shefty [Wed, 23 Jul 2008 21:13:05 +0000 (21:13 +0000)]
uvp/av: complete all processing in pre_create/destroy_av() calls
According to the documentation, if a UVP returns IB_VERBS_PROCESSING_DONE
from a pre() IOCTL call, then all verbs related processing has completed.
The mthca pre_create_av() and pre_destroy_av() uvp implementation can
both return IB_VERBS_PROCESSING_DONE, but requires that users still call
post_create_av() and post_destroy_av(). Fix the mthca UVP to complete all
processing in the pre() IOCTL calls when returning IB_VERBS_PROCESSING_DONE,
and update IBAL to remove unnecessary post() IOCTL calls.
Signed-off-by: Sean Hefty <sean.hefty@intel.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1442
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
shefty [Wed, 23 Jul 2008 21:08:13 +0000 (21:08 +0000)]
uvp/ci_umv_buf: always allocate uvp buffer
The UVP controls the ci_umv_buf, but does not allocate the p_inout_buf if it
is non-zero. However, the uvp frees the buffer later. It should always
allocate the buffer, since the caller does not know the required size and
cannot allocate it on the uvp's behalf. This avoids an unneeded
initialization by the caller, and the if check by the uvp.
Signed-off-by: Sean Hefty <sean.hefty@intel.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1441
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
shefty [Wed, 23 Jul 2008 21:03:49 +0000 (21:03 +0000)]
verbs: optimize work request/completion structures
Change work completion types to quickly allow a user to determine if a
completions is for a send or receive. Align work request and work
completion type values to be the same for consistency.
Update work request structure to avoid unnecessary internal padding and
allocating extra unused space for pointers and structures that can be
part of a union. Arrange structure layout to allow casting between
the UVP, IBAL, WinVerbs, and libibverbs work requests.
Update debug print functions to match changes.
Signed-off-by: Sean Hefty <sean.hefty@intel.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1440
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
shefty [Wed, 23 Jul 2008 20:34:43 +0000 (20:34 +0000)]
mthca/pnp: respond to query interface
Add infrastructure to respond to query calls for the
RDMA_INTERFACE_VERB interface.
Signed-off-by: Sean Hefty <sean.hefty@intel.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1439
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
shefty [Wed, 23 Jul 2008 20:24:16 +0000 (20:24 +0000)]
uvp: obtain desired interface by GUID
The current uvp_get_interface() routine takes a structure as input.
Included in the structure is a version number.
A better solution to supporting multiple interfaces is to define
interfaces using GUIDs. This not only allows different versions of
the same interface (for example the UVP interface), but also provides
a mechanism that can be used to add new interfaces without affecting
existing ABIs or APIs.
This will make it easier to extend the existing interfaces in the future.
Signed-off-by: Sean Hefty <sean.hefty@intel.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1438
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
shefty [Wed, 23 Jul 2008 20:20:52 +0000 (20:20 +0000)]
cq: allow polling with an array of wc's
Allow polling for a list of work completions using an array of
completion structures, rather than a linked list. This avoids needing
to walk the list to link the structures together before calling poll,
which is a fast path operation.
A new completion structure is added that provides the qp_context
associated with a completion. This avoids changes to the existing
ULPs, while taking advantage of the underlying UVP capabilities.
Providing the qp_context is useful when dealing with SRQ.
Signed-off-by: Sean Hefty <sean.hefty@intel.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1437
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
shefty [Wed, 23 Jul 2008 20:14:05 +0000 (20:14 +0000)]
uvp/interface: add support for reporting QP context in WCs
Extend the uvp_interface to include support for reporting the QP context in
work completions. The required changes are to allow specifying a qp_context
in the pre_create_qp() IOCTL call, and reporting the qp_context through the
work completion structure.
Signed-off-by: Sean Hefty <sean.hefty@intel.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1436
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
shefty [Wed, 23 Jul 2008 20:09:45 +0000 (20:09 +0000)]
events: allow callbacks per CQ, QP, or SRQ
The underlying hardware drivers both support setting callbacks on a per
widget (CQ, QP, or SRQ) basis, but the verbs interface only allows one
global event handler and one completion handler for the HCA. Modify the
verbs interface to allow setting events callbacks directly on the HCA
objects. This allows the HCA to support multiple consumers of its
interface, and users can optimize their event handling based on the call.
For example, the HCA drivers can invoke callbacks directly to the ULPs
without the calls first being filtered by IBAL. This will improve
completion event reporting.
To minimize changes to the existing stack, the current event handler is
used for all events, regardless of type. Optimizations are left for a
separate patch.
Signed-off-by: Sean Hefty <sean.hefty@intel.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1435
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
shefty [Wed, 23 Jul 2008 20:01:18 +0000 (20:01 +0000)]
ib_types/events: remove trap data from event record
The trap data in the ib_event_rec is both incomplete (wrt the types of
traps that it can report) and unused. Remove it to save stack space.
This will also make it cleaner to have event handlers per QP, SRQ, CQ, etc.
Signed-off-by: Sean Hefty <sean.hefty@intel.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1434
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
shefty [Wed, 23 Jul 2008 19:56:47 +0000 (19:56 +0000)]
complib/cl_byteswap_osd.h: Add missing include file for stdlib.h
Avoid build errors when cl_byteswap_osd.h is included directly.
Signed-off-by: Sean Hefty <sean.hefty@intel.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1433
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
tzachid [Tue, 22 Jul 2008 06:55:12 +0000 (06:55 +0000)]
Removing false Prefast alarms by:
Adding __analysis_assume() to ASSERT when DBG and _PREFAST_ are used for use in all the WinOF tree.
Adding __pragma(warning(suppress:6326)) to suppress constants compare warning (performance decrease is acceptable since this is chked code/ heavy windows event logging.
Signed by:Doron Tsur
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1431
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
tzachid [Tue, 22 Jul 2008 06:48:18 +0000 (06:48 +0000)]
[IPOIB, MLX4] Checksum offload (mlnx: 2828)
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1430
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
tzachid [Tue, 22 Jul 2008 06:30:21 +0000 (06:30 +0000)]
[mlx4] Use t-first interrupts by default. (mlnx: 2836)
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1429
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
stansmith [Mon, 21 Jul 2008 23:15:27 +0000 (23:15 +0000)]
[DAPL] Fully support dat_cr_accept() private data.
dapl/common/dapl_adapter_util.h
dapl/common/dapl_cr_accept.c
dapl/ibal/dapl_ibal_cm.c
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1428
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
tzachid [Mon, 21 Jul 2008 12:37:02 +0000 (12:37 +0000)]
[mlx4] Fix bug in win64 doorbell. (mlnx: 2777, 2791)
Due the bug always the code acquire the spin lock although we run on 64 bits machine
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1426
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
tzachid [Mon, 21 Jul 2008 12:16:10 +0000 (12:16 +0000)]
[mlx4] Add support for 6368 device.
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1425
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Mon, 21 Jul 2008 10:57:08 +0000 (10:57 +0000)]
[HW, TOOLS] Improve VSTAT output in case of a driver startup failure. [MLNX: 2819]
When low level drivers fail on startup, which usually happens upon an incorrect FW, they report to all the above stack a dev_id of the burning device ("livefish") and imitate such a device thereafter. It was done in order to allow to all the upper level drivers to start their work.
VSTAT shows in this case the dev_id of a "livefish", which is a bit misleading.
This patch fixes this behavior. VSTAT will now show the real dev_id. The drivers still imitate the "livefish" device. The detailed message about the startup failure can be found in System Event Log (as it always was).
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1424
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Mon, 21 Jul 2008 10:36:38 +0000 (10:36 +0000)]
[MLX4] added a possibility to register event handler with MLX4_BUS driver. [MLNX:2786]
It is an extension of the Ethernet interface of mlx4_bus driver.
The mlx4_eth handler is called on DPC level upon asynchronous events like PORT_UP/PORT_DOWN, passing event data and the callback context parameter, set upon registration.
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1423
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Mon, 21 Jul 2008 10:26:12 +0000 (10:26 +0000)]
[HW, TOOLS] fixed a bug, causing incorrect value of max_addr_handles in query_ca. [MLNX: 2790]
It is relevant only for Tavor, but the changes influence all drivers and modify ABI, so the AL_IOCTL_VERSION has been increased.
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1422
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
stansmith [Fri, 18 Jul 2008 23:36:48 +0000 (23:36 +0000)]
[WinOF] buildrelease no longer contains uglt hack to work around XP32 WSD build problems.
Added a 2nd cmd line arg to set OPENIB_REV value when building installers. Fix eliminates folder structure dependency, making the script more useful to a wider audience.
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1419
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
stansmith [Fri, 18 Jul 2008 23:33:50 +0000 (23:33 +0000)]
[DAPL2] DAPL2 debug cleanup, along with patches to IBAL provider to correctly handle accept side private_data.
Fixed the async QP & CQ error handlers as they had not been updated with latest typedef's (ib_async_qp_handler_t & ib_async_cq_handler_t), hence calling arg mismatch vs. handling definitions. Resulted in bad EP pointer dereference during Async QP error handling.
Added debug value DAPL_DBG_EVD_DEQUEUE to throttle debug output when watching EVD dequeue operations.
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1418
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
stansmith [Fri, 18 Jul 2008 00:22:47 +0000 (00:22 +0000)]
[WinOF] Don't build WSD for WXP32
tools\wsdinstall\user\makefile
tools\ulp\wsd\user\makefile
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1414
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
stansmith [Fri, 18 Jul 2008 00:19:39 +0000 (00:19 +0000)]
[WinOF] added support for mthca.inf from trunk\bin\kernel\xxx
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1413
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
stansmith [Fri, 18 Jul 2008 00:17:11 +0000 (00:17 +0000)]
[MTHCA] mthca.inf file stamping support.
rename mthca.inf --> mthca.inx
added makefile.inc
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1412
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Thu, 17 Jul 2008 08:16:01 +0000 (08:16 +0000)]
[IBAL] This patch fixes the build error due to CSQ use for XP builds.
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1408
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
stansmith [Thu, 17 Jul 2008 01:08:45 +0000 (01:08 +0000)]
[WinOF] for XP32 builds, place holder files (until someone comes up with a better plan) utilized by makebin to cover the case of WSD not available for XP32. netipoib-xp32.inf intentionally contains 64 bit sections as to minimize differences between it and netipoib.inf file.
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1404
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
stansmith [Thu, 17 Jul 2008 01:05:08 +0000 (01:05 +0000)]
[WinOF] updated for .inf file stamping & .inf file relocation to trunk\bin path
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1403
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
stansmith [Tue, 15 Jul 2008 15:06:51 +0000 (15:06 +0000)]
[DAPL2] updated old license header text to be consistent with OFA BSD license; 1st commit was mislabeled [DAPL2] should have been [DAPL].
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1396
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
stansmith [Tue, 15 Jul 2008 15:04:52 +0000 (15:04 +0000)]
[DAPL2] updated old license header text to be consistent with OFA BSD license.
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1395
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
stansmith [Sun, 13 Jul 2008 22:26:58 +0000 (22:26 +0000)]
[DAPL] fix x86(32-bit) pointer sign extension warning when going to wr_id (u64).
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1394
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Sun, 13 Jul 2008 11:35:53 +0000 (11:35 +0000)]
[IBAL] Limit time spent at DISPATCH_LEVEL when processing MADs.
In working with some switch SMs, I found that under stress the QP0 MAD processing could get delayed by eternal QP1 MAD processing (from hitting the SA for path queries). This caused the SMs to remove the node from the fabric (multicast group membership, etc) because it appeared unreachable.
This patch adds a DPC for QP0 and QP1 to the SMI, and limits the SMI to processing 16 MADs before re-queueing the DPC to the DPC queue.
Because QP0 processing is crucial to the fabric operating properly, the QP0 DPC is set to high importance so that it always gets queued to the front of the DPC queue, pre-empting any QP1 processing (among other things).
In any case, with this patch all my changes have now been mailed to the list.
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1393
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Sun, 13 Jul 2008 11:31:46 +0000 (11:31 +0000)]
[ALL] Enable warning C4826.
Warning C4826 warns you if you have signed pointer extension when a 32-bit pointer is extended to 64-bits. This patch turns the warning on by default (for any users of complib), and fixes all instances of problematic code. It also eradicates __ptr64 usage from the Qlogic VNIC driver.
Code affected:
- IBAL
- MTHCA
- MLX4
- QLGCVNIC
Note that I didn't change DAPL because it's licensed under the CPL and not BSD. So someone else will have to fix that. In fact, DAPL should probably just go back into the SourceForge project rather than being duplicated everywhere. Code in the WinOF SVN should be BSD only according to the contributor's agreement.
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1392
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Sun, 13 Jul 2008 11:24:55 +0000 (11:24 +0000)]
[IBAL] Refine UAL_NDI_NOOP handler.
The UAL_NDI_NOOP IOCTL handler was added to allow memory registration in user-mode to notify a client using an I/O completion port. This patch extends the functionality to allow the IOCTL to return either STATUS_SUCCESS or STATUS_TIMEOUT. The STATUS_TIMEOUT facility is used by the NetworkDirect provider when IBAT returns pending. It's crude, but gets the job done.
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1391
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Sun, 13 Jul 2008 11:19:40 +0000 (11:19 +0000)]
[IBAL] Fix TO_LONG_PTR use in IOCTLs. Re-applied 1387 patch.
Some IOCTLs transfer API structures with embedded pointers. These embedded pointers use the TO_LONG_PTR macro to pad everything out so that __ptr64 isn't used. The idea here is fine, but the change to eliminate the __ptr64 was riddled with problems that weren't caught by the find/replace brute force code changes.
Specifically, you had code like this:
>core\al\user\ual_mr.c, ual_reg_mem@67
>
> /* Clear the mr_ioctl */
> cl_memclr( &mr_ioctl, sizeof(mr_ioctl) );
In theory, no uninitialized upper 32-bits of a TO_LONG_PTR structure would get sent to the kernel.
> mr_ioctl.in.h_pd = h_pd->obj.hdl;
> mr_ioctl.in.mem_create = *p_mr_create;
Oops, the mem_create in the IOCTL buffer was overwritten with the caller's structure, which may have uninitialized padding. This isn't subsequently cleared, effectively defeating the purpose of the memclr.
>+ mr_ioctl.in.mem_create.vaddr_padding =
>+ (ULONG_PTR)p_mr_create->vaddr;
Pretty much every instance of embedded structures in IOCTLs was broken in this way. There were cases where things were closer to being right:
>core\al\user\ual_qp.c, ual_create_qp@313
> */
> qp_ioctl.in.h_pd = h_pd->obj.hdl;
> qp_ioctl.in.qp_create = *p_qp_create;
Ok, same copy issue as above...
> qp_ioctl.in.qp_create.h_rq_cq =
> (ib_cq_handle_t)HDL_TO_PTR(p_qp_create->h_rq_cq->obj.hdl);
> qp_ioctl.in.qp_create.h_sq_cq =
>
> (ib_cq_handle_t)HDL_TO_PTR(p_qp_create->h_sq_cq->obj.hdl);
Ah, close but not quite - you have the assignment, but it only assigns the pointer part of the TO_LONG_PTR union. The padding is still a copy of the user's structure, potentially giving an invalid handle in the kernel. All uses of HDL_TO_PTR were eliminated as they didn't actually accomplish anything.
This patch fixes this, and always uses the 'padding' field of the TO_LONG_PTR union so that the value is always fully set.
There's also a bug fixed in UD work requests that get sent via IOCTL - the AV handle was never swizzled to its appropriate kernel handle.
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1390
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Sun, 13 Jul 2008 11:12:55 +0000 (11:12 +0000)]
[IBAL] Remove TO_LONG_PTR from IOCTL structures. Re-applied 1386 patch with out SMI changes.
This patch removes all instances of TO_LONG_PTR from internal IOCTL structures. The only place TO_LONG_PTR should be used is in public structures that contain pointers and are exchanged between user-mode and kernel-mode. Actually, the code should ideally have proxy structures for such API structures into which API structure members
are copied member-wise, and whose size is fixed. Unused pointers should be stripped from the IOCTL proxy structures. But that's a change for some other time...
All fields in internal IOCTL structures that were formerly TO_LONG_PTR are not uint64_t, and all uses have appropriate casts.
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1389
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Sun, 13 Jul 2008 11:08:58 +0000 (11:08 +0000)]
[IBAL] revert two previous patches
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1388
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Sun, 13 Jul 2008 10:54:52 +0000 (10:54 +0000)]
[IBAL] Fix TO_LONG_PTR use in IOCTLs.
Some IOCTLs transfer API structures with embedded pointers. These embedded pointers use the TO_LONG_PTR macro to pad everything out so that __ptr64 isn't used. The idea here is fine, but the change to eliminate the __ptr64 was riddled with problems that weren't caught by the find/replace brute force code changes.
Specifically, you had code like this:
>core\al\user\ual_mr.c, ual_reg_mem@67
>
> /* Clear the mr_ioctl */
> cl_memclr( &mr_ioctl, sizeof(mr_ioctl) );
In theory, no uninitialized upper 32-bits of a TO_LONG_PTR structure would get sent to the kernel.
> mr_ioctl.in.h_pd = h_pd->obj.hdl;
> mr_ioctl.in.mem_create = *p_mr_create;
Oops, the mem_create in the IOCTL buffer was overwritten with the caller's structure, which may have uninitialized padding. This isn't subsequently cleared, effectively defeating the purpose of the memclr.
>+ mr_ioctl.in.mem_create.vaddr_padding =
>+ (ULONG_PTR)p_mr_create->vaddr;
Pretty much every instance of embedded structures in IOCTLs was broken in this way. There were cases where things were closer to being right:
>core\al\user\ual_qp.c, ual_create_qp@313
> */
> qp_ioctl.in.h_pd = h_pd->obj.hdl;
> qp_ioctl.in.qp_create = *p_qp_create;
Ok, same copy issue as above...
> qp_ioctl.in.qp_create.h_rq_cq =
> (ib_cq_handle_t)HDL_TO_PTR(p_qp_create->h_rq_cq->obj.hdl);
> qp_ioctl.in.qp_create.h_sq_cq =
>
> (ib_cq_handle_t)HDL_TO_PTR(p_qp_create->h_sq_cq->obj.hdl);
Ah, close but not quite - you have the assignment, but it only assigns the pointer part of the TO_LONG_PTR union. The padding is still a copy of the user's structure, potentially giving an invalid handle in the kernel. All uses of HDL_TO_PTR were eliminated as they didn't actually accomplish anything.
This patch fixes this, and always uses the 'padding' field of the TO_LONG_PTR union so that the value is always fully set.
There's also a bug fixed in UD work requests that get sent via IOCTL - the AV handle was never swizzled to its appropriate kernel handle.
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1387
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Sun, 13 Jul 2008 10:51:31 +0000 (10:51 +0000)]
[IBAL] Remove TO_LONG_PTR from IOCTL structures.
This patch removes all instances of TO_LONG_PTR from internal IOCTL structures. The only place TO_LONG_PTR should be used is in public structures that contain pointers and are exchanged between user-mode and kernel-mode. Actually, the code should ideally have proxy structures for such API structures into which API structure members
are copied member-wise, and whose size is fixed. Unused pointers should be stripped from the IOCTL proxy structures. But that's a change for some other time...
All fields in internal IOCTL structures that were formerly TO_LONG_PTR are not uint64_t, and all uses have appropriate casts.
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1386
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Sun, 13 Jul 2008 10:47:12 +0000 (10:47 +0000)]
[IBAL] Remove PD context from IOCTLs.
IBAL's ib_query_qp and ib_query_mw IOCTLs return the PD context in the output IOCTL buffer. It is however never referenced.
This patch removes the fields (which had been changed to TO_LONG_PTR).
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1385
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Sun, 13 Jul 2008 10:43:22 +0000 (10:43 +0000)]
[IBAL, HW] Remove pointers from ci_umv_buf_t.
Part of cleaning up the __ptr64 stuff properly - rather than use the TO_LONG_PTR in the ci_umv_buf_t structure, use uint64_t.
The problem with using TO_LONG_PTR in structures that are exchanged between 32-bit clients and 64-bit drivers is that care must be taken to ensure that the upper 'padding' bytes are cleared properly.
Making the field a uint64_t makes it fool proof (though it does require casting, but at least the compiler will trap errors unlike for the padding.)
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1384
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Sun, 13 Jul 2008 10:39:47 +0000 (10:39 +0000)]
[INC] Clean up TO_LONG_PTR use in ib_types.h.
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1383
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Sun, 13 Jul 2008 10:34:29 +0000 (10:34 +0000)]
[INC] Remove STRUCT_PTR64.
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1382
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Sun, 13 Jul 2008 10:31:12 +0000 (10:31 +0000)]
[INC] Remove TYPEDEF_PTR64.
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1381
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Sun, 13 Jul 2008 10:28:11 +0000 (10:28 +0000)]
[IBAL, HW, IPOIB] Remove VOID_PTR64.
Also fixed GPL license and missing copyright issues.
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1380
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Sun, 13 Jul 2008 10:24:27 +0000 (10:24 +0000)]
[HW] Remove FUNC_PTR64.
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1379
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Sun, 13 Jul 2008 10:20:55 +0000 (10:20 +0000)]
[COMPLIB] This patch removes a useless comment.
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1378
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Sun, 13 Jul 2008 10:16:17 +0000 (10:16 +0000)]
[MTHCA] This patch cleans up the atomic_set function in the HCA drivers.
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1377
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Sun, 13 Jul 2008 09:10:39 +0000 (09:10 +0000)]
[IBAL] Cleanup ND reject IOCTL handling.
This patch removes a local variable, and changes the reject reason from IB_REJ_INSUF_QP to IB_REJ_USER_DEFINED.
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1376
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Sun, 13 Jul 2008 08:55:53 +0000 (08:55 +0000)]
[OPENMS] This patch removes XXX_PTR64 and TO_ULONG_PTR from OpenSM.
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1375
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Sun, 13 Jul 2008 08:52:24 +0000 (08:52 +0000)]
[IBAL] Change CEP DREP API
The al_cep_drep API currently takes the ib_cm_drep_t structure. This structure is passed in the IOCTL. It has en embedded pointer that isn't used since the private data is copied into the IOCTL structure.
This patch removes the ib_cm_drep_t structure from the IOCTL structure, and passes the private data buffer and length in explicitly.
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1374
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Sun, 13 Jul 2008 08:29:42 +0000 (08:29 +0000)]
[TOOLS] This patch cleans up the includes for the HCA co-installer and corrects the version information to correctly identify the DLL as such (rather than as an executable).
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1373
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Sun, 13 Jul 2008 08:19:26 +0000 (08:19 +0000)]
[CORE, ULP] fix file version fields. [MLNX: 2748]
Signed-off-by: Reuven Amitai <reuven@mellanox.co.il>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1372
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
stansmith [Fri, 11 Jul 2008 19:08:03 +0000 (19:08 +0000)]
[WinOF] added clean option, clearer usage test, cleanup.
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1371
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
stansmith [Fri, 11 Jul 2008 19:05:54 +0000 (19:05 +0000)]
[DAPL2] synchronize with OFED 1.4 DAT/DAPL code base.
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1370
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
ftillier [Fri, 11 Jul 2008 16:00:48 +0000 (16:00 +0000)]
Add missing copyright.
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1368
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
ftillier [Fri, 11 Jul 2008 15:59:03 +0000 (15:59 +0000)]
Add missing copyright.
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1367
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
tzachid [Thu, 10 Jul 2008 08:07:28 +0000 (08:07 +0000)]
[mlx4] move eq definitions to a common header file
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1366
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
tzachid [Thu, 10 Jul 2008 08:04:08 +0000 (08:04 +0000)]
[ipoib] Fix maximum mtu to be 4092.
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1365
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
tzachid [Thu, 10 Jul 2008 07:51:20 +0000 (07:51 +0000)]
[ipoib] fix DHCP client id insertion.
singed by: anatolyg@voltaire.com
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1364
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Wed, 9 Jul 2008 17:19:12 +0000 (17:19 +0000)]
[ALL] Remove listen error callback
The listen error callback is the vestigial tail of IBAL... At some point in the distant past, it served a function, though a dubious one at best given the implementation of the listen error callbacks in client code that all effectively generate some output but really ignore the event.
This patch eliminates the listen error callback, its associated callback record, and all the no-op handlers in the various clients.
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1363
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Wed, 9 Jul 2008 15:43:13 +0000 (15:43 +0000)]
[MLX4] fix a bug, causing successful registration of RO memory for write access
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1362
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Wed, 9 Jul 2008 15:39:26 +0000 (15:39 +0000)]
[MTHCA] Enable creating zero-sized QPs
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1361
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Wed, 9 Jul 2008 12:27:24 +0000 (12:27 +0000)]
[IBAL] Driver verifier caught this one. If an IRP is completed via IoCompletRequest the IRP dispatch routine needs to return the same status as the IRP's completion status. There's no reason to use the CL_COMPLETED value here anyway (and it should probably be eliminated to prevent exactly this type of issue.)
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1360
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Wed, 9 Jul 2008 12:22:38 +0000 (12:22 +0000)]
This patch fixes a bug in the ND proxy where an IOCTL handler would return STATUS_PENDING without marking the IRP pending.
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1359
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Wed, 9 Jul 2008 12:18:47 +0000 (12:18 +0000)]
This patch adds a missing call to destroy a QP's associated CEP if a ND-related CM REQ times out or fails for any reason.
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1358
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Wed, 9 Jul 2008 12:15:02 +0000 (12:15 +0000)]
[IBAL] This patch removes ATS queries from the ND proxy, with the anticipation that all address translation will be done by the caller (via the IBAT library).
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1357
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Wed, 9 Jul 2008 10:39:14 +0000 (10:39 +0000)]
[IBAL] Fix CEP destruction.
In my previous patch "Fix race reading/setting connection ID" I incorrectly stated that the patch changed the semantics of creation/destruction of the CEPs by providing the destroy callback at CEP creation time. It didn't, but this patch does.
Note that it also backs out the "Cleanup CEPs after child objects have been destroyed" changes, as those actually introduced the following issue:
UM listen CEPs are not tracked in AL's handle table, but can queue MADs which take a reference on the AL instance. AL's destroying callback must cleanup the CEPs to free the MADs in order for the ref count to reach zero.
The root problem, and the iterations of the fix that are apparent in the patch sequence has to do with race conditions cleaning up QPs while CM messages are being received and processed. First there was the issue of the CID stored in the QP having two reserved states and races checking/assigning this value. This was fixed (successfully) by pushing checks into the CEP manager, protected by the CEP manager's spinlock. Next was the issue that a reference on the QP is taken when the CEP is bound to a QP, but if AL was destroyed the CEP cleanup in AL would blow away the CEPs before the QPs were done being destroyed. This would leak a reference count on the QP since the CEP was destroyed without a destroy callback. The change that added a cleanup callback to AL was the first (failed) attempt to fix this (for the reasons listed above). This patch is the successful attempt to fix this, as it sets the destroy callback at creation time. No matter what path destroys the CEP, if a destroy callback was taken (because some object has a reference for the CEP), the destroy callback will always be invoked.
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1356
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Wed, 9 Jul 2008 10:26:28 +0000 (10:26 +0000)]
[IBAL] This patch fixes ND CM IOCTL handling to work properly at scale. There were several race conditions in the old code.
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1355
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Wed, 9 Jul 2008 10:25:19 +0000 (10:25 +0000)]
[MLX4] fixed incorrect mlx4\kernel\bus\ib module initialization, which caused BSOD upon disabling second HCA
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1354
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
tzachid [Wed, 9 Jul 2008 09:07:25 +0000 (09:07 +0000)]
[mlx4] allow mlx4 users to add extra eqs for their internal use.
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1353
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
tzachid [Wed, 9 Jul 2008 07:24:53 +0000 (07:24 +0000)]
[mlx4] Fix WPP for mlx4 part one
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1352
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
tzachid [Wed, 9 Jul 2008 07:15:46 +0000 (07:15 +0000)]
[WSD] Fix printing on error.
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1351
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
stansmith [Tue, 8 Jul 2008 18:58:45 +0000 (18:58 +0000)]
[WinOF] use nul device for output
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1350
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
stansmith [Tue, 8 Jul 2008 18:21:32 +0000 (18:21 +0000)]
[DAPL2] added requirement and code to enforce using delayed env. var expansion. Used to config EP tests: threads & EPs.
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1348
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
stansmith [Tue, 8 Jul 2008 18:19:10 +0000 (18:19 +0000)]
[SRP] added INX -> INF file version stamping.
INF file created in ..\..\..\bin\kernel\xxx\
.inf file version now matches .sys file version.
added makefile.inc
ib_srp.inf renamed to ib_srp.inx per MS/WDK convention.
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1347
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
stansmith [Tue, 8 Jul 2008 18:17:07 +0000 (18:17 +0000)]
[IPOIB] added INX -> INF file version stamping.
INF file created in ..\..\..\bin\kernel\xxx
.inf file version now matches .sys file version.
added makefile.inc
netipoib.inf renamed to netipoib.inx per MS/WDK convention.
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1346
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
stansmith [Tue, 8 Jul 2008 18:10:43 +0000 (18:10 +0000)]
[IBBUS] Removed extra MS example baggage MISCFILES
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1345
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
stansmith [Tue, 8 Jul 2008 18:09:41 +0000 (18:09 +0000)]
[VNIC] Removed extra MS example baggage MISCFILES
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1344
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
tzachid [Tue, 8 Jul 2008 14:51:08 +0000 (14:51 +0000)]
[ipoib] Add support for another mlnx series of GUIDs.
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1343
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
tzachid [Tue, 8 Jul 2008 14:36:14 +0000 (14:36 +0000)]
[IPOIB, MLX4] Enabling the use of 4K MTU on ipoib.
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1342
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
tzachid [Tue, 8 Jul 2008 14:34:09 +0000 (14:34 +0000)]
[ipoib] Fix for improper handling of IPoIB params
signed by:xalex
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1341
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
stansmith [Mon, 7 Jul 2008 22:05:30 +0000 (22:05 +0000)]
[QLGCVNIC] added INX -> INF file stamping. INF file created in ..\..\..\bin\kernel\xxx
.inf file version now matches .sys file version.
added file makefile.inc
netvnic.inf renamed to netvnic.inx per MS/WDK convention.
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1340
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
stansmith [Mon, 7 Jul 2008 18:48:02 +0000 (18:48 +0000)]
[IBBUS] added INX -> INF file stamping. INF file created in ..\..\..\bin\kernel\xxx
.inf file version now matches .sys file version.
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1338
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
stansmith [Mon, 7 Jul 2008 18:45:01 +0000 (18:45 +0000)]
[CORE] openib.def now includes mod_ver.def to retrieve IB_MAJORVERSION & IB_MINORVERSION #'s. INF file stamping prompted this change.
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1337
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Thu, 3 Jul 2008 08:31:57 +0000 (08:31 +0000)]
[WSD] This patch removes the dependency of WSD on DAPL ATS, and reduces connection establishment SA queries from 2 (ATS query + PR query) to 1 (PR query).
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1332
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Thu, 3 Jul 2008 08:22:07 +0000 (08:22 +0000)]
[CORE, TESTS] This patch adds a library and test utility that performs IP to IB address translation without going to the SA for DAPL ATS service records.
It's a sequence of operations between the IP helper library and IPoIB.
1. Get the local IPoIB port's IB address information (GID).
2. Lookup the destination MAC address via the IP Helper functions, send ARP if needed 3. Ask IPoIB for the destination IB address information given the destination Ethernet MAC.
As input, the IBAT library takes two IP addresses (v4 or v6). As output, it returns two GIDs (as IN6_ADDRs), as well as the pkey.
There's a test program, wherebu, that will exercise the IBAT library.
Note that there is special code for Windows Vista/Server 2008 to take advantage of newer functionality in the IP Helper library. Without this lookups get quite slow as you increase the number of nodes. On our 256 node cluster the Windows Server 2008 code path performed an order of magnitude better than the Windows Server 2003 code path.
There will be a follow up patch that moves WSD over to using this library.
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1331
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Wed, 2 Jul 2008 18:10:45 +0000 (18:10 +0000)]
[IBAL] fix to 1326 CID management patch.
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1330
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Wed, 2 Jul 2008 18:03:49 +0000 (18:03 +0000)]
[IBAL] This patch fixes IBAL object destruction. It does the following:
1. Removes forcing synchronous destruction for user-mode exported objects. This isn't needed, and slows down cleanup of the object hierarchy.
2. Clears the user-mode exported handle from the handle table before invoking the 'destroying' callback of an object, so that all further reference on the object will fail. Currently, an IOCTL could take a reference on an object after the 'destroying' callback has returned.
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1329
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Wed, 2 Jul 2008 17:53:15 +0000 (17:53 +0000)]
[IBAL] IBAL currently blows away all CEPs from its 'destroying' callback. This patch moves this so that any left over CEPs are cleaned up in the 'cleanup' callback, so that objects that 'own' a CEP have a chance to clean themselves up first.
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1328
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Wed, 2 Jul 2008 17:17:49 +0000 (17:17 +0000)]
[IBAL] This patch renames 'que' to 'queue'.
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1327
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Wed, 2 Jul 2008 13:32:47 +0000 (13:32 +0000)]
[IBAL] IBAL has two reserved CID values that it stores in the QPs - AL_INVALID_CID, meaning that there is no CEP associated with the QP but that one can be associated, and AL_RESERVED_CID, which means no CEP is associated, and none should be because the QP is being destroyed.
The code uses atomic operations to check for/set AL_INVALID_CID or AL_RESERVED_CID. Since there are two possible 'special' values, atomics can't be used reliably.
There has been a report of this related to SRP and BSODs.
Additionally, the code would provide the destroy callback when destroying the CEP. However, the CEP can be destroyed through different paths, and it's important to make sure the destroy callback is invoked always so that reference counts can be properly released.
This patch pushes all assignments and checks for special values into the CEP manager, protected by the CEP manager's lock that it holds when performing the CEP lookup. It also changes the semantics of creation/destruction of the CEPs to provide the destroy callback when the CEP is created or bound to an object (the binding path is for the passive side of a connection).
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1326
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Wed, 2 Jul 2008 12:48:17 +0000 (12:48 +0000)]
[IBAL] The current connection establishment code will return STATUS_HOST_UNREACHABLE when an SA operation times out. This patch returns STATUS_TIMEOUT if the SA query timed out, which tends to happen in larger clusters quite often.
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1325
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Wed, 2 Jul 2008 12:39:02 +0000 (12:39 +0000)]
[IBAL] Use the CM protocol to exchange initiator depth and responder resources.
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1324
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Wed, 2 Jul 2008 12:22:39 +0000 (12:22 +0000)]
[IBAL] The current ndi_dreq_cm function destroys the CEP after the QP is moved to the error state. The CEP should be destroyed first to send the DREQ before changing the QP state.
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1323
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Wed, 2 Jul 2008 12:06:40 +0000 (12:06 +0000)]
[IBAL] The CEP manager currently keeps a separate field to store the initiator depth requested in a REQ. When the user sends the REP, the CEP stored the responder resources as the minimum of the requested depth or the CA's capabilities.
This change eliminates the separate field, and uses the responder resources to store the received REQ's initiator depth. This simplifies the code a bit.
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1322
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Wed, 2 Jul 2008 11:50:44 +0000 (11:50 +0000)]
[IBAL] fix to the previous (1320) patch.
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1321
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Wed, 2 Jul 2008 11:12:53 +0000 (11:12 +0000)]
[IBAL] Convert ib_api_status_t to NTSTATUS for al_cep_get_pdata to make the IRP handling simpler.
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1320
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Wed, 2 Jul 2008 10:34:39 +0000 (10:34 +0000)]
[IBAL] Add code to allow user-mode code to register memory via the existing IBAL IOCTLs, and if that succeeds, issue a no-op IOCTL that completes the user's overlapped request to their IOCP (or whatever mechanism they are using - the I/O manager will take care of it).
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1319
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Wed, 2 Jul 2008 10:24:10 +0000 (10:24 +0000)]
[IBAL] This patch changes when the private data is stored to when the CM MAD is received and processed. This makes the code more consistent and simpler.
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1318
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86
leonidk [Tue, 1 Jul 2008 18:27:55 +0000 (18:27 +0000)]
[IBAL] This patch adds a missing reference taken on a QP when delaying the QP modification for a received DREQ.
Signed-off-by: Fab Tillier <ftillier@microsoft.com>
git-svn-id: svn://openib.tc.cornell.edu/gen1/trunk@1317
ad392aa1-c5ef-ae45-8dd8-
e69d62a5ef86