* 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/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/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/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
-
#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)
*/
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 struct backing_dev_info shmem_backing_dev_info __read_mostly = {
.ra_pages = 0, /* No readahead */
- .capabilities = BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_WRITEBACK,
+ .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_SWAP_BACKED,
.unplug_io_fn = default_unplug_io_fn,
};
error = 1;
if (!inode)
goto out;
- /* Precharge page while we can wait, compensate afterwards */
+ /*
+ * 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;
error = radix_tree_preload(GFP_KERNEL);
- if (error)
- goto uncharge;
+ if (error) {
+ mem_cgroup_uncharge_cache_page(page);
+ goto out;
+ }
error = 1;
spin_lock(&info->lock);
ptr = shmem_swp_entry(info, idx, NULL);
- if (ptr && ptr->val == entry.val)
- error = add_to_page_cache(page, inode->i_mapping,
+ if (ptr && ptr->val == entry.val) {
+ error = add_to_page_cache_locked(page, inode->i_mapping,
idx, GFP_NOWAIT);
+ /* does mem_cgroup_uncharge_cache_page on error */
+ } else /* we must compensate for our precharge above */
+ mem_cgroup_uncharge_cache_page(page);
+
if (error == -EEXIST) {
struct page *filepage = find_get_page(inode->i_mapping, idx);
error = 1;
shmem_swp_unmap(ptr);
spin_unlock(&info->lock);
radix_tree_preload_end();
-uncharge:
- mem_cgroup_uncharge_page(page);
out:
unlock_page(page);
page_cache_release(page);
}
/* 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);
SetPageUptodate(filepage);
set_page_dirty(filepage);
swap_free(swap);
- } else if (!(error = add_to_page_cache(
- swappage, mapping, idx, GFP_NOWAIT))) {
+ } else if (!(error = add_to_page_cache_locked(swappage, mapping,
+ idx, GFP_NOWAIT))) {
info->flags |= SHMEM_PAGEIN;
shmem_swp_set(info, entry, 0);
shmem_swp_unmap(entry);
} else {
shmem_swp_unmap(entry);
spin_unlock(&info->lock);
- unlock_page(swappage);
if (error == -ENOMEM) {
/* allow reclaim from this memory cgroup */
- error = mem_cgroup_cache_charge(swappage,
- current->mm, gfp & ~__GFP_HIGHMEM);
+ error = mem_cgroup_shrink_usage(swappage,
+ current->mm,
+ gfp);
if (error) {
+ unlock_page(swappage);
page_cache_release(swappage);
goto failed;
}
- mem_cgroup_uncharge_page(swappage);
}
+ unlock_page(swappage);
page_cache_release(swappage);
goto repeat;
}
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);
}
if (!filepage) {
+ int ret;
+
spin_unlock(&info->lock);
filepage = shmem_alloc_page(gfp, info, idx);
if (!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);
swap = *entry;
shmem_swp_unmap(entry);
}
- if (error || swap.val || 0 != add_to_page_cache_lru(
- filepage, mapping, idx, GFP_NOWAIT)) {
+ ret = error || swap.val;
+ if (ret)
+ mem_cgroup_uncharge_cache_page(filepage);
+ else
+ ret = add_to_page_cache_lru(filepage, mapping,
+ idx, GFP_NOWAIT);
+ /*
+ * At add_to_page_cache_lru() failure, uncharge will
+ * be done automatically.
