when a discarded area is read the discard_zeroes_data
parameter will be set to one. Otherwise it will be 0 and
the result of reading a discarded area is undefined.
+
+What: /sys/block/<disk>/queue/write_same_max_bytes
+Date: January 2012
+Contact: Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+ Some devices support a write same operation in which a
+ single data block can be written to a range of several
+ contiguous blocks on storage. This can be used to wipe
+ areas on disk or to initialize drives in a RAID
+ configuration. write_same_max_bytes indicates how many
+ bytes can be written in a single write same command. If
+ write_same_max_bytes is 0, write same is not supported
+ by the device.
+
bio_end_io_t *bi_end_io; /* bi_end_io (bio) */
atomic_t bi_cnt; /* pin count: free when it hits zero */
void *bi_private;
- bio_destructor_t *bi_destructor; /* bi_destructor (bio) */
};
With this multipage bio design:
so bio_alloc(gfp_mask, nr_iovecs) will allocate a vec_list of the
given size from these slabs.
-The bi_destructor() routine takes into account the possibility of the bio
-having originated from a different source (see later discussions on
-n/w to block transfers and kvec_cb)
-
The bio_get() routine may be used to hold an extra reference on a bio prior
to i/o submission, if the bio fields are likely to be accessed after the
i/o is issued (since the bio may otherwise get freed in case i/o completion
--- /dev/null
+Percpu rw semaphores
+--------------------
+
+Percpu rw semaphores is a new read-write semaphore design that is
+optimized for locking for reading.
+
+The problem with traditional read-write semaphores is that when multiple
+cores take the lock for reading, the cache line containing the semaphore
+is bouncing between L1 caches of the cores, causing performance
+degradation.
+
+Locking for reading is very fast, it uses RCU and it avoids any atomic
+instruction in the lock and unlock path. On the other hand, locking for
+writing is very expensive, it calls synchronize_rcu() that can take
+hundreds of milliseconds.
+
+The lock is declared with "struct percpu_rw_semaphore" type.
+The lock is initialized percpu_init_rwsem, it returns 0 on success and
+-ENOMEM on allocation failure.
+The lock must be freed with percpu_free_rwsem to avoid memory leak.
+
+The lock is locked for read with percpu_down_read, percpu_up_read and
+for write with percpu_down_write, percpu_up_write.
+
+The idea of using RCU for optimized rw-lock was introduced by
+Eric Dumazet <eric.dumazet@gmail.com>.
+The code was written by Mikulas Patocka <mpatocka@redhat.com>
F: drivers/pinctrl/spear/
PKTCDVD DRIVER
-M: Peter Osterlund <petero2@telia.com>
+M: Jiri Kosina <jkosina@suse.cz>
S: Maintained
F: drivers/block/pktcdvd.c
F: include/linux/pktcdvd.h
S: Maintained
F: drivers/memstick/host/tifm_ms.c
+SONY MEMORYSTICK STANDARD SUPPORT
+M: Maxim Levitsky <maximlevitsky@gmail.com>
+S: Maintained
+F: drivers/memstick/core/ms_block.*
+
SOUND
M: Jaroslav Kysela <perex@perex.cz>
M: Takashi Iwai <tiwai@suse.de>
/*
* A queue starts its life with bypass turned on to avoid
* unnecessary bypass on/off overhead and nasty surprises during
- * init. The initial bypass will be finished at the end of
- * blk_init_allocated_queue().
+ * init. The initial bypass will be finished when the queue is
+ * registered by blk_register_queue().
*/
q->bypass_depth = 1;
__set_bit(QUEUE_FLAG_BYPASS, &q->queue_flags);
q->request_fn = rfn;
q->prep_rq_fn = NULL;
q->unprep_rq_fn = NULL;
- q->queue_flags = QUEUE_FLAG_DEFAULT;
+ q->queue_flags |= QUEUE_FLAG_DEFAULT;
/* Override internal queue lock with supplied lock pointer */
if (lock)
/* init elevator */
if (elevator_init(q, NULL))
return NULL;
-
- blk_queue_congestion_threshold(q);
-
- /* all done, end the initial bypass */
- blk_queue_bypass_end(q);
return q;
}
EXPORT_SYMBOL(blk_init_allocated_queue);
goto end_io;
}
- if (unlikely(!(bio->bi_rw & REQ_DISCARD) &&
- nr_sectors > queue_max_hw_sectors(q))) {
+ if (likely(bio_is_rw(bio) &&
+ nr_sectors > queue_max_hw_sectors(q))) {
printk(KERN_ERR "bio too big device %s (%u > %u)\n",
bdevname(bio->bi_bdev, b),
bio_sectors(bio),
if ((bio->bi_rw & REQ_DISCARD) &&
(!blk_queue_discard(q) ||
- ((bio->bi_rw & REQ_SECURE) &&
- !blk_queue_secdiscard(q)))) {
+ ((bio->bi_rw & REQ_SECURE) && !blk_queue_secdiscard(q)))) {
+ err = -EOPNOTSUPP;
+ goto end_io;
+ }
+
+ if (bio->bi_rw & REQ_WRITE_SAME && !bdev_write_same(bio->bi_bdev)) {
err = -EOPNOTSUPP;
goto end_io;
}
*/
void submit_bio(int rw, struct bio *bio)
{
- int count = bio_sectors(bio);
-
bio->bi_rw |= rw;
/*
* If it's a regular read/write or a barrier with data attached,
* go through the normal accounting stuff before submission.
*/
- if (bio_has_data(bio) && !(rw & REQ_DISCARD)) {
+ if (bio_has_data(bio)) {
+ unsigned int count;
+
+ if (unlikely(rw & REQ_WRITE_SAME))
+ count = bdev_logical_block_size(bio->bi_bdev) >> 9;
+ else
+ count = bio_sectors(bio);
+
if (rw & WRITE) {
count_vm_events(PGPGOUT, count);
} else {
*/
int blk_rq_check_limits(struct request_queue *q, struct request *rq)
{
- if (rq->cmd_flags & REQ_DISCARD)
+ if (!rq_mergeable(rq))
return 0;
- if (blk_rq_sectors(rq) > queue_max_sectors(q) ||
- blk_rq_bytes(rq) > queue_max_hw_sectors(q) << 9) {
+ if (blk_rq_sectors(rq) > blk_queue_get_max_sectors(q, rq->cmd_flags)) {
printk(KERN_ERR "%s: over max size limit.\n", __func__);
return -EIO;
}
req->buffer = bio_data(req->bio);
/* update sector only for requests with clear definition of sector */
- if (req->cmd_type == REQ_TYPE_FS || (req->cmd_flags & REQ_DISCARD))
+ if (req->cmd_type == REQ_TYPE_FS)
req->__sector += total_bytes >> 9;
/* mixed attributes always follow the first bio */
blk_rq_init(NULL, rq);
__rq_for_each_bio(bio_src, rq_src) {
- bio = bio_alloc_bioset(gfp_mask, bio_src->bi_max_vecs, bs);
+ bio = bio_clone_bioset(bio_src, gfp_mask, bs);
if (!bio)
goto free_and_out;
- __bio_clone(bio, bio_src);
-
- if (bio_integrity(bio_src) &&
- bio_integrity_clone(bio, bio_src, gfp_mask, bs))
- goto free_and_out;
-
if (bio_ctr && bio_ctr(bio, bio_src, data))
goto free_and_out;
free_and_out:
if (bio)
- bio_free(bio, bs);
+ bio_put(bio);
blk_rq_unprep_clone(rq);
return -ENOMEM;
}
EXPORT_SYMBOL(blkdev_issue_discard);
+/**
+ * blkdev_issue_write_same - queue a write same operation
+ * @bdev: target blockdev
+ * @sector: start sector
+ * @nr_sects: number of sectors to write
+ * @gfp_mask: memory allocation flags (for bio_alloc)
+ * @page: page containing data to write
+ *
+ * Description:
+ * Issue a write same request for the sectors in question.
+ */
+int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
+ sector_t nr_sects, gfp_t gfp_mask,
+ struct page *page)
+{
+ DECLARE_COMPLETION_ONSTACK(wait);
+ struct request_queue *q = bdev_get_queue(bdev);
+ unsigned int max_write_same_sectors;
+ struct bio_batch bb;
+ struct bio *bio;
+ int ret = 0;
+
+ if (!q)
+ return -ENXIO;
+
+ max_write_same_sectors = q->limits.max_write_same_sectors;
+
+ if (max_write_same_sectors == 0)
+ return -EOPNOTSUPP;
+
+ atomic_set(&bb.done, 1);
+ bb.flags = 1 << BIO_UPTODATE;
+ bb.wait = &wait;
+
+ while (nr_sects) {
+ bio = bio_alloc(gfp_mask, 1);
+ if (!bio) {
+ ret = -ENOMEM;
+ break;
+ }
+
+ bio->bi_sector = sector;
+ bio->bi_end_io = bio_batch_end_io;
+ bio->bi_bdev = bdev;
+ bio->bi_private = &bb;
+ bio->bi_vcnt = 1;
+ bio->bi_io_vec->bv_page = page;
+ bio->bi_io_vec->bv_offset = 0;
+ bio->bi_io_vec->bv_len = bdev_logical_block_size(bdev);
+
+ if (nr_sects > max_write_same_sectors) {
+ bio->bi_size = max_write_same_sectors << 9;
+ nr_sects -= max_write_same_sectors;
+ sector += max_write_same_sectors;
+ } else {
+ bio->bi_size = nr_sects << 9;
+ nr_sects = 0;
+ }
+
+ atomic_inc(&bb.done);
+ submit_bio(REQ_WRITE | REQ_WRITE_SAME, bio);
+ }
+
+ /* Wait for bios in-flight */
+ if (!atomic_dec_and_test(&bb.done))
+ wait_for_completion(&wait);
+
+ if (!test_bit(BIO_UPTODATE, &bb.flags))
+ ret = -ENOTSUPP;
+
+ return ret;
+}
+EXPORT_SYMBOL(blkdev_issue_write_same);
+
/**
* blkdev_issue_zeroout - generate number of zero filed write bios
* @bdev: blockdev to issue
* Generate and issue number of bios with zerofiled pages.
*/
-int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
+int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
sector_t nr_sects, gfp_t gfp_mask)
{
int ret;
return ret;
}
+
+/**
+ * blkdev_issue_zeroout - zero-fill a block range
+ * @bdev: blockdev to write
+ * @sector: start sector
+ * @nr_sects: number of sectors to write
+ * @gfp_mask: memory allocation flags (for bio_alloc)
+ *
+ * Description:
+ * Generate and issue number of bios with zerofiled pages.
+ */
+
+int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
+ sector_t nr_sects, gfp_t gfp_mask)
+{
+ if (bdev_write_same(bdev)) {
+ unsigned char bdn[BDEVNAME_SIZE];
+
+ if (!blkdev_issue_write_same(bdev, sector, nr_sects, gfp_mask,
+ ZERO_PAGE(0)))
+ return 0;
+
+ bdevname(bdev, bdn);
+ pr_err("%s: WRITE SAME failed. Manually zeroing.\n", bdn);
+ }
+
+ return __blkdev_issue_zeroout(bdev, sector, nr_sects, gfp_mask);
+}
EXPORT_SYMBOL(blkdev_issue_zeroout);
int ll_back_merge_fn(struct request_queue *q, struct request *req,
struct bio *bio)
{
- unsigned short max_sectors;
-
- if (unlikely(req->cmd_type == REQ_TYPE_BLOCK_PC))
- max_sectors = queue_max_hw_sectors(q);
- else
- max_sectors = queue_max_sectors(q);
-
- if (blk_rq_sectors(req) + bio_sectors(bio) > max_sectors) {
+ if (blk_rq_sectors(req) + bio_sectors(bio) >
+ blk_rq_get_max_sectors(req)) {
req->cmd_flags |= REQ_NOMERGE;
if (req == q->last_merge)
q->last_merge = NULL;
int ll_front_merge_fn(struct request_queue *q, struct request *req,
struct bio *bio)
{
- unsigned short max_sectors;
-
- if (unlikely(req->cmd_type == REQ_TYPE_BLOCK_PC))
- max_sectors = queue_max_hw_sectors(q);
- else
- max_sectors = queue_max_sectors(q);
-
-
- if (blk_rq_sectors(req) + bio_sectors(bio) > max_sectors) {
+ if (blk_rq_sectors(req) + bio_sectors(bio) >
+ blk_rq_get_max_sectors(req)) {
req->cmd_flags |= REQ_NOMERGE;
if (req == q->last_merge)
q->last_merge = NULL;
/*
* Will it become too large?
*/
- if ((blk_rq_sectors(req) + blk_rq_sectors(next)) > queue_max_sectors(q))
+ if ((blk_rq_sectors(req) + blk_rq_sectors(next)) >
+ blk_rq_get_max_sectors(req))
return 0;
total_phys_segments = req->nr_phys_segments + next->nr_phys_segments;
if (!rq_mergeable(req) || !rq_mergeable(next))
return 0;
- /*
- * Don't merge file system requests and discard requests
- */
- if ((req->cmd_flags & REQ_DISCARD) != (next->cmd_flags & REQ_DISCARD))
- return 0;
-
- /*
- * Don't merge discard requests and secure discard requests
- */
- if ((req->cmd_flags & REQ_SECURE) != (next->cmd_flags & REQ_SECURE))
+ if (!blk_check_merge_flags(req->cmd_flags, next->cmd_flags))
return 0;
/*
|| next->special)
return 0;
+ if (req->cmd_flags & REQ_WRITE_SAME &&
+ !blk_write_same_mergeable(req->bio, next->bio))
+ return 0;
+
/*
* If we are allowed to merge, then append bio list
* from next to rq and release next. merge_requests_fn
bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
{
- if (!rq_mergeable(rq))
+ if (!rq_mergeable(rq) || !bio_mergeable(bio))
return false;
- /* don't merge file system requests and discard requests */
- if ((bio->bi_rw & REQ_DISCARD) != (rq->bio->bi_rw & REQ_DISCARD))
- return false;
-
- /* don't merge discard requests and secure discard requests */
- if ((bio->bi_rw & REQ_SECURE) != (rq->bio->bi_rw & REQ_SECURE))
+ if (!blk_check_merge_flags(rq->cmd_flags, bio->bi_rw))
return false;
/* different data direction or already started, don't merge */
if (bio_integrity(bio) != blk_integrity_rq(rq))
return false;
+ /* must be using the same buffer */
+ if (rq->cmd_flags & REQ_WRITE_SAME &&
+ !blk_write_same_mergeable(rq->bio, bio))
+ return false;
+
return true;
}
lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
lim->max_segment_size = BLK_MAX_SEGMENT_SIZE;
lim->max_sectors = lim->max_hw_sectors = BLK_SAFE_MAX_SECTORS;
+ lim->max_write_same_sectors = 0;
lim->max_discard_sectors = 0;
lim->discard_granularity = 0;
lim->discard_alignment = 0;
lim->max_segments = USHRT_MAX;
lim->max_hw_sectors = UINT_MAX;
lim->max_sectors = UINT_MAX;
+ lim->max_write_same_sectors = UINT_MAX;
}
EXPORT_SYMBOL(blk_set_stacking_limits);
}
EXPORT_SYMBOL(blk_queue_max_discard_sectors);
+/**
+ * blk_queue_max_write_same_sectors - set max sectors for a single write same
+ * @q: the request queue for the device
+ * @max_write_same_sectors: maximum number of sectors to write per command
+ **/
+void blk_queue_max_write_same_sectors(struct request_queue *q,
+ unsigned int max_write_same_sectors)
+{
+ q->limits.max_write_same_sectors = max_write_same_sectors;
+}
+EXPORT_SYMBOL(blk_queue_max_write_same_sectors);
+
/**
* blk_queue_max_segments - set max hw segments for a request for this queue
* @q: the request queue for the device
t->max_sectors = min_not_zero(t->max_sectors, b->max_sectors);
t->max_hw_sectors = min_not_zero(t->max_hw_sectors, b->max_hw_sectors);
+ t->max_write_same_sectors = min(t->max_write_same_sectors,
+ b->max_write_same_sectors);
t->bounce_pfn = min_not_zero(t->bounce_pfn, b->bounce_pfn);
t->seg_boundary_mask = min_not_zero(t->seg_boundary_mask,
static ssize_t
queue_var_store(unsigned long *var, const char *page, size_t count)
{
- char *p = (char *) page;
+ int err;
+ unsigned long v;
+
+ err = strict_strtoul(page, 10, &v);
+ if (err || v > UINT_MAX)
+ return -EINVAL;
+
+ *var = v;
- *var = simple_strtoul(p, &p, 10);
return count;
}
return -EINVAL;
ret = queue_var_store(&nr, page, count);
+ if (ret < 0)
+ return ret;
+
if (nr < BLKDEV_MIN_RQ)
nr = BLKDEV_MIN_RQ;
unsigned long ra_kb;
ssize_t ret = queue_var_store(&ra_kb, page, count);
+ if (ret < 0)
+ return ret;
+
q->backing_dev_info.ra_pages = ra_kb >> (PAGE_CACHE_SHIFT - 10);
return ret;
return queue_var_show(queue_discard_zeroes_data(q), page);
}
+static ssize_t queue_write_same_max_show(struct request_queue *q, char *page)
+{
+ return sprintf(page, "%llu\n",
+ (unsigned long long)q->limits.max_write_same_sectors << 9);
+}
+
+
static ssize_t
queue_max_sectors_store(struct request_queue *q, const char *page, size_t count)
{
page_kb = 1 << (PAGE_CACHE_SHIFT - 10);
ssize_t ret = queue_var_store(&max_sectors_kb, page, count);
+ if (ret < 0)
+ return ret;
+
if (max_sectors_kb > max_hw_sectors_kb || max_sectors_kb < page_kb)
return -EINVAL;
unsigned long nm;
ssize_t ret = queue_var_store(&nm, page, count);
+ if (ret < 0)
+ return ret;
+
spin_lock_irq(q->queue_lock);
queue_flag_clear(QUEUE_FLAG_NOMERGES, q);
queue_flag_clear(QUEUE_FLAG_NOXMERGES, q);
unsigned long val;
ret = queue_var_store(&val, page, count);
+ if (ret < 0)
+ return ret;
+
spin_lock_irq(q->queue_lock);
if (val == 2) {
queue_flag_set(QUEUE_FLAG_SAME_COMP, q);
.show = queue_discard_zeroes_data_show,
};
+static struct queue_sysfs_entry queue_write_same_max_entry = {
+ .attr = {.name = "write_same_max_bytes", .mode = S_IRUGO },
+ .show = queue_write_same_max_show,
+};
+
static struct queue_sysfs_entry queue_nonrot_entry = {
.attr = {.name = "rotational", .mode = S_IRUGO | S_IWUSR },
.show = queue_show_nonrot,
&queue_discard_granularity_entry.attr,
&queue_discard_max_entry.attr,
&queue_discard_zeroes_data_entry.attr,
+ &queue_write_same_max_entry.attr,
&queue_nonrot_entry.attr,
&queue_nomerges_entry.attr,
&queue_rq_affinity_entry.attr,
if (WARN_ON(!q))
return -ENXIO;
+ /*
+ * Initialization must be complete by now. Finish the initial
+ * bypass from queue allocation.
+ */
+ blk_queue_bypass_end(q);
+
ret = blk_trace_init_sysfs(dev);
if (ret)
return ret;
tags = __blk_queue_init_tags(q, depth);
if (!tags)
- goto fail;
+ return -ENOMEM;
+
} else if (q->queue_tags) {
rc = blk_queue_resize_tags(q, depth);
if (rc)
queue_flag_set_unlocked(QUEUE_FLAG_QUEUED, q);
INIT_LIST_HEAD(&q->tag_busy_list);
return 0;
-fail:
- kfree(tags);
- return -ENOMEM;
}
EXPORT_SYMBOL(blk_queue_init_tags);
*
* a) it's attached to a gendisk, and
* b) the queue had IO stats enabled when this request was started, and
- * c) it's a file system request or a discard request
+ * c) it's a file system request
*/
static inline int blk_do_io_stat(struct request *rq)
{
return rq->rq_disk &&
(rq->cmd_flags & REQ_IO_STAT) &&
- (rq->cmd_type == REQ_TYPE_FS ||
- (rq->cmd_flags & REQ_DISCARD));
+ (rq->cmd_type == REQ_TYPE_FS);
}
/*
if (rq->cmd_flags & REQ_SOFTBARRIER) {
/* barriers are scheduling boundary, update end_sector */
- if (rq->cmd_type == REQ_TYPE_FS ||
- (rq->cmd_flags & REQ_DISCARD)) {
+ if (rq->cmd_type == REQ_TYPE_FS) {
q->end_sector = rq_end_sector(rq);
q->boundary_rq = rq;
}
if (elv_attempt_insert_merge(q, rq))
break;
case ELEVATOR_INSERT_SORT:
- BUG_ON(rq->cmd_type != REQ_TYPE_FS &&
- !(rq->cmd_flags & REQ_DISCARD));
+ BUG_ON(rq->cmd_type != REQ_TYPE_FS);
rq->cmd_flags |= REQ_SORTED;
q->nr_sorted++;
if (rq_mergeable(rq)) {
WARN_ON(disk->minors && !(disk->major || disk->first_minor));
WARN_ON(!disk->minors && !(disk->flags & GENHD_FL_EXT_DEVT));
- disk->flags |= GENHD_FL_UP;
-
retval = blk_alloc_devt(&disk->part0, &devt);
if (retval) {
WARN_ON(1);
}
disk_to_dev(disk)->devt = devt;
+ disk->flags |= GENHD_FL_UP;
+
/* ->major and ->first_minor aren't supposed to be
* dereferenced from here on, but set them just in case.
