M7350v1_en_gpl

kernel/drivers/block/aoe/Makefile

@@ -0,0 +1,6 @@
+#
+# Makefile for ATA over Ethernet
+#
+
+obj-$(CONFIG_ATA_OVER_ETH)	+= aoe.o
+aoe-y := aoeblk.o aoechr.o aoecmd.o aoedev.o aoemain.o aoenet.o

kernel/drivers/block/aoe/aoe.h

@@ -0,0 +1,203 @@
+/* Copyright (c) 2007 Coraid, Inc.  See COPYING for GPL terms. */
+#define VERSION "47"
+#define AOE_MAJOR 152
+#define DEVICE_NAME "aoe"
+
+/* set AOE_PARTITIONS to 1 to use whole-disks only
+ * default is 16, which is 15 partitions plus the whole disk
+ */
+#ifndef AOE_PARTITIONS
+#define AOE_PARTITIONS (16)
+#endif
+
+#define SYSMINOR(aoemajor, aoeminor) ((aoemajor) * NPERSHELF + (aoeminor))
+#define AOEMAJOR(sysminor) ((sysminor) / NPERSHELF)
+#define AOEMINOR(sysminor) ((sysminor) % NPERSHELF)
+#define WHITESPACE " \t\v\f\n"
+
+enum {
+	AOECMD_ATA,
+	AOECMD_CFG,
+	AOECMD_VEND_MIN = 0xf0,
+
+	AOEFL_RSP = (1<<3),
+	AOEFL_ERR = (1<<2),
+
+	AOEAFL_EXT = (1<<6),
+	AOEAFL_DEV = (1<<4),
+	AOEAFL_ASYNC = (1<<1),
+	AOEAFL_WRITE = (1<<0),
+
+	AOECCMD_READ = 0,
+	AOECCMD_TEST,
+	AOECCMD_PTEST,
+	AOECCMD_SET,
+	AOECCMD_FSET,
+
+	AOE_HVER = 0x10,
+};
+
+struct aoe_hdr {
+	unsigned char dst[6];
+	unsigned char src[6];
+	__be16 type;
+	unsigned char verfl;
+	unsigned char err;
+	__be16 major;
+	unsigned char minor;
+	unsigned char cmd;
+	__be32 tag;
+};
+
+struct aoe_atahdr {
+	unsigned char aflags;
+	unsigned char errfeat;
+	unsigned char scnt;
+	unsigned char cmdstat;
+	unsigned char lba0;
+	unsigned char lba1;
+	unsigned char lba2;
+	unsigned char lba3;
+	unsigned char lba4;
+	unsigned char lba5;
+	unsigned char res[2];
+};
+
+struct aoe_cfghdr {
+	__be16 bufcnt;
+	__be16 fwver;
+	unsigned char scnt;
+	unsigned char aoeccmd;
+	unsigned char cslen[2];
+};
+
+enum {
+	DEVFL_UP = 1,	/* device is installed in system and ready for AoE->ATA commands */
+	DEVFL_TKILL = (1<<1),	/* flag for timer to know when to kill self */
+	DEVFL_EXT = (1<<2),	/* device accepts lba48 commands */
+	DEVFL_CLOSEWAIT = (1<<3), /* device is waiting for all closes to revalidate */
+	DEVFL_GDALLOC = (1<<4),	/* need to alloc gendisk */
+	DEVFL_KICKME = (1<<5),	/* slow polling network card catch */
+	DEVFL_NEWSIZE = (1<<6),	/* need to update dev size in block layer */
+
+	BUFFL_FAIL = 1,
+};
+
+enum {
+	DEFAULTBCNT = 2 * 512,	/* 2 sectors */
+	NPERSHELF = 16,		/* number of slots per shelf address */
+	FREETAG = -1,
+	MIN_BUFS = 16,
+	NTARGETS = 8,
+	NAOEIFS = 8,
+	NSKBPOOLMAX = 128,
+
+	TIMERTICK = HZ / 10,
+	MINTIMER = HZ >> 2,
+	MAXTIMER = HZ << 1,
+	HELPWAIT = 20,
+};
+
+struct buf {
+	struct list_head bufs;
+	ulong stime;	/* for disk stats */
+	ulong flags;
+	ulong nframesout;
+	ulong resid;
+	ulong bv_resid;
+	ulong bv_off;
+	sector_t sector;
+	struct bio *bio;
+	struct bio_vec *bv;
+};
+
+struct frame {
+	int tag;
+	ulong waited;
+	struct buf *buf;
+	char *bufaddr;
+	ulong bcnt;
+	sector_t lba;
+	struct sk_buff *skb;
+};
+
+struct aoeif {
+	struct net_device *nd;
+	unsigned char lost;
+	unsigned char lostjumbo;
+	ushort maxbcnt;
+};
+
+struct aoetgt {
+	unsigned char addr[6];
+	ushort nframes;
+	struct frame *frames;
+	struct aoeif ifs[NAOEIFS];
+	struct aoeif *ifp;	/* current aoeif in use */
+	ushort nout;
+	ushort maxout;
+	u16 lasttag;		/* last tag sent */
+	u16 useme;
+	ulong lastwadj;		/* last window adjustment */
+	int wpkts, rpkts;
+	int dataref;
+};
+
+struct aoedev {
+	struct aoedev *next;
+	ulong sysminor;
+	ulong aoemajor;
+	u16 aoeminor;
+	u16 flags;
+	u16 nopen;		/* (bd_openers isn't available without sleeping) */
+	u16 rttavg;		/* round trip average of requests/responses */
+	u16 mintimer;
+	u16 fw_ver;		/* version of blade's firmware */
+	struct work_struct work;/* disk create work struct */
+	struct gendisk *gd;
+	struct request_queue *blkq;
+	struct hd_geometry geo; 
+	sector_t ssize;
+	struct timer_list timer;
+	spinlock_t lock;
+	struct sk_buff_head sendq;
+	struct sk_buff_head skbpool;
+	mempool_t *bufpool;	/* for deadlock-free Buf allocation */
+	struct list_head bufq;	/* queue of bios to work on */
+	struct buf *inprocess;	/* the one we're currently working on */
+	struct aoetgt *targets[NTARGETS];
+	struct aoetgt **tgt;	/* target in use when working */
+	struct aoetgt **htgt;	/* target needing rexmit assistance */
+};
+
+
+int aoeblk_init(void);
+void aoeblk_exit(void);
+void aoeblk_gdalloc(void *);
+void aoedisk_rm_sysfs(struct aoedev *d);
+
+int aoechr_init(void);
+void aoechr_exit(void);
+void aoechr_error(char *);
+
+void aoecmd_work(struct aoedev *d);
+void aoecmd_cfg(ushort aoemajor, unsigned char aoeminor);
+void aoecmd_ata_rsp(struct sk_buff *);
+void aoecmd_cfg_rsp(struct sk_buff *);
+void aoecmd_sleepwork(struct work_struct *);
+void aoecmd_cleanslate(struct aoedev *);
+struct sk_buff *aoecmd_ata_id(struct aoedev *);
+
+int aoedev_init(void);
+void aoedev_exit(void);
+struct aoedev *aoedev_by_aoeaddr(int maj, int min);
+struct aoedev *aoedev_by_sysminor_m(ulong sysminor);
+void aoedev_downdev(struct aoedev *d);
+int aoedev_flush(const char __user *str, size_t size);
+
+int aoenet_init(void);
+void aoenet_exit(void);
+void aoenet_xmit(struct sk_buff_head *);
+int is_aoe_netif(struct net_device *ifp);
+int set_aoe_iflist(const char __user *str, size_t size);
+

kernel/drivers/block/aoe/aoeblk.c

@@ -0,0 +1,331 @@
+/* Copyright (c) 2007 Coraid, Inc.  See COPYING for GPL terms. */
+/*
+ * aoeblk.c
+ * block device routines
+ */
+
+#include <linux/kernel.h>
+#include <linux/hdreg.h>
+#include <linux/blkdev.h>
+#include <linux/backing-dev.h>
+#include <linux/fs.h>
+#include <linux/ioctl.h>
+#include <linux/slab.h>
+#include <linux/ratelimit.h>
+#include <linux/genhd.h>
+#include <linux/netdevice.h>
+#include <linux/mutex.h>
+#include <linux/export.h>
+#include "aoe.h"
+
+static DEFINE_MUTEX(aoeblk_mutex);
+static struct kmem_cache *buf_pool_cache;
+
+static ssize_t aoedisk_show_state(struct device *dev,
+				  struct device_attribute *attr, char *page)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+	struct aoedev *d = disk->private_data;
+
+	return snprintf(page, PAGE_SIZE,
+			"%s%s\n",
+			(d->flags & DEVFL_UP) ? "up" : "down",
+			(d->flags & DEVFL_KICKME) ? ",kickme" :
+			(d->nopen && !(d->flags & DEVFL_UP)) ? ",closewait" : "");
+	/* I'd rather see nopen exported so we can ditch closewait */
+}
+static ssize_t aoedisk_show_mac(struct device *dev,
+				struct device_attribute *attr, char *page)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+	struct aoedev *d = disk->private_data;
+	struct aoetgt *t = d->targets[0];
+
+	if (t == NULL)
+		return snprintf(page, PAGE_SIZE, "none\n");
+	return snprintf(page, PAGE_SIZE, "%pm\n", t->addr);
+}
+static ssize_t aoedisk_show_netif(struct device *dev,
+				  struct device_attribute *attr, char *page)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+	struct aoedev *d = disk->private_data;
+	struct net_device *nds[8], **nd, **nnd, **ne;
+	struct aoetgt **t, **te;
+	struct aoeif *ifp, *e;
+	char *p;
+
+	memset(nds, 0, sizeof nds);
+	nd = nds;
+	ne = nd + ARRAY_SIZE(nds);
+	t = d->targets;
+	te = t + NTARGETS;
+	for (; t < te && *t; t++) {
+		ifp = (*t)->ifs;
+		e = ifp + NAOEIFS;
+		for (; ifp < e && ifp->nd; ifp++) {
+			for (nnd = nds; nnd < nd; nnd++)
+				if (*nnd == ifp->nd)
+					break;
+			if (nnd == nd && nd != ne)
+				*nd++ = ifp->nd;
+		}
+	}
+
+	ne = nd;
+	nd = nds;
+	if (*nd == NULL)
+		return snprintf(page, PAGE_SIZE, "none\n");
+	for (p = page; nd < ne; nd++)
+		p += snprintf(p, PAGE_SIZE - (p-page), "%s%s",
+			p == page ? "" : ",", (*nd)->name);
+	p += snprintf(p, PAGE_SIZE - (p-page), "\n");
+	return p-page;
+}
+/* firmware version */
+static ssize_t aoedisk_show_fwver(struct device *dev,
+				  struct device_attribute *attr, char *page)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+	struct aoedev *d = disk->private_data;
+
+	return snprintf(page, PAGE_SIZE, "0x%04x\n", (unsigned int) d->fw_ver);
+}
+
+static DEVICE_ATTR(state, S_IRUGO, aoedisk_show_state, NULL);
+static DEVICE_ATTR(mac, S_IRUGO, aoedisk_show_mac, NULL);
+static DEVICE_ATTR(netif, S_IRUGO, aoedisk_show_netif, NULL);
+static struct device_attribute dev_attr_firmware_version = {
+	.attr = { .name = "firmware-version", .mode = S_IRUGO },
+	.show = aoedisk_show_fwver,
+};
+
+static struct attribute *aoe_attrs[] = {
+	&dev_attr_state.attr,
+	&dev_attr_mac.attr,
+	&dev_attr_netif.attr,
+	&dev_attr_firmware_version.attr,
+	NULL,
+};
+
+static const struct attribute_group attr_group = {
+	.attrs = aoe_attrs,
+};
+
+static int
+aoedisk_add_sysfs(struct aoedev *d)
+{
+	return sysfs_create_group(&disk_to_dev(d->gd)->kobj, &attr_group);
+}
+void
+aoedisk_rm_sysfs(struct aoedev *d)
+{
+	sysfs_remove_group(&disk_to_dev(d->gd)->kobj, &attr_group);
+}
+
+static int
+aoeblk_open(struct block_device *bdev, fmode_t mode)
+{
+	struct aoedev *d = bdev->bd_disk->private_data;
+	ulong flags;
+
+	mutex_lock(&aoeblk_mutex);
+	spin_lock_irqsave(&d->lock, flags);
+	if (d->flags & DEVFL_UP) {
+		d->nopen++;
+		spin_unlock_irqrestore(&d->lock, flags);
+		mutex_unlock(&aoeblk_mutex);
+		return 0;
+	}
+	spin_unlock_irqrestore(&d->lock, flags);
+	mutex_unlock(&aoeblk_mutex);
+	return -ENODEV;
+}
+
+static int
+aoeblk_release(struct gendisk *disk, fmode_t mode)
+{
+	struct aoedev *d = disk->private_data;
+	ulong flags;
+
+	spin_lock_irqsave(&d->lock, flags);
+
+	if (--d->nopen == 0) {
+		spin_unlock_irqrestore(&d->lock, flags);
+		aoecmd_cfg(d->aoemajor, d->aoeminor);
+		return 0;
+	}
+	spin_unlock_irqrestore(&d->lock, flags);
+
+	return 0;
+}
+
+static void
+aoeblk_make_request(struct request_queue *q, struct bio *bio)
+{
+	struct sk_buff_head queue;
+	struct aoedev *d;
+	struct buf *buf;
+	ulong flags;
+
+	blk_queue_bounce(q, &bio);
+
+	if (bio == NULL) {
+		printk(KERN_ERR "aoe: bio is NULL\n");
+		BUG();
+		return;
+	}
+	d = bio->bi_bdev->bd_disk->private_data;
+	if (d == NULL) {
+		printk(KERN_ERR "aoe: bd_disk->private_data is NULL\n");
+		BUG();
+		bio_endio(bio, -ENXIO);
+		return;
+	} else if (bio->bi_io_vec == NULL) {
+		printk(KERN_ERR "aoe: bi_io_vec is NULL\n");
+		BUG();
+		bio_endio(bio, -ENXIO);
+		return;
+	}
+	buf = mempool_alloc(d->bufpool, GFP_NOIO);
+	if (buf == NULL) {
+		printk(KERN_INFO "aoe: buf allocation failure\n");
+		bio_endio(bio, -ENOMEM);
+		return;
+	}
+	memset(buf, 0, sizeof(*buf));
+	INIT_LIST_HEAD(&buf->bufs);
+	buf->stime = jiffies;
+	buf->bio = bio;
+	buf->resid = bio->bi_size;
+	buf->sector = bio->bi_sector;
+	buf->bv = &bio->bi_io_vec[bio->bi_idx];
+	buf->bv_resid = buf->bv->bv_len;
+	WARN_ON(buf->bv_resid == 0);
+	buf->bv_off = buf->bv->bv_offset;
+
+	spin_lock_irqsave(&d->lock, flags);
+
+	if ((d->flags & DEVFL_UP) == 0) {
+		pr_info_ratelimited("aoe: device %ld.%d is not up\n",
+			d->aoemajor, d->aoeminor);
+		spin_unlock_irqrestore(&d->lock, flags);
+		mempool_free(buf, d->bufpool);
+		bio_endio(bio, -ENXIO);
+		return;
+	}
+
+	list_add_tail(&buf->bufs, &d->bufq);
+
+	aoecmd_work(d);
+	__skb_queue_head_init(&queue);
+	skb_queue_splice_init(&d->sendq, &queue);
+
+	spin_unlock_irqrestore(&d->lock, flags);
+	aoenet_xmit(&queue);
+}
+
+static int
+aoeblk_getgeo(struct block_device *bdev, struct hd_geometry *geo)
+{
+	struct aoedev *d = bdev->bd_disk->private_data;
+
+	if ((d->flags & DEVFL_UP) == 0) {
+		printk(KERN_ERR "aoe: disk not up\n");
+		return -ENODEV;
+	}
+
+	geo->cylinders = d->geo.cylinders;
+	geo->heads = d->geo.heads;
+	geo->sectors = d->geo.sectors;
+	return 0;
+}
+
+static const struct block_device_operations aoe_bdops = {
+	.open = aoeblk_open,
+	.release = aoeblk_release,
+	.getgeo = aoeblk_getgeo,
+	.owner = THIS_MODULE,
+};
+
+/* alloc_disk and add_disk can sleep */
+void
+aoeblk_gdalloc(void *vp)
+{
+	struct aoedev *d = vp;
+	struct gendisk *gd;
+	ulong flags;
+
+	gd = alloc_disk(AOE_PARTITIONS);
+	if (gd == NULL) {
+		printk(KERN_ERR
+			"aoe: cannot allocate disk structure for %ld.%d\n",
+			d->aoemajor, d->aoeminor);
+		goto err;
+	}
+
+	d->bufpool = mempool_create_slab_pool(MIN_BUFS, buf_pool_cache);
+	if (d->bufpool == NULL) {
+		printk(KERN_ERR "aoe: cannot allocate bufpool for %ld.%d\n",
+			d->aoemajor, d->aoeminor);
+		goto err_disk;
+	}
+
+	d->blkq = blk_alloc_queue(GFP_KERNEL);
+	if (!d->blkq)
+		goto err_mempool;
+	blk_queue_make_request(d->blkq, aoeblk_make_request);
+	d->blkq->backing_dev_info.name = "aoe";
+	if (bdi_init(&d->blkq->backing_dev_info))
+		goto err_blkq;
+	spin_lock_irqsave(&d->lock, flags);
+	gd->major = AOE_MAJOR;
+	gd->first_minor = d->sysminor * AOE_PARTITIONS;
+	gd->fops = &aoe_bdops;
+	gd->private_data = d;
+	set_capacity(gd, d->ssize);
+	snprintf(gd->disk_name, sizeof gd->disk_name, "etherd/e%ld.%d",
+		d->aoemajor, d->aoeminor);
+
+	gd->queue = d->blkq;
+	d->gd = gd;
+	d->flags &= ~DEVFL_GDALLOC;
+	d->flags |= DEVFL_UP;
+
+	spin_unlock_irqrestore(&d->lock, flags);
+
+	add_disk(gd);
+	aoedisk_add_sysfs(d);
+	return;
+
+err_blkq:
+	blk_cleanup_queue(d->blkq);
+	d->blkq = NULL;
+err_mempool:
+	mempool_destroy(d->bufpool);
+err_disk:
+	put_disk(gd);
+err:
+	spin_lock_irqsave(&d->lock, flags);
+	d->flags &= ~DEVFL_GDALLOC;
+	spin_unlock_irqrestore(&d->lock, flags);
+}
+
+void
+aoeblk_exit(void)
+{
+	kmem_cache_destroy(buf_pool_cache);
+}
+
+int __init
+aoeblk_init(void)
+{
+	buf_pool_cache = kmem_cache_create("aoe_bufs",
+					   sizeof(struct buf),
+					   0, 0, NULL);
+	if (buf_pool_cache == NULL)
+		return -ENOMEM;
+
+	return 0;
+}
+

kernel/drivers/block/aoe/aoechr.c

@@ -0,0 +1,315 @@
+/* Copyright (c) 2007 Coraid, Inc.  See COPYING for GPL terms. */
+/*
+ * aoechr.c
+ * AoE character device driver
+ */
+
+#include <linux/hdreg.h>
+#include <linux/blkdev.h>
+#include <linux/completion.h>
+#include <linux/delay.h>
+#include <linux/slab.h>
+#include <linux/mutex.h>
+#include <linux/skbuff.h>
+#include <linux/export.h>
+#include "aoe.h"
+
+enum {
+	//MINOR_STAT = 1, (moved to sysfs)
+	MINOR_ERR = 2,
+	MINOR_DISCOVER,
+	MINOR_INTERFACES,
+	MINOR_REVALIDATE,
+	MINOR_FLUSH,
+	MSGSZ = 2048,
+	NMSG = 100,		/* message backlog to retain */
+};
+
+struct aoe_chardev {
+	ulong minor;
+	char name[32];
+};
+
+enum { EMFL_VALID = 1 };
+
+struct ErrMsg {
+	short flags;
+	short len;
+	char *msg;
+};
+
+static DEFINE_MUTEX(aoechr_mutex);
+static struct ErrMsg emsgs[NMSG];
+static int emsgs_head_idx, emsgs_tail_idx;
+static struct completion emsgs_comp;
+static spinlock_t emsgs_lock;
+static int nblocked_emsgs_readers;
+static struct class *aoe_class;
+static struct aoe_chardev chardevs[] = {
+	{ MINOR_ERR, "err" },
+	{ MINOR_DISCOVER, "discover" },
+	{ MINOR_INTERFACES, "interfaces" },
+	{ MINOR_REVALIDATE, "revalidate" },
+	{ MINOR_FLUSH, "flush" },
+};
+
+static int
+discover(void)
+{
+	aoecmd_cfg(0xffff, 0xff);
+	return 0;
+}
+
+static int
+interfaces(const char __user *str, size_t size)
+{
+	if (set_aoe_iflist(str, size)) {
+		printk(KERN_ERR
+			"aoe: could not set interface list: too many interfaces\n");
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int
+revalidate(const char __user *str, size_t size)
+{
+	int major, minor, n;
+	ulong flags;
+	struct aoedev *d;
+	struct sk_buff *skb;
+	char buf[16];
+
+	if (size >= sizeof buf)
+		return -EINVAL;
+	buf[sizeof buf - 1] = '\0';
+	if (copy_from_user(buf, str, size))
+		return -EFAULT;
+
+	/* should be e%d.%d format */
+	n = sscanf(buf, "e%d.%d", &major, &minor);
+	if (n != 2) {
+		printk(KERN_ERR "aoe: invalid device specification\n");
+		return -EINVAL;
+	}
+	d = aoedev_by_aoeaddr(major, minor);
+	if (!d)
+		return -EINVAL;
+	spin_lock_irqsave(&d->lock, flags);
+	aoecmd_cleanslate(d);
+loop:
+	skb = aoecmd_ata_id(d);
+	spin_unlock_irqrestore(&d->lock, flags);
+	/* try again if we are able to sleep a bit,
+	 * otherwise give up this revalidation
+	 */
+	if (!skb && !msleep_interruptible(200)) {
+		spin_lock_irqsave(&d->lock, flags);
+		goto loop;
+	}
+	if (skb) {
+		struct sk_buff_head queue;
+		__skb_queue_head_init(&queue);
+		__skb_queue_tail(&queue, skb);
+		aoenet_xmit(&queue);
+	}
+	aoecmd_cfg(major, minor);
+	return 0;
+}
+
+void
+aoechr_error(char *msg)
+{
+	struct ErrMsg *em;
+	char *mp;
+	ulong flags, n;
+
+	n = strlen(msg);
+
+	spin_lock_irqsave(&emsgs_lock, flags);
+
+	em = emsgs + emsgs_tail_idx;
+	if ((em->flags & EMFL_VALID)) {
+bail:		spin_unlock_irqrestore(&emsgs_lock, flags);
+		return;
+	}
+
+	mp = kmalloc(n, GFP_ATOMIC);
+	if (mp == NULL) {
+		printk(KERN_ERR "aoe: allocation failure, len=%ld\n", n);
+		goto bail;
+	}
+
+	memcpy(mp, msg, n);
+	em->msg = mp;
+	em->flags |= EMFL_VALID;
+	em->len = n;
+
+	emsgs_tail_idx++;
+	emsgs_tail_idx %= ARRAY_SIZE(emsgs);
+
+	spin_unlock_irqrestore(&emsgs_lock, flags);
+
+	if (nblocked_emsgs_readers)
+		complete(&emsgs_comp);
+}
+
+static ssize_t
+aoechr_write(struct file *filp, const char __user *buf, size_t cnt, loff_t *offp)
+{
+	int ret = -EINVAL;
+
+	switch ((unsigned long) filp->private_data) {
+	default:
+		printk(KERN_INFO "aoe: can't write to that file.\n");
+		break;
+	case MINOR_DISCOVER:
+		ret = discover();
+		break;
+	case MINOR_INTERFACES:
+		ret = interfaces(buf, cnt);
+		break;
+	case MINOR_REVALIDATE:
+		ret = revalidate(buf, cnt);
+		break;
+	case MINOR_FLUSH:
+		ret = aoedev_flush(buf, cnt);
+	}
+	if (ret == 0)
+		ret = cnt;
+	return ret;
+}
+
+static int
+aoechr_open(struct inode *inode, struct file *filp)
+{
+	int n, i;
+
+	mutex_lock(&aoechr_mutex);
+	n = iminor(inode);
+	filp->private_data = (void *) (unsigned long) n;
+
+	for (i = 0; i < ARRAY_SIZE(chardevs); ++i)
+		if (chardevs[i].minor == n) {
+			mutex_unlock(&aoechr_mutex);
+			return 0;
+		}
+	mutex_unlock(&aoechr_mutex);
+	return -EINVAL;
+}
+
+static int
+aoechr_rel(struct inode *inode, struct file *filp)
+{
+	return 0;
+}
+
+static ssize_t
+aoechr_read(struct file *filp, char __user *buf, size_t cnt, loff_t *off)
+{
+	unsigned long n;
+	char *mp;
+	struct ErrMsg *em;
+	ssize_t len;
+	ulong flags;
+
+	n = (unsigned long) filp->private_data;
+	if (n != MINOR_ERR)
+		return -EFAULT;
+
+	spin_lock_irqsave(&emsgs_lock, flags);
+
+	for (;;) {
+		em = emsgs + emsgs_head_idx;
+		if ((em->flags & EMFL_VALID) != 0)
+			break;
+		if (filp->f_flags & O_NDELAY) {
+			spin_unlock_irqrestore(&emsgs_lock, flags);
+			return -EAGAIN;
+		}
+		nblocked_emsgs_readers++;
+
+		spin_unlock_irqrestore(&emsgs_lock, flags);
+
+		n = wait_for_completion_interruptible(&emsgs_comp);
+
+		spin_lock_irqsave(&emsgs_lock, flags);
+
+		nblocked_emsgs_readers--;
+
+		if (n) {
+			spin_unlock_irqrestore(&emsgs_lock, flags);
+			return -ERESTARTSYS;
+		}
+	}
+	if (em->len > cnt) {
+		spin_unlock_irqrestore(&emsgs_lock, flags);
+		return -EAGAIN;
+	}
+	mp = em->msg;
+	len = em->len;
+	em->msg = NULL;
+	em->flags &= ~EMFL_VALID;
+
+	emsgs_head_idx++;
+	emsgs_head_idx %= ARRAY_SIZE(emsgs);
+
+	spin_unlock_irqrestore(&emsgs_lock, flags);
+
+	n = copy_to_user(buf, mp, len);
+	kfree(mp);
+	return n == 0 ? len : -EFAULT;
+}
+
+static const struct file_operations aoe_fops = {
+	.write = aoechr_write,
+	.read = aoechr_read,
+	.open = aoechr_open,
+	.release = aoechr_rel,
+	.owner = THIS_MODULE,
+	.llseek = noop_llseek,
+};
+
+static char *aoe_devnode(struct device *dev, umode_t *mode)
+{
+	return kasprintf(GFP_KERNEL, "etherd/%s", dev_name(dev));
+}
+
+int __init
+aoechr_init(void)
+{
+	int n, i;
+
+	n = register_chrdev(AOE_MAJOR, "aoechr", &aoe_fops);
+	if (n < 0) { 
+		printk(KERN_ERR "aoe: can't register char device\n");
+		return n;
+	}
+	init_completion(&emsgs_comp);
+	spin_lock_init(&emsgs_lock);
+	aoe_class = class_create(THIS_MODULE, "aoe");
+	if (IS_ERR(aoe_class)) {
+		unregister_chrdev(AOE_MAJOR, "aoechr");
+		return PTR_ERR(aoe_class);
+	}
+	aoe_class->devnode = aoe_devnode;
+
+	for (i = 0; i < ARRAY_SIZE(chardevs); ++i)
+		device_create(aoe_class, NULL,
+			      MKDEV(AOE_MAJOR, chardevs[i].minor), NULL,
+			      chardevs[i].name);
+
+	return 0;
+}
+
+void
+aoechr_exit(void)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(chardevs); ++i)
+		device_destroy(aoe_class, MKDEV(AOE_MAJOR, chardevs[i].minor));
+	class_destroy(aoe_class);
+	unregister_chrdev(AOE_MAJOR, "aoechr");
+}
+

kernel/drivers/block/aoe/aoedev.c

@@ -0,0 +1,277 @@
+/* Copyright (c) 2007 Coraid, Inc.  See COPYING for GPL terms. */
+/*
+ * aoedev.c
+ * AoE device utility functions; maintains device list.
+ */
+
+#include <linux/hdreg.h>
+#include <linux/blkdev.h>
+#include <linux/netdevice.h>
+#include <linux/delay.h>
+#include <linux/slab.h>
+#include "aoe.h"
+
+static void dummy_timer(ulong);
+static void aoedev_freedev(struct aoedev *);
+static void freetgt(struct aoedev *d, struct aoetgt *t);
+static void skbpoolfree(struct aoedev *d);
+
+static struct aoedev *devlist;
+static DEFINE_SPINLOCK(devlist_lock);
+
+struct aoedev *
+aoedev_by_aoeaddr(int maj, int min)
+{
+	struct aoedev *d;
+	ulong flags;
+
+	spin_lock_irqsave(&devlist_lock, flags);
+
+	for (d=devlist; d; d=d->next)
+		if (d->aoemajor == maj && d->aoeminor == min)
+			break;
+
+	spin_unlock_irqrestore(&devlist_lock, flags);
+	return d;
+}
+
+static void
+dummy_timer(ulong vp)
+{
+	struct aoedev *d;
+
+	d = (struct aoedev *)vp;
+	if (d->flags & DEVFL_TKILL)
+		return;
+	d->timer.expires = jiffies + HZ;
+	add_timer(&d->timer);
+}
+
+void
+aoedev_downdev(struct aoedev *d)
+{
+	struct aoetgt **t, **te;
+	struct frame *f, *e;
+	struct buf *buf;
+	struct bio *bio;
+
+	t = d->targets;
+	te = t + NTARGETS;
+	for (; t < te && *t; t++) {
+		f = (*t)->frames;
+		e = f + (*t)->nframes;
+		for (; f < e; f->tag = FREETAG, f->buf = NULL, f++) {
+			if (f->tag == FREETAG || f->buf == NULL)
+				continue;
+			buf = f->buf;
+			bio = buf->bio;
+			if (--buf->nframesout == 0
+			&& buf != d->inprocess) {
+				mempool_free(buf, d->bufpool);
+				bio_endio(bio, -EIO);
+			}
+		}
+		(*t)->maxout = (*t)->nframes;
+		(*t)->nout = 0;
+	}
+	buf = d->inprocess;
+	if (buf) {
+		bio = buf->bio;
+		mempool_free(buf, d->bufpool);
+		bio_endio(bio, -EIO);
+	}
+	d->inprocess = NULL;
+	d->htgt = NULL;
+
+	while (!list_empty(&d->bufq)) {
+		buf = container_of(d->bufq.next, struct buf, bufs);
+		list_del(d->bufq.next);
+		bio = buf->bio;
+		mempool_free(buf, d->bufpool);
+		bio_endio(bio, -EIO);
+	}
+
+	if (d->gd)
+		set_capacity(d->gd, 0);
+
+	d->flags &= ~DEVFL_UP;
+}
+
+static void
+aoedev_freedev(struct aoedev *d)
+{
+	struct aoetgt **t, **e;
+
+	cancel_work_sync(&d->work);
+	if (d->gd) {
+		aoedisk_rm_sysfs(d);
+		del_gendisk(d->gd);
+		put_disk(d->gd);
+	}
+	t = d->targets;
+	e = t + NTARGETS;
+	for (; t < e && *t; t++)
+		freetgt(d, *t);
+	if (d->bufpool)
+		mempool_destroy(d->bufpool);
+	skbpoolfree(d);
+	blk_cleanup_queue(d->blkq);
+	kfree(d);
+}
+
+int
+aoedev_flush(const char __user *str, size_t cnt)
+{
+	ulong flags;
+	struct aoedev *d, **dd;
+	struct aoedev *rmd = NULL;
+	char buf[16];
+	int all = 0;
+
+	if (cnt >= 3) {
+		if (cnt > sizeof buf)
+			cnt = sizeof buf;
+		if (copy_from_user(buf, str, cnt))
+			return -EFAULT;
+		all = !strncmp(buf, "all", 3);
+	}
+
+	spin_lock_irqsave(&devlist_lock, flags);
+	dd = &devlist;
+	while ((d = *dd)) {
+		spin_lock(&d->lock);
+		if ((!all && (d->flags & DEVFL_UP))
+		|| (d->flags & (DEVFL_GDALLOC|DEVFL_NEWSIZE))
+		|| d->nopen) {
+			spin_unlock(&d->lock);
+			dd = &d->next;
+			continue;
+		}
+		*dd = d->next;
+		aoedev_downdev(d);
+		d->flags |= DEVFL_TKILL;
+		spin_unlock(&d->lock);
+		d->next = rmd;
+		rmd = d;
+	}
+	spin_unlock_irqrestore(&devlist_lock, flags);
+	while ((d = rmd)) {
+		rmd = d->next;
+		del_timer_sync(&d->timer);
+		aoedev_freedev(d);	/* must be able to sleep */
+	}
+	return 0;
+}
+
+/* I'm not really sure that this is a realistic problem, but if the
+network driver goes gonzo let's just leak memory after complaining. */
+static void
+skbfree(struct sk_buff *skb)
+{
+	enum { Sms = 100, Tms = 3*1000};
+	int i = Tms / Sms;
+
+	if (skb == NULL)
+		return;
+	while (atomic_read(&skb_shinfo(skb)->dataref) != 1 && i-- > 0)
+		msleep(Sms);
+	if (i < 0) {
+		printk(KERN_ERR
+			"aoe: %s holds ref: %s\n",
+			skb->dev ? skb->dev->name : "netif",
+			"cannot free skb -- memory leaked.");
+		return;
+	}
+	skb_shinfo(skb)->nr_frags = skb->data_len = 0;
+	skb_trim(skb, 0);
+	dev_kfree_skb(skb);
+}
+
+static void
+skbpoolfree(struct aoedev *d)
+{
+	struct sk_buff *skb, *tmp;
+
+	skb_queue_walk_safe(&d->skbpool, skb, tmp)
+		skbfree(skb);
+
+	__skb_queue_head_init(&d->skbpool);
+}
+
+/* find it or malloc it */
+struct aoedev *
+aoedev_by_sysminor_m(ulong sysminor)
+{
+	struct aoedev *d;
+	ulong flags;
+
+	spin_lock_irqsave(&devlist_lock, flags);
+
+	for (d=devlist; d; d=d->next)
+		if (d->sysminor == sysminor)
+			break;
+	if (d)
+		goto out;
+	d = kcalloc(1, sizeof *d, GFP_ATOMIC);
+	if (!d)
+		goto out;
+	INIT_WORK(&d->work, aoecmd_sleepwork);
+	spin_lock_init(&d->lock);
+	skb_queue_head_init(&d->sendq);
+	skb_queue_head_init(&d->skbpool);
+	init_timer(&d->timer);
+	d->timer.data = (ulong) d;
+	d->timer.function = dummy_timer;
+	d->timer.expires = jiffies + HZ;
+	add_timer(&d->timer);
+	d->bufpool = NULL;	/* defer to aoeblk_gdalloc */
+	d->tgt = d->targets;
+	INIT_LIST_HEAD(&d->bufq);
+	d->sysminor = sysminor;
+	d->aoemajor = AOEMAJOR(sysminor);
+	d->aoeminor = AOEMINOR(sysminor);
+	d->mintimer = MINTIMER;
+	d->next = devlist;
+	devlist = d;
+ out:
+	spin_unlock_irqrestore(&devlist_lock, flags);
+	return d;
+}
+
+static void
+freetgt(struct aoedev *d, struct aoetgt *t)
+{
+	struct frame *f, *e;
+
+	f = t->frames;
+	e = f + t->nframes;
+	for (; f < e; f++)
+		skbfree(f->skb);
+	kfree(t->frames);
+	kfree(t);
+}
+
+void
+aoedev_exit(void)
+{
+	struct aoedev *d;
+	ulong flags;
+
+	while ((d = devlist)) {
+		devlist = d->next;
+
+		spin_lock_irqsave(&d->lock, flags);
+		aoedev_downdev(d);
+		d->flags |= DEVFL_TKILL;
+		spin_unlock_irqrestore(&d->lock, flags);
+
+		del_timer_sync(&d->timer);
+		aoedev_freedev(d);
+	}
+}
+
+int __init
+aoedev_init(void)
+{
+	return 0;
+}

kernel/drivers/block/aoe/aoemain.c

@@ -0,0 +1,111 @@
+/* Copyright (c) 2007 Coraid, Inc.  See COPYING for GPL terms. */
+/*
+ * aoemain.c
+ * Module initialization routines, discover timer
+ */
+
+#include <linux/hdreg.h>
+#include <linux/blkdev.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include "aoe.h"
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Sam Hopkins <sah@coraid.com>");
+MODULE_DESCRIPTION("AoE block/char driver for 2.6.2 and newer 2.6 kernels");
+MODULE_VERSION(VERSION);
+
+enum { TINIT, TRUN, TKILL };
+
+static void
+discover_timer(ulong vp)
+{
+	static struct timer_list t;
+	static volatile ulong die;
+	static spinlock_t lock;
+	ulong flags;
+	enum { DTIMERTICK = HZ * 60 }; /* one minute */
+
+	switch (vp) {
+	case TINIT:
+		init_timer(&t);
+		spin_lock_init(&lock);
+		t.data = TRUN;
+		t.function = discover_timer;
+		die = 0;
+	case TRUN:
+		spin_lock_irqsave(&lock, flags);
+		if (!die) {
+			t.expires = jiffies + DTIMERTICK;
+			add_timer(&t);
+		}
+		spin_unlock_irqrestore(&lock, flags);
+
+		aoecmd_cfg(0xffff, 0xff);
+		return;
+	case TKILL:
+		spin_lock_irqsave(&lock, flags);
+		die = 1;
+		spin_unlock_irqrestore(&lock, flags);
+
+		del_timer_sync(&t);
+	default:
+		return;
+	}
+}
+
+static void
+aoe_exit(void)
+{
+	discover_timer(TKILL);
+
+	aoenet_exit();
+	unregister_blkdev(AOE_MAJOR, DEVICE_NAME);
+	aoechr_exit();
+	aoedev_exit();
+	aoeblk_exit();		/* free cache after de-allocating bufs */
+}
+
+static int __init
+aoe_init(void)
+{
+	int ret;
+
+	ret = aoedev_init();
+	if (ret)
+		return ret;
+	ret = aoechr_init();
+	if (ret)
+		goto chr_fail;
+	ret = aoeblk_init();
+	if (ret)
+		goto blk_fail;
+	ret = aoenet_init();
+	if (ret)
+		goto net_fail;
+	ret = register_blkdev(AOE_MAJOR, DEVICE_NAME);
+	if (ret < 0) {
+		printk(KERN_ERR "aoe: can't register major\n");
+		goto blkreg_fail;
+	}
+
+	printk(KERN_INFO "aoe: AoE v%s initialised.\n", VERSION);
+	discover_timer(TINIT);
+	return 0;
+
+ blkreg_fail:
+	aoenet_exit();
+ net_fail:
+	aoeblk_exit();
+ blk_fail:
+	aoechr_exit();
+ chr_fail:
+	aoedev_exit();
+	
+	printk(KERN_INFO "aoe: initialisation failure.\n");
+	return ret;
+}
+
+module_init(aoe_init);
+module_exit(aoe_exit);
+

kernel/drivers/block/aoe/aoenet.c

@@ -0,0 +1,172 @@
+/* Copyright (c) 2007 Coraid, Inc.  See COPYING for GPL terms. */
+/*
+ * aoenet.c
+ * Ethernet portion of AoE driver
+ */
+
+#include <linux/gfp.h>
+#include <linux/hdreg.h>
+#include <linux/blkdev.h>
+#include <linux/netdevice.h>
+#include <linux/moduleparam.h>
+#include <net/net_namespace.h>
+#include <asm/unaligned.h>
+#include "aoe.h"
+
+#define NECODES 5
+
+static char *aoe_errlist[] =
+{
+	"no such error",
+	"unrecognized command code",
+	"bad argument parameter",
+	"device unavailable",
+	"config string present",
+	"unsupported version"
+};
+
+enum {
+	IFLISTSZ = 1024,
+};
+
+static char aoe_iflist[IFLISTSZ];
+module_param_string(aoe_iflist, aoe_iflist, IFLISTSZ, 0600);
+MODULE_PARM_DESC(aoe_iflist, "aoe_iflist=\"dev1 [dev2 ...]\"");
+
+#ifndef MODULE
+static int __init aoe_iflist_setup(char *str)
+{
+	strncpy(aoe_iflist, str, IFLISTSZ);
+	aoe_iflist[IFLISTSZ - 1] = '\0';
+	return 1;
+}
+
+__setup("aoe_iflist=", aoe_iflist_setup);
+#endif
+
+int
+is_aoe_netif(struct net_device *ifp)
+{
+	register char *p, *q;
+	register int len;
+
+	if (aoe_iflist[0] == '\0')
+		return 1;
+
+	p = aoe_iflist + strspn(aoe_iflist, WHITESPACE);
+	for (; *p; p = q + strspn(q, WHITESPACE)) {
+		q = p + strcspn(p, WHITESPACE);
+		if (q != p)
+			len = q - p;
+		else
+			len = strlen(p); /* last token in aoe_iflist */
+
+		if (strlen(ifp->name) == len && !strncmp(ifp->name, p, len))
+			return 1;
+		if (q == p)
+			break;
+	}
+
+	return 0;
+}
+
+int
+set_aoe_iflist(const char __user *user_str, size_t size)
+{
+	if (size >= IFLISTSZ)
+		return -EINVAL;
+
+	if (copy_from_user(aoe_iflist, user_str, size)) {
+		printk(KERN_INFO "aoe: copy from user failed\n");
+		return -EFAULT;
+	}
+	aoe_iflist[size] = 0x00;
+	return 0;
+}
+
+void
+aoenet_xmit(struct sk_buff_head *queue)
+{
+	struct sk_buff *skb, *tmp;
+
+	skb_queue_walk_safe(queue, skb, tmp) {
+		__skb_unlink(skb, queue);
+		dev_queue_xmit(skb);
+	}
+}
+
+/* 
+ * (1) len doesn't include the header by default.  I want this. 
+ */
+static int
+aoenet_rcv(struct sk_buff *skb, struct net_device *ifp, struct packet_type *pt, struct net_device *orig_dev)
+{
+	struct aoe_hdr *h;
+	u32 n;
+
+	if (dev_net(ifp) != &init_net)
+		goto exit;
+
+	skb = skb_share_check(skb, GFP_ATOMIC);
+	if (skb == NULL)
+		return 0;
+	if (skb_linearize(skb))
+		goto exit;
+	if (!is_aoe_netif(ifp))
+		goto exit;
+	skb_push(skb, ETH_HLEN);	/* (1) */
+
+	h = (struct aoe_hdr *) skb_mac_header(skb);
+	n = get_unaligned_be32(&h->tag);
+	if ((h->verfl & AOEFL_RSP) == 0 || (n & 1<<31))
+		goto exit;
+
+	if (h->verfl & AOEFL_ERR) {
+		n = h->err;
+		if (n > NECODES)
+			n = 0;
+		if (net_ratelimit())
+			printk(KERN_ERR
+				"%s%d.%d@%s; ecode=%d '%s'\n",
+				"aoe: error packet from ",
+				get_unaligned_be16(&h->major),
+				h->minor, skb->dev->name,
+				h->err, aoe_errlist[n]);
+		goto exit;
+	}
+
+	switch (h->cmd) {
+	case AOECMD_ATA:
+		aoecmd_ata_rsp(skb);
+		break;
+	case AOECMD_CFG:
+		aoecmd_cfg_rsp(skb);
+		break;
+	default:
+		if (h->cmd >= AOECMD_VEND_MIN)
+			break;	/* don't complain about vendor commands */
+		printk(KERN_INFO "aoe: unknown cmd %d\n", h->cmd);
+	}
+exit:
+	dev_kfree_skb(skb);
+	return 0;
+}
+
+static struct packet_type aoe_pt __read_mostly = {
+	.type = __constant_htons(ETH_P_AOE),
+	.func = aoenet_rcv,
+};
+
+int __init
+aoenet_init(void)
+{
+	dev_add_pack(&aoe_pt);
+	return 0;
+}
+
+void
+aoenet_exit(void)
+{
+	dev_remove_pack(&aoe_pt);
+}
+