On Fri, Jul 25, 2014 at 04:00:19PM -0400, Martin K. Petersen wrote:
> For bidirectional commands we need to be able to distinguish between the
> in and out scsi_data_buffers when calculating the wire transfer length.
> Make scsi_transfer_length() take a scsi_data_buffer argument so the
> caller can
I've pushed out new version of the for-3.17 core and drivers trees:
git://git.infradead.org/users/hch/scsi-queue.git core-for-3.17
git://git.infradead.org/users/hch/scsi-queue.git drivers-for-3.17
In the core tree the biggest update is the merge of the blk-mq
support, but various smaller upda
A set of flags introduced in the block layer enable better control over
how protection information is handled. These flags are useful for both
error injection and data recovery purposes. Checking can be enabled and
disabled for controller and disk, and the guard tag format is now a
per-I/O property
The protection interval is not necessarily tied to the logical block
size of a block device. Stop using the terms "sector" and "sectors".
Going forward we will use the term "seed" to describe the initial
reference tag value for a given I/O. "Interval" will be used to describe
the portion of the da
bip_buf is not really needed so we can remove it.
Signed-off-by: Martin K. Petersen
Reviewed-by: Christoph Hellwig
Reviewed-by: Sagi Grimberg
---
block/bio-integrity.c | 10 ++
include/linux/bio.h | 3 ---
2 files changed, 6 insertions(+), 7 deletions(-)
diff --git a/block/bio-inte
Make the choice of checksum a per-I/O property by introducing a flag
that can be inspected by the SCSI layer. There are several reasons for
this:
1. It allows us to switch choice of checksum without unloading and
reloading the HBA driver.
2. During error recovery we need to be able to tell
The T10 Protection Information format is also used by some devices that
do not go through the SCSI layer (virtual block devices, NVMe). Relocate
the relevant functions to a block layer library that can be used without
involving SCSI.
Signed-off-by: Martin K. Petersen
Reviewed-by: Christoph Hellwi
Add a BLK_ prefix to the integrity profile flags. Also rename the flags
to be more consistent with the generate/verify terminology in the rest
of the integrity code.
Signed-off-by: Martin K. Petersen
Reviewed-by: Christoph Hellwig
Reviewed-by: Sagi Grimberg
---
block/bio-integrity.c | 4 ++--
We'd occasionally merge requests with conflicting integrity flags.
Introduce a merge helper which checks that the requests have compatible
integrity payloads.
Signed-off-by: Martin K. Petersen
Reviewed-by: Christoph Hellwig
Reviewed-by: Sagi Grimberg
---
block/blk-integrity.c | 36 +++
Instead of the "operate" parameter we pass in a seed value and a pointer
to a function that can be used to process the integrity metadata. The
generation function is changed to have a return value to fit into this
scheme.
Signed-off-by: Martin K. Petersen
Reviewed-by: Sagi Grimberg
---
block/bi
Move flags affecting the integrity code out of the bio bi_flags and into
the block integrity payload.
Signed-off-by: Martin K. Petersen
Reviewed-by: Sagi Grimberg
---
block/bio-integrity.c | 4 ++--
drivers/scsi/sd_dif.c | 4 ++--
include/linux/bio.h | 9 -
include/linux/b
So far we have relied on the app tag size to determine whether a disk
has been formatted with T10 protection information or not. However, not
all target devices provide application tag storage.
Add a flag to the block integrity profile that indicates whether the
disk has been formatted with protec
None of the filesystems appear interested in using the integrity tagging
feature. Potentially because very few storage devices actually permit
using the application tag space.
Remove the tagging functions.
Signed-off-by: Martin K. Petersen
Reviewed-by: Christoph Hellwig
---
Documentation/block
Now that the protection interval has been detached from the sector size
we need to be able to handle sizes that are different from 4K and
512. Make the interval calculation generic.
Signed-off-by: Martin K. Petersen
---
block/bio-integrity.c | 6 +-
1 file changed, 1 insertion(+), 5 deletion
bdev_integrity_enabled() is only used by bio_integrity_enabled().
Combine these two functions.
Signed-off-by: Martin K. Petersen
Reviewed-by: Christoph Hellwig
Reviewed-by: Sagi Grimberg
---
Documentation/block/data-integrity.txt | 10 -
block/bio-integrity.c | 39
This is the data integrity patch series originally submitted for 3.16.
It has been rebased on top of the current 3.17 SCSI queue tree. I
believe I have addressed all the changes requested in the reviews. Aside
from a code cleanup in the sd prot_op code there are no functional
changes.
- bi_specia
For commands like REQ_COPY we need a way to pass extra information along
with each bio. Like integrity metadata this information must be
available at the bottom of the stack so bi_private does not suffice.
Rename the existing bi_integrity field to bi_special and make it a union
so we can have diff
For bidirectional commands we need to be able to distinguish between the
in and out scsi_data_buffers when calculating the wire transfer length.
Make scsi_transfer_length() take a scsi_data_buffer argument so the
caller can choose which I/O direction the calculation should apply to.
Signed-off-by:
On Fri, 25 Jul 2014, Joe Lawrence wrote:
On Fri, 25 Jul 2014 11:23:02 -0400
Chad Dupuis wrote:
On Wed, 18 Jun 2014, Joe Lawrence wrote:
Introduce mutual exclusion between the qla2xxx_remove_one PCI driver
callback and qla2x00_disable_board_on_pci_error, which is scheduled as
board_disabl
> "Sreekanth" == Sreekanth Reddy writes:
Sreekanth,
Sreekanth> Following are the changes that I have done in this patch over
Sreekanth> the first RDPQ support patch,
Please, please do the function moves in a different patch. Or use a
simple prototype declaration like I did to avoid moving t
> "Christoph" == Christoph Hellwig writes:
Christoph> Either someone who can actually test the hardware will have
Christoph> to come up with a similar hack for the blk-mq case, or we'll
Christoph> have to bite the bullet and fix the way the EH ioctls work
Christoph> for real, but until that h
hpsa: Work In Progress: "lockless monster" patches
To be clear, I am not suggesting that these patches be merged at this time.
This patchset is vs. Christoph Hellwig's scsi-mq.4 branch which
may be found here: git://git.infradead.org/users/hch/scsi.git
We've been working for a long time on a pa
> "Christoph" == Christoph Hellwig writes:
Christoph> This patch adds support for an alternate I/O path in the scsi
Christoph> midlayer which uses the blk-mq infrastructure instead of the
Christoph> legacy request code.
Reviewed-by: Martin K. Petersen
--
Martin K. Petersen Oracle Lin
> "Christoph" == Christoph Hellwig writes:
Christoph> Blk-mq drivers usually preallocate their S/G list as part of
Christoph> the request, but if we want to support the very large S/G
Christoph> lists currently supported by the SCSI code that would tie up
Christoph> a lot of memory in the pre
> "Christoph" == Christoph Hellwig writes:
Christoph> Replace the calls to the various blk_end_request variants
Christoph> with opencode equivalents. Blk-mq is using a model that
Christoph> gives the driver control between the bio updates and the
Christoph> actual completion, and making the
> "Christoph" == Christoph Hellwig writes:
Christoph> This saves us an atomic operation for each I/O submission and
Christoph> completion for the usual case where the driver doesn't set a
Christoph> per-target can_queue value. Only a few iscsi hardware
Christoph> offload drivers set the per-
> "Christoph" == Christoph Hellwig writes:
Christoph> Seems like these counters are missing any sort of
Christoph> synchronization for updates, as a over 10 year old comment
Christoph> from me noted. Fix this by using atomic counters, and while
Christoph> we're at it also make sure they are
On Fri, 25 Jul 2014 11:23:02 -0400
Chad Dupuis wrote:
>
>
> On Wed, 18 Jun 2014, Joe Lawrence wrote:
>
> > Introduce mutual exclusion between the qla2xxx_remove_one PCI driver
> > callback and qla2x00_disable_board_on_pci_error, which is scheduled as
> > board_disable work by qla2x00_check_reg
On Fri, Jul 25, 2014 at 01:37:29PM +0200, jgr...@suse.com wrote:
> This series adds XEN pvSCSI support. With pvSCSI it is possible to use
> physical
> SCSI devices from a XEN domain.
>
> The support consists of a backend in the privileged Domain-0 doing the real
> I/O and a frontend in the unpriv
On Fri, 2014-07-25 at 16:47 +, KY Srinivasan wrote:
>
> > -Original Message-
> > From: Martin K. Petersen [mailto:martin.peter...@oracle.com]
> > Sent: Thursday, July 24, 2014 8:54 AM
> > To: Sitsofe Wheeler
> > Cc: Martin K. Petersen; Christoph Hellwig; KY Srinivasan;
> > gre...@linux
> "KY" == KY Srinivasan writes:
KY> For the pass through case, the host validates the request and passes
KY> the request to the device. However, not all scsi commands are
KY> passed through even though the device it is being passed through may
KY> support the command. WRITE_SAME is one such
> -Original Message-
> From: Martin K. Petersen [mailto:martin.peter...@oracle.com]
> Sent: Thursday, July 24, 2014 8:54 AM
> To: Sitsofe Wheeler
> Cc: Martin K. Petersen; Christoph Hellwig; KY Srinivasan;
> gre...@linuxfoundation.org; linux-ker...@vger.kernel.org;
> de...@linuxdriverproj
On Fri, 2014-07-25 at 15:46 +0100, James Bottomley wrote:
> On Fri, 2014-07-25 at 15:23 +0100, Pawel Moll wrote:
> > The host devices without a parent were "forcefully adopted"
> > by platform bus. This patch removes this assignment. In
> > effect the dev_dev may be NULL now, which means ISA.
> >
On Wed, 18 Jun 2014, Joe Lawrence wrote:
Introduce mutual exclusion between the qla2xxx_remove_one PCI driver
callback and qla2x00_disable_board_on_pci_error, which is scheduled as
board_disable work by qla2x00_check_reg{32,16}_for_disconnect:
* Leave the driver-specific data attached to the
On Fri, 2014-07-25 at 15:23 +0100, Pawel Moll wrote:
> The host devices without a parent were "forcefully adopted"
> by platform bus. This patch removes this assignment. In
> effect the dev_dev may be NULL now, which means ISA.
>
> Cc: James E.J. Bottomley
> Cc: linux-scsi@vger.kernel.org
> Signe
The host devices without a parent were "forcefully adopted"
by platform bus. This patch removes this assignment. In
effect the dev_dev may be NULL now, which means ISA.
Cc: James E.J. Bottomley
Cc: linux-scsi@vger.kernel.org
Signed-off-by: Pawel Moll
---
This patch is a part of effort to remove
Hi Martin,
Following are the changes that I have done in this patch over the
first RDPQ support patch,
1. Reduced the redundancy in the function
_base_release_memory_pools(), _base_allocate_memory_pools().
2. Set pci_set_consistent_dma_mask() to DMA_BIT_MASK(32). still I am
analysing whether this
From: Juergen Gross
Introduces the XEN pvSCSI backend. With pvSCSI it is possible for a XEN domU
to issue SCSI commands to a SCSI LUN assigned to that domU. The SCSI commands
are passed to the pvSCSI backend in a driver domain (usually Dom0) which is
owner of the physical device. This allows e.g.
From: Juergen Gross
Introduces the XEN pvSCSI frontend. With pvSCSI it is possible for a XEN domU
to issue SCSI commands to a SCSI LUN assigned to that domU. The SCSI commands
are passed to the pvSCSI backend in a driver domain (usually Dom0) which is
owner of the physical device. This allows e.g
On Tue, Jul 22, 2014 at 12:18:19AM -0400, Martin K. Petersen wrote:
> More nitpicking. In the two previous atomic conversion patches you kept
> %hu for the atomic_t. Here it's %d.
I'll fix it to use %d everywhere, given that's it's not an unsigned short
anymore.
--
To unsubscribe from this list:
From: Juergen Gross
Add myself as maintainer for the Xen pvSCSI stuff.
Signed-off-by: Juergen Gross
---
MAINTAINERS | 8
1 file changed, 8 insertions(+)
diff --git a/MAINTAINERS b/MAINTAINERS
index 86efa7e..53f84c3 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10046,6 +10046,14 @@ S
From: Juergen Gross
Add the definition of pvSCSI protocol used between the pvSCSI frontend in a
XEN domU and the pvSCSI backend in a XEN driver domain (usually Dom0).
This header was originally provided by Fujitsu for XEN based on Linux 2.6.18.
Changes are:
- added comment
- adapt to Linux style
This series adds XEN pvSCSI support. With pvSCSI it is possible to use physical
SCSI devices from a XEN domain.
The support consists of a backend in the privileged Domain-0 doing the real
I/O and a frontend in the unprivileged domU passing I/O-requests to the backend.
The code is taken (and adapt
Hi Eddie,
just want to add you to the CC list.
Some days ago the bnx2fc's maintainer email address has been updated,
this should be the new one: qlogic-storage-upstr...@qlogic.com
I tried to send this patch to the new address but I received the following
delivery failure notification:
In some cases, the fcoe_rx_list may contains multiple instances
of the same skb (the so called "shared skbs").
the bnx2fc_l2_rcv thread is a loop that extracts a skb from the list,
modifies (and destroys) its content and the proceed to the next one.
The problem is that if the skb is shared, the re
45 matches
Mail list logo
