please pull infiniband.git for-linus
Linus, please pull from
master.kernel.org:/pub/scm/linux/kernel/git/roland/infiniband.git for-linus
This tree is also available from kernel.org mirrors at:
git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband.git for-linus
This will get the batch of changes queued up for the 2.6.24 merge window (although I still have a few more things to merge later, once Dave Miller's networking tree has landed too):
Ali Ayoub (1):
IB/sa: Error handling thinko fix
Anton Blanchard (3):
IB/fmr_pool: Clean up some error messages in fmr_pool.c IB/ehca: Make output clearer by removing some debug messages IB/ehca: Export module parameters in sysfs
Arthur Jones (4):
IB/ipath: iba6110 rev4 GPIO counters support
IB/ipath: Use counters in ipath_poll and cleanup interrupts in ipath_close IB/ipath: iba6110 rev4 no longer needs recv header overrun workaround IB/ipath: Indicate a couple of chip bugs to userspace
Dave Olson (5):
IB/ipath: Verify host bus bandwidth to chip will not limit performance IB/ipath: Correctly describe workaround for TID write chip bug IB/ipath: Future proof eeprom checksum code (contents reading) IB/ipath: Fix QHT7040 serial number check
IB/ipath: Minor fix to ordering of freeing and zeroing of tid pages.
Dotan Barak (2):
mlx4_core: Use enum value GO_BIT_TIMEOUT_MSECS
IPoIB/cm: Clean up initialization of QP attr in ipoib_cm_create_tx_qp()
Eli Cohen (3):
IPoIB: Fix typo to end statement with ';' instead of ','
IPoIB: Fix error path memory leak
IB/mthca: Mark error paths as unlikely() in post_srq_recv functions
Hoang-Nam Nguyen (4):
IB/ehca: Use remap_4k_pfn() to map firmware contexts to user space IB/ehca: Fix large page HW cap defines
IB/ehca: Fix mem leak of firmware ctrlblock in ehca_create_srq() IB/ehca: Adjust 64-bit alignment of create QP response for userspace
Jack Morgenstein (5):
IB/mlx4: Display misc device information under /sys/class/infiniband/
mlx4_core: Support ICM tables in coherent memory
mlx4_core: Write MTTs from CPU instead with of WRITE_MTT FW command IB/mlx4: Implement FMRs
mlx4_core: Increase max number of QPs per multicast group to 56
Joachim Fenkes (11):
IB/ehca: Refactor hvcall tracing
IB/ehca: Print return codes as signed decimal integers
IB/ehca: ehca_gen_warn() should always print
IB/ehca: Add check for max #SGE to create_qp()
IB/ehca: Path migration support
IB/ehca: Serialize MR alloc and MR free hvCalls
IB/ehca: Replace get_paca()->paca_index by the more portable raw_smp_processor_id() IB/ehca: Bump version number and change its format
IB/umem: Add hugetlb flag to struct ib_umem
IB/ehca: Only use MR large pages for hugetlb regions
IB/ehca: Return srq_attr->max_sge in ehca_query_srq()
Michael Albaugh (2):
IB/ipath: Maintain active time on all chips IB/ipath: Better handling of unexpected GPIO interrupts
Michael S. Tsirkin (2):
mlx4_core: Enable MSI-X by default
IB/mthca: Enable MSI-X by default
Or Gerlitz (1):
IPoIB: Allow setting policy to ignore multicast groups
Peter Oruba (1):
IB/mthca: Use PCI-X/PCI-Express read control interfaces
Ralph Campbell (13):
IB/core: Fix handling of multicast response failures IB/ipath: Performance optimization for CPU differences IB/ipath: Change UD to queue work requests like RC & UC IB/ipath: Remove unneeded code for ipathfs
