* Copyright (c) 2004, Luke Kenneth Casson Leighton <lkcl@lkcl.net>
* Copyright (c) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com>
*
+ * tiny-shmem:
+ * Copyright (c) 2004, 2008 Matt Mackall <mpm@selenic.com>
+ *
* This file is released under the GPL.
*/
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/vfs.h>
+#include <linux/mount.h>
+#include <linux/pagemap.h>
+#include <linux/file.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/swap.h>
+
+static struct vfsmount *shm_mnt;
+
+#ifdef CONFIG_SHMEM
/*
* This virtual memory filesystem is heavily based on the ramfs. It
* extends ramfs by the ability to use swap and honor resource limits
* which makes it a completely usable filesystem.
*/
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/fs.h>
#include <linux/xattr.h>
#include <linux/exportfs.h>
+#include <linux/posix_acl.h>
#include <linux/generic_acl.h>
-#include <linux/mm.h>
#include <linux/mman.h>
-#include <linux/file.h>
-#include <linux/swap.h>
-#include <linux/pagemap.h>
#include <linux/string.h>
#include <linux/slab.h>
#include <linux/backing-dev.h>
#include <linux/shmem_fs.h>
-#include <linux/mount.h>
#include <linux/writeback.h>
-#include <linux/vfs.h>
#include <linux/blkdev.h>
#include <linux/security.h>
#include <linux/swapops.h>
#include <linux/migrate.h>
#include <linux/highmem.h>
#include <linux/seq_file.h>
+#include <linux/magic.h>
#include <asm/uaccess.h>
#include <asm/div64.h>
#include <asm/pgtable.h>
-/* This magic number is used in glibc for posix shared memory */
-#define TMPFS_MAGIC 0x01021994
-
+/*
+ * The maximum size of a shmem/tmpfs file is limited by the maximum size of
+ * its triple-indirect swap vector - see illustration at shmem_swp_entry().
+ *
+ * With 4kB page size, maximum file size is just over 2TB on a 32-bit kernel,
+ * but one eighth of that on a 64-bit kernel. With 8kB page size, maximum
+ * file size is just over 4TB on a 64-bit kernel, but 16TB on a 32-bit kernel,
+ * MAX_LFS_FILESIZE being then more restrictive than swap vector layout.
+ *
+ * We use / and * instead of shifts in the definitions below, so that the swap
+ * vector can be tested with small even values (e.g. 20) for ENTRIES_PER_PAGE.
+ */
#define ENTRIES_PER_PAGE (PAGE_CACHE_SIZE/sizeof(unsigned long))
-#define ENTRIES_PER_PAGEPAGE (ENTRIES_PER_PAGE*ENTRIES_PER_PAGE)
-#define BLOCKS_PER_PAGE (PAGE_CACHE_SIZE/512)
+#define ENTRIES_PER_PAGEPAGE ((unsigned long long)ENTRIES_PER_PAGE*ENTRIES_PER_PAGE)
+
+#define SHMSWP_MAX_INDEX (SHMEM_NR_DIRECT + (ENTRIES_PER_PAGEPAGE/2) * (ENTRIES_PER_PAGE+1))
+#define SHMSWP_MAX_BYTES (SHMSWP_MAX_INDEX << PAGE_CACHE_SHIFT)
-#define SHMEM_MAX_INDEX (SHMEM_NR_DIRECT + (ENTRIES_PER_PAGEPAGE/2) * (ENTRIES_PER_PAGE+1))
-#define SHMEM_MAX_BYTES ((unsigned long long)SHMEM_MAX_INDEX << PAGE_CACHE_SHIFT)
+#define SHMEM_MAX_BYTES min_t(unsigned long long, SHMSWP_MAX_BYTES, MAX_LFS_FILESIZE)
+#define SHMEM_MAX_INDEX ((unsigned long)((SHMEM_MAX_BYTES+1) >> PAGE_CACHE_SHIFT))
+#define BLOCKS_PER_PAGE (PAGE_CACHE_SIZE/512)
#define VM_ACCT(size) (PAGE_CACHE_ALIGN(size) >> PAGE_SHIFT)
/* info->flags needs VM_flags to handle pagein/truncate races efficiently */
*/
static inline int shmem_acct_size(unsigned long flags, loff_t size)
{
- return (flags & VM_ACCOUNT)?
- security_vm_enough_memory(VM_ACCT(size)): 0;
+ return (flags & VM_NORESERVE) ?