*/
disk_replace_part_tbl(disk, NULL);
free_part_stats(&disk->part0);
free_part_info(&disk->part0);
- if (disk->queue)
+ if (disk->queue && disk->flags & GENHD_FL_UP)
blk_put_queue(disk->queue);
kfree(disk);
}
return blkdev_issue_discard(bdev, start, len, GFP_KERNEL, flags);
}
+static int blk_ioctl_zeroout(struct block_device *bdev, uint64_t start,
+ uint64_t len)
+{
+ if (start & 511)
+ return -EINVAL;
+ if (len & 511)
+ return -EINVAL;
+ start >>= 9;
+ len >>= 9;
+
+ if (start + len > (i_size_read(bdev->bd_inode) >> 9))
+ return -EINVAL;
+
+ return blkdev_issue_zeroout(bdev, start, len, GFP_KERNEL);
+}
+
static int put_ushort(unsigned long arg, unsigned short val)
{
return put_user(val, (unsigned short __user *)arg);
return blk_ioctl_discard(bdev, range[0], range[1],
cmd == BLKSECDISCARD);
}
+ case BLKZEROOUT: {
+ uint64_t range[2];
+
+ if (!(mode & FMODE_WRITE))
+ return -EBADF;
+
+ if (copy_from_user(range, (void __user *)arg, sizeof(range)))
+ return -EFAULT;
+
+ return blk_ioctl_zeroout(bdev, range[0], range[1]);
+ }
case HDIO_GETGEO: {
struct hd_geometry geo;
config BLK_CPQ_CISS_DA
tristate "Compaq Smart Array 5xxx support"
depends on PCI
+ select CHECK_SIGNATURE
help
This is the driver for Compaq Smart Array 5xxx controllers.
Everyone using these boards should say Y here.
return;
}
/* write all data in the battery backed cache to disk */
- memset(flush_buf, 0, 4);
return_code = sendcmd_withirq(h, CCISS_CACHE_FLUSH, flush_buf,
4, 0, CTLR_LUNID, TYPE_CMD);
kfree(flush_buf);
.release = drbd_release,
};
-static void bio_destructor_drbd(struct bio *bio)
-{
- bio_free(bio, drbd_md_io_bio_set);
-}
-
struct bio *bio_alloc_drbd(gfp_t gfp_mask)
{
- struct bio *bio;
-
if (!drbd_md_io_bio_set)
return bio_alloc(gfp_mask, 1);
- bio = bio_alloc_bioset(gfp_mask, 1, drbd_md_io_bio_set);
- if (!bio)
- return NULL;
- bio->bi_destructor = bio_destructor_drbd;
- return bio;
+ return bio_alloc_bioset(gfp_mask, 1, drbd_md_io_bio_set);
}
#ifdef __CHECKER__
static struct platform_device floppy_device[N_DRIVE];
+static bool floppy_available(int drive)
+{
+ if (!(allowed_drive_mask & (1 << drive)))
+ return false;
+ if (fdc_state[FDC(drive)].version == FDC_NONE)
+ return false;
+ return true;
+}
+
static struct kobject *floppy_find(dev_t dev, int *part, void *data)
{
int drive = (*part & 3) | ((*part & 0x80) >> 5);
- if (drive >= N_DRIVE ||
- !(allowed_drive_mask & (1 << drive)) ||
- fdc_state[FDC(drive)].version == FDC_NONE)
+ if (drive >= N_DRIVE || !floppy_available(drive))
return NULL;
if (((*part >> 2) & 0x1f) >= ARRAY_SIZE(floppy_type))
return NULL;
static int __init do_floppy_init(void)
{
- int i, unit, drive;
- int err, dr;
+ int i, unit, drive, err;
set_debugt();
interruptjiffies = resultjiffies = jiffies;
raw_cmd = NULL;
- for (dr = 0; dr < N_DRIVE; dr++) {
- disks[dr] = alloc_disk(1);
- if (!disks[dr]) {
- err = -ENOMEM;
- goto out_put_disk;
- }
+ floppy_wq = alloc_ordered_workqueue("floppy", 0);
+ if (!floppy_wq)
+ return -ENOMEM;
- floppy_wq = alloc_ordered_workqueue("floppy", 0);
- if (!floppy_wq) {
+ for (drive = 0; drive < N_DRIVE; drive++) {
+ disks[drive] = alloc_disk(1);
+ if (!disks[drive]) {
err = -ENOMEM;
goto out_put_disk;
}
- disks[dr]->queue = blk_init_queue(do_fd_request, &floppy_lock);
- if (!disks[dr]->queue) {
+ disks[drive]->queue = blk_init_queue(do_fd_request, &floppy_lock);
+ if (!disks[drive]->queue) {
err = -ENOMEM;
- goto out_destroy_workq;
+ goto out_put_disk;
}
- blk_queue_max_hw_sectors(disks[dr]->queue, 64);
- disks[dr]->major = FLOPPY_MAJOR;
- disks[dr]->first_minor = TOMINOR(dr);
- disks[dr]->fops = &floppy_fops;
- sprintf(disks[dr]->disk_name, "fd%d", dr);
+ blk_queue_max_hw_sectors(disks[drive]->queue, 64);
+ disks[drive]->major = FLOPPY_MAJOR;
+ disks[drive]->first_minor = TOMINOR(drive);
+ disks[drive]->fops = &floppy_fops;
+ sprintf(disks[drive]->disk_name, "fd%d", drive);
- init_timer(&motor_off_timer[dr]);
- motor_off_timer[dr].data = dr;
- motor_off_timer[dr].function = motor_off_callback;
+ init_timer(&motor_off_timer[drive]);
+ motor_off_timer[drive].data = drive;
+ motor_off_timer[drive].function = motor_off_callback;
}
err = register_blkdev(FLOPPY_MAJOR, "fd");
}
for (drive = 0; drive < N_DRIVE; drive++) {
- if (!(allowed_drive_mask & (1 << drive)))
- continue;
- if (fdc_state[FDC(drive)].version == FDC_NONE)
+ if (!floppy_available(drive))
continue;
floppy_device[drive].name = floppy_device_name;
err = platform_device_register(&floppy_device[drive]);
if (err)
- goto out_release_dma;
+ goto out_remove_drives;
err = device_create_file(&floppy_device[drive].dev,
&dev_attr_cmos);
out_unreg_platform_dev:
platform_device_unregister(&floppy_device[drive]);
+out_remove_drives:
+ while (drive--) {
+ if (floppy_available(drive)) {
+ del_gendisk(disks[drive]);
+ device_remove_file(&floppy_device[drive].dev, &dev_attr_cmos);
+ platform_device_unregister(&floppy_device[drive]);
+ }
+ }
out_release_dma:
if (atomic_read(&usage_count))
floppy_release_irq_and_dma();
out_unreg_region:
blk_unregister_region(MKDEV(FLOPPY_MAJOR, 0), 256);
platform_driver_unregister(&floppy_driver);
-out_destroy_workq:
- destroy_workqueue(floppy_wq);
out_unreg_blkdev:
unregister_blkdev(FLOPPY_MAJOR, "fd");
out_put_disk:
- while (dr--) {
- del_timer_sync(&motor_off_timer[dr]);
- if (disks[dr]->queue) {
- blk_cleanup_queue(disks[dr]->queue);
- /*
- * put_disk() is not paired with add_disk() and
- * will put queue reference one extra time. fix it.
- */
- disks[dr]->queue = NULL;
+ for (drive = 0; drive < N_DRIVE; drive++) {
+ if (!disks[drive])
+ break;
+ if (disks[drive]->queue) {
+ del_timer_sync(&motor_off_timer[drive]);
+ blk_cleanup_queue(disks[drive]->queue);
}
- put_disk(disks[dr]);
+ put_disk(disks[drive]);
}
+ destroy_workqueue(floppy_wq);
return err;
}
for (drive = 0; drive < N_DRIVE; drive++) {
del_timer_sync(&motor_off_timer[drive]);
- if ((allowed_drive_mask & (1 << drive)) &&
- fdc_state[FDC(drive)].version != FDC_NONE) {
+ if (floppy_available(drive)) {
del_gendisk(disks[drive]);
device_remove_file(&floppy_device[drive].dev, &dev_attr_cmos);
platform_device_unregister(&floppy_device[drive]);
}
blk_cleanup_queue(disks[drive]->queue);
- /*
- * These disks have not called add_disk(). Don't put down
- * queue reference in put_disk().
- */
- if (!(allowed_drive_mask & (1 << drive)) ||
- fdc_state[FDC(drive)].version == FDC_NONE)
- disks[drive]->queue = NULL;
-
put_disk(disks[drive]);
}
if (lo->lo_state != Lo_bound)
return -ENXIO;
- if (lo->lo_refcnt > 1) /* we needed one fd for the ioctl */
- return -EBUSY;
+ /*
+ * If we've explicitly asked to tear down the loop device,
+ * and it has an elevated reference count, set it for auto-teardown when
+ * the last reference goes away. This stops $!~#$@ udev from
+ * preventing teardown because it decided that it needs to run blkid on
+ * the loopback device whenever they appear. xfstests is notorious for
+ * failing tests because blkid via udev races with a losetup
+ * <dev>/do something like mkfs/losetup -d <dev> causing the losetup -d
+ * command to fail with EBUSY.
+ */
+ if (lo->lo_refcnt > 1) {
+ lo->lo_flags |= LO_FLAGS_AUTOCLEAR;
+ mutex_unlock(&lo->lo_ctl_mutex);
+ return 0;
+ }
if (filp == NULL)
return -EINVAL;
}
return rv;
}
-
-static void mtip_set_timeout(struct host_to_dev_fis *fis, unsigned int *timeout)
+static void mtip_set_timeout(struct driver_data *dd,
+ struct host_to_dev_fis *fis,
+ unsigned int *timeout, u8 erasemode)
{
switch (fis->command) {
case ATA_CMD_DOWNLOAD_MICRO:
break;
case ATA_CMD_SEC_ERASE_UNIT:
case 0xFC:
- *timeout = 240000; /* 4 minutes */
+ if (erasemode)
+ *timeout = ((*(dd->port->identify + 90) * 2) * 60000);
+ else
+ *timeout = ((*(dd->port->identify + 89) * 2) * 60000);
break;
case ATA_CMD_STANDBYNOW1:
*timeout = 120000; /* 2 minutes */
unsigned int transfer_size;
unsigned long task_file_data;
int intotal = outtotal + req_task->out_size;
+ int erasemode = 0;
taskout = req_task->out_size;
taskin = req_task->in_size;
fis.lba_hi,
fis.device);
- mtip_set_timeout(&fis, &timeout);
+ /* check for erase mode support during secure erase.*/
+ if ((fis.command == ATA_CMD_SEC_ERASE_UNIT)
+ && (outbuf[0] & MTIP_SEC_ERASE_MODE)) {
+ erasemode = 1;
+ }
+
+ mtip_set_timeout(dd, &fis, &timeout, erasemode);
/* Determine the correct transfer size.*/
if (force_single_sector)
/* offset of Device Control register in PCIe extended capabilites space */
#define PCIE_CONFIG_EXT_DEVICE_CONTROL_OFFSET 0x48
+/* check for erase mode support during secure erase */
+#define MTIP_SEC_ERASE_MODE 0x3
+
/* # of times to retry timed out/failed IOs */
#define MTIP_MAX_RETRIES 2
struct bio *tmp, *new_chain = NULL, *tail = NULL;
while (old_chain) {
- tmp = bio_kmalloc(gfpmask, old_chain->bi_max_vecs);
+ tmp = bio_clone_kmalloc(old_chain, gfpmask);
if (!tmp)
goto err_out;
- __bio_clone(tmp, old_chain);
tmp->bi_bdev = NULL;
gfpmask &= ~__GFP_WAIT;
tmp->bi_next = NULL;
}
}
-static void pkt_bio_destructor(struct bio *bio)
-{
- kfree(bio->bi_io_vec);
- kfree(bio);
-}
-
-static struct bio *pkt_bio_alloc(int nr_iovecs)
-{
- struct bio_vec *bvl = NULL;
- struct bio *bio;
-
- bio = kmalloc(sizeof(struct bio), GFP_KERNEL);
- if (!bio)
- goto no_bio;
- bio_init(bio);
-
- bvl = kcalloc(nr_iovecs, sizeof(struct bio_vec), GFP_KERNEL);
- if (!bvl)
- goto no_bvl;
-
- bio->bi_max_vecs = nr_iovecs;
- bio->bi_io_vec = bvl;
- bio->bi_destructor = pkt_bio_destructor;
-
- return bio;
-
- no_bvl:
- kfree(bio);
- no_bio:
- return NULL;
-}
-
/*
* Allocate a packet_data struct
*/
goto no_pkt;
pkt->frames = frames;
- pkt->w_bio = pkt_bio_alloc(frames);
+ pkt->w_bio = bio_kmalloc(GFP_KERNEL, frames);
if (!pkt->w_bio)
goto no_bio;
bio_list_init(&pkt->orig_bios);
for (i = 0; i < frames; i++) {
- struct bio *bio = pkt_bio_alloc(1);
+ struct bio *bio = bio_kmalloc(GFP_KERNEL, 1);
if (!bio)
goto no_rd_bio;
+
pkt->r_bios[i] = bio;
}
* Schedule reads for missing parts of the packet.
*/
for (f = 0; f < pkt->frames; f++) {
- struct bio_vec *vec;
-
int p, offset;
+
if (written[f])
continue;
+
bio = pkt->r_bios[f];
- vec = bio->bi_io_vec;
- bio_init(bio);
- bio->bi_max_vecs = 1;
+ bio_reset(bio);
bio->bi_sector = pkt->sector + f * (CD_FRAMESIZE >> 9);
bio->bi_bdev = pd->bdev;
bio->bi_end_io = pkt_end_io_read;
bio->bi_private = pkt;
- bio->bi_io_vec = vec;
- bio->bi_destructor = pkt_bio_destructor;
p = (f * CD_FRAMESIZE) / PAGE_SIZE;
offset = (f * CD_FRAMESIZE) % PAGE_SIZE;
}
/* Start the write request */
- bio_init(pkt->w_bio);
- pkt->w_bio->bi_max_vecs = PACKET_MAX_SIZE;
+ bio_reset(pkt->w_bio);
pkt->w_bio->bi_sector = pkt->sector;
pkt->w_bio->bi_bdev = pd->bdev;
pkt->w_bio->bi_end_io = pkt_end_io_packet_write;
pkt->w_bio->bi_private = pkt;
- pkt->w_bio->bi_io_vec = bvec;
- pkt->w_bio->bi_destructor = pkt_bio_destructor;
for (f = 0; f < pkt->frames; f++)
if (!bio_add_page(pkt->w_bio, bvec[f].bv_page, CD_FRAMESIZE, bvec[f].bv_offset))
BUG();
struct block_device *bdev;
/* Cached size parameter. */
sector_t size;
- bool flush_support;
- bool discard_secure;
+ unsigned int flush_support:1;
+ unsigned int discard_secure:1;
};
struct backend_info;
{
struct xen_blkif *blkif;
- blkif = kmem_cache_alloc(xen_blkif_cachep, GFP_KERNEL);
+ blkif = kmem_cache_zalloc(xen_blkif_cachep, GFP_KERNEL);
if (!blkif)
return ERR_PTR(-ENOMEM);
- memset(blkif, 0, sizeof(*blkif));
blkif->domid = domid;
spin_lock_init(&blkif->blk_ring_lock);
atomic_set(&blkif->refcnt, 1);
}
}
-void xen_blkif_free(struct xen_blkif *blkif)
+static void xen_blkif_free(struct xen_blkif *blkif)
{
if (!atomic_dec_and_test(&blkif->refcnt))
BUG();
VBD_SHOW(physical_device, "%x:%x\n", be->major, be->minor);
VBD_SHOW(mode, "%s\n", be->mode);
-int xenvbd_sysfs_addif(struct xenbus_device *dev)
+static int xenvbd_sysfs_addif(struct xenbus_device *dev)
{
int error;
return error;
}
-void xenvbd_sysfs_delif(struct xenbus_device *dev)
+static void xenvbd_sysfs_delif(struct xenbus_device *dev)
{
sysfs_remove_group(&dev->dev.kobj, &xen_vbdstat_group);
device_remove_file(&dev->dev, &dev_attr_mode);
static const struct file_operations raw_fops = {
.read = do_sync_read,
- .aio_read = generic_file_aio_read,
+ .aio_read = blkdev_aio_read,
.write = do_sync_write,
.aio_write = blkdev_aio_write,
.fsync = blkdev_fsync,
return 0;
}
-static void dm_crypt_bio_destructor(struct bio *bio)
-{
- struct dm_crypt_io *io = bio->bi_private;
- struct crypt_config *cc = io->cc;
-
- bio_free(bio, cc->bs);
-}
-
/*
* Generate a new unfragmented bio with the given size
* This should never violate the device limitations
clone->bi_end_io = crypt_endio;
clone->bi_bdev = cc->dev->bdev;
clone->bi_rw = io->base_bio->bi_rw;
- clone->bi_destructor = dm_crypt_bio_destructor;
}
static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp)
* copy the required bvecs because we need the original
* one in order to decrypt the whole bio data *afterwards*.
*/
- clone = bio_alloc_bioset(gfp, bio_segments(base_bio), cc->bs);
+ clone = bio_clone_bioset(base_bio, gfp, cc->bs);
if (!clone)
return 1;
crypt_inc_pending(io);
clone_init(io, clone);
- clone->bi_idx = 0;
- clone->bi_vcnt = bio_segments(base_bio);
- clone->bi_size = base_bio->bi_size;
clone->bi_sector = cc->start + io->sector;
- memcpy(clone->bi_io_vec, bio_iovec(base_bio),
- sizeof(struct bio_vec) * clone->bi_vcnt);
generic_make_request(clone);
return 0;
dp->context_ptr = data;
}
-static void dm_bio_destructor(struct bio *bio)
-{
- unsigned region;
- struct io *io;
-
- retrieve_io_and_region_from_bio(bio, &io, ®ion);
-
- bio_free(bio, io->client->bios);
-}
-
/*
* Functions for getting the pages from kernel memory.
*/
bio->bi_sector = where->sector + (where->count - remaining);
bio->bi_bdev = where->bdev;
bio->bi_end_io = endio;
- bio->bi_destructor = dm_bio_destructor;
store_io_and_region_in_bio(bio, io, region);
if (rw & REQ_DISCARD) {
};
/*
- * For request-based dm.
- * One of these is allocated per bio.
+ * For request-based dm - the bio clones we allocate are embedded in these
+ * structs.
+ *
+ * We allocate these with bio_alloc_bioset, using the front_pad parameter when
+ * the bioset is created - this means the bio has to come at the end of the
+ * struct.
*/
struct dm_rq_clone_bio_info {
struct bio *orig;
struct dm_rq_target_io *tio;
+ struct bio clone;
};
union map_info *dm_get_mapinfo(struct bio *bio)
static struct kmem_cache *_io_cache;
static struct kmem_cache *_tio_cache;
static struct kmem_cache *_rq_tio_cache;
+
+/*
+ * Unused now, and needs to be deleted. But since io_pool is overloaded and it's
+ * still used for _io_cache, I'm leaving this for a later cleanup
+ */
static struct kmem_cache *_rq_bio_info_cache;
static int __init local_init(void)
mempool_free(tio, tio->md->tio_pool);
}
-static struct dm_rq_clone_bio_info *alloc_bio_info(struct mapped_device *md)
-{
- return mempool_alloc(md->io_pool, GFP_ATOMIC);
-}
-
-static void free_bio_info(struct dm_rq_clone_bio_info *info)
-{
- mempool_free(info, info->tio->md->io_pool);
-}
-
static int md_in_flight(struct mapped_device *md)
{
return atomic_read(&md->pending[READ]) +
}
}
- /*
- * Store md for cleanup instead of tio which is about to get freed.
- */
- bio->bi_private = md->bs;
-
free_tio(md, tio);
bio_put(bio);
dec_pending(io, error);
/* error the io and bail out, or requeue it if needed */
md = tio->io->md;
dec_pending(tio->io, r);
- /*
- * Store bio_set for cleanup.
- */
- clone->bi_end_io = NULL;
- clone->bi_private = md->bs;
bio_put(clone);
free_tio(md, tio);
} else if (r) {
unsigned short idx;
};
-static void dm_bio_destructor(struct bio *bio)
-{
- struct bio_set *bs = bio->bi_private;
-
- bio_free(bio, bs);
-}
-
/*
* Creates a little bio that just does part of a bvec.
*/
struct bio_vec *bv = bio->bi_io_vec + idx;
clone = bio_alloc_bioset(GFP_NOIO, 1, bs);
- clone->bi_destructor = dm_bio_destructor;
*clone->bi_io_vec = *bv;
clone->bi_sector = sector;
clone->bi_flags |= 1 << BIO_CLONED;
if (bio_integrity(bio)) {
- bio_integrity_clone(clone, bio, GFP_NOIO, bs);
+ bio_integrity_clone(clone, bio, GFP_NOIO);
bio_integrity_trim(clone,
bio_sector_offset(bio, idx, offset), len);
}
clone = bio_alloc_bioset(GFP_NOIO, bio->bi_max_vecs, bs);
__bio_clone(clone, bio);
- clone->bi_destructor = dm_bio_destructor;
clone->bi_sector = sector;
clone->bi_idx = idx;
clone->bi_vcnt = idx + bv_count;
clone->bi_flags &= ~(1 << BIO_SEG_VALID);
if (bio_integrity(bio)) {
- bio_integrity_clone(clone, bio, GFP_NOIO, bs);
+ bio_integrity_clone(clone, bio, GFP_NOIO);
if (idx != bio->bi_idx || clone->bi_size < bio->bi_size)
bio_integrity_trim(clone,
* ci->bio->bi_max_vecs is BIO_INLINE_VECS anyway, for both flush
* and discard, so no need for concern about wasted bvec allocations.
