From: Benjamin Herrenschmidt [EMAIL PROTECTED]
Date: Mon, 19 Nov 2007 16:35:23 +1100
I'm not sure what is the best way to fix that. Internally, I've done
some test whacking some cacheline_aligned in the scsi_cmnd data
structure to verify I no longer get random SLAB corruption when using my
Hi Hannes,
Can you tell me when these patches get in the kernel? Is that going to
be 2.6.24.x or can we expect them before that?
Sander
On Thu, 2007-11-15 at 10:13 +0100, Hannes Reinecke wrote:
Hi all,
this patchset adds some more abstraction to the multipath
hardware handlers.
- A
On Mon, Nov 19, 2007 at 04:35:23PM +1100, Benjamin Herrenschmidt wrote:
The other one I'm hitting now is that the SCSI layer nowadays embeds the
'nowadays'? It has always been so.
sense_buffer inside the scsi_cmnd structure without any kind of
alignment whatsoever. I've been hitting
On Mon, 2007-11-19 at 05:32 -0700, Matthew Wilcox wrote:
On Mon, Nov 19, 2007 at 04:35:23PM +1100, Benjamin Herrenschmidt wrote:
The other one I'm hitting now is that the SCSI layer nowadays embeds the
'nowadays'? It has always been so.
sense_buffer inside the scsi_cmnd structure
Oliver (or anybody else):
Adding dynamic (AKA runtime) power management to the SCSI core is
looking a little difficult. (Actually, since as far as I know the SCSI
specification takes no heed of power management, perhaps this should be
called idle-device management.)
Imagine a SCSI disk has been
On Mon, Nov 19, 2007 at 10:36:19AM -0500, Alan Stern wrote:
These are conflicting requirements. How can we send the START-STOP
UNIT commands to spin the disk up/down through the request queue while
delaying or failing all others?
You can insert commands at the head of a request queue.
On Mon, 19 Nov 2007, Matthew Wilcox wrote:
On Mon, Nov 19, 2007 at 10:36:19AM -0500, Alan Stern wrote:
These are conflicting requirements. How can we send the START-STOP
UNIT commands to spin the disk up/down through the request queue while
delaying or failing all others?
You can
On Mon, 19 Nov 2007, James Smart wrote:
Also, don't forget that you need to sequence spin-up. A jbod tower with
multiple drives all spinning up concurrently can overload the power
supply. Most towers avoid this at power-on by having drive jumpers
sequence the drives. This is a hard nut to
Alan Stern sez:
Sure. But that won't do any good if the requests get held on
the queue
(or failed immediately) because the disk is supposedly suspended.
Somehow those requests have to be allowed to proceed while all others
are forced to wait (or to fail).
Not a failure. Not ready is
Mark Lord wrote:
Fajun Chen wrote:
As a matter of fact, I'm using /dev/sg*. Due to the size of my test
application, I have not be able to compress it into a small and
publishable form. However, this issue can be easily reproduced on my
ARM XScale target using sg3_util code as follows:
1.
On Mon, 19 Nov 2007, Salyzyn, Mark wrote:
Alan Stern sez:
Sure. But that won't do any good if the requests get held on
the queue
(or failed immediately) because the disk is supposedly suspended.
Somehow those requests have to be allowed to proceed while all others
are forced to wait
James Chapman wrote:
Mark Lord wrote:
One way to deal with it in an embedded device, is to force the
application that's generating the I/O to self-throttle.
Or modify the device driver to self-throttle.
Does disk access have to be so interrupt driven? Could disk interrupt
handling be done
On Mon, 2007-11-19 at 11:46 -0500, Alan Stern wrote:
On Mon, 19 Nov 2007, Salyzyn, Mark wrote:
Alan Stern sez:
Sure. But that won't do any good if the requests get held on
the queue
(or failed immediately) because the disk is supposedly suspended.
Somehow those requests have to
SFF ATA controllers are peculiar in that...
1. it doesn't have reliable IRQ pending bit.
2. it doesn't have reliable IRQ mask bit.
3. some controllers tank the machine completely if status or data
register is accessed differently than the chip likes.
And 4. which is a killer for a lot
2.6.22-stable review patch. If anyone has any objections, please let us
know.
--
From: HighPoint Linux Team [EMAIL PROTECTED]
patch 0fec02c93f60fb44ba3a24a0d3e4a52521d34d3f in mainline.
avoid buffer overflow when returning sense data.
With current adapter firmware the driver
On Mon, Nov 19, 2007 at 10:19:12AM -0800, Greg Kroah-Hartman wrote:
2.6.22-stable review patch. If anyone has any objections, please let us
know.
Makes sense to backport this.
Acked-by: Matthew Wilcox [EMAIL PROTECTED]
--
Intel are signing my paycheques ... these opinions are still mine
On Mon, 19 Nov 2007, James Bottomley wrote:
Here's how it will work: scsi_prep_state_check() will see that the
device is in a suspended state (probably a substate of SDEV_QUIESCE).
The return value will depend on the type of suspend:
For manual suspend or system suspend, the
On Mon, Nov 19, 2007 at 02:16:12PM -0500, Alan Stern wrote:
Regarding this thread's original question, the best idea I've come up
with so far is to store an extra flag in the scsi_device structure
indicating that a suspend or resume transition is underway. When the
flag is set, commands with
On Mon, 19 Nov 2007, Matthew Wilcox wrote:
On Mon, Nov 19, 2007 at 02:16:12PM -0500, Alan Stern wrote:
Regarding this thread's original question, the best idea I've come up
with so far is to store an extra flag in the scsi_device structure
indicating that a suspend or resume transition is
On Mon, 2007-11-19 at 00:38 -0800, David Miller wrote:
From: Benjamin Herrenschmidt [EMAIL PROTECTED]
Date: Mon, 19 Nov 2007 16:35:23 +1100
I'm not sure what is the best way to fix that. Internally, I've done
some test whacking some cacheline_aligned in the scsi_cmnd data
structure
On Mon, 2007-11-19 at 05:32 -0700, Matthew Wilcox wrote:
On Mon, Nov 19, 2007 at 04:35:23PM +1100, Benjamin Herrenschmidt wrote:
The other one I'm hitting now is that the SCSI layer nowadays embeds the
'nowadays'? It has always been so.
Wasn't it kmalloc'ed at one point ?
sense_buffer
On Mon, 2007-11-19 at 09:09 -0600, James Bottomley wrote:
What other drivers do is DMA to their own allocation and then memcpy to
the sense buffer.
There is a movement to allocate the sense data as its own sg list, but
I don't think that patch has even been posted yet.
I'd like to
I'd like to be rid of it inside the command for various reasons: every
command has one of these, and they're expensive in the allocation (at 96
bytes). There's no reason we have to allocate and free that amount of
space with every command. In theory, the number of these is bounded at
the
On Mon, 19 Nov 2007 05:44:01 -0800 (PST)
[EMAIL PROTECTED] wrote:
http://bugzilla.kernel.org/show_bug.cgi?id=9405
Summary: iSCSI does not implement ordering guarantees required by
e.g. journaling filesystems
Product: IO/Storage
Version:
On Mon, 2007-11-19 at 12:50 -0800, Andrew Morton wrote:
On Mon, 19 Nov 2007 05:44:01 -0800 (PST)
[EMAIL PROTECTED] wrote:
http://bugzilla.kernel.org/show_bug.cgi?id=9405
Summary: iSCSI does not implement ordering guarantees required by
e.g. journaling
Andrew Morton wrote:
On Mon, 19 Nov 2007 05:44:01 -0800 (PST)
[EMAIL PROTECTED] wrote:
http://bugzilla.kernel.org/show_bug.cgi?id=9405
Summary: iSCSI does not implement ordering guarantees required by
e.g. journaling filesystems
Product: IO/Storage
On Mon, Nov 19, 2007 at 03:15:22PM -0600, Mike Christie wrote:
+iSCSI
It's traditional to use all-caps here, even when the normal
capitalisation is different. so I think this should be ISCSI.
Damned if I know why we have this convention, though.
+P: Mike Christie
+M: [EMAIL PROTECTED]
James Bottomley wrote:
On Mon, 2007-11-19 at 12:50 -0800, Andrew Morton wrote:
On Mon, 19 Nov 2007 05:44:01 -0800 (PST)
[EMAIL PROTECTED] wrote:
http://bugzilla.kernel.org/show_bug.cgi?id=9405
Summary: iSCSI does not implement ordering guarantees required by
Matthew Wilcox wrote:
On Mon, Nov 19, 2007 at 03:15:22PM -0600, Mike Christie wrote:
+iSCSI
It's traditional to use all-caps here, even when the normal
capitalisation is different. so I think this should be ISCSI.
Damned if I know why we have this convention, though.
Thanks. Here is a
On Mon, 2007-11-19 at 15:22 -0600, Mike Christie wrote:
James Bottomley wrote:
On Mon, 2007-11-19 at 12:50 -0800, Andrew Morton wrote:
On Mon, 19 Nov 2007 05:44:01 -0800 (PST)
[EMAIL PROTECTED] wrote:
http://bugzilla.kernel.org/show_bug.cgi?id=9405
Summary: iSCSI does
I've been debugging various issues on the PowerPC 44x embedded
architecture which happens to have non-coherent PCI DMA.
One of the problem I'm hitting is that one really need to enforce
kmalloc alignement to cache lines or bad things will happen (among
others with USB), for some
On Mon, 2007-11-19 at 13:43 -0800, Roland Dreier wrote:
I've been debugging various issues on the PowerPC 44x embedded
architecture which happens to have non-coherent PCI DMA.
One of the problem I'm hitting is that one really need to enforce
kmalloc alignement to cache lines or bad
Patch 1 of 3
This patch creates more sysfs attributes to be exported by cciss. Hopefully
we can work better with udev. Please consider this patch for inclusion.
Signed-off-by: Mike Miller [EMAIL PROTECTED]
diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c
index 7d70496..2ba5a89 100644
Patch 2 of 3
This patch adds support for the blktrace utility. Please consider this for
inclusion. Seems there was already a call to blk_add_trace. This patch adds
ifdef's and includes the header file.
Signed-off-by: Mike Miller [EMAIL PROTECTED]
diff --git a/drivers/block/cciss.c
Patch 3 of 3
This patch bumps the version of the driver from .14 to .18 to more closely
match the driver that HP ships. This driver already supports all the
hardware that the HP 3.6.18 version supports. So the versions should match,
also. Please consider this for inclusion.
Signed-off-by: Mike
From: Benjamin Herrenschmidt [EMAIL PROTECTED]
Date: Tue, 20 Nov 2007 06:51:14 +1100
On Mon, 2007-11-19 at 00:38 -0800, David Miller wrote:
From: Benjamin Herrenschmidt [EMAIL PROTECTED]
Date: Mon, 19 Nov 2007 16:35:23 +1100
You could make a dma_cacheline_aligned and use that.
It
On Mon, Nov 19, 2007 at 11:38:35AM -0700, Matthew Wilcox wrote:
On Mon, Nov 19, 2007 at 10:19:12AM -0800, Greg Kroah-Hartman wrote:
2.6.22-stable review patch. If anyone has any objections, please let us
know.
Makes sense to backport this.
Acked-by: Matthew Wilcox [EMAIL PROTECTED]
On Mon, 2007-11-19 at 14:31 -0800, David Miller wrote:
From: Benjamin Herrenschmidt [EMAIL PROTECTED]
Date: Tue, 20 Nov 2007 06:51:14 +1100
On Mon, 2007-11-19 at 00:38 -0800, David Miller wrote:
From: Benjamin Herrenschmidt [EMAIL PROTECTED]
Date: Mon, 19 Nov 2007 16:35:23 +1100
On Mon, 2007-11-19 at 16:46 -0800, David Miller wrote:
1) Require that entire buffers are commited by call sites,
and thus embedding DMA'd within non-DMA stuff isn't allowed
2) Add the __dma_cacheline_aligned tag.
But note that with #2 it could get quite ugly because the
alignment
From: Benjamin Herrenschmidt [EMAIL PROTECTED]
Date: Tue, 20 Nov 2007 11:55:01 +1100
BTW. What is the status nowadays with skb's ?
Good question.
Some drivers are problematic (or were) because they put
DMA descriptor chaining information at the head of the
buffer, but those have been fixed
Signed-off-by: Joe Perches [EMAIL PROTECTED]
---
drivers/scsi/lpfc/lpfc_attr.c |2 +-
drivers/scsi/lpfc/lpfc_ct.c |2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c
index 80a1121..d9d6791 100644
---
Signed-off-by: Joe Perches [EMAIL PROTECTED]
---
drivers/scsi/aic94xx/aic94xx_sds.c |4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/scsi/aic94xx/aic94xx_sds.c
b/drivers/scsi/aic94xx/aic94xx_sds.c
index 06509bf..f45f0b9 100644
---
Signed-off-by: Joe Perches [EMAIL PROTECTED]
---
drivers/scsi/aic7xxx/aic79xx_osm.c |2 +-
drivers/scsi/aic7xxx/aic79xx_osm_pci.c |2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/scsi/aic7xxx/aic79xx_osm.c
b/drivers/scsi/aic7xxx/aic79xx_osm.c
index
Signed-off-by: Joe Perches [EMAIL PROTECTED]
---
drivers/scsi/qla4xxx/ql4_init.c |2 +-
drivers/scsi/qla4xxx/ql4_os.c |4 ++--
2 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/scsi/qla4xxx/ql4_init.c b/drivers/scsi/qla4xxx/ql4_init.c
index d692c71..ab619a8 100644
Signed-off-by: Joe Perches [EMAIL PROTECTED]
---
drivers/scsi/qla4xxx/ql4_init.c |2 +-
drivers/scsi/qla4xxx/ql4_os.c |4 ++--
2 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/scsi/qla4xxx/ql4_init.c b/drivers/scsi/qla4xxx/ql4_init.c
index d692c71..ab619a8 100644
Signed-off-by: Joe Perches [EMAIL PROTECTED]
---
drivers/scsi/NCR_D700.c|2 +-
drivers/scsi/aic7xxx_old.c |2 +-
drivers/scsi/dc395x.c |2 +-
drivers/scsi/hosts.c |2 +-
drivers/scsi/iscsi_tcp.c |6 +++---
drivers/scsi/scsi_proc.c |2 +-
2) Add the __dma_cacheline_aligned tag.
But note that with #2 it could get quite ugly because the
alignment and size both have a minimum that needs to be
enforced, not just the alignment alone. So either:
struct foo {
unsigned int other_unrelated_stuff;
struct
On Mon, 2007-11-19 at 18:10 -0800, Roland Dreier wrote:
I wrapped this ugliness up inside the macro back in what I posted in
2002 (http://lkml.org/lkml/2002/6/12/234):
#define __dma_buffer __dma_buffer_line(__LINE__)
#define __dma_buffer_line(line) __dma_buffer_expand_line(line)
#define
FYI, Here's what I have for the SCSI change. I haven't updated drivers
to care for the new return code though, help appreciated with that as I
don't know much about these drivers.
Index: linux-work/drivers/scsi/scsi_error.c
===
---
On Mon, 19 Nov 2007 16:07:17 -0600 Mike Miller [EMAIL PROTECTED] wrote:
Patch 2 of 3
This patch adds support for the blktrace utility. Please consider this for
inclusion. Seems there was already a call to blk_add_trace. This patch adds
ifdef's and includes the header file.
Signed-off-by:
On Mon, 19 Nov 2007 16:03:07 -0600 Mike Miller [EMAIL PROTECTED] wrote:
Patch 1 of 3
This patch creates more sysfs attributes to be exported by cciss. Hopefully
we can work better with udev. Please consider this patch for inclusion.
It would be appropriate if the changelog were to describe
51 matches
Mail list logo
