Jack Morgenstein
fa9656bbd9
IB/mad: include GID/class when matching receives ...
Received responses are currently matched against sent requests based
on TID only. According to the spec, responses should match based on
the combination of TID, management class, and requester LID/GID.
Without the additional qualification, an agent that is responding to
two requests, both of which have the same TID, can match RMPP ACKs
with the incorrect transaction. This problem can occur on the SM node
when responding to SA queries.
Signed-off-by: Jack Morgenstein <jackm@mellanox.co.il>
Signed-off-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2006-03-30 07:19:48 -08:00
[PATCH] more s/fucn/func/ typo fixes
2006-03-26 08:57:09 -08:00
[PATCH] Replace 0xff.. with correct DMA_xBIT_MASK
2006-03-28 09:16:07 -08:00
[PATCH] Notifier chain update: API changes
2006-03-27 08:44:50 -08:00
[PATCH] Replace 0xff.. with correct DMA_xBIT_MASK
2006-03-28 09:16:07 -08:00
[PATCH] Remove MODULE_PARM
2006-03-25 08:22:52 -08:00
[PATCH] do_SAK: don't depend on session ID 0
2006-03-28 18:36:40 -08:00
[CPUFREQ] cpufreq_conservative: keep ignore_nice_load and freq_step values when reselected
2006-03-28 12:20:18 -05:00
[PATCH] hp300: fix driver_register() return handling, remove dio_module_init()
2006-03-25 08:22:53 -08:00
[PATCH] Typo fixes
2006-03-28 09:16:08 -08:00
[PATCH] EISA: Ignore generated file drivers/eisa/devlist.h
2006-03-25 08:23:01 -08:00
[PATCH] Notifier chain update: API changes
2006-03-27 08:44:50 -08:00
[PATCH] RTC subsystem: I2C cleanup
2006-03-27 08:44:51 -08:00
[PATCH] ide-tape: use time_after(), time_after_eq()
2006-03-28 09:16:07 -08:00
ohci1394: cleanup the "Unexpected PCI resource length" warning.
2006-03-28 20:04:04 -05:00
IB/mad: include GID/class when matching receives
2006-03-30 07:19:48 -08:00
[PATCH] mark f_ops const in the inode
2006-03-28 09:16:05 -08:00
[PATCH] mark f_ops const in the inode
2006-03-28 09:16:05 -08:00
[PATCH] Notifier chain update: API changes
2006-03-27 08:44:50 -08:00
[PATCH] md: Convert reconfig_sem to reconfig_mutex
2006-03-27 08:45:03 -08:00
[PATCH] mark f_ops const in the inode
2006-03-28 09:16:05 -08:00
[PATCH] mark f_ops const in the inode
2006-03-28 09:16:05 -08:00
[PATCH] show MCP menu only on ARCH_SA1100
2006-03-24 07:33:28 -08:00
[PATCH] Make most file operations structs in fs/ const
2006-03-28 09:16:06 -08:00
[PATCH] Remove MODULE_PARM
2006-03-25 08:22:52 -08:00
Kconfig help: MTD_JEDECPROBE already supports Intel
2006-03-26 19:15:03 +02:00
[PATCH] Typo fixes
2006-03-28 09:16:08 -08:00
[PATCH] mark f_ops const in the inode
2006-03-28 09:16:05 -08:00
[PATCH] Notifier chain update: API changes
2006-03-27 08:44:50 -08:00
[PATCH] pnp: parport: adjust pnp_register_driver signature
2006-03-27 08:44:52 -08:00
[PATCH] sem2mutex: misc static one-file mutexes
2006-03-26 08:56:55 -08:00
[PATCH] pnp: PNP: adjust pnp_register_driver signature
2006-03-27 08:44:53 -08:00
[PATCH] RTC subsystem: M48T86 driver
2006-03-27 08:44:52 -08:00
Merge git://git.kernel.org/pub/scm/linux/kernel/git/bunk/trivial
2006-03-26 09:41:18 -08:00
[PATCH] Typo fixes
2006-03-28 09:16:08 -08:00
Merge master.kernel.org:/home/rmk/linux-2.6-serial
2006-03-28 13:52:37 -08:00
[PATCH] mark f_ops const in the inode
2006-03-28 09:16:05 -08:00
[PATCH] Typo fixes
2006-03-28 09:16:08 -08:00
[PATCH] video/sis/init301.c:SiS_ChrontelDoSomething2(): remove dead code
2006-03-27 08:44:58 -08:00
fix typos "wich" -> "which"
2006-03-24 18:23:14 +01:00
[PATCH] amiga: fix driver_register() return handling, remove zorro_module_init()
2006-03-25 08:22:53 -08:00
[PATCH] RTC Subsystem: library functions
2006-03-27 08:44:50 -08:00
[PATCH] RTC Subsystem: library functions
2006-03-27 08:44:50 -08:00
fa9656bbd9