*/
- clone = bio_alloc_bioset(GFP_NOIO, ci->bio->bi_max_vecs, ci->md->bs);
- __bio_clone(clone, ci->bio);
- clone->bi_destructor = dm_bio_destructor;
+ clone = bio_clone_bioset(ci->bio, GFP_NOIO, ci->md->bs);
+
if (len) {
clone->bi_sector = ci->sector;
clone->bi_size = to_bytes(len);
}
EXPORT_SYMBOL_GPL(dm_dispatch_request);
-static void dm_rq_bio_destructor(struct bio *bio)
-{
- struct dm_rq_clone_bio_info *info = bio->bi_private;
- struct mapped_device *md = info->tio->md;
-
- free_bio_info(info);
- bio_free(bio, md->bs);
-}
-
static int dm_rq_bio_constructor(struct bio *bio, struct bio *bio_orig,
void *data)
{
struct dm_rq_target_io *tio = data;
- struct mapped_device *md = tio->md;
- struct dm_rq_clone_bio_info *info = alloc_bio_info(md);
-
- if (!info)
- return -ENOMEM;
+ struct dm_rq_clone_bio_info *info =
+ container_of(bio, struct dm_rq_clone_bio_info, clone);
info->orig = bio_orig;
info->tio = tio;
bio->bi_end_io = end_clone_bio;
bio->bi_private = info;
- bio->bi_destructor = dm_rq_bio_destructor;
return 0;
}
if (!pools->tio_pool)
goto free_io_pool_and_out;
- pools->bs = bioset_create(pool_size, 0);
+ pools->bs = (type == DM_TYPE_BIO_BASED) ?
+ bioset_create(pool_size, 0) :
+ bioset_create(pool_size,
+ offsetof(struct dm_rq_clone_bio_info, clone));
if (!pools->bs)
goto free_tio_pool_and_out;
* like bio_clone, but with a local bio set
*/
-static void mddev_bio_destructor(struct bio *bio)
-{
- struct mddev *mddev, **mddevp;
-
- mddevp = (void*)bio;
- mddev = mddevp[-1];
-
- bio_free(bio, mddev->bio_set);
-}
-
struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs,
struct mddev *mddev)
{
struct bio *b;
- struct mddev **mddevp;
if (!mddev || !mddev->bio_set)
return bio_alloc(gfp_mask, nr_iovecs);
- b = bio_alloc_bioset(gfp_mask, nr_iovecs,
- mddev->bio_set);
+ b = bio_alloc_bioset(gfp_mask, nr_iovecs, mddev->bio_set);
if (!b)
return NULL;
- mddevp = (void*)b;
- mddevp[-1] = mddev;
- b->bi_destructor = mddev_bio_destructor;
return b;
}
EXPORT_SYMBOL_GPL(bio_alloc_mddev);
struct bio *bio_clone_mddev(struct bio *bio, gfp_t gfp_mask,
struct mddev *mddev)
{
- struct bio *b;
- struct mddev **mddevp;
-
if (!mddev || !mddev->bio_set)
return bio_clone(bio, gfp_mask);
- b = bio_alloc_bioset(gfp_mask, bio->bi_max_vecs,
- mddev->bio_set);
- if (!b)
- return NULL;
- mddevp = (void*)b;
- mddevp[-1] = mddev;
- b->bi_destructor = mddev_bio_destructor;
- __bio_clone(b, bio);
- if (bio_integrity(bio)) {
- int ret;
-
- ret = bio_integrity_clone(b, bio, gfp_mask, mddev->bio_set);
-
- if (ret < 0) {
- bio_put(b);
- return NULL;
- }
- }
-
- return b;
+ return bio_clone_bioset(bio, gfp_mask, mddev->bio_set);
}
EXPORT_SYMBOL_GPL(bio_clone_mddev);
}
if (mddev->bio_set == NULL)
- mddev->bio_set = bioset_create(BIO_POOL_SIZE,
- sizeof(struct mddev *));
+ mddev->bio_set = bioset_create(BIO_POOL_SIZE, 0);
spin_lock(&pers_lock);
pers = find_pers(mddev->level, mddev->clevel);
if (md_check_no_bitmap(mddev))
return -EINVAL;
blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors);
+ blk_queue_max_write_same_sectors(mddev->queue, mddev->chunk_sectors);
/* if private is not null, we are here after takeover */
if (mddev->private == NULL) {
support. This provides a block device driver, which you can use
to mount the filesystem. Almost everyone wishing MemoryStick
support should say Y or M here.
+
+config MS_BLOCK
+ tristate "MemoryStick Standard device driver"
+ depends on BLOCK && EXPERIMENTAL
+ help
+ Say Y here to enable the MemoryStick Standard device driver
+ support. This provides a block device driver, which you can use
+ to mount the filesystem.
+ This driver works with old (bulky) MemoryStick and MemoryStick Duo
+ but not PRO. Say Y if you have such card.
+ Driver is new and not yet well tested, thus it can damage your card
+ (even permanently)
#
obj-$(CONFIG_MEMSTICK) += memstick.o
-
+obj-$(CONFIG_MS_BLOCK) += ms_block.o
obj-$(CONFIG_MSPRO_BLOCK) += mspro_block.o
--- /dev/null
+/*
+ * ms_block.c - Sony MemoryStick (legacy) storage support
+
+ * Copyright (C) 2012 Maxim Levitsky <maximlevitsky@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Minor portions of the driver were copied from mspro_block.c which is
+ * Copyright (C) 2007 Alex Dubov <oakad@yahoo.com>
+ *
+ */
+
+#define pr_fmt(fmt) DRIVER_NAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/blkdev.h>
+#include <linux/memstick.h>
+#include <linux/idr.h>
+#include <linux/hdreg.h>
+#include <linux/delay.h>
+#include <linux/slab.h>
+#include <linux/random.h>
+#include <linux/bitmap.h>
+#include <linux/scatterlist.h>
+#include <linux/jiffies.h>
+#include <linux/workqueue.h>
+#include <linux/mutex.h>
+#include "ms_block.h"
+
+static int debug;
+static int cache_flush_timeout = 1000;
+static bool verify_writes;
+
+/*
+ * Copies section of 'sg_from' starting from offset 'offset' and with length
+ * 'len' To another scatterlist of to_nents enties
+ */
+static size_t msb_sg_copy(struct scatterlist *sg_from, struct scatterlist *sg_to,
+ int to_nents, size_t offset, size_t len)
+{
+ size_t copied = 0;
+
+ while (offset > 0) {
+ if (offset >= sg_from->length) {
+ if (sg_is_last(sg_from))
+ return 0;
+
+ offset -= sg_from->length;
+ sg_from = sg_next(sg_from);
+ continue;
+ }
+
+ copied = min(len, sg_from->length - offset);
+ sg_set_page(sg_to, sg_page(sg_from),
+ copied, sg_from->offset + offset);
+
+ len -= copied;
+ offset = 0;
+
+ if (sg_is_last(sg_from) || !len)
+ goto out;
+
+ sg_to = sg_next(sg_to);
+ to_nents--;
+ sg_from = sg_next(sg_from);
+ }
+
+ while (len > sg_from->length && to_nents--) {
+ len -= sg_from->length;
+ copied += sg_from->length;
+
+ sg_set_page(sg_to, sg_page(sg_from),
+ sg_from->length, sg_from->offset);
+
+ if (sg_is_last(sg_from) || !len)
+ goto out;
+
+ sg_from = sg_next(sg_from);
+ sg_to = sg_next(sg_to);
+ }
+
+ if (len && to_nents) {
+ sg_set_page(sg_to, sg_page(sg_from), len, sg_from->offset);
+ copied += len;
+ }
+out:
+ sg_mark_end(sg_to);
+ return copied;
+}
+
+/*
+ * Compares section of 'sg' starting from offset 'offset' and with length 'len'
+ * to linear buffer of length 'len' at address 'buffer'
+ * Returns 0 if equal and -1 otherwice
+ */
+static int msb_sg_compare_to_buffer(struct scatterlist *sg,
+ size_t offset, u8 *buffer, size_t len)
+{
+ int retval = 0, cmplen;
+ struct sg_mapping_iter miter;
+
+ sg_miter_start(&miter, sg, sg_nents(sg),
+ SG_MITER_ATOMIC | SG_MITER_FROM_SG);
+
+ while (sg_miter_next(&miter) && len > 0) {
+ if (offset >= miter.length) {
+ offset -= miter.length;
+ continue;
+ }
+
+ cmplen = min(miter.length - offset, len);
+ retval = memcmp(miter.addr + offset, buffer, cmplen) ? -1 : 0;
+ if (retval)
+ break;
+
+ buffer += cmplen;
+ len -= cmplen;
+ offset = 0;
+ }
+
+ if (!retval && len)
+ retval = -1;
+
+ sg_miter_stop(&miter);
+ return retval;
+}
+
+
+/* Get zone at which block with logical address 'lba' lives
+ * Flash is broken into zones.
+ * Each zone consists of 512 eraseblocks, out of which in first
+ * zone 494 are used and 496 are for all following zones.
+ * Therefore zone #0 hosts blocks 0-493, zone #1 blocks 494-988, etc...
+*/
+static int msb_get_zone_from_lba(int lba)
+{
+ if (lba < 494)
+ return 0;
+ return ((lba - 494) / 496) + 1;
+}
+
+/* Get zone of physical block. Trivial */
+static int msb_get_zone_from_pba(int pba)
+{
+ return pba / MS_BLOCKS_IN_ZONE;
+}
+
+/* Debug test to validate free block counts */
+#ifdef DEBUG
+static int msb_validate_used_block_bitmap(struct msb_data *msb)
+{
+ int total_free_blocks = 0;
+ int i;
+
+ for (i = 0 ; i < msb->zone_count ; i++)
+ total_free_blocks += msb->free_block_count[i];
+
+ if (msb->block_count - bitmap_weight(msb->used_blocks_bitmap,
+ msb->block_count) == total_free_blocks)
+ return 0;
+
+ pr_err("BUG: free block counts don't match the bitmap");
+ msb->read_only = true;
+ return -EINVAL;
+}
+#endif
+
+/* Mark physical block as used */
+static void msb_mark_block_used(struct msb_data *msb, int pba)
+{
+ int zone = msb_get_zone_from_pba(pba);
+
+ if (test_bit(pba, msb->used_blocks_bitmap)) {
+ pr_err(
+ "BUG: attempt to mark already used pba %d as used", pba);
+ msb->read_only = true;
+ return;
+ }
+
+#ifdef DEBUG
+ if (msb_validate_used_block_bitmap(msb))
+ return;
+#endif
+ /* No races because all IO is single threaded */
+ __set_bit(pba, msb->used_blocks_bitmap);
+ msb->free_block_count[zone]--;
+}
+
+/* Mark physical block as free */
+static void msb_mark_block_unused(struct msb_data *msb, int pba)
+{
+ int zone = msb_get_zone_from_pba(pba);
+
+ if (!test_bit(pba, msb->used_blocks_bitmap)) {
+ pr_err("BUG: attempt to mark "
+ "already unused pba %d as unused" , pba);
+ msb->read_only = true;
+ return;
+ }
+
+#ifdef DEBUG
+ if (msb_validate_used_block_bitmap(msb))
+ return;
+#endif
+ /* No races because all IO is single threaded */
+ __clear_bit(pba, msb->used_blocks_bitmap);
+ msb->free_block_count[zone]++;
+}
+
+/* Invalidate current register window */
+static void msb_invalidate_reg_window(struct msb_data *msb)
+{
+ msb->reg_addr.w_offset = offsetof(struct ms_register, id);
+ msb->reg_addr.w_length = sizeof(struct ms_id_register);
+ msb->reg_addr.r_offset = offsetof(struct ms_register, id);
+ msb->reg_addr.r_length = sizeof(struct ms_id_register);
+ msb->addr_valid = false;
+}
+
+/* Start a state machine */
+static int msb_run_state_machine(struct msb_data *msb, int (*state_func)
+ (struct memstick_dev *card, struct memstick_request **req))
+{
+ struct memstick_dev *card = msb->card;
+
+ WARN_ON(msb->state != -1);
+ msb->int_polling = false;
+ msb->state = 0;
+ msb->exit_error = 0;
+
+ memset(&card->current_mrq, 0, sizeof(card->current_mrq));
+
+ card->next_request = state_func;
+ memstick_new_req(card->host);
+ wait_for_completion(&card->mrq_complete);
+
+ WARN_ON(msb->state != -1);
+ return msb->exit_error;
+}
+
+/* State machines call that to exit */
+static int msb_exit_state_machine(struct msb_data *msb, int error)
+{
+ WARN_ON(msb->state == -1);
+
+ msb->state = -1;
+ msb->exit_error = error;
+ msb->card->next_request = h_msb_default_bad;
+
+ /* Invalidate reg window on errors */
+ if (error)
+ msb_invalidate_reg_window(msb);
+
+ complete(&msb->card->mrq_complete);
+ return -ENXIO;
+}
+
+/* read INT register */
+static int msb_read_int_reg(struct msb_data *msb, long timeout)
+{
+ struct memstick_request *mrq = &msb->card->current_mrq;
+
+ WARN_ON(msb->state == -1);
+
+ if (!msb->int_polling) {
+ msb->int_timeout = jiffies +
+ msecs_to_jiffies(timeout == -1 ? 500 : timeout);
+ msb->int_polling = true;
+ } else if (time_after(jiffies, msb->int_timeout)) {
+ mrq->data[0] = MEMSTICK_INT_CMDNAK;
+ return 0;
+ }
+
+ if ((msb->caps & MEMSTICK_CAP_AUTO_GET_INT) &&
+ mrq->need_card_int && !mrq->error) {
+ mrq->data[0] = mrq->int_reg;
+ mrq->need_card_int = false;
+ return 0;
+ } else {
+ memstick_init_req(mrq, MS_TPC_GET_INT, NULL, 1);
+ return 1;
+ }
+}
+
+/* Read a register */
+static int msb_read_regs(struct msb_data *msb, int offset, int len)
+{
+ struct memstick_request *req = &msb->card->current_mrq;
+
+ if (msb->reg_addr.r_offset != offset ||
+ msb->reg_addr.r_length != len || !msb->addr_valid) {
+
+ msb->reg_addr.r_offset = offset;
+ msb->reg_addr.r_length = len;
+ msb->addr_valid = true;
+
+ memstick_init_req(req, MS_TPC_SET_RW_REG_ADRS,
+ &msb->reg_addr, sizeof(msb->reg_addr));
+ return 0;
+ }
+
+ memstick_init_req(req, MS_TPC_READ_REG, NULL, len);
+ return 1;
+}
+
+/* Write a card register */
+static int msb_write_regs(struct msb_data *msb, int offset, int len, void *buf)
+{
+ struct memstick_request *req = &msb->card->current_mrq;
+
+ if (msb->reg_addr.w_offset != offset ||
+ msb->reg_addr.w_length != len || !msb->addr_valid) {
+
+ msb->reg_addr.w_offset = offset;
+ msb->reg_addr.w_length = len;
+ msb->addr_valid = true;
+
+ memstick_init_req(req, MS_TPC_SET_RW_REG_ADRS,
+ &msb->reg_addr, sizeof(msb->reg_addr));
+ return 0;
+ }
+
+ memstick_init_req(req, MS_TPC_WRITE_REG, buf, len);
+ return 1;
+}
+
+/* Handler for absence of IO */
+static int h_msb_default_bad(struct memstick_dev *card,
+ struct memstick_request **mrq)
+{
+ return -ENXIO;
+}
+
+/*
+ * This function is a handler for reads of one page from device.
+ * Writes output to msb->current_sg, takes sector address from msb->reg.param
+ * Can also be used to read extra data only. Set params accordintly.
+ */
+static int h_msb_read_page(struct memstick_dev *card,
+ struct memstick_request **out_mrq)
+{
+ struct msb_data *msb = memstick_get_drvdata(card);
+ struct memstick_request *mrq = *out_mrq = &card->current_mrq;
+ struct scatterlist sg[2];
+ u8 command, intreg;
+
+ if (mrq->error) {
+ dbg("read_page, unknown error");
+ return msb_exit_state_machine(msb, mrq->error);
+ }
+again:
+ switch (msb->state) {
+ case MSB_RP_SEND_BLOCK_ADDRESS:
+ /* msb_write_regs sometimes "fails" because it needs to update
+ the reg window, and thus it returns request for that.
+ Then we stay in this state and retry */
+ if (!msb_write_regs(msb,
+ offsetof(struct ms_register, param),
+ sizeof(struct ms_param_register),
+ (unsigned char *)&msb->regs.param))
+ return 0;
+
+ msb->state = MSB_RP_SEND_READ_COMMAND;
+ return 0;
+
+ case MSB_RP_SEND_READ_COMMAND:
+ command = MS_CMD_BLOCK_READ;
+ memstick_init_req(mrq, MS_TPC_SET_CMD, &command, 1);
+ msb->state = MSB_RP_SEND_INT_REQ;
+ return 0;
+
+ case MSB_RP_SEND_INT_REQ:
+ msb->state = MSB_RP_RECEIVE_INT_REQ_RESULT;
+ /* If dont actually need to send the int read request (only in
+ serial mode), then just fall through */
+ if (msb_read_int_reg(msb, -1))
+ return 0;
+ /* fallthrough */
+
+ case MSB_RP_RECEIVE_INT_REQ_RESULT:
+ intreg = mrq->data[0];
+ msb->regs.status.interrupt = intreg;
+
+ if (intreg & MEMSTICK_INT_CMDNAK)
+ return msb_exit_state_machine(msb, -EIO);
+
+ if (!(intreg & MEMSTICK_INT_CED)) {
+ msb->state = MSB_RP_SEND_INT_REQ;
+ goto again;
+ }
+
+ msb->int_polling = false;
+ msb->state = (intreg & MEMSTICK_INT_ERR) ?
+ MSB_RP_SEND_READ_STATUS_REG : MSB_RP_SEND_OOB_READ;
+ goto again;
+
+ case MSB_RP_SEND_READ_STATUS_REG:
+ /* read the status register to understand source of the INT_ERR */
+ if (!msb_read_regs(msb,
+ offsetof(struct ms_register, status),
+ sizeof(struct ms_status_register)))
+ return 0;
+
+ msb->state = MSB_RP_RECEIVE_OOB_READ;
+ return 0;
+
+ case MSB_RP_RECIVE_STATUS_REG:
+ msb->regs.status = *(struct ms_status_register *)mrq->data;
+ msb->state = MSB_RP_SEND_OOB_READ;
+ /* fallthrough */
+
+ case MSB_RP_SEND_OOB_READ:
+ if (!msb_read_regs(msb,
+ offsetof(struct ms_register, extra_data),
+ sizeof(struct ms_extra_data_register)))
+ return 0;
+
+ msb->state = MSB_RP_RECEIVE_OOB_READ;
+ return 0;
+
+ case MSB_RP_RECEIVE_OOB_READ:
+ msb->regs.extra_data =
+ *(struct ms_extra_data_register *) mrq->data;
+ msb->state = MSB_RP_SEND_READ_DATA;
+ /* fallthrough */
+
+ case MSB_RP_SEND_READ_DATA:
+ /* Skip that state if we only read the oob */
+ if (msb->regs.param.cp == MEMSTICK_CP_EXTRA) {
+ msb->state = MSB_RP_RECEIVE_READ_DATA;
+ goto again;
+ }
+
+ sg_init_table(sg, ARRAY_SIZE(sg));
+ msb_sg_copy(msb->current_sg, sg, ARRAY_SIZE(sg),
+ msb->current_sg_offset,
+ msb->page_size);
+
+ memstick_init_req_sg(mrq, MS_TPC_READ_LONG_DATA, sg);
+ msb->state = MSB_RP_RECEIVE_READ_DATA;
+ return 0;
+
+ case MSB_RP_RECEIVE_READ_DATA:
+ if (!(msb->regs.status.interrupt & MEMSTICK_INT_ERR)) {
+ msb->current_sg_offset += msb->page_size;
+ return msb_exit_state_machine(msb, 0);
+ }
+
+ if (msb->regs.status.status1 & MEMSTICK_UNCORR_ERROR) {
+ dbg("read_page: uncorrectable error");
+ return msb_exit_state_machine(msb, -EBADMSG);
+ }
+
+ if (msb->regs.status.status1 & MEMSTICK_CORR_ERROR) {
+ dbg("read_page: correctable error");
+ msb->current_sg_offset += msb->page_size;
+ return msb_exit_state_machine(msb, -EUCLEAN);
+ } else {
+ dbg("read_page: INT error, but no status error bits");
+ return msb_exit_state_machine(msb, -EIO);
+ }
+ }
+
+ BUG();
+}
+
+/*
+ * Handler of writes of exactly one block.
+ * Takes address from msb->regs.param.
