/*
* hugetlbpage-backed filesystem. Based on ramfs.
*
- * William Irwin, 2002
+ * Nadia Yvette Chambers, 2002
*
* Copyright (C) 2002 Linus Torvalds.
*/
#include <linux/statfs.h>
#include <linux/security.h>
#include <linux/magic.h>
+#include <linux/migrate.h>
#include <asm/uaccess.h>
static const struct inode_operations hugetlbfs_dir_inode_operations;
static const struct inode_operations hugetlbfs_inode_operations;
+struct hugetlbfs_config {
+ kuid_t uid;
+ kgid_t gid;
+ umode_t mode;
+ long nr_blocks;
+ long nr_inodes;
+ struct hstate *hstate;
+};
+
+struct hugetlbfs_inode_info {
+ struct shared_policy policy;
+ struct inode vfs_inode;
+};
+
+static inline struct hugetlbfs_inode_info *HUGETLBFS_I(struct inode *inode)
+{
+ return container_of(inode, struct hugetlbfs_inode_info, vfs_inode);
+}
+
static struct backing_dev_info hugetlbfs_backing_dev_info = {
.name = "hugetlbfs",
.ra_pages = 0, /* No readahead */
static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
{
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
loff_t len, vma_len;
int ret;
struct hstate *h = hstate_file(file);
* way when do_mmap_pgoff unwinds (may be important on powerpc
* and ia64).
*/
- vma->vm_flags |= VM_HUGETLB | VM_RESERVED;
+ vma->vm_flags |= VM_HUGETLB | VM_DONTEXPAND | VM_DONTDUMP;
vma->vm_ops = &hugetlb_vm_ops;
- if (vma->vm_pgoff & ~(huge_page_mask(h) >> PAGE_SHIFT))
+ if (vma->vm_pgoff & (~huge_page_mask(h) >> PAGE_SHIFT))
return -EINVAL;
vma_len = (loff_t)(vma->vm_end - vma->vm_start);
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
- unsigned long start_addr;
struct hstate *h = hstate_file(file);
+ struct vm_unmapped_area_info info;
if (len & ~huge_page_mask(h))
return -EINVAL;
return addr;
}
- start_addr = mm->free_area_cache;
-
- if (len <= mm->cached_hole_size)
- start_addr = TASK_UNMAPPED_BASE;
-
-full_search:
- 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 (TASK_SIZE - len < addr) {
- /*
- * Start a new search - just in case we missed
- * some holes.
- */
- if (start_addr != TASK_UNMAPPED_BASE) {
- start_addr = TASK_UNMAPPED_BASE;
- goto full_search;
- }
- return -ENOMEM;
- }
-
- if (!vma || addr + len <= vma->vm_start)
- return addr;
- addr = ALIGN(vma->vm_end, huge_page_size(h));
- }
+ info.flags = 0;
+ info.length = len;
+ info.low_limit = TASK_UNMAPPED_BASE;
+ info.high_limit = TASK_SIZE;
+ info.align_mask = PAGE_MASK & ~huge_page_mask(h);
+ info.align_offset = 0;
+ return vm_unmapped_area(&info);
}
#endif
loff_t isize;
ssize_t retval = 0;
- mutex_lock(&inode->i_mutex);
-
/* validate length */
if (len == 0)
goto out;
- isize = i_size_read(inode);
- if (!isize)
- goto out;
-
- end_index = (isize - 1) >> huge_page_shift(h);
for (;;) {
struct page *page;
unsigned long nr, ret;
/* nr is the maximum number of bytes to copy from this page */
nr = huge_page_size(h);
+ isize = i_size_read(inode);
+ if (!isize)
+ goto out;
+ end_index = (isize - 1) >> huge_page_shift(h);
if (index >= end_index) {
if (index > end_index)
goto out;
nr = ((isize - 1) & ~huge_page_mask(h)) + 1;
- if (nr <= offset) {
+ if (nr <= offset)
goto out;
- }
}
nr = nr - offset;
/* Find the page */
- page = find_get_page(mapping, index);
+ page = find_lock_page(mapping, index);
if (unlikely(page == NULL)) {
/*
* We have a HOLE, zero out the user-buffer for the
else
ra = 0;
} else {
+ unlock_page(page);
+
/*
* We have the page, copy it to user space buffer.
