xen-blkfront.c

来自「linux 内核源代码」· C语言 代码 · 共 985 行 · 第 1/2 页

/*
 * blkfront.c
 *
 * XenLinux virtual block device driver.
 *
 * Copyright (c) 2003-2004, Keir Fraser & Steve Hand
 * Modifications by Mark A. Williamson are (c) Intel Research Cambridge
 * Copyright (c) 2004, Christian Limpach
 * Copyright (c) 2004, Andrew Warfield
 * Copyright (c) 2005, Christopher Clark
 * Copyright (c) 2005, XenSource Ltd
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License version 2
 * as published by the Free Software Foundation; or, when distributed
 * separately from the Linux kernel or incorporated into other
 * software packages, subject to the following license:
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this source file (the "Software"), to deal in the Software without
 * restriction, including without limitation the rights to use, copy, modify,
 * merge, publish, distribute, sublicense, and/or sell copies of the Software,
 * and to permit persons to whom the Software is furnished to do so, subject to
 * the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
 * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
 * IN THE SOFTWARE.
 */

#include <linux/interrupt.h>
#include <linux/blkdev.h>
#include <linux/module.h>

#include <xen/xenbus.h>
#include <xen/grant_table.h>
#include <xen/events.h>
#include <xen/page.h>

#include <xen/interface/grant_table.h>
#include <xen/interface/io/blkif.h>

#include <asm/xen/hypervisor.h>

enum blkif_state {
	BLKIF_STATE_DISCONNECTED,
	BLKIF_STATE_CONNECTED,
	BLKIF_STATE_SUSPENDED,
};

struct blk_shadow {
	struct blkif_request req;
	unsigned long request;
	unsigned long frame[BLKIF_MAX_SEGMENTS_PER_REQUEST];
};

static struct block_device_operations xlvbd_block_fops;

#define BLK_RING_SIZE __RING_SIZE((struct blkif_sring *)0, PAGE_SIZE)

/*
 * We have one of these per vbd, whether ide, scsi or 'other'.  They
 * hang in private_data off the gendisk structure. We may end up
 * putting all kinds of interesting stuff here :-)
 */
struct blkfront_info
{
	struct xenbus_device *xbdev;
	dev_t dev;
	struct gendisk *gd;
	int vdevice;
	blkif_vdev_t handle;
	enum blkif_state connected;
	int ring_ref;
	struct blkif_front_ring ring;
	unsigned int evtchn, irq;
	struct request_queue *rq;
	struct work_struct work;
	struct gnttab_free_callback callback;
	struct blk_shadow shadow[BLK_RING_SIZE];
	unsigned long shadow_free;
	int feature_barrier;

	/**
	 * The number of people holding this device open.  We won't allow a
	 * hot-unplug unless this is 0.
	 */
	int users;
};

static DEFINE_SPINLOCK(blkif_io_lock);

#define MAXIMUM_OUTSTANDING_BLOCK_REQS \
	(BLKIF_MAX_SEGMENTS_PER_REQUEST * BLK_RING_SIZE)
#define GRANT_INVALID_REF	0

#define PARTS_PER_DISK		16

#define BLKIF_MAJOR(dev) ((dev)>>8)
#define BLKIF_MINOR(dev) ((dev) & 0xff)

#define DEV_NAME	"xvd"	/* name in /dev */

/* Information about our VBDs. */
#define MAX_VBDS 64
static LIST_HEAD(vbds_list);

static int get_id_from_freelist(struct blkfront_info *info)
{
	unsigned long free = info->shadow_free;
	BUG_ON(free > BLK_RING_SIZE);
	info->shadow_free = info->shadow[free].req.id;
	info->shadow[free].req.id = 0x0fffffee; /* debug */
	return free;
}

static void add_id_to_freelist(struct blkfront_info *info,
			       unsigned long id)
{
	info->shadow[id].req.id  = info->shadow_free;
	info->shadow[id].request = 0;
	info->shadow_free = id;
}

static void blkif_restart_queue_callback(void *arg)
{
	struct blkfront_info *info = (struct blkfront_info *)arg;
	schedule_work(&info->work);
}

/*
 * blkif_queue_request
 *
 * request block io
 *
 * id: for guest use only.
 * operation: BLKIF_OP_{READ,WRITE,PROBE}
 * buffer: buffer to read/write into. this should be a
 *   virtual address in the guest os.
 */
static int blkif_queue_request(struct request *req)
{
	struct blkfront_info *info = req->rq_disk->private_data;
	unsigned long buffer_mfn;
	struct blkif_request *ring_req;
	struct req_iterator iter;
	struct bio_vec *bvec;
	unsigned long id;
	unsigned int fsect, lsect;
	int ref;
	grant_ref_t gref_head;

	if (unlikely(info->connected != BLKIF_STATE_CONNECTED))
		return 1;

	if (gnttab_alloc_grant_references(
		BLKIF_MAX_SEGMENTS_PER_REQUEST, &gref_head) < 0) {
		gnttab_request_free_callback(
			&info->callback,
			blkif_restart_queue_callback,
			info,
			BLKIF_MAX_SEGMENTS_PER_REQUEST);
		return 1;
	}

