linux-kernel - [PATCH 0/2] tcm: Add WRITE_SAME_16 support w/ UNMAP=1 emulation

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>] [day] [month] [year] [list]

Date:	Sat,  2 Oct 2010 17:53:32 -0700
From:	"Nicholas A. Bellinger" <nab@...ux-iscsi.org>
To:	linux-scsi <linux-scsi@...r.kernel.org>,
	linux-kernel <linux-kernel@...r.kernel.org>,
	Boaz Harrosh <bharrosh@...asas.com>,
	"Martin K. Petersen" <martin.petersen@...cle.com>,
	Douglas Gilbert <dgilbert@...erlog.com>
Cc:	FUJITA Tomonori <fujita.tomonori@....ntt.co.jp>,
	Mike Christie <michaelc@...wisc.edu>,
	Hannes Reinecke <hare@...e.de>,
	James Bottomley <James.Bottomley@...e.de>,
	Nicholas Bellinger <nab@...ux-iscsi.org>
Subject: [PATCH 0/2] tcm: Add WRITE_SAME_16 support w/ UNMAP=1 emulation

From: Nicholas Bellinger <nab@...ux-iscsi.org>

Greetings all,

This series adds initial support for WRITE_SAME_16 w/ UNMAP=1 emulation into
TCM/IBLOCK and TCM/FILEIO subsystem plugins using generic Block Discard logic.
This also includes proper TCM/pSCSI passthrough support to handle all possible
flavours of WRITE_SAME_16 for underlying HW that supports it.

The main items to note here for the IBLOCK+FILEIO emulated (eg: not passthrough)
case are:

	*) WRITE_SAME_16 w/ PBDATA and LBDATA will return INVALID_FIELD_IN_CDB
	*) WRITE_SAME_16 w/o UNMAP=1 will return INVALID_FIELD_IN_CDB
	*) WRITE_SAME_16 w/ UNMAP=1 will make IBLOCK+FILEIO call
	   transport_generic_write_same(), and not actually write the
	   received payload.

The first patch adds the main WRITE_SAME_16 pieces into TCM_Core, adds the new
emulate_tpws device attribute, and updates Block Limits VPD, Thin Provisioning
VPD and READ_CAPACITY_* to take emulate_tpws=1 into account to signal/handle
SBC-3 TPE=1 operation.

The second patch adds support into IBLOCK + FILEIO for using the TCM Core provided
transport_generic_write_same(), and will set both DEV_ATTRIB(dev)->emulate_tp[ws,u]=1
when blk_queue_discard()==1 signals underlying HW supports some flavour of TPE.

So far this series been tested with TCM_Loop -> (IBLOCK,FILEIO,pSCSI) -> scsi_debug
on v2.6.36-rc6 using explict 'sg_write_same -S' callers via SG_IO.

Once again, many thanks to mkp for sharing his knowledge of this area!

Signed-off-by: Nicholas A. Bellinger <nab@...ux-iscsi.org>

Nicholas Bellinger (2):
  tcm: Add WRITE_SAME_16 emulation and passthrough support
  tcm/iblock,fileio: Add WRITE_SAME_16 w/ UNMAP=1 bit support

 drivers/target/target_core_configfs.c  |    4 +
 drivers/target/target_core_device.c    |   15 +++++-
 drivers/target/target_core_file.c      |   47 +++++++++++++++-
 drivers/target/target_core_iblock.c    |   21 +++++++-
 drivers/target/target_core_transport.c |   99 ++++++++++++++++++++++++++++++--
 include/target/target_core_base.h      |    5 +-
 include/target/target_core_device.h    |    1 +
 include/target/target_core_transport.h |    6 ++
 8 files changed, 189 insertions(+), 9 deletions(-)

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/