Revision e1cbbfa5f5aaf40a1fe70856fac4dfcc33e0e651 authored by Josef Bacik on 17 March 2015, 14:52:28 UTC, committed by Josef Bacik on 17 March 2015, 20:36:35 UTC
We are keeping track of how many extents we need to reserve properly based on the amount we want to write, but we were still incrementing outstanding_extents if we wrote less than what we requested. This isn't quite right since we will be limited to our max extent size. So instead lets do something horrible! Keep track of how many outstanding_extents we reserved, and decrement each time we allocate an extent. If we use our entire reserve make sure to jack up outstanding_extents on the inode so the accounting works out properly. Thanks, Reported-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Josef Bacik <jbacik@fb.com>
1 parent 6a3891c
dir.c
/*
* linux/fs/ext2/dir.c
*
* Copyright (C) 1992, 1993, 1994, 1995
* Remy Card (card@masi.ibp.fr)
* Laboratoire MASI - Institut Blaise Pascal
* Universite Pierre et Marie Curie (Paris VI)
*
* from
*
* linux/fs/minix/dir.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*
* ext2 directory handling functions
*
* Big-endian to little-endian byte-swapping/bitmaps by
* David S. Miller (davem@caip.rutgers.edu), 1995
*
* All code that works with directory layout had been switched to pagecache
* and moved here. AV
*/
#include "ext2.h"
#include <linux/buffer_head.h>
#include <linux/pagemap.h>
#include <linux/swap.h>
typedef struct ext2_dir_entry_2 ext2_dirent;
/*
* Tests against MAX_REC_LEN etc were put in place for 64k block
* sizes; if that is not possible on this arch, we can skip
* those tests and speed things up.
*/
static inline unsigned ext2_rec_len_from_disk(__le16 dlen)
{
unsigned len = le16_to_cpu(dlen);
#if (PAGE_CACHE_SIZE >= 65536)
if (len == EXT2_MAX_REC_LEN)
return 1 << 16;
#endif
return len;
}
static inline __le16 ext2_rec_len_to_disk(unsigned len)
{
#if (PAGE_CACHE_SIZE >= 65536)
if (len == (1 << 16))
return cpu_to_le16(EXT2_MAX_REC_LEN);
else
BUG_ON(len > (1 << 16));
#endif
return cpu_to_le16(len);
}
/*
* ext2 uses block-sized chunks. Arguably, sector-sized ones would be
* more robust, but we have what we have
*/
static inline unsigned ext2_chunk_size(struct inode *inode)
{
return inode->i_sb->s_blocksize;
}
static inline void ext2_put_page(struct page *page)
{
kunmap(page);
page_cache_release(page);
}
static inline unsigned long dir_pages(struct inode *inode)
{
return (inode->i_size+PAGE_CACHE_SIZE-1)>>PAGE_CACHE_SHIFT;
}
/*
* Return the offset into page `page_nr' of the last valid
* byte in that page, plus one.
*/
static unsigned
ext2_last_byte(struct inode *inode, unsigned long page_nr)
{
unsigned last_byte = inode->i_size;
last_byte -= page_nr << PAGE_CACHE_SHIFT;
if (last_byte > PAGE_CACHE_SIZE)
last_byte = PAGE_CACHE_SIZE;
return last_byte;
}
static int ext2_commit_chunk(struct page *page, loff_t pos, unsigned len)
{
struct address_space *mapping = page->mapping;
struct inode *dir = mapping->host;
int err = 0;
dir->i_version++;
block_write_end(NULL, mapping, pos, len, len, page, NULL);
if (pos+len > dir->i_size) {
i_size_write(dir, pos+len);
mark_inode_dirty(dir);
}
if (IS_DIRSYNC(dir)) {
err = write_one_page(page, 1);
if (!err)
err = sync_inode_metadata(dir, 1);
} else {
unlock_page(page);
}
return err;
}
static void ext2_check_page(struct page *page, int quiet)
{
struct inode *dir = page->mapping->host;
struct super_block *sb = dir->i_sb;
unsigned chunk_size = ext2_chunk_size(dir);
char *kaddr = page_address(page);
u32 max_inumber = le32_to_cpu(EXT2_SB(sb)->s_es->s_inodes_count);
unsigned offs, rec_len;
unsigned limit = PAGE_CACHE_SIZE;
ext2_dirent *p;
char *error;
if ((dir->i_size >> PAGE_CACHE_SHIFT) == page->index) {
limit = dir->i_size & ~PAGE_CACHE_MASK;
if (limit & (chunk_size - 1))
goto Ebadsize;
if (!limit)
goto out;
}
for (offs = 0; offs <= limit - EXT2_DIR_REC_LEN(1); offs += rec_len) {
p = (ext2_dirent *)(kaddr + offs);
rec_len = ext2_rec_len_from_disk(p->rec_len);
if (unlikely(rec_len < EXT2_DIR_REC_LEN(1)))
goto Eshort;
if (unlikely(rec_len & 3))
goto Ealign;
if (unlikely(rec_len < EXT2_DIR_REC_LEN(p->name_len)))
goto Enamelen;
if (unlikely(((offs + rec_len - 1) ^ offs) & ~(chunk_size-1)))
goto Espan;
if (unlikely(le32_to_cpu(p->inode) > max_inumber))
goto Einumber;
}
if (offs != limit)
goto Eend;
out:
SetPageChecked(page);
return;
/* Too bad, we had an error */
Ebadsize:
if (!quiet)
ext2_error(sb, __func__,
"size of directory #%lu is not a multiple "
"of chunk size", dir->i_ino);
goto fail;
Eshort:
error = "rec_len is smaller than minimal";
goto bad_entry;
Ealign:
error = "unaligned directory entry";
goto bad_entry;
Enamelen:
error = "rec_len is too small for name_len";
goto bad_entry;
Espan:
error = "directory entry across blocks";
goto bad_entry;
Einumber:
error = "inode out of bounds";
bad_entry:
if (!quiet)
ext2_error(sb, __func__, "bad entry in directory #%lu: : %s - "
"offset=%lu, inode=%lu, rec_len=%d, name_len=%d",
dir->i_ino, error, (page->index<<PAGE_CACHE_SHIFT)+offs,
(unsigned long) le32_to_cpu(p->inode),
rec_len, p->name_len);
goto fail;
Eend:
if (!quiet) {
p = (ext2_dirent *)(kaddr + offs);
ext2_error(sb, "ext2_check_page",
"entry in directory #%lu spans the page boundary"
"offset=%lu, inode=%lu",
dir->i_ino, (page->index<<PAGE_CACHE_SHIFT)+offs,
(unsigned long) le32_to_cpu(p->inode));
}
fail:
SetPageChecked(page);
SetPageError(page);
}
static struct page * ext2_get_page(struct inode *dir, unsigned long n,
int quiet)
{
struct address_space *mapping = dir->i_mapping;
struct page *page = read_mapping_page(mapping, n, NULL);
if (!IS_ERR(page)) {
kmap(page);
if (!PageChecked(page))
ext2_check_page(page, quiet);
if (PageError(page))
goto fail;
}
return page;
fail:
ext2_put_page(page);
return ERR_PTR(-EIO);
}
/*
* NOTE! unlike strncmp, ext2_match returns 1 for success, 0 for failure.
*
* len <= EXT2_NAME_LEN and de != NULL are guaranteed by caller.
*/
static inline int ext2_match (int len, const char * const name,
struct ext2_dir_entry_2 * de)
{
if (len != de->name_len)
return 0;
if (!de->inode)
return 0;
return !memcmp(name, de->name, len);
}
/*
* p is at least 6 bytes before the end of page
*/
static inline ext2_dirent *ext2_next_entry(ext2_dirent *p)
{
return (ext2_dirent *)((char *)p +
ext2_rec_len_from_disk(p->rec_len));
}
static inline unsigned
ext2_validate_entry(char *base, unsigned offset, unsigned mask)
{
ext2_dirent *de = (ext2_dirent*)(base + offset);
ext2_dirent *p = (ext2_dirent*)(base + (offset&mask));
while ((char*)p < (char*)de) {
if (p->rec_len == 0)
break;
p = ext2_next_entry(p);
}
return (char *)p - base;
}
static unsigned char ext2_filetype_table[EXT2_FT_MAX] = {
[EXT2_FT_UNKNOWN] = DT_UNKNOWN,
[EXT2_FT_REG_FILE] = DT_REG,
[EXT2_FT_DIR] = DT_DIR,
[EXT2_FT_CHRDEV] = DT_CHR,
[EXT2_FT_BLKDEV] = DT_BLK,
[EXT2_FT_FIFO] = DT_FIFO,
[EXT2_FT_SOCK] = DT_SOCK,
[EXT2_FT_SYMLINK] = DT_LNK,
};
#define S_SHIFT 12
static unsigned char ext2_type_by_mode[S_IFMT >> S_SHIFT] = {
[S_IFREG >> S_SHIFT] = EXT2_FT_REG_FILE,
[S_IFDIR >> S_SHIFT] = EXT2_FT_DIR,
[S_IFCHR >> S_SHIFT] = EXT2_FT_CHRDEV,
[S_IFBLK >> S_SHIFT] = EXT2_FT_BLKDEV,
[S_IFIFO >> S_SHIFT] = EXT2_FT_FIFO,
[S_IFSOCK >> S_SHIFT] = EXT2_FT_SOCK,
[S_IFLNK >> S_SHIFT] = EXT2_FT_SYMLINK,
};
static inline void ext2_set_de_type(ext2_dirent *de, struct inode *inode)
{
umode_t mode = inode->i_mode;
if (EXT2_HAS_INCOMPAT_FEATURE(inode->i_sb, EXT2_FEATURE_INCOMPAT_FILETYPE))
de->file_type = ext2_type_by_mode[(mode & S_IFMT)>>S_SHIFT];
else
de->file_type = 0;
}
static int
ext2_readdir(struct file *file, struct dir_context *ctx)
{
loff_t pos = ctx->pos;
struct inode *inode = file_inode(file);
struct super_block *sb = inode->i_sb;
unsigned int offset = pos & ~PAGE_CACHE_MASK;
unsigned long n = pos >> PAGE_CACHE_SHIFT;
unsigned long npages = dir_pages(inode);
unsigned chunk_mask = ~(ext2_chunk_size(inode)-1);
unsigned char *types = NULL;
int need_revalidate = file->f_version != inode->i_version;
if (pos > inode->i_size - EXT2_DIR_REC_LEN(1))
return 0;
if (EXT2_HAS_INCOMPAT_FEATURE(sb, EXT2_FEATURE_INCOMPAT_FILETYPE))
types = ext2_filetype_table;
for ( ; n < npages; n++, offset = 0) {
char *kaddr, *limit;
ext2_dirent *de;
struct page *page = ext2_get_page(inode, n, 0);
if (IS_ERR(page)) {
ext2_error(sb, __func__,
"bad page in #%lu",
inode->i_ino);
ctx->pos += PAGE_CACHE_SIZE - offset;
return PTR_ERR(page);
}
kaddr = page_address(page);
if (unlikely(need_revalidate)) {
if (offset) {
offset = ext2_validate_entry(kaddr, offset, chunk_mask);
ctx->pos = (n<<PAGE_CACHE_SHIFT) + offset;
}
file->f_version = inode->i_version;
need_revalidate = 0;
}
de = (ext2_dirent *)(kaddr+offset);
limit = kaddr + ext2_last_byte(inode, n) - EXT2_DIR_REC_LEN(1);
for ( ;(char*)de <= limit; de = ext2_next_entry(de)) {
if (de->rec_len == 0) {
ext2_error(sb, __func__,
"zero-length directory entry");
ext2_put_page(page);
return -EIO;
}
if (de->inode) {
unsigned char d_type = DT_UNKNOWN;
if (types && de->file_type < EXT2_FT_MAX)
d_type = types[de->file_type];
if (!dir_emit(ctx, de->name, de->name_len,
le32_to_cpu(de->inode),
d_type)) {
ext2_put_page(page);
return 0;
}
}
ctx->pos += ext2_rec_len_from_disk(de->rec_len);
}
ext2_put_page(page);
}
return 0;
}
/*
* ext2_find_entry()
*
* finds an entry in the specified directory with the wanted name. It
* returns the page in which the entry was found (as a parameter - res_page),
* and the entry itself. Page is returned mapped and unlocked.
