scsi: support packing multi-segment in UNMAP command
Subsystems (2)
PATCH v5 1/1 scsi: support packing multi-segment in UNMAP command
As SCSI SBC4 specification section 5.30.2 describes that it can support unmapping one or more LBA range in single UNMAP command.
However, previously we only pack one LBA range in UNMAP command by default no matter device gives the block limits that says it can support unmapping multiple LBA ranges with a single UNMAP command.
This patch sets max_discard_segments config according to block limits of device, and supports unmapping multiple LBA ranges with a single UNMAP command.
---
v5:
- fix to assign cmd->cmnd[7] and cmd->cmnd[8] w/ data_len correctly.
- fix to let ufshpb recognize and handle discard request which contains multiple ranges correctly.
drivers/scsi/sd.c | 36 +++++++++++++++++++++++++----------- drivers/scsi/sd.h | 1 + drivers/ufs/core/ufshpb.c | 21 +++++++++++++++++++-- 3 files changed, 45 insertions(+), 13 deletions(-)
drivers/scsi/sd.c +25 -11
@@ -792,6 +792,8 @@ static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode) q->limits.discard_granularity =max (sdkp->physical_block_size, sdkp->unmap_granularity * logical_block_size); +blk_queue_max_discard_segments (q,min_t (u32,U16_MAX , + sdkp->max_unmap_block_desc_count)); sdkp->provisioning_mode = mode;switch (mode) {
@@ -851,9 +853,10 @@ static blk_status_t sd_setup_unmap_cmnd(struct scsi_cmnd *cmd)struct scsi_device *sdp = cmd->device;struct request *rq =scsi_cmd_to_rq (cmd);struct scsi_disk *sdkp =scsi_disk (rq->q->disk); -u64 lba =sectors_to_logical (sdp,blk_rq_pos (rq)); -u32 nr_blocks =sectors_to_logical (sdp,blk_rq_sectors (rq)); -unsigned int data_len =24 ; +unsigned short segments =blk_rq_nr_discard_segments (rq); +unsigned int data_len =8 +16 * segments; +unsigned int descriptor_offset =8 ; +struct bio *bio;char *buf; buf =sd_set_special_bvec (rq, data_len);
@@ -862,12 +865,20 @@ static blk_status_t sd_setup_unmap_cmnd(struct scsi_cmnd *cmd) cmd->cmd_len =10 ; cmd->cmnd[0 ] =UNMAP ; - cmd->cmnd[8 ] =24 ; + cmd->cmnd[7 ] = data_len >>8 ; + cmd->cmnd[8 ] = data_len &0xff ; + +put_unaligned_be16 (6 +16 * segments, &buf[0 ]); +put_unaligned_be16 (16 * segments, &buf[2 ]); -put_unaligned_be16 (6 +16 , &buf[0 ]); -put_unaligned_be16 (16 , &buf[2 ]); -put_unaligned_be64 (lba, &buf[8 ]); -put_unaligned_be32 (nr_blocks, &buf[16 ]); +__rq_for_each_bio (bio, rq) { +u64 lba =sectors_to_logical (sdp, bio->bi_iter.bi_sector); +u32 nr_blocks =sectors_to_logical (sdp,bio_sectors (bio)); + +put_unaligned_be64 (lba, &buf[descriptor_offset]); +put_unaligned_be32 (nr_blocks, &buf[descriptor_offset +8 ]); + descriptor_offset +=16 ; + } cmd->allowed = sdkp->max_retries; cmd->transfersize = data_len;
@@ -2917,7 +2928,7 @@ static void sd_read_block_limits(struct scsi_disk *sdkp) sdkp->opt_xfer_blocks =get_unaligned_be32 (&vpd->data[12 ]);if (vpd->len >=64 ) { -unsigned int lba_count, desc_count; +unsigned int lba_count; sdkp->max_ws_blocks = (u32 )get_unaligned_be64 (&vpd->data[36 ]);
@@ -2925,9 +2936,12 @@ static void sd_read_block_limits(struct scsi_disk *sdkp) goto out; lba_count =get_unaligned_be32 (&vpd->data[20 ]); - desc_count =get_unaligned_be32 (&vpd->data[24 ]); -if (lba_count && desc_count) +/* Extract the MAXIMUM UNMAP BLOCK DESCRIPTOR COUNT. */ + sdkp->max_unmap_block_desc_count = +get_unaligned_be32 (&vpd->data[24 ]); + +if (lba_count && sdkp->max_unmap_block_desc_count) sdkp->max_unmap_blocks = lba_count; sdkp->unmap_granularity =get_unaligned_be32 (&vpd->data[28 ]);
drivers/scsi/sd.h +1 -0
