X-Git-Url: http://pileus.org/git/?a=blobdiff_plain;f=arch%2Fx86%2Fkernel%2Fapic%2Fio_apic.c;h=b739d398bb29bc6951e777827cd56c982cedb452;hb=a6a25dd3270944f3c4182ffcbe0f60482471e849;hp=1817fa911024f07151d3edf91bd350722c9f79f8;hpb=818b930bc15077fc00ff16bb22c5df1857f05afa;p=~andy%2Flinux

diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 1817fa91102..9a7131f29c8 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -234,11 +234,11 @@ int __init arch_early_irq_init(void)
 		zalloc_cpumask_var_node(&cfg[i].old_domain, GFP_KERNEL, node);
 		/*
 		 * For legacy IRQ's, start with assigning irq0 to irq15 to
-		 * IRQ0_VECTOR to IRQ15_VECTOR on cpu 0.
+		 * IRQ0_VECTOR to IRQ15_VECTOR for all cpu's.
 		 */
 		if (i < legacy_pic->nr_legacy_irqs) {
 			cfg[i].vector = IRQ0_VECTOR + i;
-			cpumask_set_cpu(0, cfg[i].domain);
+			cpumask_setall(cfg[i].domain);
 		}
 	}
 
@@ -300,9 +300,9 @@ static struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node)
 	return cfg;
 }
 
-static int alloc_irq_from(unsigned int from, int node)
+static int alloc_irqs_from(unsigned int from, unsigned int count, int node)
 {
-	return irq_alloc_desc_from(from, node);
+	return irq_alloc_descs_from(from, count, node);
 }
 
 static void free_irq_at(unsigned int at, struct irq_cfg *cfg)
@@ -1141,7 +1141,8 @@ __assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask)
 			 * allocation for the members that are not used anymore.
 			 */
 			cpumask_andnot(cfg->old_domain, cfg->domain, tmp_mask);
-			cfg->move_in_progress = 1;
+			cfg->move_in_progress =
+			   cpumask_intersects(cfg->old_domain, cpu_online_mask);
 			cpumask_and(cfg->domain, cfg->domain, tmp_mask);
 			break;
 		}
@@ -1172,8 +1173,9 @@ next:
 		current_vector = vector;
 		current_offset = offset;
 		if (cfg->vector) {
-			cfg->move_in_progress = 1;
 			cpumask_copy(cfg->old_domain, cfg->domain);
+			cfg->move_in_progress =
+			   cpumask_intersects(cfg->old_domain, cpu_online_mask);
 		}
 		for_each_cpu_and(new_cpu, tmp_mask, cpu_online_mask)
 			per_cpu(vector_irq, new_cpu)[vector] = irq;
@@ -1241,12 +1243,6 @@ void __setup_vector_irq(int cpu)
 		cfg = irq_get_chip_data(irq);
 		if (!cfg)
 			continue;
-		/*
-		 * If it is a legacy IRQ handled by the legacy PIC, this cpu
-		 * will be part of the irq_cfg's domain.
-		 */
-		if (irq < legacy_pic->nr_legacy_irqs && !IO_APIC_IRQ(irq))
-			cpumask_set_cpu(cpu, cfg->domain);
 
 		if (!cpumask_test_cpu(cpu, cfg->domain))
 			continue;
@@ -1319,14 +1315,10 @@ static void ioapic_register_intr(unsigned int irq, struct irq_cfg *cfg,
 				      fasteoi ? "fasteoi" : "edge");
 }
 
-static int setup_ioapic_entry(int irq, struct IO_APIC_route_entry *entry,
-			       unsigned int destination, int vector,
-			       struct io_apic_irq_attr *attr)
+int native_setup_ioapic_entry(int irq, struct IO_APIC_route_entry *entry,
+			      unsigned int destination, int vector,
+			      struct io_apic_irq_attr *attr)
 {
-	if (irq_remapping_enabled)
-		return setup_ioapic_remapped_entry(irq, entry, destination,
-						   vector, attr);
-
 	memset(entry, 0, sizeof(*entry));
 
 	entry->delivery_mode = apic->irq_delivery_mode;
@@ -1356,16 +1348,6 @@ static void setup_ioapic_irq(unsigned int irq, struct irq_cfg *cfg,
 	if (!IO_APIC_IRQ(irq))
 		return;
 
-	/*
-	 * For legacy irqs, cfg->domain starts with cpu 0. Now that IO-APIC
-	 * can handle this irq and the apic driver is finialized at this point,
-	 * update the cfg->domain.
-	 */
-	if (irq < legacy_pic->nr_legacy_irqs &&
-	    cpumask_equal(cfg->domain, cpumask_of(0)))
-		apic->vector_allocation_domain(0, cfg->domain,
-					       apic->target_cpus());
-
 	if (assign_irq_vector(irq, cfg, apic->target_cpus()))
 		return;
 
@@ -1384,8 +1366,8 @@ static void setup_ioapic_irq(unsigned int irq, struct irq_cfg *cfg,
 		    attr->ioapic, mpc_ioapic_id(attr->ioapic), attr->ioapic_pin,
 		    cfg->vector, irq, attr->trigger, attr->polarity, dest);
 
-	if (setup_ioapic_entry(irq, &entry, dest, cfg->vector, attr)) {
-		pr_warn("Failed to setup ioapic entry for ioapic %d, pin %d\n",
+	if (x86_io_apic_ops.setup_entry(irq, &entry, dest, cfg->vector, attr)) {
+		pr_warn("Failed to setup ioapic entry for ioapic  %d, pin %d\n",
 			mpc_ioapic_id(attr->ioapic), attr->ioapic_pin);
 		__clear_irq_vector(irq, cfg);
 
@@ -1527,9 +1509,63 @@ static void __init setup_timer_IRQ0_pin(unsigned int ioapic_idx,
 	ioapic_write_entry(ioapic_idx, pin, entry);
 }
 
-__apicdebuginit(void) print_IO_APIC(int ioapic_idx)
+void native_io_apic_print_entries(unsigned int apic, unsigned int nr_entries)
+{
+	int i;
+
+	pr_debug(" NR Dst Mask Trig IRR Pol Stat Dmod Deli Vect:\n");
+
+	for (i = 0; i <= nr_entries; i++) {
+		struct IO_APIC_route_entry entry;
+
+		entry = ioapic_read_entry(apic, i);
+
+		pr_debug(" %02x %02X  ", i, entry.dest);
+		pr_cont("%1d    %1d    %1d   %1d   %1d    "
+			"%1d    %1d    %02X\n",
+			entry.mask,
+			entry.trigger,
+			entry.irr,
+			entry.polarity,
+			entry.delivery_status,
+			entry.dest_mode,
+			entry.delivery_mode,
+			entry.vector);
+	}
+}
+
+void intel_ir_io_apic_print_entries(unsigned int apic,
+				    unsigned int nr_entries)
 {
 	int i;
+
+	pr_debug(" NR Indx Fmt Mask Trig IRR Pol Stat Indx2 Zero Vect:\n");
+
+	for (i = 0; i <= nr_entries; i++) {
+		struct IR_IO_APIC_route_entry *ir_entry;
+		struct IO_APIC_route_entry entry;
+
+		entry = ioapic_read_entry(apic, i);
+
+		ir_entry = (struct IR_IO_APIC_route_entry *)&entry;
+
+		pr_debug(" %02x %04X ", i, ir_entry->index);
+		pr_cont("%1d   %1d    %1d    %1d   %1d   "
+			"%1d    %1d     %X    %02X\n",
+			ir_entry->format,
+			ir_entry->mask,
+			ir_entry->trigger,
+			ir_entry->irr,
+			ir_entry->polarity,
+			ir_entry->delivery_status,
+			ir_entry->index2,
+			ir_entry->zero,
+			ir_entry->vector);
+	}
+}
+
+__apicdebuginit(void) print_IO_APIC(int ioapic_idx)
+{
 	union IO_APIC_reg_00 reg_00;
 	union IO_APIC_reg_01 reg_01;
 	union IO_APIC_reg_02 reg_02;
@@ -1582,58 +1618,7 @@ __apicdebuginit(void) print_IO_APIC(int ioapic_idx)
 
 	printk(KERN_DEBUG ".... IRQ redirection table:\n");
 
-	if (irq_remapping_enabled) {
-		printk(KERN_DEBUG " NR Indx Fmt Mask Trig IRR"
-			" Pol Stat Indx2 Zero Vect:\n");
-	} else {
-		printk(KERN_DEBUG " NR Dst Mask Trig IRR Pol"
-			" Stat Dmod Deli Vect:\n");
-	}
-
-	for (i = 0; i <= reg_01.bits.entries; i++) {
-		if (irq_remapping_enabled) {
-			struct IO_APIC_route_entry entry;
-			struct IR_IO_APIC_route_entry *ir_entry;
-
-			entry = ioapic_read_entry(ioapic_idx, i);
-			ir_entry = (struct IR_IO_APIC_route_entry *) &entry;
-			printk(KERN_DEBUG " %02x %04X ",
-				i,
-				ir_entry->index
-			);
-			pr_cont("%1d   %1d    %1d    %1d   %1d   "
-				"%1d    %1d     %X    %02X\n",
-				ir_entry->format,
-				ir_entry->mask,
-				ir_entry->trigger,
-				ir_entry->irr,
-				ir_entry->polarity,
-				ir_entry->delivery_status,
-				ir_entry->index2,
-				ir_entry->zero,
-				ir_entry->vector
-			);
-		} else {
-			struct IO_APIC_route_entry entry;
-
-			entry = ioapic_read_entry(ioapic_idx, i);
-			printk(KERN_DEBUG " %02x %02X  ",
-				i,
-				entry.dest
-			);
-			pr_cont("%1d    %1d    %1d   %1d   %1d    "
-				"%1d    %1d    %02X\n",
-				entry.mask,
-				entry.trigger,
-				entry.irr,
-				entry.polarity,
-				entry.delivery_status,
-				entry.dest_mode,
-				entry.delivery_mode,
-				entry.vector
-			);
-		}
-	}
+	x86_io_apic_ops.print_entries(ioapic_idx, reg_01.bits.entries);
 }
 
 __apicdebuginit(void) print_IO_APICs(void)
@@ -1935,30 +1920,14 @@ void __init enable_IO_APIC(void)
 	clear_IO_APIC();
 }
 
-/*
- * Not an __init, needed by the reboot code
- */
-void disable_IO_APIC(void)
+void native_disable_io_apic(void)
 {
-	/*
-	 * Clear the IO-APIC before rebooting:
-	 */
-	clear_IO_APIC();
-
-	if (!legacy_pic->nr_legacy_irqs)
-		return;
-
 	/*
 	 * If the i8259 is routed through an IOAPIC
 	 * Put that IOAPIC in virtual wire mode
 	 * so legacy interrupts can be delivered.
-	 *
-	 * With interrupt-remapping, for now we will use virtual wire A mode,
-	 * as virtual wire B is little complex (need to configure both
-	 * IOAPIC RTE as well as interrupt-remapping table entry).
-	 * As this gets called during crash dump, keep this simple for now.
 	 */
-	if (ioapic_i8259.pin != -1 && !irq_remapping_enabled) {
+	if (ioapic_i8259.pin != -1) {
 		struct IO_APIC_route_entry entry;
 
 		memset(&entry, 0, sizeof(entry));
@@ -1978,12 +1947,25 @@ void disable_IO_APIC(void)
 		ioapic_write_entry(ioapic_i8259.apic, ioapic_i8259.pin, entry);
 	}
 
+	if (cpu_has_apic || apic_from_smp_config())
+		disconnect_bsp_APIC(ioapic_i8259.pin != -1);
+
+}
+
+/*
+ * Not an __init, needed by the reboot code
+ */
+void disable_IO_APIC(void)
+{
 	/*
-	 * Use virtual wire A mode when interrupt remapping is enabled.
+	 * Clear the IO-APIC before rebooting:
 	 */
-	if (cpu_has_apic || apic_from_smp_config())
-		disconnect_bsp_APIC(!irq_remapping_enabled &&
-				ioapic_i8259.pin != -1);
+	clear_IO_APIC();
+
+	if (!legacy_pic->nr_legacy_irqs)
+		return;
+
+	x86_io_apic_ops.disable();
 }
 
 #ifdef CONFIG_X86_32
@@ -2199,9 +2181,11 @@ static int ioapic_retrigger_irq(struct irq_data *data)
 {
 	struct irq_cfg *cfg = data->chip_data;
 	unsigned long flags;
+	int cpu;
 
 	raw_spin_lock_irqsave(&vector_lock, flags);
-	apic->send_IPI_mask(cpumask_of(cpumask_first(cfg->domain)), cfg->vector);
+	cpu = cpumask_first_and(cfg->domain, cpu_online_mask);
+	apic->send_IPI_mask(cpumask_of(cpu), cfg->vector);
 	raw_spin_unlock_irqrestore(&vector_lock, flags);
 
 	return 1;
@@ -2381,9 +2365,10 @@ int __ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
 	return 0;
 }
 
-static int
-ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
-		    bool force)
+
+int native_ioapic_set_affinity(struct irq_data *data,
+			       const struct cpumask *mask,
+			       bool force)
 {
 	unsigned int dest, irq = data->irq;
 	unsigned long flags;
@@ -2582,8 +2567,7 @@ static void irq_remap_modify_chip_defaults(struct irq_chip *chip)
 	chip->irq_print_chip = ir_print_prefix;
 	chip->irq_ack = ir_ack_apic_edge;
 	chip->irq_eoi = ir_ack_apic_level;
-
-	chip->irq_set_affinity = set_remapped_irq_affinity;
+	chip->irq_set_affinity = x86_io_apic_ops.set_affinity;
 }
 #endif /* CONFIG_IRQ_REMAP */
 
@@ -2594,7 +2578,7 @@ static struct irq_chip ioapic_chip __read_mostly = {
 	.irq_unmask		= unmask_ioapic_irq,
 	.irq_ack		= ack_apic_edge,
 	.irq_eoi		= ack_apic_level,
-	.irq_set_affinity	= ioapic_set_affinity,
+	.irq_set_affinity	= native_ioapic_set_affinity,
 	.irq_retrigger		= ioapic_retrigger_irq,
 };
 
@@ -2994,37 +2978,58 @@ device_initcall(ioapic_init_ops);
 /*
  * Dynamic irq allocate and deallocation
  */
-unsigned int create_irq_nr(unsigned int from, int node)
+unsigned int __create_irqs(unsigned int from, unsigned int count, int node)
 {
-	struct irq_cfg *cfg;
+	struct irq_cfg **cfg;
 	unsigned long flags;
-	unsigned int ret = 0;
-	int irq;
+	int irq, i;
 
 	if (from < nr_irqs_gsi)
 		from = nr_irqs_gsi;
 
-	irq = alloc_irq_from(from, node);
-	if (irq < 0)
-		return 0;
-	cfg = alloc_irq_cfg(irq, node);
-	if (!cfg) {
-		free_irq_at(irq, NULL);
+	cfg = kzalloc_node(count * sizeof(cfg[0]), GFP_KERNEL, node);
+	if (!cfg)
 		return 0;
+
+	irq = alloc_irqs_from(from, count, node);
+	if (irq < 0)
+		goto out_cfgs;
+
+	for (i = 0; i < count; i++) {
+		cfg[i] = alloc_irq_cfg(irq + i, node);
+		if (!cfg[i])
+			goto out_irqs;
 	}
 
 	raw_spin_lock_irqsave(&vector_lock, flags);
-	if (!__assign_irq_vector(irq, cfg, apic->target_cpus()))
-		ret = irq;
+	for (i = 0; i < count; i++)
+		if (__assign_irq_vector(irq + i, cfg[i], apic->target_cpus()))
+			goto out_vecs;
 	raw_spin_unlock_irqrestore(&vector_lock, flags);
 
-	if (ret) {
-		irq_set_chip_data(irq, cfg);
-		irq_clear_status_flags(irq, IRQ_NOREQUEST);
-	} else {
-		free_irq_at(irq, cfg);
+	for (i = 0; i < count; i++) {
+		irq_set_chip_data(irq + i, cfg[i]);
+		irq_clear_status_flags(irq + i, IRQ_NOREQUEST);
 	}
-	return ret;
+
+	kfree(cfg);
+	return irq;
+
+out_vecs:
+	for (i--; i >= 0; i--)
+		__clear_irq_vector(irq + i, cfg[i]);
+	raw_spin_unlock_irqrestore(&vector_lock, flags);
+out_irqs:
+	for (i = 0; i < count; i++)
+		free_irq_at(irq + i, cfg[i]);
+out_cfgs:
+	kfree(cfg);
+	return 0;
+}
+
+unsigned int create_irq_nr(unsigned int from, int node)
+{
+	return __create_irqs(from, 1, node);
 }
 
 int create_irq(void)
@@ -3057,6 +3062,14 @@ void destroy_irq(unsigned int irq)
 	free_irq_at(irq, cfg);
 }
 
+void destroy_irqs(unsigned int irq, unsigned int count)
+{
+	unsigned int i;
+
+	for (i = 0; i < count; i++)
+		destroy_irq(irq + i);
+}
+
 /*
  * MSI message composition
  */
@@ -3083,7 +3096,7 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq,
 
 	if (irq_remapped(cfg)) {
 		compose_remapped_msi_msg(pdev, irq, dest, msg, hpet_id);
-		return err;
+		return 0;
 	}
 
 	if (x2apic_enabled())
@@ -3110,7 +3123,7 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq,
 			MSI_DATA_DELIVERY_LOWPRI) |
 		MSI_DATA_VECTOR(cfg->vector);
 
-	return err;
+	return 0;
 }
 
 static int
@@ -3148,18 +3161,26 @@ static struct irq_chip msi_chip = {
 	.irq_retrigger		= ioapic_retrigger_irq,
 };
 
-static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq)
+int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc,
+		  unsigned int irq_base, unsigned int irq_offset)
 {
 	struct irq_chip *chip = &msi_chip;
 	struct msi_msg msg;
+	unsigned int irq = irq_base + irq_offset;
 	int ret;
 
 	ret = msi_compose_msg(dev, irq, &msg, -1);
 	if (ret < 0)
 		return ret;
 
-	irq_set_msi_desc(irq, msidesc);
-	write_msi_msg(irq, &msg);
+	irq_set_msi_desc_off(irq_base, irq_offset, msidesc);
+
+	/*
+	 * MSI-X message is written per-IRQ, the offset is always 0.
+	 * MSI message denotes a contiguous group of IRQs, written for 0th IRQ.
+	 */
+	if (!irq_offset)
+		write_msi_msg(irq, &msg);
 
 	if (irq_remapped(irq_get_chip_data(irq))) {
 		irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
@@ -3175,46 +3196,26 @@ static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq)
 
 int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 {
-	int node, ret, sub_handle, index = 0;
 	unsigned int irq, irq_want;
 	struct msi_desc *msidesc;
+	int node, ret;
 
-	/* x86 doesn't support multiple MSI yet */
+	/* Multiple MSI vectors only supported with interrupt remapping */
 	if (type == PCI_CAP_ID_MSI && nvec > 1)
 		return 1;
 
 	node = dev_to_node(&dev->dev);
 	irq_want = nr_irqs_gsi;
-	sub_handle = 0;
 	list_for_each_entry(msidesc, &dev->msi_list, list) {
 		irq = create_irq_nr(irq_want, node);
 		if (irq == 0)
-			return -1;
+			return -ENOSPC;
+
 		irq_want = irq + 1;
-		if (!irq_remapping_enabled)
-			goto no_ir;
 
-		if (!sub_handle) {
-			/*
-			 * allocate the consecutive block of IRTE's
-			 * for 'nvec'
-			 */
-			index = msi_alloc_remapped_irq(dev, irq, nvec);
-			if (index < 0) {
-				ret = index;
-				goto error;
-			}
-		} else {
-			ret = msi_setup_remapped_irq(dev, irq, index,
-						     sub_handle);
-			if (ret < 0)
-				goto error;
-		}
-no_ir:
-		ret = setup_msi_irq(dev, msidesc, irq);
+		ret = setup_msi_irq(dev, msidesc, irq, 0);
 		if (ret < 0)
 			goto error;
-		sub_handle++;
 	}
 	return 0;
 
@@ -3310,17 +3311,12 @@ static struct irq_chip hpet_msi_type = {
 	.irq_retrigger = ioapic_retrigger_irq,
 };
 
-int arch_setup_hpet_msi(unsigned int irq, unsigned int id)
+int default_setup_hpet_msi(unsigned int irq, unsigned int id)
 {
 	struct irq_chip *chip = &hpet_msi_type;
 	struct msi_msg msg;
 	int ret;
 
-	if (irq_remapping_enabled) {
-		if (!setup_hpet_msi_remapped(irq, id))
-			return -1;
-	}
-
 	ret = msi_compose_msg(NULL, irq, &msg, id);
 	if (ret < 0)
 		return ret;
@@ -3694,10 +3690,7 @@ void __init setup_ioapic_dest(void)
 		else
 			mask = apic->target_cpus();
 
-		if (irq_remapping_enabled)
-			set_remapped_irq_affinity(idata, mask, false);
-		else
-			ioapic_set_affinity(idata, mask, false);
+		x86_io_apic_ops.set_affinity(idata, mask, false);
 	}
 
 }