summaryrefslogtreecommitdiffstats
path: root/drivers/block/aoe
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/block/aoe')
-rw-r--r--drivers/block/aoe/Makefile6
-rw-r--r--drivers/block/aoe/aoe.h204
-rw-r--r--drivers/block/aoe/aoeblk.c317
-rw-r--r--drivers/block/aoe/aoechr.c304
-rw-r--r--drivers/block/aoe/aoecmd.c1086
-rw-r--r--drivers/block/aoe/aoedev.c277
-rw-r--r--drivers/block/aoe/aoemain.c111
-rw-r--r--drivers/block/aoe/aoenet.c182
8 files changed, 2487 insertions, 0 deletions
diff --git a/drivers/block/aoe/Makefile b/drivers/block/aoe/Makefile
new file mode 100644
index 0000000..e76d997
--- /dev/null
+++ b/drivers/block/aoe/Makefile
@@ -0,0 +1,6 @@
+#
+# Makefile for ATA over Ethernet
+#
+
+obj-$(CONFIG_ATA_OVER_ETH) += aoe.o
+aoe-objs := aoeblk.o aoechr.o aoecmd.o aoedev.o aoemain.o aoenet.o
diff --git a/drivers/block/aoe/aoe.h b/drivers/block/aoe/aoe.h
new file mode 100644
index 0000000..8e54c1f
--- /dev/null
+++ b/drivers/block/aoe/aoe.h
@@ -0,0 +1,204 @@
+/* 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);
+
+unsigned long long mac_addr(char addr[6]);
diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c
new file mode 100644
index 0000000..1747dd2
--- /dev/null
+++ b/drivers/block/aoe/aoeblk.c
@@ -0,0 +1,317 @@
+/* Copyright (c) 2007 Coraid, Inc. See COPYING for GPL terms. */
+/*
+ * aoeblk.c
+ * block device routines
+ */
+
+#include <linux/hdreg.h>
+#include <linux/blkdev.h>
+#include <linux/backing-dev.h>
+#include <linux/fs.h>
+#include <linux/ioctl.h>
+#include <linux/genhd.h>
+#include <linux/netdevice.h>
+#include "aoe.h"
+
+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, "%012llx\n", mac_addr(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;
+
+ spin_lock_irqsave(&d->lock, flags);
+ if (d->flags & DEVFL_UP) {
+ d->nopen++;
+ spin_unlock_irqrestore(&d->lock, flags);
+ return 0;
+ }
+ spin_unlock_irqrestore(&d->lock, flags);
+ 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 int
+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 0;
+ }
+ 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 0;
+ } else if (bio->bi_io_vec == NULL) {
+ printk(KERN_ERR "aoe: bi_io_vec is NULL\n");
+ BUG();
+ bio_endio(bio, -ENXIO);
+ return 0;
+ }
+ buf = mempool_alloc(d->bufpool, GFP_NOIO);
+ if (buf == NULL) {
+ printk(KERN_INFO "aoe: buf allocation failure\n");
+ bio_endio(bio, -ENOMEM);
+ return 0;
+ }
+ 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) {
+ printk(KERN_INFO "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 0;
+ }
+
+ 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);
+
+ return 0;
+}
+
+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 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;
+ }
+
+ blk_queue_make_request(&d->blkq, aoeblk_make_request);
+ if (bdi_init(&d->blkq.backing_dev_info))
+ goto err_mempool;
+ 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_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;
+}
+
diff --git a/drivers/block/aoe/aoechr.c b/drivers/block/aoe/aoechr.c
new file mode 100644
index 0000000..200efc4
--- /dev/null
+++ b/drivers/block/aoe/aoechr.c
@@ -0,0 +1,304 @@
+/* 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/smp_lock.h>
+#include <linux/skbuff.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 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;
+
+ lock_kernel();
+ n = iminor(inode);
+ filp->private_data = (void *) (unsigned long) n;
+
+ for (i = 0; i < ARRAY_SIZE(chardevs); ++i)
+ if (chardevs[i].minor == n) {
+ unlock_kernel();
+ return 0;
+ }
+ unlock_kernel();
+ 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,
+};
+
+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);
+ }
+ 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");
+}
+
diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c
new file mode 100644
index 0000000..71ff78c
--- /dev/null
+++ b/drivers/block/aoe/aoecmd.c
@@ -0,0 +1,1086 @@
+/* Copyright (c) 2007 Coraid, Inc. See COPYING for GPL terms. */
+/*
+ * aoecmd.c
+ * Filesystem request handling methods
+ */
+
+#include <linux/hdreg.h>
+#include <linux/blkdev.h>
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include <linux/genhd.h>
+#include <linux/moduleparam.h>
+#include <net/net_namespace.h>
+#include <asm/unaligned.h>
+#include "aoe.h"
+
+static int aoe_deadsecs = 60 * 3;
+module_param(aoe_deadsecs, int, 0644);
+MODULE_PARM_DESC(aoe_deadsecs, "After aoe_deadsecs seconds, give up and fail dev.");
+
+static int aoe_maxout = 16;
+module_param(aoe_maxout, int, 0644);
+MODULE_PARM_DESC(aoe_maxout,
+ "Only aoe_maxout outstanding packets for every MAC on eX.Y.");
+
+static struct sk_buff *
+new_skb(ulong len)
+{
+ struct sk_buff *skb;
+
+ skb = alloc_skb(len, GFP_ATOMIC);
+ if (skb) {
+ skb_reset_mac_header(skb);
+ skb_reset_network_header(skb);
+ skb->protocol = __constant_htons(ETH_P_AOE);
+ skb->priority = 0;
+ skb->next = skb->prev = NULL;
+
+ /* tell the network layer not to perform IP checksums
+ * or to get the NIC to do it
+ */
+ skb->ip_summed = CHECKSUM_NONE;
+ }
+ return skb;
+}
+
+static struct frame *
+getframe(struct aoetgt *t, int tag)
+{
+ struct frame *f, *e;
+
+ f = t->frames;
+ e = f + t->nframes;
+ for (; f<e; f++)
+ if (f->tag == tag)
+ return f;
+ return NULL;
+}
+
+/*
+ * Leave the top bit clear so we have tagspace for userland.
