#include <linux/fs.h>
#include <linux/mount.h>
#include <linux/file.h>
+#include <linux/kernel.h>
#include <linux/writeback.h>
#include <linux/pagemap.h>
#include <linux/highmem.h>
#include <linux/init.h>
#include <linux/string.h>
#include <linux/capability.h>
+#include <linux/ctype.h>
#include <linux/backing-dev.h>
#include <linux/hugetlb.h>
#include <linux/pagevec.h>
+#include <linux/parser.h>
+#include <linux/mman.h>
#include <linux/quotaops.h>
#include <linux/slab.h>
#include <linux/dnotify.h>
/* some random number */
#define HUGETLBFS_MAGIC 0x958458f6
-static struct super_operations hugetlbfs_ops;
-static struct address_space_operations hugetlbfs_aops;
+static const struct super_operations hugetlbfs_ops;
+static const struct address_space_operations hugetlbfs_aops;
const struct file_operations hugetlbfs_file_operations;
-static struct inode_operations hugetlbfs_dir_inode_operations;
-static struct inode_operations hugetlbfs_inode_operations;
+static const struct inode_operations hugetlbfs_dir_inode_operations;
+static const struct inode_operations hugetlbfs_inode_operations;
static struct backing_dev_info hugetlbfs_backing_dev_info = {
.ra_pages = 0, /* No readahead */
int sysctl_hugetlb_shm_group;
+enum {
+ Opt_size, Opt_nr_inodes,
+ Opt_mode, Opt_uid, Opt_gid,
+ Opt_err,
+};
+
+static match_table_t tokens = {
+ {Opt_size, "size=%s"},
+ {Opt_nr_inodes, "nr_inodes=%s"},
+ {Opt_mode, "mode=%o"},
+ {Opt_uid, "uid=%u"},
+ {Opt_gid, "gid=%u"},
+ {Opt_err, NULL},
+};
+
static void huge_pagevec_release(struct pagevec *pvec)
{
int i;
static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
{
- struct inode *inode = file->f_dentry->d_inode;
- struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode);
+ struct inode *inode = file->f_path.dentry->d_inode;
loff_t len, vma_len;
int ret;
- if (vma->vm_pgoff & (HPAGE_SIZE / PAGE_SIZE - 1))
- return -EINVAL;
-
- if (vma->vm_start & ~HPAGE_MASK)
- return -EINVAL;
-
- if (vma->vm_end & ~HPAGE_MASK)
- return -EINVAL;
+ /*
+ * vma address alignment (but not the pgoff alignment) has
+ * already been checked by prepare_hugepage_range. If you add
+ * any error returns here, do so after setting VM_HUGETLB, so
+ * is_vm_hugetlb_page tests below unmap_region go the right
+ * way when do_mmap_pgoff unwinds (may be important on powerpc
+ * and ia64).
+ */
+ vma->vm_flags |= VM_HUGETLB | VM_RESERVED;
+ vma->vm_ops = &hugetlb_vm_ops;
- if (vma->vm_end - vma->vm_start < HPAGE_SIZE)
+ if (vma->vm_pgoff & ~(HPAGE_MASK >> PAGE_SHIFT))
return -EINVAL;
vma_len = (loff_t)(vma->vm_end - vma->vm_start);
mutex_lock(&inode->i_mutex);
file_accessed(file);
- vma->vm_flags |= VM_HUGETLB | VM_RESERVED;
- vma->vm_ops = &hugetlb_vm_ops;
ret = -ENOMEM;
len = vma_len + ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
- if (!(vma->vm_flags & VM_WRITE) && len > inode->i_size)
- goto out;
- if (vma->vm_flags & VM_MAYSHARE)
- if (hugetlb_extend_reservation(info, len >> HPAGE_SHIFT) != 0)
- goto out;
+ if (vma->vm_flags & VM_MAYSHARE &&
+ hugetlb_reserve_pages(inode, vma->vm_pgoff >> (HPAGE_SHIFT-PAGE_SHIFT),
+ len >> HPAGE_SHIFT))
+ goto out;
ret = 0;
hugetlb_prefault_arch_hook(vma->vm_mm);
- if (inode->i_size < len)
+ if (vma->vm_flags & VM_WRITE && inode->i_size < len)
inode->i_size = len;
out:
mutex_unlock(&inode->i_mutex);
* Called under down_write(mmap_sem).
