lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <1326301493-28760-9-git-send-email-fenghua.yu@intel.com>
Date:	Wed, 11 Jan 2012 09:04:49 -0800
From:	"Fenghua Yu" <fenghua.yu@...el.com>
To:	"Ingo Molnar" <mingo@...e.hu>,
	"Thomas Gleixner" <tglx@...utronix.de>,
	"H Peter Anvin" <hpa@...or.com>,
	"Linus Torvalds" <torvalds@...ux-foundation.org>,
	"Andrew Morton" <akpm@...ux-foundation.org>,
	"Asit K Mallick" <asit.k.mallick@...el.com>,
	"Tony Luck" <tony.luck@...el.com>,
	"Arjan van de Ven" <arjan.van.de.ven@...el.com>,
	"Suresh B Siddha" <suresh.b.siddha@...el.com>,
	"Len Brown" <len.brown@...el.com>,
	"Randy Dunlap" <rdunlap@...otime.net>,
	"Srivatsa S. Bhat" <srivatsa.bhat@...ux.vnet.ibm.com>,
	Konrad Rzeszutek Wilk <konrad.wilk@...cle.com>,
	Peter Zijlstra <peterz@...radead.org>,
	"Chen Gong" <gong.chen@...ux.intel.com>,
	"linux-kernel" <linux-kernel@...r.kernel.org>,
	"linux-pm" <linux-pm@...r.kernel.org>, "x86" <x86@...nel.org>
Cc:	Fenghua Yu <fenghua.yu@...el.com>
Subject: [PATCH v5 08/12] x86/smpboot.c: Wake up CPU0 via NMI instead of INITs

From: Fenghua Yu <fenghua.yu@...el.com>

Instead of waiting for STARTUP after INITs, BSP will execute
the BIOS boot-strap code which is not a desired behavior for
waking up BSP. To avoid the boot-strap code, wake up CPU0 by
NMI instead.

This works to wake up soft offlined CPU0 only. If CPU0 is hard offlined (i.e.
physically hot removed and then hot added), NMI won't wake it up. We'll change
this code in the future to wake up hard offlined CPU0 if real platform and
request are available.

AP is still waken up as before by INIT, INIT, STARTUP sequence.

Signed-off-by: Fenghua Yu <fenghua.yu@...el.com>
---
 arch/x86/include/asm/cpu.h |    1 +
 arch/x86/kernel/smpboot.c  |   82 ++++++++++++++++++++++++++++++++++++++++----
 2 files changed, 76 insertions(+), 7 deletions(-)

diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
index 4564c8e..a119572 100644
--- a/arch/x86/include/asm/cpu.h
+++ b/arch/x86/include/asm/cpu.h
@@ -28,6 +28,7 @@ struct x86_cpu {
 #ifdef CONFIG_HOTPLUG_CPU
 extern int arch_register_cpu(int num);
 extern void arch_unregister_cpu(int);
+extern void __cpuinit start_cpu0(void);
 #endif
 
 DECLARE_PER_CPU(int, cpu_state);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index a3c4be3..0d93599 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -149,15 +149,17 @@ static void __cpuinit smp_callin(void)
 	 * we may get here before an INIT-deassert IPI reaches
 	 * our local APIC.  We have to wait for the IPI or we'll
 	 * lock up on an APIC access.
+	 *
+	 * Since CPU0 is not wakened up by INIT, it doesn't wait for the IPI.
 	 */
-	if (apic->wait_for_init_deassert)
+	cpuid = smp_processor_id();
+	if (apic->wait_for_init_deassert && cpuid != 0)
 		apic->wait_for_init_deassert(&init_deasserted);
 
 	/*
 	 * (This works even if the APIC is not enabled.)
 	 */
 	phys_id = read_apic_id();
-	cpuid = smp_processor_id();
 	if (cpumask_test_cpu(cpuid, cpu_callin_mask)) {
 		panic("%s: phys CPU#%d, CPU#%d already present??\n", __func__,
 					phys_id, cpuid);
@@ -251,6 +253,8 @@ static void __cpuinit smp_callin(void)
 	cpumask_set_cpu(cpuid, cpu_callin_mask);
 }
 
+static int cpu0_logical_apicid;
+static int enable_start_cpu0;
 /*
  * Activate a secondary processor.
  */
@@ -265,6 +269,8 @@ notrace static void __cpuinit start_secondary(void *unused)
 	preempt_disable();
 	smp_callin();
 
+	enable_start_cpu0 = 0;
+
 #ifdef CONFIG_X86_32
 	/* switch away from the initial page table */
 	load_cr3(swapper_pg_dir);
@@ -493,7 +499,7 @@ void __inquire_remote_apic(int apicid)
  * won't ... remember to clear down the APIC, etc later.
  */
 int __cpuinit
-wakeup_secondary_cpu_via_nmi(int logical_apicid, unsigned long start_eip)
+wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip)
 {
 	unsigned long send_status, accept_status = 0;
 	int maxlvt;
@@ -501,7 +507,7 @@ wakeup_secondary_cpu_via_nmi(int logical_apicid, unsigned long start_eip)
 	/* Target chip */
 	/* Boot on the stack */
 	/* Kick the second */
-	apic_icr_write(APIC_DM_NMI | apic->dest_logical, logical_apicid);
+	apic_icr_write(APIC_DM_NMI | apic->dest_logical, apicid);
 
 	pr_debug("Waiting for send to finish...\n");
 	send_status = safe_apic_wait_icr_idle();
@@ -677,6 +683,17 @@ static void __cpuinit announce_cpu(int cpu, int apicid)
 			node, cpu, apicid);
 }
 
+static int wakeup_cpu0_nmi(unsigned int cmd, struct pt_regs *regs)
+{
+	int cpu;
+
+	cpu = smp_processor_id();
+	if (cpu == 0 && !cpu_online(cpu) && enable_start_cpu0)
+		return NMI_HANDLED;
+
+	return NMI_DONE;
+}
+
 /*
  * NOTE - on most systems this is a PHYSICAL apic ID, but on multiquad
  * (ie clustered apic addressing mode), this is a LOGICAL apic ID.
@@ -771,8 +788,47 @@ do_rest:
 	 */
 	if (apic->wakeup_secondary_cpu)
 		boot_error = apic->wakeup_secondary_cpu(apicid, start_ip);
-	else
-		boot_error = wakeup_secondary_cpu_via_init(apicid, start_ip);
+	else {
+		if (cpu)
+			/*
+			 * Wake up AP by INIT, INIT, STARTUP sequence.
+			 */
+			boot_error = wakeup_secondary_cpu_via_init(apicid,
+								   start_ip);
+		else {
+			/*
+			 * Instead of waiting for STARTUP after INITs, BSP will
+			 * execute the BIOS boot-strap code which is not a
+			 * desired behavior for waking up BSP. To avoid the
+			 * boot-strap code, wake up CPU0 by NMI instead.
+			 *
+			 * This works to wake up soft offlined CPU0 only. If
+			 * CPU0 is hard offlined (i.e. physically hot removed
+			 * and then hot added), NMI won't wake it up. We'll
+			 * change this code in the future to wake up hard
+			 * offlined CPU0 if real platform and request are
+			 * available.
+			 */
+			int id;
+
+			enable_start_cpu0 = 1;
+			/*
+			 * Register a NMI handler to help wake up CPU0.
+			 */
+			boot_error = register_nmi_handler(NMI_LOCAL,
+					 wakeup_cpu0_nmi, 0, "wake_cpu0");
+
+			if (!boot_error) {
+				if (apic->dest_logical == APIC_DEST_LOGICAL)
+					id = cpu0_logical_apicid;
+				else
+					id = apicid;
+				boot_error = wakeup_secondary_cpu_via_nmi(id,
+								start_ip);
+				unregister_nmi_handler(NMI_LOCAL, "wake_cpu0");
+			}
+		}
+	}
 
 	if (!boot_error) {
 		/*
@@ -1088,6 +1144,8 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 	 */
 	setup_local_APIC();
 
+	cpu0_logical_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR));
+
 	/*
 	 * Enable IO APIC before setting up error vector
 	 */
@@ -1431,6 +1489,11 @@ static inline void mwait_play_dead(void)
 		__monitor(mwait_ptr, 0, 0);
 		mb();
 		__mwait(eax, 0);
+		/*
+		 * If NMI wakes up CPU0, start offlined CPU0.
+		 */
+		if (smp_processor_id() == 0 && enable_start_cpu0)
+			start_cpu0();
 	}
 }
 
@@ -1441,10 +1504,15 @@ static inline void hlt_play_dead(void)
 
 	while (1) {
 		native_halt();
+		/*
+		 * If NMI wakes up CPU0, start offlined CPU0.
+		 */
+		if (smp_processor_id() == 0 && enable_start_cpu0)
+			start_cpu0();
 	}
 }
 
-void native_play_dead(void)
+void __ref native_play_dead(void)
 {
 	play_dead_common();
 	tboot_shutdown(TB_SHUTDOWN_WFS);
-- 
1.6.0.3

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