@@ -719,6 +719,17 @@ static noinline int should_fail_bio(struct bio *bio)
}
ALLOW_ERROR_INJECTION(should_fail_bio, ERRNO);
+static inline int bio_check_copy_eod(struct bio *bio, sector_t start,
+ sector_t nr_sectors, sector_t maxsector)
+{
+ if (nr_sectors && maxsector && (nr_sectors > maxsector ||
+ start > maxsector - nr_sectors)) {
+ handle_bad_sector(bio, maxsector);
+ return -EIO;
+ }
+ return 0;
+}
+
/*
* Check whether this bio extends beyond the end of the device or partition.
* This may well happen - the kernel calls bread() without checking the size of
@@ -737,6 +748,75 @@ static inline int bio_check_eod(struct bio *bio, sector_t maxsector)
return 0;
}
+/*
+ * Check for copy limits and remap source ranges if needed.
+ */
+static inline int blk_check_copy(struct bio *bio)
+{
+ struct hd_struct *p = NULL;
+ struct request_queue *q = bio->bi_disk->queue;
+ struct blk_copy_payload *payload;
+ unsigned short nr_range;
+ int ret = -EIO;
+ int i, copy_len = 0;
+
+ rcu_read_lock();
+
+ if (bio->bi_partno) {
+ p = __disk_get_part(bio->bi_disk, bio->bi_partno);
+ if (unlikely(!p))
+ goto out;
+ if (unlikely(bio_check_ro(bio, p)))
+ goto out;
+ } else {
+ if (unlikely(bio_check_ro(bio, &bio->bi_disk->part0)))
+ goto out;
+ }
+
+ payload = bio_data(bio);
+ nr_range = payload->copy_range;
+
+ /* cannot handle copy crossing nr_ranges limit */
+ if (payload->copy_range > q->limits.max_copy_nr_ranges)
+ goto out;
+
+ for (i = 0; i < nr_range; i++) {
+ copy_len += payload->range[i].len;
+ if (p) {
+ if (bio_check_copy_eod(bio, payload->range[i].src,
+ payload->range[i].len, part_nr_sects_read(p)))
+ goto out;
+ payload->range[i].src += p->start_sect;
+ } else {
+ if (unlikely(bio_check_copy_eod(bio, payload->range[i].src,
+ payload->range[i].len,
+ get_capacity(bio->bi_disk))))
+ goto out;
+ }
+ }
+
+ /* cannot handle copy more than copy limits */
+ if (copy_len > q->limits.max_copy_sectors)
+ goto out;
+
+ if (p) {
+ if (unlikely(bio_check_copy_eod(bio, bio->bi_iter.bi_sector, copy_len,
+ part_nr_sects_read(p))))
+ goto out;
+ } else {
+ if (unlikely(bio_check_copy_eod(bio, bio->bi_iter.bi_sector, copy_len,
+ get_capacity(bio->bi_disk))))
+ goto out;
+
+ }
+
+ if (p)
+ bio->bi_partno = 0;
+ ret = 0;
+out:
+ rcu_read_unlock();
+ return ret;
+}
/*
* Remap block n of partition p to block n+start(p) of the disk.