IB/ipath: UC RDMA WRITE with IMMEDIATE doesn't send the immediate IB/ipath: Remove redundant code
IB/ipath: Generate flush CQE when QP is in error state IB/ipath: Implement IB_EVENT_QP_LAST_WQE_REACHED
IB/ipath: Optimize completion queue entry insertion and polling IB/ipath: Add ability to set the LMC via the sysfs debugging interface IB/ipath: Remove duplicate copy of LMC
IB/ipath: Fix IB_EVENT_PORT_ERR event
IB/ipath: Remove redundant link state checks
Roland Dreier (18):
IPoIB: Make sure no receives are handled when stopping device
IB: find_first_zero_bit() takes unsigned pointer
mlx4_core: Don't free special QPs in QP number bitmap IB/mlx4: Use __set_data_seg() in mlx4_ib_post_recv() IB/ehca: Include <linux/mutex.h> from ehca_classes.h IB/mlx4: Fix up SRQ limit_watermark endianness
IB/iser: Remove unnecessary includes
mlx4_core: Change capability decoding: SRC->XRC
IB/umad: Add P_Key index support
IB/umad: Fix bit ordering and 32-on-64 problems on big endian systems IB/uverbs: Make ib_uverbs_release_event_file() static
mlx4_core: Reserve the correct number of MTT segments
mlx4_core: Fix meaning of dev->caps.reserved_mtts IB/mthca: Increase max number of QPs per multicast group to 56 IB/mthca: Use mmiowb() to avoid firmware commands getting jumbled up
mlx4_core: Use mmiowb() to avoid firmware commands getting jumbled up IB/ehca: Fix clipping of device limits to INT_MAX
mlx4_core: Fix section mismatches
Satyam Sharma (1):
IB/ehca: Misc cpuinit section annotations and #ifdef cleanups
Sean Hefty (7):
IPoIB: Specify Traffic Class with path record queries for QoS support IB/sa: Add new QoS fields to path record
RDMA/cma: Add ability to specify type of service RDMA/ucma: Allow user space to set service type
IB/srp: Add QoS support through service ID
IB/cm: Modify interface to send MRAs in response to duplicate messages RDMA/cma: Queue IB CM MRAs to avoid unnecessary remote retries
Stefan Roscher (2):
IB/ehca: Small QP userspace support
IB/ehca: Support more than 4k QPs for userspace and kernelspace
Steve Wise (2):
RDMA/cxgb3: Make the iw_cxgb3 module parameters writable RDMA/cma: Use neigh_event_send() to start neighbour discovery
Documentation/infiniband/user_mad.txt | 14 + drivers/infiniband/core/addr.c | 3 +- drivers/infiniband/core/cm.c | 51 ++-- drivers/infiniband/core/cma.c | 46 +++- drivers/infiniband/core/device.c | 4 +- drivers/infiniband/core/fmr_pool.c | 22 +- drivers/infiniband/core/multicast.c | 2 +- drivers/infiniband/core/sa_query.c | 12 +- drivers/infiniband/core/ucma.c | 74 +++++- drivers/infiniband/core/umem.c | 20 ++- drivers/infiniband/core/user_mad.c | 151 +++++++--- drivers/infiniband/core/uverbs.h | 1 - drivers/infiniband/core/uverbs_main.c | 16 +- drivers/infiniband/hw/cxgb3/iwch_cm.c | 16 +- drivers/infiniband/hw/ehca/ehca_classes.h | 14 +- drivers/infiniband/hw/ehca/ehca_cq.c | 23 +- drivers/infiniband/hw/ehca/ehca_hca.c | 34 +- drivers/infiniband/hw/ehca/ehca_irq.c | 33 +-- drivers/infiniband/hw/ehca/ehca_main.c | 52 ++-- drivers/infiniband/hw/ehca/ehca_mcast.c | 4 +- drivers/infiniband/hw/ehca/ehca_mrmw.c | 102 ++++---- drivers/infiniband/hw/ehca/ehca_qp.c | 169 +++++++---- drivers/infiniband/hw/ehca/ehca_reqs.c | 2 +- drivers/infiniband/hw/ehca/ehca_sqp.c | 2 +- drivers/infiniband/hw/ehca/ehca_tools.h | 19 +- drivers/infiniband/hw/ehca/ehca_uverbs.c | 46 ++-- drivers/infiniband/hw/ehca/hcp_if.c | 105 ++++--- drivers/infiniband/hw/ehca/ipz_pt_fn.c | 1 + drivers/infiniband/hw/ipath/ipath_common.h | 4 +- drivers/infiniband/hw/ipath/ipath_cq.c | 94 +++--- drivers/infiniband/hw/ipath/ipath_diag.c | 22 +- drivers/infiniband/hw/ipath/ipath_driver.c | 93 ++++++- drivers/infiniband/hw/ipath/ipath_eeprom.c | 10 +- drivers/infiniband/hw/ipath/ipath_file_ops.c | 74 +++-- drivers/infiniband/hw/ipath/ipath_fs.c | 187 ------------ drivers/infiniband/hw/ipath/ipath_iba6110.c | 57 ++-- drivers/infiniband/hw/ipath/ipath_iba6120.c | 18 +- drivers/infiniband/hw/ipath/ipath_intr.c | 64 +++-- drivers/infiniband/hw/ipath/ipath_kernel.h | 12 +- drivers/infiniband/hw/ipath/ipath_mad.c | 53 ++-- drivers/infiniband/hw/ipath/ipath_qp.c | 31 ++- drivers/infiniband/hw/ipath/ipath_rc.c | 73 ++++-- drivers/infiniband/hw/ipath/ipath_ruc.c | 308 +++++++------------- drivers/infiniband/hw/ipath/ipath_stats.c | 17 +- drivers/infiniband/hw/ipath/ipath_sysfs.c | 40 +++- drivers/infiniband/hw/ipath/ipath_uc.c | 98 +++---- drivers/infiniband/hw/ipath/ipath_ud.c | 382 ++++++++---------------- drivers/infiniband/hw/ipath/ipath_verbs.c | 329 ++++++++++++++------- drivers/infiniband/hw/ipath/ipath_verbs.h | 45 ++- drivers/infiniband/hw/mlx4/main.c | 50 +++ drivers/infiniband/hw/mlx4/mlx4_ib.h | 16 + drivers/infiniband/hw/mlx4/mr.c | 100 ++++++- drivers/infiniband/hw/mlx4/qp.c | 14 +- drivers/infiniband/hw/mlx4/srq.c | 2 +- drivers/infiniband/hw/mthca/mthca_cmd.c | 6 + drivers/infiniband/hw/mthca/mthca_dev.h | 2 +- drivers/infiniband/hw/mthca/mthca_main.c | 110 ++++---- drivers/infiniband/hw/mthca/mthca_srq.c | 8 +- drivers/infiniband/ulp/ipoib/ipoib.h | 24 ++- drivers/infiniband/ulp/ipoib/ipoib_cm.c | 18 +- drivers/infiniband/ulp/ipoib/ipoib_ib.c | 8 + drivers/infiniband/ulp/ipoib/ipoib_main.c | 45 +++- drivers/infiniband/ulp/ipoib/ipoib_multicast.c | 31 +-- drivers/infiniband/ulp/ipoib/ipoib_verbs.c | 2 +- drivers/infiniband/ulp/ipoib/ipoib_vlan.c | 2 + drivers/infiniband/ulp/iser/iser_initiator.c | 2 - drivers/infiniband/ulp/iser/iser_memory.c | 2 - drivers/infiniband/ulp/iser/iser_verbs.c | 1 - drivers/infiniband/ulp/srp/ib_srp.c | 2 + drivers/net/mlx4/cmd.c | 11 +- drivers/net/mlx4/cq.c | 2 +- drivers/net/mlx4/eq.c | 13 +- drivers/net/mlx4/fw.c | 2 +- drivers/net/mlx4/icm.c | 134 +++++++-- drivers/net/mlx4/icm.h | 9 +- drivers/net/mlx4/main.c | 130 +++++---- drivers/net/mlx4/mcg.c | 2 +- drivers/net/mlx4/mlx4.h | 10 +- drivers/net/mlx4/mr.c | 242 +++++++++++++--- drivers/net/mlx4/pd.c | 2 +- drivers/net/mlx4/qp.c | 5 +- drivers/net/mlx4/srq.c | 4 +- include/linux/mlx4/device.h | 27 ++ include/rdma/ib_cm.h | 7 +- include/rdma/ib_sa.h | 11 +- include/rdma/ib_umem.h | 1 + include/rdma/ib_user_mad.h | 70 +++++- include/rdma/rdma_cm.h | 14 + include/rdma/rdma_user_cm.h | 18 ++ 89 files changed, 2498 insertions(+), 1710 deletions(-)
From: Roland Dreier <[email protected]>
Date: Thu, 11 Oct 2007 18:08:52 -0700
Quoted 3 lines
This will get the batch of changes queued up for the 2.6.24 merge window (although I still have a few more things to merge later, once Dave Miller's networking tree has landed too):
Roland are you absolutely sure this won't create merge conflicts with my 8MB net-2.6 merge, inside of which there are many infiniband driver changes?
I really wish you would submit your inifiniband work through normal network driver channels, such as Jeff Garzik. Jeff has been syncing on almost a daily basis with me so that I wouldn't have to worry about changes coming out of left field and adding additional merge issues for an already difficult merge.
Even if you're confident there won't be merge issues, could you just wait for the net-2.6 stuff to go in first?
Thanks.
Quoted 7 lines
Quoted 3 lines
This will get the batch of changes queued up for the 2.6.24 merge window (although I still have a few more things to merge later, once Dave Miller's networking tree has landed too):
Roland are you absolutely sure this won't create merge conflicts with my 8MB net-2.6 merge, inside of which there are many infiniband driver changes?
I'm not absolutely sure of anything but I have merged our two git trees quite a few times during the 2.6.23 cycle and I have not seen any conflicts. Unless you've added some more IB changes very recently I don't think there should be any problem.
Quoted 5 lines
I really wish you would submit your inifiniband work through normal network driver channels, such as Jeff Garzik. Jeff has been syncing on almost a daily basis with me so that I wouldn't have to worry about changes coming out of left field and adding additional merge issues for an already difficult merge.
I'm not sure what you mean. During the 2.6.23 cycle I've been sending any patches that potentially could conflict with the net-2.6 tree to you and Jeff so that you can merge them upstream via your tree. Or do you mean Jeff should become the maintainer of drivers/infiniband??
Can't you guys just keep the networking stuff contained in its little box so it doesn't create maintenance problems for InfiniBand stuff?
Quoted 2 lines
Even if you're confident there won't be merge issues, could you just wait for the net-2.6 stuff to go in first?
I don't mind waiting but I guess it's up to Linus really.
- R.
From: Roland Dreier <[email protected]>
Date: Thu, 11 Oct 2007 19:21:06 -0700
Quoted 4 lines
I'm not sure what you mean. During the 2.6.23 cycle I've been sending any patches that potentially could conflict with the net-2.6 tree to you and Jeff so that you can merge them upstream via your tree. Or do you mean Jeff should become the maintainer of
drivers/infiniband??
Not the maintainer, I'm just saying you should gateway your patches through him.
Quoted 3 lines · David Miller
Even if you're confident there won't be merge issues, could you just wait for the net-2.6 stuff to go in first?
I pulled the net stuff first, and merged the IB stuff afterwards. No conflicts in IB, but there *were* conflicts with the networking pull for other reasons.
That horrid, horrid mess that is called include/linux/mod_devicetable.h and scripts/mod/file2alias.c must go at some point. The thing is unmaintainable. Different maintainers add their own structures to both, and functions to both, and it's just messy. That's not how maintainable and modularized code should be written.
Now it broke on sdio vs ssb, but there was actually a conflict earlier with the Kbuild merge (which I aborted for other reasons), so this file really is starting to be a problem.
The merge was fairly straightforward and stupid - it's not like the code added is *complicated*, but all those small functions and structrues are set up to be a maze of very similar lines, so the merge is actually much worse than it should be - because there is inherent similarity, some lines are automatically auto-merged, making the result just harder to visualize.
So I merged it all, and I don't expect any problems, but I'm hoping somebody is thinking about that mod_devicetable.h/file2alias.c mess.
I'm not entirely sure who to blame on that thing. I'm adding Greg to the Cc, on the assumption that blaming him is usually the right thing to do ;)
Oh, and obviously, the NAPI changes may well have resulted in a merge that had no actual *conflicts* in it, but whether the end result works or not (and whether any IB drivers need updating due to the NAPI changes), I cannot tell. I've pushed out my tree, so people who are competent or just morbidly curious should start looking at it: it's got the following things merged now:
- x86 merge
- mmc
- v4l-dvb
- blackfin
- avr32
- block layer updates
- Jeff's dmi-const
- Purdie's blacklight and led trees
- ide
- mips
- net
- infiniband
and it all builds for me, but hey, I don't use half of it.
Oh, btw, one final note: because of just a *ton* of renames, if you actually want git to do rename-detection for you and do automatic merges across those x86 renames, you should likely add
[diff] renamelimit=0
to your .gitconfig file. Otherwise, the rename detection heuristics may end up saying "I'm not going to even bother finding renames in that mess".
(That final note really shouldn't affect any normal users, but I thought I'd mention it in case somebody is going to want git to merge things across the x86 merge, and gets stuck not realizing why some versions of git might not notice the renames).
Linus
From: Linus Torvalds <[email protected]>
Date: Thu, 11 Oct 2007 19:58:04 -0700 (PDT)
Quoted 21 lines · David Miller
Quoted 3 lines
Even if you're confident there won't be merge issues, could you just wait for the net-2.6 stuff to go in first?
I pulled the net stuff first, and merged the IB stuff afterwards. No conflicts in IB, but there *were* conflicts with the networking pull for other reasons.
That horrid, horrid mess that is called
include/linux/mod_devicetable.handscripts/mod/file2alias.cmust go at some point. The thing is unmaintainable. Different maintainers add their own structures to both, and functions to both, and it's just messy. That's not how maintainable and modularized code should be written.Now it broke on sdio vs ssb, but there was actually a conflict earlier with the
Kbuildmerge (which I aborted for other reasons), so this file really is starting to be a problem.
Quoted 8 lines
The merge was fairly straightforward and stupid - it's not like the code added is *complicated*, but all those small functions and structrues are set up to be a maze of very similar lines, so the merge is actually much worse than it should be - because there is inherent similarity, some lines are automatically auto-merged, making the result just harder to visualize.
So I merged it all, and I don't expect any problems, but I'm hoping somebody is thinking about that
mod_devicetable.h/file2alias.cmess.
It all looks good from here.
Quoted 6 lines · Linus Torvalds
So I merged it all, and I don't expect any problems, but I'm hoping somebody is thinking about that
mod_devicetable.h/file2alias.cmess.I'm not entirely sure who to blame on that thing. I'm adding Greg to the Cc, on the assumption that blaming him is usually the right thing to do ;)
Hey, it wasn't me this time, I haven't even built my trees for you to pull from and break everything yet :)
But yeah, splitting up the mod_devicetable.h/file2alias.c mess is a very good idea, I'll see what I can come up with tomorrow.
thanks,
greg k-h
Quoted 10 lines · Greg KH
Quoted 6 lines · Linus Torvalds
So I merged it all, and I don't expect any problems, but I'm hoping somebody is thinking about that
mod_devicetable.h/file2alias.cmess.I'm not entirely sure who to blame on that thing. I'm adding Greg to the Cc, on the assumption that blaming him is usually the right thing to do ;)
Hey, it wasn't me this time, I haven't even built my trees for you to pull from and break everything yet :)
No, I meant more in the "who the hell is responsible for designing those *files*" rather than who is responsible for the particular merge mess that happened to involve them this time around.
Quoted 2 lines
But yeah, splitting up the
mod_devicetable.h/file2alias.cmess is a very good idea, I'll see what I can come up with tomorrow.
I don't think it's a huge issue, but I wanted to bring it up because these days we're normally so good with these kinds of things that it actually stood out a bit. I used to do these kinds of nasty merges all the time with init/main.c and the configuration files, until we split them up.
So I'm certainly perfectly able and used to doing them, it's just that I also think that we have generally learnt to do so much better.
In other words: no hurry or pressure, I just wanted to bring it up, since during the merge I got flashbacks to various "bad old times" that I had hoped we had mostly left behind.
Those files were originally designed/set up by Rusty. I could have blamed him, or perhaps Sam as a kbuild guy, but the reason I cc'd you is that I think this kind of smells like a "device model"ish thing...
Hmm?
Linus
Quoted 15 lines · Linus Torvalds
Oh, and obviously, the NAPI changes may well have resulted in a merge that had no actual *conflicts* in it, but whether the end result works or not (and whether any IB drivers need updating due to the NAPI changes), I cannot tell. I've pushed out my tree, so people who are competent or just morbidly curious should start looking at it: it's got the following things merged now:
- x86 merge
- mmc
- v4l-dvb
- blackfin
- avr32
- block layer updates
- Jeff's dmi-const
- Purdie's blacklight and led trees
- ide
- mips
- net
- infiniband
Quoted 1 line
and it all builds for me, but hey, I don't use half of it.
works here on intel x86-64, amd64, and 32-bit pentium4.
and without disk corruption, so I may now attend to the libata merge :)
Jeff
Quoted 7 lines
Quoted 4 lines
I'm not sure what you mean. During the 2.6.23 cycle I've been sending any patches that potentially could conflict with the net-2.6 tree to you and Jeff so that you can merge them upstream via your tree. Or do you mean Jeff should become the maintainer of
drivers/infiniband??Not the maintainer, I'm just saying you should gateway your patches through him.
What value do you see in that? It just seems like it creates more work for Jeff and gives no benefit over the current status quo.
- R.
Redesigning file2alias for easy merging (bits of kbuild/kconfig)
In reply to Linus Torvalds* Thu, 11 Oct 2007 21:03:14 -0700 (PDT)
Quoted 28 lines · Greg KH
Quoted 11 lines · Linus Torvalds
Quoted 6 lines
So I merged it all, and I don't expect any problems, but I'm hoping somebody is thinking about that
mod_devicetable.h/file2alias.cmess.I'm not entirely sure who to blame on that thing. I'm adding Greg to the Cc, on the assumption that blaming him is usually the right thing to do ;)
Hey, it wasn't me this time, I haven't even built my trees for you to pull from and break everything yet :)
No, I meant more in the "who the hell is responsible for designing those *files*" rather than who is responsible for the particular merge mess that happened to involve them this time around.
Quoted 2 lines
But yeah, splitting up the
mod_devicetable.h/file2alias.cmess is a very good idea, I'll see what I can come up with tomorrow.I don't think it's a huge issue, but I wanted to bring it up because these days we're normally so good with these kinds of things that it actually stood out a bit. I used to do these kinds of nasty merges all the time with
init/main.cand the configuration files, until we split them up.So I'm certainly perfectly able and used to doing them, it's just that I also think that we have generally learnt to do so much better.
Quoted 7 lines
In other words: no hurry or pressure, I just wanted to bring it up, since during the merge I got flashbacks to various "bad old times" that I had hoped we had mostly left behind.
Those files were originally designed/set up by Rusty. I could have blamed him, or perhaps Sam as a kbuild guy, but the reason I cc'd you is that I think this kind of smells like a "device model"ish thing...
If any amount of work will be done on (re)designing, i'd like to propose documenting all that mod magic.
OK, it can be figured out from the code, and quick split+script_glue can be "designed". But if goals and key points would be written in plain text by person(s) who used to do and maintain it, that will be helpful.
Thanks.
____
Quoted 10 lines · On Thu, 11 Oct 2007 18:17:19 -0700 (PDT) David Miller <[email protected]>…
From: Roland Dreier <[email protected]>
Date: Thu, 11 Oct 2007 18:08:52 -0700Quoted 3 lines
This will get the batch of changes queued up for the 2.6.24 merge window (although I still have a few more things to merge later, once Dave Miller's networking tree has landed too):
Roland are you absolutely sure this won't create merge conflicts with my 8MB net-2.6 merge, inside of which there are many infiniband driver changes?
I'd have told him if there were any such problems.
There might of course be runtime problems, but I'm sure the infiniband developers are testing -mm kernels so that any such problems will be picked up beforehand (heh, I kill me).