+ 0 : security_vm_enough_memory_kern(VM_ACCT(size));
}
static inline void shmem_unacct_size(unsigned long flags, loff_t size)
{
- if (flags & VM_ACCOUNT)
+ if (!(flags & VM_NORESERVE))
vm_unacct_memory(VM_ACCT(size));
}
*/
static inline int shmem_acct_block(unsigned long flags)
{
- return (flags & VM_ACCOUNT)?
- 0: security_vm_enough_memory(VM_ACCT(PAGE_CACHE_SIZE));
+ return (flags & VM_NORESERVE) ?
+ security_vm_enough_memory_kern(VM_ACCT(PAGE_CACHE_SIZE)) : 0;
}
static inline void shmem_unacct_blocks(unsigned long flags, long pages)
{
- if (!(flags & VM_ACCOUNT))
+ if (flags & VM_NORESERVE)
vm_unacct_memory(pages * VM_ACCT(PAGE_CACHE_SIZE));
}
static const struct inode_operations shmem_inode_operations;
static const struct inode_operations shmem_dir_inode_operations;
static const struct inode_operations shmem_special_inode_operations;
-static struct vm_operations_struct shmem_vm_ops;
+static const struct vm_operations_struct shmem_vm_ops;
static struct backing_dev_info shmem_backing_dev_info __read_mostly = {
.ra_pages = 0, /* No readahead */
- .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK,
+ .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_SWAP_BACKED,
.unplug_io_fn = default_unplug_io_fn,
};
error = inode_setattr(inode, attr);
#ifdef CONFIG_TMPFS_POSIX_ACL
if (!error && (attr->ia_valid & ATTR_MODE))
- error = generic_acl_chmod(inode, &shmem_acl_ops);
+ error = generic_acl_chmod(inode);
#endif
if (page)
page_cache_release(page);
error = 1;
if (!inode)
goto out;
- /* Precharge page using GFP_KERNEL while we can wait */
+ /*
+ * Charge page using GFP_KERNEL while we can wait.
+ * Charged back to the user(not to caller) when swap account is used.
+ * add_to_page_cache() will be called with GFP_NOWAIT.
+ */
error = mem_cgroup_cache_charge(page, current->mm, GFP_KERNEL);
if (error)
goto out;
goto out;
}
mutex_unlock(&shmem_swaplist_mutex);
-out: return found; /* 0 or 1 or -ENOMEM */
+ /*
+ * Can some race bring us here? We've been holding page lock,
+ * so I think not; but would rather try again later than BUG()
+ */
+ unlock_page(page);
+ page_cache_release(page);
+out:
+ return (found < 0) ? found : 0;
}
/*
* sync from ever calling shmem_writepage; but a stacking filesystem
* may use the ->writepage of its underlying filesystem, in which case
* tmpfs should write out to swap only in response to memory pressure,
- * and not for pdflush or sync. However, in those cases, we do still
- * want to check if there's a redundant swappage to be discarded.
+ * and not for the writeback threads or sync. However, in those cases,
+ * we do still want to check if there's a redundant swappage to be
+ * discarded.
*/
if (wbc->for_reclaim)
swap = get_swap_page();
else
inode = NULL;
spin_unlock(&info->lock);
- swap_duplicate(swap);
+ swap_shmem_alloc(swap);
BUG_ON(page_mapped(page));
page_cache_release(page); /* pagecache ref */
- set_page_dirty(page);
- unlock_page(page);
+ swap_writepage(page, wbc);
if (inode) {
mutex_lock(&shmem_swaplist_mutex);
/* move instead of add in case we're racing */
shmem_swp_unmap(entry);
unlock:
spin_unlock(&info->lock);
- swap_free(swap);
+ /*
+ * add_to_swap_cache() doesn't return -EEXIST, so we can safely
+ * clear SWAP_HAS_CACHE flag.
+ */
+ swapcache_free(swap, NULL);
redirty:
set_page_dirty(page);
if (wbc->for_reclaim)
}
/* We have to do this with page locked to prevent races */
- if (TestSetPageLocked(swappage)) {
+ if (!trylock_page(swappage)) {
shmem_swp_unmap(entry);
spin_unlock(&info->lock);
wait_on_page_locked(swappage);
} else {
shmem_swp_unmap(entry);
spin_unlock(&info->lock);
- unlock_page(swappage);
- page_cache_release(swappage);
if (error == -ENOMEM) {
- /* allow reclaim from this memory cgroup */
- error = mem_cgroup_shrink_usage(current->mm,
+ /*
+ * reclaim from proper memory cgroup and
+ * call memcg's OOM if needed.
+ */
+ error = mem_cgroup_shmem_charge_fallback(
+ swappage,
+ current->mm,
gfp);
- if (error)
+ if (error) {
+ unlock_page(swappage);
+ page_cache_release(swappage);
goto failed;
+ }
}
+ unlock_page(swappage);
+ page_cache_release(swappage);
goto repeat;
}
} else if (sgp == SGP_READ && !filepage) {
shmem_swp_unmap(entry);
filepage = find_get_page(mapping, idx);
if (filepage &&
- (!PageUptodate(filepage) || TestSetPageLocked(filepage))) {
+ (!PageUptodate(filepage) || !trylock_page(filepage))) {
spin_unlock(&info->lock);
wait_on_page_locked(filepage);
page_cache_release(filepage);
error = -ENOMEM;
goto failed;
}
+ SetPageSwapBacked(filepage);
/* Precharge page while we can wait, compensate after */
error = mem_cgroup_cache_charge(filepage, current->mm,
- gfp & ~__GFP_HIGHMEM);
+ GFP_KERNEL);
if (error) {
page_cache_release(filepage);
shmem_unacct_blocks(info->flags, 1);
if (error)
return ((error == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS);
- mark_page_accessed(vmf->page);
return ret | VM_FAULT_LOCKED;
}
if (!user_shm_lock(inode->i_size, user))
goto out_nomem;
info->flags |= VM_LOCKED;
+ mapping_set_unevictable(file->f_mapping);
}
if (!lock && (info->flags & VM_LOCKED) && user) {
user_shm_unlock(inode->i_size, user);
info->flags &= ~VM_LOCKED;
+ mapping_clear_unevictable(file->f_mapping);
+ scan_mapping_unevictable_pages(file->f_mapping);
}
retval = 0;
+
out_nomem:
spin_unlock(&info->lock);
return retval;
return 0;
}
-static struct inode *
-shmem_get_inode(struct super_block *sb, int mode, dev_t dev)
+static struct inode *shmem_get_inode(struct super_block *sb, int mode,
+ dev_t dev, unsigned long flags)
{
struct inode *inode;
struct shmem_inode_info *info;
inode = new_inode(sb);
if (inode) {
inode->i_mode = mode;
- inode->i_uid = current->fsuid;
- inode->i_gid = current->fsgid;
+ inode->i_uid = current_fsuid();
+ inode->i_gid = current_fsgid();
inode->i_blocks = 0;
inode->i_mapping->backing_dev_info = &shmem_backing_dev_info;
inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
info = SHMEM_I(inode);
memset(info, 0, (char *)inode - (char *)info);
spin_lock_init(&info->lock);
+ info->flags = flags & VM_NORESERVE;
INIT_LIST_HEAD(&info->swaplist);
+ cache_no_acl(inode);
switch (mode & S_IFMT) {
default:
if (pos + copied > inode->i_size)
i_size_write(inode, pos + copied);
- unlock_page(page);
set_page_dirty(page);
+ unlock_page(page);
page_cache_release(page);
return copied;
static int
shmem_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev)
{
- struct inode *inode = shmem_get_inode(dir->i_sb, mode, dev);
+ struct inode *inode;
int error = -ENOSPC;
+ inode = shmem_get_inode(dir->i_sb, mode, dev, VM_NORESERVE);
if (inode) {
error = security_inode_init_security(inode, dir, NULL, NULL,
NULL);
return error;
}
}
- error = shmem_acl_init(inode, dir);
+#ifdef CONFIG_TMPFS_POSIX_ACL
+ error = generic_acl_init(inode, dir);
if (error) {
iput(inode);
return error;
}
+#else
+ error = 0;
+#endif
if (dir->i_mode & S_ISGID) {
inode->i_gid = dir->i_gid;
if (S_ISDIR(mode))
if (len > PAGE_CACHE_SIZE)
return -ENAMETOOLONG;
- inode = shmem_get_inode(dir->i_sb, S_IFLNK|S_IRWXUGO, 0);
+ inode = shmem_get_inode(dir->i_sb, S_IFLNK|S_IRWXUGO, 0, VM_NORESERVE);
if (!inode)
return -ENOSPC;
iput(inode);
return error;
}
- unlock_page(page);
inode->i_mapping->a_ops = &shmem_aops;
inode->i_op = &shmem_symlink_inode_operations;
kaddr = kmap_atomic(page, KM_USER0);
memcpy(kaddr, symname, len);
kunmap_atomic(kaddr, KM_USER0);
set_page_dirty(page);
+ unlock_page(page);
page_cache_release(page);
}
if (dir->i_mode & S_ISGID)
* filesystem level, though.
