linux-2.6
16 years agoIB/ipath: Clean up some comments
Dave Olson [Mon, 7 Jan 2008 05:02:34 +0000 (21:02 -0800)] 
IB/ipath: Clean up some comments

Signed-off-by: Dave Olson <dave.olson@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoIB/ipath: Export hardware counters more consistently
Ralph Campbell [Mon, 7 Jan 2008 05:02:34 +0000 (21:02 -0800)] 
IB/ipath: Export hardware counters more consistently

Various hardware counters are exported via the ipath file system (since
it is binary data).  The old file format was very dependent on the HW
offsets for these registers.  Newer HCA chips can have different
counters at different offsets.  This patch adds a level of indirection
to make the file format consistent across HCAs.

Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoIB/ipath: MAD performance sampling registers support
Ralph Campbell [Mon, 7 Jan 2008 05:02:33 +0000 (21:02 -0800)] 
IB/ipath: MAD performance sampling registers support

Add support for QLogic HCAs which have hardware performance sampling
registers for PortSamplesControl and PortSamplesResult MADs.

Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoIB/srp: Add identifying information to log messages
David Dillow [Mon, 7 Jan 2008 23:23:41 +0000 (18:23 -0500)] 
IB/srp: Add identifying information to log messages

When you have multiple targets, it gets really confusing when you try
to track down who did a reset when there is no identifying information
in the log message, especially when the same extension ID is mapped
through two different local IB ports.  So, add an identifier that can
be used to track back to which local IB port/remote target pair is the
one having problems.

Signed-off-by: David Dillow <dillowda@ornl.gov>
Acked-by: Pete Wyckoff <pw@osc.edu>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoIPoIB/CM: Enable SRQ support on HCAs that support fewer than 16 SG entries
Pradeep Satyanarayana [Fri, 21 Dec 2007 21:08:23 +0000 (13:08 -0800)] 
IPoIB/CM: Enable SRQ support on HCAs that support fewer than 16 SG entries

Some HCAs (such as ehca2) support SRQ, but only support fewer than 16 SG
entries for SRQs.  Currently IPoIB/CM implicitly assumes all HCAs will
support 16 SG entries for SRQs (to handle a 64K MTU with 4K pages). This
patch removes that restriction by limiting the maximum MTU in connected
mode to what the maximum number of SRQ SG entries allows.

This patch addresses <https://bugs.openfabrics.org/show_bug.cgi?id=728>

Signed-off-by: Pradeep Satyanarayana <pradeeps@linux.vnet.ibm.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoIB/srp: Enable SG list chaining
David Dillow [Wed, 19 Dec 2007 22:09:15 +0000 (17:09 -0500)] 
IB/srp: Enable SG list chaining

By default, the SCSI mid-layer seems to send down 512KB requests
(sg_tablesize = 256), with some requests occasionally combined. By
allowing the mid-layer to chain requests, we can easily grow to 1024KB
or larger -- I've tested 4096KB I/O requests with no problems.

I looked through the DMA paths on the hardware drivers to ensure they
could take advantage of the SG chaining, and it seems that every one
except ipath uses the system's DMA routines, which have been converted
to handle chaining.  ipath looks like it should be OK, but I have no
way to test it.

Signed-off-by: David Dillow <dillowda@ornl.gov>
[ Tested on ipath.  - Roland ]

Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoIB/srp: Respect target credit limit
David Dillow [Wed, 19 Dec 2007 22:08:43 +0000 (17:08 -0500)] 
IB/srp: Respect target credit limit

The current SRP initiator will send requests even if it has no credits
available.  The results of sending extra requests are vendor specific,
but on some devices, overrunning credits will cost 85% of peak
performance -- e.g. 100 MB/s vs 720 MB/s.  Other devices may just drop
the requests.

This patch will tell the SCSI midlayer to queue requests if there are
fewer than two credits remaining, and will not issue a task management
request if there are no credits remaining.  The mid-layer will retry
the queued command once an outstanding command completes.

The patch also removes the unlikely() in __srp_get_tx_iu(), as it is
not at all unlikely to hit this limit under heavy load.

Signed-off-by: David Dillow <dillowda@ornl.gov>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoIPoIB: improve IPv4/IPv6 to IB mcast mapping functions
Rolf Manderscheid [Mon, 10 Dec 2007 20:38:41 +0000 (13:38 -0700)] 
IPoIB: improve IPv4/IPv6 to IB mcast mapping functions

An IPoIB subnet on an IB fabric that spans multiple IB subnets can't
use link-local scope in multicast GIDs.  The existing routines that
map IP/IPv6 multicast addresses into IB link-level addresses hard-code
the scope to link-local, and they also leave the partition key field
uninitialised.  This patch adds a parameter (the link-level broadcast
address) to the mapping routines, allowing them to initialise both the
scope and the P_Key appropriately, and fixes up the call sites.

The next step will be to add a way to configure the scope for an IPoIB
interface.

Signed-off-by: Rolf Manderscheid <rvm@obsidianresearch.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoIB/ipath: Changes for fields moving from devdata to portdata
Dave Olson [Thu, 6 Dec 2007 08:28:02 +0000 (00:28 -0800)] 
IB/ipath: Changes for fields moving from devdata to portdata

This patch moves some arrays that were defined per-device to be
variables defined in the per context data structure, thus avoiding extra
kzalloc() calls.

Signed-off-by: Dave Olson <dave.olson@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoIB/ipath: Generalize some xxx_SHIFT macros
Dave Olson [Fri, 21 Dec 2007 09:50:59 +0000 (01:50 -0800)] 
IB/ipath: Generalize some xxx_SHIFT macros

In preparation for upcoming chips that have different values for
INFINIPATH_R_PORTENABLE_SHIFT, INFINIPATH_R_INTRAVAIL_SHIFT,
INFINIPATH_R_TAILUPD_SHIFT, and portcfg_shift, remove the shared
#defines and use device-specific variables instead.

Signed-off-by: Dave Olson <dave.olson@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoIB/ipath: kreceive uses portdata rather than devdata
Ralph Campbell [Thu, 20 Dec 2007 10:43:23 +0000 (02:43 -0800)] 
IB/ipath: kreceive uses portdata rather than devdata

kreceive is now portdata * instead of devdata * and other kreceive
related cleanups....

Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoIB/ipath: Cleanup ipath_get_egrbuf()
Ralph Campbell [Sat, 22 Dec 2007 00:47:04 +0000 (16:47 -0800)] 
IB/ipath: Cleanup ipath_get_egrbuf()

Remove an unused parameter and fix up the comment.

Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoIB/ipath: Fix RNR NAK handling
Ralph Campbell [Sat, 15 Dec 2007 03:22:34 +0000 (19:22 -0800)] 
IB/ipath: Fix RNR NAK handling

This patch fixes a couple of minor problems with RNR NAK handling:
 - The insertion sort was causing extra delay when inserting ahead
   vs. behind an existing entry on the list.
 - A resend of a first packet of a message which is still not ready,
   needs another RNR NAK (i.e., it was suppressed when it shouldn't).
 - Also, the resend tasklet doesn't need to be woken up unless the
   ACK/NAK actually indicates progress has been made.

Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoIB/ehca: Forward event client-reregister-required to registered clients
Hoang-Nam Nguyen [Thu, 20 Dec 2007 14:06:33 +0000 (15:06 +0100)] 
IB/ehca: Forward event client-reregister-required to registered clients

This patch allows ehca to forward event client-reregister-required to
registered clients.  One such event is generated by a switch eg. after
its reboot.

Signed-off-by: Hoang-Nam Nguyen <hnguyen@de.ibm.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoIB/mlx4: Micro-optimize mlx4_ib_poll_one()
Roland Dreier [Fri, 25 Jan 2008 22:15:34 +0000 (14:15 -0800)] 
IB/mlx4: Micro-optimize mlx4_ib_poll_one()

Rather than byte-swapping cqe->g_mlpath_rqpn each time we extract a
field from it, byte-swap it once into a temporary variable.  This
results in smaller, better code -- eg, on 32-bit x86:

add/remove: 0/0 grow/shrink: 0/1 up/down: 0/-5 (-5)
function                                     old     new   delta
mlx4_ib_poll_cq                             1188    1183      -5

Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoIB/mthca: Remove MSI support as scheduled
Adrian Bunk [Tue, 1 Jan 2008 13:47:10 +0000 (15:47 +0200)] 
IB/mthca: Remove MSI support as scheduled

Remove MSI support from the mthca driver, as scheduled.  There is no
reason to use MSI instead of MSI-X, since MSI-X performs better.  No
one has spoken up since MSI support was deprecated in commit f6be6fbe
("IB/mthca: Schedule MSI support for removal"), so apparently the MSI
support is unused.

Signed-off-by: Adrian Bunk <bunk@kernel.org>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoIB/iser: Typo fix (s/destory/destroy/)
Oliver Pinter [Fri, 25 Jan 2008 22:15:32 +0000 (14:15 -0800)] 
IB/iser: Typo fix (s/destory/destroy/)

Signed-off-by: Oliver Pinter <oliver.pntr@gmail.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoIB/iser: update URLs of iSER docs
Erez Zilber [Fri, 25 Jan 2008 22:15:32 +0000 (14:15 -0800)] 
IB/iser: update URLs of iSER docs

Signed-off-by: Erez Zilber <erezz@voltaire.com>
16 years agoRDMA/cma: add support for rdma_migrate_id()
Sean Hefty [Wed, 14 Nov 2007 08:29:50 +0000 (00:29 -0800)] 
RDMA/cma: add support for rdma_migrate_id()

This is based on user feedback from Doug Ledford at RedHat:

Events that occur on an rdma_cm_id are reported to userspace through an
event channel.  Connection request events are reported on the event
channel associated with the listen.  When the connection is accepted, a
new rdma_cm_id is created and automatically uses the listen event
channel.  This is suboptimal where the user only wants listen events on
that channel.

Additionally, it may be desirable to have events related to connection
establishment use a different event channel than those related to
already established connections.

Allow the user to migrate an rdma_cm_id between event channels. All
pending events associated with the rdma_cm_id are moved to the new event
channel.

Signed-off-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoRDMA/cma: Reenable device removal on passive side
Vladimir Sokolovsky [Sat, 8 Dec 2007 04:32:03 +0000 (20:32 -0800)] 
RDMA/cma: Reenable device removal on passive side

Enable conn_id remove on the passive side after connection
establishment.  This corrects an issue where the IB driver can't be
unloaded after running applications over RDS.  The 'dev_remove' counter
does not reach 0 for established connections on the passive side.

This problem is limited to device removal, and only occurs on the
passive side if there are established connections.

Signed-off-by: Vladimir Sokolovsky <vlad@mellanox.co.il>
Reviewed-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoIB/mad: Fix incorrect access to items on local_list
Sean Hefty [Sat, 1 Dec 2007 01:30:18 +0000 (17:30 -0800)] 
IB/mad: Fix incorrect access to items on local_list

In cancel_mads(), MADs are moved from the wait_list and local_list
to a cancel_list for processing.  However, the structures on these two
lists are not the same.  The wait_list references struct
ib_mad_send_wr_private, but local_list references struct
ib_mad_local_private.  Cancel_mads() treats all items moved to the
cancel_list as struct ib_mad_send_wr_private.  This leads to a system
crash when requests are moved from the local_list to the cancel_list.

Fix this by leaving local_list alone.  All requests on the local_list
have completed are just awaiting processing by a queued worker thread.

Bug (crash) reported by Dotan Barak <dotanb@dev.mellanox.co.il>.
Problem with local_list access reported by Robert Reynolds
<rreynolds@opengridcomputing.com>.

Signed-off-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoIB/cm: Add basic performance counters
Sean Hefty [Tue, 17 Jul 2007 04:49:35 +0000 (21:49 -0700)] 
IB/cm: Add basic performance counters

Add performance/debug counters to track sent/received messages, retries,
and duplicates.  Counters are tracked per CM message type, per port.

The counters are always enabled, so intrusive state tracking is not done.

Signed-off-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoIB/mad: Report number of times a mad was retried
Sean Hefty [Tue, 27 Nov 2007 08:11:04 +0000 (00:11 -0800)] 
IB/mad: Report number of times a mad was retried

To allow ULPs to tune timeout values and capture retry statistics,
report the number of times that a mad send operation was retried.

For RMPP mads, report the total number of times that the any portion
(send window) of the send operation was retried.

Signed-off-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoIB/multicast: Report errors on multicast groups if P_key changes
Sean Hefty [Tue, 23 Oct 2007 04:52:54 +0000 (21:52 -0700)] 
IB/multicast: Report errors on multicast groups if P_key changes

P_key changes can invalidate multicast groups.  Report errors on all
multicast groups affected by a pkey change.

Signed-off-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoIB: Spelling fixes in comments
Joe Perches [Mon, 17 Dec 2007 19:30:36 +0000 (11:30 -0800)] 
IB: Spelling fixes in comments

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agomlx4_core: Fix max_eqs masking in QUERY_DEV_CAP
Jack Morgenstein [Mon, 10 Dec 2007 03:25:23 +0000 (05:25 +0200)] 
mlx4_core: Fix max_eqs masking in QUERY_DEV_CAP

log_max_eqs is a 4-bit field, not a 3-bit field in the response to the
QUERY_DEV_CAP FW command, so we should mask with 0xf instead of 0x7
when reading it.

Found by Yossi Leybovitch of Mellanox.

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoIB/ipath: Convert from .nopage to .fault
Nick Piggin [Thu, 13 Dec 2007 23:58:57 +0000 (15:58 -0800)] 
IB/ipath: Convert from .nopage to .fault

Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoIB/ipath: Add the work completion error code to the QP error debug output
Ralph Campbell [Sat, 3 Nov 2007 00:40:36 +0000 (17:40 -0700)] 
IB/ipath: Add the work completion error code to the QP error debug output

Add the work completion error code to the QP error debug output.
This makes it easier to determine the cause of the error.

Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoIB/ipath: Better comment for rmb() in ipath_intr()
Arthur Jones [Thu, 18 Oct 2007 01:18:29 +0000 (18:18 -0700)] 
IB/ipath: Better comment for rmb() in ipath_intr()

An internal code review found the comment here lacking -- update it with
more specifics of how and why the rmb() is there.

Signed-off-by: Arthur Jones <arthur.jones@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoIB/ipath: Fix comments for ipath_create_srq()
Ralph Campbell [Tue, 27 Nov 2007 07:44:15 +0000 (23:44 -0800)] 
IB/ipath: Fix comments for ipath_create_srq()

During a code review, someone noticed the comments didn't match the code.

Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoIB/ipath: Fix error returned from ib_resize_cq if new size smaller than # entries
Ralph Campbell [Fri, 9 Nov 2007 03:53:01 +0000 (19:53 -0800)] 
IB/ipath: Fix error returned from ib_resize_cq if new size smaller than # entries

The gen2_basic tests check for the errno value when a CQ is resized
smaller than the number of outstanding completions queue on the CQ.
This patch changes ib_ipath to return EINVAL which is what ib_mthca
returns and what gen2_basic expects.

Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoIB/ipath: Fix sendctrl locking
John Gregor [Wed, 5 Sep 2007 08:57:14 +0000 (01:57 -0700)] 
IB/ipath: Fix sendctrl locking

Code review pointed out that the locking around uses of ipath_sendctrl
and kr_sendctrl were, in several places, incorrect and/or inconsistent.

Signed-off-by: John Gregor <john.gregor@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoIB/ipath: Remove dead code for user process waiting for send buffer
Ralph Campbell [Sat, 13 Oct 2007 03:48:06 +0000 (20:48 -0700)] 
IB/ipath: Remove dead code for user process waiting for send buffer

At one point in time there was code to allow a user process to
wait for a send buffer if none were available. This feature was
never used and most of the code was removed. This removes
some missed unused code.

Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoRDMA/cxgb3: Support version 5.0 firmware
Steve Wise [Mon, 26 Nov 2007 17:28:46 +0000 (11:28 -0600)] 
RDMA/cxgb3: Support version 5.0 firmware

The 5.0 firmware now supports translating sgls in recv work requests,
so remove the host driver logic currently doing the translation.

Note: this change requires 5.0 firmware.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoRDMA/cxgb3: Hold rtnl_lock() around ethtool get_drvinfo call
Steve Wise [Mon, 26 Nov 2007 17:28:44 +0000 (11:28 -0600)] 
RDMA/cxgb3: Hold rtnl_lock() around ethtool get_drvinfo call

Currently the call into cxgb3 to get the driver info is not serialized.
The iw_cxgb3 module needs to hold the rtnl_lock around the ethtool ops
call like dev_ioctl() does.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agodrivers/infiniband: Add missing "space"
Joe Perches [Tue, 20 Nov 2007 01:48:11 +0000 (17:48 -0800)] 
drivers/infiniband: Add missing "space"

Add missing spaces in the middle of format strings.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoIB/ipath: Convert ipath_eep_sem semaphore to a mutex
Matthias Kaehlcke [Thu, 15 Nov 2007 23:23:25 +0000 (15:23 -0800)] 
IB/ipath: Convert ipath_eep_sem semaphore to a mutex

Signed-off-by: Matthias Kaehlcke <matthias.kaehlcke@gmail.com>
Acked-by: Michael Albaugh <Michael.Albaugh@qlogic.com>
Tested-by: Arthur Jones <arthur.jones@qlogic.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoIB/mad: Enable loopback of DR SMP responses from userspace
Steve Welch [Tue, 23 Oct 2007 22:06:10 +0000 (15:06 -0700)] 
IB/mad: Enable loopback of DR SMP responses from userspace

The local loopback of an outgoing DR SMP response is limited to those
that originate at the driver specific SMA implementation during the
driver specific process_mad() function.  This patch enables a
returning DR SMP originating in userspace (or elsewhere) to be
delivered to the local managment stack.  In this specific case the
driver process_mad() function does not consume or process the MAD, so
a reponse mad has not be created and the original MAD must manually be
copied to the MAD buffer that is to be handed off to the local agent.

Signed-off-by: Steve Welch <swelch@systemfabricworks.com>
Acked-by: Hal Rosenstock <hal@xsigo.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoIB/ipath: Enable loopback of DR SMP responses from userspace
Ralph Campbell [Tue, 23 Oct 2007 22:07:41 +0000 (15:07 -0700)] 
IB/ipath: Enable loopback of DR SMP responses from userspace

This patch is in response to reviewing a patch to the core MAD
processing which fixes loopback of directed route packets to/from user
level MAD agents.  This change enables the core code to work for
ib_ipath by fixing the return code from the ipath process_mad method.

Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoIB/mad: Remove redundant NULL pointer check in ib_mad_recv_done_handler()
Ralph Campbell [Tue, 23 Oct 2007 22:04:15 +0000 (15:04 -0700)] 
IB/mad: Remove redundant NULL pointer check in ib_mad_recv_done_handler()

In ib_mad_recv_done_handler(), the response pointer is checked for
NULL after allocating it.  It is then checked again in the local
process_mad() path but there is no possibility of it changing in
between.

Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Acked-by: Hal Rosenstock <hal@xsigo.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoRDMA/iwcm: Set initiator depth and responder resources to device max values
Steve Wise [Mon, 29 Oct 2007 16:34:05 +0000 (11:34 -0500)] 
RDMA/iwcm: Set initiator depth and responder resources to device max values

Set the initiator depth and responder resources to the device max
values for new connect request events in the iWARP connection manager.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoIB/ipath: Improve interrupt handler cache footprint
Dave Olson [Wed, 10 Oct 2007 12:10:35 +0000 (05:10 -0700)] 
IB/ipath: Improve interrupt handler cache footprint

Improve interrupt handler cache footprint by noinline'ing error
functions that are rarely called.

Signed-off-by: Dave Olson <dave.olson@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoIPoIB/cm: Add connected mode support for devices without SRQs
Pradeep Satyanarayana [Fri, 25 Jan 2008 22:15:24 +0000 (14:15 -0800)] 
IPoIB/cm: Add connected mode support for devices without SRQs

Some IB adapters (notably IBM's eHCA) do not implement SRQs (shared
receive queues).  The current IPoIB connected mode support only works
on devices that support SRQs.

Fix this by adding support for using the receive queue of each
connected mode receive QP.  The disadvantage of this compared to using
an SRQ is that it means a full queue of receives must be posted for
each remote connected mode peer, which means that total memory usage
is potentially much higher than when using SRQs.  To manage this, add
a new module parameter "max_nonsrq_conn_qp" that limits the number of
connections allowed per interface.

The rest of the changes are fairly straightforward: we use a table of
struct ipoib_cm_rx to hold all the active connections, and put the
table index of the connection in the high bits of receive WR IDs.
This is needed because we cannot rely on the struct ib_wc.qp field for
non-SRQ receive completions.  Most of the rest of the changes just
test whether or not an SRQ is available, and post receives or find
received packets in the right place depending on the answer.

Cleaning up dead connections actually becomes simpler, because we do
not have to do the "last WQE reached" dance that is required to
destroy QPs attached to an SRQ.  We just move the QP to the error
state and wait for all pending receives to be flushed.

Signed-off-by: Pradeep Satyanarayana <pradeeps@linux.vnet.ibm.com>
[ Completely rewritten and split up, based on Pradeep's work.  Several
  bugs fixed and no doubt several bugs introduced.  - Roland ]

Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoIPoIB/cm: Factor out ipoib_cm_free_rx_reap_list()
Roland Dreier [Fri, 25 Jan 2008 22:15:24 +0000 (14:15 -0800)] 
IPoIB/cm: Factor out ipoib_cm_free_rx_reap_list()

Factor out the code for going through the rx_reap list of struct
ipoib_cm_rx and freeing each one.  This consolidates the code
duplicated between ipoib_cm_dev_stop() and ipoib_cm_rx_reap() and
reduces the risk of error when adding additional accounting.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoIPoIB/cm: Factor out ipoib_cm_create_srq()
Roland Dreier [Fri, 25 Jan 2008 22:15:24 +0000 (14:15 -0800)] 
IPoIB/cm: Factor out ipoib_cm_create_srq()

Factor out the code to create an SRQ and allocate the receive ring in
ipoib_cm_dev_init() into a new function ipoib_cm_create_srq().  This
will make the code neater when support for devices that don't implement
SRQs is added.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoIPoIB/cm: Factor out ipoib_cm_free_rx_ring()
Roland Dreier [Fri, 25 Jan 2008 22:15:24 +0000 (14:15 -0800)] 
IPoIB/cm: Factor out ipoib_cm_free_rx_ring()

Factor out the code to unmap/free skbs and free the receive ring in
ipoib_cm_dev_cleanup() into a new function ipoib_cm_free_rx_ring().
This function will be called from a couple of other places when
support for devices that don't implement SRQs is added.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoIPoIB: Trivial formatting cleanups
Roland Dreier [Wed, 24 Oct 2007 02:57:54 +0000 (19:57 -0700)] 
IPoIB: Trivial formatting cleanups

Fix whitespace blunders, convert "foo* bar" to "foo *bar", etc.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoIB/ipath: Fix crash on unload introduced by sysfs changes
Roland Dreier [Fri, 25 Jan 2008 22:15:21 +0000 (14:15 -0800)] 
IB/ipath: Fix crash on unload introduced by sysfs changes

Commit 23b9c1ab ("Infiniband: make ipath driver use default driver
groups.") introduced a bug in the ipath driver where
ipath_device_create_group() fell through into the error path, even on
success, which meant that the sysfs groups it created would always get
removed right away.  This made ipath_device_remove_group() hit the
BUG_ON() in sysfs_remove_group() when it tried to remove those groups a
second time.

Correct the return path so that the groups stick around until they are
supposed to be cleaned up.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
16 years agoMerge git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/v4l-dvb
Linus Torvalds [Fri, 25 Jan 2008 21:59:51 +0000 (13:59 -0800)] 
Merge git://git./linux/kernel/git/mchehab/v4l-dvb

* git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/v4l-dvb: (509 commits)
  V4L/DVB (7078): radio: fix sf16fmi section mismatch
  V4L/DVB (7077): bt878: remove handcrafted PCI subsystem ID check
  V4L/DVB (7075): Make a local function static
  V4L/DVB (7074): DiB7000P: correct tuning problem for 7MHz channel
  V4L/DVB (7073): DiB7070: Reception quality improved
  V4L/DVB (7072): sets the MT2060 IF1 frequency according to EEPROM
  V4L/DVB (7071): DiB0700: Start streaming the right way
  V4L/DVB (7070): Fix some tuning problems
  V4L/DVB (7069):  Support for myTV.t
  V4L/DVB (7068): Add support for WinTV Nova-T-CE driver
  V4L/DVB (7067): fix autoserach in the Hauppauge NOVA-T 500
  V4L/DVB (7066):  ASUS My Cinema U3000 Mini DVBT Tuner
  V4L/DVB (7065): Artec T14BR patches
  V4L/DVB (7063): xc5000: Fix OOPS caused by missing firmware
  V4L/DVB (7062): radio-si570x: Some fixes and new USB ID addition
  V4L/DVB (7061): radio-si470x: Some cleanups
  V4L/DVB (7060): em28xx: remove has_tuner
  V4L/DVB (7059): cx88: Ensure the tuner is reset correctly
  V4L/DVB (7058): IR corrections for the Pinnacle 800i
  V4L/DVB (7056): tuner: suppress obsolete tuner i2c address warning for XC5000 tuners
  ...

16 years agoMerge git://git.kernel.org/pub/scm/linux/kernel/git/bart/ide-2.6
Linus Torvalds [Fri, 25 Jan 2008 21:57:26 +0000 (13:57 -0800)] 
Merge git://git./linux/kernel/git/bart/ide-2.6

* git://git.kernel.org/pub/scm/linux/kernel/git/bart/ide-2.6: (67 commits)
  ide: remove redundant DMA blacklist check from __ide_dma_on()
  ide: cleanup ide_set_dma()
  ide: remove redundant ->ide_dma_on call from set_using_dma()
  sc1200: move DMA timings to timing tables
  ide: add IDE_HFLAG_ABUSE_SET_DMA_MODE host flag
  sis5513: factor out UDMA programming code
  pdc202xx_new: move PIO programming code to pdcnew_set_pio_mode()
  ide: make 'extra' field in struct ide_port_info u8
  ide: kill duplicate code in ide_dump_{ata,atapi}_status()
  ide-disk: use ide_get_lba_addr()
  ide: printk fix
  ide: add ide_tf_read() helper
  ide: fix registers loading order in ide_dump_ata_status()
  ide-disk: use do_rw_taskfile() (take 2)
  ide-disk: add ide_tf_set_cmd() helper
  ide-disk: extend timeout for PIO-in commands
  ide: remove 'handler' field from ide_task_t (take 2)
  ide: use ->data_phase to set ->handler in do_rw_taskfile()
  ide: convert do_rw_taskfile() to use ->data_phase
  ide: merge flagged_taskfile() into do_rw_taskfile()
  ...

16 years agoMerge git://git.kernel.org/pub/scm/linux/kernel/git/mingo/linux-2.6-sched
Linus Torvalds [Fri, 25 Jan 2008 21:42:32 +0000 (13:42 -0800)] 
Merge git://git./linux/kernel/git/mingo/linux-2.6-sched

* git://git.kernel.org/pub/scm/linux/kernel/git/mingo/linux-2.6-sched: (96 commits)
  sched: keep total / count stats in addition to the max for
  sched, futex: detach sched.h and futex.h
  sched: fix: don't take a mutex from interrupt context
  sched: print backtrace of running tasks too
  printk: use ktime_get()
  softlockup: fix signedness
  sched: latencytop support
  sched: fix goto retry in pick_next_task_rt()
  timers: don't #error on higher HZ values
  sched: monitor clock underflows in /proc/sched_debug
  sched: fix rq->clock warps on frequency changes
  sched: fix, always create kernel threads with normal priority
  debug: clean up kernel/profile.c
  sched: remove the !PREEMPT_BKL code
  sched: make PREEMPT_BKL the default
  debug: track and print last unloaded module in the oops trace
  debug: show being-loaded/being-unloaded indicator for modules
  sched: rt-watchdog: fix .rlim_max = RLIM_INFINITY
  sched: rt-group: reduce rescheduling
  hrtimer: unlock hrtimer_wakeup
  ...

16 years agoide: remove redundant DMA blacklist check from __ide_dma_on()
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:19 +0000 (22:17 +0100)] 
ide: remove redundant DMA blacklist check from __ide_dma_on()

->ide_dma_on method is called only after successful ide_dma_check() call
(ide_dma_check()->ide_tune_dma() checks DMA blacklist) or if drive->using_dma
has been previously enabled for a given device (->ide_dma_on is the only place
which sets drive->using_dma to '1').

There should be no functionality changes caused by this patch.

Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide: cleanup ide_set_dma()
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:19 +0000 (22:17 +0100)] 
ide: cleanup ide_set_dma()

* ->dma_off_quietly is always called before ide_set_dma()
  so the call can be moved inside ide_set_dma().

* ide_dma_check() doesn't touch hardware so ->dma_off_quietly
  call for 'rc == -1' case is redundant, remove it.

* '0' and '-1' are the only values returned by ide_dma_check()
  so remove dead code for other cases.

There should be no functionality changes caused by this patch.

Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide: remove redundant ->ide_dma_on call from set_using_dma()
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:19 +0000 (22:17 +0100)] 
ide: remove redundant ->ide_dma_on call from set_using_dma()

ide_set_dma() calls ->ide_dma_on method itself and returns zero
only if ->ide_dma_on call succeeded.

There should be no functionality changes caused by this patch.

Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agosc1200: move DMA timings to timing tables
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:18 +0000 (22:17 +0100)] 
sc1200: move DMA timings to timing tables

Based on pata_sc1200.c.

There should be no functionality changes caused by this patch.

Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide: add IDE_HFLAG_ABUSE_SET_DMA_MODE host flag
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:18 +0000 (22:17 +0100)] 
ide: add IDE_HFLAG_ABUSE_SET_DMA_MODE host flag

* Add IDE_HFLAG_ABUSE_SET_DMA_MODE host flag and use it to decide
  what to do with transfer modes < XFER_PIO_0 in ide_set_xfer_rate().

* Set IDE_HFLAG_ABUSE_SET_DMA_MODE in host drivers that need it
  (aec62xx, amd74xx, cs5520, cs5535, hpt34x, hpt366, pdc202xx_old,
  serverworks, tc86c001 and via82cxxx) and cleanup ->set_dma_mode
  methods in host drivers that don't (IDE core code guarantees that
  ->set_dma_mode will be called only for modes which are present
  in SWDMA/MWDMA/UDMA masks).

While at it:

* Add IDE_HFLAGS_HPT34X/HPT3XX/PDC202XX/SVWKS define in
  hpt34x/hpt366/pdc202xx_old/serverworks host driver.

There should be no functionality changes caused by this patch.

Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agosis5513: factor out UDMA programming code
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:18 +0000 (22:17 +0100)] 
sis5513: factor out UDMA programming code

* Factor out UDMA programming code from sis_set_dma_mode() to per
  chipset family helpers: sis_{ata33,ata133}_program_udma_timings().

* Add sis_program_udma_timings() helper.

* Remove unneeded casts to 'unsigned long'.

* Minor cleanups.

There should be no functionality changes caused by this patch.

Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agopdc202xx_new: move PIO programming code to pdcnew_set_pio_mode()
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:18 +0000 (22:17 +0100)] 
pdc202xx_new: move PIO programming code to pdcnew_set_pio_mode()

* Move PIO programming code from pdcnew_set_mode() to pdcnew_set_pio_mode().

* Rename pdcnew_set_mode() to pdcnew_set_dma_mode().

There should be no functionality changes caused by this patch.

Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide: make 'extra' field in struct ide_port_info u8
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:17 +0000 (22:17 +0100)] 
ide: make 'extra' field in struct ide_port_info u8

The maximum value used currently for 'extra' field in struct ide_port_info
is 240.

Make 'extra' u8 so it packs nicely together with enablebits[] and 'chipset'
fields (ide_pci_enablebit_t is 3 bytes and hwif_chipset_t is 1 byte).

Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide: kill duplicate code in ide_dump_{ata,atapi}_status()
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:17 +0000 (22:17 +0100)] 
ide: kill duplicate code in ide_dump_{ata,atapi}_status()

* Move the common code from ide_dump_{ata,atapi}_status() to
  ide_dump_status().

* ide_dump_{ata,atapi}_status() -> ide_dump_{ata,atapi}_error().

There should be no functionality changes caused by this patch.

Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide-disk: use ide_get_lba_addr()
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:17 +0000 (22:17 +0100)] 
ide-disk: use ide_get_lba_addr()

* Export ide_get_lba_addr().

* Convert idedisk_{read_native,set}_max_address() to use ide_get_lba_addr().

* Remove incorrect comment from idedisk_read_native_max_address()
  (noticed by Sergei).

There should be no functionality changes caused by this patch.

Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide: printk fix
Andrew Morton [Fri, 25 Jan 2008 21:17:17 +0000 (22:17 +0100)] 
ide: printk fix

power4:

drivers/ide/ide-lib.c: In function `ide_dump_sector':
drivers/ide/ide-lib.c:516: warning: long long unsigned int format, u64 arg (arg 2)

We don't know what type is used to implement u64 hence it must always be cast
when printed.

Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide: add ide_tf_read() helper
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:17 +0000 (22:17 +0100)] 
ide: add ide_tf_read() helper

* Factor out code reading taskfile registers from ide_end_drive_cmd()
  to the new ide_tf_read() helper.

* Add IDE_TFLAG_IN_* taskfile flags to indicate the need to load
  particular IDE taskfile register in ide_tf_read().

* Update ide_end_drive_cmd() to set respective IDE_TFLAG_IN_* taksfile flags.

* Add ide_get_lba_addr() for getting LBA sector address from taskfile struct.

* Factor out code getting sector address from ide_dump_ata_status()
  to the new ide_dump_sector() function.

* Convert ide_dump_sector() to use ide_tf_read() and ide_get_lba_addr().

* Remove no longer needed ide_read_24().

The only change in functionality caused by this patch is that
ide_dump_ata_status() no longer prints "high"/"low" parts of LBA48
sector address (of course LBA48 sector address is still printed).

Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide: fix registers loading order in ide_dump_ata_status()
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:17 +0000 (22:17 +0100)] 
ide: fix registers loading order in ide_dump_ata_status()

Fix registers loading order in ide_dump_ata_status()/ide_read_24().

Load registers in this order:
* IDE_SECTOR_REG
* IDE_LCYL_REG
* IDE_HCYL_REG
* IDE_SELECT_REG

It shouldn't affect anything (just a usual paranoia to separate changes
which change the way in which hardware is accessed from code cleanups).

Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide-disk: use do_rw_taskfile() (take 2)
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:16 +0000 (22:17 +0100)] 
ide-disk: use do_rw_taskfile() (take 2)

* Add IDE_TFLAG_DMA_PIO_FALLBACK taskfile flag to indicate the need
  to skip loading taskfile registers in do_rw_taskfile().

* Export do_rw_taskfile().

* Convert __ide_do_rw_disk() to use do_rw_taskfile().

* Unexport ide_tf_load().

* Unexport {pre_task_out,task_in}_intr() and make it static.

* Remove incorrect comment about do_rw_taskfile() from <linux/ide.h>.

There should be no functionality changes caused by this patch.

v2:
* Add missing blk_fs_request() check to task_dma_ok() (for VDMA).

Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide-disk: add ide_tf_set_cmd() helper
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:16 +0000 (22:17 +0100)] 
ide-disk: add ide_tf_set_cmd() helper

* Add ide_tf_set_cmd() helper for selecting/setting command and data phase
  (note: DMA data phases are there for completness, they are not required ATM).

* Set IDE_TFLAG_WRITE taskfile flag for write requests in __ide_do_rw_disk().

* Convert __ide_do_rw_disk() to use the new ide_tf_set_cmd() helper.

There should be no functionality changes caused by this patch.

Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide-disk: extend timeout for PIO-in commands
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:16 +0000 (22:17 +0100)] 
ide-disk: extend timeout for PIO-in commands

s/WAIT_CMD/WAIT_WORSTCASE/ to make the timeout the same as in do_rw_taskfile()

Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide: remove 'handler' field from ide_task_t (take 2)
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:16 +0000 (22:17 +0100)] 
ide: remove 'handler' field from ide_task_t (take 2)

* Add IDE_TFLAG_CUSTOM_HANDLER taskfile flag and use it for internal requests
  which require custom handlers.  Check the flag in do_rw_taskfile() and set
  handler accordingly.

* Cleanup ide_init_{specify,restore,setmult}_cmd() and rename it to
  ide_tf_set_{specify,restore,setmult}_cmd().

* Make {set_geometry,recal,set_multmode}_intr() static.

* Remove no longer needed 'handler' field from ide_task_t.

v2:
* 'handler' in do_rw_taskfile() must be set to NULL initially.

There should be no functionality changes caused by this patch.

Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide: use ->data_phase to set ->handler in do_rw_taskfile()
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:16 +0000 (22:17 +0100)] 
ide: use ->data_phase to set ->handler in do_rw_taskfile()

* Use ->data_phase to set ->handler in do_rw_taskfile() instead of
  setting ->handler in callers of ide_raw_taskfile()/do_rw_taskfile().

* Unexport task_no_data_intr() and make it static.

There should be no functionality changes caused by this patch.

Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide: convert do_rw_taskfile() to use ->data_phase
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:16 +0000 (22:17 +0100)] 
ide: convert do_rw_taskfile() to use ->data_phase

* Use task->data_phase in do_rw_taskfile() to decide what to do.

* task->prehandler is only used by TASKFILE[_MULTI]_OUT so just
  use pre_task_out_intr() directly and remove no longer needed
  'prehandler' field from ide_task_t.

* Remove no longer needed ide_pre_handler_t type.

There should be no functionality changes caused by this patch.

Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide: merge flagged_taskfile() into do_rw_taskfile()
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:15 +0000 (22:17 +0100)] 
ide: merge flagged_taskfile() into do_rw_taskfile()

Based on the earlier work by Tejun Heo.

task->data_phase == TASKFILE_MULTI_{IN,OUT} vs drive->mult_count == 0
check is needed also for ide_taskfile_ioctl() requests that don't have
IDE_TFLAG_FLAGGED taskfile flag set.

Cc: Tejun Heo <htejun@gmail.com>
Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide-disk: guarantee 400ns delay after writing command register
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:15 +0000 (22:17 +0100)] 
ide-disk: guarantee 400ns delay after writing command register

Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide-disk: fix __ide_do_rw_disk() to use ->OUTBSYNC
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:15 +0000 (22:17 +0100)] 
ide-disk: fix __ide_do_rw_disk() to use ->OUTBSYNC

Fix __ide_do_rw_disk() to use ->OUTBSYNC instead of ->OUTB
(needed for pmac and scc_pata host drivers).

Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agosc1200: remove pointless hwif lookup loop
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:14 +0000 (22:17 +0100)] 
sc1200: remove pointless hwif lookup loop

Save PCI regs values for both IDE ports in one buffer, in order to eliminate
a needless and ugly loop across all hwifs, searching for our PCI device.

Partially based on the previous patch by Jeff Garzik.

Cc: Jeff Garzik <jeff@garzik.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide: remove 'tf_in_flags' field from ide_task_t
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:14 +0000 (22:17 +0100)] 
ide: remove 'tf_in_flags' field from ide_task_t

* Add IDE_TFLAG_IN_DATA taskfile flag to indicate the need of reading
  IDE_DATA_REG in ide_end_drive_cmd().

  Set the new flag in ide_taskfile_ioctl() if ->in_flags.b.data is set.

* Add IDE_TFLAG_FLAGGED_SET_IN_FLAGS taskfile flag to indicate the
  need of modifying ->in_flags in ide_taskfile_ioctl().

  Set the new flag in flagged_taskfile() and move the code modifying
  ->tf_in_flags to ide_taskfile_ioctl().

  While at it remove the bogus comment: ->tf_in_flags (except .b.data)
  have no effect on selection of registers to read.

* Remove no longer needed 'tf_in_flags' field from ide_task_t.

As the result we finally have the internals of HDIO_DRIVE_TASKFILE ioctl
separated from the core IDE code.

There should be no functionality changes caused by this patch.

Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide: remove 'command_type' field from ide_task_t
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:14 +0000 (22:17 +0100)] 
ide: remove 'command_type' field from ide_task_t

* Add 'data_buf' and 'nsect' variables in ide_taskfile_ioctl()
  to cache data buffer pointer and number of sectors to transfer
  (this allows us to have only one ide_diag_taskfile() call).

* Add IDE_TFLAG_WRITE taskfile flag and use it to check whether
  the REQ_RW request flag should be set.

* Move ->command_type handling from ide_diag_taskfile() to
  ide_taskfile_ioctl() and use ->req_cmd instead of ->command_type.

* Add 'nsect' parameter to ide_raw_taskfile().

* Merge ide_diag_taskfile() into ide_raw_taskfile().

* Initialize ->data_phase explicitly in idedisk_prepare_flush(),
  ide_start_power_step() and ide_disk_special().

* Remove no longer needed 'command_type' field from ide_task_t.

* Add #ifndef/#endif __KERNEL__ to <linux/hdreg.h> around no
  longer used by kernel IDE_DRIVE_TASK_* and TASKFILE_* defines.

There should be no functionality changes caused by this patch.

Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide: remove hwif->intrproc
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:14 +0000 (22:17 +0100)] 
ide: remove hwif->intrproc

Given that:

* hpt366.c::hpt3xx_intrproc() is the only user of hwif->intrproc

* hpt366.c::hpt3xx_quirkproc() sets drive->quirk_list to 1 for quirky drives
  which is a value unique to hpt366 host driver

we can remove hwif->intproc and just check for drive->quirk_list == 1
in ide_do_request().

Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide: remove SELECT_INTERRUPT()
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:13 +0000 (22:17 +0100)] 
ide: remove SELECT_INTERRUPT()

Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide: remove QUIRK_LIST()
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:13 +0000 (22:17 +0100)] 
ide: remove QUIRK_LIST()

Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide: add ide_pktcmd_tf_load() helper
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:13 +0000 (22:17 +0100)] 
ide: add ide_pktcmd_tf_load() helper

Add ide_pktcmd_tf_load() helper and convert ATAPI device drivers to use it.

There should be no functionality changes caused by this patch.

Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide-{floppy,tape,scsi}: fix register loading order when issuing packet command
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:13 +0000 (22:17 +0100)] 
ide-{floppy,tape,scsi}: fix register loading order when issuing packet command

Load IDE_BCOUNTL_REG before IDE_BCOUNTH_REG when issuing packet command.

It shouldn't affect anything (just a usual paranoia to separate changes
which change the way in which hardware is accessed from code cleanups).

Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide-cd: fix register loading order in cdrom_start_packet_command()
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:13 +0000 (22:17 +0100)] 
ide-cd: fix register loading order in cdrom_start_packet_command()

Load IDE_CONTROL_REG before other registers in cdrom_start_packet_command().

It shouldn't affect anything (just a usual paranoia to separate changes
which change the way in which hardware is accessed from code cleanups).

While at it move misplaced FIXME comment in the right place.

Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide: remove atapi_ireason_t (take 3)
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:12 +0000 (22:17 +0100)] 
ide: remove atapi_ireason_t (take 3)

Remove atapi_ireason_t.

While at it:
* replace 'HWIF(drive)' by 'drive->hwif' (or just 'hwif' where possible)

v2:
* v1 had CD and IO bits reversed in many places.

* Use CD and IO defines from <linux/hdreg.h>.

v3:
* Fix incorrect "(ireason & IO) == test_bit()". (Noticed by Sergei)

Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide: remove ata_nsector_t, ata_data_t and atapi_bcount_t
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:12 +0000 (22:17 +0100)] 
ide: remove ata_nsector_t, ata_data_t and atapi_bcount_t

Remove ata_nsector_t, ata_data_t (unused) and atapi_bcount_t.

While at it:
* replace 'HWIF(drive)' by 'hwif'

Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide: remove atapi_feature_t
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:12 +0000 (22:17 +0100)] 
ide: remove atapi_feature_t

Remove atapi_feature_t.

While at it:
* replace 'HWIF(drive)' by 'hwif'

Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide: remove atapi_error_t (take 2)
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:12 +0000 (22:17 +0100)] 
ide: remove atapi_error_t (take 2)

Remove atapi_error_t.

While at it:
* replace 'HWIF(drive)' by 'drive->hwif'

v2:
* Add {ILI,EOM,LFS}_ERR defines to <linux/hdreg.h>.

Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide: remove ata_status_t and atapi_status_t
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:11 +0000 (22:17 +0100)] 
ide: remove ata_status_t and atapi_status_t

Remove ata_status_t (unused) and atapi_status_t.

While at it:
* replace 'HWIF(drive)' by 'drive->hwif' (or just 'hwif' where possible)

Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide: CPU endianness doesn't matter for special_t
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:11 +0000 (22:17 +0100)] 
ide: CPU endianness doesn't matter for special_t

special_t is used only internally by the IDE subsystem (it isn't
related to hardware registers and isn't exported to the user-space).

Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide-floppy: remove dead code
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:11 +0000 (22:17 +0100)] 
ide-floppy: remove dead code

Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide: remove REQ_TYPE_ATA_TASK
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:11 +0000 (22:17 +0100)] 
ide: remove REQ_TYPE_ATA_TASK

Based on the earlier work by Tejun Heo.

All users are gone so we can finally remove it.

Cc: Tejun Heo <htejun@gmail.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide: switch ide_task_ioctl() to use REQ_TYPE_ATA_TASKFILE requests
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:11 +0000 (22:17 +0100)] 
ide: switch ide_task_ioctl() to use REQ_TYPE_ATA_TASKFILE requests

Based on the earlier work by Tejun Heo.

There should be no functionality changes caused by this patch.

Cc: Tejun Heo <htejun@gmail.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide: switch idedisk_prepare_flush() to use REQ_TYPE_ATA_TASKFILE requests
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:10 +0000 (22:17 +0100)] 
ide: switch idedisk_prepare_flush() to use REQ_TYPE_ATA_TASKFILE requests

Based on the earlier work by Tejun Heo.

There should be no functionality changes caused by this patch.

Cc: Tejun Heo <htejun@gmail.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide: extend timeout for REQ_TYPE_ATA_{CMD,TASK} requests
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:10 +0000 (22:17 +0100)] 
ide: extend timeout for REQ_TYPE_ATA_{CMD,TASK} requests

Extend timeout for REQ_TYPE_ATA_{CMD,TASK} requests from WAIT_CMD (10sec)
to WAIT_WORSTCASE (30sec, already used for REQ_TYPE_ATA_TASKFILE).

Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide: remove unnecessary writes to HOB taskfile registers
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:10 +0000 (22:17 +0100)] 
ide: remove unnecessary writes to HOB taskfile registers

* Set taskfile flags for REQ_TYPE_ATA_TASKFILE requests before
  adding the request to the queue.

* Cleanup execute_drive_cmd().

* Remove unnecessary writes to HOB taskfile registers when using
  LBA48 disk for the following cases:

  - Power Management requests
    (WIN_FLUSH_CACHE[_EXT], WIN_STANDBYNOW1, WIN_IDLEIMMEDIATE commands)

  - special commands (WIN_SPECIFY, WIN_RESTORE, WIN_SETMULT)

  - Host Protected Area support (WIN_READ_NATIVE_MAX, WIN_SET_MAX)

  - /proc/ide/ SMART support (WIN_SMART with SMART_ENABLE,
    SMART_READ_VALUES and SMART_READ_THRESHOLDS subcommands)

  - write cache enabling/disabling in ide-disk
    (WIN_SETFEATURES with SETFEATURES_{EN,DIS}_WCACHE)

  - write cache flushing in ide-disk (WIN_FLUSH_CACHE[_EXT])

  - acoustic management in ide-disk
    (WIN_SETFEATURES with SETFEATURES_{EN,DIS}_AAM)

  - door (un)locking in ide-disk (WIN_DOORLOCK, WIN_DOORUNLOCK)

  - /proc/ide/hd?/identify support (WIN_IDENTIFY)

  - ACPI _GTF taskfiles

Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide: use IDE_TFLAG_LBA48 for REQ_TYPE_ATA_TASKFILE requests
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:10 +0000 (22:17 +0100)] 
ide: use IDE_TFLAG_LBA48 for REQ_TYPE_ATA_TASKFILE requests

* Use IDE_TFLAG_LBA48 for REQ_TYPE_ATA_TASKFILE requests in ide_end_drive_cmd()
  to decide whether we need to read HOB taskfile registers.

* Update execute_drive_cmd() accordingly.

This is a preparation for the next patch which removes unnecessary writes to
HOB taskfile registers for some ATA commands.

Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide: use ide_tf_load() in execute_drive_cmd()
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:10 +0000 (22:17 +0100)] 
ide: use ide_tf_load() in execute_drive_cmd()

* Add IDE_TFLAG_OUT_DEVICE taskfile flag to indicate the need of writing
  the Device register and handle it in ide_tf_load().

  Update ide_tf_load() and {do_rw,flagged}_taskfile() users accordingly.

* Use struct ide_taskfile and ide_tf_load() in execute_drive_cmd().

* Make the debugging code dump all taskfile registers for both
  REQ_ATA_TYPE_{CMD,TASK} requests and move it to ide_tf_load()
  so it also covers REQ_ATA_TYPE_TASKFILE requests.

There should be no functionality changes caused by this patch
(unless DEBUG is defined).

Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide: remove ide_cmd() helper
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:09 +0000 (22:17 +0100)] 
ide: remove ide_cmd() helper

* Remove ide_cmd() helper.

* Clear nIEN and call SELECT_MASK() before writing taskfile registers.

Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide: execute_drive_cmd() cleanup
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:09 +0000 (22:17 +0100)] 
ide: execute_drive_cmd() cleanup

* Rename 'args' variable in 'if (rq->cmd_type == REQ_TYPE_ATA_TASKFILE)'
  block to 'task'.

* execute_drive_cmd() is used only for REQ_TYPE_ATA_{CMD,TASK,TASKFILE} so
  we can move the common code out from 'if (rq->cmd_type == REQ_TYPE_ATA_CMD)'
  and 'if (rq->cmd_type == REQ_TYPE_ATA_TASK)' blocks.

There should be no functionality changes caused by this patch.

Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide: fix registers loading order for IDE_NSECTOR_REG in execute_drive_cmd()
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:09 +0000 (22:17 +0100)] 
ide: fix registers loading order for IDE_NSECTOR_REG in execute_drive_cmd()

Move loading of IDE_NSECTOR_REG from ide_cmd() to execute_drive_cmd()
(load the IDE_NSECTOR_REG just after IDE_FEATURE_REG).

This also allows us to drop 'nsect' argument from ide_cmd() and simplify
execute_drive_cmd() code for REQ_TYPE_ATA_CMD case a bit.

It shouldn't affect anything (just a usual paranoia to separate changes
which change the way in which hardware is accessed from code cleanups).

Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
16 years agoide: fix registers loading order for WIN_SMART in execute_drive_cmd()
Bartlomiej Zolnierkiewicz [Fri, 25 Jan 2008 21:17:09 +0000 (22:17 +0100)] 
ide: fix registers loading order for WIN_SMART in execute_drive_cmd()

Fix registers loading order for REQ_TYPE_ATA_CMD request with WIN_SMART
command in execute_drive_cmd() (load IDE_FEATURE_REG and IDE_SECTOR_REG
before loading IDE_LCYL_REG and IDE_HCYL_REG).

It shouldn't affect anything (just a usual paranoia to separate changes
which change the way in which hardware is accessed from code cleanups).

Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>