[PATCH v4 0/7] hw/sd: Improve performance of read/write/erase

Christian Speich posted 7 patches 1 day, 8 hours ago
Patches applied successfully (tree, apply log)
git fetch https://github.com/patchew-project/qemu tags/patchew/20260417-sdcard-performance-b4-v4-0-119e66be10c2@avm.de
Maintainers: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>, "Philippe Mathieu-Daudé" <philmd@linaro.org>, Yanan Wang <wangyanan55@huawei.com>, Zhao Liu <zhao1.liu@intel.com>, Bin Meng <bmeng.cn@gmail.com>
hw/core/machine.c  |   5 +
hw/sd/core.c       |  53 ++++++--
hw/sd/sd.c         | 353 ++++++++++++++++++++++++++++++++++++++++-------------
hw/sd/sdhci.c      | 102 +++++++++-------
hw/sd/trace-events |   6 +-
include/hw/sd/sd.h |  22 ++--
6 files changed, 389 insertions(+), 152 deletions(-)
[PATCH v4 0/7] hw/sd: Improve performance of read/write/erase
Posted by Christian Speich 1 day, 8 hours ago
This patch series improves the performance of read/write/erase operations
on sdcards.

This is done by increasing the maximum buffer size that is worked on.
From 1 byte (master) to 512 bytes (commit 1-3) to larger than 512
(adma commit).

Testing on my system with fio I see the following rough performance
values in MiB/s.

              read write readwrite
       master:   6     6     3/  3
 first commit:  51    43    23/ 23
second commit: 392   180   144/143

Tested on a 2GiB raw image with:
  fio --filename=/dev/mmcblk0 --direct=1 --runtime=60 --time_based --bs=128k --rw={mode}

The adma values are somewhat unstable but always >100MiB/s, I'm not sure
why but I guess it has something to do with the host side caching.

The fifth commit fixes the DATA_STAT_AFTER_ERASE bit in SCR and
introduces an option to allow to erase blocks to 0x00.

The sixth commit optimizes block erase when erase-blocks-as-zero=true
is used, by passing the zeroing request down the to the block device.
Erasing 2GiB now takes 0.1s instead of 26s.

Signed-off-by: Christian Speich <c.speich@avm.de>
---
Changes in v4:
- Rebase onto master, no changes needed.
- Renames:
  - sd_blk_{read,write} -> sd_blk_{read,write}_bounce_buffer
  - sd_blk_{read,write}_direct -> sd_blk_{read,write}
  - to_erase -> erase_len
- Extract erase logic into sd_blk_erase helper
- Enable erase-blocks-as-zero by default. Add compat for 11.0 and below
  to keep it disabled.
- Add cleanup commit to update trace events.
- Link to v3: https://lore.kernel.org/qemu-devel/20260204-sdcard-performance-b4-v3-0-dc1cf172ee57@avm.de

Changes in v3:
- Rebase onto master, updating read/write path for newly added RBMP
- Split up commit 1 into multiple commits
  - change interface to allow "short" read/writes that are continued
    by the core later by calling again
- Link to v2: https://lore.kernel.org/qemu-devel/20251202-sdcard-performance-b4-v2-0-d42490b11322@avm.de

Changes in v2:
- Properly set DATA_STAT_AFTER_ERASE in SCR
- Add erase-blocks-as-zero option to allow the user to switch between
  0x00 and 0xFF for erased blocks.
- Link to v1: https://lore.kernel.org/qemu-devel/20250919-sdcard-performance-b4-v1-0-e1037e481a19@avm.de

---
Christian Speich (7):
      hw/sd: Switch read/write primitive to buf+len
      hw/sd/sd: Allow multi-byte read/write for generic paths
      hw/sd/sd: Use multi-byte/block writes for block path
      hw/sd/sdhci: Don't use bounce buffer for ADMA
      hw/sd/sdcard: Add erase-blocks-as-zero option.
      hw/sd/sdcard: Optimize erase blocks as zero.
      hw/sd: Update trace events for buf+len data

 hw/core/machine.c  |   5 +
 hw/sd/core.c       |  53 ++++++--
 hw/sd/sd.c         | 353 ++++++++++++++++++++++++++++++++++++++++-------------
 hw/sd/sdhci.c      | 102 +++++++++-------
 hw/sd/trace-events |   6 +-
 include/hw/sd/sd.h |  22 ++--
 6 files changed, 389 insertions(+), 152 deletions(-)
---
base-commit: da6c4fe60fee30dd77267764d55b38af9cb89d4b
change-id: 20250912-sdcard-performance-b4-d908bbb5a004

Best regards,
-- 
Christian Speich <c.speich@avm.de>