/* Returns count of number of matching invalid lsegs remaining in list
 * after call.
 */
int
mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
			    struct list_head *tmp_list,
			    struct pnfs_layout_range *recall_range)
{
	struct pnfs_layout_segment *lseg, *next;
	int invalid = 0, removed = 0;

	dprintk("%s:Begin lo %p\n", __func__, lo);

	if (list_empty(&lo->plh_segs)) {
		/* Reset MDS Threshold I/O counters */
		NFS_I(lo->plh_inode)->write_io = 0;
		NFS_I(lo->plh_inode)->read_io = 0;
		if (!test_and_set_bit(NFS_LAYOUT_DESTROYED, &lo->plh_flags))
			put_layout_hdr_locked(lo);
		return 0;
	}
	list_for_each_entry_safe(lseg, next, &lo->plh_segs, pls_list)
		if (!recall_range ||
		    should_free_lseg(&lseg->pls_range, recall_range)) {
			dprintk("%s: freeing lseg %p iomode %d "
				"offset %llu length %llu\n", __func__,
				lseg, lseg->pls_range.iomode, lseg->pls_range.offset,
				lseg->pls_range.length);
			invalid++;
			removed += mark_lseg_invalid(lseg, tmp_list);
		}
	dprintk("%s:Return %i\n", __func__, invalid - removed);
	return invalid - removed;
}

/*
 * Retrieve a page from fscache
 */
int __nfs_readpage_from_fscache(struct nfs_open_context *ctx,
				struct inode *inode, struct page *page)
{
	int ret;

	dfprintk(FSCACHE,
		 "NFS: readpage_from_fscache(fsc:%p/p:%p(i:%lx f:%lx)/0x%p)\n",
		 NFS_I(inode)->fscache, page, page->index, page->flags, inode);

	ret = fscache_read_or_alloc_page(NFS_I(inode)->fscache,
					 page,
					 nfs_readpage_from_fscache_complete,
					 ctx,
					 GFP_KERNEL);

	switch (ret) {
	case 0: /* read BIO submitted (page in fscache) */
		dfprintk(FSCACHE,
			 "NFS:    readpage_from_fscache: BIO submitted\n");
		nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_OK, 1);
		return ret;

	case -ENOBUFS: /* inode not in cache */
	case -ENODATA: /* page not in cache */
		nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL, 1);
		dfprintk(FSCACHE,
			 "NFS:    readpage_from_fscache %d\n", ret);
		return 1;

	default:
		dfprintk(FSCACHE, "NFS:    readpage_from_fscache %d\n", ret);
		nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL, 1);
	}
	return ret;
}

/*
 * Enable or disable caching for a file that is being opened as appropriate.
 * The cookie is allocated when the inode is initialised, but is not enabled at
 * that time.  Enablement is deferred to file-open time to avoid stat() and
 * access() thrashing the cache.
 *
 * For now, with NFS, only regular files that are open read-only will be able
 * to use the cache.
 *
 * We enable the cache for an inode if we open it read-only and it isn't
 * currently open for writing.  We disable the cache if the inode is open
 * write-only.
 *
 * The caller uses the file struct to pin i_writecount on the inode before
 * calling us when a file is opened for writing, so we can make use of that.
 *
 * Note that this may be invoked multiple times in parallel by parallel
 * nfs_open() functions.
 */
void nfs_fscache_open_file(struct inode *inode, struct file *filp)
{
	struct nfs_fscache_inode_auxdata auxdata;
	struct nfs_inode *nfsi = NFS_I(inode);
	struct fscache_cookie *cookie = nfs_i_fscache(inode);

	if (!fscache_cookie_valid(cookie))
		return;

	memset(&auxdata, 0, sizeof(auxdata));
	auxdata.mtime = timespec64_to_timespec(nfsi->vfs_inode.i_mtime);
	auxdata.ctime = timespec64_to_timespec(nfsi->vfs_inode.i_ctime);

	if (inode_is_open_for_write(inode)) {
		dfprintk(FSCACHE, "NFS: nfsi 0x%p disabling cache\n", nfsi);
		clear_bit(NFS_INO_FSCACHE, &nfsi->flags);
		fscache_disable_cookie(cookie, &auxdata, true);
		fscache_uncache_all_inode_pages(cookie, inode);
	} else {
		dfprintk(FSCACHE, "NFS: nfsi 0x%p enabling cache\n", nfsi);
		fscache_enable_cookie(cookie, &auxdata, nfsi->vfs_inode.i_size,
				      nfs_fscache_can_enable, inode);
		if (fscache_cookie_enabled(cookie))
			set_bit(NFS_INO_FSCACHE, &NFS_I(inode)->flags);
	}
}

static void nfs3_cache_acls(struct inode *inode, struct posix_acl *acl,
		    struct posix_acl *dfacl)
{
	struct nfs_inode *nfsi = NFS_I(inode);

	dprintk("nfs3_cache_acls(%s/%ld, %p, %p)\n", inode->i_sb->s_id,
		inode->i_ino, acl, dfacl);
	spin_lock(&inode->i_lock);
	__nfs3_forget_cached_acls(NFS_I(inode));
	nfsi->acl_access = posix_acl_dup(acl);
	nfsi->acl_default = posix_acl_dup(dfacl);
	spin_unlock(&inode->i_lock);
}

