Enable support of IOAPIC hotplug on x86 platforms

index cfd1b132b8e3..0e716fa56ae5 100644
@@ -218,114 +218,74 @@ static void teardown_mcfg_map(struct pci_root_info *info)
 }
 #endif
 
-static acpi_status resource_to_addr(struct acpi_resource *resource,
-				    struct acpi_resource_address64 *addr)
-{
-	acpi_status status;
-	struct acpi_resource_memory24 *memory24;
-	struct acpi_resource_memory32 *memory32;
-	struct acpi_resource_fixed_memory32 *fixed_memory32;
-
-	memset(addr, 0, sizeof(*addr));
-	switch (resource->type) {
-	case ACPI_RESOURCE_TYPE_MEMORY24:
-		memory24 = &resource->data.memory24;
-		addr->resource_type = ACPI_MEMORY_RANGE;
-		addr->minimum = memory24->minimum;
-		addr->address_length = memory24->address_length;
-		addr->maximum = addr->minimum + addr->address_length - 1;
-		return AE_OK;
-	case ACPI_RESOURCE_TYPE_MEMORY32:
-		memory32 = &resource->data.memory32;
-		addr->resource_type = ACPI_MEMORY_RANGE;
-		addr->minimum = memory32->minimum;
-		addr->address_length = memory32->address_length;
-		addr->maximum = addr->minimum + addr->address_length - 1;
-		return AE_OK;
-	case ACPI_RESOURCE_TYPE_FIXED_MEMORY32:
-		fixed_memory32 = &resource->data.fixed_memory32;
-		addr->resource_type = ACPI_MEMORY_RANGE;
-		addr->minimum = fixed_memory32->address;
-		addr->address_length = fixed_memory32->address_length;
-		addr->maximum = addr->minimum + addr->address_length - 1;
-		return AE_OK;
-	case ACPI_RESOURCE_TYPE_ADDRESS16:
-	case ACPI_RESOURCE_TYPE_ADDRESS32:
-	case ACPI_RESOURCE_TYPE_ADDRESS64:
-		status = acpi_resource_to_address64(resource, addr);
-		if (ACPI_SUCCESS(status) &&
-		    (addr->resource_type == ACPI_MEMORY_RANGE ||
-		    addr->resource_type == ACPI_IO_RANGE) &&
-		    addr->address_length > 0) {
-			return AE_OK;
-		}
-		break;
-	}
-	return AE_ERROR;
-}
-
 static acpi_status count_resource(struct acpi_resource *acpi_res, void *data)
 {
 	struct pci_root_info *info = data;
-	struct acpi_resource_address64 addr;
-	acpi_status status;
+	struct resource r = {
+		.flags = 0
+	};
 
-	status = resource_to_addr(acpi_res, &addr);
-	if (ACPI_SUCCESS(status))
+	if (!acpi_dev_resource_memory(acpi_res, &r) &&
+	    !acpi_dev_resource_address_space(acpi_res, &r))
+		return AE_OK;
+
+	if ((r.flags & (IORESOURCE_IO | IORESOURCE_MEM)) && resource_size(&r))
 		info->res_num++;
+
 	return AE_OK;
 }
 
 static acpi_status setup_resource(struct acpi_resource *acpi_res, void *data)
 {
 	struct pci_root_info *info = data;
-	struct resource *res;
-	struct acpi_resource_address64 addr;
-	acpi_status status;
-	unsigned long flags;
-	u64 start, orig_end, end;
+	struct resource *res = &info->res[info->res_num];
+	u64 translation_offset = 0;
+
+	memset(res, 0, sizeof(*res));
+	if (acpi_dev_resource_memory(acpi_res, res)) {
+		res->flags &= IORESOURCE_MEM | IORESOURCE_IO;
+	} else if (acpi_dev_resource_address_space(acpi_res, res)) {
+		u64 orig_end;
+		struct acpi_resource_address64 addr;
+
+		res->flags &= IORESOURCE_MEM | IORESOURCE_IO;
+		if (res->flags == 0)
+			return AE_OK;
 
-	status = resource_to_addr(acpi_res, &addr);
-	if (!ACPI_SUCCESS(status))
-		return AE_OK;
+		if (ACPI_FAILURE(acpi_resource_to_address64(acpi_res, &addr)))
+			return AE_OK;
 
-	if (addr.resource_type == ACPI_MEMORY_RANGE) {
-		flags = IORESOURCE_MEM;
-		if (addr.info.mem.caching == ACPI_PREFETCHABLE_MEMORY)
-			flags |= IORESOURCE_PREFETCH;
-	} else if (addr.resource_type == ACPI_IO_RANGE) {
-		flags = IORESOURCE_IO;
-	} else
-		return AE_OK;
+		if (addr.resource_type == ACPI_MEMORY_RANGE &&
+		    addr.info.mem.caching == ACPI_PREFETCHABLE_MEMORY)
+			res->flags |= IORESOURCE_PREFETCH;
 
-	start = addr.minimum + addr.translation_offset;
-	orig_end = end = addr.maximum + addr.translation_offset;
+		translation_offset = addr.translation_offset;
+		orig_end = res->end;
+		res->start += translation_offset;
+		res->end += translation_offset;
 
-	/* Exclude non-addressable range or non-addressable portion of range */
-	end = min(end, (u64)iomem_resource.end);
-	if (end <= start) {
-		dev_info(&info->bridge->dev,
-			"host bridge window [%#llx-%#llx] "
-			"(ignored, not CPU addressable)\n", start, orig_end);
-		return AE_OK;
-	} else if (orig_end != end) {
-		dev_info(&info->bridge->dev,
-			"host bridge window [%#llx-%#llx] "
-			"([%#llx-%#llx] ignored, not CPU addressable)\n", 
-			start, orig_end, end + 1, orig_end);
+		/* Exclude non-addressable range or non-addressable portion of range */
+		res->end = min(res->end, (u64)iomem_resource.end);
+		if (res->end <= res->start) {
+			dev_info(&info->bridge->dev,
+				"host bridge window [%#llx-%#llx] (ignored, not CPU addressable)\n",
+				 res->start, orig_end);
+			return AE_OK;
+		} else if (orig_end != res->end) {
+			dev_info(&info->bridge->dev,
+				"host bridge window [%#llx-%#llx] ([%#llx-%#llx] ignored, not CPU addressable)\n",
+				res->start, orig_end, res->end + 1, orig_end);
+		}
 	}
 
-	res = &info->res[info->res_num];
-	res->name = info->name;
-	res->flags = flags;
-	res->start = start;
-	res->end = end;
-	info->res_offset[info->res_num] = addr.translation_offset;
-	info->res_num++;
-
-	if (!pci_use_crs)
-		dev_printk(KERN_DEBUG, &info->bridge->dev,
-			   "host bridge window %pR (ignored)\n", res);
+	if (res->flags && resource_size(res)) {
+		res->name = info->name;
+		info->res_offset[info->res_num] = translation_offset;
+		info->res_num++;
+		if (!pci_use_crs)
+			dev_printk(KERN_DEBUG, &info->bridge->dev,
+				   "host bridge window %pR (ignored)\n", res);
+	}
 
 	return AE_OK;
 }

index 2ba8f02ced36..782a0d15c25f 100644
@@ -200,7 +200,7 @@ bool acpi_dev_resource_address_space(struct acpi_resource *ares,
 
 	status = acpi_resource_to_address64(ares, &addr);
 	if (ACPI_FAILURE(status))
-		return true;
+		return false;
 
 	res->start = addr.minimum;
 	res->end = addr.maximum;

index e32321ce9a5c..b048f3752c2b 100644
@@ -125,13 +125,12 @@ static int map_mat_entry(acpi_handle handle, int type, u32 acpi_id)
 	}
 
 	header = (struct acpi_subtable_header *)obj->buffer.pointer;
-	if (header->type == ACPI_MADT_TYPE_LOCAL_APIC) {
+	if (header->type == ACPI_MADT_TYPE_LOCAL_APIC)
 		map_lapic_id(header, acpi_id, &apic_id);
-	} else if (header->type == ACPI_MADT_TYPE_LOCAL_SAPIC) {
+	else if (header->type == ACPI_MADT_TYPE_LOCAL_SAPIC)
 		map_lsapic_id(header, type, acpi_id, &apic_id);
-	} else if (header->type == ACPI_MADT_TYPE_LOCAL_X2APIC) {
+	else if (header->type == ACPI_MADT_TYPE_LOCAL_X2APIC)
 		map_x2apic_id(header, type, acpi_id, &apic_id);
-	}
 
 exit:
 	kfree(buffer.pointer);

@@ -164,7 +163,7 @@ int acpi_map_cpuid(int apic_id, u32 acpi_id)
 		 * For example,
 		 *
 		 * Scope (_PR)
-                 * {
+		 * {
 		 *     Processor (CPU0, 0x00, 0x00000410, 0x06) {}
 		 *     Processor (CPU1, 0x01, 0x00000410, 0x06) {}
 		 *     Processor (CPU2, 0x02, 0x00000410, 0x06) {}

index b048f3752c2b..4a3150f2187c 100644
@@ -4,6 +4,10 @@
  *
  *	Alex Chiang <[email protected]>
  *	- Unified x86/ia64 implementations
+ *
+ * I/O APIC hotplug support
+ *	Yinghai Lu <[email protected]>
+ *	Jiang Liu <[email protected]>
  */
 #include <linux/export.h>
 #include <linux/acpi.h>

@@ -12,6 +16,21 @@
 #define _COMPONENT		ACPI_PROCESSOR_COMPONENT
 ACPI_MODULE_NAME("processor_core");
 
+static struct acpi_table_madt *get_madt_table(void)
+{
+	static struct acpi_table_madt *madt;
+	static int read_madt;
+
+	if (!read_madt) {
+		if (ACPI_FAILURE(acpi_get_table(ACPI_SIG_MADT, 0,
+					(struct acpi_table_header **)&madt)))
+			madt = NULL;
+		read_madt++;
+	}
+
+	return madt;
+}
+
 static int map_lapic_id(struct acpi_subtable_header *entry,
 		 u32 acpi_id, int *apic_id)
 {

@@ -67,17 +86,10 @@ static int map_lsapic_id(struct acpi_subtable_header *entry,
 static int map_madt_entry(int type, u32 acpi_id)
 {
 	unsigned long madt_end, entry;
-	static struct acpi_table_madt *madt;
-	static int read_madt;
 	int apic_id = -1;
+	struct acpi_table_madt *madt;
 
-	if (!read_madt) {
-		if (ACPI_FAILURE(acpi_get_table(ACPI_SIG_MADT, 0,
-					(struct acpi_table_header **)&madt)))
-			madt = NULL;
-		read_madt++;
-	}
-
+	madt = get_madt_table();
 	if (!madt)
 		return apic_id;
 

@@ -203,3 +215,95 @@ int acpi_get_cpuid(acpi_handle handle, int type, u32 acpi_id)
 	return acpi_map_cpuid(apic_id, acpi_id);
 }
 EXPORT_SYMBOL_GPL(acpi_get_cpuid);
+
+#ifdef CONFIG_ACPI_HOTPLUG_IOAPIC
+static int get_ioapic_id(struct acpi_subtable_header *entry, u32 gsi_base,
+			 u64 *phys_addr, int *ioapic_id)
+{
+	struct acpi_madt_io_apic *ioapic = (struct acpi_madt_io_apic *)entry;
+
+	if (ioapic->global_irq_base != gsi_base)
+		return 0;
+
+	*phys_addr = ioapic->address;
+	*ioapic_id = ioapic->id;
+	return 1;
+}
+
+static int parse_madt_ioapic_entry(u32 gsi_base, u64 *phys_addr)
+{
+	struct acpi_subtable_header *hdr;
+	unsigned long madt_end, entry;
+	int apic_id = -1;
+	struct acpi_table_madt *madt;
+
+	madt = get_madt_table();
+	if (!madt)
+		return apic_id;
+
+	entry = (unsigned long)madt;
+	madt_end = entry + madt->header.length;
+
+	/* Parse all entries looking for a match. */
+	entry += sizeof(struct acpi_table_madt);
+	while (entry + sizeof(struct acpi_subtable_header) < madt_end) {
+		hdr = (struct acpi_subtable_header *)entry;
+		if (hdr->type == ACPI_MADT_TYPE_IO_APIC &&
+		    get_ioapic_id(hdr, gsi_base, phys_addr, &apic_id))
+			break;
+		else
+			entry += hdr->length;
+	}
+
+	return apic_id;
+}
+
+static int parse_mat_ioapic_entry(acpi_handle handle, u32 gsi_base,
+				  u64 *phys_addr)
+{
+	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
+	union acpi_object *obj;
+	struct acpi_subtable_header *header;
+	int apic_id = -1;
+
+	if (ACPI_FAILURE(acpi_evaluate_object(handle, "_MAT", NULL, &buffer)))
+		goto exit;
+
+	if (!buffer.length || !buffer.pointer)
+		goto exit;
+
+	obj = buffer.pointer;
+	if (obj->type != ACPI_TYPE_BUFFER ||
+	    obj->buffer.length < sizeof(struct acpi_subtable_header))
+		goto exit;
+
+	header = (struct acpi_subtable_header *)obj->buffer.pointer;
+	if (header->type == ACPI_MADT_TYPE_IO_APIC)
+		get_ioapic_id(header, gsi_base, phys_addr, &apic_id);
+
+exit:
+	kfree(buffer.pointer);
+	return apic_id;
+}
+
+/**
+ * acpi_get_ioapic_id - Get IOAPIC ID and physical address matching @gsi_base
+ * @handle:	ACPI object for IOAPIC device
+ * @gsi_base:	GSI base to match with
+ * @phys_add:	hold physical address of matching IOAPIC record
+ *
+ * Walk resources returned by ACPI_MAT method, then ACPI MADT table, to search
+ * for an ACPI IOAPIC record matching @gsi_base.
+ * Return IOAPIC id and physical address if found a match, otherwise return <0.
+ */
+int acpi_get_ioapic_id(acpi_handle handle, u32 gsi_base, u64 *phys_addr)
+{
+	int apic_id;
+
+	apic_id = parse_mat_ioapic_entry(handle, gsi_base, phys_addr);
+	if (apic_id == -1)
+		apic_id = parse_madt_ioapic_entry(gsi_base, phys_addr);
+
+	return apic_id;
+}
+#endif /* CONFIG_ACPI_HOTPLUG_IOAPIC */

index 807cbc46d73e..3574f137242e 100644
@@ -146,6 +146,10 @@ int acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu);
 int acpi_unmap_lsapic(int cpu);
 #endif /* CONFIG_ACPI_HOTPLUG_CPU */
 
+#ifdef CONFIG_ACPI_HOTPLUG_IOAPIC
+int acpi_get_ioapic_id(acpi_handle handle, u32 gsi_base, u64 *phys_addr);
+#endif
+
 int acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base);
 int acpi_unregister_ioapic(acpi_handle handle, u32 gsi_base);
 void acpi_irq_stats_init(void);

121 lines not on this page · raw message

index 337ce5a9b15c..003945e71616 100644
@@ -237,6 +237,19 @@ static struct irq_pin_list *alloc_irq_pin_list(int node)
 	return kzalloc_node(sizeof(struct irq_pin_list), GFP_KERNEL, node);
 }
 
+static void alloc_ioapic_saved_registers(int idx)
+{
+	size_t size;
+
+	if (ioapics[idx].saved_registers)
+		return;
+
+	size = sizeof(struct IO_APIC_route_entry) * ioapics[idx].nr_registers;
+	ioapics[idx].saved_registers = kzalloc(size, GFP_KERNEL);
+	if (!ioapics[idx].saved_registers)
+		pr_err("IOAPIC %d: suspend/resume impossible!\n", idx);
+}
+
 int __init arch_early_irq_init(void)
 {
 	struct irq_cfg *cfg;

@@ -245,13 +258,8 @@ int __init arch_early_irq_init(void)
 	if (!nr_legacy_irqs())
 		io_apic_irqs = ~0UL;
 
