public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: John Blackwood <john.blackwood@ccur.com>
To: Ingo Molnar <mingo@elte.hu>,
	Rusty Russell <rusty@rustcorp.com.au>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>
Subject: [RFC][PATCH] Setting /proc/irq/[n]/smp_affinity failure on 8 cpu systems
Date: Wed, 2 Dec 2009 10:19:35 -0600	[thread overview]
Message-ID: <4B169397.5020609@ccur.com> (raw)

Hi,

I would like to mention an irq set affinity issue occurs on an
older Dell PowerEdge 6650 system:
    - 8 cpus (4 are hyper-threaded),
    - uses the struct apic 'apic_default' support
    - 32 bit (x86) kernel

This issue is that once you change the irq smp_affinity of an irq
to be less than all cpus in the system, you can never change really the
irq smp_affinity back to be all cpus in the system (0xff) again,
even though no error status is returned on the "/bin/echo ff >
/proc/irq/[n]/smp_affinity" operation.

This is due to that fact that BAD_APICID has the same value as
all cpus (0xff) on 32bit kernels, and thus the value returned from
set_desc_affinity() via the cpu_mask_to_apicid_and() function is treated
as a failure in set_ioapic_affinity_irq_desc(), and no affinity changes
are made.

It seems like changing the BAD_APICID value from 0xFF to 0xFFFF for
CONFIG_X86_32 might be one possible solution, and it seems to function
properly for this Dell PowerEdge 6650 system.

Thank you for your time.

Signed-off-by: John Blackwood <john.blackwood@ccur.com>


diff -rup linux-2.6.32-rc8/arch/x86/include/asm/apicdef.h new/arch/x86/include/asm/apicdef.h
--- linux-2.6.32-rc8/arch/x86/include/asm/apicdef.h     2009-11-19 16:32:38.000000000 -0600
+++ new/arch/x86/include/asm/apicdef.h  2009-12-01 15:15:34.000000000 -0600
@@ -413,9 +413,6 @@ struct local_apic {

    #undef u32

-#ifdef CONFIG_X86_32
- #define BAD_APICID 0xFFu
-#else
- #define BAD_APICID 0xFFFFu
-#endif
+#define BAD_APICID 0xFFFFu
+
    #endif /* _ASM_X86_APICDEF_H */
diff -rup linux-2.6.32-rc8/arch/x86/include/asm/apic.h new/arch/x86/include/asm/apic.h
--- linux-2.6.32-rc8/arch/x86/include/asm/apic.h        2009-11-19 16:32:38.000000000 -0600
+++ new/arch/x86/include/asm/apic.h     2009-12-01 15:15:34.000000000 -0600
@@ -591,7 +591,7 @@ static inline physid_mask_t default_apic
    #endif /* CONFIG_X86_LOCAL_APIC */

    #ifdef CONFIG_X86_32
-extern u8 cpu_2_logical_apicid[NR_CPUS];
+extern u16 cpu_2_logical_apicid[NR_CPUS];
    #endif

    #endif /* _ASM_X86_APIC_H */
diff -rup linux-2.6.32-rc8/arch/x86/kernel/smpboot.c new/arch/x86/kernel/smpboot.c
--- linux-2.6.32-rc8/arch/x86/kernel/smpboot.c  2009-11-19 16:32:38.000000000 -0600
+++ new/arch/x86/kernel/smpboot.c       2009-12-01 15:15:34.000000000 -0600
@@ -146,7 +146,7 @@ static void unmap_cpu_to_node(int cpu)
    #ifdef CONFIG_X86_32
    static int boot_cpu_logical_apicid;

-u8 cpu_2_logical_apicid[NR_CPUS] __read_mostly =
+u16 cpu_2_logical_apicid[NR_CPUS] __read_mostly =
                                          { [0 ... NR_CPUS-1] = BAD_APICID };

    static void map_cpu_to_logical_apicid(void)




             reply	other threads:[~2009-12-02 16:23 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-12-02 16:19 John Blackwood [this message]
2009-12-03  1:13 ` [RFC][PATCH] Setting /proc/irq/[n]/smp_affinity failure on 8 cpu systems Suresh Siddha
  -- strict thread matches above, loose matches on Subject: below --
2009-12-03 13:30 John Blackwood

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=4B169397.5020609@ccur.com \
    --to=john.blackwood@ccur.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    --cc=rusty@rustcorp.com.au \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox