inode.c

static bool nfs_mapping_need_revalidate_inode(struct inode *inode)
{
	if (nfs_have_delegated_attributes(inode))
		return false;
	return (NFS_I(inode)->cache_validity & NFS_INO_REVAL_PAGECACHE)
		|| nfs_attribute_timeout(inode)
		|| NFS_STALE(inode);
}

/**
 * nfs_revalidate_mapping - Revalidate the pagecache
 * @inode - pointer to host inode
 * @mapping - pointer to mapping
 */
int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
{
	struct nfs_inode *nfsi = NFS_I(inode);
	unsigned long *bitlock = &nfsi->flags;
	int ret = 0;

	/* swapfiles are not supposed to be shared. */
	if (IS_SWAPFILE(inode))
		goto out;

	if (nfs_mapping_need_revalidate_inode(inode)) {
		ret = __nfs_revalidate_inode(NFS_SERVER(inode), inode);
		if (ret < 0)
			goto out;
	}

	/*
	 * We must clear NFS_INO_INVALID_DATA first to ensure that
	 * invalidations that come in while we're shooting down the mappings
	 * are respected. But, that leaves a race window where one revalidator
	 * can clear the flag, and then another checks it before the mapping
	 * gets invalidated. Fix that by serializing access to this part of
	 * the function.
	 *
	 * At the same time, we need to allow other tasks to see whether we
	 * might be in the middle of invalidating the pages, so we only set
	 * the bit lock here if it looks like we're going to be doing that.
	 */
	for (;;) {
		ret = wait_on_bit(bitlock, NFS_INO_INVALIDATING,
				  nfs_wait_bit_killable, TASK_KILLABLE);
		if (ret)
			goto out;
		spin_lock(&inode->i_lock);
		if (test_bit(NFS_INO_INVALIDATING, bitlock)) {
			spin_unlock(&inode->i_lock);
			continue;
		}
		if (nfsi->cache_validity & NFS_INO_INVALID_DATA)
			break;
		spin_unlock(&inode->i_lock);
		goto out;
	}

	set_bit(NFS_INO_INVALIDATING, bitlock);
	smp_wmb();
	nfsi->cache_validity &= ~NFS_INO_INVALID_DATA;
	spin_unlock(&inode->i_lock);
	trace_nfs_invalidate_mapping_enter(inode);
	ret = nfs_invalidate_mapping(inode, mapping);
	trace_nfs_invalidate_mapping_exit(inode, ret);

	clear_bit_unlock(NFS_INO_INVALIDATING, bitlock);
	smp_mb__after_clear_bit();
	wake_up_bit(bitlock, NFS_INO_INVALIDATING);
out:
	return ret;
}

static unsigned long nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr)
{
	struct nfs_inode *nfsi = NFS_I(inode);
	unsigned long ret = 0;

	if ((fattr->valid & NFS_ATTR_FATTR_PRECHANGE)
			&& (fattr->valid & NFS_ATTR_FATTR_CHANGE)
			&& inode->i_version == fattr->pre_change_attr) {
		inode->i_version = fattr->change_attr;
		if (S_ISDIR(inode->i_mode))
			nfsi->cache_validity |= NFS_INO_INVALID_DATA;
		ret |= NFS_INO_INVALID_ATTR;
	}
	/* If we have atomic WCC data, we may update some attributes */
	if ((fattr->valid & NFS_ATTR_FATTR_PRECTIME)
			&& (fattr->valid & NFS_ATTR_FATTR_CTIME)
			&& timespec_equal(&inode->i_ctime, &fattr->pre_ctime)) {
		memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime));
		ret |= NFS_INO_INVALID_ATTR;
	}

	if ((fattr->valid & NFS_ATTR_FATTR_PREMTIME)
			&& (fattr->valid & NFS_ATTR_FATTR_MTIME)
			&& timespec_equal(&inode->i_mtime, &fattr->pre_mtime)) {
		memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime));
		if (S_ISDIR(inode->i_mode))
			nfsi->cache_validity |= NFS_INO_INVALID_DATA;
		ret |= NFS_INO_INVALID_ATTR;
	}
	if ((fattr->valid & NFS_ATTR_FATTR_PRESIZE)
			&& (fattr->valid & NFS_ATTR_FATTR_SIZE)
			&& i_size_read(inode) == nfs_size_to_loff_t(fattr->pre_size)
			&& nfsi->npages == 0) {
		i_size_write(inode, nfs_size_to_loff_t(fattr->size));
		ret |= NFS_INO_INVALID_ATTR;
	}

	if (nfsi->cache_validity & NFS_INO_INVALID_DATA)
		nfs_fscache_invalidate(inode);

	return ret;
}

/**
 * nfs_check_inode_attributes - verify consistency of the inode attribute cache
 * @inode - pointer to inode
 * @fattr - updated attributes
 *
 * Verifies the attribute cache. If we have just changed the attributes,
 * so that fattr carries weak cache consistency data, then it may
 * also update the ctime/mtime/change_attribute.
 */
static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fattr)
{
	struct nfs_inode *nfsi = NFS_I(inode);
	loff_t cur_size, new_isize;
	unsigned long invalid = 0;


	if (nfs_have_delegated_attributes(inode))
		return 0;
	/* Has the inode gone and changed behind our back? */
	if ((fattr->valid & NFS_ATTR_FATTR_FILEID) && nfsi->fileid != fattr->fileid)
		return -EIO;
	if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && (inode->i_mode & S_IFMT) != (fattr->mode & S_IFMT))
		return -EIO;

	if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 &&
			inode->i_version != fattr->change_attr)
		invalid |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;

	/* Verify a few of the more important attributes */
	if ((fattr->valid & NFS_ATTR_FATTR_MTIME) && !timespec_equal(&inode->i_mtime, &fattr->mtime))
		invalid |= NFS_INO_INVALID_ATTR;

	if (fattr->valid & NFS_ATTR_FATTR_SIZE) {
		cur_size = i_size_read(inode);
		new_isize = nfs_size_to_loff_t(fattr->size);
		if (cur_size != new_isize && nfsi->npages == 0)
			invalid |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
	}

	/* Have any file permissions changed? */
	if ((fattr->valid & NFS_ATTR_FATTR_MODE) && (inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO))
		invalid |= NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL;
	if ((fattr->valid & NFS_ATTR_FATTR_OWNER) && !uid_eq(inode->i_uid, fattr->uid))
		invalid |= NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL;
	if ((fattr->valid & NFS_ATTR_FATTR_GROUP) && !gid_eq(inode->i_gid, fattr->gid))
		invalid |= NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL;

	/* Has the link count changed? */
	if ((fattr->valid & NFS_ATTR_FATTR_NLINK) && inode->i_nlink != fattr->nlink)
		invalid |= NFS_INO_INVALID_ATTR;

	if ((fattr->valid & NFS_ATTR_FATTR_ATIME) && !timespec_equal(&inode->i_atime, &fattr->atime))
		invalid |= NFS_INO_INVALID_ATIME;

	if (invalid != 0)
		nfsi->cache_validity |= invalid;

	nfsi->read_cache_jiffies = fattr->time_start;
	return 0;
}

static int nfs_ctime_need_update(const struct inode *inode, const struct nfs_fattr *fattr)
{
	if (!(fattr->valid & NFS_ATTR_FATTR_CTIME))
		return 0;
	return timespec_compare(&fattr->ctime, &inode->i_ctime) > 0;
}

static int nfs_size_need_update(const struct inode *inode, const struct nfs_fattr *fattr)
{
	if (!(fattr->valid & NFS_ATTR_FATTR_SIZE))
		return 0;
	return nfs_size_to_loff_t(fattr->size) > i_size_read(inode);
}

static atomic_long_t nfs_attr_generation_counter;

static unsigned long nfs_read_attr_generation_counter(void)
{
	return atomic_long_read(&nfs_attr_generation_counter);
}

unsigned long nfs_inc_attr_generation_counter(void)
{
	return atomic_long_inc_return(&nfs_attr_generation_counter);
}

void nfs_fattr_init(struct nfs_fattr *fattr)
{
	fattr->valid = 0;
	fattr->time_start = jiffies;
	fattr->gencount = nfs_inc_attr_generation_counter();
	fattr->owner_name = NULL;
	fattr->group_name = NULL;
}
EXPORT_SYMBOL_GPL(nfs_fattr_init);

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;
}
EXPORT_SYMBOL_GPL(nfs_alloc_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;
}
EXPORT_SYMBOL_GPL(nfs_alloc_fhandle);

#ifdef NFS_DEBUG
/*
 * _nfs_display_fhandle_hash - calculate the crc32 hash for the filehandle
 *                             in the same way that wireshark does
 *
 * @fh: file handle
 *
 * For debugging only.
 */
u32 _nfs_display_fhandle_hash(const struct nfs_fh *fh)
{
	/* wireshark uses 32-bit AUTODIN crc and does a bitwise
	 * not on the result */
	return nfs_fhandle_hash(fh);
}
EXPORT_SYMBOL_GPL(_nfs_display_fhandle_hash);

/*
 * _nfs_display_fhandle - display an NFS file handle on the console
 *
 * @fh: file handle to display
 * @caption: display caption
 *
 * For debugging only.
 */
void _nfs_display_fhandle(const struct nfs_fh *fh, const char *caption)
{
	unsigned short i;

	if (fh == NULL || fh->size == 0) {
		printk(KERN_DEFAULT "%s at %p is empty\n", caption, fh);
		return;
	}

	printk(KERN_DEFAULT "%s at %p is %u bytes, crc: 0x%08x:\n",
	       caption, fh, fh->size, _nfs_display_fhandle_hash(fh));
	for (i = 0; i < fh->size; i += 16) {
		__be32 *pos = (__be32 *)&fh->data[i];

		switch ((fh->size - i - 1) >> 2) {
		case 0:
			printk(KERN_DEFAULT " %08x\n",
				be32_to_cpup(pos));
			break;
		case 1:
			printk(KERN_DEFAULT " %08x %08x\n",
				be32_to_cpup(pos), be32_to_cpup(pos + 1));
			break;
		case 2:
			printk(KERN_DEFAULT " %08x %08x %08x\n",
				be32_to_cpup(pos), be32_to_cpup(pos + 1),
				be32_to_cpup(pos + 2));
			break;
		default:
			printk(KERN_DEFAULT " %08x %08x %08x %08x\n",
				be32_to_cpup(pos), be32_to_cpup(pos + 1),
				be32_to_cpup(pos + 2), be32_to_cpup(pos + 3));
		}
	}
}
EXPORT_SYMBOL_GPL(_nfs_display_fhandle);
#endif

/**
 * 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);
}

/*
 * Don't trust the change_attribute, mtime, ctime or size if
 * a pnfs LAYOUTCOMMIT is outstanding
 */
static void nfs_inode_attrs_handle_layoutcommit(struct inode *inode,
		struct nfs_fattr *fattr)
{
	if (pnfs_layoutcommit_outstanding(inode))
		fattr->valid &= ~(NFS_ATTR_FATTR_CHANGE |
				NFS_ATTR_FATTR_MTIME |
				NFS_ATTR_FATTR_CTIME |
				NFS_ATTR_FATTR_SIZE);
}

static int nfs_refresh_inode_locked(struct inode *inode, struct nfs_fattr *fattr)
{
	int ret;

	trace_nfs_refresh_inode_enter(inode);

	nfs_inode_attrs_handle_layoutcommit(inode, fattr);

	if (nfs_inode_attrs_need_update(inode, fattr))
		ret = nfs_update_inode(inode, fattr);
	else
		ret = nfs_check_inode_attributes(inode, fattr);

	trace_nfs_refresh_inode_exit(inode, ret);
	return ret;
}

/**
 * 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;
}
EXPORT_SYMBOL_GPL(nfs_refresh_inode);

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;
		nfs_fscache_invalidate(inode);
	}
	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;
}
EXPORT_SYMBOL_GPL(nfs_post_op_update_inode);

/**
 * 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 = inode->i_version;
		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;
}
EXPORT_SYMBOL_GPL(nfs_post_op_update_inode_force_wcc);

/*
 * 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/%lu fh_crc=0x%08x ct=%d info=0x%x)\n",
			__func__, inode->i_sb->s_id, inode->i_ino,
			nfs_display_fhandle_hash(NFS_FH(inode)),
			atomic_read(&inode->i_count), fattr->valid);

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

	/*
	 * 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)) {
		/*
		* Big trouble! The inode has become a different object.
		*/
		printk(KERN_DEBUG "NFS: %s: inode %lu mode changed, %07o to %07o\n",
				__func__, inode->i_ino, inode->i_mode, fattr->mode);
		goto out_err;
	}

	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) &&
			!IS_AUTOMOUNT(inode))
		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 */
	invalid |= nfs_wcc_update_inode(inode, fattr);

	/* More cache consistency checks */
	if (fattr->valid & NFS_ATTR_FATTR_CHANGE) {
		if (inode->i_version != 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
				| NFS_INO_REVAL_PAGECACHE;
			if (S_ISDIR(inode->i_mode))
				nfs_force_lookup_revalidate(inode);
			inode->i_version = fattr->change_attr;
		}
	} else if (server->caps & NFS_CAP_CHANGE_ATTR)
		invalid |= save_cache_validity;

	if (fattr->valid & NFS_ATTR_FATTR_MTIME) {
		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_REVAL_FORCED);

	if (fattr->valid & NFS_ATTR_FATTR_CTIME) {
		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_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 "
					"(%Ld to %Ld)\n",
					inode->i_sb->s_id,
					inode->i_ino,
					(long long)cur_isize,
					(long long)new_isize);
		}
	} 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 (!uid_eq(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 (!gid_eq(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;
			set_nlink(inode, 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_PROTO(inode)->have_delegation(inode, FMODE_READ) ||
			(save_cache_validity & NFS_INO_REVAL_FORCED))
		nfsi->cache_validity |= invalid;

	if (invalid & NFS_INO_INVALID_DATA)
		nfs_fscache_invalidate(inode);

	return 0;
 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;
}

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;
#if IS_ENABLED(CONFIG_NFS_V4)
	nfsi->nfs4_acl = NULL;
#endif /* CONFIG_NFS_V4 */
	return &nfsi->vfs_inode;
}
EXPORT_SYMBOL_GPL(nfs_alloc_inode);

static void nfs_i_callback(struct rcu_head *head)
{
	struct inode *inode = container_of(head, struct inode, i_rcu);
	kmem_cache_free(nfs_inode_cachep, NFS_I(inode));
}

void nfs_destroy_inode(struct inode *inode)
{
	call_rcu(&inode->i_rcu, nfs_i_callback);
}
EXPORT_SYMBOL_GPL(nfs_destroy_inode);

static inline void nfs4_init_once(struct nfs_inode *nfsi)
{
#if IS_ENABLED(CONFIG_NFS_V4)
	INIT_LIST_HEAD(&nfsi->open_states);
	nfsi->delegation = NULL;
	nfsi->delegation_state = 0;
	init_rwsem(&nfsi->rwsem);
	nfsi->layout = NULL;
#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_LIST_HEAD(&nfsi->commit_info.list);
	nfsi->npages = 0;
	nfsi->commit_info.ncommit = 0;
	atomic_set(&nfsi->commit_info.rpcs_out, 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)
{
	/*
	 * Make sure all delayed rcu free inodes are flushed before we
	 * destroy cache.
	 */
	rcu_barrier();
	kmem_cache_destroy(nfs_inode_cachep);
}

struct workqueue_struct *nfsiod_workqueue;
EXPORT_SYMBOL_GPL(nfsiod_workqueue);

/*
 * start up the nfsiod workqueue
 */
static int nfsiod_start(void)
{
	struct workqueue_struct *wq;
	dprintk("RPC:       creating workqueue nfsiod\n");
	wq = alloc_workqueue("nfsiod", WQ_MEM_RECLAIM, 0);
	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);
}

int nfs_net_id;
EXPORT_SYMBOL_GPL(nfs_net_id);

static int nfs_net_init(struct net *net)
{
	nfs_clients_init(net);
	return 0;
}

static void nfs_net_exit(struct net *net)
{
	nfs_cleanup_cb_ident_idr(net);
}

static struct pernet_operations nfs_net_ops = {
	.init = nfs_net_init,
	.exit = nfs_net_exit,
	.id   = &nfs_net_id,
	.size = sizeof(struct nfs_net),
};

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

	err = register_pernet_subsys(&nfs_net_ops);
	if (err < 0)
		goto out9;

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

	err = nfsiod_start();
	if (err)
		goto out7;

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

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

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

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

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

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

#ifdef CONFIG_PROC_FS
	rpc_proc_register(&init_net, &nfs_rpcstat);
#endif
	if ((err = register_nfs_fs()) != 0)
		goto out0;

	return 0;
out0:
#ifdef CONFIG_PROC_FS
	rpc_proc_unregister(&init_net, "nfs");
#endif
	nfs_destroy_directcache();
out1:
	nfs_destroy_writepagecache();
out2:
	nfs_destroy_readpagecache();
out3:
	nfs_destroy_inodecache();
out4:
	nfs_destroy_nfspagecache();
out5:
	nfs_fs_proc_exit();
out6:
	nfsiod_stop();
out7:
	nfs_fscache_unregister();
out8:
	unregister_pernet_subsys(&nfs_net_ops);
out9:
	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();
	unregister_pernet_subsys(&nfs_net_ops);
#ifdef CONFIG_PROC_FS
	rpc_proc_unregister(&init_net, "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)