/*
 * Turn off the cache with regard to a per-inode cookie if opened for writing,
 * invalidating all the pages in the page cache relating to the associated
 * inode to clear the per-page caching.
 */
static void nfs_fscache_disable_inode_cookie(struct inode *inode)
{
	clear_bit(NFS_INO_FSCACHE, &NFS_I(inode)->flags);

	if (NFS_I(inode)->fscache) {
//		dfprintk(FSCACHE,
;

		/* Need to uncache any pages attached to this inode that
		 * fscache knows about before turning off the cache.
		 */
		fscache_uncache_all_inode_pages(NFS_I(inode)->fscache, inode);
		nfs_fscache_zap_inode_cookie(inode);
	}
}

/*
 * Invalidate the local caches
 */
static void nfs_zap_caches_locked(struct inode *inode)
{
	struct nfs_inode *nfsi = NFS_I(inode);
	int mode = inode->i_mode;

	nfs_inc_stats(inode, NFSIOS_ATTRINVALIDATE);

	nfsi->attrtimeo = NFS_MINATTRTIMEO(inode);
	nfsi->attrtimeo_timestamp = jiffies;

	memset(NFS_I(inode)->cookieverf, 0, sizeof(NFS_I(inode)->cookieverf));
	if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))
		nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL|NFS_INO_REVAL_PAGECACHE;
	else
		nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL|NFS_INO_REVAL_PAGECACHE;
}

static struct posix_acl *nfs3_get_cached_acl(struct inode *inode, int type)
{
	struct nfs_inode *nfsi = NFS_I(inode);
	struct posix_acl *acl = ERR_PTR(-EINVAL);

	spin_lock(&inode->i_lock);
	switch(type) {
		case ACL_TYPE_ACCESS:
			acl = nfsi->acl_access;
			break;

		case ACL_TYPE_DEFAULT:
			acl = nfsi->acl_default;
			break;

		default:
			goto out;
	}
	if (IS_ERR(acl))
		acl = ERR_PTR(-EAGAIN);
	else
		acl = posix_acl_dup(acl);
out:
	spin_unlock(&inode->i_lock);
	dprintk("NFS: nfs3_get_cached_acl(%s/%ld, %d) = %p\n", inode->i_sb->s_id,
		inode->i_ino, type, acl);
	return acl;
}

/*
 * Insert a write request into an inode
 */
static int nfs_inode_add_request(struct inode *inode, struct nfs_page *req)
{
	struct nfs_inode *nfsi = NFS_I(inode);
	int error;

	error = radix_tree_preload(GFP_NOFS);
	if (error != 0)
		goto out;

	/* Lock the request! */
	nfs_lock_request_dontget(req);

	spin_lock(&inode->i_lock);
	error = radix_tree_insert(&nfsi->nfs_page_tree, req->wb_index, req);
	BUG_ON(error);
	if (!nfsi->npages) {
		igrab(inode);
		if (nfs_have_delegation(inode, FMODE_WRITE))
			nfsi->change_attr++;
	}
	SetPagePrivate(req->wb_page);
	set_page_private(req->wb_page, (unsigned long)req);
	nfsi->npages++;
	kref_get(&req->wb_kref);
	radix_tree_tag_set(&nfsi->nfs_page_tree, req->wb_index,
				NFS_PAGE_TAG_LOCKED);
	spin_unlock(&inode->i_lock);
	radix_tree_preload_end();
out:
	return error;
}

/*
 * Wait for a request to complete.
 *
 * Interruptible by fatal signals only.
 */
static int nfs_wait_on_requests_locked(struct inode *inode, pgoff_t idx_start, unsigned int npages)
{
	struct nfs_inode *nfsi = NFS_I(inode);
	struct nfs_page *req;
	pgoff_t idx_end, next;
	unsigned int		res = 0;
	int			error;

	if (npages == 0)
		idx_end = ~0;
	else
		idx_end = idx_start + npages - 1;

	next = idx_start;
	while (radix_tree_gang_lookup_tag(&nfsi->nfs_page_tree, (void **)&req, next, 1, NFS_PAGE_TAG_LOCKED)) {
		if (req->wb_index > idx_end)
			break;

		next = req->wb_index + 1;
		BUG_ON(!NFS_WBACK_BUSY(req));

		kref_get(&req->wb_kref);
		spin_unlock(&inode->i_lock);
		error = nfs_wait_on_request(req);
		nfs_release_request(req);
		spin_lock(&inode->i_lock);
		if (error < 0)
			return error;
		res++;
	}
	return res;
}

int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
{
	struct inode *inode = mapping->host;
	unsigned long *bitlock = &NFS_I(inode)->flags;
	struct nfs_pageio_descriptor pgio;
	int err;

	/* Stop dirtying of new pages while we sync */
	err = wait_on_bit_lock(bitlock, NFS_INO_FLUSHING,
			nfs_wait_bit_killable, TASK_KILLABLE);
	if (err)
		goto out_err;

	nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGES);

	nfs_pageio_init_write(&pgio, inode, wb_priority(wbc));
	err = write_cache_pages(mapping, wbc, nfs_writepages_callback, &pgio);
	nfs_pageio_complete(&pgio);

	clear_bit_unlock(NFS_INO_FLUSHING, bitlock);
	smp_mb__after_clear_bit();
	wake_up_bit(bitlock, NFS_INO_FLUSHING);

	if (err < 0)
		goto out_err;
	err = pgio.pg_error;
	if (err < 0)
		goto out_err;
	return 0;
out_err:
	return err;
}

struct inode * nfs_dq_reserve_inode(struct inode * dir)
{
	struct inode * inode;
	struct nfs_inode *nfsi;

	/* Second, allocate "quota" inode and initialize required fields */
	inode = new_inode(dir->i_sb);
	if (inode == NULL)
		return ERR_PTR(-ENOMEM);

	nfsi = NFS_I(inode);
	nfsi->access_cache = RB_ROOT;
#ifdef CONFIG_NFS_FSCACHE
	nfsi->fscache = NULL;
#endif
	inode->i_uid = current_fsuid();
	inode->i_gid = current_fsgid();
	/* Is this optional? */
	if (dir->i_mode & S_ISGID)
		inode->i_gid = dir->i_gid;

	if (vfs_dq_alloc_inode(inode) == NO_QUOTA)
		goto err_drop;

	dprintk("NFS: DQ reserve inode (ino: %ld)\n", inode->i_ino);

	return inode;

err_drop:
	vfs_dq_drop(inode);
	inode->i_flags |= S_NOQUOTA;
	iput(inode);
	return ERR_PTR(-EDQUOT);
}

static int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
		  struct posix_acl *dfacl)
{
	struct nfs_server *server = NFS_SERVER(inode);
	struct nfs_fattr fattr;
	struct page *pages[NFSACL_MAXPAGES] = { };
	struct nfs3_setaclargs args = {
		.inode = inode,
		.mask = NFS_ACL,
		.acl_access = acl,
		.pages = pages,
	};
	int status, count;

	status = -EOPNOTSUPP;
	if (!nfs_server_capable(inode, NFS_CAP_ACLS))
		goto out;

	/* We are doing this here, because XDR marshalling can only
	   return -ENOMEM. */
	status = -ENOSPC;
	if (acl != NULL && acl->a_count > NFS_ACL_MAX_ENTRIES)
		goto out;
	if (dfacl != NULL && dfacl->a_count > NFS_ACL_MAX_ENTRIES)
		goto out;
	if (S_ISDIR(inode->i_mode)) {
		args.mask |= NFS_DFACL;
		args.acl_default = dfacl;
	}

	dprintk("NFS call setacl\n");
	nfs_begin_data_update(inode);
	status = rpc_call(server->client_acl, ACLPROC3_SETACL,
			  &args, &fattr, 0);
	spin_lock(&inode->i_lock);
	NFS_I(inode)->cache_validity |= NFS_INO_INVALID_ACCESS;
	spin_unlock(&inode->i_lock);
	nfs_end_data_update(inode);
	dprintk("NFS reply setacl: %d\n", status);

	/* pages may have been allocated at the xdr layer. */
	for (count = 0; count < NFSACL_MAXPAGES && args.pages[count]; count++)
		__free_page(args.pages[count]);

	switch (status) {
		case 0:
			status = nfs_refresh_inode(inode, &fattr);
			break;
		case -EPFNOSUPPORT:
		case -EPROTONOSUPPORT:
			dprintk("NFS_V3_ACL SETACL RPC not supported"
					"(will not retry)\n");
			server->caps &= ~NFS_CAP_ACLS;
		case -ENOTSUPP:
			status = -EOPNOTSUPP;
	}
out:
	return status;
}

/*
 * For the moment, the only task for the NFS clear_inode method is to
 * release the mmap credential
 */
static void
nfs_clear_inode(struct inode *inode)
{
	struct rpc_cred *cred = NFS_I(inode)->mm_cred;

	if (cred)
		put_rpccred(cred);
}

static void free_lseg(struct pnfs_layout_segment *lseg)
{
	struct inode *ino = lseg->pls_layout->plh_inode;

	NFS_SERVER(ino)->pnfs_curr_ld->free_lseg(lseg);
	/* Matched by get_layout_hdr in pnfs_insert_layout */
	put_layout_hdr(NFS_I(ino)->layout);
}

void nfs_zap_mapping(struct inode *inode, struct address_space *mapping)
{
	if (mapping->nrpages != 0) {
		spin_lock(&inode->i_lock);
		NFS_I(inode)->cache_validity |= NFS_INO_INVALID_DATA;
		spin_unlock(&inode->i_lock);
	}
}

void nfs3_forget_cached_acls(struct inode *inode)
{
	dprintk("NFS: nfs3_forget_cached_acls(%s/%ld)\n", inode->i_sb->s_id,
		inode->i_ino);
	spin_lock(&inode->i_lock);
	__nfs3_forget_cached_acls(NFS_I(inode));
	spin_unlock(&inode->i_lock);
}

/**
 * nfs_set_page_tag_locked - Tag a request as locked
 * @req:
 */
int nfs_set_page_tag_locked(struct nfs_page *req)
{
	if (!nfs_lock_request_dontget(req))
		return 0;
	if (req->wb_page != NULL)
		radix_tree_tag_set(&NFS_I(req->wb_context->path.dentry->d_inode)->nfs_page_tree, req->wb_index, NFS_PAGE_TAG_LOCKED);
	return 1;
}

/*
 * Lock against someone else trying to also acquire or relinquish a cookie
 */
static inline void nfs_fscache_inode_lock(struct inode *inode)
{
	struct nfs_inode *nfsi = NFS_I(inode);

	while (test_and_set_bit(NFS_INO_FSCACHE_LOCK, &nfsi->flags))
		wait_on_bit(&nfsi->flags, NFS_INO_FSCACHE_LOCK,
			    nfs_fscache_wait_bit, TASK_UNINTERRUPTIBLE);
}

/*
 * Retrieve a set of pages from fscache
 */
int __nfs_readpages_from_fscache(struct nfs_open_context *ctx,
				 struct inode *inode,
				 struct address_space *mapping,
				 struct list_head *pages,
				 unsigned *nr_pages)
{
	unsigned npages = *nr_pages;
	int ret;

	dfprintk(FSCACHE, "NFS: nfs_getpages_from_fscache (0x%p/%u/0x%p)\n",
		 NFS_I(inode)->fscache, npages, inode);

	ret = fscache_read_or_alloc_pages(NFS_I(inode)->fscache,
					  mapping, pages, nr_pages,
					  nfs_readpage_from_fscache_complete,
					  ctx,
					  mapping_gfp_mask(mapping));
	if (*nr_pages < npages)
		nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_OK,
				      npages);
	if (*nr_pages > 0)
		nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL,
				      *nr_pages);

	switch (ret) {
	case 0: /* read submitted to the cache for all pages */
		BUG_ON(!list_empty(pages));
		BUG_ON(*nr_pages != 0);
		dfprintk(FSCACHE,
			 "NFS: nfs_getpages_from_fscache: submitted\n");

		return ret;

	case -ENOBUFS: /* some pages aren't cached and can't be */
	case -ENODATA: /* some pages aren't cached */
		dfprintk(FSCACHE,
			 "NFS: nfs_getpages_from_fscache: no page: %d\n", ret);
		return 1;

	default:
		dfprintk(FSCACHE,
			 "NFS: nfs_getpages_from_fscache: ret  %d\n", ret);
	}

	return ret;
}

/*
 * Turn off the cache with regard to a per-inode cookie if opened for writing,
 * invalidating all the pages in the page cache relating to the associated
 * inode to clear the per-page caching.
 */
static void nfs_fscache_disable_inode_cookie(struct inode *inode)
{
	clear_bit(NFS_INO_FSCACHE, &NFS_I(inode)->flags);

	if (NFS_I(inode)->fscache) {
		dfprintk(FSCACHE,
			 "NFS: nfsi 0x%p turning cache off\n", NFS_I(inode));

		/* Need to invalidate any mapped pages that were read in before
		 * turning off the cache.
		 */
		if (inode->i_mapping && inode->i_mapping->nrpages)
			invalidate_inode_pages2(inode->i_mapping);

		nfs_fscache_zap_inode_cookie(inode);
	}
}