*/
ra = hugetlbfs_read_actor(page, offset, buf, len, nr);
ret = ra;
+ page_cache_release(page);
}
if (ra < 0) {
if (retval == 0)
retval = ra;
- if (page)
- page_cache_release(page);
goto out;
}
index += offset >> huge_page_shift(h);
offset &= ~huge_page_mask(h);
- if (page)
- page_cache_release(page);
-
/* short read or no more work */
if ((ret != nr) || (len == 0))
break;
}
out:
*ppos = ((loff_t)index << huge_page_shift(h)) + offset;
- mutex_unlock(&inode->i_mutex);
return retval;
}
{
cancel_dirty_page(page, /* No IO accounting for huge pages? */0);
ClearPageUptodate(page);
- remove_from_page_cache(page);
- put_page(page);
+ delete_from_page_cache(page);
}
static void truncate_hugepages(struct inode *inode, loff_t lstart)
}
static inline void
-hugetlb_vmtruncate_list(struct prio_tree_root *root, pgoff_t pgoff)
+hugetlb_vmtruncate_list(struct rb_root *root, pgoff_t pgoff)
{
struct vm_area_struct *vma;
- struct prio_tree_iter iter;
- vma_prio_tree_foreach(vma, &iter, root, pgoff, ULONG_MAX) {
+ vma_interval_tree_foreach(vma, root, pgoff, ULONG_MAX) {
unsigned long v_offset;
/*
* Can the expression below overflow on 32-bit arches?
- * No, because the prio_tree returns us only those vmas
+ * No, because the interval 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.
*/
else
v_offset = 0;
- __unmap_hugepage_range(vma,
- vma->vm_start + v_offset, vma->vm_end, NULL);
+ unmap_hugepage_range(vma, vma->vm_start + v_offset,
+ vma->vm_end, NULL);
}
}
pgoff = offset >> PAGE_SHIFT;
i_size_write(inode, offset);
- spin_lock(&mapping->i_mmap_lock);
- if (!prio_tree_empty(&mapping->i_mmap))
+ mutex_lock(&mapping->i_mmap_mutex);
+ if (!RB_EMPTY_ROOT(&mapping->i_mmap))
hugetlb_vmtruncate_list(&mapping->i_mmap, pgoff);
- spin_unlock(&mapping->i_mmap_lock);
+ mutex_unlock(&mapping->i_mmap_mutex);
truncate_hugepages(inode, offset);
return 0;
}
return 0;
}
-static struct inode *hugetlbfs_get_inode(struct super_block *sb, uid_t uid,
- gid_t gid, int mode, dev_t dev)
+static struct inode *hugetlbfs_get_root(struct super_block *sb,
+ struct hugetlbfs_config *config)
{
struct inode *inode;
inode = new_inode(sb);
if (inode) {
struct hugetlbfs_inode_info *info;
- inode->i_mode = mode;
- inode->i_uid = uid;
- inode->i_gid = gid;
+ inode->i_ino = get_next_ino();
+ inode->i_mode = S_IFDIR | config->mode;
+ inode->i_uid = config->uid;
+ inode->i_gid = config->gid;
+ inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+ info = HUGETLBFS_I(inode);
+ mpol_shared_policy_init(&info->policy, NULL);
+ inode->i_op = &hugetlbfs_dir_inode_operations;
+ inode->i_fop = &simple_dir_operations;
+ /* directory inodes start off with i_nlink == 2 (for "." entry) */
+ inc_nlink(inode);
+ lockdep_annotate_inode_mutex_key(inode);
+ }
+ return inode;
+}
+
+static struct inode *hugetlbfs_get_inode(struct super_block *sb,
+ struct inode *dir,
+ umode_t mode, dev_t dev)
+{
+ struct inode *inode;
+
+ inode = new_inode(sb);
+ if (inode) {
+ struct hugetlbfs_inode_info *info;
+ inode->i_ino = get_next_ino();
+ inode_init_owner(inode, dir, mode);
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;
inode->i_op = &page_symlink_inode_operations;
break;
}
+ lockdep_annotate_inode_mutex_key(inode);
}
return inode;
}
* File creation. Allocate an inode, and we're done..
*/
static int hugetlbfs_mknod(struct inode *dir,
- struct dentry *dentry, int mode, dev_t dev)
+ struct dentry *dentry, umode_t mode, dev_t dev)
{
struct inode *inode;
int error = -ENOSPC;
- gid_t gid;
-
- if (dir->i_mode & S_ISGID) {
- gid = dir->i_gid;
- if (S_ISDIR(mode))
- mode |= S_ISGID;
- } else {
- gid = current_fsgid();
- }
- inode = hugetlbfs_get_inode(dir->i_sb, current_fsuid(), gid, mode, dev);
+
+ inode = hugetlbfs_get_inode(dir->i_sb, dir, mode, dev);
if (inode) {
dir->i_ctime = dir->i_mtime = CURRENT_TIME;
d_instantiate(dentry, inode);
return error;
}
-static int hugetlbfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
+static int hugetlbfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
{
int retval = hugetlbfs_mknod(dir, dentry, mode | S_IFDIR, 0);
if (!retval)
return retval;
}
-static int hugetlbfs_create(struct inode *dir, struct dentry *dentry, int mode, struct nameidata *nd)
+static int hugetlbfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl)
{
return hugetlbfs_mknod(dir, dentry, mode | S_IFREG, 0);
}
{
struct inode *inode;
int error = -ENOSPC;
- gid_t gid;
-
- if (dir->i_mode & S_ISGID)
- gid = dir->i_gid;
- else
- gid = current_fsgid();
- inode = hugetlbfs_get_inode(dir->i_sb, current_fsuid(),
- gid, S_IFLNK|S_IRWXUGO, 0);
+ inode = hugetlbfs_get_inode(dir->i_sb, dir, S_IFLNK|S_IRWXUGO, 0);
if (inode) {
int l = strlen(symname)+1;
error = page_symlink(inode, symname, l);
return 0;
}
+static int hugetlbfs_migrate_page(struct address_space *mapping,
+ struct page *newpage, struct page *page,
+ enum migrate_mode mode)
+{
+ int rc;
+
+ rc = migrate_huge_page_move_mapping(mapping, newpage, page);
+ if (rc != MIGRATEPAGE_SUCCESS)
+ return rc;
+ migrate_page_copy(newpage, page);
+
+ return MIGRATEPAGE_SUCCESS;
+}
+
static int hugetlbfs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(dentry->d_sb);
spin_lock(&sbinfo->stat_lock);
/* If no limits set, just report 0 for max/free/used
* blocks, like simple_statfs() */
- if (sbinfo->max_blocks >= 0) {
- buf->f_blocks = sbinfo->max_blocks;
- buf->f_bavail = buf->f_bfree = sbinfo->free_blocks;
+ if (sbinfo->spool) {
+ long free_pages;
+
+ spin_lock(&sbinfo->spool->lock);
+ buf->f_blocks = sbinfo->spool->max_hpages;
+ free_pages = sbinfo->spool->max_hpages
+ - sbinfo->spool->used_hpages;
+ buf->f_bavail = buf->f_bfree = free_pages;
+ spin_unlock(&sbinfo->spool->lock);
buf->f_files = sbinfo->max_inodes;
buf->f_ffree = sbinfo->free_inodes;
}
if (sbi) {
sb->s_fs_info = NULL;
+
+ if (sbi->spool)
+ hugepage_put_subpool(sbi->spool);
+
kfree(sbi);
}
}
return &p->vfs_inode;
}
+static void hugetlbfs_i_callback(struct rcu_head *head)
+{
+ struct inode *inode = container_of(head, struct inode, i_rcu);
+ kmem_cache_free(hugetlbfs_inode_cachep, HUGETLBFS_I(inode));
+}
+
static void hugetlbfs_destroy_inode(struct inode *inode)
{
hugetlbfs_inc_free_inodes(HUGETLBFS_SB(inode->i_sb));
mpol_free_shared_policy(&HUGETLBFS_I(inode)->policy);
- kmem_cache_free(hugetlbfs_inode_cachep, HUGETLBFS_I(inode));
+ call_rcu(&inode->i_rcu, hugetlbfs_i_callback);
}
static const struct address_space_operations hugetlbfs_aops = {
.write_begin = hugetlbfs_write_begin,
.write_end = hugetlbfs_write_end,
.set_page_dirty = hugetlbfs_set_page_dirty,
+ .migratepage = hugetlbfs_migrate_page,
};
.mmap = hugetlbfs_file_mmap,
.fsync = noop_fsync,
.get_unmapped_area = hugetlb_get_unmapped_area,
+ .llseek = default_llseek,
};
static const struct inode_operations hugetlbfs_dir_inode_operations = {
case Opt_uid:
if (match_int(&args[0], &option))
goto bad_val;
- pconfig->uid = option;
+ pconfig->uid = make_kuid(current_user_ns(), option);
+ if (!uid_valid(pconfig->uid))
+ goto bad_val;
break;
case Opt_gid:
if (match_int(&args[0], &option))
goto bad_val;
- pconfig->gid = option;
+ pconfig->gid = make_kgid(current_user_ns(), option);
+ if (!gid_valid(pconfig->gid))
+ goto bad_val;
break;
case Opt_mode:
static int
hugetlbfs_fill_super(struct super_block *sb, void *data, int silent)
{
- struct inode * inode;
- struct dentry * root;
int ret;
struct hugetlbfs_config config;
struct hugetlbfs_sb_info *sbinfo;
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;
+ sbinfo->spool = NULL;
+ if (config.nr_blocks != -1) {
+ sbinfo->spool = hugepage_new_subpool(config.nr_blocks);
+ if (!sbinfo->spool)
+ goto out_free;
+ }
sb->s_maxbytes = MAX_LFS_FILESIZE;
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;
- inode = hugetlbfs_get_inode(sb, config.uid, config.gid,
- S_IFDIR | config.mode, 0);
- if (!inode)
+ sb->s_root = d_make_root(hugetlbfs_get_root(sb, &config));
+ if (!sb->s_root)
goto out_free;
-
- root = d_alloc_root(inode);
- if (!root) {
- iput(inode);
- goto out_free;
- }
- sb->s_root = root;
return 0;
out_free:
+ if (sbinfo->spool)
+ kfree(sbinfo->spool);
kfree(sbinfo);
return -ENOMEM;
}
-int hugetlb_get_quota(struct address_space *mapping, long delta)
+static struct dentry *hugetlbfs_mount(struct file_system_type *fs_type,
+ int flags, const char *dev_name, void *data)
{
- int ret = 0;
- struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(mapping->host->i_sb);
-
- if (sbinfo->free_blocks > -1) {
- spin_lock(&sbinfo->stat_lock);
- if (sbinfo->free_blocks - delta >= 0)
- sbinfo->free_blocks -= delta;
- else
- ret = -ENOMEM;
- spin_unlock(&sbinfo->stat_lock);
- }
-
- return ret;
-}
-
-void hugetlb_put_quota(struct address_space *mapping, long delta)
-{
- struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(mapping->host->i_sb);
-
- if (sbinfo->free_blocks > -1) {
- spin_lock(&sbinfo->stat_lock);
- sbinfo->free_blocks += delta;
- spin_unlock(&sbinfo->stat_lock);
- }
-}
-
-static int hugetlbfs_get_sb(struct file_system_type *fs_type,
- int flags, const char *dev_name, void *data, struct vfsmount *mnt)
-{
- return get_sb_nodev(fs_type, flags, data, hugetlbfs_fill_super, mnt);
+ return mount_nodev(fs_type, flags, data, hugetlbfs_fill_super);
}
static struct file_system_type hugetlbfs_fs_type = {
.name = "hugetlbfs",
- .get_sb = hugetlbfs_get_sb,
+ .mount = hugetlbfs_mount,
.kill_sb = kill_litter_super,
};
-static struct vfsmount *hugetlbfs_vfsmount;
+static struct vfsmount *hugetlbfs_vfsmount[HUGE_MAX_HSTATE];
static int can_do_hugetlb_shm(void)
{
- return capable(CAP_IPC_LOCK) || in_group_p(sysctl_hugetlb_shm_group);
+ kgid_t shm_group;
+ shm_group = make_kgid(&init_user_ns, sysctl_hugetlb_shm_group);
+ return capable(CAP_IPC_LOCK) || in_group_p(shm_group);
+}
+
+static int get_hstate_idx(int page_size_log)
+{
+ struct hstate *h;
+
+ if (!page_size_log)
+ return default_hstate_idx;
+ h = size_to_hstate(1 << page_size_log);
+ if (!h)
+ return -1;
+ return h - hstates;
}
-struct file *hugetlb_file_setup(const char *name, size_t size, int acctflag,
- struct user_struct **user, int creat_flags)
+struct file *hugetlb_file_setup(const char *name, unsigned long addr,
+ size_t size, vm_flags_t acctflag,
+ struct user_struct **user,
+ int creat_flags, int page_size_log)
{
- int error = -ENOMEM;
- struct file *file;
+ struct file *file = ERR_PTR(-ENOMEM);
