* Copyright (C) 2002-2004 VERITAS Software Corporation.
* Copyright (C) 2004 Andi Kleen, SuSE Labs
*
+ * Extended attribute support for tmpfs:
+ * Copyright (c) 2004, Luke Kenneth Casson Leighton <lkcl@lkcl.net>
+ * Copyright (c) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com>
+ *
* This file is released under the GPL.
*/
#include <linux/swapops.h>
#include <linux/mempolicy.h>
#include <linux/namei.h>
+#include <linux/xattr.h>
#include <asm/uaccess.h>
#include <asm/div64.h>
#include <asm/pgtable.h>
#define SHMEM_PAGEIN VM_READ
#define SHMEM_TRUNCATE VM_WRITE
+/* Definition to limit shmem_truncate's steps between cond_rescheds */
+#define LATENCY_LIMIT 64
+
/* Pretend that each entry is of this size in directory's i_size */
#define BOGO_DIRENT_SIZE 20
static struct file_operations shmem_file_operations;
static struct inode_operations shmem_inode_operations;
static struct inode_operations shmem_dir_inode_operations;
+static struct inode_operations shmem_special_inode_operations;
static struct vm_operations_struct shmem_vm_ops;
static struct backing_dev_info shmem_backing_dev_info = {
};
static LIST_HEAD(shmem_swaplist);
-static spinlock_t shmem_swaplist_lock = SPIN_LOCK_UNLOCKED;
+static DEFINE_SPINLOCK(shmem_swaplist_lock);
-static void shmem_free_block(struct inode *inode)
+static void shmem_free_blocks(struct inode *inode, long pages)
{
struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
if (sbinfo) {
spin_lock(&sbinfo->stat_lock);
- sbinfo->free_blocks++;
- inode->i_blocks -= BLOCKS_PER_PAGE;
+ sbinfo->free_blocks += pages;
+ inode->i_blocks -= pages*BLOCKS_PER_PAGE;
spin_unlock(&sbinfo->stat_lock);
}
}
freed = info->alloced - info->swapped - inode->i_mapping->nrpages;
if (freed > 0) {
- struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
info->alloced -= freed;
shmem_unacct_blocks(info->flags, freed);
- if (sbinfo) {
- spin_lock(&sbinfo->stat_lock);
- sbinfo->free_blocks += freed;
- inode->i_blocks -= freed*BLOCKS_PER_PAGE;
- spin_unlock(&sbinfo->stat_lock);
- }
+ shmem_free_blocks(inode, freed);
}
}
}
spin_unlock(&info->lock);
- page = shmem_dir_alloc(mapping_gfp_mask(inode->i_mapping));
+ page = shmem_dir_alloc(mapping_gfp_mask(inode->i_mapping) | __GFP_ZERO);
if (page) {
- clear_highpage(page);
page->nr_swapped = 0;
}
spin_lock(&info->lock);
if (!page) {
- shmem_free_block(inode);
+ shmem_free_blocks(inode, 1);
return ERR_PTR(-ENOMEM);
}
if (sgp != SGP_WRITE &&
}
if (page) {
/* another task gave its page, or truncated the file */
- shmem_free_block(inode);
+ shmem_free_blocks(inode, 1);
shmem_dir_free(page);
}
if (info->next_index <= index && !IS_ERR(entry))
return freed;
}
+static int shmem_map_and_free_swp(struct page *subdir,
+ int offset, int limit, struct page ***dir)
+{
+ swp_entry_t *ptr;
+ int freed = 0;
+
+ ptr = shmem_swp_map(subdir);
+ for (; offset < limit; offset += LATENCY_LIMIT) {
+ int size = limit - offset;
+ if (size > LATENCY_LIMIT)
+ size = LATENCY_LIMIT;
+ freed += shmem_free_swp(ptr+offset, ptr+offset+size);
+ if (need_resched()) {
+ shmem_swp_unmap(ptr);
+ if (*dir) {
+ shmem_dir_unmap(*dir);
+ *dir = NULL;
+ }
+ cond_resched();
+ ptr = shmem_swp_map(subdir);
+ }
+ }
+ shmem_swp_unmap(ptr);
+ return freed;
+}
+
+static void shmem_free_pages(struct list_head *next)
+{
+ struct page *page;
+ int freed = 0;
+
+ do {
+ page = container_of(next, struct page, lru);
+ next = next->next;
+ shmem_dir_free(page);
+ freed++;
+ if (freed >= LATENCY_LIMIT) {
+ cond_resched();
+ freed = 0;
+ }
+ } while (next);
+}
+
static void shmem_truncate(struct inode *inode)
{
struct shmem_inode_info *info = SHMEM_I(inode);
unsigned long size;
unsigned long limit;
unsigned long stage;
+ unsigned long diroff;
struct page **dir;
+ struct page *topdir;
+ struct page *middir;
struct page *subdir;
- struct page *empty;
swp_entry_t *ptr;
+ LIST_HEAD(pages_to_free);
+ long nr_pages_to_free = 0;
+ long nr_swaps_freed = 0;
int offset;
int freed;
info->flags |= SHMEM_TRUNCATE;
limit = info->next_index;
info->next_index = idx;
+ topdir = info->i_indirect;
+ if (topdir && idx <= SHMEM_NR_DIRECT) {
+ info->i_indirect = NULL;
+ nr_pages_to_free++;
+ list_add(&topdir->lru, &pages_to_free);
+ }
+ spin_unlock(&info->lock);
+
if (info->swapped && idx < SHMEM_NR_DIRECT) {
ptr = info->i_direct;
size = limit;
if (size > SHMEM_NR_DIRECT)
size = SHMEM_NR_DIRECT;
- info->swapped -= shmem_free_swp(ptr+idx, ptr+size);
+ nr_swaps_freed = shmem_free_swp(ptr+idx, ptr+size);
}
- if (!info->i_indirect)
+ if (!topdir)
goto done2;
BUG_ON(limit <= SHMEM_NR_DIRECT);
offset = idx % ENTRIES_PER_PAGE;
idx -= offset;
- empty = NULL;
- dir = shmem_dir_map(info->i_indirect);
+ dir = shmem_dir_map(topdir);
stage = ENTRIES_PER_PAGEPAGE/2;
- if (idx < ENTRIES_PER_PAGEPAGE/2)
- dir += idx/ENTRIES_PER_PAGE;
- else {
+ if (idx < ENTRIES_PER_PAGEPAGE/2) {
+ middir = topdir;
+ diroff = idx/ENTRIES_PER_PAGE;
+ } else {
dir += ENTRIES_PER_PAGE/2;
dir += (idx - ENTRIES_PER_PAGEPAGE/2)/ENTRIES_PER_PAGEPAGE;
while (stage <= idx)
stage += ENTRIES_PER_PAGEPAGE;
+ middir = *dir;
if (*dir) {
- subdir = *dir;
- size = ((idx - ENTRIES_PER_PAGEPAGE/2) %
+ diroff = ((idx - ENTRIES_PER_PAGEPAGE/2) %
ENTRIES_PER_PAGEPAGE) / ENTRIES_PER_PAGE;
- if (!size && !offset) {
- empty = subdir;
+ if (!diroff && !offset) {
*dir = NULL;
+ nr_pages_to_free++;
+ list_add(&middir->lru, &pages_to_free);
}
shmem_dir_unmap(dir);
- dir = shmem_dir_map(subdir) + size;
+ dir = shmem_dir_map(middir);
} else {
+ diroff = 0;
offset = 0;
idx = stage;
}
}
- for (; idx < limit; idx += ENTRIES_PER_PAGE, dir++) {
+ for (; idx < limit; idx += ENTRIES_PER_PAGE, diroff++) {
if (unlikely(idx == stage)) {
- shmem_dir_unmap(dir-1);
- dir = shmem_dir_map(info->i_indirect) +
+ shmem_dir_unmap(dir);
+ dir = shmem_dir_map(topdir) +
ENTRIES_PER_PAGE/2 + idx/ENTRIES_PER_PAGEPAGE;
while (!*dir) {
dir++;
goto done1;
}
stage = idx + ENTRIES_PER_PAGEPAGE;
- subdir = *dir;
+ middir = *dir;
*dir = NULL;
+ nr_pages_to_free++;
+ list_add(&middir->lru, &pages_to_free);
shmem_dir_unmap(dir);
- if (empty) {
- shmem_dir_free(empty);
- shmem_free_block(inode);
- }
- empty = subdir;
- cond_resched_lock(&info->lock);
- dir = shmem_dir_map(subdir);
+ cond_resched();
+ dir = shmem_dir_map(middir);
+ diroff = 0;
}
- subdir = *dir;
+ subdir = dir[diroff];
if (subdir && subdir->nr_swapped) {
- ptr = shmem_swp_map(subdir);
size = limit - idx;
if (size > ENTRIES_PER_PAGE)
size = ENTRIES_PER_PAGE;
- freed = shmem_free_swp(ptr+offset, ptr+size);
- shmem_swp_unmap(ptr);
- info->swapped -= freed;
+ freed = shmem_map_and_free_swp(subdir,
+ offset, size, &dir);
+ if (!dir)
+ dir = shmem_dir_map(middir);
+ nr_swaps_freed += freed;
+ if (offset)
+ spin_lock(&info->lock);
subdir->nr_swapped -= freed;
+ if (offset)
+ spin_unlock(&info->lock);
BUG_ON(subdir->nr_swapped > offset);
}
if (offset)
offset = 0;
else if (subdir) {
- *dir = NULL;
- shmem_dir_free(subdir);
- shmem_free_block(inode);
+ dir[diroff] = NULL;
+ nr_pages_to_free++;
+ list_add(&subdir->lru, &pages_to_free);
}
}
done1:
- shmem_dir_unmap(dir-1);
- if (empty) {
- shmem_dir_free(empty);
- shmem_free_block(inode);
- }
- if (info->next_index <= SHMEM_NR_DIRECT) {
- shmem_dir_free(info->i_indirect);
- info->i_indirect = NULL;
- shmem_free_block(inode);
- }
+ shmem_dir_unmap(dir);
done2:
- BUG_ON(info->swapped > info->next_index);
if (inode->i_mapping->nrpages && (info->flags & SHMEM_PAGEIN)) {
/*
* Call truncate_inode_pages again: racing shmem_unuse_inode
* Also, though shmem_getpage checks i_size before adding to
* cache, no recheck after: so fix the narrow window there too.
