Kernel

[RFC/PATCH 0/3] sched: allow arch override of cpu power
There is an "interesting" quality of POWER6 cores, which each have 2 hardware threads: assuming one thread on the core is idle, the primary thread is a little "faster" than the secondary thread. To illustrate: for cpumask in 0x1 0x2 ; do taskset $cpumask /usr/bin/time -f "%e elapsed, %U user, %S sys" \ ... 19 Jun 2008 01:20

mm: add a ptep_modify_prot transaction abstraction
Linus Torvalds wrote: On Wed, 18 Jun 2008, Jeremy Fitzhardinge wrote: Along the lines of: Hell no. There's a reason we have a special set_wrprotect() thing. We can do it more efficiently on native hardware by just clearing the bit atomically. No need to do the cmpxchg games. ... 20 Jun 2008 17:24

Don't calculate vm_total_pages twice when rebuild zonelists in online_pages()
If zonelist is required to be rebuilt in online_pages(), there is no need to recalculate vm_total_pages in that function, as it has been updated in the call build_all_zonelists(). Signed-off-by: Kent Liu <kent.liu(a)linux.intel.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu(a)jp.fujitsu.com> --- mm/memory_ho... 19 Jun 2008 01:20

[RFC/PATCH 3/3] adjust cpu power for secondary threads on POWER6
On POWER6 processors, cpu-bound programs generally perform better on the primary thread when the secondary thread is idle than they do on the secondary thread while the primary thread is idle. This difference can be observed by timing a simple shell loop: for cpumask in 0x1 0x2 ; do taskset $cpumask /usr/bin/t... 19 Jun 2008 01:20

[RFC/PATCH 2/3] add cpu_power to machdep_calls, override SD_SIBLING_INIT
Add a cpu_power() call to machdep_calls, which will allow platforms to override the scheduler's default cpu power calculation. If the platform does not provide a cpu_power() method, the scheduler's default value is used. Copy the default SD_SIBLING_INIT to powerpc's topology.h and add the SD_ASYM_CPU_POWER flag... 19 Jun 2008 01:20

[PATCH] x86: update mptable fix with no ioapic v2
if the system doesn't have ioapic, we don't need to store entries for mptable update also let mp_config_acpi_gsi not call func in mpparse so later could decouple mpparse with acpi more easily Reported-by: Daniel Exner <dex(a)dragonslave.de> Signed-off-by: Yinghai Lu <yhlu.kernel(a)gmail.com> --- arch/x86/ke... 19 Jun 2008 01:20

Oops report for the week preceding June 16th, 2008
* David Miller <davem(a)davemloft.net> wrote: From: Ingo Molnar <mingo(a)elte.hu> Date: Tue, 17 Jun 2008 17:33:56 +0200 v2.6.24 was no doubt a huge step in the right direction but it came too late and we are still suffering from the fallout today as we have not reached test cycle equilibrium ... 23 Jun 2008 13:45

mm: add a ptep_modify_prot transaction abstraction
On Wed, 18 Jun 2008, Jeremy Fitzhardinge wrote: Along the lines of: Hell no. There's a reason we have a special set_wrprotect() thing. We can do it more efficiently on native hardware by just clearing the bit atomically. No need to do the cmpxchg games. Linus -- To unsubscribe from this list: se... 20 Jun 2008 16:22

[PATCH] x86: cleanup machine_specific_memory_setup v2
1. let 64bit support 88 and e801 too 2. introduce default_machine_specific_memory_setup, and reuse it for voyager v2: fix 64 bit compiling Signed-off-by: Yinghai Lu <yhlu.kernel(a)gmail.com> --- arch/x86/kernel/e820.c | 13 +++++++------ arch/x86/mach-voyager/setup.c | 32 +------------------... 19 Jun 2008 01:20

[PATCH - take 2] knfsd: nfsd: Handle ERESTARTSYS from syscalls.
OCFS2 can return -ERESTARTSYS from write requests (and possibly elsewhere) if there is a signal pending. If nfsd is shutdown (by sending a signal to each thread) while there is still an IO load from the client, each thread could handle one last request with a signal pending. This can result in -ERESTARTSYS wh... 19 Jun 2008 01:20