OFED 1.5.1 rc4 release is available
OFED 1.5.1-rc4 is available
Notes:
The tarball is available on:
http://www.openfabrics.org/downloads/OFED/ofed-1.5.1/OFED-1.5.1-rc4.tgz
To get BUILD_ID run ofed_info
Please report any issues in bugzilla https://bugs.openfabrics.org/ for OFED 1.5.1
Vladimir & Tziporet
========================================================================
Supported Platforms and Operating Systems
---------------------------------------------
o CPU architectures:
- x86_64
- x86
- ppc64
- ia64
o Linux Operating Systems:
- RedHat EL4 up7 2.6.9-78.ELsmp
- RedHat EL4 up8 2.6.9-89.ELsmp
- RedHat EL5 up3 2.6.18-128.el5
- RedHat EL5 up4 2.6.18-164.el5
- SLES10 SP2 2.6.16.60-0.21-smp
- SLES10 SP3 2.6.16.60-0.54-smp
- SLES11 2.6.27.19-5-default
- OEL 4 up7 2.6.9-78.ELsmp
- OEL 4 up8 2.6.9-89.ELsmp
- CentOS5.3 2.6.18-128.el5
- CentOS5.4 2.6.18-164.el5
- Fedora Core12 2.6.31.5-127.fc12 *
- OpenSuSE 11.2 2.6.31.5-0.1-default *
- kernel.org 2.6.29, 2.6.30,
2.6.31 and 2.6.32 *
* Minimal QA for these versions
Main changes from 1.5.1-rc3:
===========================
1. Updated packages:
- ibutils: ibutils-1.5.4
- libmlx4: libmlx4-1.0-0.6.g72e73dc
Bug fix in mlx4_create_ah
- install.pl:
Add '--builddir' parameter
NFSoRDMA will not support SLES10 SPx
- NFSoRDMA is not supported under SLES10SPx
2. Bug fixes
commit 3e2e26b64187f3d5292653b4df761dfcd1e353ea
Merge: f52992f eada57c
Author: Vladimir Sokolovsky <vlad-VPRAkNaXOzVS1MOuV/[email protected]>
Date: Thu Mar 11 13:01:40 2010 +0200
Merge remote branch 'vu/ofed_kernel_1_5' into ofed_kernel_1_5
commit eada57cc6dfcd0f779c5254a1fc354702ac41247
Author: Vu Pham (Mellanox) <[email protected]> Date: Thu Mar 11 02:30:28 2010 -0800
srp: fixing panic bug happened during manual unload ib_srp module
commit f52992f15c05d70d17412ca92e14e6f1bf2c1ac7
Author: Yevgeny Petrilin <yevgenyp-VPRAkNaXOzVS1MOuV/[email protected]> Date: Wed Mar 10 18:46:55 2010 +0200
mlx4_en: reconfigure mac address
When the other port removes a mac address that is the same that the current port has, the table should be reconfigured. fixes bugzilla #1965
commit 7a1bbb340356e0489e50678f7e6d563f2f0be268
Author: Eli Cohen <eli-VPRAkNaXOzVS1MOuV/[email protected]> Date: Thu Mar 11 10:33:52 2010 +0200
IPoIB: Fix multicast handling
After reverting c124815 it was necessary to modify ipoib_mcast_addr_is_valid() so it will not filter out valid ipoib multicast addresses.
commit 5daec886e9a7d7baea848180c3c8dbbc7b249e79
Author: Eli Cohen <eli-VPRAkNaXOzVS1MOuV/[email protected]> Date: Thu Mar 11 09:17:21 2010 +0200
Revert "ipoib/mcast: Fix IPoIB multicast backport"
The reverted comit changes the multicat address that the kernel created causing resource leaks and other problems.
This reverts commit c12481586c4ba09cb88dc2090c67fdce7c856cde.
commit efe60c7da58f9bf235eef0381aa4a93c014805aa
Merge: 3df6ee7 0ff7a6e
Author: Vladimir Sokolovsky <vlad-VPRAkNaXOzVS1MOuV/[email protected]>
Date: Wed Mar 10 08:12:42 2010 +0200
Merge branch 'ofed_kernel_1_5' of git://git.openfabrics.org/~ralphc/linux-2.6/ into ofed_kernel_1_5
commit 3df6ee73e2364080d7ac179d1ecd8c4aaf9a9e43
Merge: 7a227ee 4c29a30
Author: Vladimir Sokolovsky <vlad-VPRAkNaXOzVS1MOuV/[email protected]>
Date: Wed Mar 10 08:11:37 2010 +0200
Merge branch 'ofed_kernel_1_5' of ssh://sofa.openfabrics.org/home/ctung/scm/ofed-1.5 into ofed_kernel_1_5
commit 7a227ee270783b7f1d773939e82343fdc3e69fb4
Merge: a679ae9 8721f26
Author: Vladimir Sokolovsky <vlad-VPRAkNaXOzVS1MOuV/[email protected]>
Date: Wed Mar 10 08:06:29 2010 +0200
Merge branch 'ofed_1_5' of ssh://sofa.openfabrics.org/~swise/scm/ofed_kernel into ofed_kernel_1_5
commit 0ff7a6e94e7e98a8f10d1c01e70c6f26d776c4ee
Author: Ralph Campbell (QLogic) <[email protected]> Date: Tue Mar 9 16:09:47 2010 -0800
IB/qib: clear symbol error counters on link UP
Clear symbol error counters on link UP.
commit 4c29a3078cee40ee9800ade03f6f91c69202f368
Author: Chien Tung <[email protected]> Date: Tue Mar 9 15:59:02 2010 -0600
RDMA/nes: make nesadapter->phy_lock usage consistent
nes_{read,write}_1G_phy_reg() are using phy_lock while nes_{read,write}_10G_phy_reg() leave that to the caller.
Remove phy_lock from 1G routines and leave the locking to the caller. Add additional phy_lock calls around 1G read/write.
commit a679ae9a392f4404fd76c82deb436d0a6cf3a2a5
Merge: 4d803f7 5bc17bc
Author: Vladimir Sokolovsky <vlad-VPRAkNaXOzVS1MOuV/[email protected]>
Date: Tue Mar 9 19:19:26 2010 +0200
Merge branch 'ofed_1_5' of ssh://69.55.231.68/home/boomer/scm/ofed_kernel into ofed_kernel_1_5
commit 5bc17bc65077ff95a5caaa43df6657b2df41dacd
Author: Tom Tucker <tom-/Yg/[email protected]> Date: Tue Mar 9 10:34:50 2010 -0600
svcrdma: Fix SQ size calculation when memreg is FRMR
From: Tom Tucker <tom-/Yg/[email protected]>
This patch updates the computation to include the worst case situation where three FRMR are required to map a single RPC REQ.
commit 8721f2647e96cb33ac7a1a2f3ece39622adba399
Author: Steve Wise <[email protected]> Date: Tue Mar 9 10:19:41 2010 -0600
cxgb3: update firmware to 7.10.0.
commit 4d803f721b73c7b9e32a1f7641bc557deeb881fc
Author: Ali Ayoub <ali-VPRAkNaXOzVWk0Htik3J/[email protected]> Date: Tue Mar 9 16:54:31 2010 +0200
ib_core: big LSO support wr opcode for packets larger than 64B
commit 7fe30cb86bc13b6404785dbc556b2d7f5d925436
Author: Ali Ayoub <ali-VPRAkNaXOzVWk0Htik3J/[email protected]> Date: Tue Mar 9 16:53:55 2010 +0200
mlx4_core: big LSO support preparation for packets larger than 64B
commit f90c487eaf52a96473961f26cd0be36f4dd4eb53
Author: Jack Morgenstein <[email protected]> Date: Tue Mar 9 16:47:28 2010 +0200
mlx4_ib: fix SRQ initialization per PRM requirements.
Very similar to mthca-memfree SRQ initialization.
commit ffbfd4bfcc9f75c4750a63e946f0b2d15f27dc12
Author: Jack Morgenstein <[email protected]> Date: Tue Mar 9 16:46:37 2010 +0200
mlx4_core: deprecate "bogus CQ" completion event warning to debug.
getting an completion event for a CQ that has been destroyed may happen when a QP is transitioned to ERR, then immediately destroyed along with its CQs.
This is legal, so the message should be for debugging only.
commit 8682ec4e3279eb3284ad4afdad9c7c289eec8296
Author: Eli Cohen <eli-VPRAkNaXOzVS1MOuV/[email protected]> Date: Tue Mar 9 14:54:51 2010 +0200
mlx4: fix allocation type
Since update_ipv6_gids() is called with spinlock acquiree, use GFP_ATOMIC.
commit 723420321fec93c004e2885abf42ce69272c8154
Author: Eli Cohen <eli-VPRAkNaXOzVS1MOuV/[email protected]> Date: Tue Mar 9 12:13:19 2010 +0200
mlx4: fix phys_state report for IBoE ports
Since physical state follows the active port state, use a proper translation function. Also use meaningful values for link width and fix the correct default for link speed and link width.
commit dcf8ff7e1f905a78395782c6cbd6d6c92afd7246
Author: Vladimir Sokolovsky <vlad-VPRAkNaXOzVS1MOuV/[email protected]> Date: Sun Mar 7 16:18:40 2010 +0200
backports: Fix RHEL5.5 backport patches
commit 409027d3cc304d183b8847f13953a49408a0744b
Author: Vladimir Sokolovsky <vlad-VPRAkNaXOzVS1MOuV/[email protected]> Date: Sun Mar 7 14:05:24 2010 +0200
get_backport_dir: Add RHEL5.5 support
commit e3d41e72a0ce7f4e956952c28d51e4e9abbfcd08
Author: Eli Cohen <eli-VPRAkNaXOzVS1MOuV/[email protected]> Date: Mon Mar 8 08:25:48 2010 +0200
ipoib: Fix lockup of the tx queue
The ipoib UD QP reports send completions to priv->send_cq which is unarmed generally; it only gets armed when the number of outstanding send requests (e.g. those for which a completion was not polled yet) reaches the size of the tx queue. This arming (done using ib_req_notify_cq()) is done only in the send path for the UD QP. However, when sending CM packets, the net queue may be stopped for the same reasons but no measures are taken to recover the UD path from a lockup.
Consider this scenario: a host sends high rate of both CM and UD packets. Suppose also that the tx queue length is N. If at some time the number of outstanding UD packets is more than N/2 and the overall outstanding packets is N-1, and now CM sends a packet making the number of outstanding equal N, the tx queue will be stopped. When all the CM packets will complete, the number of outstanding packets will still be higher than N/2 so the tx queue will not be enabled.
Fix this by calling ib_req_notify_cq() when the queue is stopped in the CM path.
commit c36de74a2987eb0ee78f7f59f18916e1a7096c4b
Merge: 1ab03e6 1e49d72
Author: Vladimir Sokolovsky <vlad-VPRAkNaXOzVS1MOuV/[email protected]>
Date: Sun Mar 7 12:21:26 2010 +0200
Merge branch 'ofed_1_5' of ssh://sofa.openfabrics.org/~swise/scm/ofed_kernel into ofed_kernel_1_5
commit 1e49d727e4a6ac012625ceb4f550783c632c11a9
Author: Steve Wise <[email protected]> Date: Thu Mar 4 10:38:48 2010 -0600
RDMA/cxgb3: wait at least one schedule cycle during device removal.
During a hot-plug LLD removal event or an EEH error event, iw_cxgb3 must ensure that any/all threads that might be in a cxgb3 exported function concurrently must return from the function before iw_cxgb3 returns from its event processing. Do this by calling synchronize_net().
commit 87581e84b1efa06c41e05b5865ca3b6430f5cac5
Author: Steve Wise <[email protected]> Date: Thu Mar 4 10:35:45 2010 -0600
cxgb3: fix hot plug removal crash
From: Divy Le Ray <[email protected]>
queue restart tasklets need to be stopped after napi handlers are stopped since the latter can restart them. So stop them after stopping napi.
commit 1ab03e6a07826382aa59f5a1b919e303ad92979d
Author: Chien Tung <[email protected]> Date: Thu Mar 4 10:24:23 2010 -0600
RDMA/nes: update backports for RHEL 5.5
commit e0006c0b7cc5e378a210d1f00023a3be60d3c27c
Merge: 590c926 b2f2c1b
Author: Vladimir Sokolovsky <vlad-VPRAkNaXOzVS1MOuV/[email protected]>
Date: Thu Mar 4 15:38:14 2010 +0200
Merge remote branch 'eli/ofed_kernel_1_5' into ofed_kernel_1_5
commit 590c926eaef8e7dcc589ffa4076767f3fec0ef10
Author: Alexander Schmidt <[email protected]> Date: Thu Mar 4 12:03:22 2010 +0100
ehca: bump version number
commit b2f2c1b1a7ed0ef8b143ea1e82ff2c59f69470fb
Author: Eli Cohen <eli-VPRAkNaXOzVS1MOuV/[email protected]> Date: Thu Mar 4 14:29:31 2010 +0200
Fix bug in SL/IB inserted in 464df47
commit 4dffb9bffcf2fefb9ff9bc466e818527df963a55
Author: Eli Cohen <eli-VPRAkNaXOzVS1MOuV/[email protected]> Date: Thu Mar 4 12:37:51 2010 +0200
ib_core: Add link_layer entry to sysfs
Now that the port link layer may be either IB or Ethernet, add this information to sysfs. For example, /sys/class/infiniband/mlx4_0/ports/1/link_layer.