[v37,0/4] scsi: ufs: Add Host Performance Booster Support

Message

Daejun Park June 11, 2021, 2:21 a.m. UTC

Changelog:

v36 -> v37
1. Fix wrong usage of find_next_bit API.
2. Address Barts' comments. (sysfs, documentation, return type)
3. Change HPB_MULTI_CHUNK_HIGH for 1MB-sized request.

v35 -> v36
1. Changed ppn variable type from u64 to __be64.
2. Added WARN_ON_ONCE() to check for HPB read IO size exceeded.

v34 -> v35
1. Addressed Bart's comments (type casting)
2. Rebase 5.14 scsi-queue

v33 -> v34
Fix warning about NULL check before some freeing functions is not needed.

v32 -> v33
1. Fix wrong usage of scsi_command_normalize_sense.
2. Addressed Bart's comments (func. name, type casting, parentheses)

v31 -> v32
Delete unused parameter of unmap API.

v30 -> v31
Delete unnecessary debug message.

v29 -> v30
1. Add support to reuse bio of pre-request.
2. Delete unreached code in the ufshpb_issue_map_req.

v28 -> v29
1. Remove unused variable that reported by kernel test robot.

v27 -> v28
1. Fix wrong return value of ufshpb_prep.

v26 -> v27
1. Fix wrong refernce of sense buffer in pre_req complete function.
2. Fix read_id error.
3. Fix chunk size checking for HPB 1.0.
4. Mute unnecessary messages before HPB initialization.

v25 -> v26
1. Fix wrong chunk size checking for HPB 1.0.
2. Fix wrong max data size for HPB single command.
3. Fix typo error.

v24 -> v25
1. Change write buffer API for unmap region.
2. Add checking hpb_enable for avoiding unnecessary memory allocation.
3. Change pr_info to dev_info.
4. Change default requeue timeout value for HPB read.
5. Fix wrong offset manipulation on ufshpb_prep_entry.

v23 -> v24
1. Fix build error reported by kernel test robot.

v22 -> v23
1. Add support compatibility of HPB 1.0.
2. Fix read id for single HPB read command.
3. Fix number of pre-allocated requests for write buffer.
4. Add fast path for response UPIU that has same LUN in sense data.
5. Remove WARN_ON for preventing kernel crash.
7. Fix wrong argument for read buffer command.

v21 -> v22
1. Add support processing response UPIU in suspend state.
2. Add support HPB hint from other LU.
3. Add sending write buffer with 0x03 after HPB init.

v20 -> v21
1. Add bMAX_DATA_SIZE_FOR_HPB_SINGLE_CMD attr. and fHPBen flag support.

v19 -> v20
1. Add documentation for sysfs entries of hpb->stat.
2. Fix read buffer command for under-sized sub-region.
3. Fix wrong condition checking for kick map work.
4. Delete redundant response UPIU checking.
5. Add LUN checking in response UPIU.
6. Fix possible deadlock problem due to runtime PM.
7. Add instant changing of sub-region state from response UPIU.
8. Fix endian problem in prefetched PPN.
9. Add JESD220-3A (HPB v2.0) support.

v18 -> 19
1. Fix null pointer error when printing sysfs from non-HPB LU.
2. Apply HPB read opcode in lrbp->cmd->cmnd (from Can Guo's review).
3. Rebase the patch on 5.12/scsi-queue.

v17 -> v18
Fix build error which reported by kernel test robot.

v16 -> v17
1. Rename hpb_state_lock to rgn_state_lock and move it to corresponding
patch.
2. Remove redundant information messages.

v15 -> v16
1. Add missed sysfs ABI documentation.

v14 -> v15
1. Remove duplicated sysfs ABI entries in documentation.
2. Add experiment result of HPB performance testing with iozone.

v13 -> v14
1. Cleanup codes by commentted in Greg's review.
2. Add documentation for sysfs entries (from Greg's review).
3. Add experiment result of HPB performance testing.

v12 -> v13
1. Cleanup codes by comments from Can Guo.
2. Add HPB related descriptor/flag/attributes in sysfs.
3. Change base commit from 5.10/scsi-queue to 5.11/scsi-queue.

v11 -> v12
1. Fixed to return error value when HPB fails to initialize pinned active 
region.
2. Fixed to disable HPB feature if HPB fails to allocate essential memory
and workqueue.
3. Fixed to change proper sub-region state when region is already evicted.

v10 -> v11
Add a newline at end the last line on Kconfig file.

v9 -> v10
1. Fixed 64-bit division error
2. Fixed problems commentted in Bart's review.

v8 -> v9
1. Change sysfs initialization.
2. Change reading descriptor during HPB initialization
3. Fixed problems commentted in Bart's review.
4. Change base commit from 5.9/scsi-queue to 5.10/scsi-queue.

v7 -> v8
Remove wrongly added tags.

v6 -> v7
1. Remove UFS feature layer.
2. Cleanup for sparse error.

v5 -> v6
Change base commit to b53293fa662e28ae0cdd40828dc641c09f133405

v4 -> v5
Delete unused macro define.

v3 -> v4
1. Cleanup.

v2 -> v3
1. Add checking input module parameter value.
2. Change base commit from 5.8/scsi-queue to 5.9/scsi-queue.
3. Cleanup for unused variables and label.

v1 -> v2
1. Change the full boilerplate text to SPDX style.
2. Adopt dynamic allocation for sub-region data structure.
3. Cleanup.

NAND flash memory-based storage devices use Flash Translation Layer (FTL)
to translate logical addresses of I/O requests to corresponding flash
memory addresses. Mobile storage devices typically have RAM with
constrained size, thus lack in memory to keep the whole mapping table.
Therefore, mapping tables are partially retrieved from NAND flash on
demand, causing random-read performance degradation.

To improve random read performance, JESD220-3 (HPB v1.0) proposes HPB
(Host Performance Booster) which uses host system memory as a cache for the
FTL mapping table. By using HPB, FTL data can be read from host memory
faster than from NAND flash memory. 

The current version only supports the DCM (device control mode).
This patch consists of 3 parts to support HPB feature.

1) HPB probe and initialization process
2) READ -> HPB READ using cached map information
3) L2P (logical to physical) map management

In the HPB probe and init process, the device information of the UFS is
queried. After checking supported features, the data structure for the HPB
is initialized according to the device information.

A read I/O in the active sub-region where the map is cached is changed to
HPB READ by the HPB.

The HPB manages the L2P map using information received from the
device. For active sub-region, the HPB caches through ufshpb_map
request. For the in-active region, the HPB discards the L2P map.
When a write I/O occurs in an active sub-region area, associated dirty
bitmap checked as dirty for preventing stale read.

HPB is shown to have a performance improvement of 58 - 67% for random read
workload. [1]

[1]:
https://www.usenix.org/conference/hotstorage17/program/presentation/jeong

Daejun Park (4):
  scsi: ufs: Introduce HPB feature
  scsi: ufs: L2P map management for HPB read
  scsi: ufs: Prepare HPB read for cached sub-region
  scsi: ufs: Add HPB 2.0 support

 Documentation/ABI/testing/sysfs-driver-ufs |  162 ++
 drivers/scsi/ufs/Kconfig                   |    9 +
 drivers/scsi/ufs/Makefile                  |    1 +
 drivers/scsi/ufs/ufs-sysfs.c               |   22 +
 drivers/scsi/ufs/ufs.h                     |   54 +-
 drivers/scsi/ufs/ufshcd.c                  |   74 +-
 drivers/scsi/ufs/ufshcd.h                  |   30 +
 drivers/scsi/ufs/ufshpb.c                  | 2380 ++++++++++++++++++++
 drivers/scsi/ufs/ufshpb.h                  |  277 +++
 9 files changed, 3007 insertions(+), 2 deletions(-)
 create mode 100644 drivers/scsi/ufs/ufshpb.c
 create mode 100644 drivers/scsi/ufs/ufshpb.h

Comments

Bart Van Assche June 11, 2021, 9:18 p.m. UTC | #1

On 6/10/21 7:21 PM, Daejun Park wrote:
> Changelog:

Does this patch series perhaps need to be rebased? This is what git am
reports against Martin's 5.14/scsi-staging branch:

$ git am ~/20210610-\[PATCH\ v37\ *
Applying: scsi: ufs: Introduce HPB feature
error: patch failed: drivers/scsi/ufs/ufshcd.c:24
error: drivers/scsi/ufs/ufshcd.c: patch does not apply
Patch failed at 0001 scsi: ufs: Introduce HPB feature
hint: Use 'git am --show-current-patch=diff' to see the failed patch
When you have resolved this problem, run "git am --continue".
If you prefer to skip this patch, run "git am --skip" instead.
To restore the original branch and stop patching, run "git am --abort".

$ patch -p1 < ~/20210610-\[PATCH\ v37\ 1_4\]\ scsi_\ ufs_\ Introduce\
HPB\ feature-10889.eml
patching file Documentation/ABI/testing/sysfs-driver-ufs
patching file drivers/scsi/ufs/Kconfig
patching file drivers/scsi/ufs/Makefile
patching file drivers/scsi/ufs/ufs-sysfs.c
patching file drivers/scsi/ufs/ufs.h
patching file drivers/scsi/ufs/ufshcd.c
Hunk #1 succeeded at 24 with fuzz 2.
Hunk #2 succeeded at 4985 (offset 20 lines).
Hunk #3 succeeded at 5013 (offset 20 lines).
Hunk #4 succeeded at 5041 (offset 20 lines).
Hunk #5 succeeded at 7123 with fuzz 2 (offset 15 lines).
Hunk #6 succeeded at 7523 (offset 12 lines).
Hunk #7 succeeded at 7551 (offset 12 lines).
Hunk #8 succeeded at 7792 (offset 12 lines).
Hunk #9 succeeded at 7938 (offset 12 lines).
Hunk #10 succeeded at 8087 (offset 12 lines).
Hunk #11 succeeded at 8135 (offset 12 lines).
Hunk #12 succeeded at 8839 (offset 12 lines).
Hunk #13 succeeded at 8964 (offset 12 lines).
Hunk #14 succeeded at 9042 (offset 12 lines).
patching file drivers/scsi/ufs/ufshcd.h
Hunk #1 succeeded at 641 (offset -2 lines).
Hunk #2 succeeded at 870 (offset -2 lines).
patching file drivers/scsi/ufs/ufshpb.c
patching file drivers/scsi/ufs/ufshpb.h

Thanks,

Bart.

Avri Altman June 13, 2021, 10:02 a.m. UTC | #2

> Does this patch series perhaps need to be rebased? This is what git am
> reports against Martin's 5.14/scsi-staging branch:
> 
> $ git am ~/20210610-\[PATCH\ v37\ *
> Applying: scsi: ufs: Introduce HPB feature
> error: patch failed: drivers/scsi/ufs/ufshcd.c:24
> error: drivers/scsi/ufs/ufshcd.c: patch does not apply
> Patch failed at 0001 scsi: ufs: Introduce HPB feature
> hint: Use 'git am --show-current-patch=diff' to see the failed patch
> When you have resolved this problem, run "git am --continue".
> If you prefer to skip this patch, run "git am --skip" instead.
> To restore the original branch and stop patching, run "git am --abort".
git am -3 seems to work.

Thanks,
Avri