aboutsummaryrefslogtreecommitdiffstats
path: root/fs/hugetlbfs/inode.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/hugetlbfs/inode.c')
-rw-r--r--fs/hugetlbfs/inode.c149
1 files changed, 85 insertions, 64 deletions
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index cc9281b6c62..78bde32ea95 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -1,7 +1,7 @@
/*
* hugetlbpage-backed filesystem. Based on ramfs.
*
- * William Irwin, 2002
+ * Nadia Yvette Chambers, 2002
*
* Copyright (C) 2002 Linus Torvalds.
*/
@@ -42,8 +42,8 @@ static const struct inode_operations hugetlbfs_dir_inode_operations;
static const struct inode_operations hugetlbfs_inode_operations;
struct hugetlbfs_config {
- uid_t uid;
- gid_t gid;
+ kuid_t uid;
+ kgid_t gid;
umode_t mode;
long nr_blocks;
long nr_inodes;
@@ -110,7 +110,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
* 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))
@@ -151,8 +151,8 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
{
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;
@@ -173,39 +173,13 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
return addr;
}
- if (len > mm->cached_hole_size)
- start_addr = mm->free_area_cache;
- else {
- start_addr = TASK_UNMAPPED_BASE;
- mm->cached_hole_size = 0;
- }
-
-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;
- mm->cached_hole_size = 0;
- goto full_search;
- }
- return -ENOMEM;
- }
-
- if (!vma || addr + len <= vma->vm_start) {
- mm->free_area_cache = addr + len;
- return addr;
- }
- if (addr + mm->cached_hole_size < vma->vm_start)
- mm->cached_hole_size = vma->vm_start - 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
@@ -397,17 +371,16 @@ static void hugetlbfs_evict_inode(struct inode *inode)
}
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.
*/
@@ -416,8 +389,8 @@ hugetlb_vmtruncate_list(struct prio_tree_root *root, pgoff_t pgoff)
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);
}
}
@@ -432,7 +405,7 @@ static int hugetlb_vmtruncate(struct inode *inode, loff_t offset)
i_size_write(inode, offset);
mutex_lock(&mapping->i_mmap_mutex);
- if (!prio_tree_empty(&mapping->i_mmap))
+ if (!RB_EMPTY_ROOT(&mapping->i_mmap))
hugetlb_vmtruncate_list(&mapping->i_mmap, pgoff);
mutex_unlock(&mapping->i_mmap_mutex);
truncate_hugepages(inode, offset);
@@ -565,7 +538,7 @@ static int hugetlbfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mod
return retval;
}
-static int hugetlbfs_create(struct inode *dir, struct dentry *dentry, umode_t 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);
}
@@ -609,11 +582,11 @@ static int hugetlbfs_migrate_page(struct address_space *mapping,
int rc;
rc = migrate_huge_page_move_mapping(mapping, newpage, page);
- if (rc)
+ if (rc != MIGRATEPAGE_SUCCESS)
return rc;
migrate_page_copy(newpage, page);
- return 0;
+ return MIGRATEPAGE_SUCCESS;
}
static int hugetlbfs_statfs(struct dentry *dentry, struct kstatfs *buf)
@@ -785,13 +758,17 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig)
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:
@@ -920,16 +897,31 @@ static struct file_system_type hugetlbfs_fs_type = {
.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, unsigned long addr,
size_t size, vm_flags_t acctflag,
- struct user_struct **user, int creat_flags)
+ struct user_struct **user,
+ int creat_flags, int page_size_log)
{
int error = -ENOMEM;
struct file *file;
@@ -939,9 +931,14 @@ struct file *hugetlb_file_setup(const char *name, unsigned long addr,
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()) {
@@ -958,7 +955,7 @@ struct file *hugetlb_file_setup(const char *name, unsigned long addr,
}
}
- 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;
@@ -966,7 +963,7 @@ struct file *hugetlb_file_setup(const char *name, unsigned long addr,
if (!path.dentry)
goto out_shm_unlock;
- path.mnt = mntget(hugetlbfs_vfsmount);
+ path.mnt = mntget(hugetlbfs_vfsmount[hstate_idx]);
error = -ENOSPC;
inode = hugetlbfs_get_inode(root->d_sb, NULL, S_IFREG | S_IRWXUGO, 0);
if (!inode)
@@ -1006,8 +1003,9 @@ out_shm_unlock:
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)
@@ -1024,14 +1022,26 @@ static int __init init_hugetlbfs_fs(void)
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:
kmem_cache_destroy(hugetlbfs_inode_cachep);
@@ -1042,8 +1052,19 @@ static int __init init_hugetlbfs_fs(void)
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);
- kern_unmount(hugetlbfs_vfsmount);
+ i = 0;
+ for_each_hstate(h)
+ kern_unmount(hugetlbfs_vfsmount[i++]);
unregister_filesystem(&hugetlbfs_fs_type);
bdi_destroy(&hugetlbfs_backing_dev_info);
}