*/
-static size_t shmem_xattr_security_list(struct inode *inode, char *list,
+static size_t shmem_xattr_security_list(struct dentry *dentry, char *list,
size_t list_len, const char *name,
- size_t name_len)
+ size_t name_len, int handler_flags)
{
- return security_inode_listsecurity(inode, list, list_len);
+ return security_inode_listsecurity(dentry->d_inode, list, list_len);
}
-static int shmem_xattr_security_get(struct inode *inode, const char *name,
- void *buffer, size_t size)
+static int shmem_xattr_security_get(struct dentry *dentry, const char *name,
+ void *buffer, size_t size, int handler_flags)
{
if (strcmp(name, "") == 0)
return -EINVAL;
- return xattr_getsecurity(inode, name, buffer, size);
+ return xattr_getsecurity(dentry->d_inode, name, buffer, size);
}
-static int shmem_xattr_security_set(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
+static int shmem_xattr_security_set(struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags, int handler_flags)
{
if (strcmp(name, "") == 0)
return -EINVAL;
- return security_inode_setsecurity(inode, name, value, size, flags);
+ return security_inode_setsecurity(dentry->d_inode, name, value,
+ size, flags);
}
static struct xattr_handler shmem_xattr_security_handler = {
};
static struct xattr_handler *shmem_xattr_handlers[] = {
- &shmem_xattr_acl_access_handler,
- &shmem_xattr_acl_default_handler,
+ &generic_acl_access_handler,
+ &generic_acl_default_handler,
&shmem_xattr_security_handler,
NULL
};
sb->s_fs_info = NULL;
}
-static int shmem_fill_super(struct super_block *sb,
- void *data, int silent)
+int shmem_fill_super(struct super_block *sb, void *data, int silent)
{
struct inode *inode;
struct dentry *root;
int err = -ENOMEM;
/* Round up to L1_CACHE_BYTES to resist false sharing */
- sbinfo = kmalloc(max((int)sizeof(struct shmem_sb_info),
+ sbinfo = kzalloc(max((int)sizeof(struct shmem_sb_info),
L1_CACHE_BYTES), GFP_KERNEL);
if (!sbinfo)
return -ENOMEM;
- sbinfo->max_blocks = 0;
- sbinfo->max_inodes = 0;
sbinfo->mode = S_IRWXUGO | S_ISVTX;
- sbinfo->uid = current->fsuid;
- sbinfo->gid = current->fsgid;
- sbinfo->mpol = NULL;
+ sbinfo->uid = current_fsuid();
+ sbinfo->gid = current_fsgid();
sb->s_fs_info = sbinfo;
#ifdef CONFIG_TMPFS
sb->s_flags |= MS_POSIXACL;
#endif
- inode = shmem_get_inode(sb, S_IFDIR | sbinfo->mode, 0);
+ inode = shmem_get_inode(sb, S_IFDIR | sbinfo->mode, 0, VM_NORESERVE);
if (!inode)
goto failed;
inode->i_uid = sbinfo->uid;
/* only struct inode is valid if it's an inline symlink */
mpol_free_shared_policy(&SHMEM_I(inode)->policy);
}
- shmem_acl_destroy_inode(inode);
kmem_cache_free(shmem_inode_cachep, SHMEM_I(inode));
}
struct shmem_inode_info *p = (struct shmem_inode_info *) foo;
inode_init_once(&p->vfs_inode);
-#ifdef CONFIG_TMPFS_POSIX_ACL
- p->i_acl = NULL;
- p->i_default_acl = NULL;
-#endif
}
static int init_inodecache(void)
.write_end = shmem_write_end,
#endif
.migratepage = migrate_page,
+ .error_remove_page = generic_error_remove_page,
};
static const struct file_operations shmem_file_operations = {
.getxattr = generic_getxattr,
.listxattr = generic_listxattr,
.removexattr = generic_removexattr,
- .permission = shmem_permission,
+ .check_acl = generic_check_acl,
#endif
};
.getxattr = generic_getxattr,
.listxattr = generic_listxattr,
.removexattr = generic_removexattr,
- .permission = shmem_permission,
+ .check_acl = generic_check_acl,
#endif
};
.getxattr = generic_getxattr,
.listxattr = generic_listxattr,
.removexattr = generic_removexattr,
- .permission = shmem_permission,
+ .check_acl = generic_check_acl,
#endif
};
.put_super = shmem_put_super,
};
-static struct vm_operations_struct shmem_vm_ops = {
+static const struct vm_operations_struct shmem_vm_ops = {
.fault = shmem_fault,
#ifdef CONFIG_NUMA
.set_policy = shmem_set_policy,
.get_sb = shmem_get_sb,
.kill_sb = kill_litter_super,
};
-static struct vfsmount *shm_mnt;
-static int __init init_tmpfs(void)
+int __init init_tmpfs(void)
{
int error;
shm_mnt = ERR_PTR(error);
return error;
}
-module_init(init_tmpfs)
+
+#else /* !CONFIG_SHMEM */
+
+/*
+ * tiny-shmem: simple shmemfs and tmpfs using ramfs code
+ *
+ * This is intended for small system where the benefits of the full
+ * shmem code (swap-backed and resource-limited) are outweighed by
+ * their complexity. On systems without swap this code should be
+ * effectively equivalent, but much lighter weight.
