linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Ido Yariv <ido@wizery.com>
To: linux-kernel@vger.kernel.org, Ingo Molnar <mingo@kernel.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	"H. Peter Anvin" <hpa@zytor.com>
Cc: Shai Fultheim <shai@scalemp.com>,
	Ravikiran Thirumalai <kiran.thirumalai@gmail.com>,
	Ido Yariv <ido@wizery.com>
Subject: [PATCH v3 2/2] vsmp: Ignore IOAPIC IRQ affinity if possible
Date: Sun,  3 Jun 2012 01:11:35 +0300	[thread overview]
Message-ID: <1338675095-27260-2-git-send-email-ido@wizery.com> (raw)
In-Reply-To: <1338675095-27260-1-git-send-email-ido@wizery.com>

From: Ravikiran Thirumalai <kiran.thirumalai@gmail.com>

vSMP can route interrupts more optimally based on internal knowledge the
OS does not have. In order to support this optimization, all CPUs must
be able to handle all possible IOAPIC interrupts.

Fix this by setting the vector allocation domain for all CPUs and by
enabling this feature in vSMP.

Signed-off-by: Ravikiran Thirumalai <kiran.thirumalai@gmail.com>
Signed-off-by: Shai Fultheim <shai@scalemp.com>
[ido@wizery.com: rebased, simplified, and reworded the commit message]
Signed-off-by: Ido Yariv <ido@wizery.com>
---
Changes from v2:
- Set the vector allocation domain in the apic_post_init callback

 arch/x86/kernel/vsmp_64.c |   25 +++++++++++++++++++++----
 1 files changed, 21 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c
index 59eea85..a24cf34 100644
--- a/arch/x86/kernel/vsmp_64.c
+++ b/arch/x86/kernel/vsmp_64.c
@@ -16,6 +16,7 @@
 #include <linux/pci_ids.h>
 #include <linux/pci_regs.h>
 #include <linux/smp.h>
+#include <linux/irq.h>
 
 #include <asm/apic.h>
 #include <asm/pci-direct.h>
@@ -95,6 +96,13 @@ static void __init set_vsmp_pv_ops(void)
 	ctl = readl(address + 4);
 	printk(KERN_INFO "vSMP CTL: capabilities:0x%08x  control:0x%08x\n",
 	       cap, ctl);
+
+	/* If possible, let the vSMP foundation route the interrupt optimally */
+	if (cap & ctl & BIT(8)) {
+		ctl &= ~BIT(8);
+		no_irq_affinity = 1;
+	}
+
 	if (cap & ctl & (1 << 4)) {
 		/* Setup irq ops and turn on vSMP  IRQ fastpath handling */
 		pv_irq_ops.irq_disable = PV_CALLEE_SAVE(vsmp_irq_disable);
@@ -102,12 +110,11 @@ static void __init set_vsmp_pv_ops(void)
 		pv_irq_ops.save_fl  = PV_CALLEE_SAVE(vsmp_save_fl);
 		pv_irq_ops.restore_fl  = PV_CALLEE_SAVE(vsmp_restore_fl);
 		pv_init_ops.patch = vsmp_patch;
-
 		ctl &= ~(1 << 4);
-		writel(ctl, address + 4);
-		ctl = readl(address + 4);
-		printk(KERN_INFO "vSMP CTL: control set to:0x%08x\n", ctl);
 	}
+	writel(ctl, address + 4);
+	ctl = readl(address + 4);
+	pr_info("vSMP CTL: control set to:0x%08x\n", ctl);
 
 	early_iounmap(address, 8);
 }
@@ -192,10 +199,20 @@ static int apicid_phys_pkg_id(int initial_apic_id, int index_msb)
 	return hard_smp_processor_id() >> index_msb;
 }
 
+/*
+ * In vSMP, all cpus should be capable of handling interrupts, regardless of
+ * the apic used.
+ */
+static void fill_vector_allocation_domain(int cpu, struct cpumask *retmask)
+{
+	cpumask_setall(retmask);
+}
+
 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;
 }
 
 void __init vsmp_init(void)
-- 
1.7.7.6


  reply	other threads:[~2012-06-02 22:12 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-04-06 12:39 [PATCH 1/2] vsmp: Fix number of CPUs when vsmp is disabled Ido Yariv
2012-04-06 12:39 ` [PATCH 2/2] vsmp: Ignore IOAPIC IRQ affinity if possible Ido Yariv
2012-04-16  7:39   ` [PATCH v2 1/2] vsmp: Fix number of CPUs when vsmp is disabled Ido Yariv
2012-04-16  7:39     ` [PATCH v2 2/2] vsmp: Ignore IOAPIC IRQ affinity if possible Ido Yariv
2012-05-07 13:19       ` Ingo Molnar
2012-05-08  0:53         ` Shai Fultheim (Shai@ScaleMP.com)
2012-05-09  9:18           ` Ingo Molnar
2012-05-09 21:21             ` Ido Yariv
2012-06-02 22:11               ` [PATCH 1/2] x86: Introduce apic post-initialization callback Ido Yariv
2012-06-02 22:11                 ` Ido Yariv [this message]
2012-06-06 15:02                   ` [tip:x86/platform] x86/vsmp: Ignore IOAPIC IRQ affinity if possible tip-bot for Ravikiran Thirumalai
2012-06-08  8:52                     ` Ingo Molnar
2012-06-08 15:43                       ` Ido Yariv
2012-06-11  8:58                         ` Ingo Molnar
2012-06-11 19:41                           ` Ido Yariv
2012-06-14 10:51                             ` Ingo Molnar
2012-06-14 15:43                               ` [PATCH] x86/vsmp: Fix linker error when CONFIG_PROC_FS is not set Ido Yariv
2012-06-15 14:22                                 ` [tip:x86/platform] " tip-bot for Ido Yariv
2012-06-06 15:01                 ` [tip:x86/platform] x86/platform: Introduce APIC post-initialization callback tip-bot for Ido Yariv
2012-06-14 17:34                   ` H. Peter Anvin
2012-06-15 14:33                     ` Ido Yariv
2012-04-28 21:33     ` [PATCH v2 1/2] vsmp: Fix number of CPUs when vsmp is disabled Ido Yariv
2012-04-29  3:05       ` Shai Fultheim (Shai@ScaleMP.com)
2012-05-07 13:24     ` Ingo Molnar
2012-05-08  7:34       ` [PATCH v3] " Ido Yariv
2012-05-08 10:05         ` [tip:x86/platform] " tip-bot for Shai Fultheim
2012-05-08 12:25           ` Ingo Molnar
2012-05-09  8:03             ` Ido Yariv
2012-05-09  8:22               ` Ido Yariv
2012-05-09  8:28                 ` [PATCH v4] " Ido Yariv
2012-05-09 15:44                   ` Ingo Molnar
2012-05-09 15:55                     ` H. Peter Anvin
2012-05-11 19:26                       ` Ido Yariv
2012-05-12  1:20                         ` Shai Fultheim (Shai@ScaleMP.com)
2012-05-09  9:12               ` [tip:x86/platform] " Ingo Molnar
2012-05-09 15:27                 ` Shai Fultheim (Shai@ScaleMP.com)

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=1338675095-27260-2-git-send-email-ido@wizery.com \
    --to=ido@wizery.com \
    --cc=hpa@zytor.com \
    --cc=kiran.thirumalai@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=shai@scalemp.com \
    --cc=tglx@linutronix.de \
    /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;
as well as URLs for NNTP newsgroup(s).