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:
 "This udpate contains:

   - rework the irq vector array to store a pointer to the irq
     descriptor instead of the irq number to avoid a lookup of the irq
     descriptor in the irq entry path

   - lguest interrupt handling cleanups

   - conversion of the local apic timer to the new clockevent callbacks

   - preparatory changes for the irq argument removal of interrupt flow
     handlers"

* 'x86-apic-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/irq: Do not dereference irq descriptor before checking it
  tools/lguest: Clean up include dir
  tools/lguest: Fix redefinition of struct virtio_pci_cfg_cap
  x86/irq: Store irq descriptor in vector array
  genirq: Provide irq_desc_has_action
  x86/irq: Get rid of an indentation level
  x86/irq: Rename VECTOR_UNDEFINED to VECTOR_UNUSED
  x86/irq: Replace numeric constant
  x86/irq: Protect smp_cleanup_move
  x86/lguest: Do not setup unused irq vectors
  x86/lguest: Clean up lguest_setup_irq
  x86/apic: Drop local_irq_save/restore in timer callbacks
  x86/apic: Migrate apic timer to new set_state interface
  x86/irq: Use access helper irq_data_get_affinity_mask()
  x86/irq: Use accessor irq_data_get_irq_handler_data()
  x86/irq: Use accessor irq_data_get_node()

arch/x86/include/asm/hw_irq.h

@@ -182,10 +182,10 @@ extern char irq_entries_start[];
 #define trace_irq_entries_start irq_entries_start
 #endif
 
-#define VECTOR_UNDEFINED	(-1)
-#define VECTOR_RETRIGGERED	(-2)
+#define VECTOR_UNUSED		NULL
+#define VECTOR_RETRIGGERED	((void *)~0UL)
 
-typedef int vector_irq_t[NR_VECTORS];
+typedef struct irq_desc* vector_irq_t[NR_VECTORS];
 DECLARE_PER_CPU(vector_irq_t, vector_irq);
 
 #endif /* !ASSEMBLY_ */

arch/x86/include/asm/irq.h

@@ -36,7 +36,9 @@ extern void kvm_set_posted_intr_wakeup_handler(void (*handler)(void));
 
 extern void (*x86_platform_ipi_callback)(void);
 extern void native_init_IRQ(void);
-extern bool handle_irq(unsigned irq, struct pt_regs *regs);
+
+struct irq_desc;
+extern bool handle_irq(struct irq_desc *desc, struct pt_regs *regs);
 
 extern __visible unsigned int do_IRQ(struct pt_regs *regs);
 

arch/x86/kernel/apic/apic.c

@@ -462,40 +462,40 @@ static int lapic_next_deadline(unsigned long delta,
 	return 0;
 }
 
-/*
- * Setup the lapic timer in periodic or oneshot mode
- */
-static void lapic_timer_setup(enum clock_event_mode mode,
-			      struct clock_event_device *evt)
+static int lapic_timer_shutdown(struct clock_event_device *evt)
 {
-	unsigned long flags;
 	unsigned int v;
 
 	/* Lapic used as dummy for broadcast ? */
 	if (evt->features & CLOCK_EVT_FEAT_DUMMY)
-		return;
+		return 0;
 
-	local_irq_save(flags);
+	v = apic_read(APIC_LVTT);
+	v |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR);
+	apic_write(APIC_LVTT, v);
+	apic_write(APIC_TMICT, 0);
+	return 0;
+}
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-	case CLOCK_EVT_MODE_ONESHOT:
-		__setup_APIC_LVTT(lapic_timer_frequency,
-				  mode != CLOCK_EVT_MODE_PERIODIC, 1);
-		break;
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		v = apic_read(APIC_LVTT);
-		v |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR);
-		apic_write(APIC_LVTT, v);
-		apic_write(APIC_TMICT, 0);
-		break;
-	case CLOCK_EVT_MODE_RESUME:
-		/* Nothing to do here */
-		break;
-	}
+static inline int
+lapic_timer_set_periodic_oneshot(struct clock_event_device *evt, bool oneshot)
+{
+	/* Lapic used as dummy for broadcast ? */
+	if (evt->features & CLOCK_EVT_FEAT_DUMMY)
+		return 0;
 
-	local_irq_restore(flags);
+	__setup_APIC_LVTT(lapic_timer_frequency, oneshot, 1);
+	return 0;
+}
+
+static int lapic_timer_set_periodic(struct clock_event_device *evt)
+{
+	return lapic_timer_set_periodic_oneshot(evt, false);
+}
+
+static int lapic_timer_set_oneshot(struct clock_event_device *evt)
+{
+	return lapic_timer_set_periodic_oneshot(evt, true);
 }
 
