path: root/fs/nfs/blocklayout/blocklayout.c

/*
 *  linux/fs/nfs/blocklayout/blocklayout.c
 *
 *  Module for the NFSv4.1 pNFS block layout driver.
 *
 *  Copyright (c) 2006 The Regents of the University of Michigan.
 *  All rights reserved.
 *
 *  Andy Adamson <andros@citi.umich.edu>
 *  Fred Isaman <iisaman@umich.edu>
 *
 * permission is granted to use, copy, create derivative works and
 * redistribute this software and such derivative works for any purpose,
 * so long as the name of the university of michigan is not used in
 * any advertising or publicity pertaining to the use or distribution
 * of this software without specific, written prior authorization.  if
 * the above copyright notice or any other identification of the
 * university of michigan is included in any copy of any portion of
 * this software, then the disclaimer below must also be included.
 *
 * this software is provided as is, without representation from the
 * university of michigan as to its fitness for any purpose, and without
 * warranty by the university of michigan of any kind, either express
 * or implied, including without limitation the implied warranties of
 * merchantability and fitness for a particular purpose.  the regents
 * of the university of michigan shall not be liable for any damages,
 * including special, indirect, incidental, or consequential damages,
 * with respect to any claim arising out or in connection with the use
 * of the software, even if it has been or is hereafter advised of the
 * possibility of such damages.
 */

#include <linux/module.h>
#include <linux/init.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/bio.h>		/* struct bio */
#include <linux/prefetch.h>
#include <linux/pagevec.h>

#include "../pnfs.h"
#include "../nfs4session.h"
#include "../internal.h"
#include "blocklayout.h"

#define NFSDBG_FACILITY	NFSDBG_PNFS_LD

MODULE_LICENSE("GPL");
MODULE_AUTHOR("Andy Adamson <andros@citi.umich.edu>");
MODULE_DESCRIPTION("The NFSv4.1 pNFS Block layout driver");

static bool is_hole(struct pnfs_block_extent *be)
{
	switch (be->be_state) {
	case PNFS_BLOCK_NONE_DATA:
		return true;
	case PNFS_BLOCK_INVALID_DATA:
		return be->be_tag ? false : true;
	default:
		return false;
	}
}

/* The data we are handed might be spread across several bios.  We need
 * to track when the last one is finished.
 */
struct parallel_io {
	struct kref refcnt;
	void (*pnfs_callback) (void *data);
	void *data;
};

static inline struct parallel_io *alloc_parallel(void *data)
{
	struct parallel_io *rv;

	rv  = kmalloc(sizeof(*rv), GFP_NOFS);
	if (rv) {
		rv->data = data;
		kref_init(&rv->refcnt);
	}
	return rv;
}

static inline void get_parallel(struct parallel_io *p)
{
	kref_get(&p->refcnt);
}

static void destroy_parallel(struct kref *kref)
{
	struct parallel_io *p = container_of(kref, struct parallel_io, refcnt);

	dprintk("%s enter\n", __func__);
	p->pnfs_callback(p->data);
	kfree(p);
}

static inline void put_parallel(struct parallel_io *p)
{
	kref_put(&p->refcnt, destroy_parallel);
}

static struct bio *
bl_submit_bio(struct bio *bio)
{
	if (bio) {
		get_parallel(bio->bi_private);
		dprintk("%s submitting %s bio %u@%llu\n", __func__,
			bio_op(bio) == READ ? "read" : "write",
			bio->bi_iter.bi_size,
			(unsigned long long)bio->bi_iter.bi_sector);
		submit_bio(bio);
	}
	return NULL;
}

static bool offset_in_map(u64 offset, struct pnfs_block_dev_map *map)
{
	return offset >= map->start && offset < map->start + map->len;
}

static struct bio *
do_add_page_to_bio(struct bio *bio, int npg, enum req_op op, sector_t isect,
		struct page *page, struct pnfs_block_dev_map *map,
		struct pnfs_block_extent *be, bio_end_io_t end_io,
		struct parallel_io *par, unsigned int offset, int *len)
{
	struct pnfs_block_dev *dev =
		container_of(be->be_device, struct pnfs_block_dev, node);
	u64 disk_addr, end;

	dprintk("%s: npg %d rw %d isect %llu offset %u len %d\n", __func__,
		npg, (__force u32)op, (unsigned long long)isect, offset, *len);

	/* translate to device offset */
	isect += be->be_v_offset;
	isect -= be->be_f_offset;

	/* translate to physical disk offset */
	disk_addr = (u64)isect << SECTOR_SHIFT;
	if (!offset_in_map(disk_addr, map)) {
		if (!dev->map(dev, disk_addr, map) || !offset_in_map(disk_addr, map))
			return ERR_PTR(-EIO);
		bio = bl_submit_bio(bio);
	}
	disk_addr += map->disk_offset;
	disk_addr -= map->start;

	/* limit length to what the device mapping allows */
	end = disk_addr + *len;
	if (end >= map->start + map->len)
		*len = map->start + map->len - disk_addr;

retry:
	if (!bio) {
		bio = bio_alloc(map->bdev, bio_max_segs(npg), op, GFP_NOIO);
		bio->bi_iter.bi_sector = disk_addr >> SECTOR_SHIFT;
		bio->bi_end_io = end_io;
		bio->bi_private = par;
	}
	if (bio_add_page(bio, page, *len, offset) < *len) {
		bio = bl_submit_bio(bio);
		goto retry;
	}
	return bio;
}

static void bl_mark_devices_unavailable(struct nfs_pgio_header *header, bool rw)
{
	struct pnfs_block_layout *bl = BLK_LSEG2EXT(header->lseg);
	size_t bytes_left = header->