X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=drivers%2Fblock%2Fxen-blkfront.c;h=05a31e55d27817bed3f8157c91389c31f0adb1f8;hb=dc2ed5e3c963490a4fe934b482537d1274961ecb;hp=d771da816d95d708cff253e41e3a6ab05cd9d930;hpb=4f93f09b72d6ff47b2399b79ed6d1cbc7dbf991b;p=safe%2Fjmp%2Flinux-2.6 diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index d771da8..05a31e5 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -38,8 +38,11 @@ #include #include #include +#include #include +#include +#include #include #include #include @@ -63,7 +66,7 @@ struct blk_shadow { unsigned long frame[BLKIF_MAX_SEGMENTS_PER_REQUEST]; }; -static struct block_device_operations xlvbd_block_fops; +static const struct block_device_operations xlvbd_block_fops; #define BLK_RING_SIZE __RING_SIZE((struct blkif_sring *)0, PAGE_SIZE) @@ -81,6 +84,7 @@ struct blkfront_info enum blkif_state connected; int ring_ref; struct blkif_front_ring ring; + struct scatterlist sg[BLKIF_MAX_SEGMENTS_PER_REQUEST]; unsigned int evtchn, irq; struct request_queue *rq; struct work_struct work; @@ -104,20 +108,22 @@ static DEFINE_SPINLOCK(blkif_io_lock); #define GRANT_INVALID_REF 0 #define PARTS_PER_DISK 16 +#define PARTS_PER_EXT_DISK 256 #define BLKIF_MAJOR(dev) ((dev)>>8) #define BLKIF_MINOR(dev) ((dev) & 0xff) -#define DEV_NAME "xvd" /* name in /dev */ +#define EXT_SHIFT 28 +#define EXTENDED (1<shadow_free; - BUG_ON(free > BLK_RING_SIZE); + BUG_ON(free >= BLK_RING_SIZE); info->shadow_free = info->shadow[free].req.id; info->shadow[free].req.id = 0x0fffffee; /* debug */ return free; @@ -137,7 +143,7 @@ static void blkif_restart_queue_callback(void *arg) schedule_work(&info->work); } -int blkif_getgeo(struct block_device *bd, struct hd_geometry *hg) +static int blkif_getgeo(struct block_device *bd, struct hd_geometry *hg) { /* We don't have real geometry info, but let's at least return values consistent with the size of the device */ @@ -153,6 +159,39 @@ int blkif_getgeo(struct block_device *bd, struct hd_geometry *hg) return 0; } +static int blkif_ioctl(struct block_device *bdev, fmode_t mode, + unsigned command, unsigned long argument) +{ + struct blkfront_info *info = bdev->bd_disk->private_data; + int i; + + dev_dbg(&info->xbdev->dev, "command: 0x%x, argument: 0x%lx\n", + command, (long)argument); + + switch (command) { + case CDROMMULTISESSION: + dev_dbg(&info->xbdev->dev, "FIXME: support multisession CDs later\n"); + for (i = 0; i < sizeof(struct cdrom_multisession); i++) + if (put_user(0, (char __user *)(argument + i))) + return -EFAULT; + return 0; + + case CDROM_GET_CAPABILITY: { + struct gendisk *gd = info->gd; + if (gd->flags & GENHD_FL_CD) + return 0; + return -EINVAL; + } + + default: + /*printk(KERN_ALERT "ioctl %08x not supported by Xen blkdev\n", + command);*/ + return -EINVAL; /* same return as native Linux */ + } + + return 0; +} + /* * blkif_queue_request * @@ -168,12 +207,11 @@ 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; + int i, ref; grant_ref_t gref_head; + struct scatterlist *sg; if (unlikely(info->connected != BLKIF_STATE_CONNECTED)) return 1; @@ -194,7 +232,7 @@ static int blkif_queue_request(struct request *req) info->shadow[id].request = (unsigned long)req; ring_req->id = id; - ring_req->sector_number = (blkif_sector_t)req->sector; + ring_req->sector_number = (blkif_sector_t)blk_rq_pos(req); ring_req->handle = info->handle; ring_req->operation = rq_data_dir(req) ? @@ -202,12 +240,13 @@ static int blkif_queue_request(struct request *req) 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; + ring_req->nr_segments = blk_rq_map_sg(req->q, req, info->sg); + BUG_ON(ring_req->nr_segments > BLKIF_MAX_SEGMENTS_PER_REQUEST); + + for_each_sg(info->sg, sg, ring_req->nr_segments, i) { + buffer_mfn = pfn_to_mfn(page_to_pfn(sg_page(sg))); + fsect = sg->offset >> 9; + lsect = fsect + (sg->length >> 9) - 1; /* install a grant reference. */ ref = gnttab_claim_grant_reference(&gref_head); BUG_ON(ref == -ENOSPC); @@ -218,16 +257,12 @@ static int blkif_queue_request(struct request *req) 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] = + info->shadow[id].frame[i] = mfn_to_pfn(buffer_mfn); + ring_req->seg[i] = (struct blkif_request_segment) { .gref = ref, .first_sect = fsect, .last_sect = lsect }; - - ring_req->nr_segments++; } info->ring.req_prod_pvt++; @@ -265,25 +300,25 @@ static void do_blkif_request(struct request_queue *rq) queued = 0; - while ((req = elv_next_request(rq)) != NULL) { + while ((req = blk_peek_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"); + blk_start_request(req); + if (!blk_fs_request(req)) { + __blk_end_request_all(req, -EIO); + continue; + } + + pr_debug("do_blk_req %p: cmd %p, sec %lx, " + "(%u/%u) buffer:%p [%s]\n", + req, req->cmd, (unsigned long)blk_rq_pos(req), + blk_rq_cur_sectors(req), blk_rq_sectors(req), + req->buffer, rq_data_dir(req) ? "write" : "read"); - blkdev_dequeue_request(req); if (blkif_queue_request(req)) { blk_requeue_request(rq, req); wait: @@ -307,10 +342,10 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size) if (rq == NULL) return -1; - elevator_init(rq, "noop"); + queue_flag_set_unlocked(QUEUE_FLAG_VIRT, rq); /* Hard sector size and max sectors impersonate the equiv. hardware. */ - blk_queue_hardsect_size(rq, sector_size); + blk_queue_logical_block_size(rq, sector_size); blk_queue_max_sectors(rq, 512); /* Each segment in a request is up to an aligned page in size. */ @@ -324,6 +359,9 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size) /* Make sure buffer addresses are sector-aligned. */ blk_queue_dma_alignment(rq, 511); + /* Make sure we don't use bounce buffers. */ + blk_queue_bounce_limit(rq, BLK_BOUNCE_ANY); + gd->queue = rq; return 0; @@ -348,31 +386,60 @@ static int xlvbd_barrier(struct blkfront_info *info) } -static int xlvbd_alloc_gendisk(int minor, blkif_sector_t capacity, - int vdevice, u16 vdisk_info, u16 sector_size, - struct blkfront_info *info) +static int xlvbd_alloc_gendisk(blkif_sector_t capacity, + struct blkfront_info *info, + u16 vdisk_info, u16 sector_size) { struct gendisk *gd; int nr_minors = 1; int err = -ENODEV; + unsigned int offset; + int minor; + int nr_parts; BUG_ON(info->gd != NULL); BUG_ON(info->rq != NULL); - if ((minor % PARTS_PER_DISK) == 0) - nr_minors = PARTS_PER_DISK; + if ((info->vdevice>>EXT_SHIFT) > 1) { + /* this is above the extended range; something is wrong */ + printk(KERN_WARNING "blkfront: vdevice 0x%x is above the extended range; ignoring\n", info->vdevice); + return -ENODEV; + } + + if (!VDEV_IS_EXTENDED(info->vdevice)) { + minor = BLKIF_MINOR(info->vdevice); + nr_parts = PARTS_PER_DISK; + } else { + minor = BLKIF_MINOR_EXT(info->vdevice); + nr_parts = PARTS_PER_EXT_DISK; + } + + if ((minor % nr_parts) == 0) + nr_minors = nr_parts; 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); + offset = minor / nr_parts; + + if (nr_minors > 1) { + if (offset < 26) + sprintf(gd->disk_name, "%s%c", DEV_NAME, 'a' + offset); + else + sprintf(gd->disk_name, "%s%c%c", DEV_NAME, + 'a' + ((offset / 26)-1), 'a' + (offset % 26)); + } else { + if (offset < 26) + sprintf(gd->disk_name, "%s%c%d", DEV_NAME, + 'a' + offset, + minor & (nr_parts - 1)); + else + sprintf(gd->disk_name, "%s%c%c%d", DEV_NAME, + 'a' + ((offset / 26) - 1), + 'a' + (offset % 26), + minor & (nr_parts - 1)); + } gd->major = XENVBD_MAJOR; gd->first_minor = minor; @@ -485,7 +552,6 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id) for (i = info->ring.rsp_cons; i != rp; i++) { unsigned long id; - int ret; bret = RING_GET_RESPONSE(&info->ring, i); id = bret->id; @@ -512,8 +578,7 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id) dev_dbg(&info->xbdev->dev, "Bad return from blkdev data " "request: %x\n", bret->status); - ret = __blk_end_request(req, error, blk_rq_bytes(req)); - BUG_ON(ret); + __blk_end_request_all(req, error); break; default: BUG(); @@ -546,7 +611,7 @@ static int setup_blkring(struct xenbus_device *dev, info->ring_ref = GRANT_INVALID_REF; - sring = (struct blkif_sring *)__get_free_page(GFP_KERNEL); + sring = (struct blkif_sring *)__get_free_page(GFP_NOIO | __GFP_HIGH); if (!sring) { xenbus_dev_fatal(dev, -ENOMEM, "allocating shared ring"); return -ENOMEM; @@ -554,6 +619,8 @@ static int setup_blkring(struct xenbus_device *dev, SHARED_RING_INIT(sring); FRONT_RING_INIT(&info->ring, sring, PAGE_SIZE); + sg_init_table(info->sg, BLKIF_MAX_SEGMENTS_PER_REQUEST); + err = xenbus_grant_ring(dev, virt_to_mfn(info->ring.sring)); if (err < 0) { free_page((unsigned long)sring); @@ -661,8 +728,13 @@ static int blkfront_probe(struct xenbus_device *dev, err = xenbus_scanf(XBT_NIL, dev->nodename, "virtual-device", "%i", &vdevice); if (err != 1) { - xenbus_dev_fatal(dev, err, "reading virtual-device"); - return err; + /* go looking in the extended area instead */ + err = xenbus_scanf(XBT_NIL, dev->nodename, "virtual-device-ext", + "%i", &vdevice); + if (err != 1) { + xenbus_dev_fatal(dev, err, "reading virtual-device"); + return err; + } } info = kzalloc(sizeof(*info), GFP_KERNEL); @@ -682,12 +754,12 @@ static int blkfront_probe(struct xenbus_device *dev, /* Front end dir is a number, which is used as the id. */ info->handle = simple_strtoul(strrchr(dev->nodename, '/')+1, NULL, 0); - dev->dev.driver_data = info; + dev_set_drvdata(&dev->dev, info); err = talk_to_backend(dev, info); if (err) { kfree(info); - dev->dev.driver_data = NULL; + dev_set_drvdata(&dev->dev, NULL); return err; } @@ -703,7 +775,8 @@ static int blkif_recover(struct blkfront_info *info) int j; /* Stage 1: Make a safe copy of the shadow state. */ - copy = kmalloc(sizeof(info->shadow), GFP_KERNEL); + copy = kmalloc(sizeof(info->shadow), + GFP_NOIO | __GFP_REPEAT | __GFP_HIGH); if (!copy) return -ENOMEM; memcpy(copy, info->shadow, sizeof(info->shadow)); @@ -771,7 +844,7 @@ static int blkif_recover(struct blkfront_info *info) */ static int blkfront_resume(struct xenbus_device *dev) { - struct blkfront_info *info = dev->dev.driver_data; + struct blkfront_info *info = dev_get_drvdata(&dev->dev); int err; dev_dbg(&dev->dev, "blkfront_resume: %s\n", dev->nodename); @@ -822,9 +895,7 @@ static void blkfront_connect(struct blkfront_info *info) if (err) info->feature_barrier = 0; - err = xlvbd_alloc_gendisk(BLKIF_MINOR(info->vdevice), - sectors, info->vdevice, - binfo, sector_size, info); + err = xlvbd_alloc_gendisk(sectors, info, binfo, sector_size); if (err) { xenbus_dev_fatal(info->xbdev, err, "xlvbd_add at %s", info->xbdev->otherend); @@ -852,7 +923,7 @@ static void blkfront_connect(struct blkfront_info *info) */ static void blkfront_closing(struct xenbus_device *dev) { - struct blkfront_info *info = dev->dev.driver_data; + struct blkfront_info *info = dev_get_drvdata(&dev->dev); unsigned long flags; dev_dbg(&dev->dev, "blkfront_closing: %s removed\n", dev->nodename); @@ -862,8 +933,6 @@ static void blkfront_closing(struct xenbus_device *dev) spin_lock_irqsave(&blkif_io_lock, flags); - del_gendisk(info->gd); - /* No more blkif_request(). */ blk_stop_queue(info->rq); @@ -877,6 +946,8 @@ static void blkfront_closing(struct xenbus_device *dev) blk_cleanup_queue(info->rq); info->rq = NULL; + del_gendisk(info->gd); + out: xenbus_frontend_closed(dev); } @@ -887,7 +958,7 @@ static void blkfront_closing(struct xenbus_device *dev) static void backend_changed(struct xenbus_device *dev, enum xenbus_state backend_state) { - struct blkfront_info *info = dev->dev.driver_data; + struct blkfront_info *info = dev_get_drvdata(&dev->dev); struct block_device *bd; dev_dbg(&dev->dev, "blkfront:backend_changed.\n"); @@ -905,6 +976,10 @@ static void backend_changed(struct xenbus_device *dev, break; case XenbusStateClosing: + if (info->gd == NULL) { + xenbus_frontend_closed(dev); + break; + } bd = bdget_disk(info->gd, 0); if (bd == NULL) xenbus_dev_fatal(dev, -ENODEV, "bdget failed"); @@ -923,7 +998,7 @@ static void backend_changed(struct xenbus_device *dev, static int blkfront_remove(struct xenbus_device *dev) { - struct blkfront_info *info = dev->dev.driver_data; + struct blkfront_info *info = dev_get_drvdata(&dev->dev); dev_dbg(&dev->dev, "blkfront_remove: %s removed\n", dev->nodename); @@ -936,21 +1011,21 @@ static int blkfront_remove(struct xenbus_device *dev) static int blkfront_is_ready(struct xenbus_device *dev) { - struct blkfront_info *info = dev->dev.driver_data; + struct blkfront_info *info = dev_get_drvdata(&dev->dev); return info->is_ready; } -static int blkif_open(struct inode *inode, struct file *filep) +static int blkif_open(struct block_device *bdev, fmode_t mode) { - struct blkfront_info *info = inode->i_bdev->bd_disk->private_data; + struct blkfront_info *info = bdev->bd_disk->private_data; info->users++; return 0; } -static int blkif_release(struct inode *inode, struct file *filep) +static int blkif_release(struct gendisk *disk, fmode_t mode) { - struct blkfront_info *info = inode->i_bdev->bd_disk->private_data; + struct blkfront_info *info = disk->private_data; info->users--; if (info->users == 0) { /* Check whether we have been instructed to close. We will @@ -959,18 +1034,19 @@ static int blkif_release(struct inode *inode, struct file *filep) struct xenbus_device *dev = info->xbdev; enum xenbus_state state = xenbus_read_driver_state(dev->otherend); - if (state == XenbusStateClosing) + if (state == XenbusStateClosing && info->is_ready) blkfront_closing(dev); } return 0; } -static struct block_device_operations xlvbd_block_fops = +static const struct block_device_operations xlvbd_block_fops = { .owner = THIS_MODULE, .open = blkif_open, .release = blkif_release, .getgeo = blkif_getgeo, + .locked_ioctl = blkif_ioctl, }; @@ -992,7 +1068,7 @@ static struct xenbus_driver blkfront = { static int __init xlblk_init(void) { - if (!is_running_on_xen()) + if (!xen_domain()) return -ENODEV; if (register_blkdev(XENVBD_MAJOR, DEV_NAME)) { @@ -1006,7 +1082,7 @@ static int __init xlblk_init(void) module_init(xlblk_init); -static void xlblk_exit(void) +static void __exit xlblk_exit(void) { return xenbus_unregister_driver(&blkfront); }