linux-kernel - [RFC 0/2] SRAMFS a direct mapped SRAM pages into user space

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: <20191004133855.17474-1-l.luba@partner.samsung.com>
Date:   Fri,  4 Oct 2019 15:38:53 +0200
From:   Lukasz Luba <l.luba@...tner.samsung.com>
To:     linux-kernel@...r.kernel.org, lukasz.luba@...num.com
Cc:     b.zolnierkie@...sung.com, m.szyprowski@...sung.com,
        s.nawrocki@...sung.com, Lukasz Luba <l.luba@...tner.samsung.com>
Subject: [RFC 0/2] SRAMFS a direct mapped SRAM pages into user space

Hi all,

This patch set tries to introduce a direct mapping mechanism of SRAM
memory regions directly into user space.
This is a draft of some reaserch work which I am going to continue.
Since it is my last day in the office I have publish it as a RFC.

Benefits of having SRAM memory in the user space:
- lower latency access
- lower power usage
- managable scratchpad which could be sharable between processes
- could be used toughether with dedicated instructions like dot product
  calculation

Regards,
Lukasz Luba

Lukasz Luba (2):
  DT: ARM: exynos: change SRAM device node
  dirvers & fs: add sram driver and sramfs

 arch/arm/boot/dts/exynos54xx.dtsi |  12 +-
 drivers/misc/Kconfig              |   7 +
 drivers/misc/Makefile             |   1 +
 drivers/misc/sram.h               |   1 +
 drivers/misc/sram_direct.c        | 863 ++++++++++++++++++++++++++++++
 include/uapi/linux/magic.h        |   1 +
 mm/memory.c                       |   5 +-
 7 files changed, 878 insertions(+), 12 deletions(-)
 create mode 100644 drivers/misc/sram_direct.c

-- 
2.17.1