+ * The bottom 16 bits are the xmit tick for rexmit/rttavg processing.
+ * This driver reserves tag -1 to mean "unused frame."
+ */
+static int
+newtag(struct aoetgt *t)
+{
+ register ulong n;
+
+ n = jiffies & 0xffff;
+ return n |= (++t->lasttag & 0x7fff) << 16;
+}
+
+static int
+aoehdr_atainit(struct aoedev *d, struct aoetgt *t, struct aoe_hdr *h)
+{
+ u32 host_tag = newtag(t);
+
+ memcpy(h->src, t->ifp->nd->dev_addr, sizeof h->src);
+ memcpy(h->dst, t->addr, sizeof h->dst);
+ h->type = __constant_cpu_to_be16(ETH_P_AOE);
+ h->verfl = AOE_HVER;
+ h->major = cpu_to_be16(d->aoemajor);
+ h->minor = d->aoeminor;
+ h->cmd = AOECMD_ATA;
+ h->tag = cpu_to_be32(host_tag);
+
+ return host_tag;
+}
+
+static inline void
+put_lba(struct aoe_atahdr *ah, sector_t lba)
+{
+ ah->lba0 = lba;
+ ah->lba1 = lba >>= 8;
+ ah->lba2 = lba >>= 8;
+ ah->lba3 = lba >>= 8;
+ ah->lba4 = lba >>= 8;
+ ah->lba5 = lba >>= 8;
+}
+
+static void
+ifrotate(struct aoetgt *t)
+{
+ t->ifp++;
+ if (t->ifp >= &t->ifs[NAOEIFS] || t->ifp->nd == NULL)
+ t->ifp = t->ifs;
+ if (t->ifp->nd == NULL) {
+ printk(KERN_INFO "aoe: no interface to rotate to\n");
+ BUG();
+ }
+}
+
+static void
+skb_pool_put(struct aoedev *d, struct sk_buff *skb)
+{
+ __skb_queue_tail(&d->skbpool, skb);
+}
+
+static struct sk_buff *
+skb_pool_get(struct aoedev *d)
+{
+ struct sk_buff *skb = skb_peek(&d->skbpool);
+
+ if (skb && atomic_read(&skb_shinfo(skb)->dataref) == 1) {
+ __skb_unlink(skb, &d->skbpool);
+ return skb;
+ }
+ if (skb_queue_len(&d->skbpool) < NSKBPOOLMAX &&
+ (skb = new_skb(ETH_ZLEN)))
+ return skb;
+
+ return NULL;
+}
+
+/* freeframe is where we do our load balancing so it's a little hairy. */
+static struct frame *
+freeframe(struct aoedev *d)
+{
+ struct frame *f, *e, *rf;
+ struct aoetgt **t;
+ struct sk_buff *skb;
+
+ if (d->targets[0] == NULL) { /* shouldn't happen, but I'm paranoid */
+ printk(KERN_ERR "aoe: NULL TARGETS!\n");
+ return NULL;
+ }
+ t = d->tgt;
+ t++;
+ if (t >= &d->targets[NTARGETS] || !*t)
+ t = d->targets;
+ for (;;) {
+ if ((*t)->nout < (*t)->maxout
+ && t != d->htgt
+ && (*t)->ifp->nd) {
+ rf = NULL;
+ f = (*t)->frames;
+ e = f + (*t)->nframes;
+ for (; f < e; f++) {
+ if (f->tag != FREETAG)
+ continue;
+ skb = f->skb;
+ if (!skb
+ && !(f->skb = skb = new_skb(ETH_ZLEN)))
+ continue;
+ if (atomic_read(&skb_shinfo(skb)->dataref)
+ != 1) {
+ if (!rf)
+ rf = f;
+ continue;
+ }
+gotone: skb_shinfo(skb)->nr_frags = skb->data_len = 0;
+ skb_trim(skb, 0);
+ d->tgt = t;
+ ifrotate(*t);
+ return f;
+ }
+ /* Work can be done, but the network layer is
+ holding our precious packets. Try to grab
+ one from the pool. */
+ f = rf;
+ if (f == NULL) { /* more paranoia */
+ printk(KERN_ERR
+ "aoe: freeframe: %s.\n",
+ "unexpected null rf");
+ d->flags |= DEVFL_KICKME;
+ return NULL;
+ }
+ skb = skb_pool_get(d);
+ if (skb) {
+ skb_pool_put(d, f->skb);
+ f->skb = skb;
+ goto gotone;
+ }
+ (*t)->dataref++;
+ if ((*t)->nout == 0)
+ d->flags |= DEVFL_KICKME;
+ }
+ if (t == d->tgt) /* we've looped and found nada */
+ break;
+ t++;
+ if (t >= &d->targets[NTARGETS] || !*t)
+ t = d->targets;
+ }
+ return NULL;
+}
+
+static int
+aoecmd_ata_rw(struct aoedev *d)
+{
+ struct frame *f;
+ struct aoe_hdr *h;
+ struct aoe_atahdr *ah;
+ struct buf *buf;
+ struct bio_vec *bv;
+ struct aoetgt *t;
+ struct sk_buff *skb;
+ ulong bcnt;