*/
@@ -825,14 +905,16 @@ static noinline_for_stack bool submit_bio_checks(struct bio *bio)
if (should_fail_bio(bio))
goto end_io;
- if (bio->bi_partno) {
- if (unlikely(blk_partition_remap(bio)))
- goto end_io;
- } else {
- if (unlikely(bio_check_ro(bio, &bio->bi_disk->part0)))
- goto end_io;
- if (unlikely(bio_check_eod(bio, get_capacity(bio->bi_disk))))
- goto end_io;
+ if (likely(!op_is_copy(bio->bi_opf))) {
+ if (bio->bi_partno) {
+ if (unlikely(blk_partition_remap(bio)))
+ goto end_io;
+ } else {
+ if (unlikely(bio_check_ro(bio, &bio->bi_disk->part0)))
+ goto end_io;
+ if (unlikely(bio_check_eod(bio, get_capacity(bio->bi_disk))))
+ goto end_io;
+ }
}
/*
@@ -856,6 +938,12 @@ static noinline_for_stack bool submit_bio_checks(struct bio *bio)
if (!blk_queue_discard(q))
goto not_supported;
break;
+ case REQ_OP_COPY:
+ if (!blk_queue_copy(q))
+ goto not_supported;
+ if (unlikely(blk_check_copy(bio)))
+ goto end_io;
+ break;
case REQ_OP_SECURE_ERASE:
if (!blk_queue_secure_erase(q))
goto not_supported;
@@ -150,6 +150,122 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
}
EXPORT_SYMBOL(blkdev_issue_discard);
+int __blkdev_issue_copy(struct block_device *bdev, sector_t dest,
+ sector_t nr_srcs, struct range_entry *rlist, gfp_t gfp_mask,
+ int flags, struct bio **biop)
+{
+ struct request_queue *q = bdev_get_queue(bdev);
+ struct bio *bio;
+ struct blk_copy_payload *payload;
+ unsigned int op;
+ sector_t bs_mask;
+ sector_t src_sects, len = 0, total_len = 0;
+ int i, ret, total_size;
+
+ if (!q)
+ return -ENXIO;
+
+ if (!nr_srcs)
+ return -EINVAL;
+
+ if (bdev_read_only(bdev))
+ return -EPERM;
+
+ if (!blk_queue_copy(q))
+ return -EOPNOTSUPP;
+ op = REQ_OP_COPY;
+
+ bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1;
+ if (dest & bs_mask)
+ return -EINVAL;
+
+ payload = kmalloc(sizeof(struct blk_copy_payload) +
+ nr_srcs * sizeof(struct range_entry),
+ GFP_ATOMIC | __GFP_NOWARN);
+ if (!payload)
+ return -ENOMEM;
+
+ bio = bio_alloc(gfp_mask, 1);
+ bio->bi_iter.bi_sector = dest;
+ bio_set_dev(bio, bdev);
+ bio_set_op_attrs(bio, op, REQ_NOMERGE);
+
+ payload->dest = dest;
+
+ for (i = 0; i < nr_srcs; i++) {
+ /* copy payload provided are in bytes */
+ src_sects = rlist[i].src;
+ if (src_sects & bs_mask)
+ return -EINVAL;
+ src_sects = src_sects >> SECTOR_SHIFT;
+
+ if (len & bs_mask)
+ return -EINVAL;
+ len = rlist[i].len >> SECTOR_SHIFT;
+ if (len > q->limits.max_copy_range_sectors)
+ return -EINVAL;
+
+ total_len += len;
+
+ WARN_ON_ONCE((src_sects << 9) > UINT_MAX);
+
+ payload->range[i].src = src_sects;
+ payload->range[i].len = len;
+ }
+
+ /* storing # of source ranges */
+ payload->copy_range = i;
+ /* storing copy len so far */
+ payload->copy_size = total_len;
+
+ total_size = sizeof(struct blk_copy_payload) + nr_srcs * sizeof(struct range_entry);
+ ret = bio_add_page(bio, virt_to_page(payload), total_size,
+ offset_in_page(payload));
+ if (ret != total_size) {
+ kfree(payload);
+ return -ENOMEM;
+ }
+
+ *biop = bio;
+ return 0;
+}
+EXPORT_SYMBOL(__blkdev_issue_copy);
+
+/**
+ * blkdev_issue_copy - queue a copy
+ * @bdev: blockdev to issue copy for
+ * @dest: dest sector
+ * @nr_srcs: number of source ranges to copy
