X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=fs%2Fhugetlbfs%2Finode.c;h=a0bbd3d1b41a29338fe9cef80e8da032f44b15fe;hb=597fe76ec36e782aa45b8dac5e12e4dbb0588967;hp=0bea6a619e100e0baa4eee8bc689c935b88ff2cc;hpb=856fc29505556cf263f3dcda2533cf3766c14ab6;p=safe%2Fjmp%2Flinux-2.6 diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 0bea6a6..a0bbd3d 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -13,39 +13,58 @@ #include #include #include +#include #include #include #include #include #include #include +#include #include #include #include -#include +#include +#include #include #include #include #include +#include #include -/* some random number */ -#define HUGETLBFS_MAGIC 0x958458f6 - -static struct super_operations hugetlbfs_ops; +static const struct super_operations hugetlbfs_ops; static const struct address_space_operations hugetlbfs_aops; const struct file_operations hugetlbfs_file_operations; -static struct inode_operations hugetlbfs_dir_inode_operations; -static struct inode_operations hugetlbfs_inode_operations; +static const struct inode_operations hugetlbfs_dir_inode_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_DIRTY | BDI_CAP_NO_WRITEBACK, + .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK, }; int sysctl_hugetlb_shm_group; +enum { + Opt_size, Opt_nr_inodes, + Opt_mode, Opt_uid, Opt_gid, + Opt_pagesize, + Opt_err, +}; + +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}, +}; + static void huge_pagevec_release(struct pagevec *pvec) { int i; @@ -58,35 +77,37 @@ 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_dentry->d_inode; + 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 + * already been checked by prepare_hugepage_range. If you add + * any error returns here, do so after setting VM_HUGETLB, so + * is_vm_hugetlb_page tests below unmap_region go the right + * way when do_mmap_pgoff unwinds (may be important on powerpc + * and ia64). + */ + vma->vm_flags |= VM_HUGETLB | VM_RESERVED; + vma->vm_ops = &hugetlb_vm_ops; - if (vma->vm_pgoff & (HPAGE_SIZE / PAGE_SIZE - 1)) - return -EINVAL; - - if (vma->vm_start & ~HPAGE_MASK) - return -EINVAL; - - if (vma->vm_end & ~HPAGE_MASK) - return -EINVAL; - - if (vma->vm_end - vma->vm_start < HPAGE_SIZE) + if (vma->vm_pgoff & ~(huge_page_mask(h) >> PAGE_SHIFT)) return -EINVAL; vma_len = (loff_t)(vma->vm_end - vma->vm_start); mutex_lock(&inode->i_mutex); 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_MAYSHARE && - hugetlb_reserve_pages(inode, vma->vm_pgoff >> (HPAGE_SHIFT-PAGE_SHIFT), - len >> HPAGE_SHIFT)) + if (hugetlb_reserve_pages(inode, + vma->vm_pgoff >> huge_page_order(h), + len >> huge_page_shift(h), vma, + vma->vm_flags)) goto out; ret = 0; @@ -103,10 +124,7 @@ out: * Called under down_write(mmap_sem). */ -#ifdef HAVE_ARCH_HUGETLB_UNMAPPED_AREA -unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, - unsigned long len, unsigned long pgoff, unsigned long flags); -#else +#ifndef HAVE_ARCH_HUGETLB_UNMAPPED_AREA static unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) @@ -114,14 +132,21 @@ 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); - 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(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)) @@ -134,7 +159,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, 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). */ @@ -152,36 +177,159 @@ full_search: 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 int +hugetlbfs_read_actor(struct page *page, unsigned long offset, + char __user *buf, unsigned long count, + unsigned long size) +{ + char *kaddr; + unsigned long left, copied = 0; + int i, chunksize; + + if (size > count) + size = count; + + /* Find which 4k chunk and offset with in that chunk */ + i = offset >> PAGE_CACHE_SHIFT; + offset = offset & ~PAGE_CACHE_MASK; + + while (size) { + chunksize = PAGE_CACHE_SIZE; + if (offset) + chunksize -= offset; + if (chunksize > size) + chunksize = size; + kaddr = kmap(&page[i]); + left = __copy_to_user(buf, kaddr + offset, chunksize); + kunmap(&page[i]); + if (left) { + copied += (chunksize - left); + break; + } + offset = 0; + size -= chunksize; + buf += chunksize; + copied += chunksize; + i++; + } + return copied ? copied : -EFAULT; +} + /* - * Read a page. Again trivial. If it didn't already exist - * in the page cache, it is zero-filled. + * Support for read() - Find the page attached to f_mapping and copy out the + * data. Its *very* similar to do_generic_mapping_read(), we can't use that + * since it has PAGE_CACHE_SIZE assumptions. */ -static int hugetlbfs_readpage(struct file *file, struct page * page) +static ssize_t hugetlbfs_read(struct file *filp, char __user *buf, + size_t len, loff_t *ppos) { - unlock_page(page); - return -EINVAL; + struct hstate *h = hstate_file(filp); + struct address_space *mapping = filp->f_mapping; + struct inode *inode = mapping->host; + 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; + + 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; + int ra; + + /* nr is the maximum number of bytes to copy from this page */ + nr = huge_page_size(h); + if (index >= end_index) { + if (index > end_index) + goto out; + nr = ((isize - 1) & ~huge_page_mask(h)) + 1; + if (nr <= offset) { + goto out; + } + } + nr = nr - offset; + + /* Find the page */ + page = find_get_page(mapping, index); + if (unlikely(page == NULL)) { + /* + * We have a HOLE, zero out the user-buffer for the + * length of the hole or request. + */ + ret = len < nr ? len : nr; + if (clear_user(buf, ret)) + ra = -EFAULT; + else + ra = 0; + } else { + /* + * We have the page, copy it to user space buffer. + */ + ra = hugetlbfs_read_actor(page, offset, buf, len, nr); + ret = ra; + } + if (ra < 0) { + if (retval == 0) + retval = ra; + if (page) + page_cache_release(page); + goto out; + } + + offset += ret; + retval += ret; + len -= ret; + 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; } -static int hugetlbfs_prepare_write(struct file *file, - struct page *page, unsigned offset, unsigned to) +static int hugetlbfs_write_begin(struct file *file, + struct address_space *mapping, + loff_t pos, unsigned len, unsigned flags, + struct page **pagep, void **fsdata) { return -EINVAL; } -static int hugetlbfs_commit_write(struct file *file, - struct page *page, unsigned offset, unsigned to) +static int hugetlbfs_write_end(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct page *page, void *fsdata) { + BUG(); return -EINVAL; } static void truncate_huge_page(struct page *page) { - clear_page_dirty(page); + cancel_dirty_page(page, /* No IO accounting for huge pages? */0); ClearPageUptodate(page); remove_from_page_cache(page); put_page(page); @@ -189,8 +337,9 @@ static void truncate_huge_page(struct page *page) 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; @@ -214,7 +363,6 @@ static void truncate_hugepages(struct inode *inode, loff_t lstart) ++next; truncate_huge_page(page); unlock_page(page); - hugetlb_put_quota(mapping); freed++; } huge_pagevec_release(&pvec); @@ -231,36 +379,11 @@ static void hugetlbfs_delete_inode(struct inode *inode) 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_LOCK))) - 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) @@ -292,25 +415,20 @@ hugetlb_vmtruncate_list(struct prio_tree_root *root, pgoff_t pgoff) v_offset = 0; __unmap_hugepage_range(vma, - vma->vm_start + v_offset, vma->vm_end); + vma->vm_start + v_offset, vma->vm_end, NULL); } } -/* - * Expanding truncates are not allowed. - */ static int hugetlb_vmtruncate(struct inode *inode, loff_t offset) { pgoff_t pgoff; struct address_space *mapping = inode->i_mapping; + struct hstate *h = hstate_inode(inode); - if (offset > inode->i_size) - return -EINVAL; - - BUG_ON(offset & ~HPAGE_MASK); + BUG_ON(offset & ~huge_page_mask(h)); pgoff = offset >> PAGE_SHIFT; - inode->i_size = offset; + i_size_write(inode, offset); spin_lock(&mapping->i_mmap_lock); if (!prio_tree_empty(&mapping->i_mmap)) hugetlb_vmtruncate_list(&mapping->i_mmap, pgoff); @@ -322,6 +440,7 @@ static int hugetlb_vmtruncate(struct inode *inode, loff_t 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; @@ -333,7 +452,7 @@ static int hugetlbfs_setattr(struct dentry *dentry, struct iattr *attr) 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; @@ -355,13 +474,19 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, uid_t uid, 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); - mpol_shared_policy_init(&info->policy, MPOL_DEFAULT, NULL); + /* + * 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: init_special_inode(inode, mode, dev); @@ -400,9 +525,9 @@ static int hugetlbfs_mknod(struct inode *dir, 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); @@ -435,9 +560,9 @@ static int hugetlbfs_symlink(struct inode *dir, 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; @@ -454,19 +579,23 @@ static int hugetlbfs_symlink(struct inode *dir, } /* - * For direct-IO reads into hugetlb pages + * mark the head page dirty */ static int hugetlbfs_set_page_dirty(struct page *page) { + struct page *head = compound_head(page); + + SetPageDirty(head); return 0; } 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 @@ -518,7 +647,7 @@ static void hugetlbfs_inc_free_inodes(struct hugetlbfs_sb_info *sbinfo) } -static kmem_cache_t *hugetlbfs_inode_cachep; +static struct kmem_cache *hugetlbfs_inode_cachep; static struct inode *hugetlbfs_alloc_inode(struct super_block *sb) { @@ -527,7 +656,7 @@ static struct inode *hugetlbfs_alloc_inode(struct super_block *sb) if (unlikely(!hugetlbfs_dec_free_inodes(sbinfo))) return NULL; - p = kmem_cache_alloc(hugetlbfs_inode_cachep, SLAB_KERNEL); + p = kmem_cache_alloc(hugetlbfs_inode_cachep, GFP_KERNEL); if (unlikely(!p)) { hugetlbfs_inc_free_inodes(sbinfo); return NULL; @@ -543,29 +672,27 @@ static void hugetlbfs_destroy_inode(struct inode *inode) } static const struct address_space_operations hugetlbfs_aops = { - .readpage = hugetlbfs_readpage, - .prepare_write = hugetlbfs_prepare_write, - .commit_write = hugetlbfs_commit_write, + .write_begin = hugetlbfs_write_begin, + .write_end = hugetlbfs_write_end, .set_page_dirty = hugetlbfs_set_page_dirty, }; -static void init_once(void *foo, kmem_cache_t *cachep, unsigned long flags) +static void init_once(void *foo) { struct hugetlbfs_inode_info *ei = (struct hugetlbfs_inode_info *)foo; - if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) == - SLAB_CTOR_CONSTRUCTOR) - inode_init_once(&ei->vfs_inode); + inode_init_once(&ei->vfs_inode); } const struct file_operations hugetlbfs_file_operations = { + .read = hugetlbfs_read, .mmap = hugetlbfs_file_mmap, .fsync = simple_sync_file, .get_unmapped_area = hugetlb_get_unmapped_area, }; -static struct inode_operations hugetlbfs_dir_inode_operations = { +static const struct inode_operations hugetlbfs_dir_inode_operations = { .create = hugetlbfs_create, .lookup = simple_lookup, .link = simple_link, @@ -578,62 +705,113 @@ static struct inode_operations hugetlbfs_dir_inode_operations = { .setattr = hugetlbfs_setattr, }; -static struct inode_operations hugetlbfs_inode_operations = { +static const struct inode_operations hugetlbfs_inode_operations = { .setattr = hugetlbfs_setattr, }; -static struct super_operations hugetlbfs_ops = { +static const struct super_operations hugetlbfs_ops = { .alloc_inode = hugetlbfs_alloc_inode, .destroy_inode = hugetlbfs_destroy_inode, .statfs = hugetlbfs_statfs, .delete_inode = hugetlbfs_delete_inode, .drop_inode = hugetlbfs_drop_inode, .put_super = hugetlbfs_put_super, + .show_options = generic_show_options, }; static int hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig) { - char *opt, *value, *rest; + 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; - while ((opt = strsep(&options, ",")) != NULL) { - if (!*opt) + + while ((p = strsep(&options, ",")) != NULL) { + int token; + if (!*p) continue; - value = strchr(opt, '='); - if (!value || !*value) - return -EINVAL; - else - *value++ = '\0'; - - if (!strcmp(opt, "uid")) - pconfig->uid = simple_strtoul(value, &value, 0); - else if (!strcmp(opt, "gid")) - pconfig->gid = simple_strtoul(value, &value, 0); - else if (!strcmp(opt, "mode")) - pconfig->mode = simple_strtoul(value,&value,0) & 0777U; - else if (!strcmp(opt, "size")) { - unsigned long long size = memparse(value, &rest); - if (*rest == '%') { - size <<= HPAGE_SHIFT; - size *= max_huge_pages; - do_div(size, 100); - rest++; + token = match_token(p, tokens, args); + switch (token) { + case Opt_uid: + if (match_int(&args[0], &option)) + goto bad_val; + pconfig->uid = option; + break; + + case Opt_gid: + if (match_int(&args[0], &option)) + goto bad_val; + pconfig->gid = option; + break; + + case Opt_mode: + if (match_octal(&args[0], &option)) + goto bad_val; + pconfig->mode = option & 01777U; + break; + + case Opt_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); + setsize = SIZE_STD; + if (*rest == '%') + setsize = SIZE_PERCENT; + break; + } + + case Opt_nr_inodes: + /* memparse() will accept a K/M/G without a digit */ + if (!isdigit(*args[0].from)) + goto bad_val; + 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; } - pconfig->nr_blocks = (size >> HPAGE_SHIFT); - value = rest; - } else if (!strcmp(opt,"nr_inodes")) { - pconfig->nr_inodes = memparse(value, &rest); - value = rest; - } else - return -EINVAL; + break; + } - if (*value) + default: + printk(KERN_ERR "hugetlbfs: Bad mount option: \"%s\"\n", + p); return -EINVAL; + 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 -EINVAL; } static int @@ -645,13 +823,15 @@ hugetlbfs_fill_super(struct super_block *sb, void *data, int silent) struct hugetlbfs_config config; struct hugetlbfs_sb_info *sbinfo; + save_mount_options(sb, data); + 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; @@ -659,14 +839,15 @@ hugetlbfs_fill_super(struct super_block *sb, void *data, int silent) 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; @@ -687,15 +868,15 @@ out_free: return -ENOMEM; } -int hugetlb_get_quota(struct address_space *mapping) +int hugetlb_get_quota(struct address_space *mapping, long delta) { 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 > 0) - sbinfo->free_blocks--; + if (sbinfo->free_blocks - delta >= 0) + sbinfo->free_blocks -= delta; else ret = -ENOMEM; spin_unlock(&sbinfo->stat_lock); @@ -704,13 +885,13 @@ int hugetlb_get_quota(struct address_space *mapping) return ret; } -void hugetlb_put_quota(struct address_space *mapping) +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++; + sbinfo->free_blocks += delta; spin_unlock(&sbinfo->stat_lock); } } @@ -731,69 +912,76 @@ static struct vfsmount *hugetlbfs_vfsmount; 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_zero_setup(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; - char buf[16]; - static atomic_t counter; - if (!can_do_hugetlb_shm()) - return ERR_PTR(-EPERM); - - if (!user_shm_lock(size, current->user)) - return ERR_PTR(-ENOMEM); + *user = NULL; + if (!hugetlbfs_vfsmount) + 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"); + } else { + *user = NULL; + return ERR_PTR(-EPERM); + } + } root = hugetlbfs_vfsmount->mnt_root; - snprintf(buf, 16, "%u", atomic_inc_return(&counter)); - quick_string.name = buf; + 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; - error = -ENFILE; - file = get_empty_filp(); - if (!file) - goto out_dentry; - + 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_file; + goto out_dentry; error = -ENOMEM; - if (hugetlb_reserve_pages(inode, 0, size >> HPAGE_SHIFT)) + 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; - file->f_vfsmnt = mntget(hugetlbfs_vfsmount); - file->f_dentry = dentry; - file->f_mapping = inode->i_mapping; - file->f_op = &hugetlbfs_file_operations; - file->f_mode = FMODE_WRITE | FMODE_READ; + + error = -ENFILE; + file = alloc_file(&path, FMODE_WRITE | FMODE_READ, + &hugetlbfs_file_operations); + if (!file) + goto out_dentry; /* inode is already attached */ + return file; out_inode: iput(inode); -out_file: - put_filp(file); 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); } @@ -802,11 +990,15 @@ static int __init init_hugetlbfs_fs(void) int error; struct vfsmount *vfsmount; + error = bdi_init(&hugetlbfs_backing_dev_info); + if (error) + return error; + hugetlbfs_inode_cachep = kmem_cache_create("hugetlbfs_inode_cache", sizeof(struct hugetlbfs_inode_info), - 0, 0, init_once, NULL); + 0, 0, init_once); if (hugetlbfs_inode_cachep == NULL) - return -ENOMEM; + goto out2; error = register_filesystem(&hugetlbfs_fs_type); if (error) @@ -824,6 +1016,8 @@ static int __init init_hugetlbfs_fs(void) out: if (error) kmem_cache_destroy(hugetlbfs_inode_cachep); + out2: + bdi_destroy(&hugetlbfs_backing_dev_info); return error; } @@ -831,6 +1025,7 @@ static void __exit exit_hugetlbfs_fs(void) { kmem_cache_destroy(hugetlbfs_inode_cachep); unregister_filesystem(&hugetlbfs_fs_type); + bdi_destroy(&hugetlbfs_backing_dev_info); } module_init(init_hugetlbfs_fs)