inode.c

	fattr->gencount = nfs_inc_attr_generation_counter();
}

struct nfs_fattr *nfs_alloc_fattr(void)
{
	struct nfs_fattr *fattr;

	fattr = kmalloc(sizeof(*fattr), GFP_NOFS);
	if (fattr != NULL)
		nfs_fattr_init(fattr);
	return fattr;
}

struct nfs_fh *nfs_alloc_fhandle(void)
{
	struct nfs_fh *fh;

	fh = kmalloc(sizeof(struct nfs_fh), GFP_NOFS);
	if (fh != NULL)
		fh->size = 0;
	return fh;
}

/**
 * nfs_inode_attrs_need_update - check if the inode attributes need updating
 * @inode - pointer to inode
 * @fattr - attributes
 *
 * Attempt to divine whether or not an RPC call reply carrying stale
 * attributes got scheduled after another call carrying updated ones.
 *
 * To do so, the function first assumes that a more recent ctime means
 * that the attributes in fattr are newer, however it also attempt to
 * catch the case where ctime either didn't change, or went backwards
 * (if someone reset the clock on the server) by looking at whether
 * or not this RPC call was started after the inode was last updated.
 * Note also the check for wraparound of 'attr_gencount'
 *
 * The function returns 'true' if it thinks the attributes in 'fattr' are
 * more recent than the ones cached in the inode.
 *
 */
static int nfs_inode_attrs_need_update(const struct inode *inode, const struct nfs_fattr *fattr)
{
	const struct nfs_inode *nfsi = NFS_I(inode);

	return ((long)fattr->gencount - (long)nfsi->attr_gencount) > 0 ||
		nfs_ctime_need_update(inode, fattr) ||
		nfs_size_need_update(inode, fattr) ||
		((long)nfsi->attr_gencount - (long)nfs_read_attr_generation_counter() > 0);
}

static int nfs_refresh_inode_locked(struct inode *inode, struct nfs_fattr *fattr)
{
	if (nfs_inode_attrs_need_update(inode, fattr))
		return nfs_update_inode(inode, fattr);
	return nfs_check_inode_attributes(inode, fattr);
}

/**
 * nfs_refresh_inode - try to update the inode attribute cache
 * @inode - pointer to inode
 * @fattr - updated attributes
 *
 * Check that an RPC call that returned attributes has not overlapped with
 * other recent updates of the inode metadata, then decide whether it is
 * safe to do a full update of the inode attributes, or whether just to
 * call nfs_check_inode_attributes.
 */
int nfs_refresh_inode(struct inode *inode, struct nfs_fattr *fattr)
{
	int status;

	if ((fattr->valid & NFS_ATTR_FATTR) == 0)
		return 0;
	spin_lock(&inode->i_lock);
	status = nfs_refresh_inode_locked(inode, fattr);
	spin_unlock(&inode->i_lock);

	return status;
}

static int nfs_post_op_update_inode_locked(struct inode *inode, struct nfs_fattr *fattr)
{
	struct nfs_inode *nfsi = NFS_I(inode);

	nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
	if (S_ISDIR(inode->i_mode))
		nfsi->cache_validity |= NFS_INO_INVALID_DATA;
	if ((fattr->valid & NFS_ATTR_FATTR) == 0)
		return 0;
	return nfs_refresh_inode_locked(inode, fattr);
}

/**
 * nfs_post_op_update_inode - try to update the inode attribute cache
 * @inode - pointer to inode
 * @fattr - updated attributes
 *
 * After an operation that has changed the inode metadata, mark the
 * attribute cache as being invalid, then try to update it.
 *
 * NB: if the server didn't return any post op attributes, this
 * function will force the retrieval of attributes before the next
 * NFS request.  Thus it should be used only for operations that
 * are expected to change one or more attributes, to avoid
 * unnecessary NFS requests and trips through nfs_update_inode().
 */
int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr)
{
	int status;

	spin_lock(&inode->i_lock);
	status = nfs_post_op_update_inode_locked(inode, fattr);
	spin_unlock(&inode->i_lock);
	return status;
}

