public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
* [PATCH] x86: use online_mask for x2apic target_cpus
@ 2009-08-04 15:59 Yinghai Lu
  2009-08-04 17:13 ` Suresh Siddha
  2009-08-08 15:21 ` [tip:x86/urgent] x86: Fix MSI-X initialization by using " tip-bot for Yinghai Lu
  0 siblings, 2 replies; 3+ messages in thread
From: Yinghai Lu @ 2009-08-04 15:59 UTC (permalink / raw)
  To: Ingo Molnar, Thomas Gleixner, H. Peter Anvin, Suresh Siddha
  Cc: linux-kernel@vger.kernel.org


found one system with x2apic report:
[  302.859446] igbvf 0000:81:10.4: enabling device (0000 -> 0002)
[  302.874369] igbvf 0000:81:10.4: using 64bit DMA mask
[  302.879023] igbvf 0000:81:10.4: using 64bit consistent DMA mask
[  302.894386] igbvf 0000:81:10.4: enabling bus mastering
[  302.898171] igbvf 0000:81:10.4: setting latency timer to 64
[  302.914050] reserve_memtype added 0xefb08000-0xefb0c000, track uncached-minus, req uncached-minus, ret uncached-minus
[  302.933839] reserve_memtype added 0xefb28000-0xefb29000, track uncached-minus, req uncached-minus, ret uncached-minus
[  302.940367]   alloc irq_desc for 265 on node 4
[  302.956874]   alloc kstat_irqs on node 4
[  302.959452] alloc irq_2_iommu on node 0
[  302.974328] igbvf 0000:81:10.4: irq 265 for MSI/MSI-X
[  302.977778]   alloc irq_desc for 266 on node 4
[  302.980347]   alloc kstat_irqs on node 4
[  302.995312] free_memtype request 0xefb28000-0xefb29000
[  302.998816] igbvf 0000:81:10.4: Failed to initialize MSI-X interrupts.

it turns out that when trying to enable msi-x.
__assign_irq_vector(new, cfg_new, apic->target_cpus()) can not get vector
because for x2apic target-cpus return cpumask_of(0)

update that to online_mask like xapic.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>

---
 arch/x86/kernel/apic/x2apic_cluster.c |    8 +++++---
 arch/x86/kernel/apic/x2apic_phys.c    |    8 +++++---
 2 files changed, 10 insertions(+), 6 deletions(-)

Index: linux-2.6/arch/x86/kernel/apic/x2apic_cluster.c
===================================================================
--- linux-2.6.orig/arch/x86/kernel/apic/x2apic_cluster.c
+++ linux-2.6/arch/x86/kernel/apic/x2apic_cluster.c
@@ -17,11 +17,13 @@ static int x2apic_acpi_madt_oem_check(ch
 	return x2apic_enabled();
 }
 
-/* Start with all IRQs pointing to boot CPU.  IRQ balancing will shift them. */
-
+/*
+ * need to use more than cpu 0, because we need more vectors when
+ * MSI-X are used.
+ */
 static const struct cpumask *x2apic_target_cpus(void)
 {
-	return cpumask_of(0);
+	return cpu_online_mask;
 }
 
 /*
Index: linux-2.6/arch/x86/kernel/apic/x2apic_phys.c
===================================================================
--- linux-2.6.orig/arch/x86/kernel/apic/x2apic_phys.c
+++ linux-2.6/arch/x86/kernel/apic/x2apic_phys.c
@@ -27,11 +27,13 @@ static int x2apic_acpi_madt_oem_check(ch
 		return 0;
 }
 
-/* Start with all IRQs pointing to boot CPU.  IRQ balancing will shift them. */
-
+/*
+ * need to use more than cpu 0, because we need more vectors when
+ * MSI-X are used.
+ */
 static const struct cpumask *x2apic_target_cpus(void)
 {
-	return cpumask_of(0);
+	return cpu_online_mask;
 }
 
 static void x2apic_vector_allocation_domain(int cpu, struct cpumask *retmask)

^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: [PATCH] x86: use online_mask for x2apic target_cpus
  2009-08-04 15:59 [PATCH] x86: use online_mask for x2apic target_cpus Yinghai Lu
@ 2009-08-04 17:13 ` Suresh Siddha
  2009-08-08 15:21 ` [tip:x86/urgent] x86: Fix MSI-X initialization by using " tip-bot for Yinghai Lu
  1 sibling, 0 replies; 3+ messages in thread
From: Suresh Siddha @ 2009-08-04 17:13 UTC (permalink / raw)
  To: Yinghai Lu
  Cc: Ingo Molnar, Thomas Gleixner, H. Peter Anvin,
	linux-kernel@vger.kernel.org

On Tue, 2009-08-04 at 08:59 -0700, Yinghai Lu wrote:
> found one system with x2apic report:
> [  302.859446] igbvf 0000:81:10.4: enabling device (0000 -> 0002)
> [  302.874369] igbvf 0000:81:10.4: using 64bit DMA mask
> [  302.879023] igbvf 0000:81:10.4: using 64bit consistent DMA mask
> [  302.894386] igbvf 0000:81:10.4: enabling bus mastering
> [  302.898171] igbvf 0000:81:10.4: setting latency timer to 64
> [  302.914050] reserve_memtype added 0xefb08000-0xefb0c000, track uncached-minus, req uncached-minus, ret uncached-minus
> [  302.933839] reserve_memtype added 0xefb28000-0xefb29000, track uncached-minus, req uncached-minus, ret uncached-minus
> [  302.940367]   alloc irq_desc for 265 on node 4
> [  302.956874]   alloc kstat_irqs on node 4
> [  302.959452] alloc irq_2_iommu on node 0
> [  302.974328] igbvf 0000:81:10.4: irq 265 for MSI/MSI-X
> [  302.977778]   alloc irq_desc for 266 on node 4
> [  302.980347]   alloc kstat_irqs on node 4
> [  302.995312] free_memtype request 0xefb28000-0xefb29000
> [  302.998816] igbvf 0000:81:10.4: Failed to initialize MSI-X interrupts.
> 
> it turns out that when trying to enable msi-x.
> __assign_irq_vector(new, cfg_new, apic->target_cpus()) can not get vector
> because for x2apic target-cpus return cpumask_of(0)
> 
> update that to online_mask like xapic.
> 
> Signed-off-by: Yinghai Lu <yinghai@kernel.org>

Acked-by: Suresh Siddha <suresh.b.siddha@intel.com>


^ permalink raw reply	[flat|nested] 3+ messages in thread

* [tip:x86/urgent] x86: Fix MSI-X initialization by using online_mask for x2apic target_cpus
  2009-08-04 15:59 [PATCH] x86: use online_mask for x2apic target_cpus Yinghai Lu
  2009-08-04 17:13 ` Suresh Siddha
@ 2009-08-08 15:21 ` tip-bot for Yinghai Lu
  1 sibling, 0 replies; 3+ messages in thread
From: tip-bot for Yinghai Lu @ 2009-08-08 15:21 UTC (permalink / raw)
  To: linux-tip-commits
  Cc: linux-kernel, hpa, mingo, yinghai, suresh.b.siddha, tglx, mingo

Commit-ID:  087d7e56deffb611a098e7e257388a41edbeef1f
Gitweb:     http://git.kernel.org/tip/087d7e56deffb611a098e7e257388a41edbeef1f
Author:     Yinghai Lu <yinghai@kernel.org>
AuthorDate: Tue, 4 Aug 2009 08:59:59 -0700
Committer:  Ingo Molnar <mingo@elte.hu>
CommitDate: Sat, 8 Aug 2009 17:04:58 +0200

x86: Fix MSI-X initialization by using online_mask for x2apic target_cpus

found a system where x2apic reports an MSI-X irq initialization
failure:

[  302.859446] igbvf 0000:81:10.4: enabling device (0000 -> 0002)
[  302.874369] igbvf 0000:81:10.4: using 64bit DMA mask
[  302.879023] igbvf 0000:81:10.4: using 64bit consistent DMA mask
[  302.894386] igbvf 0000:81:10.4: enabling bus mastering
[  302.898171] igbvf 0000:81:10.4: setting latency timer to 64
[  302.914050] reserve_memtype added 0xefb08000-0xefb0c000, track uncached-minus, req uncached-minus, ret uncached-minus
[  302.933839] reserve_memtype added 0xefb28000-0xefb29000, track uncached-minus, req uncached-minus, ret uncached-minus
[  302.940367]   alloc irq_desc for 265 on node 4
[  302.956874]   alloc kstat_irqs on node 4
[  302.959452] alloc irq_2_iommu on node 0
[  302.974328] igbvf 0000:81:10.4: irq 265 for MSI/MSI-X
[  302.977778]   alloc irq_desc for 266 on node 4
[  302.980347]   alloc kstat_irqs on node 4
[  302.995312] free_memtype request 0xefb28000-0xefb29000
[  302.998816] igbvf 0000:81:10.4: Failed to initialize MSI-X interrupts.

... it turns out that when trying to enable MSI-X,
__assign_irq_vector(new, cfg_new, apic->target_cpus()) can not
get vector because for x2apic target-cpus returns cpumask_of(0)

Update that to online_mask like xapic.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Acked-by: Suresh Siddha <suresh.b.siddha@intel.com>
LKML-Reference: <4A785AFF.3050902@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>


---
 arch/x86/kernel/apic/x2apic_cluster.c |    8 +++++---
 arch/x86/kernel/apic/x2apic_phys.c    |    8 +++++---
 2 files changed, 10 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index 2ed4e2b..a5371ec 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -17,11 +17,13 @@ static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 	return x2apic_enabled();
 }
 
-/* Start with all IRQs pointing to boot CPU.  IRQ balancing will shift them. */
-
+/*
+ * need to use more than cpu 0, because we need more vectors when
+ * MSI-X are used.
+ */
 static const struct cpumask *x2apic_target_cpus(void)
 {
-	return cpumask_of(0);
+	return cpu_online_mask;
 }
 
 /*
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index 0b631c6..a8989aa 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -27,11 +27,13 @@ static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 		return 0;
 }
 
-/* Start with all IRQs pointing to boot CPU.  IRQ balancing will shift them. */
-
+/*
+ * need to use more than cpu 0, because we need more vectors when
+ * MSI-X are used.
+ */
 static const struct cpumask *x2apic_target_cpus(void)
 {
-	return cpumask_of(0);
+	return cpu_online_mask;
 }
 
 static void x2apic_vector_allocation_domain(int cpu, struct cpumask *retmask)

^ permalink raw reply related	[flat|nested] 3+ messages in thread

end of thread, other threads:[~2009-08-08 15:22 UTC | newest]

Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2009-08-04 15:59 [PATCH] x86: use online_mask for x2apic target_cpus Yinghai Lu
2009-08-04 17:13 ` Suresh Siddha
2009-08-08 15:21 ` [tip:x86/urgent] x86: Fix MSI-X initialization by using " tip-bot for Yinghai Lu

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox