linux-kernel - [PATCH 0/5] crypto: add IV generation templates

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Message-ID: <1531899055-29362-1-git-send-email-wangxiongfeng2@huawei.com>
Date:   Wed, 18 Jul 2018 15:30:50 +0800
From:   Xiongfeng Wang <wangxiongfeng2@...wei.com>
To:     <agk@...hat.com>, <snitzer@...hat.com>,
        <herbert@...dor.apana.org.au>
CC:     <dm-devel@...hat.com>, <linux-kernel@...r.kernel.org>,
        <wangxiongfeng2@...wei.com>, <broonie@...nel.org>, <arnd@...db.de>,
        <jonathan.cameron@...wei.com>
Subject: [PATCH 0/5] crypto: add IV generation templates

Currently, the iv generation algorithms are implemented in dm-crypt.c.
This patchset moves these algorithms from the dm layer to the kernel
crypto layer by implementing them as template ciphers so they
can be implemented in hardware for performance. We modify the dm layer
to send a whole 'bio' rather than a sector at a time, so the dm layer
needs to called into the crypto layer less times. Each bio contains an
in memory representation of physically contiguous disk blocks. The dm
layer sets up a chained scatterlist of these blocks split into physically
contiguous segments in memory so that DMA can be performed.

This patchset is based on the patchset originally started by
Binoy Jayan <binoy.jayan@...aro.org>
( crypto: Add IV generation algorithms
https://patchwork.kernel.org/patch/9803469/ )

I tested the performance of software implemented ciphers before and after
applying this patchset. The performance didn't change much except for 
slight regression when writting. The detail information is as follows.

The command I used:
cryptsetup -y -c aes-xts-plain -s 256 --hash sha256 luksFormat /dev/sdd1
cryptsetup -y -c aes-cbc-essiv:sha256 -s 256 --hash sha256 luksFormat /dev/sdd1
cryptsetup -y -c aes-cbc-benbi -s 256 --hash sha256 luksFormat /dev/sdd1

cryptsetup luksOpen /dev/sdd1 crypt_fun
time dd if=/dev/mapper/crypt_fun of=/dev/null bs=1M count=500 iflag=direct
time dd if=/dev/zero of=/dev/mapper/crypt_fun bs=1M count=500 oflag=direct

Performance comparision:
--------------------------------------------------------
algorithms	| before applying   | 	after applying
--------------------------------------------------------
		|  read  | write    |  read  | write
--------------------------------------------------------
aes-xts-plain 	| 145.34 | 145.09   | 145.89 | 144.2 
--------------------------------------------------------
aes-cbc-essiv 	| 146.87 | 144.62   | 146.74 | 143.41
--------------------------------------------------------
aes-cbc-benbi 	| 146.03 | 144.74   | 146.77 | 144.46
--------------------------------------------------------

Xiongfeng Wang (5):
  crypto: api - introduce API to (un)register a array of templates
  crypto: ccm - use template array registering API to simplify the code
  crypto: gcm - use template array registering API to simplify the code
  crypto: Add IV generation templates
  dm-crypt: modify dm-crypt to rely on IV generation templates

 crypto/Kconfig          |    7 +
 crypto/Makefile         |    1 +
 crypto/algapi.c         |   27 +
 crypto/ccm.c            |   82 +-
 crypto/gcm.c            |   76 +-
 crypto/geniv.c          | 2240 +++++++++++++++++++++++++++++++++++++++++++++++
 drivers/md/Kconfig      |    1 +
 drivers/md/dm-crypt.c   | 1697 ++++++++---------------------------
 include/crypto/algapi.h |    2 +
 include/crypto/geniv.h  |   47 +
 10 files changed, 2722 insertions(+), 1458 deletions(-)
 create mode 100644 crypto/geniv.c
 create mode 100644 include/crypto/geniv.h

-- 
1.7.12.4