+ * Writes same extra data to blocks, also taken
+ * from msb->regs.extra
+ * Returns -EBADMSG if write fails due to uncorrectable error, or -EIO if
+ * device refuses to take the command or something else
+ */
+static int h_msb_write_block(struct memstick_dev *card,
+ struct memstick_request **out_mrq)
+{
+ struct msb_data *msb = memstick_get_drvdata(card);
+ struct memstick_request *mrq = *out_mrq = &card->current_mrq;
+ struct scatterlist sg[2];
+ u8 intreg, command;
+
+ if (mrq->error)
+ return msb_exit_state_machine(msb, mrq->error);
+
+again:
+ switch (msb->state) {
+
+ /* HACK: Jmicon handling of TPCs between 8 and
+ * sizeof(memstick_request.data) is broken due to hardware
+ * bug in PIO mode that is used for these TPCs
+ * Therefore split the write
+ */
+
+ case MSB_WB_SEND_WRITE_PARAMS:
+ if (!msb_write_regs(msb,
+ offsetof(struct ms_register, param),
+ sizeof(struct ms_param_register),
+ &msb->regs.param))
+ return 0;
+
+ msb->state = MSB_WB_SEND_WRITE_OOB;
+ return 0;
+
+ case MSB_WB_SEND_WRITE_OOB:
+ if (!msb_write_regs(msb,
+ offsetof(struct ms_register, extra_data),
+ sizeof(struct ms_extra_data_register),
+ &msb->regs.extra_data))
+ return 0;
+ msb->state = MSB_WB_SEND_WRITE_COMMAND;
+ return 0;
+
+
+ case MSB_WB_SEND_WRITE_COMMAND:
+ command = MS_CMD_BLOCK_WRITE;
+ memstick_init_req(mrq, MS_TPC_SET_CMD, &command, 1);
+ msb->state = MSB_WB_SEND_INT_REQ;
+ return 0;
+
+ case MSB_WB_SEND_INT_REQ:
+ msb->state = MSB_WB_RECEIVE_INT_REQ;
+ if (msb_read_int_reg(msb, -1))
+ return 0;
+ /* fallthrough */
+
+ case MSB_WB_RECEIVE_INT_REQ:
+ intreg = mrq->data[0];
+ msb->regs.status.interrupt = intreg;
+
+ /* errors mean out of here, and fast... */
+ if (intreg & (MEMSTICK_INT_CMDNAK))
+ return msb_exit_state_machine(msb, -EIO);
+
+ if (intreg & MEMSTICK_INT_ERR)
+ return msb_exit_state_machine(msb, -EBADMSG);
+
+
+ /* for last page we need to poll CED */
+ if (msb->current_page == msb->pages_in_block) {
+ if (intreg & MEMSTICK_INT_CED)
+ return msb_exit_state_machine(msb, 0);
+ msb->state = MSB_WB_SEND_INT_REQ;
+ goto again;
+
+ }
+
+ /* for non-last page we need BREQ before writing next chunk */
+ if (!(intreg & MEMSTICK_INT_BREQ)) {
+ msb->state = MSB_WB_SEND_INT_REQ;
+ goto again;
+ }
+
+ msb->int_polling = false;
+ msb->state = MSB_WB_SEND_WRITE_DATA;
+ /* fallthrough */
+
+ case MSB_WB_SEND_WRITE_DATA:
+ sg_init_table(sg, ARRAY_SIZE(sg));
+
+ if (msb_sg_copy(msb->current_sg, sg, ARRAY_SIZE(sg),
+ msb->current_sg_offset,
+ msb->page_size) < msb->page_size)
+ return msb_exit_state_machine(msb, -EIO);
+
+ memstick_init_req_sg(mrq, MS_TPC_WRITE_LONG_DATA, sg);
+ mrq->need_card_int = 1;
+ msb->state = MSB_WB_RECEIVE_WRITE_CONFIRMATION;
+ return 0;
+
+ case MSB_WB_RECEIVE_WRITE_CONFIRMATION:
+ msb->current_page++;
+ msb->current_sg_offset += msb->page_size;
+ msb->state = MSB_WB_SEND_INT_REQ;
+ goto again;
+ default:
+ BUG();
+ }
+
+ return 0;
+}
+
+/*
+ * This function is used to send simple IO requests to device that consist
+ * of register write + command
+ */
+static int h_msb_send_command(struct memstick_dev *card,
+ struct memstick_request **out_mrq)
+{
+ struct msb_data *msb = memstick_get_drvdata(card);
+ struct memstick_request *mrq = *out_mrq = &card->current_mrq;
+ u8 intreg;
+
+ if (mrq->error) {
+ dbg("send_command: unknown error");
+ return msb_exit_state_machine(msb, mrq->error);
+ }
+again:
+ switch (msb->state) {
+
+ /* HACK: see h_msb_write_block */
+ case MSB_SC_SEND_WRITE_PARAMS: /* write param register*/
+ if (!msb_write_regs(msb,
+ offsetof(struct ms_register, param),
+ sizeof(struct ms_param_register),
+ &msb->regs.param))
+ return 0;
+ msb->state = MSB_SC_SEND_WRITE_OOB;
+ return 0;
+
+ case MSB_SC_SEND_WRITE_OOB:
+ if (!msb->command_need_oob) {
+ msb->state = MSB_SC_SEND_COMMAND;
+ goto again;
+ }
+
+ if (!msb_write_regs(msb,
+ offsetof(struct ms_register, extra_data),
+ sizeof(struct ms_extra_data_register),
+ &msb->regs.extra_data))
+ return 0;
+
+ msb->state = MSB_SC_SEND_COMMAND;
+ return 0;
+
+ case MSB_SC_SEND_COMMAND:
+ memstick_init_req(mrq, MS_TPC_SET_CMD, &msb->command_value, 1);
+ msb->state = MSB_SC_SEND_INT_REQ;
+ return 0;
+
+ case MSB_SC_SEND_INT_REQ:
+ msb->state = MSB_SC_RECEIVE_INT_REQ;
+ if (msb_read_int_reg(msb, -1))
+ return 0;
+ /* fallthrough */
+
+ case MSB_SC_RECEIVE_INT_REQ:
+ intreg = mrq->data[0];
+
+ if (intreg & MEMSTICK_INT_CMDNAK)
+ return msb_exit_state_machine(msb, -EIO);
+ if (intreg & MEMSTICK_INT_ERR)
+ return msb_exit_state_machine(msb, -EBADMSG);
+
+ if (!(intreg & MEMSTICK_INT_CED)) {
+ msb->state = MSB_SC_SEND_INT_REQ;
+ goto again;
+ }
+
+ return msb_exit_state_machine(msb, 0);
+ }
+
+ BUG();
+}
+
+/* Small handler for card reset */
+static int h_msb_reset(struct memstick_dev *card,
+ struct memstick_request **out_mrq)
+{
+ u8 command = MS_CMD_RESET;
+ struct msb_data *msb = memstick_get_drvdata(card);
+ struct memstick_request *mrq = *out_mrq = &card->current_mrq;
+
+ if (mrq->error)
+ return msb_exit_state_machine(msb, mrq->error);
+
+ switch (msb->state) {
+ case MSB_RS_SEND:
+ memstick_init_req(mrq, MS_TPC_SET_CMD, &command, 1);
+ mrq->need_card_int = 0;
+ msb->state = MSB_RS_CONFIRM;
+ return 0;
+ case MSB_RS_CONFIRM:
+ return msb_exit_state_machine(msb, 0);
+ }
+ BUG();
+}
+
+/* This handler is used to do serial->parallel switch */
+static int h_msb_parallel_switch(struct memstick_dev *card,
+ struct memstick_request **out_mrq)
+{
+ struct msb_data *msb = memstick_get_drvdata(card);
+ struct memstick_request *mrq = *out_mrq = &card->current_mrq;
+ struct memstick_host *host = card->host;
+
+ if (mrq->error) {
+ dbg("parallel_switch: error");
+ msb->regs.param.system &= ~MEMSTICK_SYS_PAM;
+ return msb_exit_state_machine(msb, mrq->error);
+ }
+
+ switch (msb->state) {
+ case MSB_PS_SEND_SWITCH_COMMAND:
+ /* Set the parallel interface on memstick side */
+ msb->regs.param.system |= MEMSTICK_SYS_PAM;
+
+ if (!msb_write_regs(msb,
+ offsetof(struct ms_register, param),
+ 1,
+ (unsigned char *)&msb->regs.param))
+ return 0;
+
+ msb->state = MSB_PS_SWICH_HOST;
+ return 0;
+
+ case MSB_PS_SWICH_HOST:
+ /* Set parallel interface on our side + send a dummy request
+ to see if card responds */
+ host->set_param(host, MEMSTICK_INTERFACE, MEMSTICK_PAR4);
+ memstick_init_req(mrq, MS_TPC_GET_INT, NULL, 1);
+ msb->state = MSB_PS_CONFIRM;
+ return 0;
+
+ case MSB_PS_CONFIRM:
+ return msb_exit_state_machine(msb, 0);
+ }
+
+ BUG();
+}
+
+static int msb_switch_to_parallel(struct msb_data *msb);
+
+/* Reset the card, to guard against hw errors beeing treated as bad blocks */
+static int msb_reset(struct msb_data *msb, bool full)
+{
+
+ bool was_parallel = msb->regs.param.system & MEMSTICK_SYS_PAM;
+ struct memstick_dev *card = msb->card;
+ struct memstick_host *host = card->host;
+ int error;
+
+ /* Reset the card */
+ msb->regs.param.system = MEMSTICK_SYS_BAMD;
+
+ if (full) {
+ error = host->set_param(host,
+ MEMSTICK_POWER, MEMSTICK_POWER_OFF);
+ if (error)
+ goto out_error;
+
+ msb_invalidate_reg_window(msb);
+
+ error = host->set_param(host,
+ MEMSTICK_POWER, MEMSTICK_POWER_ON);
+ if (error)
+ goto out_error;
+
+ error = host->set_param(host,
+ MEMSTICK_INTERFACE, MEMSTICK_SERIAL);
+ if (error) {
+out_error:
+ dbg("Failed to reset the host controller");
+ msb->read_only = true;
+ return -EFAULT;
+ }
+ }
+
+ error = msb_run_state_machine(msb, h_msb_reset);
+ if (error) {
+ dbg("Failed to reset the card");
+ msb->read_only = true;
+ return -ENODEV;
+ }
+
+ /* Set parallel mode */
+ if (was_parallel)
+ msb_switch_to_parallel(msb);
+ return 0;
+}
+
+/* Attempts to switch interface to parallel mode */
+static int msb_switch_to_parallel(struct msb_data *msb)
+{
+ int error;
+
+ error = msb_run_state_machine(msb, h_msb_parallel_switch);
+ if (error) {
+ pr_err("Switch to parallel failed");
+ msb->regs.param.system &= ~MEMSTICK_SYS_PAM;
+ msb_reset(msb, true);
+ return -EFAULT;
+ }
+
+ msb->caps |= MEMSTICK_CAP_AUTO_GET_INT;
+ return 0;
+}
+
+/* Changes overwrite flag on a page */
+static int msb_set_overwrite_flag(struct msb_data *msb,
+ u16 pba, u8 page, u8 flag)
+{
+ if (msb->read_only)
+ return -EROFS;
+
+ msb->regs.param.block_address = cpu_to_be16(pba);
+ msb->regs.param.page_address = page;
+ msb->regs.param.cp = MEMSTICK_CP_OVERWRITE;
+ msb->regs.extra_data.overwrite_flag = flag;
+ msb->command_value = MS_CMD_BLOCK_WRITE;
+ msb->command_need_oob = true;
+
+ dbg_verbose("changing overwrite flag to %02x for sector %d, page %d",
+ flag, pba, page);
+ return msb_run_state_machine(msb, h_msb_send_command);
+}
+
+static int msb_mark_bad(struct msb_data *msb, int pba)
+{
+ pr_notice("marking pba %d as bad", pba);
+ msb_reset(msb, true);
+ return msb_set_overwrite_flag(
+ msb, pba, 0, 0xFF & ~MEMSTICK_OVERWRITE_BKST);
+}
+
+static int msb_mark_page_bad(struct msb_data *msb, int pba, int page)
+{
+ dbg("marking page %d of pba %d as bad", page, pba);
+ msb_reset(msb, true);
+ return msb_set_overwrite_flag(msb,
+ pba, page, ~MEMSTICK_OVERWRITE_PGST0);
+}
+
+/* Erases one physical block */
+static int msb_erase_block(struct msb_data *msb, u16 pba)
+{
+ int error, try;
+ if (msb->read_only)
+ return -EROFS;
+
+ dbg_verbose("erasing pba %d", pba);
+
+ for (try = 1 ; try < 3 ; try++) {
+ msb->regs.param.block_address = cpu_to_be16(pba);
+ msb->regs.param.page_address = 0;
+ msb->regs.param.cp = MEMSTICK_CP_BLOCK;
+ msb->command_value = MS_CMD_BLOCK_ERASE;
+ msb->command_need_oob = false;
+
+
+ error = msb_run_state_machine(msb, h_msb_send_command);
+ if (!error || msb_reset(msb, true))
+ break;
+ }
+
+ if (error) {
+ pr_err("erase failed, marking pba %d as bad", pba);
+ msb_mark_bad(msb, pba);
+ }
+
+ dbg_verbose("erase success, marking pba %d as unused", pba);
+ msb_mark_block_unused(msb, pba);
+ __set_bit(pba, msb->erased_blocks_bitmap);
+ return error;
+}
+
+/* Reads one page from device */
+static int msb_read_page(struct msb_data *msb,
+ u16 pba, u8 page, struct ms_extra_data_register *extra,
+ struct scatterlist *sg, int offset)
+{
+ int try, error;
+
+ if (pba == MS_BLOCK_INVALID) {
+ unsigned long flags;
+ struct sg_mapping_iter miter;
+ size_t len = msb->page_size;
+
+ dbg_verbose("read unmapped sector. returning 0xFF");
+
+ local_irq_save(flags);
+ sg_miter_start(&miter, sg, sg_nents(sg),
+ SG_MITER_ATOMIC | SG_MITER_TO_SG);
+
+ while (sg_miter_next(&miter) && len > 0) {
+
+ int chunklen;
+
+ if (offset && offset >= miter.length) {
+ offset -= miter.length;
+ continue;
+ }
+
+ chunklen = min(miter.length - offset, len);
+ memset(miter.addr + offset, 0xFF, chunklen);
+ len -= chunklen;
+ offset = 0;
+ }
+
+ sg_miter_stop(&miter);
+ local_irq_restore(flags);
+
+ if (offset)
+ return -EFAULT;
+
+ if (extra)
+ memset(extra, 0xFF, sizeof(*extra));
+ return 0;
+ }
+
+ if (pba >= msb->block_count) {
+ pr_err("BUG: attempt to read beyond"
+ " the end of the card at pba %d", pba);
+ return -EINVAL;
+ }
+
+ for (try = 1 ; try < 3 ; try++) {
+ msb->regs.param.block_address = cpu_to_be16(pba);
+ msb->regs.param.page_address = page;
+ msb->regs.param.cp = MEMSTICK_CP_PAGE;
+
+ msb->current_sg = sg;
+ msb->current_sg_offset = offset;
+ error = msb_run_state_machine(msb, h_msb_read_page);
+
+
+ if (error == -EUCLEAN) {
+ pr_notice("correctable error on pba %d, page %d",
+ pba, page);
+ error = 0;
+ }
+
+ if (!error && extra)
+ *extra = msb->regs.extra_data;
+
+ if (!error || msb_reset(msb, true))
+ break;
+
+ }
+
+ /* Mark bad pages */
+ if (error == -EBADMSG) {
+ pr_err("uncorrectable error on read of pba %d, page %d",
+ pba, page);
+
+ if (msb->regs.extra_data.overwrite_flag &
+ MEMSTICK_OVERWRITE_PGST0)
+ msb_mark_page_bad(msb, pba, page);
+ return -EBADMSG;
+ }
+
+ if (error)
+ pr_err("read of pba %d, page %d failed with error %d",
+ pba, page, error);
+ return error;
+}
+
+/* Reads oob of page only */
+static int msb_read_oob(struct msb_data *msb, u16 pba, u16 page,
+ struct ms_extra_data_register *extra)
+{
+ int error;
+
+ BUG_ON(!extra);
+ msb->regs.param.block_address = cpu_to_be16(pba);
+ msb->regs.param.page_address = page;
+ msb->regs.param.cp = MEMSTICK_CP_EXTRA;
+
+ if (pba > msb->block_count) {
+ pr_err("BUG: attempt to read beyond"
+ " the end of card at pba %d", pba);
+ return -EINVAL;
+ }
+
+ error = msb_run_state_machine(msb, h_msb_read_page);
+ *extra = msb->regs.extra_data;
+
+ if (error == -EUCLEAN) {
+ pr_notice("correctable error on pba %d, page %d",
+ pba, page);
+ return 0;
+ }
+
+ return error;
+}
+
+
+/* Reads a block and compares it with data contained in scatterlist orig_sg */
+static int msb_verify_block(struct msb_data *msb, u16 pba,
+ struct scatterlist *orig_sg, int offset)
+{
+ struct scatterlist sg;
+ int page = 0, error;
+
+ sg_init_one(&sg, msb->block_buffer, msb->block_size);
+
+ while (page < msb->pages_in_block) {
+
+ error = msb_read_page(msb, pba, page,
+ NULL, &sg, page * msb->page_size);
+ if (error)
+ return error;
+ page++;
+ }
+
+ if (msb_sg_compare_to_buffer(orig_sg, offset,
+ msb->block_buffer, msb->block_size))
+ return -EIO;
+ return 0;
+}
+
+/* Writes exectly one block + oob */
+static int msb_write_block(struct msb_data *msb,
+ u16 pba, u32 lba, struct scatterlist *sg, int offset)
+{
+ int error, current_try = 1;
+ BUG_ON(sg->length < msb->page_size);
+
+ if (msb->read_only)
+ return -EROFS;
+
+ if (pba == MS_BLOCK_INVALID) {
+ pr_err(
+ "BUG: write: attempt to write MS_BLOCK_INVALID block");
+ return -EINVAL;
+ }
+
+ if (pba >= msb->block_count || lba >= msb->logical_block_count) {
+ pr_err(
+ "BUG: write: attempt to write beyond the end of device");
+ return -EINVAL;
+ }
+
+ if (msb_get_zone_from_lba(lba) != msb_get_zone_from_pba(pba)) {
+ pr_err("BUG: write: lba zone mismatch");
+ return -EINVAL;
+ }
+
+ if (pba == msb->boot_block_locations[0] ||
+ pba == msb->boot_block_locations[1]) {
+ pr_err("BUG: write: attempt to write to boot blocks!");
+ return -EINVAL;
+ }
+
+ while (1) {
+
+ if (msb->read_only)
+ return -EROFS;
+
+ msb->regs.param.cp = MEMSTICK_CP_BLOCK;
+ msb->regs.param.page_address = 0;
+ msb->regs.param.block_address = cpu_to_be16(pba);
+
+ msb->regs.extra_data.management_flag = 0xFF;
+ msb->regs.extra_data.overwrite_flag = 0xF8;
+ msb->regs.extra_data.logical_address = cpu_to_be16(lba);
+
+ msb->current_sg = sg;
+ msb->current_sg_offset = offset;
+ msb->current_page = 0;
+
+ error = msb_run_state_machine(msb, h_msb_write_block);
+
+ /* Sector we just wrote to is assumed erased since its pba
+ was erased. If it wasn't erased, write will succeed
+ and will just clear the bits that were set in the block
+ thus test that what we have written,
+ matches what we expect.
+ We do trust the blocks that we erased */
+ if (!error && (verify_writes ||
+ !test_bit(pba, msb->erased_blocks_bitmap)))
+ error = msb_verify_block(msb, pba, sg, offset);
+
+ if (!error)
+ break;
+
+ if (current_try > 1 || msb_reset(msb, true))
+ break;
+
+ pr_err("write failed, trying to erase the pba %d", pba);
+ error = msb_erase_block(msb, pba);
+ if (error)
+ break;
+
+ current_try++;
+ }
+ return error;
+}
+
+/* Finds a free block for write replacement */
+static u16 msb_get_free_block(struct msb_data *msb, int zone)
+{
+ u16 pos;
+ int pba = zone * MS_BLOCKS_IN_ZONE;
+ int i;
+
+ get_random_bytes(&pos, sizeof(pos));
+
+ if (!msb->free_block_count[zone]) {
+ pr_err("NO free blocks in the zone %d, to use for a write, "
+ "(media is WORN out) switching to RO mode", zone);
+ msb->read_only = true;
+ return MS_BLOCK_INVALID;
+ }
+
+ pos %= msb->free_block_count[zone];
+
+ dbg_verbose("have %d choices for a free block, selected randomally: %d",
+ msb->free_block_count[zone], pos);
+
+ pba = find_next_zero_bit(msb->used_blocks_bitmap,
+ msb->block_count, pba);
+ for (i = 0 ; i < pos ; ++i)
+ pba = find_next_zero_bit(msb->used_blocks_bitmap,
+ msb->block_count, pba + 1);
+
+ dbg_verbose("result of the free blocks scan: pba %d", pba);
+
+ if (pba == msb->block_count || (msb_get_zone_from_pba(pba)) != zone) {
+ pr_err("BUG: cant get a free block");
+ msb->read_only = true;
+ return MS_BLOCK_INVALID;
+ }
+
+ msb_mark_block_used(msb, pba);
+ return pba;
+}
+
+static int msb_update_block(struct msb_data *msb, u16 lba,
+ struct scatterlist *sg, int offset)
+{
+ u16 pba, new_pba;
+ int error, try;
+
+ pba = msb->lba_to_pba_table[lba];
+ dbg_verbose("start of a block update at lba %d, pba %d", lba, pba);
+
+ if (pba != MS_BLOCK_INVALID) {
+ dbg_verbose("setting the update flag on the block");
+ msb_set_overwrite_flag(msb, pba, 0,
+ 0xFF & ~MEMSTICK_OVERWRITE_UDST);
+ }
+
+ for (try = 0 ; try < 3 ; try++) {
+ new_pba = msb_get_free_block(msb,
+ msb_get_zone_from_lba(lba));
+
+ if (new_pba == MS_BLOCK_INVALID) {
+ error = -EIO;
+ goto out;
+ }
+
+ dbg_verbose("block update: writing updated block to the pba %d",
+ new_pba);
+ error = msb_write_block(msb, new_pba, lba, sg, offset);
+ if (error == -EBADMSG) {
+ msb_mark_bad(msb, new_pba);
+ continue;
+ }
+
+ if (error)
+ goto out;
+
+ dbg_verbose("block update: erasing the old block");
+ msb_erase_block(msb, pba);
+ msb->lba_to_pba_table[lba] = new_pba;
+ return 0;
+ }
+out:
+ if (error) {
+ pr_err("block update error after %d tries, "
+ "switching to r/o mode", try);
+ msb->read_only = true;
+ }
+ return error;
+}
+
+/* Converts endiannes in the boot block for easy use */
+static void msb_fix_boot_page_endianness(struct ms_boot_page *p)
+{
+ p->header.block_id = be16_to_cpu(p->header.block_id);
+ p->header.format_reserved = be16_to_cpu(p->header.format_reserved);
+ p->entry.disabled_block.start_addr
+ = be32_to_cpu(p->entry.disabled_block.start_addr);
+ p->entry.disabled_block.data_size
+ = be32_to_cpu(p->entry.disabled_block.data_size);
+ p->entry.cis_idi.start_addr
+ = be32_to_cpu(p->entry.cis_idi.start_addr);
+ p->entry.cis_idi.data_size
+ = be32_to_cpu(p->entry.cis_idi.data_size);
+ p->attr.block_size = be16_to_cpu(p->attr.block_size);
+ p->attr.number_of_blocks = be16_to_cpu(p->attr.number_of_blocks);
+ p->attr.number_of_effective_blocks
+ = be16_to_cpu(p->attr.number_of_effective_blocks);
+ p->attr.page_size = be16_to_cpu(p->attr.page_size);
+ p->attr.memory_manufacturer_code
+ = be16_to_cpu(p->attr.memory_manufacturer_code);
+ p->attr.memory_device_code = be16_to_cpu(p->attr.memory_device_code);
+ p->attr.implemented_capacity
+ = be16_to_cpu(p->attr.implemented_capacity);
+ p->attr.controller_number = be16_to_cpu(p->attr.controller_number);
+ p->attr.controller_function = be16_to_cpu(p->attr.controller_function);
+}
+
+static int msb_read_boot_blocks(struct msb_data *msb)
+{
+ int pba = 0;
+ struct scatterlist sg;
+ struct ms_extra_data_register extra;
+ struct ms_boot_page *page;
+
+ msb->boot_block_locations[0] = MS_BLOCK_INVALID;
+ msb->boot_block_locations[1] = MS_BLOCK_INVALID;
+ msb->boot_block_count = 0;
+
+ dbg_verbose("Start of a scan for the boot blocks");
+
+ if (!msb->boot_page) {
+ page = kmalloc(sizeof(struct ms_boot_page)*2, GFP_KERNEL);
+ if (!page)
+ return -ENOMEM;
+
+ msb->boot_page = page;
+ } else
+ page = msb->boot_page;
+
+ msb->block_count = MS_BLOCK_MAX_BOOT_ADDR;
+
+ for (pba = 0 ; pba < MS_BLOCK_MAX_BOOT_ADDR ; pba++) {
+
+ sg_init_one(&sg, page, sizeof(*page));
+ if (msb_read_page(msb, pba, 0, &extra, &sg, 0)) {
+ dbg("boot scan: can't read pba %d", pba);
+ continue;
+ }
+
+ if (extra.management_flag & MEMSTICK_MANAGEMENT_SYSFLG) {
+ dbg("managment flag doesn't indicate boot block %d",
+ pba);
+ continue;
+ }
+
+ if (be16_to_cpu(page->header.block_id) != MS_BLOCK_BOOT_ID) {
+ dbg("the pba at %d doesn' contain boot block ID", pba);
+ continue;
+ }
+
+ msb_fix_boot_page_endianness(page);
+ msb->boot_block_locations[msb->boot_block_count] = pba;
+
+ page++;
+ msb->boot_block_count++;
+
+ if (msb->boot_block_count == 2)
+ break;
+ }
+
+ if (!msb->boot_block_count) {
+ pr_err("media doesn't contain master page, aborting");
+ return -EIO;
+ }
+
+ dbg_verbose("End of scan for boot blocks");
+ return 0;
+}
+
+static int msb_read_bad_block_table(struct msb_data *msb, int block_nr)
+{
+ struct ms_boot_page *boot_block;
+ struct scatterlist sg;
+ u16 *buffer = NULL;
+ int offset = 0;
+ int i, error = 0;
+ int data_size, data_offset, page, page_offset, size_to_read;
+ u16 pba;
+
+ BUG_ON(block_nr > 1);
+ boot_block = &msb->boot_page[block_nr];
+ pba = msb->boot_block_locations[block_nr];
+
+ if (msb->boot_block_locations[block_nr] == MS_BLOCK_INVALID)
+ return -EINVAL;
+
+ data_size = boot_block->entry.disabled_block.data_size;
+ data_offset = sizeof(struct ms_boot_page) +
+ boot_block->entry.disabled_block.start_addr;
+ if (!data_size)
+ return 0;
+
+ page = data_offset / msb->page_size;
+ page_offset = data_offset % msb->page_size;
+ size_to_read =
+ DIV_ROUND_UP(data_size + page_offset, msb->page_size) *
+ msb->page_size;
+
+ dbg("reading bad block of boot block at pba %d, offset %d len %d",
+ pba, data_offset, data_size);
+
+ buffer = kzalloc(size_to_read, GFP_KERNEL);
+ if (!buffer)
+ return -ENOMEM;
+
+ /* Read the buffer */
+ sg_init_one(&sg, buffer, size_to_read);
+
+ while (offset < size_to_read) {
+ error = msb_read_page(msb, pba, page, NULL, &sg, offset);
+ if (error)
+ goto out;
+
+ page++;
+ offset += msb->page_size;
+
+ if (page == msb->pages_in_block) {
+ pr_err(
+ "bad block table extends beyond the boot block");
+ break;
+ }
+ }
+
+ /* Process the bad block table */
+ for (i = page_offset ; i < data_size / sizeof(u16) ; i++) {
+
+ u16 bad_block = be16_to_cpu(buffer[i]);
+
+ if (bad_block >= msb->block_count) {
+ dbg("bad block table contains invalid block %d",
+ bad_block);
+ continue;
+ }
+
+ if (test_bit(bad_block, msb->used_blocks_bitmap)) {
+ dbg("duplicate bad block %d in the table",
+ bad_block);
+ continue;
+ }
+
+ dbg("block %d is marked as factory bad", bad_block);
+ msb_mark_block_used(msb, bad_block);
+ }
+out:
+ kfree(buffer);
+ return error;
+}
+
+static int msb_ftl_initialize(struct msb_data *msb)
+{
+ int i;
+
+ if (msb->ftl_initialized)
+ return 0;
+
+ msb->zone_count = msb->block_count / MS_BLOCKS_IN_ZONE;
+ msb->logical_block_count = msb->zone_count * 496 - 2;
+
+ msb->used_blocks_bitmap = kzalloc(msb->block_count / 8, GFP_KERNEL);
+ msb->erased_blocks_bitmap = kzalloc(msb->block_count / 8, GFP_KERNEL);
+ msb->lba_to_pba_table =
+ kmalloc(msb->logical_block_count * sizeof(u16), GFP_KERNEL);
+
+ if (!msb->used_blocks_bitmap || !msb->lba_to_pba_table ||
+ !msb->erased_blocks_bitmap) {
+ kfree(msb->used_blocks_bitmap);
+ kfree(msb->lba_to_pba_table);
+ kfree(msb->erased_blocks_bitmap);
+ return -ENOMEM;
+ }
+
+ for (i = 0 ; i < msb->zone_count ; i++)
+ msb->free_block_count[i] = MS_BLOCKS_IN_ZONE;
+
+ memset(msb->lba_to_pba_table, MS_BLOCK_INVALID,
+ msb->logical_block_count * sizeof(u16));
+
+ dbg("initial FTL tables created. Zone count = %d, "
+ "Logical block count = %d",
+ msb->zone_count, msb->logical_block_count);
+
+ msb->ftl_initialized = true;
+ return 0;
+}
+
+static int msb_ftl_scan(struct msb_data *msb)
+{
+ u16 pba, lba, other_block;
+ u8 overwrite_flag, managment_flag, other_overwrite_flag;
+ int error;
+ struct ms_extra_data_register extra;
+ u8 *overwrite_flags = kzalloc(msb->block_count, GFP_KERNEL);
+
+ if (!overwrite_flags)
+ return -ENOMEM;
+
+ dbg("Start of media scanning");
+ for (pba = 0 ; pba < msb->block_count ; pba++) {
+
+ if (pba == msb->boot_block_locations[0] ||
+ pba == msb->boot_block_locations[1]) {
+ dbg_verbose("pba %05d -> [boot block]", pba);
+ msb_mark_block_used(msb, pba);
+ continue;
+ }
+
+ if (test_bit(pba, msb->used_blocks_bitmap)) {
+ dbg_verbose("pba %05d -> [factory bad]", pba);
+ continue;
+ }
+
+ memset(&extra, 0, sizeof(extra));
+ error = msb_read_oob(msb, pba, 0, &extra);
+
+ /* can't trust the page if we can't read the oob */
+ if (error == -EBADMSG) {
+ pr_notice(
+ "oob of pba %d damaged, will try to erase it", pba);
+ msb_mark_block_used(msb, pba);
+ msb_erase_block(msb, pba);
+ continue;
+ } else if (error)
+ return error;
+
+ lba = be16_to_cpu(extra.logical_address);
+ managment_flag = extra.management_flag;
+ overwrite_flag = extra.overwrite_flag;
+ overwrite_flags[pba] = overwrite_flag;
+
+ /* Skip bad blocks */
+ if (!(overwrite_flag & MEMSTICK_OVERWRITE_BKST)) {
+ dbg("pba %05d -> [BAD]", pba);
+ msb_mark_block_used(msb, pba);
+ continue;
+ }
+
+ /* Skip system/drm blocks */
+ if ((managment_flag & MEMSTICK_MANAGMENT_FLAG_NORMAL) !=
+ MEMSTICK_MANAGMENT_FLAG_NORMAL) {
+ dbg("pba %05d -> [reserved managment flag %02x]",
+ pba, managment_flag);
+ msb_mark_block_used(msb, pba);
+ continue;
+ }
+
+ /* Erase temporary tables */
+ if (!(managment_flag & MEMSTICK_MANAGEMENT_ATFLG)) {
+ dbg("pba %05d -> [temp table] - will erase", pba);
+
+ msb_mark_block_used(msb, pba);
+ msb_erase_block(msb, pba);
+ continue;
+ }
+
+ if (lba == MS_BLOCK_INVALID) {
+ dbg_verbose("pba %05d -> [free]", pba);
+ continue;
+ }
+
+ msb_mark_block_used(msb, pba);
+
+ /* Block has LBA not according to zoning*/
+ if (msb_get_zone_from_lba(lba) != msb_get_zone_from_pba(pba)) {
+ pr_notice("pba %05d -> [bad lba %05d] - will erase",
+ pba, lba);
+ msb_erase_block(msb, pba);
+ continue;
+ }
+
+ /* No collisions - great */
+ if (msb->lba_to_pba_table[lba] == MS_BLOCK_INVALID) {
+ dbg_verbose("pba %05d -> [lba %05d]", pba, lba);
+ msb->lba_to_pba_table[lba] = pba;
+ continue;
+ }
+
+ other_block = msb->lba_to_pba_table[lba];
+ other_overwrite_flag = overwrite_flags[other_block];
+
+ pr_notice("Collision between pba %d and pba %d",
+ pba, other_block);
+
+ if (!(overwrite_flag & MEMSTICK_OVERWRITE_UDST)) {
+ pr_notice("pba %d is marked as stable, use it", pba);
+ msb_erase_block(msb, other_block);
+ msb->lba_to_pba_table[lba] = pba;
+ continue;
+ }
+
+ if (!(other_overwrite_flag & MEMSTICK_OVERWRITE_UDST)) {
+ pr_notice("pba %d is marked as stable, use it",
+ other_block);
+ msb_erase_block(msb, pba);
+ continue;
+ }
+
+ pr_notice("collision between blocks %d and %d,"
+ " without stable flag set on both, erasing pba %d",
+ pba, other_block, other_block);
+
+ msb_erase_block(msb, other_block);
+ msb->lba_to_pba_table[lba] = pba;
+ }
+
+ dbg("End of media scanning");
+ kfree(overwrite_flags);
+ return 0;
+}
+
+static void msb_cache_flush_timer(unsigned long data)
+{
+ struct msb_data *msb = (struct msb_data *)data;
+ msb->need_flush_cache = true;
+ queue_work(msb->io_queue, &msb->io_work);
+}
+
+
+static void msb_cache_discard(struct msb_data *msb)
+{
+ if (msb->cache_block_lba == MS_BLOCK_INVALID)
+ return;
+
+ del_timer_sync(&msb->cache_flush_timer);
+
+ dbg_verbose("Discarding the write cache");
+ msb->cache_block_lba = MS_BLOCK_INVALID;
+ bitmap_zero(&msb->valid_cache_bitmap, msb->pages_in_block);
+}
+
+static int msb_cache_init(struct msb_data *msb)
+{
+ setup_timer(&msb->cache_flush_timer, msb_cache_flush_timer,
+ (unsigned long)msb);
+
+ if (!msb->cache)
+ msb->cache = kzalloc(msb->block_size, GFP_KERNEL);
+ if (!msb->cache)
+ return -ENOMEM;
+
+ msb_cache_discard(msb);
+ return 0;
+}
+
+static int msb_cache_flush(struct msb_data *msb)
+{
+ struct scatterlist sg;
+ struct ms_extra_data_register extra;
+ int page, offset, error;
+ u16 pba, lba;
+
+ if (msb->read_only)
+ return -EROFS;
+
+ if (msb->cache_block_lba == MS_BLOCK_INVALID)
+ return 0;
+
+ lba = msb->cache_block_lba;
+ pba = msb->lba_to_pba_table[lba];
+
+ dbg_verbose("Flushing the write cache of pba %d (LBA %d)",
+ pba, msb->cache_block_lba);
+
+ sg_init_one(&sg, msb->cache , msb->block_size);
+
+ /* Read all missing pages in cache */
+ for (page = 0 ; page < msb->pages_in_block ; page++) {
+
+ if (test_bit(page, &msb->valid_cache_bitmap))
+ continue;
+
+ offset = page * msb->page_size;
+
+ dbg_verbose("reading non-present sector %d of cache block %d",
+ page, lba);
+ error = msb_read_page(msb, pba, page, &extra, &sg, offset);
+
+ /* Bad pages are copied with 00 page status */
+ if (error == -EBADMSG) {
+ pr_err("read error on sector %d, contents probably"
+ " damaged", page);
+ continue;
+ }
+
+ if (error)
+ return error;
+
+ if ((extra.overwrite_flag & MEMSTICK_OV_PG_NORMAL) !=
+ MEMSTICK_OV_PG_NORMAL) {
+ dbg("page %d is marked as bad", page);
+ continue;
+ }
+
+ set_bit(page, &msb->valid_cache_bitmap);
+ }
+
+ /* Write the cache now */
+ error = msb_update_block(msb, msb->cache_block_lba, &sg, 0);
+ pba = msb->lba_to_pba_table[msb->cache_block_lba];
+
+ /* Mark invalid pages */
+ if (!error) {
+ for (page = 0 ; page < msb->pages_in_block ; page++) {
+
+ if (test_bit(page, &msb->valid_cache_bitmap))
+ continue;
+
+ dbg("marking page %d as containing damaged data",
+ page);
+ msb_set_overwrite_flag(msb,
+ pba , page, 0xFF & ~MEMSTICK_OV_PG_NORMAL);
+ }
+ }
+
+ msb_cache_discard(msb);
+ return error;
+}
+
+static int msb_cache_write(struct msb_data *msb, int lba,
+ int page, bool add_to_cache_only, struct scatterlist *sg, int offset)
+{
+ int error;
+ struct scatterlist sg_tmp[10];
+
+ if (msb->read_only)
+ return -EROFS;
+
+ if (msb->cache_block_lba == MS_BLOCK_INVALID ||
+ lba != msb->cache_block_lba)
+ if (add_to_cache_only)
+ return 0;
+
+ /* If we need to write different block */
+ if (msb->cache_block_lba != MS_BLOCK_INVALID &&
+ lba != msb->cache_block_lba) {
+ dbg_verbose("first flush the cache");
+ error = msb_cache_flush(msb);
+ if (error)
+ return error;
+ }
+
+ if (msb->cache_block_lba == MS_BLOCK_INVALID) {
+ msb->cache_block_lba = lba;
+ mod_timer(&msb->cache_flush_timer,
+ jiffies + msecs_to_jiffies(cache_flush_timeout));
+ }
+
+ dbg_verbose("Write of LBA %d page %d to cache ", lba, page);
+
+ sg_init_table(sg_tmp, ARRAY_SIZE(sg_tmp));
+ msb_sg_copy(sg, sg_tmp, ARRAY_SIZE(sg_tmp), offset, msb->page_size);
+
+ sg_copy_to_buffer(sg_tmp, sg_nents(sg_tmp),
+ msb->cache + page * msb->page_size, msb->page_size);
+
+ set_bit(page, &msb->valid_cache_bitmap);
+ return 0;
+}
+
+static int msb_cache_read(struct msb_data *msb, int lba,
+ int page, struct scatterlist *sg, int offset)
+{
+ int pba = msb->lba_to_pba_table[lba];
+ struct scatterlist sg_tmp[10];
+ int error = 0;
+
+ if (lba == msb->cache_block_lba &&
+ test_bit(page, &msb->valid_cache_bitmap)) {
+
+ dbg_verbose("Read of LBA %d (pba %d) sector %d from cache",
+ lba, pba, page);
+
+ sg_init_table(sg_tmp, ARRAY_SIZE(sg_tmp));
+ msb_sg_copy(sg, sg_tmp, ARRAY_SIZE(sg_tmp), offset, msb->page_size);
+ sg_copy_from_buffer(sg_tmp, sg_nents(sg_tmp),
+ msb->cache + msb->page_size * page,
+ msb->page_size);
+ } else {
+ dbg_verbose("Read of LBA %d (pba %d) sector %d from device",
+ lba, pba, page);
+
+ error = msb_read_page(msb, pba, page, NULL, sg, offset);
+ if (error)
+ return error;
+
+ msb_cache_write(msb, lba, page, true, sg, offset);
+ }
+ return error;
+}
+
+/* Emulated geometry table
+ * This table content isn't that importaint,
+ * One could put here different values, providing that they still
+ * cover whole disk.