*/
- spin_unlock(&info->lock);
truncate_inode_pages(inode->i_mapping, inode->i_size);
- spin_lock(&info->lock);
}
+
+ spin_lock(&info->lock);
info->flags &= ~SHMEM_TRUNCATE;
+ info->swapped -= nr_swaps_freed;
+ if (nr_pages_to_free)
+ shmem_free_blocks(inode, nr_pages_to_free);
shmem_recalc_inode(inode);
spin_unlock(&info->lock);
+
+ /*
+ * Empty swap vector directory pages to be freed?
+ */
+ if (!list_empty(&pages_to_free)) {
+ pages_to_free.prev->next = NULL;
+ shmem_free_pages(pages_to_free.next);
+ }
}
static int shmem_notify_change(struct dentry *dentry, struct iattr *attr)
}
if (!info->i_indirect)
goto lost2;
- /* we might be racing with shmem_truncate */
- if (limit <= SHMEM_NR_DIRECT)
- goto lost2;
dir = shmem_dir_map(info->i_indirect);
stage = SHMEM_NR_DIRECT + ENTRIES_PER_PAGEPAGE/2;
pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, idx);
pvma.vm_pgoff = idx;
pvma.vm_end = PAGE_SIZE;
- page = alloc_page_vma(gfp, &pvma, 0);
+ page = alloc_page_vma(gfp | __GFP_ZERO, &pvma, 0);
mpol_free(pvma.vm_policy);
return page;
}
shmem_alloc_page(unsigned long gfp,struct shmem_inode_info *info,
unsigned long idx)
{
- return alloc_page(gfp);
+ return alloc_page(gfp | __GFP_ZERO);
}
#endif
idx);
if (!filepage) {
shmem_unacct_blocks(info->flags, 1);
- shmem_free_block(inode);
+ shmem_free_blocks(inode, 1);
error = -ENOMEM;
goto failed;
}
spin_unlock(&info->lock);
page_cache_release(filepage);
shmem_unacct_blocks(info->flags, 1);
- shmem_free_block(inode);
+ shmem_free_blocks(inode, 1);
filepage = NULL;
if (error)
goto failed;
info->alloced++;
spin_unlock(&info->lock);
- clear_highpage(filepage);
flush_dcache_page(filepage);
SetPageUptodate(filepage);
}
idx = (address - vma->vm_start) >> PAGE_SHIFT;
idx += vma->vm_pgoff;
idx >>= PAGE_CACHE_SHIFT - PAGE_SHIFT;
+ if (((loff_t) idx << PAGE_CACHE_SHIFT) >= i_size_read(inode))
+ return NOPAGE_SIGBUS;
error = shmem_getpage(inode, idx, &page, SGP_CACHE, type);
if (error)
info = SHMEM_I(inode);
memset(info, 0, (char *)inode - (char *)info);
spin_lock_init(&info->lock);
- mpol_shared_policy_init(&info->policy);
INIT_LIST_HEAD(&info->swaplist);
switch (mode & S_IFMT) {
default:
+ inode->i_op = &shmem_special_inode_operations;
init_special_inode(inode, mode, dev);
break;
case S_IFREG:
inode->i_op = &shmem_inode_operations;
inode->i_fop = &shmem_file_operations;
+ mpol_shared_policy_init(&info->policy);
break;
case S_IFDIR:
inode->i_nlink++;
inode->i_fop = &simple_dir_operations;
break;
case S_IFLNK:
+ /*
+ * Must not load anything in the rbtree,
+ * mpol_free_shared_policy will not be called.
+ */
+ mpol_shared_policy_init(&info->policy);
break;
}
+ } else if (sbinfo) {
+ spin_lock(&sbinfo->stat_lock);
+ sbinfo->free_inodes++;
+ spin_unlock(&sbinfo->stat_lock);
}
return inode;
}
static struct inode_operations shmem_symlink_inline_operations = {
.readlink = generic_readlink,
.follow_link = shmem_follow_link_inline,
+#ifdef CONFIG_TMPFS_XATTR
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
+ .listxattr = generic_listxattr,
+ .removexattr = generic_removexattr,
+#endif
};
static struct inode_operations shmem_symlink_inode_operations = {
.readlink = generic_readlink,
.follow_link = shmem_follow_link,
.put_link = shmem_put_link,
+#ifdef CONFIG_TMPFS_XATTR
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
+ .listxattr = generic_listxattr,
+ .removexattr = generic_removexattr,
+#endif
};
static int shmem_parse_options(char *options, int *mode, uid_t *uid, gid_t *gid, unsigned long *blocks, unsigned long *inodes)
sb->s_fs_info = NULL;
}
+#ifdef CONFIG_TMPFS_XATTR
+static struct xattr_handler *shmem_xattr_handlers[];
+#else
+#define shmem_xattr_handlers NULL
+#endif
+
static int shmem_fill_super(struct super_block *sb,
void *data, int silent)
{
sbinfo->max_inodes = inodes;
sbinfo->free_inodes = inodes;
}
+ sb->s_xattr = shmem_xattr_handlers;
+#else
+ sb->s_flags |= MS_NOUSER;
#endif
sb->s_maxbytes = SHMEM_MAX_BYTES;
static void shmem_destroy_inode(struct inode *inode)
{
- mpol_free_shared_policy(&SHMEM_I(inode)->policy);
+ if ((inode->i_mode & S_IFMT) == S_IFREG) {
+ /* only struct inode is valid if it's an inline symlink */
+ mpol_free_shared_policy(&SHMEM_I(inode)->policy);
+ }
kmem_cache_free(shmem_inode_cachep, SHMEM_I(inode));
}
static struct inode_operations shmem_inode_operations = {
.truncate = shmem_truncate,
.setattr = shmem_notify_change,
+#ifdef CONFIG_TMPFS_XATTR
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
+ .listxattr = generic_listxattr,
+ .removexattr = generic_removexattr,
+#endif
};
static struct inode_operations shmem_dir_inode_operations = {
.rmdir = shmem_rmdir,
.mknod = shmem_mknod,
.rename = shmem_rename,
+#ifdef CONFIG_TMPFS_XATTR
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
+ .listxattr = generic_listxattr,
+ .removexattr = generic_removexattr,
+#endif
+#endif
+};
+
+static struct inode_operations shmem_special_inode_operations = {
+#ifdef CONFIG_TMPFS_XATTR
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
+ .listxattr = generic_listxattr,
+ .removexattr = generic_removexattr,
#endif
};
#endif
};
+
+#ifdef CONFIG_TMPFS_SECURITY
+
+static size_t shmem_xattr_security_list(struct inode *inode, char *list, size_t list_len,
+ const char *name, size_t name_len)
+{
+ return security_inode_listsecurity(inode, list, list_len);
+}
+
+static int shmem_xattr_security_get(struct inode *inode, const char *name, void *buffer, size_t size)
+{
+ if (strcmp(name, "") == 0)
+ return -EINVAL;
+ return security_inode_getsecurity(inode, name, buffer, size);
+}
+
+static int shmem_xattr_security_set(struct inode *inode, const char *name, const void *value, size_t size, int flags)
+{
+ if (strcmp(name, "") == 0)
+ return -EINVAL;
+ return security_inode_setsecurity(inode, name, value, size, flags);
+}
+
+struct xattr_handler shmem_xattr_security_handler = {
+ .prefix = XATTR_SECURITY_PREFIX,
+ .list = shmem_xattr_security_list,
+ .get = shmem_xattr_security_get,
+ .set = shmem_xattr_security_set,
+};
+
+#endif /* CONFIG_TMPFS_SECURITY */
+
+#ifdef CONFIG_TMPFS_XATTR
+
+static struct xattr_handler *shmem_xattr_handlers[] = {
+#ifdef CONFIG_TMPFS_SECURITY
+ &shmem_xattr_security_handler,
+#endif
+ NULL
+};
+
+#endif /* CONFIG_TMPFS_XATTR */
+
static struct super_block *shmem_get_sb(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data)
{
vma->vm_ops = &shmem_vm_ops;
return 0;
}
-
-EXPORT_SYMBOL(shmem_file_setup);