#include <linux/pagevec.h>
#include <linux/parser.h>
#include <linux/mman.h>
-#include <linux/quotaops.h>
#include <linux/slab.h>
#include <linux/dnotify.h>
#include <linux/statfs.h>
#include <linux/security.h>
+#include <linux/magic.h>
#include <asm/uaccess.h>
-/* some random number */
-#define HUGETLBFS_MAGIC 0x958458f6
-
static const struct super_operations hugetlbfs_ops;
static const struct address_space_operations hugetlbfs_aops;
const struct file_operations hugetlbfs_file_operations;
static const struct inode_operations hugetlbfs_inode_operations;
static struct backing_dev_info hugetlbfs_backing_dev_info = {
+ .name = "hugetlbfs",
.ra_pages = 0, /* No readahead */
.capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK,
};
enum {
Opt_size, Opt_nr_inodes,
Opt_mode, Opt_uid, Opt_gid,
+ Opt_pagesize,
Opt_err,
};
-static match_table_t tokens = {
+static const 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_pagesize, "pagesize=%s"},
{Opt_err, NULL},
};
struct inode *inode = file->f_path.dentry->d_inode;
loff_t len, vma_len;
int ret;
+ struct hstate *h = hstate_file(file);
/*
* vma address alignment (but not the pgoff alignment) has
vma->vm_flags |= VM_HUGETLB | VM_RESERVED;
vma->vm_ops = &hugetlb_vm_ops;
- if (vma->vm_pgoff & ~(HPAGE_MASK >> PAGE_SHIFT))
+ if (vma->vm_pgoff & ~(huge_page_mask(h) >> PAGE_SHIFT))
return -EINVAL;
vma_len = (loff_t)(vma->vm_end - vma->vm_start);
len = vma_len + ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
if (hugetlb_reserve_pages(inode,
- vma->vm_pgoff >> (HPAGE_SHIFT-PAGE_SHIFT),
- len >> HPAGE_SHIFT, vma))
+ vma->vm_pgoff >> huge_page_order(h),
+ len >> huge_page_shift(h), vma,
+ vma->vm_flags))
goto out;
ret = 0;
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
unsigned long start_addr;
+ struct hstate *h = hstate_file(file);
- if (len & ~HPAGE_MASK)
+ if (len & ~huge_page_mask(h))
return -EINVAL;
if (len > TASK_SIZE)
return -ENOMEM;
if (flags & MAP_FIXED) {
- if (prepare_hugepage_range(addr, len))
+ if (prepare_hugepage_range(file, addr, len))
return -EINVAL;
return addr;
}
if (addr) {
- addr = ALIGN(addr, HPAGE_SIZE);
+ addr = ALIGN(addr, huge_page_size(h));
vma = find_vma(mm, addr);
if (TASK_SIZE - len >= addr &&
(!vma || addr + len <= vma->vm_start))
start_addr = TASK_UNMAPPED_BASE;
full_search:
- addr = ALIGN(start_addr, HPAGE_SIZE);
+ addr = ALIGN(start_addr, huge_page_size(h));
for (vma = find_vma(mm, addr); ; vma = vma->vm_next) {
/* At this point: (!vma || addr < vma->vm_end). */
if (!vma || addr + len <= vma->vm_start)
return addr;
- addr = ALIGN(vma->vm_end, HPAGE_SIZE);
+ addr = ALIGN(vma->vm_end, huge_page_size(h));
}
}
#endif
static ssize_t hugetlbfs_read(struct file *filp, char __user *buf,
size_t len, loff_t *ppos)
{
+ struct hstate *h = hstate_file(filp);
struct address_space *mapping = filp->f_mapping;
struct inode *inode = mapping->host;
- unsigned long index = *ppos >> HPAGE_SHIFT;
- unsigned long offset = *ppos & ~HPAGE_MASK;
+ unsigned long index = *ppos >> huge_page_shift(h);
+ unsigned long offset = *ppos & ~huge_page_mask(h);
unsigned long end_index;
loff_t isize;
ssize_t retval = 0;
if (!isize)
goto out;
- end_index = (isize - 1) >> HPAGE_SHIFT;
+ end_index = (isize - 1) >> huge_page_shift(h);
for (;;) {
struct page *page;
- int nr, ret;
+ unsigned long nr, ret;
+ int ra;
/* nr is the maximum number of bytes to copy from this page */
- nr = HPAGE_SIZE;
+ nr = huge_page_size(h);
if (index >= end_index) {
if (index > end_index)
goto out;
- nr = ((isize - 1) & ~HPAGE_MASK) + 1;
+ nr = ((isize - 1) & ~huge_page_mask(h)) + 1;
if (nr <= offset) {
goto out;
}
*/
ret = len < nr ? len : nr;
if (clear_user(buf, ret))
- ret = -EFAULT;
+ ra = -EFAULT;
+ else
+ ra = 0;
} else {
/*
* We have the page, copy it to user space buffer.