+ * 64 MB entry is what windows reports for my 64M memstick */
+
+static const struct chs_entry chs_table[] = {
+/* size sectors cylynders heads */
+ { 4, 16, 247, 2 },
+ { 8, 16, 495, 2 },
+ { 16, 16, 495, 4 },
+ { 32, 16, 991, 4 },
+ { 64, 16, 991, 8 },
+ {128, 16, 991, 16 },
+ { 0 }
+};
+
+/* Load information about the card */
+static int msb_init_card(struct memstick_dev *card)
+{
+ struct msb_data *msb = memstick_get_drvdata(card);
+ struct memstick_host *host = card->host;
+ struct ms_boot_page *boot_block;
+ int error = 0, i, raw_size_in_megs;
+
+ msb->caps = 0;
+
+ if (card->id.class >= MEMSTICK_CLASS_ROM &&
+ card->id.class <= MEMSTICK_CLASS_ROM)
+ msb->read_only = true;
+
+ msb->state = -1;
+ error = msb_reset(msb, false);
+ if (error)
+ return error;
+
+ /* Due to a bug in Jmicron driver written by Alex Dubov,
+ its serial mode barely works,
+ so we switch to parallel mode right away */
+ if (host->caps & MEMSTICK_CAP_PAR4)
+ msb_switch_to_parallel(msb);
+
+ msb->page_size = sizeof(struct ms_boot_page);
+
+ /* Read the boot page */
+ error = msb_read_boot_blocks(msb);
+ if (error)
+ return -EIO;
+
+ boot_block = &msb->boot_page[0];
+
+ /* Save intersting attributes from boot page */
+ msb->block_count = boot_block->attr.number_of_blocks;
+ msb->page_size = boot_block->attr.page_size;
+
+ msb->pages_in_block = boot_block->attr.block_size * 2;
+ msb->block_size = msb->page_size * msb->pages_in_block;
+
+ if (msb->page_size > PAGE_SIZE) {
+ /* this isn't supported by linux at all, anyway*/
+ dbg("device page %d size isn't supported", msb->page_size);
+ return -EINVAL;
+ }
+
+ msb->block_buffer = kzalloc(msb->block_size, GFP_KERNEL);
+ if (!msb->block_buffer)
+ return -ENOMEM;
+
+ raw_size_in_megs = (msb->block_size * msb->block_count) >> 20;
+
+ for (i = 0 ; chs_table[i].size ; i++) {
+
+ if (chs_table[i].size != raw_size_in_megs)
+ continue;
+
+ msb->geometry.cylinders = chs_table[i].cyl;
+ msb->geometry.heads = chs_table[i].head;
+ msb->geometry.sectors = chs_table[i].sec;
+ break;
+ }
+
+ if (boot_block->attr.transfer_supporting == 1)
+ msb->caps |= MEMSTICK_CAP_PAR4;
+
+ if (boot_block->attr.device_type & 0x03)
+ msb->read_only = true;
+
+ dbg("Total block count = %d", msb->block_count);
+ dbg("Each block consists of %d pages", msb->pages_in_block);
+ dbg("Page size = %d bytes", msb->page_size);
+ dbg("Parallel mode supported: %d", !!(msb->caps & MEMSTICK_CAP_PAR4));
+ dbg("Read only: %d", msb->read_only);
+
+#if 0
+ /* Now we can switch the interface */
+ if (host->caps & msb->caps & MEMSTICK_CAP_PAR4)
+ msb_switch_to_parallel(msb);
+#endif
+
+ error = msb_cache_init(msb);
+ if (error)
+ return error;
+
+ error = msb_ftl_initialize(msb);
+ if (error)
+ return error;
+
+
+ /* Read the bad block table */
+ error = msb_read_bad_block_table(msb, 0);
+
+ if (error && error != -ENOMEM) {
+ dbg("failed to read bad block table from primary boot block,"
+ " trying from backup");
+ error = msb_read_bad_block_table(msb, 1);
+ }
+
+ if (error)
+ return error;
+
+ /* *drum roll* Scan the media */
+ error = msb_ftl_scan(msb);
+ if (error) {
+ pr_err("Scan of media failed");
+ return error;
+ }
+
+ return 0;
+
+}
+
+static int msb_do_write_request(struct msb_data *msb, int lba,
+ int page, struct scatterlist *sg, size_t len, int *sucessfuly_written)
+{
+ int error = 0;
+ off_t offset = 0;
+ *sucessfuly_written = 0;
+
+ while (offset < len) {
+ if (page == 0 && len - offset >= msb->block_size) {
+
+ if (msb->cache_block_lba == lba)
+ msb_cache_discard(msb);
+
+ dbg_verbose("Writing whole lba %d", lba);
+ error = msb_update_block(msb, lba, sg, offset);
+ if (error)
+ return error;
+
+ offset += msb->block_size;
+ *sucessfuly_written += msb->block_size;
+ lba++;
+ continue;
+ }
+
+ error = msb_cache_write(msb, lba, page, false, sg, offset);
+ if (error)
+ return error;
+
+ offset += msb->page_size;
+ *sucessfuly_written += msb->page_size;
+
+ page++;
+ if (page == msb->pages_in_block) {
+ page = 0;
+ lba++;
+ }
+ }
+ return 0;
+}
+
+static int msb_do_read_request(struct msb_data *msb, int lba,
+ int page, struct scatterlist *sg, int len, int *sucessfuly_read)
+{
+ int error = 0;
+ int offset = 0;
+ *sucessfuly_read = 0;
+
+ while (offset < len) {
+
+ error = msb_cache_read(msb, lba, page, sg, offset);
+ if (error)
+ return error;
+
+ offset += msb->page_size;
+ *sucessfuly_read += msb->page_size;
+
+ page++;
+ if (page == msb->pages_in_block) {
+ page = 0;
+ lba++;
+ }
+ }
+ return 0;
+}
+
+static void msb_io_work(struct work_struct *work)
+{
+ struct msb_data *msb = container_of(work, struct msb_data, io_work);
+ int page, error, len;
+ sector_t lba;
+ unsigned long flags;
+ struct scatterlist *sg = msb->prealloc_sg;
+
+ dbg_verbose("IO: work started");
+
+ while (1) {
+ spin_lock_irqsave(&msb->q_lock, flags);
+
+ if (msb->need_flush_cache) {
+ msb->need_flush_cache = false;
+ spin_unlock_irqrestore(&msb->q_lock, flags);
+ msb_cache_flush(msb);
+ continue;
+ }
+
+ if (!msb->req) {
+ msb->req = blk_fetch_request(msb->queue);
+ if (!msb->req) {
+ dbg_verbose("IO: no more requests exiting");
+ spin_unlock_irqrestore(&msb->q_lock, flags);
+ return;
+ }
+ }
+
+ spin_unlock_irqrestore(&msb->q_lock, flags);
+
+ /* If card was removed meanwhile */
+ if (!msb->req)
+ return;
+
+ /* process the request */
+ dbg_verbose("IO: processing new request");
+ blk_rq_map_sg(msb->queue, msb->req, sg);
+
+ lba = blk_rq_pos(msb->req);
+
+ sector_div(lba, msb->page_size / 512);
+ page = do_div(lba, msb->pages_in_block);
+
+ if (rq_data_dir(msb->req) == READ)
+ error = msb_do_read_request(msb, lba, page, sg,
+ blk_rq_bytes(msb->req), &len);
+ else
+ error = msb_do_write_request(msb, lba, page, sg,
+ blk_rq_bytes(msb->req), &len);
+
+ spin_lock_irqsave(&msb->q_lock, flags);
+
+ if (len)
+ if (!__blk_end_request(msb->req, 0, len))
+ msb->req = NULL;
+
+ if (error && msb->req) {
+ dbg_verbose("IO: ending one sector "
+ "of the request with error");
+ if (!__blk_end_request(msb->req, error, msb->page_size))
+ msb->req = NULL;
+ }
+
+ if (msb->req)
+ dbg_verbose("IO: request still pending");
+
+ spin_unlock_irqrestore(&msb->q_lock, flags);
+ }
+}
+
+static DEFINE_IDR(msb_disk_idr); /*set of used disk numbers */
+static DEFINE_MUTEX(msb_disk_lock); /* protects against races in open/release */
+
+static int msb_bd_open(struct block_device *bdev, fmode_t mode)
+{
+ struct gendisk *disk = bdev->bd_disk;
+ struct msb_data *msb = disk->private_data;
+
+ dbg_verbose("block device open");
+
+ mutex_lock(&msb_disk_lock);
+
+ if (msb && msb->card)
+ msb->usage_count++;
+
+ mutex_unlock(&msb_disk_lock);
+ return 0;
+}
+
+static void msb_data_clear(struct msb_data *msb)
+{
+ kfree(msb->boot_page);
+ kfree(msb->used_blocks_bitmap);
+ kfree(msb->lba_to_pba_table);
+ kfree(msb->cache);
+ msb->card = NULL;
+}
+
+static int msb_disk_release(struct gendisk *disk)
+{
+ struct msb_data *msb = disk->private_data;
+
+ dbg_verbose("block device release");
+ mutex_lock(&msb_disk_lock);
+
+ if (msb) {
+ if (msb->usage_count)
+ msb->usage_count--;
+
+ if (!msb->usage_count) {
+ kfree(msb);
+ disk->private_data = NULL;
+ idr_remove(&msb_disk_idr, msb->disk_id);
+ put_disk(disk);
+ }
+ }
+ mutex_unlock(&msb_disk_lock);
+ return 0;
+}
+
+static int msb_bd_release(struct gendisk *disk, fmode_t mode)
+{
+ return msb_disk_release(disk);
+}
+
+static int msb_bd_getgeo(struct block_device *bdev,
+ struct hd_geometry *geo)
+{
+ struct msb_data *msb = bdev->bd_disk->private_data;
+ *geo = msb->geometry;
+ return 0;
+}
+
+static int msb_prepare_req(struct request_queue *q, struct request *req)
+{
+ if (req->cmd_type != REQ_TYPE_FS &&
+ req->cmd_type != REQ_TYPE_BLOCK_PC) {
+ blk_dump_rq_flags(req, "MS unsupported request");
+ return BLKPREP_KILL;
+ }
+ req->cmd_flags |= REQ_DONTPREP;
+ return BLKPREP_OK;
+}
+
+static void msb_submit_req(struct request_queue *q)
+{
+ struct memstick_dev *card = q->queuedata;
+ struct msb_data *msb = memstick_get_drvdata(card);
+ struct request *req = NULL;
+
+ dbg_verbose("Submit request");
+
+ if (msb->card_dead) {
+ dbg("Refusing requests on removed card");
+
+ WARN_ON(!msb->io_queue_stopped);
+
+ while ((req = blk_fetch_request(q)) != NULL)
+ __blk_end_request_all(req, -ENODEV);
+ return;
+ }
+
+ if (msb->req)
+ return;
+
+ if (!msb->io_queue_stopped)
+ queue_work(msb->io_queue, &msb->io_work);
+}
+
+static int msb_check_card(struct memstick_dev *card)
+{
+ struct msb_data *msb = memstick_get_drvdata(card);
+ return (msb->card_dead == 0);
+}
+
+static void msb_stop(struct memstick_dev *card)
+{
+ struct msb_data *msb = memstick_get_drvdata(card);
+ unsigned long flags;
+
+ dbg("Stopping all msblock IO");
+
+ spin_lock_irqsave(&msb->q_lock, flags);
+ blk_stop_queue(msb->queue);
+ msb->io_queue_stopped = true;
+ spin_unlock_irqrestore(&msb->q_lock, flags);
+
+ del_timer_sync(&msb->cache_flush_timer);
+ flush_workqueue(msb->io_queue);
+
+ if (msb->req) {
+ spin_lock_irqsave(&msb->q_lock, flags);
+ blk_requeue_request(msb->queue, msb->req);
+ msb->req = NULL;
+ spin_unlock_irqrestore(&msb->q_lock, flags);
+ }
+
+}
+
+static void msb_start(struct memstick_dev *card)
+{
+ struct msb_data *msb = memstick_get_drvdata(card);
+ unsigned long flags;
+
+ dbg("Resuming IO from msblock");
+
+ msb_invalidate_reg_window(msb);
+
+ spin_lock_irqsave(&msb->q_lock, flags);
+ if (!msb->io_queue_stopped || msb->card_dead) {
+ spin_unlock_irqrestore(&msb->q_lock, flags);
+ return;
+ }
+ spin_unlock_irqrestore(&msb->q_lock, flags);
+
+ /* Kick cache flush anyway, its harmless */
+ msb->need_flush_cache = true;
+ msb->io_queue_stopped = false;
+
+ spin_lock_irqsave(&msb->q_lock, flags);
+ blk_start_queue(msb->queue);
+ spin_unlock_irqrestore(&msb->q_lock, flags);
+
+ queue_work(msb->io_queue, &msb->io_work);
+
+}
+
+static const struct block_device_operations msb_bdops = {
+ .open = msb_bd_open,
+ .release = msb_bd_release,
+ .getgeo = msb_bd_getgeo,
+ .owner = THIS_MODULE
+};
+
+/* Registers the block device */
+static int msb_init_disk(struct memstick_dev *card)
+{
+ struct msb_data *msb = memstick_get_drvdata(card);
+ struct memstick_host *host = card->host;
+ int rc;
+ u64 limit = BLK_BOUNCE_HIGH;
+ unsigned long capacity;
+
+ if (host->dev.dma_mask && *(host->dev.dma_mask))
+ limit = *(host->dev.dma_mask);
+
+ mutex_lock(&msb_disk_lock);
+ if (!idr_pre_get(&msb_disk_idr, GFP_KERNEL)) {
+ mutex_unlock(&msb_disk_lock);
+ return -ENOMEM;
+ }
+ rc = idr_get_new(&msb_disk_idr, card, &msb->disk_id);
+ mutex_unlock(&msb_disk_lock);
+
+ if (rc)
+ return rc;
+
+ msb->disk = alloc_disk(0);
+ if (!msb->disk) {
+ rc = -ENOMEM;
+ goto out_release_id;
+ }
+
+ msb->queue = blk_init_queue(msb_submit_req, &msb->q_lock);
+ if (!msb->queue) {
+ rc = -ENOMEM;
+ goto out_put_disk;
+ }
+
+ msb->queue->queuedata = card;
+ blk_queue_prep_rq(msb->queue, msb_prepare_req);
+
+ blk_queue_bounce_limit(msb->queue, limit);
+ blk_queue_max_hw_sectors(msb->queue, MS_BLOCK_MAX_PAGES);
+ blk_queue_max_segments(msb->queue, MS_BLOCK_MAX_SEGS);
+ blk_queue_max_segment_size(msb->queue,
+ MS_BLOCK_MAX_PAGES * msb->page_size);
+ blk_queue_logical_block_size(msb->queue, msb->page_size);
+
+ sprintf(msb->disk->disk_name, "msblk%d", msb->disk_id);
+ msb->disk->fops = &msb_bdops;
+ msb->disk->private_data = msb;
+ msb->disk->queue = msb->queue;
+ msb->disk->driverfs_dev = &card->dev;
+ msb->disk->flags |= GENHD_FL_EXT_DEVT;
+
+ capacity = msb->pages_in_block * msb->logical_block_count;
+ capacity *= (msb->page_size / 512);
+ set_capacity(msb->disk, capacity);
+ dbg("Set total disk size to %lu sectors", capacity);
+
+ msb->usage_count = 1;
+ msb->io_queue = alloc_ordered_workqueue("ms_block", WQ_MEM_RECLAIM);
+ INIT_WORK(&msb->io_work, msb_io_work);
+ sg_init_table(msb->prealloc_sg, MS_BLOCK_MAX_SEGS+1);
+
+ if (msb->read_only)
+ set_disk_ro(msb->disk, 1);
+
+ msb_start(card);
+ add_disk(msb->disk);
+ dbg("Disk added");
+ return 0;
+
+out_put_disk:
+ put_disk(msb->disk);
+out_release_id:
+ mutex_lock(&msb_disk_lock);
+ idr_remove(&msb_disk_idr, msb->disk_id);
+ mutex_unlock(&msb_disk_lock);
+ return rc;
+}
+
+static int msb_probe(struct memstick_dev *card)
+{
+ struct msb_data *msb;
+ int rc = 0;
+
+ msb = kzalloc(sizeof(struct msb_data), GFP_KERNEL);
+ if (!msb)
+ return -ENOMEM;
+ memstick_set_drvdata(card, msb);
+ msb->card = card;
+ spin_lock_init(&msb->q_lock);
+
+ rc = msb_init_card(card);
+ if (rc)
+ goto out_free;
+
+ rc = msb_init_disk(card);
+ if (!rc) {
+ card->check = msb_check_card;
+ card->stop = msb_stop;
+ card->start = msb_start;
+ return 0;
+ }
+out_free:
+ memstick_set_drvdata(card, NULL);
+ msb_data_clear(msb);
+ kfree(msb);
+ return rc;
+}
+
+static void msb_remove(struct memstick_dev *card)
+{
+ struct msb_data *msb = memstick_get_drvdata(card);
+ unsigned long flags;
+
+ if (!msb->io_queue_stopped)
+ msb_stop(card);
+
+ dbg("Removing the disk device");
+
+ /* Take care of unhandled + new requests from now on */
+ spin_lock_irqsave(&msb->q_lock, flags);
+ msb->card_dead = true;
+ blk_start_queue(msb->queue);
+ spin_unlock_irqrestore(&msb->q_lock, flags);
+
+ /* Remove the disk */
+ del_gendisk(msb->disk);
+ blk_cleanup_queue(msb->queue);
+ msb->queue = NULL;
+
+ mutex_lock(&msb_disk_lock);
+ msb_data_clear(msb);
+ mutex_unlock(&msb_disk_lock);
+
+ msb_disk_release(msb->disk);
+ memstick_set_drvdata(card, NULL);
+}
+
+#ifdef CONFIG_PM
+
+static int msb_suspend(struct memstick_dev *card, pm_message_t state)
+{
+ msb_stop(card);
+ return 0;
+}
+
+static int msb_resume(struct memstick_dev *card)
+{
+ struct msb_data *msb = memstick_get_drvdata(card);
+ struct msb_data *new_msb = NULL;
+ bool card_dead = true;
+
+#ifndef CONFIG_MEMSTICK_UNSAFE_RESUME
+ msb->card_dead = true;
+ return 0;
+#endif
+ mutex_lock(&card->host->lock);
+
+ new_msb = kzalloc(sizeof(struct msb_data), GFP_KERNEL);
+ if (!new_msb)
+ goto out;
+
+ new_msb->card = card;
+ memstick_set_drvdata(card, new_msb);
+ spin_lock_init(&new_msb->q_lock);
+ sg_init_table(msb->prealloc_sg, MS_BLOCK_MAX_SEGS+1);
+
+ if (msb_init_card(card))
+ goto out;
+
+ if (msb->block_size != new_msb->block_size)
+ goto out;
+
+ if (memcmp(msb->boot_page, new_msb->boot_page,
+ sizeof(struct ms_boot_page)))
+ goto out;
+
+ if (msb->logical_block_count != new_msb->logical_block_count ||
+ memcmp(msb->lba_to_pba_table, new_msb->lba_to_pba_table,
+ msb->logical_block_count))
+ goto out;
+
+ if (msb->block_count != new_msb->block_count ||
+ memcmp(msb->used_blocks_bitmap, new_msb->used_blocks_bitmap,
+ msb->block_count / 8))
+ goto out;
+
+ card_dead = false;
+out:
+ if (card_dead)
+ dbg("Card was removed/replaced during suspend");
+
+ msb->card_dead = card_dead;
+ memstick_set_drvdata(card, msb);
+
+ if (new_msb) {
+ msb_data_clear(new_msb);
+ kfree(new_msb);
+ }
+
+ msb_start(card);
+ mutex_unlock(&card->host->lock);
+ return 0;
+}
+#else
+
+#define msb_suspend NULL
+#define msb_resume NULL
+
+#endif /* CONFIG_PM */
+
+static struct memstick_device_id msb_id_tbl[] = {
+ {MEMSTICK_MATCH_ALL, MEMSTICK_TYPE_LEGACY, MEMSTICK_CATEGORY_STORAGE,
+ MEMSTICK_CLASS_FLASH},
+
+ {MEMSTICK_MATCH_ALL, MEMSTICK_TYPE_LEGACY, MEMSTICK_CATEGORY_STORAGE,
+ MEMSTICK_CLASS_ROM},
+
+ {MEMSTICK_MATCH_ALL, MEMSTICK_TYPE_LEGACY, MEMSTICK_CATEGORY_STORAGE,
+ MEMSTICK_CLASS_RO},
+
+ {MEMSTICK_MATCH_ALL, MEMSTICK_TYPE_LEGACY, MEMSTICK_CATEGORY_STORAGE,
+ MEMSTICK_CLASS_WP},
+
+ {MEMSTICK_MATCH_ALL, MEMSTICK_TYPE_DUO, MEMSTICK_CATEGORY_STORAGE_DUO,
+ MEMSTICK_CLASS_DUO},
+ {}
+};
+MODULE_DEVICE_TABLE(memstick, msb_id_tbl);
+
+
+static struct memstick_driver msb_driver = {
+ .driver = {
+ .name = DRIVER_NAME,
+ .owner = THIS_MODULE
+ },
+ .id_table = msb_id_tbl,
+ .probe = msb_probe,
+ .remove = msb_remove,
+ .suspend = msb_suspend,
+ .resume = msb_resume
+};
+
+static int major;
+
+static int __init msb_init(void)
+{
+ int rc = register_blkdev(0, DRIVER_NAME);
+
+ if (rc < 0) {
+ pr_err("failed to register major (error %d)\n", rc);
+ return rc;
+ }
+
+ major = rc;
+ rc = memstick_register_driver(&msb_driver);
+ if (rc) {
+ unregister_blkdev(major, DRIVER_NAME);
+ pr_err("failed to register memstick driver (error %d)\n", rc);
+ }
+
+ return rc;
+}
+
+static void __exit msb_exit(void)
+{
+ memstick_unregister_driver(&msb_driver);
+ unregister_blkdev(major, DRIVER_NAME);
+ idr_destroy(&msb_disk_idr);
+}
+
+module_init(msb_init);
+module_exit(msb_exit);
+
+module_param(cache_flush_timeout, int, S_IRUGO);
+MODULE_PARM_DESC(cache_flush_timeout,
+ "Cache flush timeout in msec (1000 default)");
+module_param(debug, int, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(debug, "Debug level (0-2)");
+
+module_param(verify_writes, bool, S_IRUGO);
+MODULE_PARM_DESC(verify_writes, "Read back and check all data that is written");
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Maxim Levitsky");
+MODULE_DESCRIPTION("Sony MemoryStick block device driver");
--- /dev/null
+/*
+ * ms_block.c - Sony MemoryStick (legacy) storage support
+
+ * Copyright (C) 2010 Maxim Levitsky <maximlevitsky@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Minor portions of the driver are copied from mspro_block.c which is
+ * Copyright (C) 2007 Alex Dubov <oakad@yahoo.com>
+ *
+ * Also ms structures were copied from old broken driver by same author
+ * These probably come from MS spec
+ *
+ */
+
+#ifndef MS_BLOCK_NEW_H
+#define MS_BLOCK_NEW_H
+
+#define MS_BLOCK_MAX_SEGS 32
+#define MS_BLOCK_MAX_PAGES ((2 << 16) - 1)
+
+#define MS_BLOCK_MAX_BOOT_ADDR 0x000c
+#define MS_BLOCK_BOOT_ID 0x0001
+#define MS_BLOCK_INVALID 0xffff
+#define MS_MAX_ZONES 16
+#define MS_BLOCKS_IN_ZONE 512
+
+#define MS_BLOCK_MAP_LINE_SZ 16
+#define MS_BLOCK_PART_SHIFT 3
+
+
+#define MEMSTICK_UNCORR_ERROR (MEMSTICK_STATUS1_UCFG | \
+ MEMSTICK_STATUS1_UCEX | MEMSTICK_STATUS1_UCDT)
+
+#define MEMSTICK_CORR_ERROR (MEMSTICK_STATUS1_FGER | MEMSTICK_STATUS1_EXER | \
+ MEMSTICK_STATUS1_DTER)
+
+#define MEMSTICK_INT_ERROR (MEMSTICK_INT_CMDNAK | MEMSTICK_INT_ERR)
+
+#define MEMSTICK_OVERWRITE_FLAG_NORMAL \
+ (MEMSTICK_OVERWRITE_PGST1 | \
+ MEMSTICK_OVERWRITE_PGST0 | \
+ MEMSTICK_OVERWRITE_BKST)
+
+#define MEMSTICK_OV_PG_NORMAL \
+ (MEMSTICK_OVERWRITE_PGST1 | MEMSTICK_OVERWRITE_PGST0)
+
+#define MEMSTICK_MANAGMENT_FLAG_NORMAL \
+ (MEMSTICK_MANAGEMENT_SYSFLG | \
+ MEMSTICK_MANAGEMENT_SCMS1 | \
+ MEMSTICK_MANAGEMENT_SCMS0) \
+
+struct ms_boot_header {
+ unsigned short block_id;
+ unsigned short format_reserved;
+ unsigned char reserved0[184];
+ unsigned char data_entry;
+ unsigned char reserved1[179];
+} __packed;
+
+
+struct ms_system_item {
+ unsigned int start_addr;
+ unsigned int data_size;
+ unsigned char data_type_id;
+ unsigned char reserved[3];
+} __packed;
+
+struct ms_system_entry {
+ struct ms_system_item disabled_block;
+ struct ms_system_item cis_idi;
+ unsigned char reserved[24];
+} __packed;
+
+struct ms_boot_attr_info {
+ unsigned char memorystick_class;
+ unsigned char format_unique_value1;
