vserver 1.9.5.x5

[linux-2.6.git] / fs / hugetlbfs / inode.c

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 4ec4283..7a006cc 100644 (file)
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -52,6 +52,9 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
        loff_t len, vma_len;
        int ret;
 
+       if ((vma->vm_flags & (VM_MAYSHARE | VM_WRITE)) == VM_WRITE)
+               return -EINVAL;
+
        if (vma->vm_pgoff & (HPAGE_SIZE / PAGE_SIZE - 1))
                return -EINVAL;
 
@@ -70,10 +73,19 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
        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;
+
        ret = hugetlb_prefault(mapping, vma);
-       len = vma_len + ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
-       if (ret == 0 && inode->i_size < len)
+       if (ret)
+               goto out;
+
+       if (inode->i_size < len)
                inode->i_size = len;
+out:
        up(&inode->i_sem);
 
        return ret;
@@ -93,6 +105,7 @@ 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;
 
        if (len & ~HPAGE_MASK)
                return -EINVAL;
@@ -107,12 +120,25 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
                        return addr;
        }
 
-       addr = ALIGN(mm->free_area_cache, HPAGE_SIZE);
+       start_addr = mm->free_area_cache;
+
+full_search:
+       addr = ALIGN(start_addr, HPAGE_SIZE);
 
        for (vma = find_vma(mm, addr); ; vma = vma->vm_next) {
                /* At this point:  (!vma || addr < vma->vm_end). */
-               if (TASK_SIZE - len < addr)
+               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, HPAGE_SIZE);
@@ -142,7 +168,7 @@ static int hugetlbfs_commit_write(struct file *file,
        return -EINVAL;
 }
 
-void huge_pagevec_release(struct pagevec *pvec)
+static void huge_pagevec_release(struct pagevec *pvec)
 {
        int i;
 
@@ -152,7 +178,7 @@ void huge_pagevec_release(struct pagevec *pvec)
        pagevec_reinit(pvec);
 }
 
-void truncate_huge_page(struct page *page)
+static void truncate_huge_page(struct page *page)
 {
        clear_page_dirty(page);
        ClearPageUptodate(page);
@@ -160,7 +186,7 @@ void truncate_huge_page(struct page *page)
        put_page(page);
 }
 
-void truncate_hugepages(struct address_space *mapping, loff_t lstart)
+static void truncate_hugepages(struct address_space *mapping, loff_t lstart)
 {
        const pgoff_t start = lstart >> HPAGE_SHIFT;
        struct pagevec pvec;
@@ -199,6 +225,7 @@ static void hugetlbfs_delete_inode(struct inode *inode)
 
        hlist_del_init(&inode->i_hash);
        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);
@@ -241,6 +268,7 @@ static void hugetlbfs_forget_inode(struct inode *inode)
        hlist_del_init(&inode->i_hash);
 out_truncate:
        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);
@@ -272,11 +300,10 @@ static void hugetlbfs_drop_inode(struct inode *inode)
 static inline void
 hugetlb_vmtruncate_list(struct prio_tree_root *root, unsigned long h_pgoff)
 {
-       struct vm_area_struct *vma = NULL;
+       struct vm_area_struct *vma;
        struct prio_tree_iter iter;
 
-       while ((vma = vma_prio_tree_next(vma, root, &iter,
-                                       h_pgoff, ULONG_MAX)) != NULL) {
+       vma_prio_tree_foreach(vma, &iter, root, h_pgoff, ULONG_MAX) {
                unsigned long h_vm_pgoff;
                unsigned long v_length;
                unsigned long v_offset;
@@ -468,7 +495,7 @@ static int hugetlbfs_symlink(struct inode *dir,
 /*
  * For direct-IO reads into hugetlb pages
  */
-int hugetlbfs_set_page_dirty(struct page *page)
+static int hugetlbfs_set_page_dirty(struct page *page)
 {
        return 0;
 }
@@ -640,10 +667,12 @@ hugetlbfs_fill_super(struct super_block *sb, void *data, int silent)
        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_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)
@@ -708,7 +737,7 @@ static struct vfsmount *hugetlbfs_vfsmount;
  */
 static unsigned long hugetlbfs_counter(void)
 {
-       static spinlock_t lock = SPIN_LOCK_UNLOCKED;
+       static DEFINE_SPINLOCK(lock);
        static unsigned long counter;
        unsigned long ret;
 
@@ -721,12 +750,13 @@ static unsigned long hugetlbfs_counter(void)
 static int can_do_hugetlb_shm(void)
 {
        return likely(capable(CAP_IPC_LOCK) ||
-                       in_group_p(sysctl_hugetlb_shm_group));
+                       in_group_p(sysctl_hugetlb_shm_group) ||
+                       can_do_mlock());
 }
 
 struct file *hugetlb_zero_setup(size_t size)
 {
-       int error;
+       int error = -ENOMEM;
        struct file *file;
        struct inode *inode;
        struct dentry *dentry, *root;
@@ -739,6 +769,9 @@ struct file *hugetlb_zero_setup(size_t size)
        if (!is_hugepage_mem_enough(size))
                return ERR_PTR(-ENOMEM);
 
+       if (!user_shm_lock(size, current->user))
+               return ERR_PTR(-ENOMEM);
+
        root = hugetlbfs_vfsmount->mnt_root;
        snprintf(buf, 16, "%lu", hugetlbfs_counter());
        quick_string.name = buf;
@@ -746,7 +779,7 @@ struct file *hugetlb_zero_setup(size_t size)
        quick_string.hash = 0;
        dentry = d_alloc(root, &quick_string);
        if (!dentry)
-               return ERR_PTR(-ENOMEM);
+               goto out_shm_unlock;
 
        error = -ENFILE;
        file = get_empty_filp();
@@ -773,6 +806,8 @@ out_file:
        put_filp(file);
 out_dentry:
        dput(dentry);
+out_shm_unlock:
+       user_shm_unlock(size, current->user);
        return ERR_PTR(error);
 }
 
@@ -783,8 +818,7 @@ static int __init init_hugetlbfs_fs(void)
 
        hugetlbfs_inode_cachep = kmem_cache_create("hugetlbfs_inode_cache",
                                        sizeof(struct hugetlbfs_inode_info),
-                                       0, SLAB_RECLAIM_ACCOUNT,
-                                       init_once, NULL);
+                                       0, 0, init_once, NULL);
        if (hugetlbfs_inode_cachep == NULL)
                return -ENOMEM;