Implementation is based on existing read and write infrastructure.
copy_max_bytes: A new configfs and module parameter is introduced, which
can be used to set hardware/driver supported maximum copy limit.
Only request based queue mode will support for copy offload.
Added tracefs support to copy IO tracing.
Reviewed-by: Hannes Reinecke <hare@suse.de>
Suggested-by: Damien Le Moal <damien.lemoal@opensource.wdc.com>
Signed-off-by: Anuj Gupta <anuj20.g@samsung.com>
Signed-off-by: Nitesh Shetty <nj.shetty@samsung.com>
Signed-off-by: Vincent Fu <vincent.fu@samsung.com>
---
Documentation/block/null_blk.rst | 5 ++
drivers/block/null_blk/main.c | 102 +++++++++++++++++++++++++++++-
drivers/block/null_blk/null_blk.h | 1 +
drivers/block/null_blk/trace.h | 23 +++++++
4 files changed, 128 insertions(+), 3 deletions(-)
diff --git a/Documentation/block/null_blk.rst b/Documentation/block/null_blk.rst
index 4dd78f24d10a..6153e02fcf13 100644
--- a/Documentation/block/null_blk.rst
+++ b/Documentation/block/null_blk.rst
@@ -149,3 +149,8 @@ zone_size=[MB]: Default: 256
zone_nr_conv=[nr_conv]: Default: 0
The number of conventional zones to create when block device is zoned. If
zone_nr_conv >= nr_zones, it will be reduced to nr_zones - 1.
+
+copy_max_bytes=[size in bytes]: Default: COPY_MAX_BYTES
+ A module and configfs parameter which can be used to set hardware/driver
+ supported maximum copy offload limit.
+ COPY_MAX_BYTES(=128MB at present) is defined in fs.h
diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c
index b33b9ebfebd2..dcfbd5275414 100644
--- a/drivers/block/null_blk/main.c
+++ b/drivers/block/null_blk/main.c
@@ -172,6 +172,10 @@ static int g_max_sectors;
module_param_named(max_sectors, g_max_sectors, int, 0444);
MODULE_PARM_DESC(max_sectors, "Maximum size of a command (in 512B sectors)");
+static unsigned long g_copy_max_bytes = BLK_COPY_MAX_BYTES;
+module_param_named(copy_max_bytes, g_copy_max_bytes, ulong, 0444);
+MODULE_PARM_DESC(copy_max_bytes, "Maximum size of a copy command (in bytes)");
+
static unsigned int nr_devices = 1;
module_param(nr_devices, uint, 0444);
MODULE_PARM_DESC(nr_devices, "Number of devices to register");
@@ -433,6 +437,7 @@ NULLB_DEVICE_ATTR(home_node, uint, NULL);
NULLB_DEVICE_ATTR(queue_mode, uint, NULL);
NULLB_DEVICE_ATTR(blocksize, uint, NULL);
NULLB_DEVICE_ATTR(max_sectors, uint, NULL);
+NULLB_DEVICE_ATTR(copy_max_bytes, uint, NULL);
NULLB_DEVICE_ATTR(irqmode, uint, NULL);
NULLB_DEVICE_ATTR(hw_queue_depth, uint, NULL);
NULLB_DEVICE_ATTR(index, uint, NULL);
@@ -577,6 +582,7 @@ static struct configfs_attribute *nullb_device_attrs[] = {
&nullb_device_attr_queue_mode,
&nullb_device_attr_blocksize,
&nullb_device_attr_max_sectors,
+ &nullb_device_attr_copy_max_bytes,
&nullb_device_attr_irqmode,
&nullb_device_attr_hw_queue_depth,
&nullb_device_attr_index,
@@ -687,7 +693,7 @@ static ssize_t memb_group_features_show(struct config_item *item, char *page)
"shared_tags,size,submit_queues,use_per_node_hctx,"
"virt_boundary,zoned,zone_capacity,zone_max_active,"
"zone_max_open,zone_nr_conv,zone_offline,zone_readonly,"
- "zone_size,zone_append_max_sectors\n");
+ "zone_size,zone_append_max_sectors,copy_max_bytes\n");
}
CONFIGFS_ATTR_RO(memb_group_, features);
@@ -753,6 +759,7 @@ static struct nullb_device *null_alloc_dev(void)
dev->queue_mode = g_queue_mode;
dev->blocksize = g_bs;
dev->max_sectors = g_max_sectors;
+ dev->copy_max_bytes = g_copy_max_bytes;
dev->irqmode = g_irqmode;
dev->hw_queue_depth = g_hw_queue_depth;
dev->blocking = g_blocking;
@@ -1221,6 +1228,81 @@ static int null_transfer(struct nullb *nullb, struct page *page,
return err;
}
+static inline int nullb_setup_copy(struct nullb *nullb, struct request *req,
+ bool is_fua)
+{
+ sector_t sector_in = 0, sector_out = 0;
+ loff_t offset_in, offset_out;
+ void *in, *out;
+ ssize_t chunk, rem = 0;
+ struct bio *bio;
+ struct nullb_page *t_page_in, *t_page_out;
+ u16 seg = 1;
+ int status = -EIO;
+
+ if (blk_rq_nr_phys_segments(req) != BLK_COPY_MAX_SEGMENTS)
+ return status;
+
+ /*
+ * First bio contains information about destination and last bio
+ * contains information about source.
+ */
+ __rq_for_each_bio(bio, req) {
+ if (seg == blk_rq_nr_phys_segments(req)) {
+ sector_in = bio->bi_iter.bi_sector;
+ if (rem != bio->bi_iter.bi_size)
+ return status;
+ } else {
+ sector_out = bio->bi_iter.bi_sector;
+ rem = bio->bi_iter.bi_size;
+ }
+ seg++;
+ }
+
+ trace_nullb_copy_op(req, sector_out << SECTOR_SHIFT,
+ sector_in << SECTOR_SHIFT, rem);
+
+ spin_lock_irq(&nullb->lock);
+ while (rem > 0) {
+ chunk = min_t(size_t, nullb->dev->blocksize, rem);
+ offset_in = (sector_in & SECTOR_MASK) << SECTOR_SHIFT;
+ offset_out = (sector_out & SECTOR_MASK) << SECTOR_SHIFT;
+
+ if (null_cache_active(nullb) && !is_fua)
+ null_make_cache_space(nullb, PAGE_SIZE);
+
+ t_page_in = null_lookup_page(nullb, sector_in, false,
+ !null_cache_active(nullb));
+ if (!t_page_in)
+ goto err;
+ t_page_out = null_insert_page(nullb, sector_out,
+ !null_cache_active(nullb) ||
+ is_fua);
+ if (!t_page_out)
+ goto err;
+
+ in = kmap_local_page(t_page_in->page);
+ out = kmap_local_page(t_page_out->page);
+
+ memcpy(out + offset_out, in + offset_in, chunk);
+ kunmap_local(out);
+ kunmap_local(in);
+ __set_bit(sector_out & SECTOR_MASK, t_page_out->bitmap);
+
+ if (is_fua)
+ null_free_sector(nullb, sector_out, true);
+
+ rem -= chunk;
+ sector_in += chunk >> SECTOR_SHIFT;
+ sector_out += chunk >> SECTOR_SHIFT;
+ }
+
+ status = 0;
+err:
+ spin_unlock_irq(&nullb->lock);
+ return status;
+}
+
static blk_status_t null_handle_rq(struct nullb_cmd *cmd)
{
struct request *rq = blk_mq_rq_from_pdu(cmd);
@@ -1230,13 +1312,16 @@ static blk_status_t null_handle_rq(struct nullb_cmd *cmd)
sector_t sector = blk_rq_pos(rq);
struct req_iterator iter;
struct bio_vec bvec;
+ bool fua = rq->cmd_flags & REQ_FUA;
+
+ if (op_is_copy(req_op(rq)))
+ return nullb_setup_copy(nullb, rq, fua);
spin_lock_irq(&nullb->lock);
rq_for_each_segment(bvec, rq, iter) {
len = bvec.bv_len;
err = null_transfer(nullb, bvec.bv_page, len, bvec.bv_offset,
- op_is_write(req_op(rq)), sector,
- rq->cmd_flags & REQ_FUA);
+ op_is_write(req_op(rq)), sector, fua);
if (err)
break;
sector += len >> SECTOR_SHIFT;
@@ -1721,6 +1806,12 @@ static void null_config_discard(struct nullb *nullb, struct queue_limits *lim)
lim->max_hw_discard_sectors = UINT_MAX >> 9;
}
+static void null_config_copy(struct nullb *nullb, struct queue_limits *lim)
+{
+ lim->max_copy_hw_sectors = nullb->dev->copy_max_bytes >> SECTOR_SHIFT;
+ lim->max_copy_sectors = nullb->dev->copy_max_bytes >> SECTOR_SHIFT;
+}
+
static const struct block_device_operations null_ops = {
.owner = THIS_MODULE,
.report_zones = null_report_zones,
@@ -1843,6 +1934,9 @@ static int null_validate_conf(struct nullb_device *dev)
return -EINVAL;
}
+ if (dev->queue_mode == NULL_Q_BIO)
+ dev->copy_max_bytes = 0;
+
return 0;
}
@@ -1909,6 +2003,8 @@ static int null_add_dev(struct nullb_device *dev)
if (dev->virt_boundary)
lim.virt_boundary_mask = PAGE_SIZE - 1;
null_config_discard(nullb, &lim);
+ null_config_copy(nullb, &lim);
+
if (dev->zoned) {
rv = null_init_zoned_dev(dev, &lim);
if (rv)
diff --git a/drivers/block/null_blk/null_blk.h b/drivers/block/null_blk/null_blk.h
index 3234e6c85eed..c588729c17bd 100644
--- a/drivers/block/null_blk/null_blk.h
+++ b/drivers/block/null_blk/null_blk.h
@@ -91,6 +91,7 @@ struct nullb_device {
unsigned int queue_mode; /* block interface */
unsigned int blocksize; /* block size */
unsigned int max_sectors; /* Max sectors per command */
+ unsigned long copy_max_bytes; /* Max copy offload length in bytes */
unsigned int irqmode; /* IRQ completion handler */
unsigned int hw_queue_depth; /* queue depth */
unsigned int index; /* index of the disk, only valid with a disk */
diff --git a/drivers/block/null_blk/trace.h b/drivers/block/null_blk/trace.h
index f9eadac6b22f..cda1a2249978 100644
--- a/drivers/block/null_blk/trace.h
+++ b/drivers/block/null_blk/trace.h
@@ -76,6 +76,29 @@ TRACE_EVENT(nullb_report_zones,
);
#endif /* CONFIG_BLK_DEV_ZONED */
+TRACE_EVENT(nullb_copy_op,
+ TP_PROTO(struct request *req,
+ sector_t dst, sector_t src, size_t len),
+ TP_ARGS(req, dst, src, len),
+ TP_STRUCT__entry(
+ __array(char, disk, DISK_NAME_LEN)
+ __field(enum req_op, op)
+ __field(sector_t, dst)
+ __field(sector_t, src)
+ __field(size_t, len)
+ ),
+ TP_fast_assign(
+ __entry->op = req_op(req);
+ __assign_disk_name(__entry->disk, req->q->disk);
+ __entry->dst = dst;
+ __entry->src = src;
+ __entry->len = len;
+ ),
+ TP_printk("%s req=%-15s: dst=%llu, src=%llu, len=%lu",
+ __print_disk_name(__entry->disk),
+ blk_op_str(__entry->op),
+ __entry->dst, __entry->src, __entry->len)
+);
#endif /* _TRACE_NULLB_H */
#undef TRACE_INCLUDE_PATH
--
2.17.1On 5/20/24 03:20, Nitesh Shetty wrote:
> + if (blk_rq_nr_phys_segments(req) != BLK_COPY_MAX_SEGMENTS)
> + return status;
Why is this check necessary?
> + /*
> + * First bio contains information about destination and last bio
> + * contains information about source.
> + */
Please check this at runtime (WARN_ON_ONCE()?).
> + __rq_for_each_bio(bio, req) {
> + if (seg == blk_rq_nr_phys_segments(req)) {
> + sector_in = bio->bi_iter.bi_sector;
> + if (rem != bio->bi_iter.bi_size)
> + return status;
> + } else {
> + sector_out = bio->bi_iter.bi_sector;
> + rem = bio->bi_iter.bi_size;
> + }
> + seg++;
> + }
_rq_for_each_bio() iterates over the bios in a request. Does a copy
offload request always have two bios - one copy destination bio and
one copy source bio? If so, is 'seg' a bio counter? Why is that bio
counter compared with the number of physical segments in the request?
> + trace_nullb_copy_op(req, sector_out << SECTOR_SHIFT,
> + sector_in << SECTOR_SHIFT, rem);
> +
> + spin_lock_irq(&nullb->lock);
> + while (rem > 0) {
> + chunk = min_t(size_t, nullb->dev->blocksize, rem);
> + offset_in = (sector_in & SECTOR_MASK) << SECTOR_SHIFT;
> + offset_out = (sector_out & SECTOR_MASK) << SECTOR_SHIFT;
> +
> + if (null_cache_active(nullb) && !is_fua)
> + null_make_cache_space(nullb, PAGE_SIZE);
> +
> + t_page_in = null_lookup_page(nullb, sector_in, false,
> + !null_cache_active(nullb));
> + if (!t_page_in)
> + goto err;
> + t_page_out = null_insert_page(nullb, sector_out,
> + !null_cache_active(nullb) ||
> + is_fua);
> + if (!t_page_out)
> + goto err;
> +
> + in = kmap_local_page(t_page_in->page);
> + out = kmap_local_page(t_page_out->page);
> +
> + memcpy(out + offset_out, in + offset_in, chunk);
> + kunmap_local(out);
> + kunmap_local(in);
> + __set_bit(sector_out & SECTOR_MASK, t_page_out->bitmap);
> +
> + if (is_fua)
> + null_free_sector(nullb, sector_out, true);
> +
> + rem -= chunk;
> + sector_in += chunk >> SECTOR_SHIFT;
> + sector_out += chunk >> SECTOR_SHIFT;
> + }
> +
> + status = 0;
> +err:
> + spin_unlock_irq(&nullb->lock);
In the worst case, how long does this loop disable interrupts?
> +TRACE_EVENT(nullb_copy_op,
> + TP_PROTO(struct request *req,
> + sector_t dst, sector_t src, size_t len),
> + TP_ARGS(req, dst, src, len),
> + TP_STRUCT__entry(
> + __array(char, disk, DISK_NAME_LEN)
> + __field(enum req_op, op)
> + __field(sector_t, dst)
> + __field(sector_t, src)
> + __field(size_t, len)
> + ),
Isn't __string() preferred over __array() since the former occupies less space
in the trace buffer?
Thanks,
Bart.
On 20/05/24 04:42PM, Bart Van Assche wrote:
>On 5/20/24 03:20, Nitesh Shetty wrote:
>>+ if (blk_rq_nr_phys_segments(req) != BLK_COPY_MAX_SEGMENTS)
>>+ return status;
>
>Why is this check necessary?
>
>>+ /*
>>+ * First bio contains information about destination and last bio
>>+ * contains information about source.
>>+ */
>
>Please check this at runtime (WARN_ON_ONCE()?).
>
>>+ __rq_for_each_bio(bio, req) {
>>+ if (seg == blk_rq_nr_phys_segments(req)) {
>>+ sector_in = bio->bi_iter.bi_sector;
>>+ if (rem != bio->bi_iter.bi_size)
>>+ return status;
>>+ } else {
>>+ sector_out = bio->bi_iter.bi_sector;
>>+ rem = bio->bi_iter.bi_size;
>>+ }
>>+ seg++;
>>+ }
>
>_rq_for_each_bio() iterates over the bios in a request. Does a copy
>offload request always have two bios - one copy destination bio and
>one copy source bio? If so, is 'seg' a bio counter? Why is that bio
>counter compared with the number of physical segments in the request?
>
Yes, your observation is right. We are treating first bio as dst and
second as src. If not for that comparision, we might need to store the
index in a temporary variable and parse based on index value.
>>+ trace_nullb_copy_op(req, sector_out << SECTOR_SHIFT,
>>+ sector_in << SECTOR_SHIFT, rem);
>>+
>>+ spin_lock_irq(&nullb->lock);
>>+ while (rem > 0) {
>>+ chunk = min_t(size_t, nullb->dev->blocksize, rem);
>>+ offset_in = (sector_in & SECTOR_MASK) << SECTOR_SHIFT;
>>+ offset_out = (sector_out & SECTOR_MASK) << SECTOR_SHIFT;
>>+
>>+ if (null_cache_active(nullb) && !is_fua)
>>+ null_make_cache_space(nullb, PAGE_SIZE);
>>+
>>+ t_page_in = null_lookup_page(nullb, sector_in, false,
>>+ !null_cache_active(nullb));
>>+ if (!t_page_in)
>>+ goto err;
>>+ t_page_out = null_insert_page(nullb, sector_out,
>>+ !null_cache_active(nullb) ||
>>+ is_fua);
>>+ if (!t_page_out)
>>+ goto err;
>>+
>>+ in = kmap_local_page(t_page_in->page);
>>+ out = kmap_local_page(t_page_out->page);
>>+
>>+ memcpy(out + offset_out, in + offset_in, chunk);
>>+ kunmap_local(out);
>>+ kunmap_local(in);
>>+ __set_bit(sector_out & SECTOR_MASK, t_page_out->bitmap);
>>+
>>+ if (is_fua)
>>+ null_free_sector(nullb, sector_out, true);
>>+
>>+ rem -= chunk;
>>+ sector_in += chunk >> SECTOR_SHIFT;
>>+ sector_out += chunk >> SECTOR_SHIFT;
>>+ }
>>+
>>+ status = 0;
>>+err:
>>+ spin_unlock_irq(&nullb->lock);
>
>In the worst case, how long does this loop disable interrupts?
>
We havn't measured this. But this should be similar to read and write in
present infra, as we followed similar approach.
>>+TRACE_EVENT(nullb_copy_op,
>>+ TP_PROTO(struct request *req,
>>+ sector_t dst, sector_t src, size_t len),
>>+ TP_ARGS(req, dst, src, len),
>>+ TP_STRUCT__entry(
>>+ __array(char, disk, DISK_NAME_LEN)
>>+ __field(enum req_op, op)
>>+ __field(sector_t, dst)
>>+ __field(sector_t, src)
>>+ __field(size_t, len)
>>+ ),
>
>Isn't __string() preferred over __array() since the former occupies less space
>in the trace buffer?
>
Again we followed the present existing implementation, to have a simpler
series to review.
Thank you,
Nitesh Shetty
On 5/21/24 07:46, Nitesh Shetty wrote:
> On 20/05/24 04:42PM, Bart Van Assche wrote:
>> On 5/20/24 03:20, Nitesh Shetty wrote:
>>> + __rq_for_each_bio(bio, req) {
>>> + if (seg == blk_rq_nr_phys_segments(req)) {
>>> + sector_in = bio->bi_iter.bi_sector;
>>> + if (rem != bio->bi_iter.bi_size)
>>> + return status;
>>> + } else {
>>> + sector_out = bio->bi_iter.bi_sector;
>>> + rem = bio->bi_iter.bi_size;
>>> + }
>>> + seg++;
>>> + }
>>
>> _rq_for_each_bio() iterates over the bios in a request. Does a copy
>> offload request always have two bios - one copy destination bio and
>> one copy source bio? If so, is 'seg' a bio counter? Why is that bio
>> counter compared with the number of physical segments in the request?
>>
> Yes, your observation is right. We are treating first bio as dst and
> second as src. If not for that comparision, we might need to store the
> index in a temporary variable and parse based on index value.
I'm still wondering why 'seg' is compared with blk_rq_nr_phys_segments(req).
Thanks,
Bart.
On 22/05/24 10:52AM, Bart Van Assche wrote:
>On 5/21/24 07:46, Nitesh Shetty wrote:
>>On 20/05/24 04:42PM, Bart Van Assche wrote:
>>>On 5/20/24 03:20, Nitesh Shetty wrote:
>>>>+ __rq_for_each_bio(bio, req) {
>>>>+ if (seg == blk_rq_nr_phys_segments(req)) {
>>>>+ sector_in = bio->bi_iter.bi_sector;
>>>>+ if (rem != bio->bi_iter.bi_size)
>>>>+ return status;
>>>>+ } else {
>>>>+ sector_out = bio->bi_iter.bi_sector;
>>>>+ rem = bio->bi_iter.bi_size;
>>>>+ }
>>>>+ seg++;
>>>>+ }
>>>
>>>_rq_for_each_bio() iterates over the bios in a request. Does a copy
>>>offload request always have two bios - one copy destination bio and
>>>one copy source bio? If so, is 'seg' a bio counter? Why is that bio
>>>counter compared with the number of physical segments in the request?
>>>
>>Yes, your observation is right. We are treating first bio as dst and
>>second as src. If not for that comparision, we might need to store the
>>index in a temporary variable and parse based on index value.
>
>I'm still wondering why 'seg' is compared with blk_rq_nr_phys_segments(req).
>
In this case blk_rq_nr_phys_segments is used as counter value(==2), which tells
its a src IO. But using a macro instead of this comparison will avoid this
confusion. We will change this in next version to make it explicit.
Thank you,
Nitesh Shetty
© 2016 - 2025 Red Hat, Inc.