[linux-2.6-block.git] / fs / orangefs / inode.c

/*
 * (C) 2001 Clemson University and The University of Chicago
 *
 * See COPYING in top-level directory.
 */

/*
 *  Linux VFS inode operations.
 */

#include "protocol.h"
#include "orangefs-kernel.h"
#include "orangefs-bufmap.h"

static int read_one_page(struct page *page)
{
	int ret;
	int max_block;
	ssize_t bytes_read = 0;
	struct inode *inode = page->mapping->host;
	const __u32 blocksize = PAGE_CACHE_SIZE;	/* inode->i_blksize */
	const __u32 blockbits = PAGE_CACHE_SHIFT;	/* inode->i_blkbits */
	struct iov_iter to;
	struct bio_vec bv = {.bv_page = page, .bv_len = PAGE_SIZE};

	iov_iter_bvec(&to, ITER_BVEC | READ, &bv, 1, PAGE_SIZE);

	gossip_debug(GOSSIP_INODE_DEBUG,
		    "orangefs_readpage called with page %p\n",
		     page);

	max_block = ((inode->i_size / blocksize) + 1);

	if (page->index < max_block) {
		loff_t blockptr_offset = (((loff_t) page->index) << blockbits);

		bytes_read = orangefs_inode_read(inode,
						 &to,
						 &blockptr_offset,
						 inode->i_size);
	}
	/* this will only zero remaining unread portions of the page data */
	iov_iter_zero(~0U, &to);
	/* takes care of potential aliasing */
	flush_dcache_page(page);
	if (bytes_read < 0) {
		ret = bytes_read;
		SetPageError(page);
	} else {
		SetPageUptodate(page);
		if (PageError(page))
			ClearPageError(page);
		ret = 0;
	}
	/* unlock the page after the ->readpage() routine completes */
	unlock_page(page);
	return ret;
}

static int orangefs_readpage(struct file *file, struct page *page)
{
	return read_one_page(page);
}

static int orangefs_readpages(struct file *file,
			   struct address_space *mapping,
			   struct list_head *pages,
			   unsigned nr_pages)
{
	int page_idx;
	int ret;

	gossip_debug(GOSSIP_INODE_DEBUG, "orangefs_readpages called\n");

	for (page_idx = 0; page_idx < nr_pages; page_idx++) {
		struct page *page;

		page = list_entry(pages->prev, struct page, lru);
		list_del(&page->lru);
		if (!add_to_page_cache(page,
				       mapping,
				       page->index,
				       GFP_KERNEL)) {
			ret = read_one_page(page);
			gossip_debug(GOSSIP_INODE_DEBUG,
				"failure adding page to cache, read_one_page returned: %d\n",
				ret);
	      } else {
			page_cache_release(page);
	      }
	}
	BUG_ON(!list_empty(pages));
	return 0;
}

static void orangefs_invalidatepage(struct page *page,
				 unsigned int offset,
				 unsigned int length)
{
	gossip_debug(GOSSIP_INODE_DEBUG,
		     "orangefs_invalidatepage called on page %p "
		     "(offset is %u)\n",
		     page,
		     offset);

	ClearPageUptodate(page);
	ClearPageMappedToDisk(page);
	return;

}

static int orangefs_releasepage(struct page *page, gfp_t foo)
{
	gossip_debug(GOSSIP_INODE_DEBUG,
		     "orangefs_releasepage called on page %p\n",
		     page);
	return 0;
}

/*
 * Having a direct_IO entry point in the address_space_operations
 * struct causes the kernel to allows us to use O_DIRECT on
 * open. Nothing will ever call this thing, but in the future we
 * will need to be able to use O_DIRECT on open in order to support
 * AIO. Modeled after NFS, they do this too.
 */
/*
 * static ssize_t orangefs_direct_IO(int rw,
 *			struct kiocb *iocb,
 *			struct iov_iter *iter,
 *			loff_t offset)
 *{
 *	gossip_debug(GOSSIP_INODE_DEBUG,
 *		     "orangefs_direct_IO: %s\n",
 *		     iocb->ki_filp->f_path.dentry->d_name.name);
 *
 *	return -EINVAL;
 *}
 */

struct backing_dev_info orangefs_backing_dev_info = {
	.name = "orangefs",
	.ra_pages = 0,
	.capabilities = BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_WRITEBACK,
};

