[PATCH] IB/ehca: Fix CQE flags reporting

2009-09-01 Thread Joachim Fenkes
Was reporting CQE flags in the wrong bit positions, causing consumers to miss incoming immediate data. Signed-off-by: Joachim Fenkes --- Please review and queue for 2.6.32 if you think it's okay. Thanks! Joachim drivers/infiniband/hw/ehca/ehca_reqs.c |6 +- 1 files chang

Re: [ewg] [PATCH] IB/ehca: Construct MAD redirect replies from request MAD

2009-08-28 Thread Joachim Fenkes
Hal Rosenstock wrote on 27.08.2009 15:31:40: > I don't think it should be hard coded. IMO it would be better to default to 18 > and somehow able to be adjusted (via a (dynamic) module parameter ?). I don't see how making this a parameter would benefit any end user, while on the other hand it c

Re: [ewg] [PATCH] IB/ehca: Construct MAD redirect replies from request MAD

2009-08-27 Thread Joachim Fenkes
Hal Rosenstock wrote on 26.08.2009 17:15:03: > Thanks for doing this. It looks sane to me. The only issue I recall that > appears to be remaining is a better setting of ClassPortInfo:RespTimeValue > rather than hardcoding. Perhaps using the value from PortInfo is the way to go > (ideally it

[PATCH] IB/ehca: Construct MAD redirect replies from request MAD

2009-08-26 Thread Joachim Fenkes
The old code used a lot of hardcoded values, which might not be valid in all environments (especially routed fabrics or partitioned subnets). Copy as much information as possible from the incoming request to prevent that. Signed-off-by: Joachim Fenkes --- Hal, Jason -- here's the cha

[PATCH] IB/ehca: Remove superfluous bitmasks from QP control block

2009-06-03 Thread Joachim Fenkes
All the fields in the control block are nicely right-aligned, so no masking is necessary. Signed-off-by: Joachim Fenkes --- drivers/infiniband/hw/ehca/ehca_classes_pSeries.h | 28 - drivers/infiniband/hw/ehca/ehca_qp.c | 18 +++- 2 files changed, 5

Re: [PATCH] IB/ehca: Change misleading error message

2008-11-26 Thread Joachim Fenkes
Roland Dreier <[EMAIL PROTECTED]> wrote on 26.11.2008 00:13:51: > That's too bad... I applied this patch but out of curiousity, why > doesn't the hot-remove/hot-add work? I would have thought that > re-registering all of memory after the hot-add would do the right thing. That's right, but right

[PATCH] IB/ehca: Change misleading error message

2008-11-25 Thread Joachim Fenkes
The error message printed when the eHCA driver prevents memory hotplug is misleading -- the user might think that hot-removing the lhca, hotplugging memory, then hot-adding the lhca again will work, but it doesn't. Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- drivers/infinib

[PATCH] IB/ehca: Fix locking for shca_list_lock

2008-11-21 Thread Joachim Fenkes
shca_list_lock is taken from softirq context in ehca_poll_eqs, so we need to lock IRQ safe elsewhere. Signed-off-by: Michael Ellerman <[EMAIL PROTECTED]> Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- On Friday 21 November 2008 17:02, Johannes Berg wrote: > On Fri, 2008

[PATCH] IB/ehca: Fix lockdep failures for shca_list_lock

2008-11-21 Thread Joachim Fenkes
From: Michael Ellerman <[EMAIL PROTECTED]> shca_list_lock is taken from softirq context in ehca_poll_eqs, so we need to lock IRQ safe elsewhere. Signed-off-by: Michael Ellerman <[EMAIL PROTECTED]> Acked-by: Joachim Fenkes <[EMAIL PROTECTED]> --- drivers/infiniband/hw/ehca/

Re: [PATCH] IB/ehca: Fix suppression of port activation events

2008-11-11 Thread Joachim Fenkes
Roland Dreier <[EMAIL PROTECTED]> wrote on 10.11.2008 21:36:23: > > A previous fix introduced a regression where port activation events were > > dropped unconditionally if port autodetection was not enabled. Fixed. > > Is this a fix to "IB/ehca: Remove reference to special QP in case of > port

[PATCH] IB/ehca: Fix suppression of port activation events

2008-11-07 Thread Joachim Fenkes
A previous fix introduced a regression where port activation events were dropped unconditionally if port autodetection was not enabled. Fixed. Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- Roland -- this patch is made against your for-linus branch. Please review and apply if you

Re: [PATCH] ibmebus/of_platform: Move "name" sysfs attribute into generic OF devices

2008-08-19 Thread Joachim Fenkes
Paul Mackerras <[EMAIL PROTECTED]> wrote on 19.08.2008 06:14:00: > > Recent of_platform changes made of_bus_type_init() overwrite the bus type's > > .dev_attrs list, so move ibmebus' "name" attribute (which is needed by eHCA > > userspace support) into generic OF device code. Tested on POWER. >

[PATCH] ibmebus/of_platform: Move "name" sysfs attribute into generic OF devices

2008-08-05 Thread Joachim Fenkes
Recent of_platform changes made of_bus_type_init() overwrite the bus type's .dev_attrs list, so move ibmebus' "name" attribute (which is needed by eHCA userspace support) into generic OF device code. Tested on POWER. Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]>

