aboutsummaryrefslogtreecommitdiff
path: root/fs/hugetlbfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/hugetlbfs')
-rw-r--r--fs/hugetlbfs/inode.c105
1 files changed, 65 insertions, 40 deletions
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 78bde32ea95..1e2872b2534 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -6,6 +6,8 @@
* Copyright (C) 2002 Linus Torvalds.
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/module.h>
#include <linux/thread_info.h>
#include <asm/current.h>
@@ -97,7 +99,7 @@ static void huge_pagevec_release(struct pagevec *pvec)
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);
@@ -110,7 +112,7 @@ 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_DONTEXPAND | VM_DONTDUMP;
+ vma->vm_flags |= VM_HUGETLB | VM_DONTEXPAND;
vma->vm_ops = &hugetlb_vm_ops;
if (vma->vm_pgoff & (~huge_page_mask(h) >> PAGE_SHIFT))
@@ -366,7 +368,13 @@ static void truncate_hugepages(struct inode *inode, loff_t lstart)
static void hugetlbfs_evict_inode(struct inode *inode)
{
+ struct resv_map *resv_map;
+
truncate_hugepages(inode, 0);
+ resv_map = (struct resv_map *)inode->i_mapping->private_data;
+ /* root inode doesn't have the resv_map, so we should check it */
+ if (resv_map)
+ resv_map_release(&resv_map->refs);
clear_inode(inode);
}
@@ -463,21 +471,36 @@ static struct inode *hugetlbfs_get_root(struct super_block *sb,
return inode;
}
+/*
+ * Hugetlbfs is not reclaimable; therefore its i_mmap_mutex will never
+ * be taken from reclaim -- unlike regular filesystems. This needs an
+ * annotation because huge_pmd_share() does an allocation under
+ * i_mmap_mutex.
+ */
+static struct lock_class_key hugetlbfs_i_mmap_mutex_key;
+
static struct inode *hugetlbfs_get_inode(struct super_block *sb,
struct inode *dir,
umode_t mode, dev_t dev)
{
struct inode *inode;
+ struct resv_map *resv_map;
+
+ resv_map = resv_map_alloc();
+ if (!resv_map)
+ return NULL;
inode = new_inode(sb);
if (inode) {
struct hugetlbfs_inode_info *info;
inode->i_ino = get_next_ino();
inode_init_owner(inode, dir, mode);
+ lockdep_set_class(&inode->i_mapping->i_mmap_mutex,
+ &hugetlbfs_i_mmap_mutex_key);
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);
+ inode->i_mapping->private_data = resv_map;
info = HUGETLBFS_I(inode);
/*
* The policy is initialized here even if we are creating a
@@ -507,7 +530,9 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
break;
}
lockdep_annotate_inode_mutex_key(inode);
- }
+ } else
+ kref_put(&resv_map->refs, resv_map_release);
+
return inode;
}
@@ -800,8 +825,7 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig)
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",
+ pr_err("Unsupported page size %lu MB\n",
ps >> 20);
return -EINVAL;
}
@@ -809,8 +833,7 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig)
}
default:
- printk(KERN_ERR "hugetlbfs: Bad mount option: \"%s\"\n",
- p);
+ pr_err("Bad mount option: \"%s\"\n", p);
return -EINVAL;
break;
}
@@ -830,8 +853,7 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig)
return 0;
bad_val:
- printk(KERN_ERR "hugetlbfs: Bad value '%s' for mount option '%s'\n",
- args[0].from, p);
+ pr_err("Bad value '%s' for mount option '%s'\n", args[0].from, p);
return -EINVAL;
}
@@ -879,8 +901,7 @@ hugetlbfs_fill_super(struct super_block *sb, void *data, int silent)
goto out_free;
return 0;
out_free:
- if (sbinfo->spool)
- kfree(sbinfo->spool);
+ kfree(sbinfo->spool);
kfree(sbinfo);
return -ENOMEM;
}
@@ -896,6 +917,7 @@ static struct file_system_type hugetlbfs_fs_type = {
.mount = hugetlbfs_mount,
.kill_sb = kill_litter_super,
};
+MODULE_ALIAS_FS("hugetlbfs");
static struct vfsmount *hugetlbfs_vfsmount[HUGE_MAX_HSTATE];
@@ -908,29 +930,30 @@ static int can_do_hugetlb_shm(void)
static int get_hstate_idx(int page_size_log)
{
- struct hstate *h;
+ struct hstate *h = hstate_sizelog(page_size_log);
- 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,
+static const struct dentry_operations anon_ops = {
+ .d_dname = simple_dname
+};
+
+/*
+ * Note that size should be aligned to proper hugepage size in caller side,
+ * otherwise hugetlb_reserve_pages reserves one less hugepages than intended.
+ */
+struct file *hugetlb_file_setup(const char *name, 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 super_block *sb;
struct qstr quick_string;
- struct hstate *hstate;
- unsigned long num_pages;
int hstate_idx;
hstate_idx = get_hstate_idx(page_size_log);
@@ -945,8 +968,7 @@ struct file *hugetlb_file_setup(const char *name, unsigned long addr,
*user = current_user();
if (user_shm_lock(size, *user)) {
task_lock(current);
- printk_once(KERN_WARNING
- "%s (%d): Using mlock ulimits for SHM_HUGETLB is deprecated\n",
+ pr_warn_once("%s (%d): Using mlock ulimits for SHM_HUGETLB is deprecated\n",
current->comm, current->pid);
task_unlock(current);
} else {
@@ -955,36 +977,34 @@ struct file *hugetlb_file_setup(const char *name, unsigned long addr,
}
}
- root = hugetlbfs_vfsmount[hstate_idx]->mnt_root;
+ sb = hugetlbfs_vfsmount[hstate_idx]->mnt_sb;
quick_string.name = name;
quick_string.len = strlen(quick_string.name);
quick_string.hash = 0;
- path.dentry = d_alloc(root, &quick_string);
+ path.dentry = d_alloc_pseudo(sb, &quick_string);
if (!path.dentry)
goto out_shm_unlock;
+ d_set_d_op(path.dentry, &anon_ops);
path.mnt = mntget(hugetlbfs_vfsmount[hstate_idx]);
- error = -ENOSPC;
- inode = hugetlbfs_get_inode(root->d_sb, NULL, S_IFREG | S_IRWXUGO, 0);
+ file = ERR_PTR(-ENOSPC);
+ inode = hugetlbfs_get_inode(sb, NULL, S_IFREG | S_IRWXUGO, 0);
if (!inode)
goto out_dentry;
- hstate = hstate_inode(inode);
- size += addr & ~huge_page_mask(hstate);
- num_pages = ALIGN(size, huge_page_size(hstate)) >>
- huge_page_shift(hstate);
- error = -ENOMEM;
- if (hugetlb_reserve_pages(inode, 0, num_pages, NULL, acctflag))
+ file = ERR_PTR(-ENOMEM);
+ if (hugetlb_reserve_pages(inode, 0,
+ size >> huge_page_shift(hstate_inode(inode)), NULL,
+ acctflag))
goto out_inode;
d_instantiate(path.dentry, inode);
inode->i_size = size;
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;
@@ -998,7 +1018,7 @@ out_shm_unlock:
user_shm_unlock(size, *user);
*user = NULL;
}
- return ERR_PTR(error);
+ return file;
}
static int __init init_hugetlbfs_fs(void)
@@ -1007,6 +1027,11 @@ static int __init init_hugetlbfs_fs(void)
int error;
int i;
+ if (!hugepages_supported()) {
+ pr_info("disabling because there are no supported hugepage sizes\n");
+ return -ENOTSUPP;
+ }
+
error = bdi_init(&hugetlbfs_backing_dev_info);
if (error)
return error;
@@ -1032,7 +1057,7 @@ static int __init init_hugetlbfs_fs(void)
buf);
if (IS_ERR(hugetlbfs_vfsmount[i])) {
- pr_err("hugetlb: Cannot mount internal hugetlbfs for "
+ pr_err("Cannot mount internal hugetlbfs for "
"page size %uK", ps_kb);
error = PTR_ERR(hugetlbfs_vfsmount[i]);
hugetlbfs_vfsmount[i] = NULL;
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-10 18:04:16 +0000