/** ORANGEFS2 implementation of address space operations */
const struct address_space_operations orangefs_address_operations = {
	.readpage = orangefs_readpage,
	.readpages = orangefs_readpages,
	.invalidatepage = orangefs_invalidatepage,
	.releasepage = orangefs_releasepage,
/*	.direct_IO = orangefs_direct_IO */
};

static int orangefs_setattr_size(struct inode *inode, struct iattr *iattr)
{
	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
	struct orangefs_kernel_op_s *new_op;
	loff_t orig_size;
	int ret = -EINVAL;

	gossip_debug(GOSSIP_INODE_DEBUG,
		     "%s: %pU: Handle is %pU | fs_id %d | size is %llu\n",
		     __func__,
		     get_khandle_from_ino(inode),
		     &orangefs_inode->refn.khandle,
		     orangefs_inode->refn.fs_id,
		     iattr->ia_size);

	/* Ensure that we have a up to date size, so we know if it changed. */
	ret = orangefs_inode_getattr(inode, 0, 1);
	if (ret == -ESTALE)
		ret = -EIO;
	if (ret) {
		gossip_err("%s: orangefs_inode_getattr failed, ret:%d:.\n",
		    __func__, ret);
		return ret;
	}
	orig_size = i_size_read(inode);

	truncate_setsize(inode, iattr->ia_size);

	new_op = op_alloc(ORANGEFS_VFS_OP_TRUNCATE);
	if (!new_op)
		return -ENOMEM;

	new_op->upcall.req.truncate.refn = orangefs_inode->refn;
	new_op->upcall.req.truncate.size = (__s64) iattr->ia_size;

	ret = service_operation(new_op, __func__,
				get_interruptible_flag(inode));

	/*
	 * the truncate has no downcall members to retrieve, but
	 * the status value tells us if it went through ok or not
	 */
	gossip_debug(GOSSIP_INODE_DEBUG,
		     "orangefs: orangefs_truncate got return value of %d\n",
		     ret);

	op_release(new_op);

	if (ret != 0)
		return ret;

	/*
	 * Only change the c/mtime if we are changing the size or we are
	 * explicitly asked to change it.  This handles the semantic difference
	 * between truncate() and ftruncate() as implemented in the VFS.
	 *
	 * The regular truncate() case without ATTR_CTIME and ATTR_MTIME is a
	 * special case where we need to update the times despite not having
	 * these flags set.  For all other operations the VFS set these flags
	 * explicitly if it wants a timestamp update.
	 */
	if (orig_size != i_size_read(inode) &&
	    !(iattr->ia_valid & (ATTR_CTIME | ATTR_MTIME))) {
		iattr->ia_ctime = iattr->ia_mtime =
			current_fs_time(inode->i_sb);
		iattr->ia_valid |= ATTR_CTIME | ATTR_MTIME;
	}

	return ret;
}

/*
 * Change attributes of an object referenced by dentry.
 */
int orangefs_setattr(struct dentry *dentry, struct iattr *iattr)
{
	int ret = -EINVAL;
	struct inode *inode = dentry->d_inode;

	gossip_debug(GOSSIP_INODE_DEBUG,
		     "orangefs_setattr: called on %s\n",
		     dentry->d_name.name);

	ret = inode_change_ok(inode, iattr);
	if (ret)
		goto out;

	if ((iattr->ia_valid & ATTR_SIZE) &&
	    iattr->ia_size != i_size_read(inode)) {
		ret = orangefs_setattr_size(inode, iattr);
		if (ret)
			goto out;
	}

	setattr_copy(inode, iattr);
	mark_inode_dirty(inode);

	ret = orangefs_inode_setattr(inode, iattr);
	gossip_debug(GOSSIP_INODE_DEBUG,
		     "orangefs_setattr: inode_setattr returned %d\n",
		     ret);

	if (!ret && (iattr->ia_valid & ATTR_MODE))
		/* change mod on a file that has ACLs */
		ret = posix_acl_chmod(inode, inode->i_mode);

out:
	gossip_debug(GOSSIP_INODE_DEBUG, "orangefs_setattr: returning %d\n", ret);
	return ret;
}

/*
 * Obtain attributes of an object given a dentry
 */
int orangefs_getattr(struct vfsmount *mnt,
		  struct dentry *dentry,
		  struct kstat *kstat)
{
	int ret = -ENOENT;
	struct inode *inode = dentry->d_inode;
	struct orangefs_inode_s *orangefs_inode = NULL;

	gossip_debug(GOSSIP_INODE_DEBUG,
		     "orangefs_getattr: called on %s\n",
		     dentry->d_name.name);

	ret = orangefs_inode_getattr(inode, 0, 1);
	if (ret == 0) {
		generic_fillattr(inode, kstat);

		/* override block size reported to stat */
		orangefs_inode = ORANGEFS_I(inode);
		kstat->blksize = orangefs_inode->blksize;
	}
	return ret;
}

int orangefs_permission(struct inode *inode, int mask)
{
	int ret;

	if (mask & MAY_NOT_BLOCK)
		return -ECHILD;

	gossip_debug(GOSSIP_INODE_DEBUG, "%s: refreshing\n", __func__);

	/* Make sure the permission (and other common attrs) are up to date. */
	ret = orangefs_inode_getattr(inode, 0, 0);
	if (ret < 0)
		return ret;

	return generic_permission(inode, mask);
}

/* ORANGEDS2 implementation of VFS inode operations for files */
struct inode_operations orangefs_file_inode_operations = {
	.get_acl = orangefs_get_acl,
	.set_acl = orangefs_set_acl,
	.setattr = orangefs_setattr,
	.getattr = orangefs_getattr,
	.setxattr = generic_setxattr,
	.getxattr = generic_getxattr,
	.listxattr = orangefs_listxattr,
	.removexattr = generic_removexattr,
	.permission = orangefs_permission,
};

static int orangefs_init_iops(struct inode *inode)
{
	inode->i_mapping->a_ops = &orangefs_address_operations;

	switch (inode->i_mode & S_IFMT) {
	case S_IFREG:
		inode->i_op = &orangefs_file_inode_operations;
		inode->i_fop = &orangefs_file_operations;
		inode->i_blkbits = PAGE_CACHE_SHIFT;
		break;
	case S_IFLNK:
		inode->i_op = &orangefs_symlink_inode_operations;
		break;
	case S_IFDIR:
		inode->i_op = &orangefs_dir_inode_operations;
		inode->i_fop = &orangefs_dir_operations;
		break;
	default:
		gossip_debug(GOSSIP_INODE_DEBUG,
			     "%s: unsupported mode\n",
			     __func__);
		return -EINVAL;
	}

	return 0;
}

/*
 * Given a ORANGEFS object identifier (fsid, handle), convert it into a ino_t type
 * that will be used as a hash-index from where the handle will
 * be searched for in the VFS hash table of inodes.
 */
static inline ino_t orangefs_handle_hash(struct orangefs_object_kref *ref)
{
	if (!ref)
		return 0;
	return orangefs_khandle_to_ino(&(ref->khandle));
}

/*
 * Called to set up an inode from iget5_locked.
 */
static int orangefs_set_inode(struct inode *inode, void *data)
{
	struct orangefs_object_kref *ref = (struct orangefs_object_kref *) data;
	ORANGEFS_I(inode)->refn.fs_id = ref->fs_id;
	ORANGEFS_I(inode)->refn.khandle = ref->khandle;
	return 0;
}

/*
 * Called to determine if handles match.
 */
static int orangefs_test_inode(struct inode *inode, void *data)
{
	struct orangefs_object_kref *ref = (struct orangefs_object_kref *) data;
	struct orangefs_inode_s *orangefs_inode = NULL;

	orangefs_inode = ORANGEFS_I(inode);
	return (!ORANGEFS_khandle_cmp(&(orangefs_inode->refn.khandle), &(ref->khandle))
		&& orangefs_inode->refn.fs_id == ref->fs_id);
}

/*
 * Front-end to lookup the inode-cache maintained by the VFS using the ORANGEFS
 * file handle.
 *
 * @sb: the file system super block instance.
 * @ref: The ORANGEFS object for which we are trying to locate an inode structure.
 */
struct inode *orangefs_iget(struct super_block *sb, struct orangefs_object_kref *ref)
{
	struct inode *inode = NULL;
	unsigned long hash;
	int error;

	hash = orangefs_handle_hash(ref);
	inode = iget5_locked(sb, hash, orangefs_test_inode, orangefs_set_inode, ref);
	if (!inode || !(inode->i_state & I_NEW))
		return inode;

	error = orangefs_inode_getattr(inode, 1, 0);
	if (error) {
		iget_failed(inode);
		return ERR_PTR(error);
	}

	inode->i_ino = hash;	/* needed for stat etc */
	orangefs_init_iops(inode);
	unlock_new_inode(inode);

	gossip_debug(GOSSIP_INODE_DEBUG,
		     "iget handle %pU, fsid %d hash %ld i_ino %lu\n",
		     &ref->khandle,
		     ref->fs_id,
		     hash,
		     inode->i_ino);