[PATCH 2/2] IB/ehca: Default value for Local CA ACK Delay

2008-07-21 Thread Joachim Fenkes
Some firmware versions report a Local CA ACK Delay of 0. In that case, return a more sensible default value of 12 (-> 16 msec) instead. Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- drivers/infiniband/hw/ehca/ehca_hca.c |4 +++- 1 files changed, 3 insertions(+), 1 deletions

[PATCH 1/2] IB/ehca: Filter PATH_MIG events if QP was never armed

2008-07-21 Thread Joachim Fenkes
Certain firmware versions sometimes cause spurious PATH_MIG events to occur during QP creation. Filter these events by making sure PATH_MIG events are only handed down when they actually make sense (i.e. when the QP has been armed at least once). Signed-off-by: Joachim Fenkes <[EMAIL PROTEC

[PATCH 0/2] IB/ehca: Two minor circumventions

2008-07-21 Thread Joachim Fenkes
[1/2] fixes spurious PATH_MIG events with certain FW versions [2/2] inserts a default value for Local CA ACK Delay Please review these patches and queue them for inclusion into the kernel if you think they're okay. Thanks! Joachim ___ Linuxppc-dev ma

[PATCH] IB/ehca: Make device table externally visible

2008-07-01 Thread Joachim Fenkes
This gives ehca an autogenerated modalias and therefore enables automatic loading. Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- drivers/infiniband/hw/ehca/ehca_main.c |1 + 1 files changed, 1 insertions(+), 0 deletions(-) diff --git a/drivers/infiniband/hw/ehca/ehca_mai

[PATCH] IB/ehca: Reject recv WRs if QP is in RESET state

2008-06-09 Thread Joachim Fenkes
Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- On Friday 06 June 2008 22:20, Dotan Barak wrote: > I checked the code in the ehca driver and noticed that > post RR to a QP is being accepted in any state (including the RESET state). You're right, this is only consist

IB/ehca: Reject send WRs only for RESET, INIT and RTR state

2008-06-06 Thread Joachim Fenkes
Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- drivers/infiniband/hw/ehca/ehca_reqs.c |6 -- 1 files changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/hw/ehca/ehca_reqs.c b/drivers/infiniband/hw/ehca/ehca_reqs.c index bbe0436..f093b00 100644 --- a/d

Re: [PATCH 1/5] IB/ehca: Prevent posting of SQ WQEs if QP not in RTS

2008-04-21 Thread Joachim Fenkes
On Monday 21 April 2008 10:04, Joachim Fenkes wrote: > + if (unlikely(my_qp->state != IB_QPS_RTS)) { > + ehca_err(qp->device, "QP not in RTS state qpn=%x", qp->qp_num); > + return -EINVAL; > + } Myself, I'm not very happy with

[PATCH 5/5] IB/ehca: Bump version number to 0026

2008-04-21 Thread Joachim Fenkes
Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- drivers/infiniband/hw/ehca/ehca_main.c |2 +- 1 files changed, 1 insertions(+), 1 deletions(-) diff --git a/drivers/infiniband/hw/ehca/ehca_main.c b/drivers/infiniband/hw/ehca/ehca_main.c index 45fe35a..6504897 100644 --- a/d

[PATCH 4/5] IB/ehca: Make some module parameters bool, update descriptions

2008-04-21 Thread Joachim Fenkes
Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- drivers/infiniband/hw/ehca/ehca_main.c | 37 +++ 1 files changed, 18 insertions(+), 19 deletions(-) diff --git a/drivers/infiniband/hw/ehca/ehca_main.c b/drivers/infiniband/hw/ehca/ehca_main.c index a

[PATCH 3/5] IB/ehca: Remove mr_largepage parameter

2008-04-21 Thread Joachim Fenkes
Always enable large page support; didn't seem to cause problems for anyone. Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- drivers/infiniband/hw/ehca/ehca_main.c | 22 +++--- 1 files changed, 3 insertions(+), 19 deletions(-) diff --git a/drivers/infinib

[PATCH 2/5] IB/ehca: Move high-volume debug output to higher debug levels

2008-04-21 Thread Joachim Fenkes
Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- drivers/infiniband/hw/ehca/ehca_irq.c|2 +- drivers/infiniband/hw/ehca/ehca_main.c | 14 ++-- drivers/infiniband/hw/ehca/ehca_mrmw.c | 16 ++ drivers/infiniband/hw/ehca/ehca_qp.c | 12 d

[PATCH 1/5] IB/ehca: Prevent posting of SQ WQEs if QP not in RTS

2008-04-21 Thread Joachim Fenkes
...as required by IB Spec, C10-29. Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- drivers/infiniband/hw/ehca/ehca_classes.h |1 + drivers/infiniband/hw/ehca/ehca_qp.c |3 +++ drivers/infiniband/hw/ehca/ehca_reqs.c|5 + 3 files changed, 9 insertions(+), 0 del

[PATCH 0/5] IB/ehca: IB compliance fix, tracing verbosity and module parameters

2008-04-21 Thread Joachim Fenkes
Please review these patches and queue them for inclusion into 2.6.26 if you think they're okay. Thanks! Joachim -- Joachim Fenkes -- eHCA Linux Driver Developer and Hardware Tamer IBM Deutschland Entwicklung GmbH -- Dept. 3627 (I/O Firmware Dev. 2) Schoenaicher Strasse 220 -- 71032 Boebl

[PATCH 1/2] IB/ehca: Update sma_attr also in case of disruptive config change

2008-01-25 Thread Joachim Fenkes
Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- drivers/infiniband/hw/ehca/ehca_irq.c |2 ++ 1 files changed, 2 insertions(+), 0 deletions(-) diff --git a/drivers/infiniband/hw/ehca/ehca_irq.c b/drivers/infiniband/hw/ehca/ehca_irq.c index 863b34f..b5ca94c 100644 --- a/d

[PATCH 2/2] IB/ehca: Add PMA support

2008-01-25 Thread Joachim Fenkes
From: Hoang-Nam Nguyen <[EMAIL PROTECTED]> This patch enables ehca to redirect any PMA queries to the actual PMA QP. Signed-off-by: Hoang-Nam Nguyen <[EMAIL PROTECTED]> Reviewed-by: Joachim Fenkes <[EMAIL PROTECTED]> Reviewed-by: Christoph Raisch <[EMAIL PROTECTED]> --

[PATCH 0/2] IB/ehca: PMA support and a minor fix

2008-01-25 Thread Joachim Fenkes
them and apply for 2.6.25 if you think they're okay. Thanks and regards, Joachim -- Joachim Fenkes -- eHCA Linux Driver Developer and Hardware Tamer IBM Deutschland Entwicklung GmbH -- Dept. 3627 (I/O Firmware Dev. 2) Schoenaicher Strasse 220 -- 71032 Boeblingen -- Germany eMa

[PATCH] IB/ehca: Prevent sending UD packets to QP0

2008-01-24 Thread Joachim Fenkes
Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- drivers/infiniband/hw/ehca/ehca_reqs.c |4 1 files changed, 4 insertions(+), 0 deletions(-) diff --git a/drivers/infiniband/hw/ehca/ehca_reqs.c b/drivers/infiniband/hw/ehca/ehca_reqs.c index 3aacc8c..2ce8cff 100644 --- a/drive

[PATCH 4/4] IB/ehca: Prevent RDMA-related connection failures

2008-01-17 Thread Joachim Fenkes
empty (size 0) RDMA Read into the message stream every now and then if the consumer doesn't post them frequently enough. Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- drivers/infiniband/hw/ehca/ehca_classes.h |5 ++ drivers/infiniband/hw/ehca/ehca_qp.c | 14 ++

[PATCH 3/4] IB/ehca: Add "port connection autodetect mode"

2008-01-17 Thread Joachim Fenkes
From: Hoang-Nam Nguyen <[EMAIL PROTECTED]> This patch enhances ehca with a capability to "autodetect" the ports being connected physically. In order to utilize that function the module option nr_ports must be set to -1 (default is 2 - two ports). This feature is experimental and will made the defa

[PATCH 2/4] IB/ehca: Define array to store SMI/GSI QPs

2008-01-17 Thread Joachim Fenkes
From: Hoang-Nam Nguyen Signed-off-by: Hoang-Nam Nguyen <[EMAIL PROTECTED]> --- drivers/infiniband/hw/ehca/ehca_classes.h |2 +- drivers/infiniband/hw/ehca/ehca_main.c|6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/infiniband/hw/ehca/ehca_classes.h b

[PATCH 1/4] IB/ehca: Remove CQ-QP-link before destroying QP in error path of create_qp()

2008-01-17 Thread Joachim Fenkes
From: Hoang-Nam Nguyen Signed-off-by: Hoang-Nam Nguyen <[EMAIL PROTECTED]> --- drivers/infiniband/hw/ehca/ehca_qp.c |5 - 1 files changed, 4 insertions(+), 1 deletions(-) diff --git a/drivers/infiniband/hw/ehca/ehca_qp.c b/drivers/infiniband/hw/ehca/ehca_qp.c index f116eb7..26c6a94 100

[PATCH 0/4] IB/ehca: fixes, port connectivity autodetection, problem workaround

2008-01-17 Thread Joachim Fenkes
workaround The patches will apply, in order, on top of Roland's for-2.6.25 branch. Please review them and apply for 2.6.25 if you think they're okay. Thanks and regards, Joachim -- Joachim Fenkes -- eHCA Linux Driver Developer and Hardware Tamer IBM Deutschland Entwicklung GmbH --

Re: [PATCH] [POWERPC] make ibmebus use of_(un)register_driver

2008-01-14 Thread Joachim Fenkes
driver_unregister(&drv->driver); > + of_unregister_driver(drv); > } > EXPORT_SYMBOL(ibmebus_unregister_driver); Looks like a transparent change to me. Good one. Joachim Acked-by: Joachim Fenkes <[EMAIL PROTECTED]> ___ Linuxppc-dev mailing list Linuxppc-dev@ozlabs.org https://ozlabs.org/mailman/listinfo/linuxppc-dev

RE: [ofa-general] Re: [ewg] Re: [PATCH] IB/ehca: Serialize HCA-related hCalls on POWER5

2007-12-13 Thread Joachim Fenkes
"Caitlin Bestler" <[EMAIL PROTECTED]> wrote on 13.12.2007 22:08:34: > To clarify, an FMR Work Request is simply posted to the SendQ like > any other Work Request (of course the QP has to be privileged, or > it will complete in error). An SQ Post should never block. This would require hardware su

Re: [ofa-general] Re: [ewg] Re: [PATCH] IB/ehca: Serialize HCA-related hCalls on POWER5

2007-12-13 Thread Joachim Fenkes
[EMAIL PROTECTED] wrote on 13.12.2007 20:22:49: > On Dec 13, 2007 12:30 AM, Or Gerlitz <[EMAIL PROTECTED]> wrote: > > The current implementation of the open iscsi initiator makes sure to > > issue commands in thread (sleepable) context, see iscsi_xmitworker and > > references to it in drivers/scsi

[PATCH] IB/ehca: Fix lock flag location, bump version number

2007-12-13 Thread Joachim Fenkes
Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- This addresses a comment of Roland and bumps the version number. If it's not too late, please apply for 2.6.24. Thanks! drivers/infiniband/hw/ehca/ehca_classes.h |1 + drivers/infiniband/hw/ehca/ehca_main.c|2

Re: [PATCH] IB/ehca: Serialize HCA-related hCalls on POWER5

2007-12-11 Thread Joachim Fenkes
Roland Dreier <[EMAIL PROTECTED]> wrote on 10.12.2007 22:47:37: > It's a big problem. If you cannot implement FMRs in such a way that > you can handling having map_phys_fmr being called in a context that > can't sleep, then I think the only option is to remove your FMR > support. That's kind of

[PATCH] IB/ehca: Serialize HCA-related hCalls if necessary

2007-12-10 Thread Joachim Fenkes
Several pSeries firmware versions share a rare locking issue in the HCA-related hCalls. Check for a feature flag that indicates the issue being fixed and serialize all HCA hCalls if not. Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- This is the revised version of my previous patch,

Re: [PATCH] IB/ehca: Serialize HCA-related hCalls on POWER5

2007-12-10 Thread Joachim Fenkes
Hi, guys, > We're taking this to the firmware architects at the moment, but they're not > very fond of the idea of reporting the absence of bugs through capability > flags, as this could quickly lead to the exhaustion of flag bits. We'll let > the discussion stew for a bit, but if we don't g

Re: [PATCH] IB/ehca: Serialize HCA-related hCalls on POWER5

2007-12-10 Thread Joachim Fenkes
On Monday 10 December 2007 00:22, Roland Dreier wrote: > Fair enough... according to Documentation/infiniband/core_locking.txt, > the only driver methods that cannot sleep are: > > [...] > map_phys_fmr In fact, we do use hCalls there. Our hardware doesn't actually support FMRs, so we tran

[PATCH] IB/ehca: Return correct #SGEs for SRQ

2007-12-10 Thread Joachim Fenkes
Firmware would round up the number of SGEs to four, because the WQE structure holds four SGEs. For SRQ, only three are supported, so return a fixed value instead. Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- The patch will apply cleanly on top of Roland's git. Please revie

Re: [PATCH] IB/ehca: Serialize HCA-related hCalls on POWER5

2007-12-07 Thread Joachim Fenkes
Roland Dreier <[EMAIL PROTECTED]> wrote on 06.12.2007 19:27:09: > > > + ehca_lock_hcalls = !(cur_cpu_spec->cpu_user_features > > > +& PPC_FEATURE_ARCH_2_05); > > > We already talked about this yesterday, but I still feel that checking the >

[PATCH] IB/ehca: Serialize HCA-related hCalls on POWER5

2007-12-06 Thread Joachim Fenkes
-related hCalls on POWER5. Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- We tested this patch, especially the autodetection, and it works okay. Please review and apply for 2.6.24-rc5 - thanks! drivers/infiniband/hw/ehca/ehca_main.c | 16 drivers/infiniband/h

[PATCH] IB/ehca: Fix static rate if path faster than link

2007-11-28 Thread Joachim Fenkes
The formula would yield -1 for this, which is wrong in a bad way (max throttling). Clamp to 0, which is the correct value. Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- This fixes another regression introduced in rc3. Please review and apply for 2.6.24-rc4. Thanks! drivers/infi

[PATCH] IB/ehca: Fix static rate regression

2007-11-22 Thread Joachim Fenkes
Wrong choice of port number caused modify_qp() to fail -- fixed. Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- Please apply this for 2.6.24-rc4 as it fixes a regression introduced in rc3. Thanks! drivers/infiniband/hw/ehca/ehca_qp.c |4 ++-- 1 files changed, 2 insertions

[PATCH 2/2] IB/ehca: Fix static rate calculation

2007-11-02 Thread Joachim Fenkes
The IPD formula was a little off and assumed a fixed physical link rate; fix the formula and query the actual physical link rate, now that we can get it. Also, refactor the calculation into a common function ehca_calc_ipd() and use that instead of duplicating code. Signed-off-by: Joachim Fenkes

[PATCH 1/2] IB/ehca: Return physical link information in query_port()

2007-11-02 Thread Joachim Fenkes
Newer firmware versions return physical port information to the partition, so hand that information to the consumer if it's present. Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- drivers/infiniband/hw/ehca/ehca_hca.c | 20 ++-- drivers/infiniband/hw/ehc

[PATCH 0/2] IB/ehca: Return physical link information, fix static rate calculation

2007-11-02 Thread Joachim Fenkes
supported [2/2] fixes static rate calculation based on that info The patches will apply, in order, on top of Roland's for-2.6.24 branch. Please review them and apply for 2.6.24-rc2 if you think they're okay. Thanks and regards, Joachim -- Joachim Fenkes -- eHCA Linux Driver Developer an

Re: [PATCH 4/5] ibmebus: Move to of_device and of_platform_driver, match eHCA and eHEA drivers

2007-10-17 Thread Joachim Fenkes
On Tuesday 16 October 2007 17:27, Stephen Rothwell wrote: > One small change - I intend to remove the name and owner fields from > struct of_platform_driver, so you should not bother initialising the name > field and just initialise the name field of the embedded struct > device_driver instead. T

[PATCH 5/5] IB/ehca: Enable large page MRs by default

2007-10-16 Thread Joachim Fenkes
Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- drivers/infiniband/hw/ehca/ehca_main.c |2 +- 1 files changed, 1 insertions(+), 1 deletions(-) diff --git a/drivers/infiniband/hw/ehca/ehca_main.c b/drivers/infiniband/hw/ehca/ehca_main.c index d477dc3..2f51c13 100644 --- a/d

[PATCH 4/5] IB/ehca: Change meaning of hca_cap_mr_pgsize

2007-10-16 Thread Joachim Fenkes
ehca_shca.hca_cap_mr_pgsize now contains all supported page sizes ORed together. This makes some checks easier to code and understand, plus we can return this value verbatim in query_hca(), fixing a problem with SRP (reported by Anton Blanchard -- thanks!). Signed-off-by: Joachim Fenkes <[EM

[PATCH 3/5] IB/ehca: Fix ehca_encode_hwpage_size() and alloc_fmr()

2007-10-16 Thread Joachim Fenkes
Simplify ehca_encode_hwpage_size(), fixing an infinite loop for pgsize == 0 in the process. Fix the bug in alloc_fmr() that triggered the loop. Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- drivers/infiniband/hw/ehca/ehca_mrmw.c | 15 --- 1 files changed, 4 inse

[PATCH 2/5] IB/ehca: Fix masking error in {,re}reg_phys_mr()

2007-10-16 Thread Joachim Fenkes
Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- drivers/infiniband/hw/ehca/ehca_mrmw.c |4 ++-- 1 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/hw/ehca/ehca_mrmw.c b/drivers/infiniband/hw/ehca/ehca_mrmw.c index da88738..16c9efd 100644 --- a/d

[PATCH 1/5] IB/ehca: Supply QP token for SRQ base QPs

2007-10-16 Thread Joachim Fenkes
Because hardware reports the SRQ token in RWQEs of SRQ base QPs, supply the base QP token as SRQ token, so we can properly find the SRQ base QP. Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- drivers/infiniband/hw/ehca/ehca_qp.c |4 +++- 1 files changed, 3 insertions(+), 1 del

[PATCH 0/5] IB/ehca: SRQ and MR/MW fixes

2007-10-16 Thread Joachim Fenkes
hca_cap_mr_pgsize and fixes a problem with ib_srp [5/5] enables large page MRs by default I built the patches on top of Roland's for-2.6.24 git branch. Please review and queue them for 2.6.24-rc1 if you're okay with them. Thanks! Cheers, Joachim -- Joachim Fenkes  --  eHCA Linux Driver Dev

Re: [PATCH 4/5] ibmebus: Move to of_device and of_platform_driver, match eHCA and eHEA drivers

2007-10-16 Thread Joachim Fenkes
vely. Match the external ibmebus > > > > interface and drivers using it. > > > > > > > > Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> > > > > > > This is somewhat difficult as this patch touches files that are the > > > respon

[PATCH 5/5] ibmebus: More speaking error return code in ibmebus_store_probe()

2007-09-26 Thread Joachim Fenkes
Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- arch/powerpc/kernel/ibmebus.c |4 ++-- 1 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c index c1e2963..0bd186c 100644 --- a/arch/powerpc/kernel/ibmebus.c

[PATCH 4/5] ibmebus: Move to of_device and of_platform_driver, match eHCA and eHEA drivers

2007-09-26 Thread Joachim Fenkes
Replace struct ibmebus_dev and struct ibmebus_driver with struct of_device and struct of_platform_driver, respectively. Match the external ibmebus interface and drivers using it. Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- drivers/infiniband/hw/ehca/ehca_classes.h |2 +- d

[PATCH 3/5] ibmebus: Add device creation and bus probing based on of_device

2007-09-26 Thread Joachim Fenkes
, the devtree is matched against its matchlist. Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- arch/powerpc/kernel/ibmebus.c | 100 +--- 1 files changed, 82 insertions(+), 18 deletions(-) diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/

[PATCH 2/5] ibmebus: Remove bus match/probe/remove functions

2007-09-26 Thread Joachim Fenkes
will be happy. Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- arch/powerpc/kernel/ibmebus.c | 199 ++--- 1 files changed, 6 insertions(+), 193 deletions(-) diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c index d

[PATCH 1/5] PowerPC: Move of_device allocation into of_device.[ch]

2007-09-26 Thread Joachim Fenkes
stead of reinventing the wheel. Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- include/asm-powerpc/of_device.h |4 ++ include/linux/of_device.h |5 ++ arch/powerpc/kernel/of_device.c | 80 + arch/powerpc/kernel/of_platfo

[PATCH 0/5] [REPOST] PowerPC: ibmebus refactoring and fixes

2007-09-26 Thread Joachim Fenkes
nux/of_device.h |5 + 11 files changed, 228 insertions(+), 350 deletions(-) -- Joachim Fenkes  --  eHCA Linux Driver Developer and Hardware Tamer IBM Deutschland Entwicklung GmbH  --  Dept. 3627 (I/O Firmware Dev. 2) Schoenaicher Strasse 220  --  71032 Boeblingen  --  Germany eMail: [

Re: [PATCH 1/5] PowerPC: Move of_device allocation into of_device.[ch]

2007-09-26 Thread Joachim Fenkes
Arnd Bergmann <[EMAIL PROTECTED]> wrote on 25.09.2007 16:27:57: > The patch looks good to me, especially since you did exactly what I > suggested ;-) Yes, our discussions were very productive. Thanks and sorry I forgot to mention your input. > Maybe the description should have another sentence

Re: [PATCH 2/5] ibmebus: Remove bus match/probe/remove functions

2007-09-26 Thread Joachim Fenkes
Arnd Bergmann <[EMAIL PROTECTED]> wrote on 25.09.2007 16:29:51: > The description makes it sound like a git-bisect would get broken > by this patch, which should never happen. If the patch indeed > ends up with a broken kernel, it would be better to merge it with > the later patch that fixes the c

Re: [PATCH 3/5] ibmebus: Add device creation and bus probing based on of_device

2007-09-26 Thread Joachim Fenkes
> > +/* These devices will automatically be added to the bus during init */ > > +static struct of_device_id builtin_matches[] = { > > + { .name = "lhca" }, > > + { .compatible = "IBM,lhca" }, > > + { .name = "lhea" }, > > + { .compatible = "IBM,lhea" }, > > + {}, > > +}; > > + > > Hmm,

Re: [PATCH 4/5] ibmebus: Move to of_device and of_platform_driver, match eHCA and eHEA drivers

2007-09-26 Thread Joachim Fenkes
Arnd Bergmann <[EMAIL PROTECTED]> wrote on 25.09.2007 16:42:40: > This is missing a description, The description is "ibmebus: Move to of_device and of_platform_driver, match eHCA and eHEA drivers" -- I thought that should be enough since the patch is rather straightforward. I can add a more det

[PATCH 5/5] ibmebus: More speaking error return code in ibmebus_store_probe()

2007-09-25 Thread Joachim Fenkes
Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- arch/powerpc/kernel/ibmebus.c |4 ++-- 1 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c index 379472f..8c08a98 100644 --- a/arch/powerpc/kernel/ibmebus.c

[PATCH 4/5] ibmebus: Move to of_device and of_platform_driver, match eHCA and eHEA drivers

2007-09-25 Thread Joachim Fenkes
Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- drivers/infiniband/hw/ehca/ehca_classes.h |2 +- drivers/net/ehea/ehea.h |2 +- include/asm-powerpc/ibmebus.h | 38 +++ arch/powerpc/kernel/ibmebus.c | 28 ++- d

[PATCH 3/5] ibmebus: Add device creation and bus probing based on of_device

2007-09-25 Thread Joachim Fenkes
, the devtree is matched against its matchlist. Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- arch/powerpc/kernel/ibmebus.c | 97 ++--- 1 files changed, 81 insertions(+), 16 deletions(-) diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/

[PATCH 2/5] ibmebus: Remove bus match/probe/remove functions

2007-09-25 Thread Joachim Fenkes
ibmebus_{,un}register_driver() are replaced by dummy functions because ibmebus is temporarily unusable in this transitional state. Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- arch/powerpc/kernel/ibmebus.c | 199 ++--- 1 files changed, 6 inse

[PATCH 1/5] PowerPC: Move of_device allocation into of_device.[ch]

2007-09-25 Thread Joachim Fenkes
Extract generic of_device allocation code from of_platform_device_create() and move it into of_device.[ch], called of_device_alloc(). Also, there's now of_device_free() which puts the device node. Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- include/asm-powerpc/of_device

[PATCH 0/5] PowerPC: ibmebus refactoring and fixes

2007-09-25 Thread Joachim Fenkes
deletions(-) -- Joachim Fenkes  --  eHCA Linux Driver Developer and Hardware Tamer IBM Deutschland Entwicklung GmbH  --  Dept. 3627 (I/O Firmware Dev. 2) Schoenaicher Strasse 220  --  71032 Boeblingen  --  Germany eMail: [EMAIL PROTECTED] ___ Linuxppc-d

Re: [PATCH 02/12] IB/ehca: Add 1 is not longer needed because of firmware interface change

2007-09-14 Thread Joachim Fenkes
Roland Dreier <[EMAIL PROTECTED]> wrote on 12.09.2007 22:21:54: > What happens if someone runs the new driver with older firmware? Or > what if someone upgrades the firmware without updating the driver? Thanks for pointing our noses to this. Your comment triggered some further internal discussi

[PATCH 3/3] IB/ehca: Make sure user pages are from hugetlb before using MR large pages

2007-09-13 Thread Joachim Fenkes
...because, on virtualized hardware like System p, we can't be sure that the physical pages behind them are contiguous. Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- drivers/infiniband/hw/ehca/ehca_mrmw.c | 25 +++-- 1 files changed, 15 insertions(+), 1

[PATCH 2/3] IB/umem: Add hugetlb flag to struct ib_umem

2007-09-13 Thread Joachim Fenkes
During ib_umem_get(), determine whether all pages from the memory region are hugetlb pages and report this in the "hugetlb" field. Low-level driver can use this information if they need it. Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- drivers/infiniband/co

[PATCH 1/3] IB/ehca: Fix large page HW cap defines

2007-09-13 Thread Joachim Fenkes
From: Hoang-Nam Nguyen <[EMAIL PROTECTED]> Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- drivers/infiniband/hw/ehca/ehca_classes.h |8 1 files changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/infiniband/hw/ehca/ehca_classes.h b/drivers/infini

[PATCH 0/3] IB/ehca: MR/MW fixes

2007-09-13 Thread Joachim Fenkes
inally uses the hugetlb flag in ehca_reg_user_mr() The patches should apply cleanly, in order, on top of my previous 12-patch set. Please review the changes and apply the patches for 2.6.24 if they are okay. Regards, Joachim -- Joachim Fenkes  --  eHCA Linux Driver Developer and Hardware Tamer

Re: [PATCH] IB/ehca: Make sure user pages are from hugetlb before using MR large pages

2007-09-13 Thread Joachim Fenkes
Roland Dreier <[EMAIL PROTECTED]> wrote on 13.09.2007 06:33:45: > > -#define HCA_CAP_MR_PGSIZE_4K 1 > > -#define HCA_CAP_MR_PGSIZE_64K 2 > > -#define HCA_CAP_MR_PGSIZE_1M 4 > > -#define HCA_CAP_MR_PGSIZE_16M 8 > > +#define HCA_CAP_MR_PGSIZE_4K 0x8000 > > +#define HCA_CAP_MR_PGSIZE_64K

[PATCH 08/12] IB/ehca: Replace get_paca()->paca_index by the more portable raw_smp_processor_id()

2007-09-12 Thread Joachim Fenkes
We can use raw_smp_processor_id() here because the processor ID is only used for debug output and may therefore be preemption-unsafe. Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- This is the same patch, but with smp_processor_id() replaced by raw_smp_processor_id(), as kindly p

Re: [PATCH 08/12] IB/ehca: Replace get_paca()->paca_index by the more portable smp_processor_id()

2007-09-12 Thread Joachim Fenkes
On Tuesday 11 September 2007 16:51, Nathan Lynch wrote: > > - get_paca()->paca_index, __FUNCTION__, \ > > + smp_processor_id(), __FUNCTION__, \ > > I think I see these macros used in preemptible code (e.g. ehca_probe), > where smp_processo

[PATCH] IB/ehca: Make sure user pages are from hugetlb before using MR large pages

2007-09-12 Thread Joachim Fenkes
From: Hoang-Nam Nguyen <[EMAIL PROTECTED]> ...because, on virtualized hardware like System p, we can't be sure that the physical pages behind them are contiguous. Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- Another patch for 2.6.24 that will apply cleanly on t

[PATCH 12/12] IB/ehca: Bump version number and change its format

2007-09-11 Thread Joachim Fenkes
Nobody needed the SVNEHCA_ prefix anyway. Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- drivers/infiniband/hw/ehca/ehca_main.c |6 -- 1 files changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/hw/ehca/ehca_main.c b/drivers/infiniband/hw/ehca/ehca_

[PATCH 11/12] IB/ehca: Serialize MR alloc and MR free hvCalls

2007-09-11 Thread Joachim Fenkes
Some firmware levels exhibit a race condition between H_ALLOC_RESOURCE(MR) and H_FREE_RESOURCE(MR). Work around this problem by locking these hvCalls against each other. Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- drivers/infiniband/hw/ehca/hcp_if.c

[PATCH 10/12] IB/ehca: Path migration support

2007-09-11 Thread Joachim Fenkes
Rectify some modify_qp() issues related to path migration. Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- drivers/infiniband/hw/ehca/ehca_irq.c |4 +- drivers/infiniband/hw/ehca/ehca_qp.c | 90 - 2 files changed, 68 insertions(+), 26 del

[PATCH 08/12] IB/ehca: Replace get_paca()->paca_index by the more portable smp_processor_id()

2007-09-11 Thread Joachim Fenkes
Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- drivers/infiniband/hw/ehca/ehca_tools.h | 14 +++--- 1 files changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/infiniband/hw/ehca/ehca_tools.h b/drivers/infiniband/hw/ehca/ehca_tools.h index f9b264b..863f972

[PATCH 09/12] IB/ehca: Add check for max #SGE to create_qp()

2007-09-11 Thread Joachim Fenkes
Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- drivers/infiniband/hw/ehca/ehca_qp.c | 14 +- 1 files changed, 13 insertions(+), 1 deletions(-) diff --git a/drivers/infiniband/hw/ehca/ehca_qp.c b/drivers/infiniband/hw/ehca/ehca_qp.c index d2ab84a..7154f62 100644

[PATCH 07/12] IB/ehca: ehca_gen_warn() should always print

2007-09-11 Thread Joachim Fenkes
Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- drivers/infiniband/hw/ehca/ehca_tools.h |9 +++-- 1 files changed, 3 insertions(+), 6 deletions(-) diff --git a/drivers/infiniband/hw/ehca/ehca_tools.h b/drivers/infiniband/hw/ehca/ehca_tools.h index 57c77a7..f9b264b 100644

[PATCH 06/12] IB/ehca: Print return codes as signed decimal integers

2007-09-11 Thread Joachim Fenkes
...because -12 is easier to read than FFF4. Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- drivers/infiniband/hw/ehca/ehca_cq.c | 14 +++--- drivers/infiniband/hw/ehca/ehca_hca.c|2 +- drivers/infiniband/hw/ehca/ehca_main.c | 24 +- drivers/infiniband/h

[PATCH 05/12] IB/ehca: Refactor hvcall tracing

2007-09-11 Thread Joachim Fenkes
Change hvcall trace output towards better readability: reg numbers instead of argument numbers, return code as signed decimal instead of unsigned hex. Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- drivers/infiniband/hw/ehca/hcp_if.c | 57 ++ 1

[PATCH 04/12] IB/ehca: Use remap_4k_pfn() to map firmware contexts to user space

2007-09-11 Thread Joachim Fenkes
e proper virtual address. For details about remap_4k_pfn(), see commit 721151d0 or http://patchwork.ozlabs.org/linuxppc/patch?id=10281 Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- drivers/infiniband/hw/ehca/ehca_classes.h |4 +++- drivers/infiniband/hw/ehca/ehca_cq.c

[PATCH 03/12] IB/ehca: Support more than 4k QPs for userspace and kernelspace

2007-09-11 Thread Joachim Fenkes
From: Stefan Roscher <[EMAIL PROTECTED]> Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- drivers/infiniband/hw/ehca/ehca_cq.c |7 ++- drivers/infiniband/hw/ehca/ehca_main.c |2 +- drivers/infiniband/hw/ehca/ehca_qp.c |9 +++-- drivers/infini

[PATCH 02/12] IB/ehca: Add 1 is not longer needed because of firmware interface change

2007-09-11 Thread Joachim Fenkes
From: Stefan Roscher <[EMAIL PROTECTED]> Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- drivers/infiniband/hw/ehca/hcp_if.c |4 ++-- 1 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/hw/ehca/hcp_if.c b/drivers/infiniband/hw/ehca/hcp_if.c i

[PATCH 01/12] IB/ehca: Small QP userspace support

2007-09-11 Thread Joachim Fenkes
From: Stefan Roscher <[EMAIL PROTECTED]> Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- drivers/infiniband/hw/ehca/ehca_qp.c |7 +++ drivers/infiniband/hw/ehca/ipz_pt_fn.c |1 + 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/infini

[PATCH 00/12] IB/ehca: New features and fixes for 2.6.24

2007-09-11 Thread Joachim Fenkes
in order, against Roland's git. Please review the changes and apply the patches for 2.6.24 if they are okay. Regards, Joachim -- Joachim Fenkes  --  eHCA Linux Driver Developer and Hardware Tamer IBM Deutschland Entwicklung GmbH  --  Dept. 3627 (I/O Firmware Dev. 2) Schoenaicher Strasse 2

Re: [PATCH 2.6.23] ibmebus: Prevent bus_id collisions

2007-08-31 Thread Joachim Fenkes
> > The plaintiff makes a valid point. How about a staging approach: We put > > the patch as it is now into 2.6.23 so the problem is fixed, and I'll post > > a "nice" version with autoloading support and a generic of_make_bus_id > > function for 2.6.24. Agree? > > Ok, sounds fair. Can you ma

Re: [PATCH 2.6.23] ibmebus: Prevent bus_id collisions

2007-08-31 Thread Joachim Fenkes
Hi, Arnd, > The whole logic of dynamically adding and removing device is rather bogus, > and it prevents autoloading of device drivers. of_platform_make_bus_id > is the function that is responsible for creating unique names over there. The plaintiff makes a valid point. How about a staging appr

[PATCH 2/2] IB/ehca: SRQ fixes to enable IPoIB CM

2007-08-31 Thread Joachim Fenkes
a) Report max_srq > 0 if SRQ is supported b) Report "last wqe reached" event when base QP dies Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]> --- drivers/infiniband/hw/ehca/ehca_hca.c | 10 +-- drivers/infiniband/hw/ehca/ehca_irq.c | 48 +-

  1   2   >