+ unsigned short block_size;
+ unsigned short number_of_blocks;
+ unsigned short number_of_effective_blocks;
+ unsigned short page_size;
+ unsigned char extra_data_size;
+ unsigned char format_unique_value2;
+ unsigned char assembly_time[8];
+ unsigned char format_unique_value3;
+ unsigned char serial_number[3];
+ unsigned char assembly_manufacturer_code;
+ unsigned char assembly_model_code[3];
+ unsigned short memory_manufacturer_code;
+ unsigned short memory_device_code;
+ unsigned short implemented_capacity;
+ unsigned char format_unique_value4[2];
+ unsigned char vcc;
+ unsigned char vpp;
+ unsigned short controller_number;
+ unsigned short controller_function;
+ unsigned char reserved0[9];
+ unsigned char transfer_supporting;
+ unsigned short format_unique_value5;
+ unsigned char format_type;
+ unsigned char memorystick_application;
+ unsigned char device_type;
+ unsigned char reserved1[22];
+ unsigned char format_uniqure_value6[2];
+ unsigned char reserved2[15];
+} __packed;
+
+struct ms_cis_idi {
+ unsigned short general_config;
+ unsigned short logical_cylinders;
+ unsigned short reserved0;
+ unsigned short logical_heads;
+ unsigned short track_size;
+ unsigned short page_size;
+ unsigned short pages_per_track;
+ unsigned short msw;
+ unsigned short lsw;
+ unsigned short reserved1;
+ unsigned char serial_number[20];
+ unsigned short buffer_type;
+ unsigned short buffer_size_increments;
+ unsigned short long_command_ecc;
+ unsigned char firmware_version[28];
+ unsigned char model_name[18];
+ unsigned short reserved2[5];
+ unsigned short pio_mode_number;
+ unsigned short dma_mode_number;
+ unsigned short field_validity;
+ unsigned short current_logical_cylinders;
+ unsigned short current_logical_heads;
+ unsigned short current_pages_per_track;
+ unsigned int current_page_capacity;
+ unsigned short mutiple_page_setting;
+ unsigned int addressable_pages;
+ unsigned short single_word_dma;
+ unsigned short multi_word_dma;
+ unsigned char reserved3[128];
+} __packed;
+
+
+struct ms_boot_page {
+ struct ms_boot_header header;
+ struct ms_system_entry entry;
+ struct ms_boot_attr_info attr;
+} __packed;
+
+struct msb_data {
+ unsigned int usage_count;
+ struct memstick_dev *card;
+ struct gendisk *disk;
+ struct request_queue *queue;
+ spinlock_t q_lock;
+ struct hd_geometry geometry;
+ struct attribute_group attr_group;
+ struct request *req;
+ int caps;
+ int disk_id;
+
+ /* IO */
+ struct workqueue_struct *io_queue;
+ bool io_queue_stopped;
+ struct work_struct io_work;
+ struct scatterlist prealloc_sg[MS_BLOCK_MAX_SEGS+1];
+ bool card_dead;
+
+ /* Media properties */
+ struct ms_boot_page *boot_page;
+ u16 boot_block_locations[2];
+ int boot_block_count;
+
+ bool read_only;
+ unsigned short page_size;
+ int block_size;
+ int pages_in_block;
+ int zone_count;
+ int block_count;
+ int logical_block_count;
+
+ /* FTL tables */
+ unsigned long *used_blocks_bitmap;
+ unsigned long *erased_blocks_bitmap;
+ u16 *lba_to_pba_table;
+ int free_block_count[MS_MAX_ZONES];
+ bool ftl_initialized;
+
+ /* Cache */
+ unsigned char *cache;
+ unsigned long valid_cache_bitmap;
+ int cache_block_lba;
+ bool need_flush_cache;
+ struct timer_list cache_flush_timer;
+
+ /* Preallocated buffers */
+ unsigned char *block_buffer;
+ struct scatterlist sg[MS_BLOCK_MAX_SEGS+1];
+
+
+ /* handler's local data */
+ struct ms_register_addr reg_addr;
+ bool addr_valid;
+
+ u8 command_value;
+ bool command_need_oob;
+ struct scatterlist *current_sg;
+ int current_sg_offset;
+
+ struct ms_register regs;
+ int current_page;
+
+ int state;
+ int exit_error;
+ bool int_polling;
+ unsigned long int_timeout;
+
+};
+
+enum msb_readpage_states {
+ MSB_RP_SEND_BLOCK_ADDRESS = 0,
+ MSB_RP_SEND_READ_COMMAND,
+
+ MSB_RP_SEND_INT_REQ,
+ MSB_RP_RECEIVE_INT_REQ_RESULT,
+
+ MSB_RP_SEND_READ_STATUS_REG,
+ MSB_RP_RECIVE_STATUS_REG,
+
+ MSB_RP_SEND_OOB_READ,
+ MSB_RP_RECEIVE_OOB_READ,
+
+ MSB_RP_SEND_READ_DATA,
+ MSB_RP_RECEIVE_READ_DATA,
+};
+
+enum msb_write_block_states {
+ MSB_WB_SEND_WRITE_PARAMS = 0,
+ MSB_WB_SEND_WRITE_OOB,
+ MSB_WB_SEND_WRITE_COMMAND,
+
+ MSB_WB_SEND_INT_REQ,
+ MSB_WB_RECEIVE_INT_REQ,
+
+ MSB_WB_SEND_WRITE_DATA,
+ MSB_WB_RECEIVE_WRITE_CONFIRMATION,
+};
+
+enum msb_send_command_states {
+ MSB_SC_SEND_WRITE_PARAMS,
+ MSB_SC_SEND_WRITE_OOB,
+ MSB_SC_SEND_COMMAND,
+
+ MSB_SC_SEND_INT_REQ,
+ MSB_SC_RECEIVE_INT_REQ,
+
+};
+
+enum msb_reset_states {
+ MSB_RS_SEND,
+ MSB_RS_CONFIRM,
+};
+
+enum msb_par_switch_states {
+ MSB_PS_SEND_SWITCH_COMMAND,
+ MSB_PS_SWICH_HOST,
+ MSB_PS_CONFIRM,
+};
+
+struct chs_entry {
+ unsigned long size;
+ unsigned char sec;
+ unsigned short cyl;
+ unsigned char head;
+};
+
+static int msb_reset(struct msb_data *msb, bool full);
+
+static int h_msb_default_bad(struct memstick_dev *card,
+ struct memstick_request **mrq);
+
+#define DRIVER_NAME "ms_block"
+
+#define __dbg(level, format, ...) \
+ do { \
+ if (debug >= level) \
+ pr_err(format "\n", ## __VA_ARGS__); \
+ } while (0)
+
+
+#define dbg(format, ...) __dbg(1, format, ## __VA_ARGS__)
+#define dbg_verbose(format, ...) __dbg(2, format, ## __VA_ARGS__)
+
+#endif
kfree(ibr);
}
-static void iblock_bio_destructor(struct bio *bio)
-{
- struct se_cmd *cmd = bio->bi_private;
- struct iblock_dev *ib_dev = cmd->se_dev->dev_ptr;
-
- bio_free(bio, ib_dev->ibd_bio_set);
-}
-
static struct bio *
iblock_get_bio(struct se_cmd *cmd, sector_t lba, u32 sg_num)
{
bio->bi_bdev = ib_dev->ibd_bd;
bio->bi_private = cmd;
- bio->bi_destructor = iblock_bio_destructor;
bio->bi_end_io = &iblock_bio_done;
bio->bi_sector = lba;
return bio;
}
/**
- * bio_integrity_alloc_bioset - Allocate integrity payload and attach it to bio
+ * bio_integrity_alloc - Allocate integrity payload and attach it to bio
* @bio: bio to attach integrity metadata to
* @gfp_mask: Memory allocation mask
* @nr_vecs: Number of integrity metadata scatter-gather elements
- * @bs: bio_set to allocate from
*
* Description: This function prepares a bio for attaching integrity
* metadata. nr_vecs specifies the maximum number of pages containing
* integrity metadata that can be attached.
*/
-struct bio_integrity_payload *bio_integrity_alloc_bioset(struct bio *bio,
- gfp_t gfp_mask,
- unsigned int nr_vecs,
- struct bio_set *bs)
+struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
+ gfp_t gfp_mask,
+ unsigned int nr_vecs)
{
struct bio_integrity_payload *bip;
unsigned int idx = vecs_to_idx(nr_vecs);
+ struct bio_set *bs = bio->bi_pool;
+
+ if (!bs)
+ bs = fs_bio_set;
BUG_ON(bio == NULL);
bip = NULL;
return bip;
}
-EXPORT_SYMBOL(bio_integrity_alloc_bioset);
-
-/**
- * bio_integrity_alloc - Allocate integrity payload and attach it to bio
- * @bio: bio to attach integrity metadata to
- * @gfp_mask: Memory allocation mask
- * @nr_vecs: Number of integrity metadata scatter-gather elements
- *
- * Description: This function prepares a bio for attaching integrity
- * metadata. nr_vecs specifies the maximum number of pages containing
- * integrity metadata that can be attached.
- */
-struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
- gfp_t gfp_mask,
- unsigned int nr_vecs)
-{
- return bio_integrity_alloc_bioset(bio, gfp_mask, nr_vecs, fs_bio_set);
-}
EXPORT_SYMBOL(bio_integrity_alloc);
/**
* bio_integrity_free - Free bio integrity payload
* @bio: bio containing bip to be freed
- * @bs: bio_set this bio was allocated from
*
* Description: Used to free the integrity portion of a bio. Usually
* called from bio_free().
*/
-void bio_integrity_free(struct bio *bio, struct bio_set *bs)
+void bio_integrity_free(struct bio *bio)
{
struct bio_integrity_payload *bip = bio->bi_integrity;
+ struct bio_set *bs = bio->bi_pool;
+
+ if (!bs)
+ bs = fs_bio_set;
BUG_ON(bip == NULL);
* @bio: New bio
* @bio_src: Original bio
* @gfp_mask: Memory allocation mask
- * @bs: bio_set to allocate bip from
*
* Description: Called to allocate a bip when cloning a bio
*/
int bio_integrity_clone(struct bio *bio, struct bio *bio_src,
- gfp_t gfp_mask, struct bio_set *bs)
+ gfp_t gfp_mask)
{
struct bio_integrity_payload *bip_src = bio_src->bi_integrity;
struct bio_integrity_payload *bip;
BUG_ON(bip_src == NULL);
- bip = bio_integrity_alloc_bioset(bio, gfp_mask, bip_src->bip_vcnt, bs);
+ bip = bio_integrity_alloc(bio, gfp_mask, bip_src->bip_vcnt);
if (bip == NULL)
return -EIO;
* IO code that does not need private memory pools.
*/
struct bio_set *fs_bio_set;
+EXPORT_SYMBOL(fs_bio_set);
/*
* Our slab pool management
return bvl;
}
-void bio_free(struct bio *bio, struct bio_set *bs)
+static void __bio_free(struct bio *bio)
{
+ bio_disassociate_task(bio);
+
+ if (bio_integrity(bio))
+ bio_integrity_free(bio);
+}
+
+static void bio_free(struct bio *bio)
+{
+ struct bio_set *bs = bio->bi_pool;
void *p;
- if (bio_has_allocated_vec(bio))
- bvec_free_bs(bs, bio->bi_io_vec, BIO_POOL_IDX(bio));
+ __bio_free(bio);
- if (bio_integrity(bio))
- bio_integrity_free(bio, bs);
+ if (bs) {
+ if (bio_has_allocated_vec(bio))
+ bvec_free_bs(bs, bio->bi_io_vec, BIO_POOL_IDX(bio));
- /*
- * If we have front padding, adjust the bio pointer before freeing
- */
- p = bio;
- if (bs->front_pad)
+ /*
+ * If we have front padding, adjust the bio pointer before freeing
+ */
+ p = bio;
p -= bs->front_pad;
- mempool_free(p, bs->bio_pool);
+ mempool_free(p, bs->bio_pool);
+ } else {
+ /* Bio was allocated by bio_kmalloc() */
+ kfree(bio);
+ }
}
-EXPORT_SYMBOL(bio_free);
void bio_init(struct bio *bio)
{
}
EXPORT_SYMBOL(bio_init);
+/**
+ * bio_reset - reinitialize a bio
+ * @bio: bio to reset
+ *
+ * Description:
+ * After calling bio_reset(), @bio will be in the same state as a freshly
+ * allocated bio returned bio bio_alloc_bioset() - the only fields that are
+ * preserved are the ones that are initialized by bio_alloc_bioset(). See
+ * comment in struct bio.
+ */
+void bio_reset(struct bio *bio)
+{
+ unsigned long flags = bio->bi_flags & (~0UL << BIO_RESET_BITS);
+
+ __bio_free(bio);
+
+ memset(bio, 0, BIO_RESET_BYTES);
+ bio->bi_flags = flags|(1 << BIO_UPTODATE);
+}
+EXPORT_SYMBOL(bio_reset);
+
/**
* bio_alloc_bioset - allocate a bio for I/O
* @gfp_mask: the GFP_ mask given to the slab allocator
* @bs: the bio_set to allocate from.
*
* Description:
- * bio_alloc_bioset will try its own mempool to satisfy the allocation.
- * If %__GFP_WAIT is set then we will block on the internal pool waiting
- * for a &struct bio to become free.
+ * If @bs is NULL, uses kmalloc() to allocate the bio; else the allocation is
+ * backed by the @bs's mempool.
*
- * Note that the caller must set ->bi_destructor on successful return
- * of a bio, to do the appropriate freeing of the bio once the reference
- * count drops to zero.
- **/
+ * When @bs is not NULL, if %__GFP_WAIT is set then bio_alloc will always be
+ * able to allocate a bio. This is due to the mempool guarantees. To make this
+ * work, callers must never allocate more than 1 bio at a time from this pool.
+ * Callers that need to allocate more than 1 bio must always submit the
+ * previously allocated bio for IO before attempting to allocate a new one.
+ * Failure to do so can cause deadlocks under memory pressure.
+ *
+ * RETURNS:
+ * Pointer to new bio on success, NULL on failure.
+ */
struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
{
+ unsigned front_pad;
+ unsigned inline_vecs;
unsigned long idx = BIO_POOL_NONE;
struct bio_vec *bvl = NULL;
struct bio *bio;
void *p;
- p = mempool_alloc(bs->bio_pool, gfp_mask);
+ if (!bs) {
+ if (nr_iovecs > UIO_MAXIOV)
+ return NULL;
+
+ p = kmalloc(sizeof(struct bio) +
+ nr_iovecs * sizeof(struct bio_vec),
+ gfp_mask);
+ front_pad = 0;
+ inline_vecs = nr_iovecs;
+ } else {
+ p = mempool_alloc(bs->bio_pool, gfp_mask);
+ front_pad = bs->front_pad;
+ inline_vecs = BIO_INLINE_VECS;
+ }
+
if (unlikely(!p))
return NULL;
- bio = p + bs->front_pad;
+ bio = p + front_pad;
bio_init(bio);
- if (unlikely(!nr_iovecs))
- goto out_set;
-
- if (nr_iovecs <= BIO_INLINE_VECS) {
- bvl = bio->bi_inline_vecs;
- nr_iovecs = BIO_INLINE_VECS;
- } else {
+ if (nr_iovecs > inline_vecs) {
bvl = bvec_alloc_bs(gfp_mask, nr_iovecs, &idx, bs);
if (unlikely(!bvl))
goto err_free;
-
- nr_iovecs = bvec_nr_vecs(idx);
+ } else if (nr_iovecs) {
+ bvl = bio->bi_inline_vecs;
}
-out_set:
+
+ bio->bi_pool = bs;
bio->bi_flags |= idx << BIO_POOL_OFFSET;
bio->bi_max_vecs = nr_iovecs;
bio->bi_io_vec = bvl;
}
EXPORT_SYMBOL(bio_alloc_bioset);
-static void bio_fs_destructor(struct bio *bio)
-{
- bio_free(bio, fs_bio_set);
-}
-
-/**
- * bio_alloc - allocate a new bio, memory pool backed
- * @gfp_mask: allocation mask to use
- * @nr_iovecs: number of iovecs
- *
- * bio_alloc will allocate a bio and associated bio_vec array that can hold
- * at least @nr_iovecs entries. Allocations will be done from the
- * fs_bio_set. Also see @bio_alloc_bioset and @bio_kmalloc.
- *
- * If %__GFP_WAIT is set, then bio_alloc will always be able to allocate
- * a bio. This is due to the mempool guarantees. To make this work, callers
- * must never allocate more than 1 bio at a time from this pool. Callers
- * that need to allocate more than 1 bio must always submit the previously
- * allocated bio for IO before attempting to allocate a new one. Failure to
- * do so can cause livelocks under memory pressure.
- *
- * RETURNS:
- * Pointer to new bio on success, NULL on failure.
- */
-struct bio *bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs)
-{
- struct bio *bio = bio_alloc_bioset(gfp_mask, nr_iovecs, fs_bio_set);
-
- if (bio)
- bio->bi_destructor = bio_fs_destructor;
-
- return bio;
-}
-EXPORT_SYMBOL(bio_alloc);
-
-static void bio_kmalloc_destructor(struct bio *bio)
-{
- if (bio_integrity(bio))
- bio_integrity_free(bio, fs_bio_set);
- kfree(bio);
-}
-
-/**
- * bio_kmalloc - allocate a bio for I/O using kmalloc()
- * @gfp_mask: the GFP_ mask given to the slab allocator
- * @nr_iovecs: number of iovecs to pre-allocate
- *
- * Description:
- * Allocate a new bio with @nr_iovecs bvecs. If @gfp_mask contains
- * %__GFP_WAIT, the allocation is guaranteed to succeed.
- *
- **/
-struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned int nr_iovecs)
-{
- struct bio *bio;
-
- if (nr_iovecs > UIO_MAXIOV)
- return NULL;
-
- bio = kmalloc(sizeof(struct bio) + nr_iovecs * sizeof(struct bio_vec),
- gfp_mask);
- if (unlikely(!bio))
- return NULL;
-
- bio_init(bio);
- bio->bi_flags |= BIO_POOL_NONE << BIO_POOL_OFFSET;
- bio->bi_max_vecs = nr_iovecs;
- bio->bi_io_vec = bio->bi_inline_vecs;
- bio->bi_destructor = bio_kmalloc_destructor;
-
- return bio;
-}
-EXPORT_SYMBOL(bio_kmalloc);
-
void zero_fill_bio(struct bio *bio)
{
unsigned long flags;
/*
* last put frees it
*/
- if (atomic_dec_and_test(&bio->bi_cnt)) {
- bio_disassociate_task(bio);
- bio->bi_next = NULL;
- bio->bi_destructor(bio);
- }
+ if (atomic_dec_and_test(&bio->bi_cnt))
+ bio_free(bio);
}
EXPORT_SYMBOL(bio_put);
EXPORT_SYMBOL(__bio_clone);
/**
- * bio_clone - clone a bio
+ * bio_clone_bioset - clone a bio
* @bio: bio to clone
* @gfp_mask: allocation priority
+ * @bs: bio_set to allocate from
*
* Like __bio_clone, only also allocates the returned bio
*/
-struct bio *bio_clone(struct bio *bio, gfp_t gfp_mask)
+struct bio *bio_clone_bioset(struct bio *bio, gfp_t gfp_mask,
+ struct bio_set *bs)
{
- struct bio *b = bio_alloc_bioset(gfp_mask, bio->bi_max_vecs, fs_bio_set);
+ struct bio *b;
+ b = bio_alloc_bioset(gfp_mask, bio->bi_max_vecs, bs);
if (!b)
return NULL;
- b->bi_destructor = bio_fs_destructor;
__bio_clone(b, bio);
if (bio_integrity(bio)) {
int ret;
- ret = bio_integrity_clone(b, bio, gfp_mask, fs_bio_set);
+ ret = bio_integrity_clone(b, bio, gfp_mask);
if (ret < 0) {
bio_put(b);
return b;
}
-EXPORT_SYMBOL(bio_clone);
+EXPORT_SYMBOL(bio_clone_bioset);
/**
* bio_get_nr_vecs - return approx number of vecs
trace_block_split(bdev_get_queue(bi->bi_bdev), bi,
bi->bi_sector + first_sectors);
- BUG_ON(bi->bi_vcnt != 1);
+ BUG_ON(bi->bi_vcnt != 1 && bi->bi_vcnt != 0);
BUG_ON(bi->bi_idx != 0);
atomic_set(&bp->cnt, 3);
bp->error = 0;
bp->bio2.bi_size -= first_sectors << 9;
bp->bio1.bi_size = first_sectors << 9;
- bp->bv1 = bi->bi_io_vec[0];
- bp->bv2 = bi->bi_io_vec[0];
- bp->bv2.bv_offset += first_sectors << 9;
- bp->bv2.bv_len -= first_sectors << 9;
- bp->bv1.bv_len = first_sectors << 9;
+ if (bi->bi_vcnt != 0) {
+ bp->bv1 = bi->bi_io_vec[0];
+ bp->bv2 = bi->bi_io_vec[0];
+
+ if (bio_is_rw(bi)) {
+ bp->bv2.bv_offset += first_sectors << 9;
+ bp->bv2.bv_len -= first_sectors << 9;
+ bp->bv1.bv_len = first_sectors << 9;
+ }
- bp->bio1.bi_io_vec = &bp->bv1;
- bp->bio2.bi_io_vec = &bp->bv2;
+ bp->bio1.bi_io_vec = &bp->bv1;
+ bp->bio2.bi_io_vec = &bp->bv2;
- bp->bio1.bi_max_vecs = 1;
- bp->bio2.bi_max_vecs = 1;
+ bp->bio1.bi_max_vecs = 1;
+ bp->bio2.bi_max_vecs = 1;
+ }
bp->bio1.bi_end_io = bio_pair_end_1;
bp->bio2.bi_end_io = bio_pair_end_2;
int set_blocksize(struct block_device *bdev, int size)
{
+ struct address_space *mapping;
+
/* Size must be a power of two, and between 512 and PAGE_SIZE */
if (size > PAGE_SIZE || size < 512 || !is_power_of_2(size))
return -EINVAL;
if (size < bdev_logical_block_size(bdev))
return -EINVAL;
+ /* Prevent starting I/O or mapping the device */
+ percpu_down_write(&bdev->bd_block_size_semaphore);
+
+ /* Check that the block device is not memory mapped */
+ mapping = bdev->bd_inode->i_mapping;
+ mutex_lock(&mapping->i_mmap_mutex);
+ if (!prio_tree_empty(&mapping->i_mmap) ||
+ !list_empty(&mapping->i_mmap_nonlinear)) {
+ mutex_unlock(&mapping->i_mmap_mutex);
+ percpu_up_write(&bdev->bd_block_size_semaphore);
+ return -EBUSY;
+ }
+ mutex_unlock(&mapping->i_mmap_mutex);
+
/* Don't change the size if it is same as current */
if (bdev->bd_block_size != size) {
sync_blockdev(bdev);
bdev->bd_inode->i_blkbits = blksize_bits(size);
kill_bdev(bdev);
}
+
+ percpu_up_write(&bdev->bd_block_size_semaphore);
+
return 0;
}
struct bdev_inode *ei = kmem_cache_alloc(bdev_cachep, GFP_KERNEL);
if (!ei)
return NULL;
+
+ if (unlikely(percpu_init_rwsem(&ei->bdev.bd_block_size_semaphore))) {
+ kmem_cache_free(bdev_cachep, ei);
+ return NULL;
+ }
+
return &ei->vfs_inode;
}
struct inode *inode = container_of(head, struct inode, i_rcu);
struct bdev_inode *bdi = BDEV_I(inode);
+ percpu_free_rwsem(&bdi->bdev.bd_block_size_semaphore);
+
kmem_cache_free(bdev_cachep, bdi);
}
return blkdev_ioctl(bdev, mode, cmd, arg);
}
+ssize_t blkdev_aio_read(struct kiocb *iocb, const struct iovec *iov,
+ unsigned long nr_segs, loff_t pos)
+{
+ ssize_t ret;
+ struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host);
+
+ percpu_down_read(&bdev->bd_block_size_semaphore);
+
+ ret = generic_file_aio_read(iocb, iov, nr_segs, pos);
+
+ percpu_up_read(&bdev->bd_block_size_semaphore);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(blkdev_aio_read);
+
/*
* Write data to the block device. Only intended for the block device itself
* and the raw driver which basically is a fake block device.
unsigned long nr_segs, loff_t pos)
{
struct file *file = iocb->ki_filp;
+ struct block_device *bdev = I_BDEV(file->f_mapping->host);
struct blk_plug plug;
ssize_t ret;
BUG_ON(iocb->ki_pos != pos);
blk_start_plug(&plug);
+
+ percpu_down_read(&bdev->bd_block_size_semaphore);
+
ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
if (ret > 0 || ret == -EIOCBQUEUED) {
ssize_t err;
if (err < 0 && ret > 0)
ret = err;
}
+
+ percpu_up_read(&bdev->bd_block_size_semaphore);
+
blk_finish_plug(&plug);
+
return ret;
}
EXPORT_SYMBOL_GPL(blkdev_aio_write);
+static int blkdev_mmap(struct file *file, struct vm_area_struct *vma)
+{
+ int ret;
+ struct block_device *bdev = I_BDEV(file->f_mapping->host);
+
+ percpu_down_read(&bdev->bd_block_size_semaphore);
+
+ ret = generic_file_mmap(file, vma);
+
+ percpu_up_read(&bdev->bd_block_size_semaphore);
+
+ return ret;
+}
+
/*
* Try to release a page associated with block device when the system
* is under memory pressure.
.llseek = block_llseek,
.read = do_sync_read,
.write = do_sync_write,
- .aio_read = generic_file_aio_read,
+ .aio_read = blkdev_aio_read,
.aio_write = blkdev_aio_write,
- .mmap = generic_file_mmap,
+ .mmap = blkdev_mmap,
.fsync = blkdev_fsync,
.unlocked_ioctl = block_ioctl,
#ifdef CONFIG_COMPAT
struct bio *bio;
if (per_dev != master_dev) {
- bio = bio_kmalloc(GFP_KERNEL,
- master_dev->bio->bi_max_vecs);
+ bio = bio_clone_kmalloc(master_dev->bio,
+ GFP_KERNEL);
if (unlikely(!bio)) {
ORE_DBGMSG(
"Failed to allocate BIO size=%u\n",
goto out;
}
- __bio_clone(bio, master_dev->bio);
bio->bi_bdev = NULL;
bio->bi_next = NULL;
per_dev->offset = master_dev->offset;
extern struct bio_set *bioset_create(unsigned int, unsigned int);
extern void bioset_free(struct bio_set *);
-extern struct bio *bio_alloc(gfp_t, unsigned int);
-extern struct bio *bio_kmalloc(gfp_t, unsigned int);
extern struct bio *bio_alloc_bioset(gfp_t, int, struct bio_set *);
extern void bio_put(struct bio *);
-extern void bio_free(struct bio *, struct bio_set *);
+
+extern void __bio_clone(struct bio *, struct bio *);
+extern struct bio *bio_clone_bioset(struct bio *, gfp_t, struct bio_set *bs);
+
+extern struct bio_set *fs_bio_set;
+
+static inline struct bio *bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs)
+{
+ return bio_alloc_bioset(gfp_mask, nr_iovecs, fs_bio_set);
+}
+
+static inline struct bio *bio_clone(struct bio *bio, gfp_t gfp_mask)
+{
+ return bio_clone_bioset(bio, gfp_mask, fs_bio_set);
+}
+
+static inline struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned int nr_iovecs)
+{
+ return bio_alloc_bioset(gfp_mask, nr_iovecs, NULL);
+}
+
+static inline struct bio *bio_clone_kmalloc(struct bio *bio, gfp_t gfp_mask)
+{
+ return bio_clone_bioset(bio, gfp_mask, NULL);
+
+}
extern void bio_endio(struct bio *, int);
struct request_queue;
extern int bio_phys_segments(struct request_queue *, struct bio *);
-extern void __bio_clone(struct bio *, struct bio *);
-extern struct bio *bio_clone(struct bio *, gfp_t);
-
extern void bio_init(struct bio *);
+extern void bio_reset(struct bio *);
extern int bio_add_page(struct bio *, struct page *, unsigned int,unsigned int);
extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *,
struct kmem_cache *slab;
};
-extern struct bio_set *fs_bio_set;
-
/*
* a small number of entries is fine, not going to be performance critical.
* basically we just need to survive
/*
* Check whether this bio carries any data or not. A NULL bio is allowed.
*/
-static inline int bio_has_data(struct bio *bio)
+static inline bool bio_has_data(struct bio *bio)
{
- return bio && bio->bi_io_vec != NULL;
+ if (bio && bio->bi_vcnt)
+ return true;
+
+ return false;
+}
+
+static inline bool bio_is_rw(struct bio *bio)
+{
+ if (!bio_has_data(bio))
+ return false;
+
+ if (bio->bi_rw & REQ_WRITE_SAME)
+ return false;
+
+ return true;
+}
+
+static inline bool bio_mergeable(struct bio *bio)
+{
+ if (bio->bi_rw & REQ_NOMERGE_FLAGS)
+ return false;
+
+ return true;
}
/*
#define bio_integrity(bio) (bio->bi_integrity != NULL)
-extern struct bio_integrity_payload *bio_integrity_alloc_bioset(struct bio *, gfp_t, unsigned int, struct bio_set *);
extern struct bio_integrity_payload *bio_integrity_alloc(struct bio *, gfp_t, unsigned int);
-extern void bio_integrity_free(struct bio *, struct bio_set *);
+extern void bio_integrity_free(struct bio *);
extern int bio_integrity_add_page(struct bio *, struct page *, unsigned int, unsigned int);
extern int bio_integrity_enabled(struct bio *bio);
extern int bio_integrity_set_tag(struct bio *, void *, unsigned int);
extern void bio_integrity_advance(struct bio *, unsigned int);
extern void bio_integrity_trim(struct bio *, unsigned int, unsigned int);
extern void bio_integrity_split(struct bio *, struct bio_pair *, int);
-extern int bio_integrity_clone(struct bio *, struct bio *, gfp_t, struct bio_set *);
+extern int bio_integrity_clone(struct bio *, struct bio *, gfp_t);
extern int bioset_integrity_create(struct bio_set *, int);
extern void bioset_integrity_free(struct bio_set *);
extern void bio_integrity_init(void);
return 0;
}
-static inline void bio_integrity_free(struct bio *bio, struct bio_set *bs)
+static inline void bio_integrity_free(struct bio *bio)
{
return;
}
static inline int bio_integrity_clone(struct bio *bio, struct bio *bio_src,
- gfp_t gfp_mask, struct bio_set *bs)
+ gfp_t gfp_mask)
{
return 0;
}
unsigned int bi_seg_front_size;
unsigned int bi_seg_back_size;
- unsigned int bi_max_vecs; /* max bvl_vecs we can hold */
-
- atomic_t bi_cnt; /* pin count */
-
- struct bio_vec *bi_io_vec; /* the actual vec list */
-
bio_end_io_t *bi_end_io;
void *bi_private;
struct bio_integrity_payload *bi_integrity; /* data integrity */
#endif
- bio_destructor_t *bi_destructor; /* destructor */
+ /*
+ * Everything starting with bi_max_vecs will be preserved by bio_reset()
+ */
+
+ unsigned int bi_max_vecs; /* max bvl_vecs we can hold */
+
+ atomic_t bi_cnt; /* pin count */
+
+ struct bio_vec *bi_io_vec; /* the actual vec list */
+
+ struct bio_set *bi_pool;
/*
* We can inline a number of vecs at the end of the bio, to avoid
struct bio_vec bi_inline_vecs[0];
};
+#define BIO_RESET_BYTES offsetof(struct bio, bi_max_vecs)
+
/*
* bio flags
*/
#define BIO_FS_INTEGRITY 9 /* fs owns integrity data, not block layer */
#define BIO_QUIET 10 /* Make BIO Quiet */
#define BIO_MAPPED_INTEGRITY 11/* integrity metadata has been remapped */
+
+/*
+ * Flags starting here get preserved by bio_reset() - this includes
+ * BIO_POOL_IDX()
+ */
+#define BIO_RESET_BITS 12
+
#define bio_flagged(bio, flag) ((bio)->bi_flags & (1 << (flag)))
/*
__REQ_PRIO, /* boost priority in cfq */
__REQ_DISCARD, /* request to discard sectors */
__REQ_SECURE, /* secure discard (used with __REQ_DISCARD) */
+ __REQ_WRITE_SAME, /* write same block many times */
__REQ_NOIDLE, /* don't anticipate more IO after this one */
__REQ_FUA, /* forced unit access */
#define REQ_META (1 << __REQ_META)
#define REQ_PRIO (1 << __REQ_PRIO)
#define REQ_DISCARD (1 << __REQ_DISCARD)
+#define REQ_WRITE_SAME (1 << __REQ_WRITE_SAME)
#define REQ_NOIDLE (1 << __REQ_NOIDLE)
#define REQ_FAILFAST_MASK \
(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER)
#define REQ_COMMON_MASK \
(REQ_WRITE | REQ_FAILFAST_MASK | REQ_SYNC | REQ_META | REQ_PRIO | \
- REQ_DISCARD | REQ_NOIDLE | REQ_FLUSH | REQ_FUA | REQ_SECURE)
+ REQ_DISCARD | REQ_WRITE_SAME | REQ_NOIDLE | REQ_FLUSH | REQ_FUA | \
+ REQ_SECURE)
#define REQ_CLONE_MASK REQ_COMMON_MASK
+/* This mask is used for both bio and request merge checking */
+#define REQ_NOMERGE_FLAGS \
+ (REQ_NOMERGE | REQ_STARTED | REQ_SOFTBARRIER | REQ_FLUSH | REQ_FUA)
+
#define REQ_RAHEAD (1 << __REQ_RAHEAD)
#define REQ_THROTTLED (1 << __REQ_THROTTLED)
unsigned int io_min;
unsigned int io_opt;
unsigned int max_discard_sectors;
+ unsigned int max_write_same_sectors;
unsigned int discard_granularity;
unsigned int discard_alignment;
#define blk_account_rq(rq) \
(((rq)->cmd_flags & REQ_STARTED) && \
- ((rq)->cmd_type == REQ_TYPE_FS || \
- ((rq)->cmd_flags & REQ_DISCARD)))
+ ((rq)->cmd_type == REQ_TYPE_FS))
#define blk_pm_request(rq) \
((rq)->cmd_type == REQ_TYPE_PM_SUSPEND || \
rl->flags &= ~flag;
}
+static inline bool rq_mergeable(struct request *rq)
+{
+ if (rq->cmd_type != REQ_TYPE_FS)
+ return false;
-/*
- * mergeable request must not have _NOMERGE or _BARRIER bit set, nor may
- * it already be started by driver.
- */
-#define RQ_NOMERGE_FLAGS \
- (REQ_NOMERGE | REQ_STARTED | REQ_SOFTBARRIER | REQ_FLUSH | REQ_FUA | REQ_DISCARD)
-#define rq_mergeable(rq) \
- (!((rq)->cmd_flags & RQ_NOMERGE_FLAGS) && \
- (((rq)->cmd_flags & REQ_DISCARD) || \
- (rq)->cmd_type == REQ_TYPE_FS))
+ if (rq->cmd_flags & REQ_NOMERGE_FLAGS)
+ return false;
+
+ return true;
+}
+
+static inline bool blk_check_merge_flags(unsigned int flags1,
+ unsigned int flags2)
+{
+ if ((flags1 & REQ_DISCARD) != (flags2 & REQ_DISCARD))
+ return false;
+
+ if ((flags1 & REQ_SECURE) != (flags2 & REQ_SECURE))
+ return false;
+
+ if ((flags1 & REQ_WRITE_SAME) != (flags2 & REQ_WRITE_SAME))
+ return false;
+
+ return true;
+}
+
+static inline bool blk_write_same_mergeable(struct bio *a, struct bio *b)
+{
+ if (bio_data(a) == bio_data(b))
+ return true;
+
+ return false;
+}
/*
* q->prep_rq_fn return values
return blk_rq_cur_bytes(rq) >> 9;
}
+static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q,
+ unsigned int cmd_flags)
+{
+ if (unlikely(cmd_flags & REQ_DISCARD))
+ return q->limits.max_discard_sectors;
+
+ if (unlikely(cmd_flags & REQ_WRITE_SAME))
+ return q->limits.max_write_same_sectors;
+
+ return q->limits.max_sectors;
+}
+
+static inline unsigned int blk_rq_get_max_sectors(struct request *rq)
+{
+ struct request_queue *q = rq->q;
+
+ if (unlikely(rq->cmd_type == REQ_TYPE_BLOCK_PC))
+ return q->limits.max_hw_sectors;
+
+ return blk_queue_get_max_sectors(q, rq->cmd_flags);
+}
+
/*
* Request issue related functions.
*/
extern void blk_queue_max_segment_size(struct request_queue *, unsigned int);
extern void blk_queue_max_discard_sectors(struct request_queue *q,
unsigned int max_discard_sectors);
+extern void blk_queue_max_write_same_sectors(struct request_queue *q,
+ unsigned int max_write_same_sectors);
extern void blk_queue_logical_block_size(struct request_queue *, unsigned short);
extern void blk_queue_physical_block_size(struct request_queue *, unsigned int);
extern void blk_queue_alignment_offset(struct request_queue *q,
extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *);
extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
sector_t nr_sects, gfp_t gfp_mask, unsigned long flags);
+extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
+ sector_t nr_sects, gfp_t gfp_mask, struct page *page);
extern int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
sector_t nr_sects, gfp_t gfp_mask);
static inline int sb_issue_discard(struct super_block *sb, sector_t block,
return queue_discard_zeroes_data(bdev_get_queue(bdev));
}
+static inline unsigned int bdev_write_same(struct block_device *bdev)
+{
+ struct request_queue *q = bdev_get_queue(bdev);
+
+ if (q)
+ return q->limits.max_write_same_sectors;
+
+ return 0;
+}
+
static inline int queue_dma_alignment(struct request_queue *q)
{
return q ? q->dma_alignment : 511;
#define BLKDISCARDZEROES _IO(0x12,124)
#define BLKSECDISCARD _IO(0x12,125)
#define BLKROTATIONAL _IO(0x12,126)
+#define BLKZEROOUT _IO(0x12,127)
#define BMAP_IOCTL 1 /* obsolete - kept for compatibility */
#define FIBMAP _IO(0x00,1) /* bmap access */
#include <linux/migrate_mode.h>
#include <linux/uidgid.h>
#include <linux/lockdep.h>
+#include <linux/percpu-rwsem.h>
#include <asm/byteorder.h>
int bd_fsfreeze_count;
/* Mutex for freeze */
struct mutex bd_fsfreeze_mutex;
+ /* A semaphore that prevents I/O while block size is being changed */
+ struct percpu_rw_semaphore bd_block_size_semaphore;
};
/*
unsigned long *nr_segs, size_t *count, int access_flags);
/* fs/block_dev.c */
+extern ssize_t blkdev_aio_read(struct kiocb *iocb, const struct iovec *iov,
+ unsigned long nr_segs, loff_t pos);
extern ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos);
extern int blkdev_fsync(struct file *filp, loff_t start, loff_t end,
--- /dev/null
+#ifndef _LINUX_PERCPU_RWSEM_H
+#define _LINUX_PERCPU_RWSEM_H
+
+#include <linux/mutex.h>
+#include <linux/percpu.h>
+#include <linux/rcupdate.h>
+#include <linux/delay.h>
+
+struct percpu_rw_semaphore {
+ unsigned __percpu *counters;
+ bool locked;
+ struct mutex mtx;
+};
+
+static inline void percpu_down_read(struct percpu_rw_semaphore *p)
+{
+ rcu_read_lock();
+ if (unlikely(p->locked)) {
+ rcu_read_unlock();
+ mutex_lock(&p->mtx);
+ this_cpu_inc(*p->counters);
+ mutex_unlock(&p->mtx);
+ return;
+ }
+ this_cpu_inc(*p->counters);
+ rcu_read_unlock();
+}
+
+static inline void percpu_up_read(struct percpu_rw_semaphore *p)
+{
+ /*
+ * On X86, write operation in this_cpu_dec serves as a memory unlock
+ * barrier (i.e. memory accesses may be moved before the write, but
+ * no memory accesses are moved past the write).
+ * On other architectures this may not be the case, so we need smp_mb()
+ * there.
+ */
+#if defined(CONFIG_X86) && (!defined(CONFIG_X86_PPRO_FENCE) && !defined(CONFIG_X86_OOSTORE))
+ barrier();
+#else
+ smp_mb();
+#endif
+ this_cpu_dec(*p->counters);
+}
+
+static inline unsigned __percpu_count(unsigned __percpu *counters)
+{
+ unsigned total = 0;
+ int cpu;
+
+ for_each_possible_cpu(cpu)
+ total += ACCESS_ONCE(*per_cpu_ptr(counters, cpu));
+
+ return total;
+}
+
+static inline void percpu_down_write(struct percpu_rw_semaphore *p)
+{
+ mutex_lock(&p->mtx);
+ p->locked = true;
+ synchronize_rcu();
+ while (__percpu_count(p->counters))
+ msleep(1);
+ smp_rmb(); /* paired with smp_mb() in percpu_sem_up_read() */
+}
+
+static inline void percpu_up_write(struct percpu_rw_semaphore *p)
+{
+ p->locked = false;
+ mutex_unlock(&p->mtx);
+}
+
+static inline int percpu_init_rwsem(struct percpu_rw_semaphore *p)
+{
+ p->counters = alloc_percpu(unsigned);
+ if (unlikely(!p->counters))
+ return -ENOMEM;
+ p->locked = false;
+ mutex_init(&p->mtx);
+ return 0;
+}
+
+static inline void percpu_free_rwsem(struct percpu_rw_semaphore *p)
+{
+ free_percpu(p->counters);
+ p->counters = NULL; /* catch use after free bugs */
+}
+
+#endif
return page_address(sg_page(sg)) + sg->offset;
}
+int sg_nents(struct scatterlist *sg);
struct scatterlist *sg_next(struct scatterlist *);
struct scatterlist *sg_last(struct scatterlist *s, unsigned int);
void sg_init_table(struct scatterlist *, unsigned int);
}
EXPORT_SYMBOL(sg_next);
+/**
+ * sg_nents - return total count of entries in scatterlist
+ * @sg: The scatterlist
+ *
+ * Description:
+ * Allows to know how many entries are in sg, taking into acount
+ * chaining as well
+ *
+ **/
+int sg_nents(struct scatterlist *sg)
+{
+ int nents;
+ for (nents = 0; sg; sg = sg_next(sg))
+ nents++;
+ return nents;
+}
+EXPORT_SYMBOL(sg_nents);
+
+
/**
* sg_last - return the last scatterlist entry in a list
* @sgl: First entry in the scatterlist