From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753908AbaD1HVz (ORCPT ); Mon, 28 Apr 2014 03:21:55 -0400 Received: from ar-005-i193.relay.mailchannels.net ([162.253.144.75]:20149 "EHLO relay.mailchannels.net" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1751288AbaD1HVy (ORCPT ); Mon, 28 Apr 2014 03:21:54 -0400 X-Sender-Id: totalchoicehosting|x-authuser|oren%40scalemp.com X-Sender-Id: totalchoicehosting|x-authuser|oren%40scalemp.com X-MC-Relay: Neutral X-MailChannels-SenderId: totalchoicehosting%7Cx-authuser%7Coren%2540scalemp.com X-MailChannels-Auth-Id: totalchoicehosting From: Oren Twaig To: Thomas Gleixner , Ingo Molnar , "H. Peter Anvin" , Andi Kleen Cc: x86@kernel.org, linux-kernel@vger.kernel.org, Shai Fultheim , Oren Twaig Subject: [PATCH v3] X86: Hook apic vector allocation domain only when interrupt routing are set to ignore Date: Mon, 28 Apr 2014 10:21:37 +0300 Message-Id: <1398669697-2123-1-git-send-email-oren@scalemp.com> X-Mailer: git-send-email 1.7.9.5 X-AuthUser: oren@scalemp.com Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Correct IRQ routing in case a vSMP Foundation box is detected but the Interrupt Routing Comply (IRC) is set to "comply". Before the patch: When a vSMP Foundation box was detected and IRC was set to "comply", users (and kernel) couldn't effectively set the destination of the IRQs. This is because the hook inside vsmp_64.c always setup all CPUs as the IRQ destination using cpumask_setall() as the return value for IRQ allocation mask. Later, this "overrided" mask caused the kernel to set the IRQ destination to the lowest online CPU in the mask (CPU0 usually). After the patch: When the IRC is set to "comply", Users (and kernel) can control the destination of the IRQs as we will not be changing the default "apic->vector_allocation_domain". Signed-off-by: Oren Twaig Acked-by: Shai Fultheim --- arch/x86/kernel/vsmp_64.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c index f6584a9..39dd854 100644 --- a/arch/x86/kernel/vsmp_64.c +++ b/arch/x86/kernel/vsmp_64.c @@ -26,6 +26,9 @@ #define TOPOLOGY_REGISTER_OFFSET 0x10 +/* Flag below is initialized once during vSMP Foundation PCI initialization. */ +static int interrupt_routing_comply = 1; + #if defined CONFIG_PCI && defined CONFIG_PARAVIRT /* * Interrupt control on vSMPowered systems: @@ -101,6 +104,10 @@ static void __init set_vsmp_pv_ops(void) #ifdef CONFIG_SMP if (cap & ctl & BIT(8)) { ctl &= ~BIT(8); + + /* Interrupt routing set to ignore */ + interrupt_routing_comply = 0; + #ifdef CONFIG_PROC_FS /* Don't let users change irq affinity via procfs */ no_irq_affinity = 1; @@ -218,7 +225,9 @@ static void vsmp_apic_post_init(void) { /* need to update phys_pkg_id */ apic->phys_pkg_id = apicid_phys_pkg_id; - apic->vector_allocation_domain = fill_vector_allocation_domain; + + if (!interrupt_routing_comply) + apic->vector_allocation_domain = fill_vector_allocation_domain; } void __init vsmp_init(void)