*/
- ret = hugetlbfs_read_actor(page, offset, buf, len, nr);
+ ra = hugetlbfs_read_actor(page, offset, buf, len, nr);
+ ret = ra;
}
- if (ret < 0) {
+ if (ra < 0) {
if (retval == 0)
- retval = ret;
+ retval = ra;
if (page)
page_cache_release(page);
goto out;
offset += ret;
retval += ret;
len -= ret;
- index += offset >> HPAGE_SHIFT;
- offset &= ~HPAGE_MASK;
+ index += offset >> huge_page_shift(h);
+ offset &= ~huge_page_mask(h);
if (page)
page_cache_release(page);
break;
}
out:
- *ppos = ((loff_t)index << HPAGE_SHIFT) + offset;
+ *ppos = ((loff_t)index << huge_page_shift(h)) + offset;
mutex_unlock(&inode->i_mutex);
return retval;
}
-/*
- * Read a page. Again trivial. If it didn't already exist
- * in the page cache, it is zero-filled.
- */
-static int hugetlbfs_readpage(struct file *file, struct page * page)
-{
- unlock_page(page);
- return -EINVAL;
-}
-
static int hugetlbfs_write_begin(struct file *file,
struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
static void truncate_hugepages(struct inode *inode, loff_t lstart)
{
+ struct hstate *h = hstate_inode(inode);
struct address_space *mapping = &inode->i_data;
- const pgoff_t start = lstart >> HPAGE_SHIFT;
+ const pgoff_t start = lstart >> huge_page_shift(h);
struct pagevec pvec;
pgoff_t next;
int i, freed = 0;
static void hugetlbfs_forget_inode(struct inode *inode) __releases(inode_lock)
{
- struct super_block *sb = inode->i_sb;
-
- if (!hlist_unhashed(&inode->i_hash)) {
- if (!(inode->i_state & (I_DIRTY|I_SYNC)))
- list_move(&inode->i_list, &inode_unused);
- inodes_stat.nr_unused++;
- if (!sb || (sb->s_flags & MS_ACTIVE)) {
- spin_unlock(&inode_lock);
- return;
- }
- inode->i_state |= I_WILL_FREE;
- spin_unlock(&inode_lock);
- /*
- * write_inode_now is a noop as we set BDI_CAP_NO_WRITEBACK
- * in our backing_dev_info.
- */
- write_inode_now(inode, 1);
- spin_lock(&inode_lock);
- inode->i_state &= ~I_WILL_FREE;
- inodes_stat.nr_unused--;
- hlist_del_init(&inode->i_hash);
+ if (generic_detach_inode(inode)) {
+ truncate_hugepages(inode, 0);
+ clear_inode(inode);
+ destroy_inode(inode);
}
- list_del_init(&inode->i_list);
- list_del_init(&inode->i_sb_list);
- inode->i_state |= I_FREEING;
- inodes_stat.nr_inodes--;
- spin_unlock(&inode_lock);
- truncate_hugepages(inode, 0);
- clear_inode(inode);
- destroy_inode(inode);
}
static void hugetlbfs_drop_inode(struct inode *inode)
v_offset = 0;
__unmap_hugepage_range(vma,
- vma->vm_start + v_offset, vma->vm_end);
+ vma->vm_start + v_offset, vma->vm_end, NULL);
}
}
{
pgoff_t pgoff;
struct address_space *mapping = inode->i_mapping;
+ struct hstate *h = hstate_inode(inode);
- BUG_ON(offset & ~HPAGE_MASK);
+ BUG_ON(offset & ~huge_page_mask(h));
pgoff = offset >> PAGE_SHIFT;
i_size_write(inode, offset);
static int hugetlbfs_setattr(struct dentry *dentry, struct iattr *attr)
{
struct inode *inode = dentry->d_inode;
+ struct hstate *h = hstate_inode(inode);
int error;
unsigned int ia_valid = attr->ia_valid;
if (ia_valid & ATTR_SIZE) {
error = -EINVAL;
- if (!(attr->ia_size & ~HPAGE_MASK))
+ if (!(attr->ia_size & ~huge_page_mask(h)))
error = hugetlb_vmtruncate(inode, attr->ia_size);
if (error)
goto out;
inode->i_mode = mode;
inode->i_uid = uid;
inode->i_gid = gid;
- 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);
+ /*
+ * The policy is initialized here even if we are creating a
+ * private inode because initialization simply creates an
+ * an empty rb tree and calls spin_lock_init(), later when we
+ * call mpol_free_shared_policy() it will just return because
+ * the rb tree will still be empty.