+ */
+ if (ret) {
spin_unlock(&info->lock);
- mem_cgroup_uncharge_page(filepage);
page_cache_release(filepage);
shmem_unacct_blocks(info->flags, 1);
shmem_free_blocks(inode, 1);
goto failed;
goto repeat;
}
- mem_cgroup_uncharge_page(filepage);
info->flags |= SHMEM_PAGEIN;
}
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->a_ops = &shmem_aops;
inode->i_mapping->backing_dev_info = &shmem_backing_dev_info;
inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
inode->i_generation = get_seconds();
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);
switch (mode & S_IFMT) {
init_special_inode(inode, mode, dev);
break;
case S_IFREG:
+ inode->i_mapping->a_ops = &shmem_aops;
inode->i_op = &shmem_inode_operations;
inode->i_fop = &shmem_file_operations;
mpol_shared_policy_init(&info->policy,
file_accessed(filp);
}
-static ssize_t shmem_file_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos)
+static ssize_t shmem_file_aio_read(struct kiocb *iocb,
+ const struct iovec *iov, unsigned long nr_segs, loff_t pos)
{
- read_descriptor_t desc;
+ struct file *filp = iocb->ki_filp;
+ ssize_t retval;
+ unsigned long seg;
+ size_t count;
+ loff_t *ppos = &iocb->ki_pos;
- if ((ssize_t) count < 0)
- return -EINVAL;
- if (!access_ok(VERIFY_WRITE, buf, count))
- return -EFAULT;
- if (!count)
- return 0;
+ retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE);
+ if (retval)
+ return retval;
- desc.written = 0;
- desc.count = count;
- desc.arg.buf = buf;
- desc.error = 0;
+ for (seg = 0; seg < nr_segs; seg++) {
+ read_descriptor_t desc;
- do_shmem_file_read(filp, ppos, &desc, file_read_actor);
- if (desc.written)
- return desc.written;
- return desc.error;
+ desc.written = 0;
+ desc.arg.buf = iov[seg].iov_base;
+ desc.count = iov[seg].iov_len;
+ if (desc.count == 0)
+ continue;
+ desc.error = 0;
+ do_shmem_file_read(filp, ppos, &desc, file_read_actor);
+ retval += desc.written;
+ if (desc.error) {
+ retval = retval ?: desc.error;
+ break;
+ }
+ if (desc.count > 0)
+ break;
+ }
+ return retval;
}
static int shmem_statfs(struct dentry *dentry, struct kstatfs *buf)
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);
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;
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);
sbinfo->max_blocks = 0;
sbinfo->max_inodes = 0;
sbinfo->mode = S_IRWXUGO | S_ISVTX;
- sbinfo->uid = current->fsuid;
- sbinfo->gid = current->fsgid;
+ sbinfo->uid = current_fsuid();
+ sbinfo->gid = current_fsgid();
sbinfo->mpol = NULL;
sb->s_fs_info = sbinfo;
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;
kmem_cache_free(shmem_inode_cachep, SHMEM_I(inode));
}
-static void init_once(struct kmem_cache *cachep, void *foo)
+static void init_once(void *foo)
{
struct shmem_inode_info *p = (struct shmem_inode_info *) foo;
.mmap = shmem_mmap,
#ifdef CONFIG_TMPFS
.llseek = generic_file_llseek,
- .read = shmem_file_read,
+ .read = do_sync_read,
.write = do_sync_write,
+ .aio_read = shmem_file_aio_read,
.aio_write = generic_file_aio_write,
.fsync = simple_sync_file,
.splice_read = generic_file_splice_read,
.get_sb = shmem_get_sb,
.kill_sb = kill_litter_super,
};
-static struct vfsmount *shm_mnt;
static int __init init_tmpfs(void)
{
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,
+};
+
+static 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;
+}
+
+#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 LLONG_MAX
+
+#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)
{
goto put_dentry;
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;
- SHMEM_I(inode)->flags = flags & VM_ACCOUNT;
d_instantiate(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);
+ &shmem_file_operations);
+
+#ifndef CONFIG_MMU
+ error = ramfs_nommu_expand_for_mapping(inode, size);
+ if (error)
+ goto close_file;
+#endif
return file;
close_file:
shmem_unacct_size(flags, size);
return ERR_PTR(error);
}
+EXPORT_SYMBOL_GPL(shmem_file_setup);
/**
* shmem_zero_setup - setup a shared anonymous mapping
vma->vm_ops = &shmem_vm_ops;
return 0;
}
+
+module_init(init_tmpfs)
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff