int i;
struct page *page;
nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
if (nr_pages == 0)
break;
pgidx = 0;
for (i = 0; i < nr_pages; i++) {
page = pvec.pages[i];
/*
* At this point, the page may be truncated or
* invalidated (changing page->mapping to NULL), or
* even swizzled back from swapper_space to tmpfs file
* mapping. However, page->index will not change
* because we have a reference on the page.
*/
if (page->index > end) {
/*
* can't be range_cyclic (1st pass) because
* end == -1 in that case.
*/
done = 1;
break;
}
done_index = page->index + 1;
lock_page(page);
/*
* Page truncated or invalidated. We can freely skip it
* then, even for data integrity operations: the page
* has disappeared concurrently, so there could be no
* real expectation of this data interity operation
* even if there is now a new, dirty page at the same
* pagecache address.
*/
if (unlikely(page->mapping != mapping)) {
continue_unlock:
unlock_page(page);
continue;
}
if (!PageDirty(page)) {
/* someone wrote it for us */
goto continue_unlock;
}
if (PageWriteback(page)) {
if (wbc->sync_mode != WB_SYNC_NONE)
wait_on_page_writeback(page);
else
goto continue_unlock;
}
BUG_ON(PageWriteback(page));
if (!clear_page_dirty_for_io(page))
goto continue_unlock;
pgs[pgidx++] = page;
}
/*trace_wbc_writepage(wbc, mapping->backing_dev_info);*/
ret = ecryptfs_encrypt_pages(pgs, pgidx);
//printk("[g-ecryptfs] Info: enc %d pages in writepages\n", pgidx);
mapping_set_error(mapping, ret);
for (i = 0; i < nr_pages; i++) {
page = pvec.pages[i];
if (unlikely(ret)) {
if (ret == AOP_WRITEPAGE_ACTIVATE) {
if (PageLocked(page))
unlock_page(page);
ret = 0;
} else {
/*
* done_index is set past this page,
* so media errors will not choke
* background writeout for the entire
* file. This has consequences for
* range_cyclic semantics (ie. it may
* not be suitable for data integrity
* writeout).
*/
done = 1;
break;
}
}
/*
* We stop writing back only if we are not doing
* integrity sync. In case of integrity sync we have to
* keep going until we have written all the pages
* we tagged for writeback prior to entering this loop.
*/
if (--wbc->nr_to_write <= 0 &&
wbc->sync_mode == WB_SYNC_NONE) {
done = 1;
break;
}
}
pagevec_release(&pvec);
cond_resched();
}
if (!cycled && !done) {
/*
* range_cyclic:
* We hit the last page and there is more work to be done: wrap
* back to the start of the file
*/
cycled = 1;
index = 0;
end = writeback_index - 1;
goto retry;
}
if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
mapping->writeback_index = done_index;
kfree(pgs);
return ret;
}