struct inode *inode;
struct path path;
struct dentry *root;
struct qstr quick_string;
+ struct hstate *hstate;
+ unsigned long num_pages;
+ int hstate_idx;
+
+ hstate_idx = get_hstate_idx(page_size_log);
+ if (hstate_idx < 0)
+ return ERR_PTR(-ENODEV);
*user = NULL;
- if (!hugetlbfs_vfsmount)
+ if (!hugetlbfs_vfsmount[hstate_idx])
return ERR_PTR(-ENOENT);
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");
+ task_lock(current);
+ printk_once(KERN_WARNING
+ "%s (%d): Using mlock ulimits for SHM_HUGETLB is deprecated\n",
+ current->comm, current->pid);
+ task_unlock(current);
} else {
*user = NULL;
return ERR_PTR(-EPERM);
}
}
- root = hugetlbfs_vfsmount->mnt_root;
+ root = hugetlbfs_vfsmount[hstate_idx]->mnt_root;
quick_string.name = name;
quick_string.len = strlen(quick_string.name);
quick_string.hash = 0;
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);
+ path.mnt = mntget(hugetlbfs_vfsmount[hstate_idx]);
+ file = ERR_PTR(-ENOSPC);
+ inode = hugetlbfs_get_inode(root->d_sb, NULL, S_IFREG | S_IRWXUGO, 0);
if (!inode)
goto out_dentry;
- error = -ENOMEM;
- if (hugetlb_reserve_pages(inode, 0,
- size >> huge_page_shift(hstate_inode(inode)), NULL,
- acctflag))
+ hstate = hstate_inode(inode);
+ size += addr & ~huge_page_mask(hstate);
+ num_pages = ALIGN(size, huge_page_size(hstate)) >>
+ huge_page_shift(hstate);
+ file = ERR_PTR(-ENOMEM);
+ if (hugetlb_reserve_pages(inode, 0, num_pages, NULL, acctflag))
goto out_inode;
d_instantiate(path.dentry, inode);
inode->i_size = size;
- inode->i_nlink = 0;
+ clear_nlink(inode);
- error = -ENFILE;
file = alloc_file(&path, FMODE_WRITE | FMODE_READ,
&hugetlbfs_file_operations);
- if (!file)
+ if (IS_ERR(file))
goto out_dentry; /* inode is already attached */
return file;
user_shm_unlock(size, *user);
*user = NULL;
}
- return ERR_PTR(error);
+ return file;
}
static int __init init_hugetlbfs_fs(void)
{
+ struct hstate *h;
int error;
- struct vfsmount *vfsmount;
+ int i;
error = bdi_init(&hugetlbfs_backing_dev_info);
if (error)
return error;
+ error = -ENOMEM;
hugetlbfs_inode_cachep = kmem_cache_create("hugetlbfs_inode_cache",
sizeof(struct hugetlbfs_inode_info),
0, 0, init_once);
if (error)
goto out;
- vfsmount = kern_mount(&hugetlbfs_fs_type);
+ i = 0;
+ for_each_hstate(h) {
+ char buf[50];
+ unsigned ps_kb = 1U << (h->order + PAGE_SHIFT - 10);
- if (!IS_ERR(vfsmount)) {
- hugetlbfs_vfsmount = vfsmount;
- return 0;
- }
+ snprintf(buf, sizeof(buf), "pagesize=%uK", ps_kb);
+ hugetlbfs_vfsmount[i] = kern_mount_data(&hugetlbfs_fs_type,
+ buf);
- error = PTR_ERR(vfsmount);
+ if (IS_ERR(hugetlbfs_vfsmount[i])) {
+ pr_err("hugetlb: Cannot mount internal hugetlbfs for "
+ "page size %uK", ps_kb);
+ error = PTR_ERR(hugetlbfs_vfsmount[i]);
+ hugetlbfs_vfsmount[i] = NULL;
+ }
+ i++;
+ }
+ /* Non default hstates are optional */
+ if (!IS_ERR_OR_NULL(hugetlbfs_vfsmount[default_hstate_idx]))
+ return 0;
out:
- if (error)
- kmem_cache_destroy(hugetlbfs_inode_cachep);
+ kmem_cache_destroy(hugetlbfs_inode_cachep);
out2:
bdi_destroy(&hugetlbfs_backing_dev_info);
return error;
static void __exit exit_hugetlbfs_fs(void)
{
+ struct hstate *h;
+ int i;
+
+
+ /*
+ * Make sure all delayed rcu free inodes are flushed before we
+ * destroy cache.
+ */
+ rcu_barrier();
kmem_cache_destroy(hugetlbfs_inode_cachep);
+ i = 0;
+ for_each_hstate(h)
+ kern_unmount(hugetlbfs_vfsmount[i++]);
unregister_filesystem(&hugetlbfs_fs_type);
bdi_destroy(&hugetlbfs_backing_dev_info);
}
Code Review / linux-3.10.git / blobdiff