* Entry is guaranteed to be valid.
*/
struct ext2_dir_entry_2 *ext2_find_entry (struct inode * dir,
struct qstr *child, struct page ** res_page)
{
const char *name = child->name;
int namelen = child->len;
unsigned reclen = EXT2_DIR_REC_LEN(namelen);
unsigned long start, n;
unsigned long npages = dir_pages(dir);
struct page *page = NULL;
struct ext2_inode_info *ei = EXT2_I(dir);
ext2_dirent * de;
int dir_has_error = 0;
if (npages == 0)
goto out;
/* OFFSET_CACHE */
*res_page = NULL;
start = ei->i_dir_start_lookup;
if (start >= npages)
start = 0;
n = start;
do {
char *kaddr;
page = ext2_get_page(dir, n, dir_has_error);
if (!IS_ERR(page)) {
kaddr = page_address(page);
de = (ext2_dirent *) kaddr;
kaddr += ext2_last_byte(dir, n) - reclen;
while ((char *) de <= kaddr) {
if (de->rec_len == 0) {
ext2_error(dir->i_sb, __func__,
"zero-length directory entry");
ext2_put_page(page);
goto out;
}
if (ext2_match (namelen, name, de))
goto found;
de = ext2_next_entry(de);
}
ext2_put_page(page);
} else
dir_has_error = 1;
if (++n >= npages)
n = 0;
/* next page is past the blocks we've got */
if (unlikely(n > (dir->i_blocks >> (PAGE_CACHE_SHIFT - 9)))) {
ext2_error(dir->i_sb, __func__,
"dir %lu size %lld exceeds block count %llu",
dir->i_ino, dir->i_size,
(unsigned long long)dir->i_blocks);
goto out;
}
} while (n != start);
out:
return NULL;
found:
*res_page = page;
ei->i_dir_start_lookup = n;
return de;
}
struct ext2_dir_entry_2 * ext2_dotdot (struct inode *dir, struct page **p)
{
struct page *page = ext2_get_page(dir, 0, 0);
ext2_dirent *de = NULL;
if (!IS_ERR(page)) {
de = ext2_next_entry((ext2_dirent *) page_address(page));
*p = page;
}
return de;
}
ino_t ext2_inode_by_name(struct inode *dir, struct qstr *child)
{
ino_t res = 0;
struct ext2_dir_entry_2 *de;
struct page *page;
de = ext2_find_entry (dir, child, &page);
if (de) {
res = le32_to_cpu(de->inode);
ext2_put_page(page);
}
return res;
}
static int ext2_prepare_chunk(struct page *page, loff_t pos, unsigned len)
{
return __block_write_begin(page, pos, len, ext2_get_block);
}
/* Releases the page */
void ext2_set_link(struct inode *dir, struct ext2_dir_entry_2 *de,
struct page *page, struct inode *inode, int update_times)
{
loff_t pos = page_offset(page) +
(char *) de - (char *) page_address(page);
unsigned len = ext2_rec_len_from_disk(de->rec_len);
int err;
lock_page(page);
err = ext2_prepare_chunk(page, pos, len);
BUG_ON(err);
de->inode = cpu_to_le32(inode->i_ino);
ext2_set_de_type(de, inode);
err = ext2_commit_chunk(page, pos, len);
ext2_put_page(page);
if (update_times)
dir->i_mtime = dir->i_ctime = CURRENT_TIME_SEC;
EXT2_I(dir)->i_flags &= ~EXT2_BTREE_FL;
mark_inode_dirty(dir);
}
/*
* Parent is locked.
*/
int ext2_add_link (struct dentry *dentry, struct inode *inode)
{
struct inode *dir = dentry->d_parent->d_inode;
const char *name = dentry->d_name.name;
int namelen = dentry->d_name.len;
unsigned chunk_size = ext2_chunk_size(dir);
unsigned reclen = EXT2_DIR_REC_LEN(namelen);
unsigned short rec_len, name_len;
struct page *page = NULL;
ext2_dirent * de;
unsigned long npages = dir_pages(dir);
unsigned long n;
char *kaddr;
loff_t pos;
int err;
/*
* We take care of directory expansion in the same loop.
* This code plays outside i_size, so it locks the page
* to protect that region.
*/
for (n = 0; n <= npages; n++) {
char *dir_end;
page = ext2_get_page(dir, n, 0);
err = PTR_ERR(page);
if (IS_ERR(page))
goto out;
lock_page(page);
kaddr = page_address(page);
dir_end = kaddr + ext2_last_byte(dir, n);
de = (ext2_dirent *)kaddr;
kaddr += PAGE_CACHE_SIZE - reclen;
while ((char *)de <= kaddr) {
if ((char *)de == dir_end) {
/* We hit i_size */
name_len = 0;
rec_len = chunk_size;
de->rec_len = ext2_rec_len_to_disk(chunk_size);
de->inode = 0;
goto got_it;
}
if (de->rec_len == 0) {
ext2_error(dir->i_sb, __func__,
"zero-length directory entry");
err = -EIO;
goto out_unlock;
}
err = -EEXIST;
if (ext2_match (namelen, name, de))
goto out_unlock;
name_len = EXT2_DIR_REC_LEN(de->name_len);
rec_len = ext2_rec_len_from_disk(de->rec_len);
if (!de->inode && rec_len >= reclen)
goto got_it;
if (rec_len >= name_len + reclen)
goto got_it;
de = (ext2_dirent *) ((char *) de + rec_len);
}
unlock_page(page);
ext2_put_page(page);
}
BUG();
return -EINVAL;
got_it:
pos = page_offset(page) +
(char*)de - (char*)page_address(page);
err = ext2_prepare_chunk(page, pos, rec_len);
if (err)
goto out_unlock;
if (de->inode) {
ext2_dirent *de1 = (ext2_dirent *) ((char *) de + name_len);
de1->rec_len = ext2_rec_len_to_disk(rec_len - name_len);
de->rec_len = ext2_rec_len_to_disk(name_len);
de = de1;
}
de->name_len = namelen;
memcpy(de->name, name, namelen);
de->inode = cpu_to_le32(inode->i_ino);
ext2_set_de_type (de, inode);
err = ext2_commit_chunk(page, pos, rec_len);
dir->i_mtime = dir->i_ctime = CURRENT_TIME_SEC;
EXT2_I(dir)->i_flags &= ~EXT2_BTREE_FL;
mark_inode_dirty(dir);
/* OFFSET_CACHE */
out_put:
ext2_put_page(page);
out:
return err;
out_unlock:
unlock_page(page);
goto out_put;
}
/*
* ext2_delete_entry deletes a directory entry by merging it with the
* previous entry. Page is up-to-date. Releases the page.