	return inode;
}

/*
 * Allocate an inode for a newly created file and insert it into the inode hash.
 */
struct inode *orangefs_new_inode(struct super_block *sb, struct inode *dir,
		int mode, dev_t dev, struct orangefs_object_kref *ref)
{
	unsigned long hash = orangefs_handle_hash(ref);
	struct inode *inode;
	int error;

	gossip_debug(GOSSIP_INODE_DEBUG,
		     "%s:(sb is %p | MAJOR(dev)=%u | MINOR(dev)=%u mode=%o)\n",
		     __func__,
		     sb,
		     MAJOR(dev),
		     MINOR(dev),
		     mode);

	inode = new_inode(sb);
	if (!inode)
		return NULL;

	orangefs_set_inode(inode, ref);
	inode->i_ino = hash;	/* needed for stat etc */

	error = orangefs_inode_getattr(inode, 1, 0);
	if (error)
		goto out_iput;

	orangefs_init_iops(inode);

	inode->i_mode = mode;
	inode->i_uid = current_fsuid();
	inode->i_gid = current_fsgid();
	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
	inode->i_size = PAGE_CACHE_SIZE;
	inode->i_rdev = dev;

	error = insert_inode_locked4(inode, hash, orangefs_test_inode, ref);
	if (error < 0)
		goto out_iput;

	gossip_debug(GOSSIP_INODE_DEBUG,
		     "Initializing ACL's for inode %pU\n",
		     get_khandle_from_ino(inode));
	orangefs_init_acl(inode, dir);
	return inode;

out_iput:
	iput(inode);
	return ERR_PTR(error);
}
Commit	Line	Data
5db11c21 MM	1	/*
	2	* (C) 2001 Clemson University and The University of Chicago
	3	*
	4	* See COPYING in top-level directory.
	5	*/
	6
	7	/*
	8	* Linux VFS inode operations.
	9	*/
	10
	11	#include "protocol.h"
575e9461 MM	12	#include "orangefs-kernel.h"
575e9461 MM	13	#include "orangefs-bufmap.h"
5db11c21 MM	14
	15	static int read_one_page(struct page *page)
	16	{
5db11c21 MM	17	int ret;
	18	int max_block;
	19	ssize_t bytes_read = 0;
	20	struct inode *inode = page->mapping->host;
	21	const __u32 blocksize = PAGE_CACHE_SIZE; /* inode->i_blksize */
	22	const __u32 blockbits = PAGE_CACHE_SHIFT; /* inode->i_blkbits */
74f68fce AV	23	struct iov_iter to;
	24	struct bio_vec bv = {.bv_page = page, .bv_len = PAGE_SIZE};
	25
	26	iov_iter_bvec(&to, ITER_BVEC \| READ, &bv, 1, PAGE_SIZE);
5db11c21 MM	27
5db11c21 MM	28	gossip_debug(GOSSIP_INODE_DEBUG,
8bb8aefd	29	"orangefs_readpage called with page %p\n",
5db11c21	30	page);
5db11c21 MM	31
	32	max_block = ((inode->i_size / blocksize) + 1);
	33
	34	if (page->index < max_block) {
	35	loff_t blockptr_offset = (((loff_t) page->index) << blockbits);
	36
8bb8aefd YL	37	bytes_read = orangefs_inode_read(inode,
	38	&to,
	39	&blockptr_offset,
	40	inode->i_size);
5db11c21	41	}
74f68fce AV	42	/* this will only zero remaining unread portions of the page data */
74f68fce AV	43	iov_iter_zero(~0U, &to);
5db11c21 MM	44	/* takes care of potential aliasing */
	45	flush_dcache_page(page);
	46	if (bytes_read < 0) {
	47	ret = bytes_read;
	48	SetPageError(page);
	49	} else {
	50	SetPageUptodate(page);
	51	if (PageError(page))
	52	ClearPageError(page);
	53	ret = 0;
	54	}
5db11c21 MM	55	/* unlock the page after the ->readpage() routine completes */
	56	unlock_page(page);
	57	return ret;
	58	}
	59
8bb8aefd	60	static int orangefs_readpage(struct file file, struct page page)
5db11c21 MM	61	{
	62	return read_one_page(page);
	63	}
	64
8bb8aefd	65	static int orangefs_readpages(struct file *file,
5db11c21 MM	66	struct address_space *mapping,
	67	struct list_head *pages,
	68	unsigned nr_pages)
	69	{
	70	int page_idx;
	71	int ret;
	72
8bb8aefd	73	gossip_debug(GOSSIP_INODE_DEBUG, "orangefs_readpages called\n");
5db11c21 MM	74
	75	for (page_idx = 0; page_idx < nr_pages; page_idx++) {
	76	struct page *page;
	77
	78	page = list_entry(pages->prev, struct page, lru);
	79	list_del(&page->lru);
	80	if (!add_to_page_cache(page,
	81	mapping,
	82	page->index,
	83	GFP_KERNEL)) {
	84	ret = read_one_page(page);
	85	gossip_debug(GOSSIP_INODE_DEBUG,
	86	"failure adding page to cache, read_one_page returned: %d\n",
	87	ret);
	88	} else {
	89	page_cache_release(page);
	90	}
	91	}
	92	BUG_ON(!list_empty(pages));
	93	return 0;
	94	}
	95
8bb8aefd	96	static void orangefs_invalidatepage(struct page *page,
5db11c21 MM	97	unsigned int offset,
	98	unsigned int length)
	99	{
	100	gossip_debug(GOSSIP_INODE_DEBUG,
8bb8aefd	101	"orangefs_invalidatepage called on page %p "
5db11c21 MM	102	"(offset is %u)\n",
	103	page,
	104	offset);
	105
	106	ClearPageUptodate(page);
	107	ClearPageMappedToDisk(page);
	108	return;
	109
	110	}
	111
8bb8aefd	112	static int orangefs_releasepage(struct page *page, gfp_t foo)
5db11c21 MM	113	{
5db11c21 MM	114	gossip_debug(GOSSIP_INODE_DEBUG,
8bb8aefd	115	"orangefs_releasepage called on page %p\n",
5db11c21 MM	116	page);
	117	return 0;
	118	}
	119
	120	/*
	121	* Having a direct_IO entry point in the address_space_operations
	122	* struct causes the kernel to allows us to use O_DIRECT on
	123	* open. Nothing will ever call this thing, but in the future we
	124	* will need to be able to use O_DIRECT on open in order to support
	125	* AIO. Modeled after NFS, they do this too.
	126	*/
	127	/*
575e9461	128	* static ssize_t orangefs_direct_IO(int rw,
54804949 MM	129	* struct kiocb *iocb,