*/
-#ifdef HAVE_ARCH_HUGETLB_UNMAPPED_AREA
-unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
- unsigned long len, unsigned long pgoff, unsigned long flags);
-#else
+#ifndef HAVE_ARCH_HUGETLB_UNMAPPED_AREA
static unsigned long
hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
unsigned long len, unsigned long pgoff, unsigned long flags)
if (len > TASK_SIZE)
return -ENOMEM;
+ if (flags & MAP_FIXED) {
+ if (prepare_hugepage_range(addr, len))
+ return -EINVAL;
+ return addr;
+ }
+
if (addr) {
addr = ALIGN(addr, HPAGE_SIZE);
vma = find_vma(mm, addr);
static void truncate_huge_page(struct page *page)
{
- clear_page_dirty(page);
+ cancel_dirty_page(page, /* No IO accounting for huge pages? */0);
ClearPageUptodate(page);
remove_from_page_cache(page);
put_page(page);
const pgoff_t start = lstart >> HPAGE_SHIFT;
struct pagevec pvec;
pgoff_t next;
- int i;
+ int i, freed = 0;
- hugetlb_truncate_reservation(HUGETLBFS_I(inode),
- lstart >> HPAGE_SHIFT);
- if (!mapping->nrpages)
- return;
pagevec_init(&pvec, 0);
next = start;
while (1) {
truncate_huge_page(page);
unlock_page(page);
hugetlb_put_quota(mapping);
+ freed++;
}
huge_pagevec_release(&pvec);
}
BUG_ON(!lstart && mapping->nrpages);
+ hugetlb_unreserve_pages(inode, start, freed);
}
static void hugetlbfs_delete_inode(struct inode *inode)
clear_inode(inode);
}
-static void hugetlbfs_forget_inode(struct inode *inode)
+static void hugetlbfs_forget_inode(struct inode *inode) __releases(inode_lock)
{
struct super_block *sb = inode->i_sb;
hugetlbfs_forget_inode(inode);
}
-/*
- * h_pgoff is in HPAGE_SIZE units.
- * vma->vm_pgoff is in PAGE_SIZE units.
- */
static inline void
-hugetlb_vmtruncate_list(struct prio_tree_root *root, unsigned long h_pgoff)
+hugetlb_vmtruncate_list(struct prio_tree_root *root, pgoff_t pgoff)
{
struct vm_area_struct *vma;
struct prio_tree_iter iter;
- vma_prio_tree_foreach(vma, &iter, root, h_pgoff, ULONG_MAX) {
- unsigned long h_vm_pgoff;
+ vma_prio_tree_foreach(vma, &iter, root, pgoff, ULONG_MAX) {
unsigned long v_offset;
- h_vm_pgoff = vma->vm_pgoff >> (HPAGE_SHIFT - PAGE_SHIFT);
- v_offset = (h_pgoff - h_vm_pgoff) << HPAGE_SHIFT;
/*
- * Is this VMA fully outside the truncation point?
+ * Can the expression below overflow on 32-bit arches?
+ * No, because the prio_tree returns us only those vmas
+ * which overlap the truncated area starting at pgoff,
+ * and no vma on a 32-bit arch can span beyond the 4GB.
*/
- if (h_vm_pgoff >= h_pgoff)
+ if (vma->vm_pgoff < pgoff)
+ v_offset = (pgoff - vma->vm_pgoff) << PAGE_SHIFT;
+ else
v_offset = 0;
- unmap_hugepage_range(vma,
+ __unmap_hugepage_range(vma,
vma->vm_start + v_offset, vma->vm_end);
}
}
*/
static int hugetlb_vmtruncate(struct inode *inode, loff_t offset)
{
- unsigned long pgoff;
+ pgoff_t pgoff;
struct address_space *mapping = inode->i_mapping;
if (offset > inode->i_size)
return -EINVAL;
BUG_ON(offset & ~HPAGE_MASK);
- pgoff = offset >> HPAGE_SHIFT;
+ pgoff = offset >> PAGE_SHIFT;
inode->i_size = offset;
spin_lock(&mapping->i_mmap_lock);
inode->i_mode = mode;
inode->i_uid = uid;
inode->i_gid = gid;
- inode->i_blksize = HPAGE_SIZE;
inode->i_blocks = 0;
inode->i_mapping->a_ops = &hugetlbfs_aops;
inode->i_mapping->backing_dev_info =&hugetlbfs_backing_dev_info;
inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+ INIT_LIST_HEAD(&inode->i_mapping->private_list);
info = HUGETLBFS_I(inode);
mpol_shared_policy_init(&info->policy, MPOL_DEFAULT, NULL);
switch (mode & S_IFMT) {
inode->i_fop = &simple_dir_operations;
/* directory inodes start off with i_nlink == 2 (for "." entry) */
- inode->i_nlink++;
+ inc_nlink(inode);
break;
case S_IFLNK:
inode->i_op = &page_symlink_inode_operations;
{
int retval = hugetlbfs_mknod(dir, dentry, mode | S_IFDIR, 0);
if (!retval)
- dir->i_nlink++;
+ inc_nlink(dir);
return retval;
}
}
/*
- * For direct-IO reads into hugetlb pages
+ * mark the head page dirty
*/
static int hugetlbfs_set_page_dirty(struct page *page)
{
+ struct page *head = compound_head(page);
+
+ SetPageDirty(head);
return 0;
}
}
-static kmem_cache_t *hugetlbfs_inode_cachep;
+static struct kmem_cache *hugetlbfs_inode_cachep;
static struct inode *hugetlbfs_alloc_inode(struct super_block *sb)
{
if (unlikely(!hugetlbfs_dec_free_inodes(sbinfo)))
return NULL;
- p = kmem_cache_alloc(hugetlbfs_inode_cachep, SLAB_KERNEL);
+ p = kmem_cache_alloc(hugetlbfs_inode_cachep, GFP_KERNEL);
if (unlikely(!p)) {
hugetlbfs_inc_free_inodes(sbinfo);
return NULL;
}
- p->prereserved_hpages = 0;
return &p->vfs_inode;
}
kmem_cache_free(hugetlbfs_inode_cachep, HUGETLBFS_I(inode));
}
-static struct address_space_operations hugetlbfs_aops = {
+static const struct address_space_operations hugetlbfs_aops = {
.readpage = hugetlbfs_readpage,
.prepare_write = hugetlbfs_prepare_write,
.commit_write = hugetlbfs_commit_write,
};
-static void init_once(void *foo, kmem_cache_t *cachep, unsigned long flags)
+static void init_once(void *foo, struct kmem_cache *cachep, unsigned long flags)
{
struct hugetlbfs_inode_info *ei = (struct hugetlbfs_inode_info *)foo;
- if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) ==
- SLAB_CTOR_CONSTRUCTOR)
- inode_init_once(&ei->vfs_inode);
+ inode_init_once(&ei->vfs_inode);
}
const struct file_operations hugetlbfs_file_operations = {
.get_unmapped_area = hugetlb_get_unmapped_area,
};
-static struct inode_operations hugetlbfs_dir_inode_operations = {
+static const struct inode_operations hugetlbfs_dir_inode_operations = {
.create = hugetlbfs_create,
.lookup = simple_lookup,
.link = simple_link,
.setattr = hugetlbfs_setattr,
};
-static struct inode_operations hugetlbfs_inode_operations = {
+static const struct inode_operations hugetlbfs_inode_operations = {
.setattr = hugetlbfs_setattr,
};
-static struct super_operations hugetlbfs_ops = {
+static const struct super_operations hugetlbfs_ops = {
.alloc_inode = hugetlbfs_alloc_inode,
.destroy_inode = hugetlbfs_destroy_inode,
.statfs = hugetlbfs_statfs,
static int
hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig)
{
- char *opt, *value, *rest;
+ char *p, *rest;
+ substring_t args[MAX_OPT_ARGS];
+ int option;
if (!options)
return 0;
- while ((opt = strsep(&options, ",")) != NULL) {
- if (!*opt)
+
+ while ((p = strsep(&options, ",")) != NULL) {
+ int token;
+ if (!*p)
continue;
- value = strchr(opt, '=');
- if (!value || !*value)
- return -EINVAL;
- else
- *value++ = '\0';
-
- if (!strcmp(opt, "uid"))
- pconfig->uid = simple_strtoul(value, &value, 0);
- else if (!strcmp(opt, "gid"))
- pconfig->gid = simple_strtoul(value, &value, 0);
- else if (!strcmp(opt, "mode"))
- pconfig->mode = simple_strtoul(value,&value,0) & 0777U;
- else if (!strcmp(opt, "size")) {
- unsigned long long size = memparse(value, &rest);
+ token = match_token(p, tokens, args);
+ switch (token) {
+ case Opt_uid:
+ if (match_int(&args[0], &option))
+ goto bad_val;
+ pconfig->uid = option;
+ break;
+
+ case Opt_gid:
+ if (match_int(&args[0], &option))
+ goto bad_val;
+ pconfig->gid = option;
+ break;
+
+ case Opt_mode:
+ if (match_octal(&args[0], &option))
+ goto bad_val;
+ pconfig->mode = option & 0777U;
+ break;
+
+ case Opt_size: {
+ unsigned long long size;
+ /* memparse() will accept a K/M/G without a digit */
+ if (!isdigit(*args[0].from))
+ goto bad_val;
+ size = memparse(args[0].from, &rest);
if (*rest == '%') {
size <<= HPAGE_SHIFT;
size *= max_huge_pages;
do_div(size, 100);
- rest++;
}
- size &= HPAGE_MASK;
pconfig->nr_blocks = (size >> HPAGE_SHIFT);
- value = rest;
- } else if (!strcmp(opt,"nr_inodes")) {
- pconfig->nr_inodes = memparse(value, &rest);
- value = rest;
- } else
- return -EINVAL;
+ break;
+ }
- if (*value)
+ case Opt_nr_inodes:
+ /* memparse() will accept a K/M/G without a digit */
+ if (!isdigit(*args[0].from))
+ goto bad_val;
+ pconfig->nr_inodes = memparse(args[0].from, &rest);
+ break;
+
+ default:
+ printk(KERN_ERR "hugetlbfs: Bad mount option: \"%s\"\n",
+ p);
return -EINVAL;
+ break;
+ }
}
return 0;
+
+bad_val:
+ printk(KERN_ERR "hugetlbfs: Bad value '%s' for mount option '%s'\n",
+ args[0].from, p);
+ return 1;
}
static int
config.gid = current->fsgid;
config.mode = 0755;
ret = hugetlbfs_parse_options(data, &config);
-
if (ret)
return ret;
can_do_mlock());
}
-struct file *hugetlb_zero_setup(size_t size)
+struct file *hugetlb_file_setup(const char *name, size_t size)
{
int error = -ENOMEM;
struct file *file;
struct inode *inode;
struct dentry *dentry, *root;
struct qstr quick_string;
- char buf[16];
- static atomic_t counter;
+
+ if (!hugetlbfs_vfsmount)
+ return ERR_PTR(-ENOENT);
if (!can_do_hugetlb_shm())
return ERR_PTR(-EPERM);
return ERR_PTR(-ENOMEM);
root = hugetlbfs_vfsmount->mnt_root;
- snprintf(buf, 16, "%u", atomic_inc_return(&counter));
- quick_string.name = buf;
+ quick_string.name = name;
quick_string.len = strlen(quick_string.name);
quick_string.hash = 0;
dentry = d_alloc(root, &quick_string);
goto out_file;
error = -ENOMEM;
- if (hugetlb_extend_reservation(HUGETLBFS_I(inode),
- size >> HPAGE_SHIFT) != 0)
+ if (hugetlb_reserve_pages(inode, 0, size >> HPAGE_SHIFT))
goto out_inode;
d_instantiate(dentry, inode);
inode->i_size = size;
inode->i_nlink = 0;
- file->f_vfsmnt = mntget(hugetlbfs_vfsmount);
- file->f_dentry = dentry;
+ file->f_path.mnt = mntget(hugetlbfs_vfsmount);
+ file->f_path.dentry = dentry;
file->f_mapping = inode->i_mapping;
file->f_op = &hugetlbfs_file_operations;
file->f_mode = FMODE_WRITE | FMODE_READ;
hugetlbfs_inode_cachep = kmem_cache_create("hugetlbfs_inode_cache",
sizeof(struct hugetlbfs_inode_info),
- 0, 0, init_once, NULL);
+ 0, 0, init_once);
if (hugetlbfs_inode_cachep == NULL)
return -ENOMEM;
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff