kernel-fxtec-pro1x/arch/x86/kernel/apic
Rusty Russell e06b1b56f9 x86: Correct behaviour of irq affinity
Impact: get correct smp_affinity as user requested

The effect of setting desc->affinity (ie. from userspace via sysfs) has
varied over time.  In 2.6.27, the 32-bit code anded the value with
cpu_online_map, and both 32 and 64-bit did that anding whenever a cpu
was unplugged.

2.6.29 consolidated this into one routine (and fixed hotplug) but
introduced another variation: anding the affinity with cfg->domain.

We should just set it to what the user said - if possible.

(cpu_mask_to_apicid_and already takes cpu_online_mask into account)

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Acked-by: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
LKML-Reference: <49C94DDF.2010703@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-03-25 18:48:29 +01:00
..
apic.c x86, ioapic: Fix non atomic allocation with interrupts disabled 2009-03-17 15:45:29 -07:00
apic_flat_64.c x86: use default_cpu_mask_to_apicid for 64bit 2009-03-24 22:28:38 +01:00
bigsmp_32.c x86_32: apic/bigsmp_32, de-inline functions 2009-03-02 11:20:32 +01:00
es7000_32.c x86_32: apic/es7000_32, fix section mismatch 2009-03-02 12:00:24 +01:00
io_apic.c x86: Correct behaviour of irq affinity 2009-03-25 18:48:29 +01:00
ipi.c
Makefile
nmi.c
numaq_32.c x86_32: apic/numaq_32, fix section mismatch 2009-03-02 12:00:25 +01:00
probe_32.c x86: apic: simplify secondary CPU wakeup methods 2009-02-26 13:58:26 +01:00
probe_64.c x86, x2apic: cleanup ifdef CONFIG_INTR_REMAP in io_apic code 2009-03-17 15:45:07 -07:00
summit_32.c x86_32: apic/summit_32, fix section mismatch 2009-03-02 12:00:25 +01:00
x2apic_cluster.c x86: add x2apic_wrmsr_fence() to x2apic flush tlb paths 2009-03-18 09:36:14 +01:00
x2apic_phys.c x86: add x2apic_wrmsr_fence() to x2apic flush tlb paths 2009-03-18 09:36:14 +01:00
x2apic_uv_x.c x86: apic: simplify secondary CPU wakeup methods, fix 2009-02-26 14:11:06 +01:00