 /*
@@ -513,15 +513,18 @@ static void lapic_timer_broadcast(const struct cpumask *mask)
  * The local apic timer can be used for any function which is CPU local.
  */
 static struct clock_event_device lapic_clockevent = {
-	.name		= "lapic",
-	.features	= CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT
-			| CLOCK_EVT_FEAT_C3STOP | CLOCK_EVT_FEAT_DUMMY,
-	.shift		= 32,
-	.set_mode	= lapic_timer_setup,
-	.set_next_event	= lapic_next_event,
-	.broadcast	= lapic_timer_broadcast,
-	.rating		= 100,
-	.irq		= -1,
+	.name			= "lapic",
+	.features		= CLOCK_EVT_FEAT_PERIODIC |
+				  CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_C3STOP
+				  | CLOCK_EVT_FEAT_DUMMY,
+	.shift			= 32,
+	.set_state_shutdown	= lapic_timer_shutdown,
+	.set_state_periodic	= lapic_timer_set_periodic,
+	.set_state_oneshot	= lapic_timer_set_oneshot,
+	.set_next_event		= lapic_next_event,
+	.broadcast		= lapic_timer_broadcast,
+	.rating			= 100,
+	.irq			= -1,
 };
 static DEFINE_PER_CPU(struct clock_event_device, lapic_events);
 
@@ -778,7 +781,7 @@ static int __init calibrate_APIC_clock(void)
 		 * Setup the apic timer manually
 		 */
 		levt->event_handler = lapic_cal_handler;
-		lapic_timer_setup(CLOCK_EVT_MODE_PERIODIC, levt);
+		lapic_timer_set_periodic(levt);
 		lapic_cal_loops = -1;
 
 		/* Let the interrupts run */
@@ -788,7 +791,8 @@ static int __init calibrate_APIC_clock(void)
 			cpu_relax();
 
 		/* Stop the lapic timer */
-		lapic_timer_setup(CLOCK_EVT_MODE_SHUTDOWN, levt);
+		local_irq_disable();
+		lapic_timer_shutdown(levt);
 
 		/* Jiffies delta */
 		deltaj = lapic_cal_j2 - lapic_cal_j1;
@@ -799,8 +803,8 @@ static int __init calibrate_APIC_clock(void)
 			apic_printk(APIC_VERBOSE, "... jiffies result ok\n");
 		else
 			levt->features |= CLOCK_EVT_FEAT_DUMMY;
-	} else
-		local_irq_enable();
+	}
+	local_irq_enable();
 
 	if (levt->features & CLOCK_EVT_FEAT_DUMMY) {
 		pr_warning("APIC timer disabled due to verification failure\n");
@@ -878,7 +882,7 @@ static void local_apic_timer_interrupt(void)
 	if (!evt->event_handler) {
 		pr_warning("Spurious LAPIC timer interrupt on cpu %d\n", cpu);
 		/* Switch it off */
-		lapic_timer_setup(CLOCK_EVT_MODE_SHUTDOWN, evt);
+		lapic_timer_shutdown(evt);
 		return;
 	}
 

arch/x86/kernel/apic/io_apic.c

@@ -2541,7 +2541,7 @@ void __init setup_ioapic_dest(void)
 		 * Honour affinities which have been set in early boot
 		 */
 		if (!irqd_can_balance(idata) || irqd_affinity_was_set(idata))
-			mask = idata->affinity;
+			mask = irq_data_get_affinity_mask(idata);
 		else
 			mask = apic->target_cpus();
 

arch/x86/kernel/apic/msi.c

@@ -264,7 +264,7 @@ static inline int hpet_dev_id(struct irq_domain *domain)
 
 static void hpet_msi_write_msg(struct irq_data *data, struct msi_msg *msg)
 {
-	hpet_msi_write(data->handler_data, msg);
+	hpet_msi_write(irq_data_get_irq_handler_data(data), msg);
 }
 
 static struct irq_chip hpet_msi_controller = {

arch/x86/kernel/apic/vector.c

@@ -169,8 +169,7 @@ static int __assign_irq_vector(int irq, struct apic_chip_data *d,
 			goto next;
 
 		for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask) {
-			if (per_cpu(vector_irq, new_cpu)[vector] >
-			    VECTOR_UNDEFINED)
+			if (!IS_ERR_OR_NULL(per_cpu(vector_irq, new_cpu)[vector]))
 				goto next;
 		}
 		/* Found one! */
@@ -182,7 +181,7 @@ static int __assign_irq_vector(int irq, struct apic_chip_data *d,
 			   cpumask_intersects(d->old_domain, cpu_online_mask);
 		}
 		for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask)
-			per_cpu(vector_irq, new_cpu)[vector] = irq;
+			per_cpu(vector_irq, new_cpu)[vector] = irq_to_desc(irq);
 		d->cfg.vector = vector;
 		cpumask_copy(d->domain, vector_cpumask);
 		err = 0;
@@ -224,15 +223,16 @@ static int assign_irq_vector_policy(int irq, int node,
 
 static void clear_irq_vector(int irq, struct apic_chip_data *data)
 {
-	int cpu, vector;
+	struct irq_desc *desc;
 	unsigned long flags;
+	int cpu, vector;
 
 	raw_spin_lock_irqsave(&vector_lock, flags);
 	BUG_ON(!data->cfg.vector);
 
 	vector = data->cfg.vector;
 	for_each_cpu_and(cpu, data->domain, cpu_online_mask)
-		per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED;
+		per_cpu(vector_irq, cpu)[vector] = VECTOR_UNUSED;
 
 	data->cfg.vector = 0;
 	cpumask_clear(data->domain);
@@ -242,12 +242,13 @@ static void clear_irq_vector(int irq, struct apic_chip_data *data)
 		return;
 	}
 
+	desc = irq_to_desc(irq);
 	for_each_cpu_and(cpu, data->old_domain, cpu_online_mask) {
 		for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS;
 		     vector++) {
-			if (per_cpu(vector_irq, cpu)[vector] != irq)
+			if (per_cpu(vector_irq, cpu)[vector] != desc)
 				continue;
-			per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED;
+			per_cpu(vector_irq, cpu)[vector] = VECTOR_UNUSED;
 			break;
 		}
 	}
@@ -296,7 +297,7 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq,
 	struct irq_alloc_info *info = arg;
 	struct apic_chip_data *data;
 	struct irq_data *irq_data;
-	int i, err;
+	int i, err, node;
 
 	if (disable_apic)
 		return -ENXIO;
@@ -308,12 +309,13 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq,
 	for (i = 0; i < nr_irqs; i++) {
 		irq_data = irq_domain_get_irq_data(domain, virq + i);
 		BUG_ON(!irq_data);
+		node = irq_data_get_node(irq_data);
 #ifdef	CONFIG_X86_IO_APIC
 		if (virq + i < nr_legacy_irqs() && legacy_irq_data[virq + i])
 			data = legacy_irq_data[virq + i];
 		else
 #endif
-			data = alloc_apic_chip_data(irq_data->node);
+			data = alloc_apic_chip_data(node);
 		if (!data) {
 			err = -ENOMEM;
 			goto error;
@@ -322,8 +324,7 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq,
 		irq_data->chip = &lapic_controller;
 		irq_data->chip_data = data;
 		irq_data->hwirq = virq + i;
-		err = assign_irq_vector_policy(virq + i, irq_data->node, data,
-					       info);
+		err = assign_irq_vector_policy(virq + i, node, data, info);
 		if (err)
 			goto error;
 	}
@@ -403,32 +404,32 @@ int __init arch_early_irq_init(void)
 	return arch_early_ioapic_init();
 }
 
+/* Initialize vector_irq on a new cpu */
 static void __setup_vector_irq(int cpu)
 {
-	/* Initialize vector_irq on a new cpu */
-	int irq, vector;
 	struct apic_chip_data *data;
+	struct irq_desc *desc;
+	int irq, vector;
 
 	/* Mark the inuse vectors */
-	for_each_active_irq(irq) {
-		data = apic_chip_data(irq_get_irq_data(irq));
-		if (!data)
-			continue;
+	for_each_irq_desc(irq, desc) {
+		struct irq_data *idata = irq_desc_get_irq_data(desc);
 
-		if (!cpumask_test_cpu(cpu, data->domain))
+		data = apic_chip_data(idata);
+		if (!data || !cpumask_test_cpu(cpu, data->domain))
 			continue;
 		vector = data->cfg.vector;
-		per_cpu(vector_irq, cpu)[vector] = irq;
+		per_cpu(vector_irq, cpu)[vector] = desc;
 	}
 	/* Mark the free vectors */
 	for (vector = 0; vector < NR_VECTORS; ++vector) {
-		irq = per_cpu(vector_irq, cpu)[vector];
-		if (irq <= VECTOR_UNDEFINED)
+		desc = per_cpu(vector_irq, cpu)[vector];
+		if (IS_ERR_OR_NULL(desc))
 			continue;
 
-		data = apic_chip_data(irq_get_irq_data(irq));
+		data = apic_chip_data(irq_desc_get_irq_data(desc));
 		if (!cpumask_test_cpu(cpu, data->domain))
-			per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED;
+			per_cpu(vector_irq, cpu)[vector] = VECTOR_UNUSED;
 	}
 }
 
@@ -448,7 +449,7 @@ void setup_vector_irq(int cpu)
 	 * legacy vector to irq mapping:
 	 */
 	for (irq = 0; irq < nr_legacy_irqs(); irq++)
-		per_cpu(vector_irq, cpu)[ISA_IRQ_VECTOR(irq)] = irq;
+		per_cpu(vector_irq, cpu)[ISA_IRQ_VECTOR(irq)] = irq_to_desc(irq);
 
 	__setup_vector_irq(cpu);
 }
@@ -490,7 +491,8 @@ static int apic_set_affinity(struct irq_data *irq_data,
 	if (err) {
 		struct irq_data *top = irq_get_irq_data(irq);
 
-		if (assign_irq_vector(irq, data, top->affinity))
+		if (assign_irq_vector(irq, data,
+				      irq_data_get_affinity_mask(top)))
 			pr_err("Failed to recover vector for irq %d\n", irq);
 		return err;
 	}
@@ -538,27 +540,30 @@ asmlinkage __visible void smp_irq_move_cleanup_interrupt(void)
 
 	entering_ack_irq();
 
+	/* Prevent vectors vanishing under us */
+	raw_spin_lock(&vector_lock);
+
 	me = smp_processor_id();
 	for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
-		int irq;
-		unsigned int irr;
-		struct irq_desc *desc;
 		struct apic_chip_data *data;
+		struct irq_desc *desc;
+		unsigned int irr;
 
-		irq = __this_cpu_read(vector_irq[vector]);
-
-		if (irq <= VECTOR_UNDEFINED)
+	retry:
+		desc = __this_cpu_read(vector_irq[vector]);
+		if (IS_ERR_OR_NULL(desc))
 			continue;
 
-		desc = irq_to_desc(irq);
-		if (!desc)
-			continue;
+		if (!raw_spin_trylock(&desc->lock)) {
+			raw_spin_unlock(&vector_lock);
+			cpu_relax();
+			raw_spin_lock(&vector_lock);
+			goto retry;
+		}
 
-		data = apic_chip_data(&desc->irq_data);
+		data = apic_chip_data(irq_desc_get_irq_data(desc));
 		if (!data)
-			continue;
-
-		raw_spin_lock(&desc->lock);
+			goto unlock;
 
 		/*
 		 * Check if the irq migration is in progress. If so, we
@@ -583,11 +588,13 @@ asmlinkage __visible void smp_irq_move_cleanup_interrupt(void)
 			apic->send_IPI_self(IRQ_MOVE_CLEANUP_VECTOR);
 			goto unlock;
 		}
-		__this_cpu_write(vector_irq[vector], VECTOR_UNDEFINED);
+		__this_cpu_write(vector_irq[vector], VECTOR_UNUSED);
 unlock:
 		raw_spin_unlock(&desc->lock);
 	}
 
+	raw_spin_unlock(&vector_lock);
+
 	exiting_irq();
 }
 

arch/x86/kernel/hpet.c

@@ -426,7 +426,7 @@ static struct irq_domain *hpet_domain;
 
 void hpet_msi_unmask(struct irq_data *data)
 {
-	struct hpet_dev *hdev = data->handler_data;
+	struct hpet_dev *hdev = irq_data_get_irq_handler_data(data);
 	unsigned int cfg;
 
 	/* unmask it */
@@ -437,7 +437,7 @@ void hpet_msi_unmask(struct irq_data *data)
 
 void hpet_msi_mask(struct irq_data *data)
 {
-	struct hpet_dev *hdev = data->handler_data;
+	struct hpet_dev *hdev = irq_data_get_irq_handler_data(data);
 	unsigned int cfg;
 
 	/* mask it */

arch/x86/kernel/irq.c

@@ -214,10 +214,9 @@ u64 arch_irq_stat(void)
 __visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
-
+	struct irq_desc * desc;
 	/* high bit used in ret_from_ code  */
 	unsigned vector = ~regs->orig_ax;
-	unsigned irq;
 
 	/*
 	 * NB: Unlike exception entries, IRQ entries do not reliably
@@ -236,17 +235,17 @@ __visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
 	/* entering_irq() tells RCU that we're not quiescent.  Check it. */
 	RCU_LOCKDEP_WARN(!rcu_is_watching(), "IRQ failed to wake up RCU");
 
-	irq = __this_cpu_read(vector_irq[vector]);
+	desc = __this_cpu_read(vector_irq[vector]);
 
-	if (!handle_irq(irq, regs)) {
+	if (!handle_irq(desc, regs)) {
 		ack_APIC_irq();
 
-		if (irq != VECTOR_RETRIGGERED) {
-			pr_emerg_ratelimited("%s: %d.%d No irq handler for vector (irq %d)\n",
+		if (desc != VECTOR_RETRIGGERED) {
+			pr_emerg_ratelimited("%s: %d.%d No irq handler for vector\n",
 					     __func__, smp_processor_id(),
-					     vector, irq);
+					     vector);
 		} else {
-			__this_cpu_write(vector_irq[vector], VECTOR_UNDEFINED);
+			__this_cpu_write(vector_irq[vector], VECTOR_UNUSED);
 		}
 	}
 
@@ -348,10 +347,10 @@ static struct cpumask affinity_new, online_new;
  */
 int check_irq_vectors_for_cpu_disable(void)
 {
-	int irq, cpu;
 	unsigned int this_cpu, vector, this_count, count;
 	struct irq_desc *desc;
 	struct irq_data *data;
+	int cpu;
 
 	this_cpu = smp_processor_id();
 	cpumask_copy(&online_new, cpu_online_mask);
@@ -359,47 +358,43 @@ int check_irq_vectors_for_cpu_disable(void)
 
 	this_count = 0;
 	for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
-		irq = __this_cpu_read(vector_irq[vector]);
-		if (irq >= 0) {
-			desc = irq_to_desc(irq);
-			if (!desc)
-				continue;
-
-			/*
-			 * Protect against concurrent action removal,
-			 * affinity changes etc.
-			 */
-			raw_spin_lock(&desc->lock);
-			data = irq_desc_get_irq_data(desc);
-			cpumask_copy(&affinity_new, data->affinity);
-			cpumask_clear_cpu(this_cpu, &affinity_new);
-
-			/* Do not count inactive or per-cpu irqs. */
-			if (!irq_has_action(irq) || irqd_is_per_cpu(data)) {
-				raw_spin_unlock(&desc->lock);
-				continue;
-			}
+		desc = __this_cpu_read(vector_irq[vector]);
+		if (IS_ERR_OR_NULL(desc))
+			continue;
+		/*
+		 * Protect against concurrent action removal, affinity
+		 * changes etc.
+		 */
+		raw_spin_lock(&desc->lock);
+		data = irq_desc_get_irq_data(desc);
+		cpumask_copy(&affinity_new,
+			     irq_data_get_affinity_mask(data));
+		cpumask_clear_cpu(this_cpu, &affinity_new);
 
+		/* Do not count inactive or per-cpu irqs. */
+		if (!irq_desc_has_action(desc) || irqd_is_per_cpu(data)) {
 			raw_spin_unlock(&desc->lock);
-			/*
-			 * A single irq may be mapped to multiple
-			 * cpu's vector_irq[] (for example IOAPIC cluster
-			 * mode).  In this case we have two
-			 * possibilities:
-			 *
-			 * 1) the resulting affinity mask is empty; that is
-			 * this the down'd cpu is the last cpu in the irq's
-			 * affinity mask, or
-			 *
-			 * 2) the resulting affinity mask is no longer
-			 * a subset of the online cpus but the affinity
-			 * mask is not zero; that is the down'd cpu is the
-			 * last online cpu in a user set affinity mask.
-			 */
-			if (cpumask_empty(&affinity_new) ||
-			    !cpumask_subset(&affinity_new, &online_new))
-				this_count++;
+			continue;
 		}
+
+		raw_spin_unlock(&desc->lock);
+		/*
+		 * A single irq may be mapped to multiple cpu's
+		 * vector_irq[] (for example IOAPIC cluster mode).  In
+		 * this case we have two possibilities:
+		 *
+		 * 1) the resulting affinity mask is empty; that is
+		 * this the down'd cpu is the last cpu in the irq's
+		 * affinity mask, or
+		 *
+		 * 2) the resulting affinity mask is no longer a
+		 * subset of the online cpus but the affinity mask is
+		 * not zero; that is the down'd cpu is the last online
+		 * cpu in a user set affinity mask.
+		 */
+		if (cpumask_empty(&affinity_new) ||
+		    !cpumask_subset(&affinity_new, &online_new))
+			this_count++;
 	}
 
 	count = 0;
@@ -418,8 +413,8 @@ int check_irq_vectors_for_cpu_disable(void)
 		for (vector = FIRST_EXTERNAL_VECTOR;
 		     vector < first_system_vector; vector++) {
 			if (!test_bit(vector, used_vectors) &&
-			    per_cpu(vector_irq, cpu)[vector] < 0)
-					count++;
+			    IS_ERR_OR_NULL(per_cpu(vector_irq, cpu)[vector]))
+			    count++;
 		}
 	}
 
@@ -455,7 +450,7 @@ void fixup_irqs(void)
 		raw_spin_lock(&desc->lock);
 
 		data = irq_desc_get_irq_data(desc);
-		affinity = data->affinity;
+		affinity = irq_data_get_affinity_mask(data);
 		if (!irq_has_action(irq) || irqd_is_per_cpu(data) ||
 		    cpumask_subset(affinity, cpu_online_mask)) {
 			raw_spin_unlock(&desc->lock);
@@ -523,14 +518,13 @@ void fixup_irqs(void)
 	for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
 		unsigned int irr;
 
-		if (__this_cpu_read(vector_irq[vector]) <= VECTOR_UNDEFINED)
+		if (IS_ERR_OR_NULL(__this_cpu_read(vector_irq[vector])))
 			continue;
 
 		irr = apic_read(APIC_IRR + (vector / 32 * 0x10));
 		if (irr  & (1 << (vector % 32))) {
-			irq = __this_cpu_read(vector_irq[vector]);
+			desc = __this_cpu_read(vector_irq[vector]);
 
-			desc = irq_to_desc(irq);
 			raw_spin_lock(&desc->lock);
 			data = irq_desc_get_irq_data(desc);
 			chip = irq_data_get_irq_chip(data);
@@ -541,7 +535,7 @@ void fixup_irqs(void)
 			raw_spin_unlock(&desc->lock);
 		}
 		if (__this_cpu_read(vector_irq[vector]) != VECTOR_RETRIGGERED)
-			__this_cpu_write(vector_irq[vector], VECTOR_UNDEFINED);
+			__this_cpu_write(vector_irq[vector], VECTOR_UNUSED);
 	}
 }
 #endif

arch/x86/kernel/irq_32.c

@@ -148,21 +148,21 @@ void do_softirq_own_stack(void)
 	call_on_stack(__do_softirq, isp);
 }
 
-bool handle_irq(unsigned irq, struct pt_regs *regs)
+bool handle_irq(struct irq_desc *desc, struct pt_regs *regs)
 {
-	struct irq_desc *desc;
+	unsigned int irq;
 	int overflow;
 
 	overflow = check_stack_overflow();
 
-	desc = irq_to_desc(irq);
-	if (unlikely(!desc))
+	if (IS_ERR_OR_NULL(desc))
 		return false;
 
+	irq = irq_desc_get_irq(desc);
 	if (user_mode(regs) || !execute_on_irq_stack(overflow, desc, irq)) {
 		if (unlikely(overflow))
 			print_stack_overflow();
-		desc->handle_irq(irq, desc);
+		generic_handle_irq_desc(irq, desc);
 	}
 
 	return true;

arch/x86/kernel/irq_64.c

@@ -68,16 +68,13 @@ static inline void stack_overflow_check(struct pt_regs *regs)
 #endif
 }
 
-bool handle_irq(unsigned irq, struct pt_regs *regs)
+bool handle_irq(struct irq_desc *desc, struct pt_regs *regs)
 {
-	struct irq_desc *desc;
-
 	stack_overflow_check(regs);
 
-	desc = irq_to_desc(irq);
-	if (unlikely(!desc))
+	if (unlikely(IS_ERR_OR_NULL(desc)))
 		return false;
 
-	generic_handle_irq_desc(irq, desc);
+	generic_handle_irq_desc(irq_desc_get_irq(desc), desc);
 	return true;
 }

arch/x86/kernel/irqinit.c

@@ -52,7 +52,7 @@ static struct irqaction irq2 = {
 };
 
 DEFINE_PER_CPU(vector_irq_t, vector_irq) = {
-	[0 ... NR_VECTORS - 1] = VECTOR_UNDEFINED,
+	[0 ... NR_VECTORS - 1] = VECTOR_UNUSED,
 };
 
 int vector_used_by_percpu_irq(unsigned int vector)
@@ -60,7 +60,7 @@ int vector_used_by_percpu_irq(unsigned int vector)
 	int cpu;
 
 	for_each_online_cpu(cpu) {
-		if (per_cpu(vector_irq, cpu)[vector] > VECTOR_UNDEFINED)
+		if (!IS_ERR_OR_NULL(per_cpu(vector_irq, cpu)[vector]))
 			return 1;
 	}
 
@@ -94,7 +94,7 @@ void __init init_IRQ(void)
 	 * irq's migrate etc.
 	 */
 	for (i = 0; i < nr_legacy_irqs(); i++)
-		per_cpu(vector_irq, 0)[ISA_IRQ_VECTOR(i)] = i;
+		per_cpu(vector_irq, 0)[ISA_IRQ_VECTOR(i)] = irq_to_desc(i);
 
 	x86_init.irqs.intr_init();
 }

arch/x86/lguest/boot.c

@@ -835,16 +835,46 @@ static struct irq_chip lguest_irq_controller = {
 	.irq_unmask	= enable_lguest_irq,
 };
 
+/*
+ * Interrupt descriptors are allocated as-needed, but low-numbered ones are
+ * reserved by the generic x86 code.  So we ignore irq_alloc_desc_at if it
+ * tells us the irq is already used: other errors (ie. ENOMEM) we take
+ * seriously.
+ */
+static int lguest_setup_irq(unsigned int irq)
+{
+	struct irq_desc *desc;
+	int err;
+
+	/* Returns -ve error or vector number. */
+	err = irq_alloc_desc_at(irq, 0);
+	if (err < 0 && err != -EEXIST)
+		return err;
+
+	/*
+	 * Tell the Linux infrastructure that the interrupt is
+	 * controlled by our level-based lguest interrupt controller.
+	 */
+	irq_set_chip_and_handler_name(irq, &lguest_irq_controller,
+				      handle_level_irq, "level");
+
+	/* Some systems map "vectors" to interrupts weirdly.  Not us! */
+	desc = irq_to_desc(irq);
+	__this_cpu_write(vector_irq[FIRST_EXTERNAL_VECTOR + irq], desc);
+	return 0;
+}
+
 static int lguest_enable_irq(struct pci_dev *dev)
 {
+	int err;
 	u8 line = 0;
 
 	/* We literally use the PCI interrupt line as the irq number. */
 	pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &line);
-	irq_set_chip_and_handler_name(line, &lguest_irq_controller,
-				      handle_level_irq, "level");
-	dev->irq = line;
-	return 0;
+	err = lguest_setup_irq(line);
+	if (!err)
+		dev->irq = line;
+	return err;
 }
 
 /* We don't do hotplug PCI, so this shouldn't be called. */
@@ -855,17 +885,13 @@ static void lguest_disable_irq(struct pci_dev *dev)
 
 /*
  * This sets up the Interrupt Descriptor Table (IDT) entry for each hardware
- * interrupt (except 128, which is used for system calls), and then tells the
- * Linux infrastructure that each interrupt is controlled by our level-based
- * lguest interrupt controller.
+ * interrupt (except 128, which is used for system calls).
  */
 static void __init lguest_init_IRQ(void)
 {
 	unsigned int i;
 
 	for (i = FIRST_EXTERNAL_VECTOR; i < FIRST_SYSTEM_VECTOR; i++) {
-		/* Some systems map "vectors" to interrupts weirdly.  Not us! */
-		__this_cpu_write(vector_irq[i], i - FIRST_EXTERNAL_VECTOR);
 		if (i != IA32_SYSCALL_VECTOR)
 			set_intr_gate(i, irq_entries_start +
 					8 * (i - FIRST_EXTERNAL_VECTOR));
@@ -878,26 +904,6 @@ static void __init lguest_init_IRQ(void)
 	irq_ctx_init(smp_processor_id());
 }
 
-/*
- * Interrupt descriptors are allocated as-needed, but low-numbered ones are
- * reserved by the generic x86 code.  So we ignore irq_alloc_desc_at if it
- * tells us the irq is already used: other errors (ie. ENOMEM) we take
- * seriously.
- */
-int lguest_setup_irq(unsigned int irq)
-{
-	int err;
-
-	/* Returns -ve error or vector number. */
-	err = irq_alloc_desc_at(irq, 0);
-	if (err < 0 && err != -EEXIST)
-		return err;
-
-	irq_set_chip_and_handler_name(irq, &lguest_irq_controller,
-				      handle_level_irq, "level");
-	return 0;
-}
-
 /*
  * Time.
  *
@@ -1028,7 +1034,8 @@ static void lguest_time_irq(unsigned int irq, struct irq_desc *desc)
 static void lguest_time_init(void)
 {
 	/* Set up the timer interrupt (0) to go to our simple timer routine */
-	lguest_setup_irq(0);
+	if (lguest_setup_irq(0) != 0)
+		panic("Could not set up timer irq");
 	irq_set_handler(0, lguest_time_irq);
 
 	clocksource_register_hz(&lguest_clock, NSEC_PER_SEC);

arch/x86/platform/uv/uv_irq.c

@@ -89,7 +89,7 @@ static int uv_domain_alloc(struct irq_domain *domain, unsigned int virq,
 		return -EINVAL;
 
 	chip_data = kmalloc_node(sizeof(*chip_data), GFP_KERNEL,
-				 irq_data->node);
+				 irq_data_get_node(irq_data));
 	if (!chip_data)
 		return -ENOMEM;
 

drivers/xen/events/events_base.c

@@ -336,7 +336,7 @@ static void bind_evtchn_to_cpu(unsigned int chn, unsigned int cpu)
 
 	BUG_ON(irq == -1);
 #ifdef CONFIG_SMP
-	cpumask_copy(irq_get_irq_data(irq)->affinity, cpumask_of(cpu));
+	cpumask_copy(irq_get_affinity_mask(irq), cpumask_of(cpu));
 #endif
 	xen_evtchn_port_bind_to_cpu(info, cpu);
 
@@ -373,7 +373,7 @@ static void xen_irq_init(unsigned irq)
 	struct irq_info *info;
 #ifdef CONFIG_SMP
 	/* By default all event channels notify CPU#0. */
-	cpumask_copy(irq_get_irq_data(irq)->affinity, cpumask_of(0));
+	cpumask_copy(irq_get_affinity_mask(irq), cpumask_of(0));
 #endif
 
 	info = kzalloc(sizeof(*info), GFP_KERNEL);

include/linux/irqdesc.h

@@ -166,12 +166,16 @@ static inline int handle_domain_irq(struct irq_domain *domain,
 #endif
 
 /* Test to see if a driver has successfully requested an irq */
-static inline int irq_has_action(unsigned int irq)
+static inline int irq_desc_has_action(struct irq_desc *desc)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
 	return desc->action != NULL;
 }
 
+static inline int irq_has_action(unsigned int irq)
+{
+	return irq_desc_has_action(irq_to_desc(irq));
+}
+
 /* caller has locked the irq_desc and both params are valid */
 static inline void __irq_set_handler_locked(unsigned int irq,
 					    irq_flow_handler_t handler)

tools/lguest/.gitignore

 lguest
+include

tools/lguest/Makefile

@@ -11,3 +11,4 @@ lguest: include/linux/virtio_types.h
 
 clean:
 	rm -f lguest
+	rm -rf include

tools/lguest/lguest.c

@@ -125,7 +125,11 @@ struct device_list {
 /* The list of Guest devices, based on command line arguments. */
 static struct device_list devices;
 
-struct virtio_pci_cfg_cap {
+/*
+ * Just like struct virtio_pci_cfg_cap in uapi/linux/virtio_pci.h,
+ * but uses a u32 explicitly for the data.
+ */
+struct virtio_pci_cfg_cap_u32 {
 	struct virtio_pci_cap cap;
 	u32 pci_cfg_data; /* Data for BAR access. */
 };
@@ -157,7 +161,7 @@ struct pci_config {
 	struct virtio_pci_notify_cap notify;
 	struct virtio_pci_cap isr;
 	struct virtio_pci_cap device;
-	struct virtio_pci_cfg_cap cfg_access;
+	struct virtio_pci_cfg_cap_u32 cfg_access;
 };
 
 /* The device structure describes a single device. */
@@ -1291,7 +1295,7 @@ static struct device *dev_and_reg(u32 *reg)
  * only fault if they try to write with some invalid bar/offset/length.
  */
 static bool valid_bar_access(struct device *d,
-			     struct virtio_pci_cfg_cap *cfg_access)
+			     struct virtio_pci_cfg_cap_u32 *cfg_access)
 {
 	/* We only have 1 bar (BAR0) */
 	if (cfg_access->cap.bar != 0)