	/* Fill out a communications ring structure. */
	ring_req = RING_GET_REQUEST(&info->ring, info->ring.req_prod_pvt);
	id = get_id_from_freelist(info);
	info->shadow[id].request = (unsigned long)req;

	ring_req->id = id;
	ring_req->sector_number = (blkif_sector_t)req->sector;
	ring_req->handle = info->handle;

	ring_req->operation = rq_data_dir(req) ?
		BLKIF_OP_WRITE : BLKIF_OP_READ;
	if (blk_barrier_rq(req))
		ring_req->operation = BLKIF_OP_WRITE_BARRIER;

	ring_req->nr_segments = 0;
	rq_for_each_segment(bvec, req, iter) {
		BUG_ON(ring_req->nr_segments == BLKIF_MAX_SEGMENTS_PER_REQUEST);
		buffer_mfn = pfn_to_mfn(page_to_pfn(bvec->bv_page));
		fsect = bvec->bv_offset >> 9;
		lsect = fsect + (bvec->bv_len >> 9) - 1;
		/* install a grant reference. */
		ref = gnttab_claim_grant_reference(&gref_head);
		BUG_ON(ref == -ENOSPC);

		gnttab_grant_foreign_access_ref(
				ref,
				info->xbdev->otherend_id,
				buffer_mfn,
				rq_data_dir(req) );

		info->shadow[id].frame[ring_req->nr_segments] =
				mfn_to_pfn(buffer_mfn);

		ring_req->seg[ring_req->nr_segments] =
				(struct blkif_request_segment) {
					.gref       = ref,
					.first_sect = fsect,
					.last_sect  = lsect };

		ring_req->nr_segments++;
	}

	info->ring.req_prod_pvt++;

	/* Keep a private copy so we can reissue requests when recovering. */
	info->shadow[id].req = *ring_req;

	gnttab_free_grant_references(gref_head);

	return 0;
}


static inline void flush_requests(struct blkfront_info *info)
{
	int notify;

	RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&info->ring, notify);

	if (notify)
		notify_remote_via_irq(info->irq);
}

/*
 * do_blkif_request
 *  read a block; request is in a request queue
 */
static void do_blkif_request(struct request_queue *rq)
{
	struct blkfront_info *info = NULL;
	struct request *req;
	int queued;

	pr_debug("Entered do_blkif_request\n");

	queued = 0;

	while ((req = elv_next_request(rq)) != NULL) {
		info = req->rq_disk->private_data;
		if (!blk_fs_request(req)) {
			end_request(req, 0);
			continue;
		}

		if (RING_FULL(&info->ring))
			goto wait;

		pr_debug("do_blk_req %p: cmd %p, sec %lx, "
			 "(%u/%li) buffer:%p [%s]\n",
			 req, req->cmd, (unsigned long)req->sector,
			 req->current_nr_sectors,
			 req->nr_sectors, req->buffer,
			 rq_data_dir(req) ? "write" : "read");


		blkdev_dequeue_request(req);
		if (blkif_queue_request(req)) {
			blk_requeue_request(rq, req);
wait:
			/* Avoid pointless unplugs. */
			blk_stop_queue(rq);
			break;
		}

		queued++;
	}

	if (queued != 0)
		flush_requests(info);
}

static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size)
{
	struct request_queue *rq;

	rq = blk_init_queue(do_blkif_request, &blkif_io_lock);
	if (rq == NULL)
		return -1;

	elevator_init(rq, "noop");

	/* Hard sector size and max sectors impersonate the equiv. hardware. */
	blk_queue_hardsect_size(rq, sector_size);
	blk_queue_max_sectors(rq, 512);

	/* Each segment in a request is up to an aligned page in size. */
	blk_queue_segment_boundary(rq, PAGE_SIZE - 1);
	blk_queue_max_segment_size(rq, PAGE_SIZE);

	/* Ensure a merged request will fit in a single I/O ring slot. */
	blk_queue_max_phys_segments(rq, BLKIF_MAX_SEGMENTS_PER_REQUEST);
	blk_queue_max_hw_segments(rq, BLKIF_MAX_SEGMENTS_PER_REQUEST);

	/* Make sure buffer addresses are sector-aligned. */
	blk_queue_dma_alignment(rq, 511);

	gd->queue = rq;

	return 0;
}


static int xlvbd_barrier(struct blkfront_info *info)
{
	int err;

	err = blk_queue_ordered(info->rq,
				info->feature_barrier ? QUEUE_ORDERED_DRAIN : QUEUE_ORDERED_NONE,
				NULL);

	if (err)
		return err;

	printk(KERN_INFO "blkfront: %s: barriers %s\n",
	       info->gd->disk_name,
	       info->feature_barrier ? "enabled" : "disabled");
	return 0;
}


static int xlvbd_alloc_gendisk(int minor, blkif_sector_t capacity,
			       int vdevice, u16 vdisk_info, u16 sector_size,
			       struct blkfront_info *info)
{
	struct gendisk *gd;
	int nr_minors = 1;
	int err = -ENODEV;