+ char writebit, extbit;
+
+ writebit = 0x10;
+ extbit = 0x4;
+
+ f = freeframe(d);
+ if (f == NULL)
+ return 0;
+ t = *d->tgt;
+ buf = d->inprocess;
+ bv = buf->bv;
+ bcnt = t->ifp->maxbcnt;
+ if (bcnt == 0)
+ bcnt = DEFAULTBCNT;
+ if (bcnt > buf->bv_resid)
+ bcnt = buf->bv_resid;
+ /* initialize the headers & frame */
+ skb = f->skb;
+ h = (struct aoe_hdr *) skb_mac_header(skb);
+ ah = (struct aoe_atahdr *) (h+1);
+ skb_put(skb, sizeof *h + sizeof *ah);
+ memset(h, 0, skb->len);
+ f->tag = aoehdr_atainit(d, t, h);
+ t->nout++;
+ f->waited = 0;
+ f->buf = buf;
+ f->bufaddr = page_address(bv->bv_page) + buf->bv_off;
+ f->bcnt = bcnt;
+ f->lba = buf->sector;
+
+ /* set up ata header */
+ ah->scnt = bcnt >> 9;
+ put_lba(ah, buf->sector);
+ if (d->flags & DEVFL_EXT) {
+ ah->aflags |= AOEAFL_EXT;
+ } else {
+ extbit = 0;
+ ah->lba3 &= 0x0f;
+ ah->lba3 |= 0xe0; /* LBA bit + obsolete 0xa0 */
+ }
+ if (bio_data_dir(buf->bio) == WRITE) {
+ skb_fill_page_desc(skb, 0, bv->bv_page, buf->bv_off, bcnt);
+ ah->aflags |= AOEAFL_WRITE;
+ skb->len += bcnt;
+ skb->data_len = bcnt;
+ t->wpkts++;
+ } else {
+ t->rpkts++;
+ writebit = 0;
+ }
+
+ ah->cmdstat = WIN_READ | writebit | extbit;
+
+ /* mark all tracking fields and load out */
+ buf->nframesout += 1;
+ buf->bv_off += bcnt;
+ buf->bv_resid -= bcnt;
+ buf->resid -= bcnt;
+ buf->sector += bcnt >> 9;
+ if (buf->resid == 0) {
+ d->inprocess = NULL;
+ } else if (buf->bv_resid == 0) {
+ buf->bv = ++bv;
+ buf->bv_resid = bv->bv_len;
+ WARN_ON(buf->bv_resid == 0);
+ buf->bv_off = bv->bv_offset;
+ }
+
+ skb->dev = t->ifp->nd;
+ skb = skb_clone(skb, GFP_ATOMIC);
+ if (skb)
+ __skb_queue_tail(&d->sendq, skb);
+ return 1;
+}
+
+/* some callers cannot sleep, and they can call this function,
+ * transmitting the packets later, when interrupts are on
+ */
+static void
+aoecmd_cfg_pkts(ushort aoemajor, unsigned char aoeminor, struct sk_buff_head *queue)
+{
+ struct aoe_hdr *h;
+ struct aoe_cfghdr *ch;
+ struct sk_buff *skb;
+ struct net_device *ifp;
+
+ read_lock(&dev_base_lock);
+ for_each_netdev(&init_net, ifp) {
+ dev_hold(ifp);
+ if (!is_aoe_netif(ifp))
+ goto cont;
+
+ skb = new_skb(sizeof *h + sizeof *ch);
+ if (skb == NULL) {
+ printk(KERN_INFO "aoe: skb alloc failure\n");
+ goto cont;
+ }
+ skb_put(skb, sizeof *h + sizeof *ch);
+ skb->dev = ifp;
+ __skb_queue_tail(queue, skb);
+ h = (struct aoe_hdr *) skb_mac_header(skb);
+ memset(h, 0, sizeof *h + sizeof *ch);
+
+ memset(h->dst, 0xff, sizeof h->dst);
+ memcpy(h->src, ifp->dev_addr, sizeof h->src);
+ h->type = __constant_cpu_to_be16(ETH_P_AOE);
+ h->verfl = AOE_HVER;
+ h->major = cpu_to_be16(aoemajor);
+ h->minor = aoeminor;
+ h->cmd = AOECMD_CFG;
+
+cont:
+ dev_put(ifp);
+ }
+ read_unlock(&dev_base_lock);
+}
+
+static void
+resend(struct aoedev *d, struct aoetgt *t, struct frame *f)
+{
+ struct sk_buff *skb;
+ struct aoe_hdr *h;
+ struct aoe_atahdr *ah;
+ char buf[128];
+ u32 n;
+
+ ifrotate(t);
+ n = newtag(t);
+ skb = f->skb;
+ h = (struct aoe_hdr *) skb_mac_header(skb);
+ ah = (struct aoe_atahdr *) (h+1);
+
+ snprintf(buf, sizeof buf,
+ "%15s e%ld.%d oldtag=%08x@%08lx newtag=%08x "
+ "s=%012llx d=%012llx nout=%d\n",
+ "retransmit", d->aoemajor, d->aoeminor, f->tag, jiffies, n,
+ mac_addr(h->src),
+ mac_addr(h->dst), t->nout);
+ aoechr_error(buf);
+
+ f->tag = n;
+ h->tag = cpu_to_be32(n);
+ memcpy(h->dst, t->addr, sizeof h->dst);
+ memcpy(h->src, t->ifp->nd->dev_addr, sizeof h->src);
+
+ switch (ah->cmdstat) {
+ default:
+ break;
+ case WIN_READ:
+ case WIN_READ_EXT:
+ case WIN_WRITE:
+ case WIN_WRITE_EXT:
+ put_lba(ah, f->lba);
+
+ n = f->bcnt;
+ if (n > DEFAULTBCNT)
+ n = DEFAULTBCNT;
+ ah->scnt = n >> 9;
+ if (ah->aflags & AOEAFL_WRITE) {
+ skb_fill_page_desc(skb, 0, virt_to_page(f->bufaddr),
+ offset_in_page(f->bufaddr), n);
+ skb->len = sizeof *h + sizeof *ah + n;
+ skb->data_len = n;
+ }
+ }
+ skb->dev = t->ifp->nd;
+ skb = skb_clone(skb, GFP_ATOMIC);
+ if (skb == NULL)
+ return;
+ __skb_queue_tail(&d->sendq, skb);
+}
+
+static int
+tsince(int tag)
+{
+ int n;
+
+ n = jiffies & 0xffff;
+ n -= tag & 0xffff;
+ if (n < 0)
+ n += 1<<16;
+ return n;
+}
+
+static struct aoeif *
+getif(struct aoetgt *t, struct net_device *nd)
+{
+ struct aoeif *p, *e;
+
+ p = t->ifs;
+ e = p + NAOEIFS;
+ for (; p < e; p++)
+ if (p->nd == nd)
+ return p;
+ return NULL;
+}
+
+static struct aoeif *
+addif(struct aoetgt *t, struct net_device *nd)
+{
+ struct aoeif *p;
+
+ p = getif(t, NULL);
+ if (!p)
+ return NULL;
+ p->nd = nd;
+ p->maxbcnt = DEFAULTBCNT;
+ p->lost = 0;
+ p->lostjumbo = 0;
+ return p;
+}
+
+static void
+ejectif(struct aoetgt *t, struct aoeif *ifp)
+{
+ struct aoeif *e;
+ ulong n;
+
+ e = t->ifs + NAOEIFS - 1;
+ n = (e - ifp) * sizeof *ifp;
+ memmove(ifp, ifp+1, n);
+ e->nd = NULL;
+}
+
+static int
+sthtith(struct aoedev *d)
+{
+ struct frame *f, *e, *nf;
+ struct sk_buff *skb;
+ struct aoetgt *ht = *d->htgt;
+
+ f = ht->frames;
+ e = f + ht->nframes;
+ for (; f < e; f++) {
+ if (f->tag == FREETAG)
+ continue;
+ nf = freeframe(d);
+ if (!nf)
+ return 0;
+ skb = nf->skb;
+ *nf = *f;
+ f->skb = skb;
+ f->tag = FREETAG;
+ nf->waited = 0;
+ ht->nout--;
+ (*d->tgt)->nout++;
+ resend(d, *d->tgt, nf);
+ }
+ /* he's clean, he's useless. take away his interfaces */
+ memset(ht->ifs, 0, sizeof ht->ifs);
+ d->htgt = NULL;
+ return 1;
+}
+
+static inline unsigned char
+ata_scnt(unsigned char *packet) {
+ struct aoe_hdr *h;
+ struct aoe_atahdr *ah;
+
+ h = (struct aoe_hdr *) packet;
+ ah = (struct aoe_atahdr *) (h+1);
+ return ah->scnt;
+}
+
+static void
+rexmit_timer(ulong vp)
+{
+ struct sk_buff_head queue;
+ struct aoedev *d;
+ struct aoetgt *t, **tt, **te;
+ struct aoeif *ifp;
+ struct frame *f, *e;
+ register long timeout;
+ ulong flags, n;
+
+ d = (struct aoedev *) vp;
+
+ /* timeout is always ~150% of the moving average */
+ timeout = d->rttavg;
+ timeout += timeout >> 1;
+
+ spin_lock_irqsave(&d->lock, flags);
+
+ if (d->flags & DEVFL_TKILL) {
+ spin_unlock_irqrestore(&d->lock, flags);
+ return;
+ }
+ tt = d->targets;
+ te = tt + NTARGETS;
+ for (; tt < te && *tt; tt++) {
+ t = *tt;
+ f = t->frames;
+ e = f + t->nframes;
+ for (; f < e; f++) {
+ if (f->tag == FREETAG
+ || tsince(f->tag) < timeout)
+ continue;
+ n = f->waited += timeout;
+ n /= HZ;
+ if (n > aoe_deadsecs) {
+ /* waited too long. device failure. */
+ aoedev_downdev(d);
+ break;
+ }
+
+ if (n > HELPWAIT /* see if another target can help */
+ && (tt != d->targets || d->targets[1]))
+ d->htgt = tt;
+
+ if (t->nout == t->maxout) {
+ if (t->maxout > 1)
+ t->maxout--;
+ t->lastwadj = jiffies;
+ }
+
+ ifp = getif(t, f->skb->dev);
+ if (ifp && ++ifp->lost > (t->nframes << 1)
+ && (ifp != t->ifs || t->ifs[1].nd)) {
+ ejectif(t, ifp);
+ ifp = NULL;
+ }
+
+ if (ata_scnt(skb_mac_header(f->skb)) > DEFAULTBCNT / 512
+ && ifp && ++ifp->lostjumbo > (t->nframes << 1)
+ && ifp->maxbcnt != DEFAULTBCNT) {
+ printk(KERN_INFO
+ "aoe: e%ld.%d: "
+ "too many lost jumbo on "
+ "%s:%012llx - "
+ "falling back to %d frames.\n",
+ d->aoemajor, d->aoeminor,
+ ifp->nd->name, mac_addr(t->addr),
+ DEFAULTBCNT);
+ ifp->maxbcnt = 0;
+ }
+ resend(d, t, f);
+ }
+
+ /* window check */
+ if (t->nout == t->maxout
+ && t->maxout < t->nframes
+ && (jiffies - t->lastwadj)/HZ > 10) {
+ t->maxout++;
+ t->lastwadj = jiffies;
+ }
+ }
+
+ if (!skb_queue_empty(&d->sendq)) {
+ n = d->rttavg <<= 1;
+ if (n > MAXTIMER)
+ d->rttavg = MAXTIMER;
+ }
+
+ if (d->flags & DEVFL_KICKME || d->htgt) {
+ d->flags &= ~DEVFL_KICKME;
+ aoecmd_work(d);
+ }
+
+ __skb_queue_head_init(&queue);
+ skb_queue_splice_init(&d->sendq, &queue);
+
+ d->timer.expires = jiffies + TIMERTICK;
+ add_timer(&d->timer);
+
+ spin_unlock_irqrestore(&d->lock, flags);
+
+ aoenet_xmit(&queue);
+}
+
+/* enters with d->lock held */
+void
+aoecmd_work(struct aoedev *d)
+{
+ struct buf *buf;
+loop:
+ if (d->htgt && !sthtith(d))
+ return;
+ if (d->inprocess == NULL) {
+ if (list_empty(&d->bufq))
+ return;
+ buf = container_of(d->bufq.next, struct buf, bufs);
+ list_del(d->bufq.next);
+ d->inprocess = buf;
+ }
+ if (aoecmd_ata_rw(d))
+ goto loop;
+}
+
+/* this function performs work that has been deferred until sleeping is OK
+ */
+void
+aoecmd_sleepwork(struct work_struct *work)
+{
+ struct aoedev *d = container_of(work, struct aoedev, work);
+
+ if (d->flags & DEVFL_GDALLOC)
+ aoeblk_gdalloc(d);
+
+ if (d->flags & DEVFL_NEWSIZE) {
+ struct block_device *bd;
+ unsigned long flags;
+ u64 ssize;
+
+ ssize = get_capacity(d->gd);
+ bd = bdget_disk(d->gd, 0);
+
+ if (bd) {
+ mutex_lock(&bd->bd_inode->i_mutex);
+ i_size_write(bd->bd_inode, (loff_t)ssize<<9);
+ mutex_unlock(&bd->bd_inode->i_mutex);
+ bdput(bd);
+ }
+ spin_lock_irqsave(&d->lock, flags);
+ d->flags |= DEVFL_UP;
+ d->flags &= ~DEVFL_NEWSIZE;
+ spin_unlock_irqrestore(&d->lock, flags);
+ }
+}
+
+static void
+ataid_complete(struct aoedev *d, struct aoetgt *t, unsigned char *id)
+{
+ u64 ssize;
+ u16 n;
+
+ /* word 83: command set supported */
+ n = get_unaligned_le16(&id[83 << 1]);
+
+ /* word 86: command set/feature enabled */
+ n |= get_unaligned_le16(&id[86 << 1]);
+
+ if (n & (1<<10)) { /* bit 10: LBA 48 */
+ d->flags |= DEVFL_EXT;
+
+ /* word 100: number lba48 sectors */
+ ssize = get_unaligned_le64(&id[100 << 1]);
+
+ /* set as in ide-disk.c:init_idedisk_capacity */
+ d->geo.cylinders = ssize;
+ d->geo.cylinders /= (255 * 63);
+ d->geo.heads = 255;
+ d->geo.sectors = 63;
+ } else {
+ d->flags &= ~DEVFL_EXT;
+
+ /* number lba28 sectors */
+ ssize = get_unaligned_le32(&id[60 << 1]);
+
+ /* NOTE: obsolete in ATA 6 */
+ d->geo.cylinders = get_unaligned_le16(&id[54 << 1]);
+ d->geo.heads = get_unaligned_le16(&id[55 << 1]);
+ d->geo.sectors = get_unaligned_le16(&id[56 << 1]);
+ }
+
+ if (d->ssize != ssize)
+ printk(KERN_INFO
+ "aoe: %012llx e%ld.%d v%04x has %llu sectors\n",
+ mac_addr(t->addr),
+ d->aoemajor, d->aoeminor,
+ d->fw_ver, (long long)ssize);
+ d->ssize = ssize;
+ d->geo.start = 0;
+ if (d->flags & (DEVFL_GDALLOC|DEVFL_NEWSIZE))
+ return;
+ if (d->gd != NULL) {
+ set_capacity(d->gd, ssize);
+ d->flags |= DEVFL_NEWSIZE;
+ } else
+ d->flags |= DEVFL_GDALLOC;
+ schedule_work(&d->work);
+}
+
+static void
+calc_rttavg(struct aoedev *d, int rtt)
+{
+ register long n;
+
+ n = rtt;
+ if (n < 0) {
+ n = -rtt;
+ if (n < MINTIMER)
+ n = MINTIMER;
+ else if (n > MAXTIMER)
+ n = MAXTIMER;
+ d->mintimer += (n - d->mintimer) >> 1;
+ } else if (n < d->mintimer)
+ n = d->mintimer;
+ else if (n > MAXTIMER)
+ n = MAXTIMER;
+
+ /* g == .25; cf. Congestion Avoidance and Control, Jacobson & Karels; 1988 */
+ n -= d->rttavg;
+ d->rttavg += n >> 2;
+}
+
+static struct aoetgt *
+gettgt(struct aoedev *d, char *addr)
+{
+ struct aoetgt **t, **e;
+
+ t = d->targets;
+ e = t + NTARGETS;
+ for (; t < e && *t; t++)
+ if (memcmp((*t)->addr, addr, sizeof((*t)->addr)) == 0)
+ return *t;
+ return NULL;
+}
+
+static inline void
+diskstats(struct gendisk *disk, struct bio *bio, ulong duration, sector_t sector)
+{
+ unsigned long n_sect = bio->bi_size >> 9;
+ const int rw = bio_data_dir(bio);
+ struct hd_struct *part;
+ int cpu;
+
+ cpu = part_stat_lock();
+ part = disk_map_sector_rcu(disk, sector);
+
+ part_stat_inc(cpu, part, ios[rw]);
+ part_stat_add(cpu, part, ticks[rw], duration);
+ part_stat_add(cpu, part, sectors[rw], n_sect);
+ part_stat_add(cpu, part, io_ticks, duration);
+
+ part_stat_unlock();
+}
+
+void
+aoecmd_ata_rsp(struct sk_buff *skb)
+{
+ struct sk_buff_head queue;
+ struct aoedev *d;
+ struct aoe_hdr *hin, *hout;
+ struct aoe_atahdr *ahin, *ahout;
+ struct frame *f;
+ struct buf *buf;
+ struct aoetgt *t;
+ struct aoeif *ifp;
+ register long n;
+ ulong flags;
+ char ebuf[128];
+ u16 aoemajor;
+
+ hin = (struct aoe_hdr *) skb_mac_header(skb);
+ aoemajor = get_unaligned_be16(&hin->major);
+ d = aoedev_by_aoeaddr(aoemajor, hin->minor);
+ if (d == NULL) {
+ snprintf(ebuf, sizeof ebuf, "aoecmd_ata_rsp: ata response "
+ "for unknown device %d.%d\n",
+ aoemajor, hin->minor);
+ aoechr_error(ebuf);
+ return;
+ }
+
+ spin_lock_irqsave(&d->lock, flags);
+
+ n = get_unaligned_be32(&hin->tag);
+ t = gettgt(d, hin->src);
+ if (t == NULL) {
+ printk(KERN_INFO "aoe: can't find target e%ld.%d:%012llx\n",
+ d->aoemajor, d->aoeminor, mac_addr(hin->src));
+ spin_unlock_irqrestore(&d->lock, flags);
+ return;
+ }
+ f = getframe(t, n);
+ if (f == NULL) {
+ calc_rttavg(d, -tsince(n));
+ spin_unlock_irqrestore(&d->lock, flags);
+ snprintf(ebuf, sizeof ebuf,
+ "%15s e%d.%d tag=%08x@%08lx\n",
+ "unexpected rsp",
+ get_unaligned_be16(&hin->major),
+ hin->minor,
+ get_unaligned_be32(&hin->tag),
+ jiffies);
+ aoechr_error(ebuf);
+ return;
+ }
+
+ calc_rttavg(d, tsince(f->tag));
+
+ ahin = (struct aoe_atahdr *) (hin+1);
+ hout = (struct aoe_hdr *) skb_mac_header(f->skb);
+ ahout = (struct aoe_atahdr *) (hout+1);
+ buf = f->buf;
+
+ if (ahin->cmdstat & 0xa9) { /* these bits cleared on success */
+ printk(KERN_ERR
+ "aoe: ata error cmd=%2.2Xh stat=%2.2Xh from e%ld.%d\n",
+ ahout->cmdstat, ahin->cmdstat,
+ d->aoemajor, d->aoeminor);
+ if (buf)
+ buf->flags |= BUFFL_FAIL;
+ } else {
+ if (d->htgt && t == *d->htgt) /* I'll help myself, thank you. */
+ d->htgt = NULL;
+ n = ahout->scnt << 9;
+ switch (ahout->cmdstat) {
+ case WIN_READ:
+ case WIN_READ_EXT:
+ if (skb->len - sizeof *hin - sizeof *ahin < n) {
+ printk(KERN_ERR
+ "aoe: %s. skb->len=%d need=%ld\n",
+ "runt data size in read", skb->len, n);
+ /* fail frame f? just returning will rexmit. */
+ spin_unlock_irqrestore(&d->lock, flags);
+ return;
+ }
+ memcpy(f->bufaddr, ahin+1, n);
+ case WIN_WRITE:
+ case WIN_WRITE_EXT:
+ ifp = getif(t, skb->dev);
+ if (ifp) {
+ ifp->lost = 0;
+ if (n > DEFAULTBCNT)
+ ifp->lostjumbo = 0;
+ }
+ if (f->bcnt -= n) {
+ f->lba += n >> 9;
+ f->bufaddr += n;
+ resend(d, t, f);
+ goto xmit;
+ }
+ break;
+ case WIN_IDENTIFY:
+ if (skb->len - sizeof *hin - sizeof *ahin < 512) {
+ printk(KERN_INFO
+ "aoe: runt data size in ataid. skb->len=%d\n",
+ skb->len);
+ spin_unlock_irqrestore(&d->lock, flags);
+ return;
+ }
+ ataid_complete(d, t, (char *) (ahin+1));
+ break;
+ default:
+ printk(KERN_INFO
+ "aoe: unrecognized ata command %2.2Xh for %d.%d\n",
+ ahout->cmdstat,
+ get_unaligned_be16(&hin->major),
+ hin->minor);
+ }
+ }
+
+ if (buf && --buf->nframesout == 0 && buf->resid == 0) {
+ diskstats(d->gd, buf->bio, jiffies - buf->stime, buf->sector);
+ n = (buf->flags & BUFFL_FAIL) ? -EIO : 0;
+ bio_endio(buf->bio, n);
+ mempool_free(buf, d->bufpool);
+ }
+
+ f->buf = NULL;
+ f->tag = FREETAG;
+ t->nout--;
+
+ aoecmd_work(d);
+xmit:
+ __skb_queue_head_init(&queue);
+ skb_queue_splice_init(&d->sendq, &queue);
+
+ spin_unlock_irqrestore(&d->lock, flags);
+ aoenet_xmit(&queue);
+}
+
+void
+aoecmd_cfg(ushort aoemajor, unsigned char aoeminor)
+{
+ struct sk_buff_head queue;
+
+ __skb_queue_head_init(&queue);
+ aoecmd_cfg_pkts(aoemajor, aoeminor, &queue);
+ aoenet_xmit(&queue);
+}
+
+struct sk_buff *
+aoecmd_ata_id(struct aoedev *d)
+{
+ struct aoe_hdr *h;
+ struct aoe_atahdr *ah;
+ struct frame *f;
+ struct sk_buff *skb;
+ struct aoetgt *t;
+
+ f = freeframe(d);
+ if (f == NULL)
+ return NULL;
+
+ t = *d->tgt;
+
+ /* initialize the headers & frame */
+ skb = f->skb;
+ h = (struct aoe_hdr *) skb_mac_header(skb);
+ ah = (struct aoe_atahdr *) (h+1);
+ skb_put(skb, sizeof *h + sizeof *ah);
+ memset(h, 0, skb->len);
+ f->tag = aoehdr_atainit(d, t, h);
+ t->nout++;
+ f->waited = 0;
+
+ /* set up ata header */
+ ah->scnt = 1;
+ ah->cmdstat = WIN_IDENTIFY;
+ ah->lba3 = 0xa0;
+
+ skb->dev = t->ifp->nd;
+
+ d->rttavg = MAXTIMER;
+ d->timer.function = rexmit_timer;
+
+ return skb_clone(skb, GFP_ATOMIC);
+}
+
+static struct aoetgt *
+addtgt(struct aoedev *d, char *addr, ulong nframes)
+{
+ struct aoetgt *t, **tt, **te;
+ struct frame *f, *e;
+
+ tt = d->targets;
+ te = tt + NTARGETS;
+ for (; tt < te && *tt; tt++)
+ ;
+
+ if (tt == te) {
+ printk(KERN_INFO
+ "aoe: device addtgt failure; too many targets\n");
+ return NULL;
+ }
+ t = kcalloc(1, sizeof *t, GFP_ATOMIC);
+ f = kcalloc(nframes, sizeof *f, GFP_ATOMIC);
+ if (!t || !f) {
+ kfree(f);
+ kfree(t);
+ printk(KERN_INFO "aoe: cannot allocate memory to add target\n");
+ return NULL;
+ }
+
+ t->nframes = nframes;
+ t->frames = f;
+ e = f + nframes;
+ for (; f < e; f++)
+ f->tag = FREETAG;
+ memcpy(t->addr, addr, sizeof t->addr);
+ t->ifp = t->ifs;
+ t->maxout = t->nframes;
+ return *tt = t;
+}
+
+void
+aoecmd_cfg_rsp(struct sk_buff *skb)
+{
+ struct aoedev *d;
+ struct aoe_hdr *h;
+ struct aoe_cfghdr *ch;
+ struct aoetgt *t;
+ struct aoeif *ifp;
+ ulong flags, sysminor, aoemajor;
+ struct sk_buff *sl;
+ u16 n;
+
+ h = (struct aoe_hdr *) skb_mac_header(skb);
+ ch = (struct aoe_cfghdr *) (h+1);
+
+ /*
+ * Enough people have their dip switches set backwards to
+ * warrant a loud message for this special case.