	130	* struct iov_iter *iter,
	131	* loff_t offset)
	132	*{
	133	* gossip_debug(GOSSIP_INODE_DEBUG,
8bb8aefd	134	* "orangefs_direct_IO: %s\n",
54804949 MM	135	* iocb->ki_filp->f_path.dentry->d_name.name);
	136	*
	137	* return -EINVAL;
	138	*}
	139	*/
5db11c21	140
8bb8aefd YL	141	struct backing_dev_info orangefs_backing_dev_info = {
8bb8aefd YL	142	.name = "orangefs",
5db11c21 MM	143	.ra_pages = 0,
	144	.capabilities = BDI_CAP_NO_ACCT_DIRTY \| BDI_CAP_NO_WRITEBACK,
	145	};
	146
8bb8aefd YL	147	/** ORANGEFS2 implementation of address space operations */
	148	const struct address_space_operations orangefs_address_operations = {
	149	.readpage = orangefs_readpage,
	150	.readpages = orangefs_readpages,
	151	.invalidatepage = orangefs_invalidatepage,
	152	.releasepage = orangefs_releasepage,
575e9461	153	/* .direct_IO = orangefs_direct_IO */
5db11c21 MM	154	};
5db11c21 MM	155
8bb8aefd	156	static int orangefs_setattr_size(struct inode inode, struct iattr iattr)
5db11c21	157	{
8bb8aefd YL	158	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
8bb8aefd YL	159	struct orangefs_kernel_op_s *new_op;
fecd86aa	160	loff_t orig_size;
5db11c21 MM	161	int ret = -EINVAL;
	162
	163	gossip_debug(GOSSIP_INODE_DEBUG,
	164	"%s: %pU: Handle is %pU \| fs_id %d \| size is %llu\n",
	165	__func__,
	166	get_khandle_from_ino(inode),
8bb8aefd YL	167	&orangefs_inode->refn.khandle,
8bb8aefd YL	168	orangefs_inode->refn.fs_id,
5db11c21 MM	169	iattr->ia_size);
5db11c21 MM	170
fecd86aa MB	171	/* Ensure that we have a up to date size, so we know if it changed. */
	172	ret = orangefs_inode_getattr(inode, 0, 1);
	173	if (ret == -ESTALE)
	174	ret = -EIO;
	175	if (ret) {
	176	gossip_err("%s: orangefs_inode_getattr failed, ret:%d:.\n",
	177	__func__, ret);
	178	return ret;
	179	}
	180	orig_size = i_size_read(inode);
	181
5db11c21 MM	182	truncate_setsize(inode, iattr->ia_size);
5db11c21 MM	183
8bb8aefd	184	new_op = op_alloc(ORANGEFS_VFS_OP_TRUNCATE);
5db11c21 MM	185	if (!new_op)
	186	return -ENOMEM;
	187
8bb8aefd	188	new_op->upcall.req.truncate.refn = orangefs_inode->refn;
5db11c21 MM	189	new_op->upcall.req.truncate.size = (__s64) iattr->ia_size;
	190
	191	ret = service_operation(new_op, __func__,
	192	get_interruptible_flag(inode));
	193
	194	/*
	195	* the truncate has no downcall members to retrieve, but
	196	* the status value tells us if it went through ok or not
	197	*/
	198	gossip_debug(GOSSIP_INODE_DEBUG,
8bb8aefd	199	"orangefs: orangefs_truncate got return value of %d\n",
5db11c21 MM	200	ret);
	201
	202	op_release(new_op);
	203
	204	if (ret != 0)
	205	return ret;
	206
	207	/*
	208	* Only change the c/mtime if we are changing the size or we are
	209	* explicitly asked to change it. This handles the semantic difference
	210	* between truncate() and ftruncate() as implemented in the VFS.
	211	*
	212	* The regular truncate() case without ATTR_CTIME and ATTR_MTIME is a
	213	* special case where we need to update the times despite not having
	214	* these flags set. For all other operations the VFS set these flags
	215	* explicitly if it wants a timestamp update.
	216	*/
	217	if (orig_size != i_size_read(inode) &&
	218	!(iattr->ia_valid & (ATTR_CTIME \| ATTR_MTIME))) {
	219	iattr->ia_ctime = iattr->ia_mtime =
	220	current_fs_time(inode->i_sb);
	221	iattr->ia_valid \|= ATTR_CTIME \| ATTR_MTIME;
	222	}
	223
	224	return ret;
	225	}
	226
	227	/*
	228	* Change attributes of an object referenced by dentry.
	229	*/
8bb8aefd	230	int orangefs_setattr(struct dentry dentry, struct iattr iattr)
5db11c21 MM	231	{
	232	int ret = -EINVAL;
	233	struct inode *inode = dentry->d_inode;
	234
	235	gossip_debug(GOSSIP_INODE_DEBUG,
8bb8aefd	236	"orangefs_setattr: called on %s\n",
5db11c21 MM	237	dentry->d_name.name);
	238
	239	ret = inode_change_ok(inode, iattr);
	240	if (ret)
	241	goto out;
	242
	243	if ((iattr->ia_valid & ATTR_SIZE) &&
	244	iattr->ia_size != i_size_read(inode)) {
8bb8aefd	245	ret = orangefs_setattr_size(inode, iattr);
5db11c21 MM	246	if (ret)
	247	goto out;
	248	}
	249
	250	setattr_copy(inode, iattr);
	251	mark_inode_dirty(inode);
	252
8bb8aefd	253	ret = orangefs_inode_setattr(inode, iattr);
5db11c21	254	gossip_debug(GOSSIP_INODE_DEBUG,
8bb8aefd	255	"orangefs_setattr: inode_setattr returned %d\n",
5db11c21 MM	256	ret);
	257
	258	if (!ret && (iattr->ia_valid & ATTR_MODE))
	259	/* change mod on a file that has ACLs */
	260	ret = posix_acl_chmod(inode, inode->i_mode);
	261
	262	out:
8bb8aefd	263	gossip_debug(GOSSIP_INODE_DEBUG, "orangefs_setattr: returning %d\n", ret);
5db11c21 MM	264	return ret;
	265	}
	266
	267	/*
	268	* Obtain attributes of an object given a dentry
	269	*/
8bb8aefd	270	int orangefs_getattr(struct vfsmount *mnt,
5db11c21 MM	271	struct dentry *dentry,
	272	struct kstat *kstat)
	273	{
	274	int ret = -ENOENT;
	275	struct inode *inode = dentry->d_inode;
8bb8aefd	276	struct orangefs_inode_s *orangefs_inode = NULL;
5db11c21 MM	277
5db11c21 MM	278	gossip_debug(GOSSIP_INODE_DEBUG,
8bb8aefd	279	"orangefs_getattr: called on %s\n",
5db11c21 MM	280	dentry->d_name.name);
5db11c21 MM	281
8f24928d	282	ret = orangefs_inode_getattr(inode, 0, 1);
5db11c21 MM	283	if (ret == 0) {
5db11c21 MM	284	generic_fillattr(inode, kstat);
a7d3e78a	285
5db11c21	286	/* override block size reported to stat */
8bb8aefd YL	287	orangefs_inode = ORANGEFS_I(inode);
8bb8aefd YL	288	kstat->blksize = orangefs_inode->blksize;
5db11c21 MM	289	}
	290	return ret;
	291	}
	292
933287da MB	293	int orangefs_permission(struct inode *inode, int mask)
	294	{
	295	int ret;
	296
	297	if (mask & MAY_NOT_BLOCK)
	298	return -ECHILD;
	299
	300	gossip_debug(GOSSIP_INODE_DEBUG, "%s: refreshing\n", __func__);
	301
	302	/* Make sure the permission (and other common attrs) are up to date. */
8f24928d	303	ret = orangefs_inode_getattr(inode, 0, 0);
933287da MB	304	if (ret < 0)
	305	return ret;
	306
	307	return generic_permission(inode, mask);
	308	}
	309
8bb8aefd YL	310	/* ORANGEDS2 implementation of VFS inode operations for files */
	311	struct inode_operations orangefs_file_inode_operations = {
	312	.get_acl = orangefs_get_acl,
	313	.set_acl = orangefs_set_acl,
	314	.setattr = orangefs_setattr,
	315	.getattr = orangefs_getattr,
5db11c21 MM	316	.setxattr = generic_setxattr,
5db11c21 MM	317	.getxattr = generic_getxattr,
8bb8aefd	318	.listxattr = orangefs_listxattr,
5db11c21	319	.removexattr = generic_removexattr,
933287da	320	.permission = orangefs_permission,
5db11c21 MM	321	};
5db11c21 MM	322
8bb8aefd	323	static int orangefs_init_iops(struct inode *inode)
5db11c21	324	{
8bb8aefd	325	inode->i_mapping->a_ops = &orangefs_address_operations;
5db11c21 MM	326
	327	switch (inode->i_mode & S_IFMT) {
	328	case S_IFREG:
8bb8aefd YL	329	inode->i_op = &orangefs_file_inode_operations;
8bb8aefd YL	330	inode->i_fop = &orangefs_file_operations;
5db11c21 MM	331	inode->i_blkbits = PAGE_CACHE_SHIFT;
	332	break;
	333	case S_IFLNK:
8bb8aefd	334	inode->i_op = &orangefs_symlink_inode_operations;
5db11c21 MM	335	break;
5db11c21 MM	336	case S_IFDIR:
8bb8aefd YL	337	inode->i_op = &orangefs_dir_inode_operations;
8bb8aefd YL	338	inode->i_fop = &orangefs_dir_operations;
5db11c21 MM	339	break;
	340	default:
	341	gossip_debug(GOSSIP_INODE_DEBUG,
	342	"%s: unsupported mode\n",
	343	__func__);
	344	return -EINVAL;
	345	}
	346
	347	return 0;
	348	}
	349
	350	/*
8bb8aefd	351	* Given a ORANGEFS object identifier (fsid, handle), convert it into a ino_t type
5db11c21 MM	352	* that will be used as a hash-index from where the handle will
	353	* be searched for in the VFS hash table of inodes.
	354	*/
8bb8aefd	355	static inline ino_t orangefs_handle_hash(struct orangefs_object_kref *ref)
5db11c21 MM	356	{
	357	if (!ref)
	358	return 0;
8bb8aefd	359	return orangefs_khandle_to_ino(&(ref->khandle));
5db11c21 MM	360	}
	361
	362	/*
	363	* Called to set up an inode from iget5_locked.
	364	*/
8bb8aefd	365	static int orangefs_set_inode(struct inode inode, void data)
5db11c21	366	{
8bb8aefd	367	struct orangefs_object_kref ref = (struct orangefs_object_kref ) data;
a4c680a0 MB	368	ORANGEFS_I(inode)->refn.fs_id = ref->fs_id;
a4c680a0 MB	369	ORANGEFS_I(inode)->refn.khandle = ref->khandle;
5db11c21 MM	370	return 0;
	371	}
	372
	373	/*
	374	* Called to determine if handles match.
	375	*/
8bb8aefd	376	static int orangefs_test_inode(struct inode inode, void data)
5db11c21	377	{
8bb8aefd YL	378	struct orangefs_object_kref ref = (struct orangefs_object_kref ) data;
8bb8aefd YL	379	struct orangefs_inode_s *orangefs_inode = NULL;
5db11c21	380
8bb8aefd YL	381	orangefs_inode = ORANGEFS_I(inode);
	382	return (!ORANGEFS_khandle_cmp(&(orangefs_inode->refn.khandle), &(ref->khandle))
	383	&& orangefs_inode->refn.fs_id == ref->fs_id);
5db11c21 MM	384	}
	385
	386	/*
8bb8aefd	387	* Front-end to lookup the inode-cache maintained by the VFS using the ORANGEFS
5db11c21 MM	388	* file handle.
	389	*
	390	* @sb: the file system super block instance.
8bb8aefd	391	* @ref: The ORANGEFS object for which we are trying to locate an inode structure.
5db11c21	392	*/
8bb8aefd	393	struct inode orangefs_iget(struct super_block sb, struct orangefs_object_kref *ref)
5db11c21 MM	394	{
	395	struct inode *inode = NULL;
	396	unsigned long hash;
	397	int error;
	398
8bb8aefd YL	399	hash = orangefs_handle_hash(ref);
8bb8aefd YL	400	inode = iget5_locked(sb, hash, orangefs_test_inode, orangefs_set_inode, ref);
5db11c21 MM	401	if (!inode \|\| !(inode->i_state & I_NEW))
	402	return inode;
	403
075cca50	404	error = orangefs_inode_getattr(inode, 1, 0);
5db11c21 MM	405	if (error) {
	406	iget_failed(inode);
	407	return ERR_PTR(error);
	408	}
	409
	410	inode->i_ino = hash; /* needed for stat etc */
8bb8aefd	411	orangefs_init_iops(inode);
5db11c21 MM	412	unlock_new_inode(inode);
	413
	414	gossip_debug(GOSSIP_INODE_DEBUG,
	415	"iget handle %pU, fsid %d hash %ld i_ino %lu\n",
	416	&ref->khandle,
	417	ref->fs_id,
	418	hash,
	419	inode->i_ino);
	420
	421	return inode;
	422	}
	423
	424	/*
	425	* Allocate an inode for a newly created file and insert it into the inode hash.
	426	*/
8bb8aefd YL	427	struct inode orangefs_new_inode(struct super_block sb, struct inode *dir,
8bb8aefd YL	428	int mode, dev_t dev, struct orangefs_object_kref *ref)
5db11c21	429	{
8bb8aefd	430	unsigned long hash = orangefs_handle_hash(ref);
5db11c21 MM	431	struct inode *inode;
	432	int error;
	433
	434	gossip_debug(GOSSIP_INODE_DEBUG,
5253487e MM	435	"%s:(sb is %p \| MAJOR(dev)=%u \| MINOR(dev)=%u mode=%o)\n",
5253487e MM	436	__func__,
5db11c21 MM	437	sb,
	438	MAJOR(dev),
	439	MINOR(dev),
	440	mode);
	441
	442	inode = new_inode(sb);
	443	if (!inode)
	444	return NULL;
	445
8bb8aefd	446	orangefs_set_inode(inode, ref);
5db11c21 MM	447	inode->i_ino = hash; /* needed for stat etc */
5db11c21 MM	448
075cca50	449	error = orangefs_inode_getattr(inode, 1, 0);
5db11c21 MM	450	if (error)
	451	goto out_iput;
	452
8bb8aefd	453	orangefs_init_iops(inode);
5db11c21 MM	454
	455	inode->i_mode = mode;
	456	inode->i_uid = current_fsuid();
	457	inode->i_gid = current_fsgid();
	458	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
	459	inode->i_size = PAGE_CACHE_SIZE;
	460	inode->i_rdev = dev;
	461
8bb8aefd	462	error = insert_inode_locked4(inode, hash, orangefs_test_inode, ref);
5db11c21 MM	463	if (error < 0)
	464	goto out_iput;
	465
	466	gossip_debug(GOSSIP_INODE_DEBUG,
	467	"Initializing ACL's for inode %pU\n",
	468	get_khandle_from_ino(inode));
8bb8aefd	469	orangefs_init_acl(inode, dir);
5db11c21 MM	470	return inode;
	471
	472	out_iput:
	473	iput(inode);
	474	return ERR_PTR(error);
	475	}