*/
int ext2_delete_entry (struct ext2_dir_entry_2 * dir, struct page * page )
{
struct inode *inode = page->mapping->host;
char *kaddr = page_address(page);
unsigned from = ((char*)dir - kaddr) & ~(ext2_chunk_size(inode)-1);
unsigned to = ((char *)dir - kaddr) +
ext2_rec_len_from_disk(dir->rec_len);
loff_t pos;
ext2_dirent * pde = NULL;
ext2_dirent * de = (ext2_dirent *) (kaddr + from);
int err;
while ((char*)de < (char*)dir) {
if (de->rec_len == 0) {
ext2_error(inode->i_sb, __func__,
"zero-length directory entry");
err = -EIO;
goto out;
}
pde = de;
de = ext2_next_entry(de);
}
if (pde)
from = (char*)pde - (char*)page_address(page);
pos = page_offset(page) + from;
lock_page(page);
err = ext2_prepare_chunk(page, pos, to - from);
BUG_ON(err);
if (pde)
pde->rec_len = ext2_rec_len_to_disk(to - from);
dir->inode = 0;
err = ext2_commit_chunk(page, pos, to - from);
inode->i_ctime = inode->i_mtime = CURRENT_TIME_SEC;
EXT2_I(inode)->i_flags &= ~EXT2_BTREE_FL;
mark_inode_dirty(inode);
out:
ext2_put_page(page);
return err;
}
/*
* Set the first fragment of directory.
*/
int ext2_make_empty(struct inode *inode, struct inode *parent)
{
struct page *page = grab_cache_page(inode->i_mapping, 0);
unsigned chunk_size = ext2_chunk_size(inode);
struct ext2_dir_entry_2 * de;
int err;
void *kaddr;
if (!page)
return -ENOMEM;
err = ext2_prepare_chunk(page, 0, chunk_size);
if (err) {
unlock_page(page);
goto fail;
}
kaddr = kmap_atomic(page);
memset(kaddr, 0, chunk_size);
de = (struct ext2_dir_entry_2 *)kaddr;
de->name_len = 1;
de->rec_len = ext2_rec_len_to_disk(EXT2_DIR_REC_LEN(1));
memcpy (de->name, ".\0\0", 4);
de->inode = cpu_to_le32(inode->i_ino);
ext2_set_de_type (de, inode);
de = (struct ext2_dir_entry_2 *)(kaddr + EXT2_DIR_REC_LEN(1));
de->name_len = 2;
de->rec_len = ext2_rec_len_to_disk(chunk_size - EXT2_DIR_REC_LEN(1));
de->inode = cpu_to_le32(parent->i_ino);
memcpy (de->name, "..\0", 4);
ext2_set_de_type (de, inode);
kunmap_atomic(kaddr);
err = ext2_commit_chunk(page, 0, chunk_size);
fail:
page_cache_release(page);
return err;
}
/*
* routine to check that the specified directory is empty (for rmdir)
*/
int ext2_empty_dir (struct inode * inode)
{
struct page *page = NULL;
unsigned long i, npages = dir_pages(inode);
int dir_has_error = 0;
for (i = 0; i < npages; i++) {
char *kaddr;
ext2_dirent * de;
page = ext2_get_page(inode, i, dir_has_error);
if (IS_ERR(page)) {
dir_has_error = 1;
continue;
}
kaddr = page_address(page);
de = (ext2_dirent *)kaddr;
kaddr += ext2_last_byte(inode, i) - EXT2_DIR_REC_LEN(1);
while ((char *)de <= kaddr) {
if (de->rec_len == 0) {
ext2_error(inode->i_sb, __func__,
"zero-length directory entry");
printk("kaddr=%p, de=%p\n", kaddr, de);
goto not_empty;
}
if (de->inode != 0) {
/* check for . and .. */
if (de->name[0] != '.')
goto not_empty;
if (de->name_len > 2)
goto not_empty;
if (de->name_len < 2) {
if (de->inode !=
cpu_to_le32(inode->i_ino))
goto not_empty;
} else if (de->name[1] != '.')
goto not_empty;
}
de = ext2_next_entry(de);
}
ext2_put_page(page);
}
return 1;
not_empty:
ext2_put_page(page);
return 0;
}
const struct file_operations ext2_dir_operations = {
.llseek = generic_file_llseek,
.read = generic_read_dir,
.iterate = ext2_readdir,
.unlocked_ioctl = ext2_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = ext2_compat_ioctl,
#endif
.fsync = ext2_fsync,
};
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...