+ */
+ aoemajor = get_unaligned_be16(&h->major);
+ if (aoemajor == 0xfff) {
+ printk(KERN_ERR "aoe: Warning: shelf address is all ones. "
+ "Check shelf dip switches.\n");
+ return;
+ }
+
+ sysminor = SYSMINOR(aoemajor, h->minor);
+ if (sysminor * AOE_PARTITIONS + AOE_PARTITIONS > MINORMASK) {
+ printk(KERN_INFO "aoe: e%ld.%d: minor number too large\n",
+ aoemajor, (int) h->minor);
+ return;
+ }
+
+ n = be16_to_cpu(ch->bufcnt);
+ if (n > aoe_maxout) /* keep it reasonable */
+ n = aoe_maxout;
+
+ d = aoedev_by_sysminor_m(sysminor);
+ if (d == NULL) {
+ printk(KERN_INFO "aoe: device sysminor_m failure\n");
+ return;
+ }
+
+ spin_lock_irqsave(&d->lock, flags);
+
+ t = gettgt(d, h->src);
+ if (!t) {
+ t = addtgt(d, h->src, n);
+ if (!t) {
+ spin_unlock_irqrestore(&d->lock, flags);
+ return;
+ }
+ }
+ ifp = getif(t, skb->dev);
+ if (!ifp) {
+ ifp = addif(t, skb->dev);
+ if (!ifp) {
+ printk(KERN_INFO
+ "aoe: device addif failure; "
+ "too many interfaces?\n");
+ spin_unlock_irqrestore(&d->lock, flags);
+ return;
+ }
+ }
+ if (ifp->maxbcnt) {
+ n = ifp->nd->mtu;
+ n -= sizeof (struct aoe_hdr) + sizeof (struct aoe_atahdr);
+ n /= 512;
+ if (n > ch->scnt)
+ n = ch->scnt;
+ n = n ? n * 512 : DEFAULTBCNT;
+ if (n != ifp->maxbcnt) {
+ printk(KERN_INFO
+ "aoe: e%ld.%d: setting %d%s%s:%012llx\n",
+ d->aoemajor, d->aoeminor, n,
+ " byte data frames on ", ifp->nd->name,
+ mac_addr(t->addr));
+ ifp->maxbcnt = n;
+ }
+ }
+
+ /* don't change users' perspective */
+ if (d->nopen) {
+ spin_unlock_irqrestore(&d->lock, flags);
+ return;
+ }
+ d->fw_ver = be16_to_cpu(ch->fwver);
+
+ sl = aoecmd_ata_id(d);
+
+ spin_unlock_irqrestore(&d->lock, flags);
+
+ if (sl) {
+ struct sk_buff_head queue;
+ __skb_queue_head_init(&queue);
+ __skb_queue_tail(&queue, sl);
+ aoenet_xmit(&queue);
+ }
+}
+
+void
+aoecmd_cleanslate(struct aoedev *d)
+{
+ struct aoetgt **t, **te;
+ struct aoeif *p, *e;
+
+ d->mintimer = MINTIMER;
+
+ t = d->targets;
+ te = t + NTARGETS;
+ for (; t < te && *t; t++) {
+ (*t)->maxout = (*t)->nframes;
+ p = (*t)->ifs;
+ e = p + NAOEIFS;
+ for (; p < e; p++) {
+ p->lostjumbo = 0;
+ p->lost = 0;
+ p->maxbcnt = DEFAULTBCNT;
+ }
+ }
+}
diff --git a/drivers/block/aoe/aoedev.c b/drivers/block/aoe/aoedev.c
new file mode 100644
index 0000000..cc25057
--- /dev/null
+++ b/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 "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;
+
+ 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);
+ 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);
+ }
+
+ flush_scheduled_work();
+ 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;
+
+ flush_scheduled_work();
+
+ 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;
+}
diff --git a/drivers/block/aoe/aoemain.c b/drivers/block/aoe/aoemain.c
new file mode 100644
index 0000000..7f83ad9
--- /dev/null
+++ b/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);
+
diff --git a/drivers/block/aoe/aoenet.c b/drivers/block/aoe/aoenet.c
new file mode 100644
index 0000000..b67629a
--- /dev/null
+++ b/drivers/block/aoe/aoenet.c
@@ -0,0 +1,182 @@
+/* Copyright (c) 2007 Coraid, Inc. See COPYING for GPL terms. */
+/*
+ * aoenet.c
+ * Ethernet portion of AoE driver
+ */
+
+#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;
+}
+
+unsigned long long
+mac_addr(char addr[6])
+{
+ __be64 n = 0;
+ char *p = (char *) &n;
+
+ memcpy(p + 2, addr, 6); /* (sizeof addr != 6) */
+
+ return (unsigned long long) __be64_to_cpu(n);
+}
+
+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 = {
+ .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);
+}
+
OpenPOWER on IntegriCloud