1 files changed, 212 insertions, 80 deletions

diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index b17416e72fb..ad28db7e6bd 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -35,6 +35,7 @@
 #include <linux/smp.h>
 #include <linux/mm.h>
 
+#include <asm/trace/irq_vectors.h>
 #include <asm/irq_remapping.h>
 #include <asm/perf_event.h>
 #include <asm/x86_init.h>
@@ -57,10 +58,11 @@
 
 unsigned int num_processors;
 
-unsigned disabled_cpus __cpuinitdata;
+unsigned disabled_cpus;
 
 /* Processor that is doing the boot up */
 unsigned int boot_cpu_physical_apicid = -1U;
+EXPORT_SYMBOL_GPL(boot_cpu_physical_apicid);
 
 /*
  * The highest APIC ID seen during enumeration.
@@ -73,6 +75,13 @@ unsigned int max_physical_apicid;
 physid_mask_t phys_cpu_present_map;
 
 /*
+ * Processor to be disabled specified by kernel parameter
+ * disable_cpu_apicid=<int>, mostly used for the kdump 2nd kernel to
+ * avoid undefined behaviour caused by sending INIT from AP to BSP.
+ */
+static unsigned int disabled_cpu_apicid __read_mostly = BAD_APICID;
+
+/*
  * Map cpu index to physical APIC ID
  */
 DEFINE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_cpu_to_apicid, BAD_APICID);
@@ -90,21 +99,6 @@ EXPORT_EARLY_PER_CPU_SYMBOL(x86_bios_cpu_apicid);
  */
 DEFINE_EARLY_PER_CPU_READ_MOSTLY(int, x86_cpu_to_logical_apicid, BAD_APICID);
 
-/*
- * Knob to control our willingness to enable the local APIC.
- *
- * +1=force-enable
- */
-static int force_enable_local_apic __initdata;
-/*
- * APIC command line parameters
- */
-static int __init parse_lapic(char *arg)
-{
-	force_enable_local_apic = 1;
-	return 0;
-}
-early_param("lapic", parse_lapic);
 /* Local APIC was disabled by the BIOS and enabled by the kernel */
 static int enabled_via_apicbase;
 
@@ -133,6 +127,29 @@ static inline void imcr_apic_to_pic(void)
 }
 #endif
 
+/*
+ * Knob to control our willingness to enable the local APIC.
+ *
+ * +1=force-enable
+ */
+static int force_enable_local_apic __initdata;
+
+/* Control whether x2APIC mode is enabled or not */
+static bool nox2apic __initdata;
+
+/*
+ * APIC command line parameters
+ */
+static int __init parse_lapic(char *arg)
+{
+	if (config_enabled(CONFIG_X86_32) && !arg)
+		force_enable_local_apic = 1;
+	else if (arg && !strncmp(arg, "notscdeadline", 13))
+		setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
+	return 0;
+}
+early_param("lapic", parse_lapic);
+
 #ifdef CONFIG_X86_64
 static int apic_calibrate_pmtmr __initdata;
 static __init int setup_apicpmtimer(char *s)
@@ -149,8 +166,7 @@ int x2apic_mode;
 /* x2apic enabled before OS handover */
 int x2apic_preenabled;
 static int x2apic_disabled;
-static int nox2apic;
-static __init int setup_nox2apic(char *str)
+static int __init setup_nox2apic(char *str)
 {
 	if (x2apic_enabled()) {
 		int apicid = native_apic_msr_read(APIC_ID);
@@ -165,7 +181,7 @@ static __init int setup_nox2apic(char *str)
 	} else
 		setup_clear_cpu_cap(X86_FEATURE_X2APIC);
 
-	nox2apic = 1;
+	nox2apic = true;
 
 	return 0;
 }
@@ -270,8 +286,12 @@ u32 native_safe_apic_wait_icr_idle(void)
 
 void native_apic_icr_write(u32 low, u32 id)
 {
+	unsigned long flags;
+
+	local_irq_save(flags);
 	apic_write(APIC_ICR2, SET_APIC_DEST_FIELD(id));
 	apic_write(APIC_ICR, low);
+	local_irq_restore(flags);
 }
 
 u64 native_apic_icr_read(void)
@@ -315,6 +335,7 @@ int lapic_get_maxlvt(void)
 
 /* Clock divisor */
 #define APIC_DIVISOR 16
+#define TSC_DIVISOR  32
 
 /*
  * This function sets up the local APIC timer, with a timeout of
@@ -333,6 +354,9 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen)
 	lvtt_value = LOCAL_TIMER_VECTOR;
 	if (!oneshot)
 		lvtt_value |= APIC_LVT_TIMER_PERIODIC;
+	else if (boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER))
+		lvtt_value |= APIC_LVT_TIMER_TSCDEADLINE;
+
 	if (!lapic_is_integrated())
 		lvtt_value |= SET_APIC_TIMER_BASE(APIC_TIMER_BASE_DIV);
 