+ * @rlist: list of range entries
+ * @gfp_mask: memory allocation flags (for bio_alloc)
+ * @flags: BLKDEV_COPY_* flags to control behaviour //TODO
+ *
+ * Description:
+ * Issue a copy request for dest sector with source in rlist
+ */
+int blkdev_issue_copy(struct block_device *bdev, sector_t dest,
+ int nr_srcs, struct range_entry *rlist,
+ gfp_t gfp_mask, unsigned long flags)
+{
+ struct bio *bio = NULL;
+ int ret;
+
+ ret = __blkdev_issue_copy(bdev, dest, nr_srcs, rlist, gfp_mask, flags,
+ &bio);
+ if (!ret && bio) {
+ ret = submit_bio_wait(bio);
+ if (ret == -EOPNOTSUPP)
+ ret = 0;
+
+ kfree(page_address(bio_first_bvec_all(bio)->bv_page) +
+ bio_first_bvec_all(bio)->bv_offset);
+ bio_put(bio);
+ }
+
+ return ret;
+}
+EXPORT_SYMBOL(blkdev_issue_copy);
+
/**
* __blkdev_issue_write_same - generate number of bios with same page
* @bdev: target blockdev
@@ -301,6 +301,8 @@ void __blk_queue_split(struct bio **bio, unsigned int *nr_segs)
struct bio *split = NULL;
switch (bio_op(*bio)) {
+ case REQ_OP_COPY:
+ break;
case REQ_OP_DISCARD:
case REQ_OP_SECURE_ERASE:
split = blk_bio_discard_split(q, *bio, &q->bio_split, nr_segs);
@@ -60,6 +60,9 @@ void blk_set_default_limits(struct queue_limits *lim)
lim->io_opt = 0;
lim->misaligned = 0;
lim->zoned = BLK_ZONED_NONE;
+ lim->max_copy_sectors = 0;
+ lim->max_copy_nr_ranges = 0;
+ lim->max_copy_range_sectors = 0;
}
EXPORT_SYMBOL(blk_set_default_limits);
@@ -549,6 +552,14 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
t->io_opt = lcm_not_zero(t->io_opt, b->io_opt);
t->chunk_sectors = lcm_not_zero(t->chunk_sectors, b->chunk_sectors);
+ /* copy limits */
+ t->max_copy_sectors = min_not_zero(t->max_copy_sectors,
+ b->max_copy_sectors);
+ t->max_copy_range_sectors = min_not_zero(t->max_copy_range_sectors,
+ b->max_copy_range_sectors);
+ t->max_copy_nr_ranges = min_not_zero(t->max_copy_nr_ranges,
+ b->max_copy_nr_ranges);
+
/* Physical block size a multiple of the logical block size? */
if (t->physical_block_size & (t->logical_block_size - 1)) {
t->physical_block_size = t->logical_block_size;
@@ -166,6 +166,23 @@ static ssize_t queue_discard_granularity_show(struct request_queue *q, char *pag
return queue_var_show(q->limits.discard_granularity, page);
}
+static ssize_t queue_max_copy_sectors_show(struct request_queue *q, char *page)
+{
+ return queue_var_show(q->limits.max_copy_sectors, page);
+}
+
+static ssize_t queue_max_copy_range_sectors_show(struct request_queue *q,
+ char *page)
+{
+ return queue_var_show(q->limits.max_copy_range_sectors, page);
+}
+
+static ssize_t queue_max_copy_nr_ranges_show(struct request_queue *q,
+ char *page)
+{
+ return queue_var_show(q->limits.max_copy_nr_ranges, page);
+}
+
static ssize_t queue_discard_max_hw_show(struct request_queue *q, char *page)
{
@@ -590,6 +607,9 @@ QUEUE_RO_ENTRY(queue_zoned, "zoned");
QUEUE_RO_ENTRY(queue_nr_zones, "nr_zones");
QUEUE_RO_ENTRY(queue_max_open_zones, "max_open_zones");
QUEUE_RO_ENTRY(queue_max_active_zones, "max_active_zones");
+QUEUE_RO_ENTRY(queue_max_copy_sectors, "max_copy_sectors");
+QUEUE_RO_ENTRY(queue_max_copy_range_sectors, "max_copy_range_sectors");
+QUEUE_RO_ENTRY(queue_max_copy_nr_ranges, "max_copy_nr_ranges");
QUEUE_RW_ENTRY(queue_nomerges, "nomerges");
QUEUE_RW_ENTRY(queue_rq_affinity, "rq_affinity");
@@ -636,6 +656,9 @@ static struct attribute *queue_attrs[] = {
&queue_discard_max_entry.attr,
&queue_discard_max_hw_entry.attr,
&queue_discard_zeroes_data_entry.attr,
+ &queue_max_copy_sectors_entry.attr,
+ &queue_max_copy_range_sectors_entry.attr,
+ &queue_max_copy_nr_ranges_entry.attr,
&queue_write_same_max_entry.attr,
&queue_write_zeroes_max_entry.attr,
&queue_zone_append_max_entry.attr,
@@ -75,6 +75,7 @@ bool blk_req_needs_zone_write_lock(struct request *rq)
case REQ_OP_WRITE_ZEROES:
case REQ_OP_WRITE_SAME:
case REQ_OP_WRITE:
+ case REQ_OP_COPY:
return blk_rq_zone_is_seq(rq);
default:
return false;
@@ -254,6 +254,7 @@ static struct bio *bounce_clone_bio(struct bio *bio_src, gfp_t gfp_mask,
bio->bi_iter.bi_size = bio_src->bi_iter.bi_size;
switch (bio_op(bio)) {
+ case REQ_OP_COPY:
case REQ_OP_DISCARD:
case REQ_OP_SECURE_ERASE:
case REQ_OP_WRITE_ZEROES:
@@ -142,6 +142,47 @@ static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode,
GFP_KERNEL, flags);
}
+static int blk_ioctl_copy(struct block_device *bdev, fmode_t mode,
+ unsigned long arg, unsigned long flags)
+{
+ struct copy_range crange;
+ struct range_entry *rlist;
+ struct request_queue *q = bdev_get_queue(bdev);
+ sector_t dest;
+ int ret;
+
+ if (!(mode & FMODE_WRITE))
+ return -EBADF;
+
+ if (!blk_queue_copy(q))
+ return -EOPNOTSUPP;
+
+ if (copy_from_user(&crange, (void __user *)arg, sizeof(crange)))
+ return -EFAULT;
+
+ if (crange.dest & ((1 << SECTOR_SHIFT) - 1))
+ return -EFAULT;
+ dest = crange.dest >> SECTOR_SHIFT;
+
+ rlist = kmalloc_array(crange.nr_range, sizeof(*rlist),
+ GFP_ATOMIC | __GFP_NOWARN);
+
+ if (!rlist)
+ return -ENOMEM;
+
+ if (copy_from_user(rlist, (void __user *)crange.range_list,
+ sizeof(*rlist) * crange.nr_range)) {
+ ret = -EFAULT;
+ goto out;
+ }
+
+ ret = blkdev_issue_copy(bdev, dest, crange.nr_range,
+ rlist, GFP_KERNEL, flags);
+out:
+ kfree(rlist);
+ return ret;
+}
+
static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode,
unsigned long arg)
{
@@ -467,6 +508,8 @@ static int blkdev_common_ioctl(struct block_device *bdev, fmode_t mode,
case BLKSECDISCARD:
return blk_ioctl_discard(bdev, mode, arg,
BLKDEV_DISCARD_SECURE);
+ case BLKCOPY:
+ return blk_ioctl_copy(bdev, mode, arg, 0);
case BLKZEROOUT:
return blk_ioctl_zeroout(bdev, mode, arg);
case BLKREPORTZONE:
@@ -71,6 +71,7 @@ static inline bool bio_has_data(struct bio *bio)
static inline bool bio_no_advance_iter(const struct bio *bio)
{
return bio_op(bio) == REQ_OP_DISCARD ||
+ bio_op(bio) == REQ_OP_COPY ||
bio_op(bio) == REQ_OP_SECURE_ERASE ||
bio_op(bio) == REQ_OP_WRITE_SAME ||
bio_op(bio) == REQ_OP_WRITE_ZEROES;
@@ -360,6 +360,8 @@ enum req_opf {
REQ_OP_ZONE_RESET = 15,
/* reset all the zone present on the device */
REQ_OP_ZONE_RESET_ALL = 17,
+ /* copy ranges within device */
+ REQ_OP_COPY = 19,
/* SCSI passthrough using struct scsi_request */
REQ_OP_SCSI_IN = 32,
@@ -486,6 +488,11 @@ static inline bool op_is_discard(unsigned int op)
return (op & REQ_OP_MASK) == REQ_OP_DISCARD;
}
+static inline bool op_is_copy(unsigned int op)
+{
+ return (op & REQ_OP_MASK) == REQ_OP_COPY;
+}
+
/*
* Check if a bio or request operation is a zone management operation, with
* the exception of REQ_OP_ZONE_RESET_ALL which is treated as a special case
@@ -340,10 +340,13 @@ struct queue_limits {
unsigned int max_zone_append_sectors;
unsigned int discard_granularity;
unsigned int discard_alignment;
+ unsigned int max_copy_sectors;
unsigned short max_segments;
unsigned short max_integrity_segments;
unsigned short max_discard_segments;
+ unsigned short max_copy_range_sectors;
+ unsigned short max_copy_nr_ranges;
unsigned char misaligned;
unsigned char discard_misaligned;
@@ -625,6 +628,7 @@ struct request_queue {
#define QUEUE_FLAG_RQ_ALLOC_TIME 27 /* record rq->alloc_time_ns */
#define QUEUE_FLAG_HCTX_ACTIVE 28 /* at least one blk-mq hctx is active */
#define QUEUE_FLAG_NOWAIT 29 /* device supports NOWAIT */
+#define QUEUE_FLAG_COPY 30 /* supports copy */
#define QUEUE_FLAG_MQ_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \
(1 << QUEUE_FLAG_SAME_COMP) | \
@@ -647,6 +651,7 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q);
#define blk_queue_io_stat(q) test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags)
#define blk_queue_add_random(q) test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags)
#define blk_queue_discard(q) test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags)
+#define blk_queue_copy(q) test_bit(QUEUE_FLAG_COPY, &(q)->queue_flags)
#define blk_queue_zone_resetall(q) \
test_bit(QUEUE_FLAG_ZONE_RESETALL, &(q)->queue_flags)
#define blk_queue_secure_erase(q) \
@@ -1059,6 +1064,9 @@ static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q,
return min(q->limits.max_discard_sectors,
UINT_MAX >> SECTOR_SHIFT);
+ if (unlikely(op == REQ_OP_COPY))
+ return q->limits.max_copy_sectors;
+
if (unlikely(op == REQ_OP_WRITE_SAME))
return q->limits.max_write_same_sectors;
@@ -1330,6 +1338,13 @@ extern int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
sector_t nr_sects, gfp_t gfp_mask, int flags,
struct bio **biop);
+extern int __blkdev_issue_copy(struct block_device *bdev, sector_t dest,
+ sector_t nr_srcs, struct range_entry *rlist, gfp_t gfp_mask,
+ int flags, struct bio **biop);
+extern int blkdev_issue_copy(struct block_device *bdev, sector_t dest,
+ int nr_srcs, struct range_entry *rlist,
+ gfp_t gfp_mask, unsigned long flags);
+
#define BLKDEV_ZERO_NOUNMAP (1 << 0) /* do not free blocks */
#define BLKDEV_ZERO_NOFALLBACK (1 << 1) /* don't write explicit zeroes */
@@ -64,6 +64,26 @@ struct fstrim_range {
__u64 minlen;
};
+struct range_entry {
+ __u64 src;
+ __u64 len;
+};
+
+struct copy_range {
+ __u64 dest;
+ __u64 nr_range;
+ __u64 range_list;
+ __u64 rsvd;
+};
+
+struct blk_copy_payload {
+ sector_t dest;
+ int copy_range;
+ int copy_size;
+ int err;
+ struct range_entry range[];
+};
+
/* extent-same (dedupe) ioctls; these MUST match the btrfs ioctl definitions */
#define FILE_DEDUPE_RANGE_SAME 0
#define FILE_DEDUPE_RANGE_DIFFERS 1
@@ -184,6 +204,7 @@ struct fsxattr {
#define BLKSECDISCARD _IO(0x12,125)
#define BLKROTATIONAL _IO(0x12,126)
#define BLKZEROOUT _IO(0x12,127)
+#define BLKCOPY _IOWR(0x12, 128, struct copy_range)
/*
* A jump here: 130-131 are reserved for zoned block devices
* (see uapi/linux/blkzoned.h)