+ */
mpol_shared_policy_init(&info->policy, NULL);
switch (mode & S_IFMT) {
default:
if (S_ISDIR(mode))
mode |= S_ISGID;
} else {
- gid = current->fsgid;
+ gid = current_fsgid();
}
- inode = hugetlbfs_get_inode(dir->i_sb, current->fsuid, gid, mode, dev);
+ inode = hugetlbfs_get_inode(dir->i_sb, current_fsuid(), gid, mode, dev);
if (inode) {
dir->i_ctime = dir->i_mtime = CURRENT_TIME;
d_instantiate(dentry, inode);
if (dir->i_mode & S_ISGID)
gid = dir->i_gid;
else
- gid = current->fsgid;
+ gid = current_fsgid();
- inode = hugetlbfs_get_inode(dir->i_sb, current->fsuid,
+ inode = hugetlbfs_get_inode(dir->i_sb, current_fsuid(),
gid, S_IFLNK|S_IRWXUGO, 0);
if (inode) {
int l = strlen(symname)+1;
static int hugetlbfs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(dentry->d_sb);
+ struct hstate *h = hstate_inode(dentry->d_inode);
buf->f_type = HUGETLBFS_MAGIC;
- buf->f_bsize = HPAGE_SIZE;
+ buf->f_bsize = huge_page_size(h);
if (sbinfo) {
spin_lock(&sbinfo->stat_lock);
/* If no limits set, just report 0 for max/free/used
}
static const struct address_space_operations hugetlbfs_aops = {
- .readpage = hugetlbfs_readpage,
.write_begin = hugetlbfs_write_begin,
.write_end = hugetlbfs_write_end,
.set_page_dirty = hugetlbfs_set_page_dirty,
};
-static void init_once(struct kmem_cache *cachep, void *foo)
+static void init_once(void *foo)
{
struct hugetlbfs_inode_info *ei = (struct hugetlbfs_inode_info *)foo;
char *p, *rest;
substring_t args[MAX_OPT_ARGS];
int option;
+ unsigned long long size = 0;
+ enum { NO_SIZE, SIZE_STD, SIZE_PERCENT } setsize = NO_SIZE;
if (!options)
return 0;
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);
- }
- pconfig->nr_blocks = (size >> HPAGE_SHIFT);
+ setsize = SIZE_STD;
+ if (*rest == '%')
+ setsize = SIZE_PERCENT;
break;
}
pconfig->nr_inodes = memparse(args[0].from, &rest);
break;
+ case Opt_pagesize: {
+ unsigned long ps;
+ ps = memparse(args[0].from, &rest);
+ pconfig->hstate = size_to_hstate(ps);
+ if (!pconfig->hstate) {
+ printk(KERN_ERR
+ "hugetlbfs: Unsupported page size %lu MB\n",
+ ps >> 20);
+ return -EINVAL;
+ }
+ break;
+ }
+
default:
printk(KERN_ERR "hugetlbfs: Bad mount option: \"%s\"\n",
p);
break;
}
}
+
+ /* Do size after hstate is set up */
+ if (setsize > NO_SIZE) {
+ struct hstate *h = pconfig->hstate;
+ if (setsize == SIZE_PERCENT) {
+ size <<= huge_page_shift(h);
+ size *= h->max_huge_pages;
+ do_div(size, 100);
+ }
+ pconfig->nr_blocks = (size >> huge_page_shift(h));
+ }
+
return 0;
bad_val:
printk(KERN_ERR "hugetlbfs: Bad value '%s' for mount option '%s'\n",
args[0].from, p);
- return 1;
+ return -EINVAL;
}
static int
config.nr_blocks = -1; /* No limit on size by default */
config.nr_inodes = -1; /* No limit on number of inodes by default */
- config.uid = current->fsuid;
- config.gid = current->fsgid;
+ config.uid = current_fsuid();
+ config.gid = current_fsgid();
config.mode = 0755;
+ config.hstate = &default_hstate;
ret = hugetlbfs_parse_options(data, &config);
if (ret)
return ret;