	BUG_ON(info->gd != NULL);
	BUG_ON(info->rq != NULL);

	if ((minor % PARTS_PER_DISK) == 0)
		nr_minors = PARTS_PER_DISK;

	gd = alloc_disk(nr_minors);
	if (gd == NULL)
		goto out;

	if (nr_minors > 1)
		sprintf(gd->disk_name, "%s%c", DEV_NAME,
			'a' + minor / PARTS_PER_DISK);
	else
		sprintf(gd->disk_name, "%s%c%d", DEV_NAME,
			'a' + minor / PARTS_PER_DISK,
			minor % PARTS_PER_DISK);

	gd->major = XENVBD_MAJOR;
	gd->first_minor = minor;
	gd->fops = &xlvbd_block_fops;
	gd->private_data = info;
	gd->driverfs_dev = &(info->xbdev->dev);
	set_capacity(gd, capacity);

	if (xlvbd_init_blk_queue(gd, sector_size)) {
		del_gendisk(gd);
		goto out;
	}

	info->rq = gd->queue;
	info->gd = gd;

	if (info->feature_barrier)
		xlvbd_barrier(info);

	if (vdisk_info & VDISK_READONLY)
		set_disk_ro(gd, 1);

	if (vdisk_info & VDISK_REMOVABLE)
		gd->flags |= GENHD_FL_REMOVABLE;

	if (vdisk_info & VDISK_CDROM)
		gd->flags |= GENHD_FL_CD;

	return 0;

 out:
	return err;
}

static void kick_pending_request_queues(struct blkfront_info *info)
{
	if (!RING_FULL(&info->ring)) {
		/* Re-enable calldowns. */
		blk_start_queue(info->rq);
		/* Kick things off immediately. */
		do_blkif_request(info->rq);
	}
}

static void blkif_restart_queue(struct work_struct *work)
{
	struct blkfront_info *info = container_of(work, struct blkfront_info, work);

	spin_lock_irq(&blkif_io_lock);
	if (info->connected == BLKIF_STATE_CONNECTED)
		kick_pending_request_queues(info);
	spin_unlock_irq(&blkif_io_lock);
}

static void blkif_free(struct blkfront_info *info, int suspend)
{
	/* Prevent new requests being issued until we fix things up. */
	spin_lock_irq(&blkif_io_lock);
	info->connected = suspend ?
		BLKIF_STATE_SUSPENDED : BLKIF_STATE_DISCONNECTED;
	/* No more blkif_request(). */
	if (info->rq)
		blk_stop_queue(info->rq);
	/* No more gnttab callback work. */
	gnttab_cancel_free_callback(&info->callback);
	spin_unlock_irq(&blkif_io_lock);

	/* Flush gnttab callback work. Must be done with no locks held. */
	flush_scheduled_work();

	/* Free resources associated with old device channel. */
	if (info->ring_ref != GRANT_INVALID_REF) {
		gnttab_end_foreign_access(info->ring_ref, 0,
					  (unsigned long)info->ring.sring);
		info->ring_ref = GRANT_INVALID_REF;
		info->ring.sring = NULL;
	}
	if (info->irq)
		unbind_from_irqhandler(info->irq, info);
	info->evtchn = info->irq = 0;

}

static void blkif_completion(struct blk_shadow *s)
{
	int i;
	for (i = 0; i < s->req.nr_segments; i++)
		gnttab_end_foreign_access(s->req.seg[i].gref, 0, 0UL);
}

static irqreturn_t blkif_interrupt(int irq, void *dev_id)
{
	struct request *req;
	struct blkif_response *bret;
	RING_IDX i, rp;
	unsigned long flags;
	struct blkfront_info *info = (struct blkfront_info *)dev_id;
	int uptodate;

	spin_lock_irqsave(&blkif_io_lock, flags);

	if (unlikely(info->connected != BLKIF_STATE_CONNECTED)) {
		spin_unlock_irqrestore(&blkif_io_lock, flags);
		return IRQ_HANDLED;
	}

 again:
	rp = info->ring.sring->rsp_prod;
	rmb(); /* Ensure we see queued responses up to 'rp'. */

	for (i = info->ring.rsp_cons; i != rp; i++) {
		unsigned long id;
		int ret;

		bret = RING_GET_RESPONSE(&info->ring, i);
		id   = bret->id;
		req  = (struct request *)info->shadow[id].request;

		blkif_completion(&info->shadow[id]);

		add_id_to_freelist(info, id);

		uptodate = (bret->status == BLKIF_RSP_OKAY);
		switch (bret->operation) {
		case BLKIF_OP_WRITE_BARRIER:
			if (unlikely(bret->status == BLKIF_RSP_EOPNOTSUPP)) {
				printk(KERN_WARNING "blkfront: %s: write barrier op failed\n",
				       info->gd->disk_name);
				uptodate = -EOPNOTSUPP;
				info->feature_barrier = 0;
				xlvbd_barrier(info);
			}
			/* fall through */
		case BLKIF_OP_READ:
		case BLKIF_OP_WRITE:
			if (unlikely(bret->status != BLKIF_RSP_OKAY))