@@ -341,6 +365,11 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen)
 
 	apic_write(APIC_LVTT, lvtt_value);
 
+	if (lvtt_value & APIC_LVT_TIMER_TSCDEADLINE) {
+		printk_once(KERN_DEBUG "TSC deadline timer enabled\n");
+		return;
+	}
+
 	/*
 	 * Divide PICLK by 16
 	 */
@@ -453,6 +482,16 @@ static int lapic_next_event(unsigned long delta,
 	return 0;
 }
 
+static int lapic_next_deadline(unsigned long delta,
+			       struct clock_event_device *evt)
+{
+	u64 tsc;
+
+	rdtscll(tsc);
+	wrmsrl(MSR_IA32_TSC_DEADLINE, tsc + (((u64) delta) * TSC_DIVISOR));
+	return 0;
+}
+
 /*
  * Setup the lapic timer in periodic or oneshot mode
  */
@@ -520,7 +559,7 @@ static DEFINE_PER_CPU(struct clock_event_device, lapic_events);
  * Setup the local APIC timer for this CPU. Copy the initialized values
  * of the boot CPU and register the clock event in the framework.
  */
-static void __cpuinit setup_APIC_timer(void)
+static void setup_APIC_timer(void)
 {
 	struct clock_event_device *levt = &__get_cpu_var(lapic_events);
 
@@ -533,7 +572,15 @@ static void __cpuinit setup_APIC_timer(void)
 	memcpy(levt, &lapic_clockevent, sizeof(*levt));
 	levt->cpumask = cpumask_of(smp_processor_id());
 
-	clockevents_register_device(levt);
+	if (this_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) {
+		levt->features &= ~(CLOCK_EVT_FEAT_PERIODIC |
+				    CLOCK_EVT_FEAT_DUMMY);
+		levt->set_next_event = lapic_next_deadline;
+		clockevents_config_and_register(levt,
+						(tsc_khz / TSC_DIVISOR) * 1000,
+						0xF, ~0UL);
+	} else
+		clockevents_register_device(levt);
 }
 
 /*
@@ -661,7 +708,9 @@ static int __init calibrate_APIC_clock(void)
 	 * in the clockevent structure and return.
 	 */
 
-	if (lapic_timer_frequency) {
+	if (boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) {
+		return 0;
+	} else if (lapic_timer_frequency) {
 		apic_printk(APIC_VERBOSE, "lapic timer already calibrated %d\n",
 				lapic_timer_frequency);
 		lapic_clockevent.mult = div_sc(lapic_timer_frequency/APIC_DIVISOR,
@@ -674,6 +723,9 @@ static int __init calibrate_APIC_clock(void)
 		return 0;
 	}
 
+	apic_printk(APIC_VERBOSE, "Using local APIC timer interrupts.\n"
+		    "calibrating APIC timer ...\n");
+
 	local_irq_disable();
 
 	/* Replace the global interrupt handler */
@@ -811,9 +863,6 @@ void __init setup_boot_APIC_clock(void)
 		return;
 	}
 
-	apic_printk(APIC_VERBOSE, "Using local APIC timer interrupts.\n"
-		    "calibrating APIC timer ...\n");
-
 	if (calibrate_APIC_clock()) {
 		/* No broadcast on UP ! */
 		if (num_possible_cpus() > 1)
@@ -832,7 +881,7 @@ void __init setup_boot_APIC_clock(void)
 	setup_APIC_timer();
 }
 
-void __cpuinit setup_secondary_APIC_clock(void)
+void setup_secondary_APIC_clock(void)
 {
 	setup_APIC_timer();
 }
@@ -879,24 +928,42 @@ static void local_apic_timer_interrupt(void)
  * [ if a single-CPU system runs an SMP kernel then we call the local
  *   interrupt as well. Thus we cannot inline the local irq ... ]
  */
-void __irq_entry smp_apic_timer_interrupt(struct pt_regs *regs)
+__visible void __irq_entry smp_apic_timer_interrupt(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
 	/*
 	 * NOTE! We'd better ACK the irq immediately,
 	 * because timer handling can be slow.
+	 *
+	 * update_process_times() expects us to have done irq_enter().
+	 * Besides, if we don't timer interrupts ignore the global
+	 * interrupt lock, which is the WrongThing (tm) to do.
 	 */
-	ack_APIC_irq();
+	entering_ack_irq();
+	local_apic_timer_interrupt();
+	exiting_irq();
+
+	set_irq_regs(old_regs);
+}
+
+__visible void __irq_entry smp_trace_apic_timer_interrupt(struct pt_regs *regs)
+{
+	struct pt_regs *old_regs = set_irq_regs(regs);
+
 	/*
+	 * NOTE! We'd better ACK the irq immediately,
+	 * because timer handling can be slow.
+	 *
 	 * update_process_times() expects us to have done irq_enter().
 	 * Besides, if we don't timer interrupts ignore the global
 	 * interrupt lock, which is the WrongThing (tm) to do.
 	 */
-	irq_enter();
-	exit_idle();
+	entering_ack_irq();
+	trace_local_timer_entry(LOCAL_TIMER_VECTOR);
 	local_apic_timer_interrupt();
-	irq_exit();
+	trace_local_timer_exit(LOCAL_TIMER_VECTOR);
+	exiting_irq();
 
 	set_irq_regs(old_regs);
 }
@@ -1177,7 +1244,7 @@ void __init init_bsp_APIC(void)
 	apic_write(APIC_LVT1, value);
 }
 
-static void __cpuinit lapic_setup_esr(void)
+static void lapic_setup_esr(void)
 {
 	unsigned int oldvalue, value, maxlvt;
 
@@ -1224,7 +1291,7 @@ static void __cpuinit lapic_setup_esr(void)
  * Used to setup local APIC while initializing BSP or bringin up APs.
  * Always called with preemption disabled.
  */
-void __cpuinit setup_local_APIC(void)
+void setup_local_APIC(void)
 {
 	int cpu = smp_processor_id();
 	unsigned int value, queued;
@@ -1419,7 +1486,7 @@ void __cpuinit setup_local_APIC(void)
 #endif
 }
 
-void __cpuinit end_local_APIC_setup(void)
+void end_local_APIC_setup(void)
 {
 	lapic_setup_esr();
 
@@ -1444,8 +1511,7 @@ void __init bsp_end_local_APIC_setup(void)
 	 * Now that local APIC setup is completed for BP, configure the fault
 	 * handling for interrupt remapping.
 	 */
-	if (irq_remapping_enabled)
-		irq_remap_enable_fault_handling();
+	irq_remap_enable_fault_handling();
 
 }
 
@@ -1875,12 +1941,10 @@ int __init APIC_init_uniprocessor(void)
 /*
  * This interrupt should _never_ happen with our APIC/SMP architecture
  */
-void smp_spurious_interrupt(struct pt_regs *regs)
+static inline void __smp_spurious_interrupt(void)
 {
 	u32 v;
 
-	irq_enter();
-	exit_idle();
 	/*
 	 * Check if this really is a spurious interrupt and ACK it
 	 * if it is a vectored one.  Just in case...
@@ -1895,15 +1959,30 @@ void smp_spurious_interrupt(struct pt_regs *regs)
 	/* see sw-dev-man vol 3, chapter 7.4.13.5 */
 	pr_info("spurious APIC interrupt on CPU#%d, "
 		"should never happen.\n", smp_processor_id());
-	irq_exit();
+}
+
+__visible void smp_spurious_interrupt(struct pt_regs *regs)
+{
+	entering_irq();
+	__smp_spurious_interrupt();
+	exiting_irq();
+}
+
+__visible void smp_trace_spurious_interrupt(struct pt_regs *regs)
+{
+	entering_irq();
+	trace_spurious_apic_entry(SPURIOUS_APIC_VECTOR);
+	__smp_spurious_interrupt();
+	trace_spurious_apic_exit(SPURIOUS_APIC_VECTOR);
+	exiting_irq();
 }
 
 /*
  * This interrupt should never happen with our APIC/SMP architecture
  */
-void smp_error_interrupt(struct pt_regs *regs)
+static inline void __smp_error_interrupt(struct pt_regs *regs)
 {
-	u32 v0, v1;
+	u32 v;
 	u32 i = 0;
 	static const char * const error_interrupt_reason[] = {
 		"Send CS error",		/* APIC Error Bit 0 */
@@ -1916,29 +1995,42 @@ void smp_error_interrupt(struct pt_regs *regs)
 		"Illegal register address",	/* APIC Error Bit 7 */
 	};
 
-	irq_enter();
-	exit_idle();
 	/* First tickle the hardware, only then report what went on. -- REW */
-	v0 = apic_read(APIC_ESR);
-	apic_write(APIC_ESR, 0);
-	v1 = apic_read(APIC_ESR);
+	if (lapic_get_maxlvt() > 3)	/* Due to the Pentium erratum 3AP. */
+		apic_write(APIC_ESR, 0);
+	v = apic_read(APIC_ESR);
 	ack_APIC_irq();
 	atomic_inc(&irq_err_count);
 
-	apic_printk(APIC_DEBUG, KERN_DEBUG "APIC error on CPU%d: %02x(%02x)",
-		    smp_processor_id(), v0 , v1);
+	apic_printk(APIC_DEBUG, KERN_DEBUG "APIC error on CPU%d: %02x",
+		    smp_processor_id(), v);
 
-	v1 = v1 & 0xff;
-	while (v1) {
-		if (v1 & 0x1)
+	v &= 0xff;
+	while (v) {
+		if (v & 0x1)
 			apic_printk(APIC_DEBUG, KERN_CONT " : %s", error_interrupt_reason[i]);
 		i++;
-		v1 >>= 1;
+		v >>= 1;
 	}
 
 	apic_printk(APIC_DEBUG, KERN_CONT "\n");
 
-	irq_exit();
+}
+
+__visible void smp_error_interrupt(struct pt_regs *regs)
+{
+	entering_irq();
+	__smp_error_interrupt(regs);
+	exiting_irq();
+}
+
+__visible void smp_trace_error_interrupt(struct pt_regs *regs)
+{
+	entering_irq();
+	trace_error_apic_entry(ERROR_APIC_VECTOR);
+	__smp_error_interrupt(regs);
+	trace_error_apic_exit(ERROR_APIC_VECTOR);
+	exiting_irq();
 }
 
 /**
@@ -2030,13 +2122,45 @@ void disconnect_bsp_APIC(int virt_wire_setup)
 	apic_write(APIC_LVT1, value);
 }
 
-void __cpuinit generic_processor_info(int apicid, int version)
+int generic_processor_info(int apicid, int version)
 {
 	int cpu, max = nr_cpu_ids;
 	bool boot_cpu_detected = physid_isset(boot_cpu_physical_apicid,
 				phys_cpu_present_map);
 
 	/*
+	 * boot_cpu_physical_apicid is designed to have the apicid
+	 * returned by read_apic_id(), i.e, the apicid of the
+	 * currently booting-up processor. However, on some platforms,
+	 * it is temporarily modified by the apicid reported as BSP
+	 * through MP table. Concretely:
+	 *
+	 * - arch/x86/kernel/mpparse.c: MP_processor_info()
+	 * - arch/x86/mm/amdtopology.c: amd_numa_init()
+	 *
+	 * This function is executed with the modified
+	 * boot_cpu_physical_apicid. So, disabled_cpu_apicid kernel
+	 * parameter doesn't work to disable APs on kdump 2nd kernel.
+	 *
+	 * Since fixing handling of boot_cpu_physical_apicid requires
+	 * another discussion and tests on each platform, we leave it
+	 * for now and here we use read_apic_id() directly in this
+	 * function, generic_processor_info().
+	 */
+	if (disabled_cpu_apicid != BAD_APICID &&
+	    disabled_cpu_apicid != read_apic_id() &&
+	    disabled_cpu_apicid == apicid) {
+		int thiscpu = num_processors + disabled_cpus;
+
+		pr_warning("APIC: Disabling requested cpu."
+			   " Processor %d/0x%x ignored.\n",
+			   thiscpu, apicid);
+
+		disabled_cpus++;
+		return -ENODEV;
+	}
+
+	/*
 	 * If boot cpu has not been detected yet, then only allow upto
 	 * nr_cpu_ids - 1 processors and keep one slot free for boot cpu
 	 */
@@ -2050,7 +2174,7 @@ void __cpuinit generic_processor_info(int apicid, int version)
 			"  Processor %d/0x%x ignored.\n", max, thiscpu, apicid);
 
 		disabled_cpus++;
-		return;
+		return -ENODEV;
 	}
 
 	if (num_processors >= nr_cpu_ids) {
@@ -2061,7 +2185,7 @@ void __cpuinit generic_processor_info(int apicid, int version)
 			"  Processor %d/0x%x ignored.\n", max, thiscpu, apicid);
 
 		disabled_cpus++;
-		return;
+		return -EINVAL;
 	}
 
 	num_processors++;
@@ -2106,6 +2230,8 @@ void __cpuinit generic_processor_info(int apicid, int version)
 #endif
 	set_cpu_possible(cpu, true);
 	set_cpu_present(cpu, true);
+
+	return cpu;
 }
 
 int hard_smp_processor_id(void)
@@ -2218,8 +2344,7 @@ static int lapic_suspend(void)
 	local_irq_save(flags);
 	disable_local_APIC();
 
-	if (irq_remapping_enabled)
-		irq_remapping_disable();
+	irq_remapping_disable();
 
 	local_irq_restore(flags);
 	return 0;
@@ -2235,16 +2360,15 @@ static void lapic_resume(void)
 		return;
 
 	local_irq_save(flags);
-	if (irq_remapping_enabled) {
-		/*
-		 * IO-APIC and PIC have their own resume routines.
-		 * We just mask them here to make sure the interrupt
-		 * subsystem is completely quiet while we enable x2apic
-		 * and interrupt-remapping.
-		 */
-		mask_ioapic_entries();
-		legacy_pic->mask_all();
-	}
+
+	/*
+	 * IO-APIC and PIC have their own resume routines.
+	 * We just mask them here to make sure the interrupt
+	 * subsystem is completely quiet while we enable x2apic
+	 * and interrupt-remapping.
+	 */
+	mask_ioapic_entries();
+	legacy_pic->mask_all();
 
 	if (x2apic_mode)
 		enable_x2apic();
@@ -2272,7 +2396,7 @@ static void lapic_resume(void)
 	apic_write(APIC_SPIV, apic_pm_state.apic_spiv);
 	apic_write(APIC_LVT0, apic_pm_state.apic_lvt0);
 	apic_write(APIC_LVT1, apic_pm_state.apic_lvt1);
-#if defined(CONFIG_X86_MCE_P4THERMAL) || defined(CONFIG_X86_MCE_INTEL)
+#if defined(CONFIG_X86_MCE_INTEL)
 	if (maxlvt >= 5)
 		apic_write(APIC_LVTTHMR, apic_pm_state.apic_thmr);
 #endif
@@ -2287,8 +2411,7 @@ static void lapic_resume(void)
 	apic_write(APIC_ESR, 0);
 	apic_read(APIC_ESR);
 
-	if (irq_remapping_enabled)
-		irq_remapping_reenable(x2apic_mode);
+	irq_remapping_reenable(x2apic_mode);
 
 	local_irq_restore(flags);
 }
@@ -2303,7 +2426,7 @@ static struct syscore_ops lapic_syscore_ops = {
 	.suspend	= lapic_suspend,
 };
 
-static void __cpuinit apic_pm_activate(void)
+static void apic_pm_activate(void)
 {
 	apic_pm_state.active = 1;
 }
@@ -2328,7 +2451,7 @@ static void apic_pm_activate(void) { }
 
 #ifdef CONFIG_X86_64
 
-static int __cpuinit apic_cluster_num(void)
+static int apic_cluster_num(void)
 {
 	int i, clusters, zeros;
 	unsigned id;
@@ -2373,10 +2496,10 @@ static int __cpuinit apic_cluster_num(void)
 	return clusters;
 }
 
-static int __cpuinitdata multi_checked;
-static int __cpuinitdata multi;
+static int multi_checked;
+static int multi;
 
-static int __cpuinit set_multi(const struct dmi_system_id *d)
+static int set_multi(const struct dmi_system_id *d)
 {
 	if (multi)
 		return 0;
@@ -2385,7 +2508,7 @@ static int __cpuinit set_multi(const struct dmi_system_id *d)
 	return 0;
 }
 
-static const __cpuinitconst struct dmi_system_id multi_dmi_table[] = {
+static const struct dmi_system_id multi_dmi_table[] = {
 	{
 		.callback = set_multi,
 		.ident = "IBM System Summit2",
@@ -2397,7 +2520,7 @@ static const __cpuinitconst struct dmi_system_id multi_dmi_table[] = {
 	{}
 };
 
-static void __cpuinit dmi_check_multi(void)
+static void dmi_check_multi(void)
 {
 	if (multi_checked)
 		return;
@@ -2414,7 +2537,7 @@ static void __cpuinit dmi_check_multi(void)
  * multi-chassis.
  * Use DMI to check them
  */
-__cpuinit int apic_is_clustered_box(void)
+int apic_is_clustered_box(void)
 {
 	dmi_check_multi();
 	if (multi)
@@ -2515,3 +2638,12 @@ static int __init lapic_insert_resource(void)
  * that is using request_resource
  */
 late_initcall(lapic_insert_resource);
+
+static int __init apic_set_disabled_cpu_apicid(char *arg)
+{
+	if (!arg || !get_option(&arg, &disabled_cpu_apicid))
+		return -EINVAL;
+
+	return 0;
+}
+early_param("disable_cpu_apicid", apic_set_disabled_cpu_apicid);