+ */
+
+#include <linux/ramfs.h>
+
+static struct file_system_type tmpfs_fs_type = {
+ .name = "tmpfs",
+ .get_sb = ramfs_get_sb,
+ .kill_sb = kill_litter_super,
+};
+
+int __init init_tmpfs(void)
+{
+ BUG_ON(register_filesystem(&tmpfs_fs_type) != 0);
+
+ shm_mnt = kern_mount(&tmpfs_fs_type);
+ BUG_ON(IS_ERR(shm_mnt));
+
+ return 0;
+}
+
+int shmem_unuse(swp_entry_t entry, struct page *page)
+{
+ return 0;
+}
+
+int shmem_lock(struct file *file, int lock, struct user_struct *user)
+{
+ return 0;
+}
+
+#define shmem_vm_ops generic_file_vm_ops
+#define shmem_file_operations ramfs_file_operations
+#define shmem_get_inode(sb, mode, dev, flags) ramfs_get_inode(sb, mode, dev)
+#define shmem_acct_size(flags, size) 0
+#define shmem_unacct_size(flags, size) do {} while (0)
+#define SHMEM_MAX_BYTES MAX_LFS_FILESIZE
+
+#endif /* CONFIG_SHMEM */
+
+/* common code */
/**
* shmem_file_setup - get an unlinked file living in tmpfs
* @name: name for dentry (to be seen in /proc/<pid>/maps
* @size: size to be set for the file
- * @flags: vm_flags
+ * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size
*/
-struct file *shmem_file_setup(char *name, loff_t size, unsigned long flags)
+struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags)
{
int error;
struct file *file;
struct inode *inode;
- struct dentry *dentry, *root;
+ struct path path;
+ struct dentry *root;
struct qstr this;
if (IS_ERR(shm_mnt))
this.len = strlen(name);
this.hash = 0; /* will go */
root = shm_mnt->mnt_root;
- dentry = d_alloc(root, &this);
- if (!dentry)
+ path.dentry = d_alloc(root, &this);
+ if (!path.dentry)
goto put_memory;
-
- error = -ENFILE;
- file = get_empty_filp();
- if (!file)
- goto put_dentry;
+ path.mnt = mntget(shm_mnt);
error = -ENOSPC;
- inode = shmem_get_inode(root->d_sb, S_IFREG | S_IRWXUGO, 0);
+ inode = shmem_get_inode(root->d_sb, S_IFREG | S_IRWXUGO, 0, flags);
if (!inode)
- goto close_file;
+ goto put_dentry;
- SHMEM_I(inode)->flags = flags & VM_ACCOUNT;
- d_instantiate(dentry, inode);
+ d_instantiate(path.dentry, inode);
inode->i_size = size;
inode->i_nlink = 0; /* It is unlinked */
- init_file(file, shm_mnt, dentry, FMODE_WRITE | FMODE_READ,
- &shmem_file_operations);
+#ifndef CONFIG_MMU
+ error = ramfs_nommu_expand_for_mapping(inode, size);
+ if (error)
+ goto put_dentry;
+#endif
+
+ error = -ENFILE;
+ file = alloc_file(&path, FMODE_WRITE | FMODE_READ,
+ &shmem_file_operations);
+ if (!file)
+ goto put_dentry;
+
return file;
-close_file:
- put_filp(file);
put_dentry:
- dput(dentry);
+ path_put(&path);
put_memory:
shmem_unacct_size(flags, size);
return ERR_PTR(error);
}
+EXPORT_SYMBOL_GPL(shmem_file_setup);
/**
* shmem_zero_setup - setup a shared anonymous mapping
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff