Hi,
This may be petty question, but I am not really sure
about this.
When a I/O comes to the low level SCSI HBA driver
through enqueue() interface,
can it happen that I/O data memory is paged out or can
be paged out?
I mean, doing DMA mapping such as pci_map_single()
provides, just physical
o.k. I got the answer.
It is already been locked when it comes to the low
level HBA driver.
Thanks,
Parav
--- Parav Pandit [EMAIL PROTECTED] wrote:
Hi,
This may be petty question, but I am not really sure
about this.
When a I/O comes to the low level SCSI HBA driver
through enqueue()
This patch just makes the version number in ips.c and ips.h consistent. It
seems that this has been forgotten in a60768e2d43eb30a1adb8a119aeac35dc0d03ef6.
Signed-off-by: Bernhard Walle [EMAIL PROTECTED]
---
drivers/scsi/ips.h |6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
---
On Tue, Sep 04, 2007 at 04:16:26PM +0200, Bernhard Walle wrote:
This patch just makes the version number in ips.c and ips.h consistent. It
seems that this has been forgotten in
a60768e2d43eb30a1adb8a119aeac35dc0d03ef6.
A better fix would be to no longer have two different places defining a
Add the SMC LP, SUN EM and Adaptec 5405 cards to the aacraid
documentation list of supported products. These cards are picked up with
family match, so no associated code changes.
This attached patch is against current scsi-misc-2.6.
ObligatoryDisclaimer: Please accept my condolences regarding
Boaz raised my attention to this patchset today...
We suspect we'll still need the extern entry points for handling the bidi
request in the scsi_io_completion() path as we only want to call
end_that_request_chunk on req-next_rq and never
end_that_request_last.
(see
On Tue, Sep 04 2007, Halevy, Benny wrote:
Boaz raised my attention to this patchset today...
We suspect we'll still need the extern entry points for handling the bidi
request in the scsi_io_completion() path as we only want to call
end_that_request_chunk on req-next_rq and never
Hi Jens,
Thank you for the comments.
On Mon, 3 Sep 2007 09:45:45 +0200, Jens Axboe [EMAIL PROTECTED] wrote:
+extern int blk_end_request(struct request *rq, int uptodate, int nr_bytes);
+extern int __blk_end_request(struct request *rq, int uptodate, int
nr_bytes);
extern int
Hi,
On Tue, 4 Sep 2007 17:25:14 -0400, Halevy, Benny [EMAIL PROTECTED] wrote:
We suspect we'll still need the extern entry points for handling the bidi
request in the scsi_io_completion() path as we only want to call
end_that_request_chunk on req-next_rq and never
end_that_request_last.
9 matches
Mail list logo