if (!sbinfo)
return -ENOMEM;
sb->s_fs_info = sbinfo;
+ sbinfo->hstate = config.hstate;
spin_lock_init(&sbinfo->stat_lock);
sbinfo->max_blocks = config.nr_blocks;
sbinfo->free_blocks = config.nr_blocks;
sbinfo->max_inodes = config.nr_inodes;
sbinfo->free_inodes = config.nr_inodes;
sb->s_maxbytes = MAX_LFS_FILESIZE;
- sb->s_blocksize = HPAGE_SIZE;
- sb->s_blocksize_bits = HPAGE_SHIFT;
+ sb->s_blocksize = huge_page_size(config.hstate);
+ sb->s_blocksize_bits = huge_page_shift(config.hstate);
sb->s_magic = HUGETLBFS_MAGIC;
sb->s_op = &hugetlbfs_ops;
sb->s_time_gran = 1;
static int can_do_hugetlb_shm(void)
{
- return likely(capable(CAP_IPC_LOCK) ||
- in_group_p(sysctl_hugetlb_shm_group) ||
- can_do_mlock());
+ return capable(CAP_IPC_LOCK) || in_group_p(sysctl_hugetlb_shm_group);
}
-struct file *hugetlb_file_setup(const char *name, size_t size)
+struct file *hugetlb_file_setup(const char *name, size_t size, int acctflag,
+ struct user_struct **user, int creat_flags)
{
int error = -ENOMEM;
struct file *file;
struct inode *inode;
- struct dentry *dentry, *root;
+ struct path path;
+ struct dentry *root;
struct qstr quick_string;
+ *user = NULL;
if (!hugetlbfs_vfsmount)
return ERR_PTR(-ENOENT);
- if (!can_do_hugetlb_shm())
- return ERR_PTR(-EPERM);
-
- if (!user_shm_lock(size, current->user))
- return ERR_PTR(-ENOMEM);
+ if (creat_flags == HUGETLB_SHMFS_INODE && !can_do_hugetlb_shm()) {
+ *user = current_user();
+ if (user_shm_lock(size, *user)) {
+ WARN_ONCE(1,
+ "Using mlock ulimits for SHM_HUGETLB deprecated\n");
+ } else {
+ *user = NULL;
+ return ERR_PTR(-EPERM);
+ }
+ }
root = hugetlbfs_vfsmount->mnt_root;
quick_string.name = name;
quick_string.len = strlen(quick_string.name);
quick_string.hash = 0;
- dentry = d_alloc(root, &quick_string);
- if (!dentry)
+ path.dentry = d_alloc(root, &quick_string);
+ if (!path.dentry)
goto out_shm_unlock;
+ path.mnt = mntget(hugetlbfs_vfsmount);
error = -ENOSPC;
- inode = hugetlbfs_get_inode(root->d_sb, current->fsuid,
- current->fsgid, S_IFREG | S_IRWXUGO, 0);
+ inode = hugetlbfs_get_inode(root->d_sb, current_fsuid(),
+ current_fsgid(), S_IFREG | S_IRWXUGO, 0);
if (!inode)
goto out_dentry;
error = -ENOMEM;
- if (hugetlb_reserve_pages(inode, 0, size >> HPAGE_SHIFT, NULL))
+ if (hugetlb_reserve_pages(inode, 0,
+ size >> huge_page_shift(hstate_inode(inode)), NULL,
+ acctflag))
goto out_inode;
- d_instantiate(dentry, inode);
+ d_instantiate(path.dentry, inode);
inode->i_size = size;
inode->i_nlink = 0;
error = -ENFILE;
- file = alloc_file(hugetlbfs_vfsmount, dentry,
- FMODE_WRITE | FMODE_READ,
+ file = alloc_file(&path, FMODE_WRITE | FMODE_READ,
&hugetlbfs_file_operations);
if (!file)
goto out_dentry; /* inode is already attached */
out_inode:
iput(inode);
out_dentry:
- dput(dentry);
+ path_put(&path);
out_shm_unlock:
- user_shm_unlock(size, current->user);
+ if (*user) {
+ user_shm_unlock(size, *user);
+ *user = NULL;
+ }
return ERR_PTR(error);
}
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff