Merge branch 'x86-apic-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 apic updates from Thomas Gleixner:

 - Cleanup the apic IPI implementation by removing duplicated code and
   consolidating the functions into the APIC core.

 - Implement a safe variant of the IPI broadcast mode. Contrary to
   earlier attempts this uses the core tracking of which CPUs have been
   brought online at least once so that a broadcast does not end up in
   some dead end in BIOS/SMM code when the CPU is still waiting for
   init. Once all CPUs have been brought up once, IPI broadcasting is
   enabled. Before that regular one by one IPIs are issued.

 - Drop the paravirt CR8 related functions as they have no user anymore

 - Initialize the APIC TPR to block interrupt 16-31 as they are reserved
   for CPU exceptions and should never be raised by any well behaving
   device.

 - Emit a warning when vector space exhaustion breaks the admin set
   affinity of an interrupt.

 - Make sure to use the NMI fallback when shutdown via reboot vector IPI
   fails. The original code had conditions which prevent the code path
   to be reached.

 - Annotate various APIC config variables as RO after init.

[ The ipi broadcase change came in earlier through the cpu hotplug
  branch, but I left the explanation in the commit message since it was
  shared between the two different branches    - Linus ]

* 'x86-apic-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (28 commits)
  x86/apic/vector: Warn when vector space exhaustion breaks affinity
  x86/apic: Annotate global config variables as "read-only after init"
  x86/apic/x2apic: Implement IPI shorthands support
  x86/apic/flat64: Remove the IPI shorthand decision logic
  x86/apic: Share common IPI helpers
  x86/apic: Remove the shorthand decision logic
  x86/smp: Enhance native_send_call_func_ipi()
  x86/smp: Move smp_function_call implementations into IPI code
  x86/apic: Provide and use helper for send_IPI_allbutself()
  x86/apic: Add static key to Control IPI shorthands
  x86/apic: Move no_ipi_broadcast() out of 32bit
  x86/apic: Add NMI_VECTOR wait to IPI shorthand
  x86/apic: Remove dest argument from __default_send_IPI_shortcut()
  x86/hotplug: Silence APIC and NMI when CPU is dead
  x86/cpu: Move arch_smt_update() to a neutral place
  x86/apic/uv: Make x2apic_extra_bits static
  x86/apic: Consolidate the apic local headers
  x86/apic: Move apic_flat_64 header into apic directory
  x86/apic: Move ipi header into apic directory
  x86/apic: Cleanup the include maze
  ...

1 files changed, 115 insertions, 73 deletions

diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 909abb2d59eb..9e2dd2b296cd 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -65,10 +65,10 @@ unsigned int num_processors;
 unsigned disabled_cpus;
 
 /* Processor that is doing the boot up */
-unsigned int boot_cpu_physical_apicid = -1U;
+unsigned int boot_cpu_physical_apicid __ro_after_init = -1U;
 EXPORT_SYMBOL_GPL(boot_cpu_physical_apicid);
 
-u8 boot_cpu_apic_version;
+u8 boot_cpu_apic_version __ro_after_init;
 
 /*
  * The highest APIC ID seen during enumeration.
@@ -85,13 +85,13 @@ physid_mask_t phys_cpu_present_map;
  * 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;
+static unsigned int disabled_cpu_apicid __ro_after_init = BAD_APICID;
 
 /*
  * This variable controls which CPUs receive external NMIs.  By default,
  * external NMIs are delivered only to the BSP.
  */
-static int apic_extnmi = APIC_EXTNMI_BSP;
+static int apic_extnmi __ro_after_init = APIC_EXTNMI_BSP;
 
 /*
  * Map cpu index to physical APIC ID
@@ -114,7 +114,7 @@ EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_acpiid);
 DEFINE_EARLY_PER_CPU_READ_MOSTLY(int, x86_cpu_to_logical_apicid, BAD_APICID);
 
 /* Local APIC was disabled by the BIOS and enabled by the kernel */
-static int enabled_via_apicbase;
+static int enabled_via_apicbase __ro_after_init;
 
 /*
  * Handle interrupt mode configuration register (IMCR).
@@ -172,23 +172,23 @@ static __init int setup_apicpmtimer(char *s)
 __setup("apicpmtimer", setup_apicpmtimer);
 #endif
 
-unsigned long mp_lapic_addr;
-int disable_apic;
+unsigned long mp_lapic_addr __ro_after_init;
+int disable_apic __ro_after_init;
 /* Disable local APIC timer from the kernel commandline or via dmi quirk */
 static int disable_apic_timer __initdata;
 /* Local APIC timer works in C2 */
-int local_apic_timer_c2_ok;
+int local_apic_timer_c2_ok __ro_after_init;
 EXPORT_SYMBOL_GPL(local_apic_timer_c2_ok);
 
 /*
  * Debug level, exported for io_apic.c
  */
-int apic_verbosity;
+int apic_verbosity __ro_after_init;
 
-int pic_mode;
+int pic_mode __ro_after_init;
 
 /* Have we found an MP table */
-int smp_found_config;
+int smp_found_config __ro_after_init;
 
 static struct resource lapic_resource = {
 	.name = "Local APIC",
@@ -199,7 +199,7 @@ unsigned int lapic_timer_period = 0;
 
 static void apic_pm_activate(void);
 
-static unsigned long apic_phys;
+static unsigned long apic_phys __ro_after_init;
 
 /*
  * Get the LAPIC version
@@ -1224,25 +1224,38 @@ void clear_local_APIC(void)
 }
 
 /**
- * disable_local_APIC - clear and disable the local APIC
+ * apic_soft_disable - Clears and software disables the local APIC on hotplug
+ *
+ * Contrary to disable_local_APIC() this does not touch the enable bit in
+ * MSR_IA32_APICBASE. Clearing that bit on systems based on the 3 wire APIC
+ * bus would require a hardware reset as the APIC would lose track of bus
+ * arbitration. On systems with FSB delivery APICBASE could be disabled,
+ * but it has to be guaranteed that no interrupt is sent to the APIC while
+ * in that state and it's not clear from the SDM whether it still responds
+ * to INIT/SIPI messages. Stay on the safe side and use software disable.
  */
-void disable_local_APIC(void)
+void apic_soft_disable(void)
 {
-	unsigned int value;
-
-	/* APIC hasn't been mapped yet */
-	if (!x2apic_mode && !apic_phys)
-		return;
+	u32 value;
 
 	clear_local_APIC();
 
-	/*
-	 * Disable APIC (implies clearing of registers
-	 * for 82489DX!).
-	 */
+	/* Soft disable APIC (implies clearing of registers for 82489DX!). */
 	value = apic_read(APIC_SPIV);
 	value &= ~APIC_SPIV_APIC_ENABLED;
 	apic_write(APIC_SPIV, value);
+}
+
+/**
+ * disable_local_APIC - clear and disable the local APIC
+ */
+void disable_local_APIC(void)
+{
+	/* APIC hasn't been mapped yet */
+	if (!x2apic_mode && !apic_phys)
+		return;
+
+	apic_soft_disable();
 
 #ifdef CONFIG_X86_32
 	/*
@@ -1307,7 +1320,7 @@ void __init sync_Arb_IDs(void)
 			APIC_INT_LEVELTRIG | APIC_DM_INIT);
 }
 
-enum apic_intr_mode_id apic_intr_mode;
+enum apic_intr_mode_id apic_intr_mode __ro_after_init;
 
 static int __init apic_intr_mode_select(void)
 {
@@ -1495,54 +1508,72 @@ static void lapic_setup_esr(void)
 			oldvalue, value);
 }
 
-static void apic_pending_intr_clear(void)
+#define APIC_IR_REGS		APIC_ISR_NR
+#define APIC_IR_BITS		(APIC_IR_REGS * 32)
+#define APIC_IR_MAPSIZE		(APIC_IR_BITS / BITS_PER_LONG)
+
+union apic_ir {
+	unsigned long	map[APIC_IR_MAPSIZE];
+	u32		regs[APIC_IR_REGS];
+};
+
+static bool apic_check_and_ack(union apic_ir *irr, union apic_ir *isr)
 {
-	long long max_loops = cpu_khz ? cpu_khz : 1000000;
-	unsigned long long tsc = 0, ntsc;
-	unsigned int queued;
-	unsigned long value;
-	int i, j, acked = 0;
+	int i, bit;
+
+	/* Read the IRRs */
+	for (i = 0; i < APIC_IR_REGS; i++)
+		irr->regs[i] = apic_read(APIC_IRR + i * 0x10);
+
+	/* Read the ISRs */
+	for (i = 0; i < APIC_IR_REGS; i++)
+		isr->regs[i] = apic_read(APIC_ISR + i * 0x10);
 
-	if (boot_cpu_has(X86_FEATURE_TSC))
-		tsc = rdtsc();
 	/*
-	 * After a crash, we no longer service the interrupts and a pending
-	 * interrupt from previous kernel might still have ISR bit set.
-	 *
-	 * Most probably by now CPU has serviced that pending interrupt and
-	 * it might not have done the ack_APIC_irq() because it thought,
-	 * interrupt came from i8259 as ExtInt. LAPIC did not get EOI so it
-	 * does not clear the ISR bit and cpu thinks it has already serivced
-	 * the interrupt. Hence a vector might get locked. It was noticed
-	 * for timer irq (vector 0x31). Issue an extra EOI to clear ISR.
+	 * If the ISR map is not empty. ACK the APIC and run another round
+	 * to verify whether a pending IRR has been unblocked and turned
+	 * into a ISR.
 	 */
-	do {
-		queued = 0;
-		for (i = APIC_ISR_NR - 1; i >= 0; i--)
-			queued |= apic_read(APIC_IRR + i*0x10);
-
-		for (i = APIC_ISR_NR - 1; i >= 0; i--) {
-			value = apic_read(APIC_ISR + i*0x10);
-			for_each_set_bit(j, &value, 32) {
-				ack_APIC_irq();
-				acked++;
-			}
-		}
-		if (acked > 256) {
-			pr_err("LAPIC pending interrupts after %d EOI\n", acked);
-			break;
-		}
-		if (queued) {
-			if (boot_cpu_has(X86_FEATURE_TSC) && cpu_khz) {
-				ntsc = rdtsc();
-				max_loops = (long long)cpu_khz << 10;
-				max_loops -= ntsc - tsc;
-			} else {
-				max_loops--;
-			}
-		}
-	} while (queued && max_loops > 0);
-	WARN_ON(max_loops <= 0);
+	if (!bitmap_empty(isr->map, APIC_IR_BITS)) {
+		/*
+		 * There can be multiple ISR bits set when a high priority
+		 * interrupt preempted a lower priority one. Issue an ACK
+		 * per set bit.
+		 */
+		for_each_set_bit(bit, isr->map, APIC_IR_BITS)
+			ack_APIC_irq();
+		return true;
+	}
+
+	return !bitmap_empty(irr->map, APIC_IR_BITS);
+}
+
+/*
+ * After a crash, we no longer service the interrupts and a pending
+ * interrupt from previous kernel might still have ISR bit set.
+ *
+ * Most probably by now the CPU has serviced that pending interrupt and it
+ * might not have done the ack_APIC_irq() because it thought, interrupt
+ * came from i8259 as ExtInt. LAPIC did not get EOI so it does not clear
+ * the ISR bit and cpu thinks it has already serivced the interrupt. Hence
+ * a vector might get locked. It was noticed for timer irq (vector
+ * 0x31). Issue an extra EOI to clear ISR.
+ *
+ * If there are pending IRR bits they turn into ISR bits after a higher
+ * priority ISR bit has been acked.
+ */
+static void apic_pending_intr_clear(void)
+{
+	union apic_ir irr, isr;
+	unsigned int i;
+
+	/* 512 loops are way oversized and give the APIC a chance to obey. */
+	for (i = 0; i < 512; i++) {
+		if (!apic_check_and_ack(&irr, &isr))
+			return;
+	}
+	/* Dump the IRR/ISR content if that failed */
+	pr_warn("APIC: Stale IRR: %256pb ISR: %256pb\n", irr.map, isr.map);
 }
 
 /**
@@ -1559,12 +1590,19 @@ static void setup_local_APIC(void)
 	int logical_apicid, ldr_apicid;
 #endif
 
-
 	if (disable_apic) {
 		disable_ioapic_support();
 		return;
 	}
 
+	/*
+	 * If this comes from kexec/kcrash the APIC might be enabled in
+	 * SPIV. Soft disable it before doing further initialization.
+	 */
+	value = apic_read(APIC_SPIV);
+	value &= ~APIC_SPIV_APIC_ENABLED;
+	apic_write(APIC_SPIV, value);
+
 #ifdef CONFIG_X86_32
 	/* Pound the ESR really hard over the head with a big hammer - mbligh */
 	if (lapic_is_integrated() && apic->disable_esr) {
@@ -1574,8 +1612,6 @@ static void setup_local_APIC(void)
 		apic_write(APIC_ESR, 0);
 	}
 #endif
-	perf_events_lapic_init();
-
 	/*
 	 * Double-check whether this APIC is really registered.
 	 * This is meaningless in clustered apic mode, so we skip it.
@@ -1603,13 +1639,17 @@ static void setup_local_APIC(void)
 #endif
 
 	/*
-	 * Set Task Priority to 'accept all'. We never change this
-	 * later on.
+	 * Set Task Priority to 'accept all except vectors 0-31'.  An APIC
+	 * vector in the 16-31 range could be delivered if TPR == 0, but we
+	 * would think it's an exception and terrible things will happen.  We
+	 * never change this later on.
 	 */
 	value = apic_read(APIC_TASKPRI);
 	value &= ~APIC_TPRI_MASK;
+	value |= 0x10;
 	apic_write(APIC_TASKPRI, value);
 
+	/* Clear eventually stale ISR/IRR bits */
 	apic_pending_intr_clear();
 
 	/*
@@ -1656,6 +1696,8 @@ static void setup_local_APIC(void)
 	value |= SPURIOUS_APIC_VECTOR;
 	apic_write(APIC_SPIV, value);
 
+	perf_events_lapic_init();
+
 	/*
 	 * Set up LVT0, LVT1:
 	 *