/**
 * nfs_post_op_update_inode_force_wcc - try to update the inode attribute cache
 * @inode - pointer to inode
 * @fattr - updated attributes
 *
 * After an operation that has changed the inode metadata, mark the
 * attribute cache as being invalid, then try to update it. Fake up
 * weak cache consistency data, if none exist.
 *
 * This function is mainly designed to be used by the ->write_done() functions.
 */
int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fattr)
{
	int status;

	spin_lock(&inode->i_lock);
	/* Don't do a WCC update if these attributes are already stale */
	if ((fattr->valid & NFS_ATTR_FATTR) == 0 ||
			!nfs_inode_attrs_need_update(inode, fattr)) {
		fattr->valid &= ~(NFS_ATTR_FATTR_PRECHANGE
				| NFS_ATTR_FATTR_PRESIZE
				| NFS_ATTR_FATTR_PREMTIME
				| NFS_ATTR_FATTR_PRECTIME);
		goto out_noforce;
	}
	if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 &&
			(fattr->valid & NFS_ATTR_FATTR_PRECHANGE) == 0) {
		fattr->pre_change_attr = NFS_I(inode)->change_attr;
		fattr->valid |= NFS_ATTR_FATTR_PRECHANGE;
	}
	if ((fattr->valid & NFS_ATTR_FATTR_CTIME) != 0 &&
			(fattr->valid & NFS_ATTR_FATTR_PRECTIME) == 0) {
		memcpy(&fattr->pre_ctime, &inode->i_ctime, sizeof(fattr->pre_ctime));
		fattr->valid |= NFS_ATTR_FATTR_PRECTIME;
	}
	if ((fattr->valid & NFS_ATTR_FATTR_MTIME) != 0 &&
			(fattr->valid & NFS_ATTR_FATTR_PREMTIME) == 0) {
		memcpy(&fattr->pre_mtime, &inode->i_mtime, sizeof(fattr->pre_mtime));
		fattr->valid |= NFS_ATTR_FATTR_PREMTIME;
	}
	if ((fattr->valid & NFS_ATTR_FATTR_SIZE) != 0 &&
			(fattr->valid & NFS_ATTR_FATTR_PRESIZE) == 0) {
		fattr->pre_size = i_size_read(inode);
		fattr->valid |= NFS_ATTR_FATTR_PRESIZE;
	}
out_noforce:
	status = nfs_post_op_update_inode_locked(inode, fattr);
	spin_unlock(&inode->i_lock);
	return status;
}

/*
 * Many nfs protocol calls return the new file attributes after
 * an operation.  Here we update the inode to reflect the state
 * of the server's inode.
 *
 * This is a bit tricky because we have to make sure all dirty pages
 * have been sent off to the server before calling invalidate_inode_pages.
 * To make sure no other process adds more write requests while we try
 * our best to flush them, we make them sleep during the attribute refresh.
 *
 * A very similar scenario holds for the dir cache.
 */
static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
{
	struct nfs_server *server;
	struct nfs_inode *nfsi = NFS_I(inode);
	loff_t cur_isize, new_isize;
	unsigned long invalid = 0;
	unsigned long now = jiffies;
	unsigned long save_cache_validity;

	dfprintk(VFS, "NFS: %s(%s/%ld ct=%d info=0x%x)\n",
			__func__, inode->i_sb->s_id, inode->i_ino,
			atomic_read(&inode->i_count), fattr->valid);

	if ((fattr->valid & NFS_ATTR_FATTR_FILEID) && nfsi->fileid != fattr->fileid)
		goto out_fileid;

	/*
	 * Make sure the inode's type hasn't changed.
	 */
	if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && (inode->i_mode & S_IFMT) != (fattr->mode & S_IFMT))
		goto out_changed;

	server = NFS_SERVER(inode);
	/* Update the fsid? */
	if (S_ISDIR(inode->i_mode) && (fattr->valid & NFS_ATTR_FATTR_FSID) &&
			!nfs_fsid_equal(&server->fsid, &fattr->fsid) &&
			!test_bit(NFS_INO_MOUNTPOINT, &nfsi->flags))
		server->fsid = fattr->fsid;

	/*
	 * Update the read time so we don't revalidate too often.
	 */
	nfsi->read_cache_jiffies = fattr->time_start;

	save_cache_validity = nfsi->cache_validity;
	nfsi->cache_validity &= ~(NFS_INO_INVALID_ATTR
			| NFS_INO_INVALID_ATIME
			| NFS_INO_REVAL_FORCED
			| NFS_INO_REVAL_PAGECACHE);

	/* Do atomic weak cache consistency updates */
	nfs_wcc_update_inode(inode, fattr);

	/* More cache consistency checks */
	if (fattr->valid & NFS_ATTR_FATTR_CHANGE) {
		if (nfsi->change_attr != fattr->change_attr) {
			dprintk("NFS: change_attr change on server for file %s/%ld\n",
					inode->i_sb->s_id, inode->i_ino);
			invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
			if (S_ISDIR(inode->i_mode))
				nfs_force_lookup_revalidate(inode);
			nfsi->change_attr = fattr->change_attr;
		}
	} else if (server->caps & NFS_CAP_CHANGE_ATTR)
		invalid |= save_cache_validity;

	if (fattr->valid & NFS_ATTR_FATTR_MTIME) {
		/* NFSv2/v3: Check if the mtime agrees */
		if (!timespec_equal(&inode->i_mtime, &fattr->mtime)) {
			dprintk("NFS: mtime change on server for file %s/%ld\n",
					inode->i_sb->s_id, inode->i_ino);
			invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA;
			if (S_ISDIR(inode->i_mode))
				nfs_force_lookup_revalidate(inode);
			memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime));
		}
	} else if (server->caps & NFS_CAP_MTIME)
		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
				| NFS_INO_INVALID_DATA
				| NFS_INO_REVAL_PAGECACHE
				| NFS_INO_REVAL_FORCED);

	if (fattr->valid & NFS_ATTR_FATTR_CTIME) {
		/* If ctime has changed we should definitely clear access+acl caches */
		if (!timespec_equal(&inode->i_ctime, &fattr->ctime)) {
			invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
			/* and probably clear data for a directory too as utimes can cause
			 * havoc with our cache.
			 */
			if (S_ISDIR(inode->i_mode)) {
				invalid |= NFS_INO_INVALID_DATA;
				nfs_force_lookup_revalidate(inode);
			}
			memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime));
		}
	} else if (server->caps & NFS_CAP_CTIME)
		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
				| NFS_INO_INVALID_ACCESS
				| NFS_INO_INVALID_ACL
				| NFS_INO_REVAL_FORCED);

	/* Check if our cached file size is stale */
	if (fattr->valid & NFS_ATTR_FATTR_SIZE) {
		new_isize = nfs_size_to_loff_t(fattr->size);
		cur_isize = i_size_read(inode);
		if (new_isize != cur_isize) {
			/* Do we perhaps have any outstanding writes, or has
			 * the file grown beyond our last write? */
			if (nfsi->npages == 0 || new_isize > cur_isize) {
				i_size_write(inode, new_isize);
				invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA;
			}
			dprintk("NFS: isize change on server for file %s/%ld\n",
					inode->i_sb->s_id, inode->i_ino);
		}
	} else
		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
				| NFS_INO_REVAL_PAGECACHE
				| NFS_INO_REVAL_FORCED);


	if (fattr->valid & NFS_ATTR_FATTR_ATIME)
		memcpy(&inode->i_atime, &fattr->atime, sizeof(inode->i_atime));
	else if (server->caps & NFS_CAP_ATIME)
		invalid |= save_cache_validity & (NFS_INO_INVALID_ATIME
				| NFS_INO_REVAL_FORCED);

	if (fattr->valid & NFS_ATTR_FATTR_MODE) {
		if ((inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO)) {
			umode_t newmode = inode->i_mode & S_IFMT;
			newmode |= fattr->mode & S_IALLUGO;
			inode->i_mode = newmode;
			invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
		}
	} else if (server->caps & NFS_CAP_MODE)
		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
				| NFS_INO_INVALID_ACCESS
				| NFS_INO_INVALID_ACL
				| NFS_INO_REVAL_FORCED);

	if (fattr->valid & NFS_ATTR_FATTR_OWNER) {
		if (inode->i_uid != fattr->uid) {
			invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
			inode->i_uid = fattr->uid;
		}
	} else if (server->caps & NFS_CAP_OWNER)
		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
				| NFS_INO_INVALID_ACCESS
				| NFS_INO_INVALID_ACL
				| NFS_INO_REVAL_FORCED);

	if (fattr->valid & NFS_ATTR_FATTR_GROUP) {
		if (inode->i_gid != fattr->gid) {
			invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
			inode->i_gid = fattr->gid;
		}
	} else if (server->caps & NFS_CAP_OWNER_GROUP)
		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
				| NFS_INO_INVALID_ACCESS
				| NFS_INO_INVALID_ACL
				| NFS_INO_REVAL_FORCED);

	if (fattr->valid & NFS_ATTR_FATTR_NLINK) {
		if (inode->i_nlink != fattr->nlink) {
			invalid |= NFS_INO_INVALID_ATTR;
			if (S_ISDIR(inode->i_mode))
				invalid |= NFS_INO_INVALID_DATA;
			inode->i_nlink = fattr->nlink;
		}
	} else if (server->caps & NFS_CAP_NLINK)
		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
				| NFS_INO_REVAL_FORCED);

	if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) {
		/*
		 * report the blocks in 512byte units
		 */
		inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used);
 	}
	if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED)
		inode->i_blocks = fattr->du.nfs2.blocks;

	/* Update attrtimeo value if we're out of the unstable period */
	if (invalid & NFS_INO_INVALID_ATTR) {
		nfs_inc_stats(inode, NFSIOS_ATTRINVALIDATE);
		nfsi->attrtimeo = NFS_MINATTRTIMEO(inode);
		nfsi->attrtimeo_timestamp = now;
		nfsi->attr_gencount = nfs_inc_attr_generation_counter();
	} else {
		if (!time_in_range_open(now, nfsi->attrtimeo_timestamp, nfsi->attrtimeo_timestamp + nfsi->attrtimeo)) {
			if ((nfsi->attrtimeo <<= 1) > NFS_MAXATTRTIMEO(inode))
				nfsi->attrtimeo = NFS_MAXATTRTIMEO(inode);
			nfsi->attrtimeo_timestamp = now;
		}
	}
	invalid &= ~NFS_INO_INVALID_ATTR;
	/* Don't invalidate the data if we were to blame */
	if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)
				|| S_ISLNK(inode->i_mode)))
		invalid &= ~NFS_INO_INVALID_DATA;
	if (!nfs_have_delegation(inode, FMODE_READ) ||
			(save_cache_validity & NFS_INO_REVAL_FORCED))
		nfsi->cache_validity |= invalid;

	return 0;
 out_changed:
	/*
	 * Big trouble! The inode has become a different object.
	 */
	printk(KERN_DEBUG "%s: inode %ld mode changed, %07o to %07o\n",
			__func__, inode->i_ino, inode->i_mode, fattr->mode);
 out_err:
	/*
	 * No need to worry about unhashing the dentry, as the
	 * lookup validation will know that the inode is bad.
	 * (But we fall through to invalidate the caches.)
	 */
	nfs_invalidate_inode(inode);
	return -ESTALE;

 out_fileid:
	printk(KERN_ERR "NFS: server %s error: fileid changed\n"
		"fsid %s: expected fileid 0x%Lx, got 0x%Lx\n",
		NFS_SERVER(inode)->nfs_client->cl_hostname, inode->i_sb->s_id,
		(long long)nfsi->fileid, (long long)fattr->fileid);
	goto out_err;
}


#ifdef CONFIG_NFS_V4

/*
 * Clean out any remaining NFSv4 state that might be left over due
 * to open() calls that passed nfs_atomic_lookup, but failed to call
 * nfs_open().
 */
void nfs4_evict_inode(struct inode *inode)
{
	truncate_inode_pages(&inode->i_data, 0);
	end_writeback(inode);
	/* If we are holding a delegation, return it! */
	nfs_inode_return_delegation_noreclaim(inode);
	/* First call standard NFS clear_inode() code */
	nfs_clear_inode(inode);
}
#endif

struct inode *nfs_alloc_inode(struct super_block *sb)
{
	struct nfs_inode *nfsi;
	nfsi = (struct nfs_inode *)kmem_cache_alloc(nfs_inode_cachep, GFP_KERNEL);
	if (!nfsi)
		return NULL;
	nfsi->flags = 0UL;
	nfsi->cache_validity = 0UL;
#ifdef CONFIG_NFS_V3_ACL
	nfsi->acl_access = ERR_PTR(-EAGAIN);
	nfsi->acl_default = ERR_PTR(-EAGAIN);
#endif
#ifdef CONFIG_NFS_V4
	nfsi->nfs4_acl = NULL;
#endif /* CONFIG_NFS_V4 */
	return &nfsi->vfs_inode;
}

void nfs_destroy_inode(struct inode *inode)
{
	kmem_cache_free(nfs_inode_cachep, NFS_I(inode));
}

static inline void nfs4_init_once(struct nfs_inode *nfsi)
{
#ifdef CONFIG_NFS_V4
	INIT_LIST_HEAD(&nfsi->open_states);
	nfsi->delegation = NULL;
	nfsi->delegation_state = 0;
	init_rwsem(&nfsi->rwsem);
#endif
}

static void init_once(void *foo)
{
	struct nfs_inode *nfsi = (struct nfs_inode *) foo;

	inode_init_once(&nfsi->vfs_inode);
	INIT_LIST_HEAD(&nfsi->open_files);
	INIT_LIST_HEAD(&nfsi->access_cache_entry_lru);
	INIT_LIST_HEAD(&nfsi->access_cache_inode_lru);
	INIT_RADIX_TREE(&nfsi->nfs_page_tree, GFP_ATOMIC);
	nfsi->npages = 0;
	nfsi->ncommit = 0;
	atomic_set(&nfsi->silly_count, 1);
	INIT_HLIST_HEAD(&nfsi->silly_list);
	init_waitqueue_head(&nfsi->waitqueue);
	nfs4_init_once(nfsi);
}

static int __init nfs_init_inodecache(void)
{
	nfs_inode_cachep = kmem_cache_create("nfs_inode_cache",
					     sizeof(struct nfs_inode),
					     0, (SLAB_RECLAIM_ACCOUNT|
						SLAB_MEM_SPREAD),
					     init_once);
	if (nfs_inode_cachep == NULL)
		return -ENOMEM;

	return 0;
}

static void nfs_destroy_inodecache(void)
{
	kmem_cache_destroy(nfs_inode_cachep);
}

struct workqueue_struct *nfsiod_workqueue;

/*
 * start up the nfsiod workqueue
 */
static int nfsiod_start(void)
{
	struct workqueue_struct *wq;
	dprintk("RPC:       creating workqueue nfsiod\n");
	wq = create_singlethread_workqueue("nfsiod");
	if (wq == NULL)
		return -ENOMEM;
	nfsiod_workqueue = wq;
	return 0;
}

/*
 * Destroy the nfsiod workqueue
 */
static void nfsiod_stop(void)
{
	struct workqueue_struct *wq;

	wq = nfsiod_workqueue;
	if (wq == NULL)
		return;
	nfsiod_workqueue = NULL;
	destroy_workqueue(wq);
}

/*
 * Initialize NFS
 */
static int __init init_nfs_fs(void)
{
	int err;

	err = nfs_dns_resolver_init();
	if (err < 0)
		goto out8;

	err = nfs_fscache_register();
	if (err < 0)
		goto out7;

	err = nfsiod_start();
	if (err)
		goto out6;

	err = nfs_fs_proc_init();
	if (err)
		goto out5;

	err = nfs_init_nfspagecache();
	if (err)
		goto out4;

	err = nfs_init_inodecache();
	if (err)
		goto out3;

	err = nfs_init_readpagecache();
	if (err)
		goto out2;

	err = nfs_init_writepagecache();
	if (err)
		goto out1;

	err = nfs_init_directcache();
	if (err)
		goto out0;

#ifdef CONFIG_PROC_FS
	rpc_proc_register(&nfs_rpcstat);
#endif
	if ((err = register_nfs_fs()) != 0)
		goto out;
	return 0;
out:
#ifdef CONFIG_PROC_FS
	rpc_proc_unregister("nfs");
#endif
	nfs_destroy_directcache();
out0:
	nfs_destroy_writepagecache();
out1:
	nfs_destroy_readpagecache();
out2:
	nfs_destroy_inodecache();
out3:
	nfs_destroy_nfspagecache();
out4:
	nfs_fs_proc_exit();
out5:
	nfsiod_stop();
out6:
	nfs_fscache_unregister();
out7:
	nfs_dns_resolver_destroy();
out8:
	return err;
}

static void __exit exit_nfs_fs(void)
{
	nfs_destroy_directcache();
	nfs_destroy_writepagecache();
	nfs_destroy_readpagecache();
	nfs_destroy_inodecache();
	nfs_destroy_nfspagecache();
	nfs_fscache_unregister();
	nfs_dns_resolver_destroy();
#ifdef CONFIG_PROC_FS
	rpc_proc_unregister("nfs");
#endif
	unregister_nfs_fs();
	nfs_fs_proc_exit();
	nfsiod_stop();
}

/* Not quite true; I just maintain it */
MODULE_AUTHOR("Olaf Kirch <okir@monad.swb.de>");
MODULE_LICENSE("GPL");
module_param(enable_ino64, bool, 0644);

module_init(init_nfs_fs)
module_exit(exit_nfs_fs)