@@ -119,6 +119,7 @@ struct scsi_disk {u32 opt_xfer_blocks;u32 max_ws_blocks;u32 max_unmap_blocks; +u32 max_unmap_block_desc_count;u32 unmap_granularity;u32 unmap_alignment;u32 index;
drivers/ufs/core/ufshpb.c +19 -2
@@ -383,13 +383,30 @@ int ufshpb_prep(struct ufs_hba *hba, struct ufshcd_lrb *lrbp) rgn = hpb->rgn_tbl + rgn_idx; srgn = rgn->srgn_tbl + srgn_idx; -/* If command type is WRITE or DISCARD, set bitmap as dirty */ -if (ufshpb_is_write_or_discard (cmd)) { +/* If command type is WRITE, set bitmap as dirty */ +if (op_is_write (req_op (scsi_cmd_to_rq (cmd)))) {ufshpb_iterate_rgn (hpb, rgn_idx, srgn_idx, srgn_offset, transfer_len, true);return 0 ; } +/* If command type is DISCARD, set bitmap as dirty */ +if (op_is_discard (req_op (scsi_cmd_to_rq (cmd)))) { +struct bio *bio; + +__rq_for_each_bio (bio,scsi_cmd_to_rq (cmd)) { + lpn =sectors_to_logical (cmd->device, + bio->bi_iter.bi_sector); + transfer_len =sectors_to_logical (cmd->device, +bio_sectors (bio)); +ufshpb_get_pos_from_lpn (hpb, lpn, &rgn_idx, + &srgn_idx, &srgn_offset); +ufshpb_iterate_rgn (hpb, rgn_idx, srgn_idx, + srgn_offset, transfer_len, true); + } +return 0 ; + } +if (!ufshpb_is_supported_chunk (hpb, transfer_len))return 0 ;
Signature · 1 line
2.25.1
drivers/ufs/core/ufshpb.c int ufshpb_prep(struct ufs_hba *hba, struct ufshcd_lrb *lrbp) · line 387
Quoted 4 lines
drivers/ufs/core/ufshpb.c +2
-2-/* If command type is WRITE or DISCARD, set bitmap as dirty */ -if (ufshpb_is_write_or_discard (cmd)) { +/* If command type is WRITE, set bitmap as dirty */ +if (op_is_write (req_op (scsi_cmd_to_rq (cmd)))) {
Umm, a driver has absolutely no business poking into the UNMAP
payload. Someone needs to fix the UFS driver first to not do this.
Quoted 7 lines · Christoph Hellwig
drivers/ufs/core/ufshpb.c int ufshpb_prep(struct ufs_hba *hba, struct ufshcd_lrb *lrbp) · line 387
Quoted 4 lines
drivers/ufs/core/ufshpb.c +2
-2-/* If command type is WRITE or DISCARD, set bitmap as dirty */ -if (ufshpb_is_write_or_discard (cmd)) { +/* If command type is WRITE, set bitmap as dirty */ +if (op_is_write (req_op (scsi_cmd_to_rq (cmd)))) {Umm, a driver has absolutely no business poking into the UNMAP
payload. Someone needs to fix the UFS driver first to not do this.
IIUC,originally, HPB driver tries to lookup LBA range{,s} from WRITE/DISCARD request, and will dirty mapped HPB regions based on LBA range{,s}, do you mean HPB driver should not parse DISCARD request?
Quoted 3 lines · Chao Yu
IIUC,originally, HPB driver tries to lookup LBA range{,s} from WRITE/DISCARD request, and will dirty mapped HPB regions based on LBA range{,s}, do you mean HPB driver should not parse DISCARD request?
Eww.. This just means we really need to drop this bogus HPB code. It will otherwise break every single time when a new SCSI command get added that modifies LBA content.
SCSI maintainers,
Any comments on this patch?
To Christoph, should I just drop HPB part change?
Quoted 149 lines · Chao Yu
As SCSI SBC4 specification section 5.30.2 describes that it can support unmapping one or more LBA range in single UNMAP command.
However, previously we only pack one LBA range in UNMAP command by default no matter device gives the block limits that says it can support unmapping multiple LBA ranges with a single UNMAP command.
This patch sets
max_discard_segmentsconfig according to block limits of device, and supports unmapping multiple LBA ranges with a single UNMAP command.Signed-off-by Chao Yu <[email protected]>---
v5:
- fix to assign cmd->cmnd[7] and cmd->cmnd[8] w/data_lencorrectly.
- fix to let ufshpb recognize and handle discard request which contains multiple ranges correctly.drivers/scsi/sd.c | 36 +++++++++++++++++++++++++----------- drivers/scsi/sd.h | 1 + drivers/ufs/core/ufshpb.c | 21 +++++++++++++++++++-- 3 files changed, 45 insertions(+), 13 deletions(-)drivers/scsi/sd.c +25
-11@@ -792,6 +792,8 @@ static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode) q->limits.discard_granularity =max (sdkp->physical_block_size, sdkp->unmap_granularity * logical_block_size); +blk_queue_max_discard_segments (q,min_t (u32,U16_MAX , + sdkp->max_unmap_block_desc_count)); sdkp->provisioning_mode = mode;switch (mode) {@@ -851,9 +853,10 @@ static blk_status_t sd_setup_unmap_cmnd(struct scsi_cmnd *cmd)struct scsi_device *sdp = cmd->device;struct request *rq =scsi_cmd_to_rq (cmd);struct scsi_disk *sdkp =scsi_disk (rq->q->disk); -u64 lba =sectors_to_logical (sdp,blk_rq_pos (rq)); -u32 nr_blocks =sectors_to_logical (sdp,blk_rq_sectors (rq)); -unsigned int data_len =24 ; +unsigned short segments =blk_rq_nr_discard_segments (rq); +unsigned int data_len =8 +16 * segments; +unsigned int descriptor_offset =8 ; +struct bio *bio;char *buf; buf =sd_set_special_bvec (rq, data_len);@@ -862,12 +865,20 @@ static blk_status_t sd_setup_unmap_cmnd(struct scsi_cmnd *cmd) cmd->cmd_len =10 ; cmd->cmnd[0 ] =UNMAP ; - cmd->cmnd[8 ] =24 ; + cmd->cmnd[7 ] = data_len >>8 ; + cmd->cmnd[8 ] = data_len &0xff ; + +put_unaligned_be16 (6 +16 * segments, &buf[0 ]); +put_unaligned_be16 (16 * segments, &buf[2 ]); -put_unaligned_be16 (6 +16 , &buf[0 ]); -put_unaligned_be16 (16 , &buf[2 ]); -put_unaligned_be64 (lba, &buf[8 ]); -put_unaligned_be32 (nr_blocks, &buf[16 ]); +__rq_for_each_bio (bio, rq) { +u64 lba =sectors_to_logical (sdp, bio->bi_iter.bi_sector); +u32 nr_blocks =sectors_to_logical (sdp,bio_sectors (bio)); + +put_unaligned_be64 (lba, &buf[descriptor_offset]); +put_unaligned_be32 (nr_blocks, &buf[descriptor_offset +8 ]); + descriptor_offset +=16 ; + } cmd->allowed = sdkp->max_retries; cmd->transfersize = data_len;@@ -2917,7 +2928,7 @@ static void sd_read_block_limits(struct scsi_disk *sdkp) sdkp->opt_xfer_blocks =get_unaligned_be32 (&vpd->data[12 ]);if (vpd->len >=64 ) { -unsigned int lba_count, desc_count; +unsigned int lba_count; sdkp->max_ws_blocks = (u32 )get_unaligned_be64 (&vpd->data[36 ]);@@ -2925,9 +2936,12 @@ static void sd_read_block_limits(struct scsi_disk *sdkp) goto out; lba_count =get_unaligned_be32 (&vpd->data[20 ]); - desc_count =get_unaligned_be32 (&vpd->data[24 ]); -if (lba_count && desc_count) +/* Extract the MAXIMUM UNMAP BLOCK DESCRIPTOR COUNT. */ + sdkp->max_unmap_block_desc_count = +get_unaligned_be32 (&vpd->data[24 ]); + +if (lba_count && sdkp->max_unmap_block_desc_count) sdkp->max_unmap_blocks = lba_count; sdkp->unmap_granularity =get_unaligned_be32 (&vpd->data[28 ]);drivers/scsi/sd.h +1
-0@@ -119,6 +119,7 @@ struct scsi_disk {u32 opt_xfer_blocks;u32 max_ws_blocks;u32 max_unmap_blocks; +u32 max_unmap_block_desc_count;u32 unmap_granularity;u32 unmap_alignment;u32 index;drivers/ufs/core/ufshpb.c +19
-2@@ -383,13 +383,30 @@ int ufshpb_prep(struct ufs_hba *hba, struct ufshcd_lrb *lrbp) rgn = hpb->rgn_tbl + rgn_idx; srgn = rgn->srgn_tbl + srgn_idx; -/* If command type is WRITE or DISCARD, set bitmap as dirty */ -if (ufshpb_is_write_or_discard (cmd)) { +/* If command type is WRITE, set bitmap as dirty */ +if (op_is_write (req_op (scsi_cmd_to_rq (cmd)))) {ufshpb_iterate_rgn (hpb, rgn_idx, srgn_idx, srgn_offset, transfer_len, true);return 0 ; } +/* If command type is DISCARD, set bitmap as dirty */ +if (op_is_discard (req_op (scsi_cmd_to_rq (cmd)))) { +struct bio *bio; + +__rq_for_each_bio (bio,scsi_cmd_to_rq (cmd)) { + lpn =sectors_to_logical (cmd->device, + bio->bi_iter.bi_sector); + transfer_len =sectors_to_logical (cmd->device, +bio_sectors (bio)); +ufshpb_get_pos_from_lpn (hpb, lpn, &rgn_idx, + &srgn_idx, &srgn_offset); +ufshpb_iterate_rgn (hpb, rgn_idx, srgn_idx, + srgn_offset, transfer_len, true); + } +return 0 ; + } +if (!ufshpb_is_supported_chunk (hpb, transfer_len))return 0 ;
Chao,
Quoted 3 lines
SCSI maintainers,
Any comments on this patch?
I have an updated version of your original multi-segment UNMAP support queued in a discard topic branch that I intend to submit shortly. Without the UFS HPB bits.
Signature · 1 line
Martin K. Petersen Oracle Linux Engineering
Quoted 11 lines · Martin K. Petersen
Chao,
Quoted 3 lines
SCSI maintainers,
Any comments on this patch?
I have an updated version of your original multi-segment UNMAP support queued in a discard topic branch that I intend to submit shortly. Without the UFS HPB bits.
Martin,
Any progress on this patch?
Chao,
Quoted 1 line
Any progress on this patch?
I'll resubmit this series for 6.6.
Signature · 1 line
Martin K. Petersen Oracle Linux Engineering
Quoted 6 lines · Martin K. Petersen
Chao,
Quoted 1 line
Any progress on this patch?
I'll resubmit this series for 6.6.
Martin,
Thank you!
Thanks,
Quoted 1 line
Quoted 1 line · Martin K. Petersen
I'll resubmit this series for 6.6.
Hi, Martin
Ping to avoid missing this patch in 6.6. :)
Thanks,
Ping,
Quoted 7 lines · Martin K. Petersen
Chao,
Quoted 1 line
Any progress on this patch?
I'll resubmit this series for 6.6.
Chao,
Quoted 2 lines
Quoted 2 lines
Quoted 1 line
Any progress on this patch?
I'll resubmit this series for 6.6.
Been working on this series to address the reported regressions. Spent quite a bit of time on it last week.
Signature · 1 line
Martin K. Petersen Oracle Linux Engineering
Quoted 2 lines · Martin K. Petersen
Been working on this series to address the reported regressions. Spent quite a bit of time on it last week.
Martin, thanks for the help. :)
Could you please share the report? Maybe I can join to check it.
Thanks,
Quoted 7 lines · Chao Yu
Quoted 2 lines · Martin K. Petersen
Been working on this series to address the reported regressions. Spent quite a bit of time on it last week.
Martin, thanks for the help. :)
Could you please share the report? Maybe I can join to check it.
Oh, I may misunderstand it, the reported regression wasn't caused by this patch, right?
Thanks,
Quoted 2 lines
Thanks,
Quoted 7 lines · Chao Yu
Quoted 2 lines · Martin K. Petersen
Been working on this series to address the reported regressions. Spent quite a bit of time on it last week.
Martin, thanks for the help. :)
Could you please share the report? Maybe I can join to check it.
It looks we will miss another merge window again... :(
Not sure I understand it correctly...
If this patch caused regression, could you please share the report w/ me?
Thanks,
Quoted 2 lines
Thanks,
Hi Martin,
Is it possible to commit this patch only to catch up 6.7-rc1, w/o other changes in 5.20/discovery? I don't feel there is any strong correlation between them, or am I missing something?
Thanks,
Quoted 9 lines · Martin K. Petersen
Chao,
Quoted 2 lines
Quoted 2 lines
Quoted 1 line
Any progress on this patch?
I'll resubmit this series for 6.6.
Been working on this series to address the reported regressions. Spent quite a bit of time on it last week.