-	for_each_ioapic(i) {
-		ioapics[i].saved_registers =
-			kzalloc(sizeof(struct IO_APIC_route_entry) *
-				ioapics[i].nr_registers, GFP_KERNEL);
-		if (!ioapics[i].saved_registers)
-			pr_err("IOAPIC %d: suspend/resume impossible!\n", i);
-	}
+	for_each_ioapic(i)
+		alloc_ioapic_saved_registers(i);
 
 	/*
 	 * For legacy IRQ's, start with assigning irq0 to irq15 to

index 003945e71616..9011c5fa5aad 100644
@@ -3575,26 +3575,51 @@ static int __init io_apic_get_unique_id(int ioapic, int apic_id)
 	return apic_id;
 }
 
-static u8 __init io_apic_unique_id(u8 id)
+static u8 __init io_apic_unique_id(int idx, u8 id)
 {
 	if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) &&
 	    !APIC_XAPIC(apic_version[boot_cpu_physical_apicid]))
-		return io_apic_get_unique_id(nr_ioapics, id);
+		return io_apic_get_unique_id(idx, id);
 	else
 		return id;
 }
 #else
-static u8 __init io_apic_unique_id(u8 id)
+static u8 __init io_apic_unique_id(int idx, u8 id)
 {
 	int i;
+	u8 new_id;
+	unsigned long flags;
 	DECLARE_BITMAP(used, 256);
+	union IO_APIC_reg_00 reg_00;
 
 	bitmap_zero(used, 256);
 	for_each_ioapic(i)
 		__set_bit(mpc_ioapic_id(i), used);
 	if (!test_bit(id, used))
 		return id;
-	return find_first_zero_bit(used, 256);
+
+	/* check register at first */
+	raw_spin_lock_irqsave(&ioapic_lock, flags);
+	reg_00.raw = io_apic_read(idx, 0);
+	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
+	new_id = reg_00.bits.ID;
+	if (!test_bit(new_id, used)) {
+		apic_printk(APIC_VERBOSE, KERN_INFO
+			"IOAPIC[%d]: Using reg apic_id %d instead of %d\n",
+			 idx, new_id, id);
+		return new_id;
+	}
+
+	new_id = find_first_zero_bit(used, 256);
+	reg_00.bits.ID = new_id;
+	raw_spin_lock_irqsave(&ioapic_lock, flags);
+	io_apic_write(idx, 0, reg_00.raw);
+	reg_00.raw = io_apic_read(idx, 0);
+	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
+	/* Sanity check */
+	BUG_ON(reg_00.bits.ID != new_id);
+
+	return new_id;
 }
 #endif
 

@@ -3860,7 +3885,7 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base,
 		return;
 	}
 
-	ioapics[idx].mp_config.apicid = io_apic_unique_id(id);
+	ioapics[idx].mp_config.apicid = io_apic_unique_id(idx, id);
 	ioapics[idx].mp_config.apicver = io_apic_get_version(idx);
 
 	/*

index 1733ab49ac5e..a666dcdeea67 100644
@@ -188,8 +188,8 @@ extern int mp_find_ioapic_pin(int ioapic, u32 gsi);
 extern u32 mp_pin_to_gsi(int ioapic, int pin);
 extern int mp_map_gsi_to_irq(u32 gsi, unsigned int flags);
 extern void mp_unmap_irq(int irq);
-extern void __init mp_register_ioapic(int id, u32 address, u32 gsi_base,
-				      struct ioapic_domain_cfg *cfg);
+extern void mp_register_ioapic(int id, u32 address, u32 gsi_base,
+			       struct ioapic_domain_cfg *cfg);
 extern int mp_irqdomain_map(struct irq_domain *domain, unsigned int virq,
 			    irq_hw_number_t hwirq);
 extern void mp_irqdomain_unmap(struct irq_domain *domain, unsigned int virq);

index 9011c5fa5aad..81f014891237 100644
@@ -3454,7 +3454,7 @@ io_apic_setup_irq_pin(unsigned int irq, int node, struct io_apic_irq_attr *attr)
 	return ret;
 }
 
-static int __init io_apic_get_redir_entries(int ioapic)
+static int io_apic_get_redir_entries(int ioapic)
 {
 	union IO_APIC_reg_01	reg_01;
 	unsigned long flags;

@@ -3500,7 +3500,7 @@ int __init arch_probe_nr_irqs(void)
 }
 
 #ifdef CONFIG_X86_32
-static int __init io_apic_get_unique_id(int ioapic, int apic_id)
+static int io_apic_get_unique_id(int ioapic, int apic_id)
 {
 	union IO_APIC_reg_00 reg_00;
 	static physid_mask_t apic_id_map = PHYSID_MASK_NONE;

@@ -3575,7 +3575,7 @@ static int __init io_apic_get_unique_id(int ioapic, int apic_id)
 	return apic_id;
 }
 
-static u8 __init io_apic_unique_id(int idx, u8 id)
+static u8 io_apic_unique_id(int idx, u8 id)
 {
 	if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) &&
 	    !APIC_XAPIC(apic_version[boot_cpu_physical_apicid]))

@@ -3584,7 +3584,7 @@ static u8 __init io_apic_unique_id(int idx, u8 id)
 		return id;
 }
 #else
-static u8 __init io_apic_unique_id(int idx, u8 id)
+static u8 io_apic_unique_id(int idx, u8 id)
 {
 	int i;
 	u8 new_id;

@@ -3623,7 +3623,7 @@ static u8 __init io_apic_unique_id(int idx, u8 id)
 }
 #endif
 
-static int __init io_apic_get_version(int ioapic)
+static int io_apic_get_version(int ioapic)
 {
 	union IO_APIC_reg_01	reg_01;
 	unsigned long flags;

@@ -3827,7 +3827,7 @@ int mp_find_ioapic_pin(int ioapic, u32 gsi)
 	return gsi - gsi_cfg->gsi_base;
 }
 
-static __init int bad_ioapic(unsigned long address)
+static int bad_ioapic(unsigned long address)
 {
 	if (nr_ioapics >= MAX_IO_APICS) {
 		pr_warn("WARNING: Max # of I/O APICs (%d) exceeded (found %d), skipping\n",

@@ -3841,7 +3841,7 @@ static __init int bad_ioapic(unsigned long address)
 	return 0;
 }
 
-static __init int bad_ioapic_register(int idx)
+static int bad_ioapic_register(int idx)
 {
 	union IO_APIC_reg_00 reg_00;
 	union IO_APIC_reg_01 reg_01;

@@ -3860,8 +3860,8 @@ static __init int bad_ioapic_register(int idx)
 	return 0;
 }
 
-void __init mp_register_ioapic(int id, u32 address, u32 gsi_base,
-			       struct ioapic_domain_cfg *cfg)
+void mp_register_ioapic(int id, u32 address, u32 gsi_base,
+			struct ioapic_domain_cfg *cfg)
 {
 	int idx = 0;
 	int entries;

index b9958c364075..44b9271580b5 100644
@@ -210,6 +210,9 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev)
 {
 	int polarity;
 
+	if (dev->irq_managed && dev->irq > 0)
+		return 0;
+
 	if (intel_mid_identify_cpu() == INTEL_MID_CPU_CHIP_TANGIER)
 		polarity = 0; /* active high */
 	else

@@ -224,13 +227,18 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev)
 	if (mp_map_gsi_to_irq(dev->irq, IOAPIC_MAP_ALLOC) < 0)
 		return -EBUSY;
 
+	dev->irq_managed = 1;
+
 	return 0;
 }
 
 static void intel_mid_pci_irq_disable(struct pci_dev *dev)
 {
-	if (!mp_should_keep_irq(&dev->dev) && dev->irq > 0)
+	if (!mp_should_keep_irq(&dev->dev) && dev->irq_managed &&
+	    dev->irq > 0) {
 		mp_unmap_irq(dev->irq);
+		dev->irq_managed = 0;
+	}
 }
 
 struct pci_ops intel_mid_pci_ops = {

index eb500c2592ad..a47e2dea0972 100644
@@ -1202,6 +1202,9 @@ static int pirq_enable_irq(struct pci_dev *dev)
 			int irq;
 			struct io_apic_irq_attr irq_attr;
 
+			if (dev->irq_managed && dev->irq > 0)
+				return 0;
+
 			irq = IO_APIC_get_PCI_irq_vector(dev->bus->number,
 						PCI_SLOT(dev->devfn),
 						pin - 1, &irq_attr);

@@ -1228,6 +1231,7 @@ static int pirq_enable_irq(struct pci_dev *dev)
 			}
 			dev = temp_dev;
 			if (irq >= 0) {
+				dev->irq_managed = 1;
 				dev->irq = irq;
 				dev_info(&dev->dev, "PCI->APIC IRQ transform: "
 					 "INT %c -> IRQ %d\n", 'A' + pin - 1, irq);

@@ -1257,8 +1261,9 @@ static int pirq_enable_irq(struct pci_dev *dev)
 static void pirq_disable_irq(struct pci_dev *dev)
 {
 	if (io_apic_assign_pci_irqs && !mp_should_keep_irq(&dev->dev) &&
-	    dev->irq) {
+	    dev->irq_managed && dev->irq) {
 		mp_unmap_irq(dev->irq);
 		dev->irq = 0;
+		dev->irq_managed = 0;
 	}
 }

index 6e6b80eb0bba..5f1fdca65e5f 100644
@@ -413,6 +413,9 @@ int acpi_pci_irq_enable(struct pci_dev *dev)
 		return 0;
 	}
 
+	if (dev->irq_managed && dev->irq > 0)
+		return 0;
+
 	entry = acpi_pci_irq_lookup(dev, pin);
 	if (!entry) {
 		/*

@@ -456,6 +459,7 @@ int acpi_pci_irq_enable(struct pci_dev *dev)
 		return rc;
 	}
 	dev->irq = rc;
+	dev->irq_managed = 1;
 
 	if (link)
 		snprintf(link_desc, sizeof(link_desc), " -> Link[%s]", link);

@@ -478,7 +482,7 @@ void acpi_pci_irq_disable(struct pci_dev *dev)
 	u8 pin;
 
 	pin = dev->pin;
-	if (!pin)
+	if (!pin || !dev->irq_managed || dev->irq <= 0)
 		return;
 
 	/* Keep IOAPIC pin configuration when suspending */

@@ -506,6 +510,9 @@ void acpi_pci_irq_disable(struct pci_dev *dev)
 	 */
 
 	dev_dbg(&dev->dev, "PCI INT %c disabled\n", pin_name(pin));
-	if (gsi >= 0 && dev->irq > 0)
+	if (gsi >= 0) {
 		acpi_unregister_gsi(gsi);
+		dev->irq = 0;
+		dev->irq_managed = 0;
+	}
 }

index 96453f9bc8ba..17838e07fd16 100644
@@ -348,6 +348,7 @@ struct pci_dev {
 	unsigned int	__aer_firmware_first:1;
 	unsigned int	broken_intx_masking:1;
 	unsigned int	io_window_1k:1;	/* Intel P2P bridge 1K I/O windows */
+	unsigned int	irq_managed:1;
 	pci_dev_flags_t dev_flags;
 	atomic_t	enable_cnt;	/* pci_enable_device has been called */
 

index a666dcdeea67..8741c1ea33c3 100644
@@ -188,8 +188,8 @@ extern int mp_find_ioapic_pin(int ioapic, u32 gsi);
 extern u32 mp_pin_to_gsi(int ioapic, int pin);
 extern int mp_map_gsi_to_irq(u32 gsi, unsigned int flags);
 extern void mp_unmap_irq(int irq);
-extern void mp_register_ioapic(int id, u32 address, u32 gsi_base,
-			       struct ioapic_domain_cfg *cfg);
+extern int mp_register_ioapic(int id, u32 address, u32 gsi_base,
+			      struct ioapic_domain_cfg *cfg);
 extern int mp_irqdomain_map(struct irq_domain *domain, unsigned int virq,
 			    irq_hw_number_t hwirq);
 extern void mp_irqdomain_unmap(struct irq_domain *domain, unsigned int virq);

129 lines not on this page · raw message

index b436fc735aa4..c598fd7604d5 100644
@@ -76,6 +76,19 @@ int acpi_fix_pin2_polarity __initdata;
 static u64 acpi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE;
 #endif
 
+/*
+ * Locks related to IOAPIC hotplug
+ * Hotplug side:
+ * 	->lock_device_hotplug()	//device_hotplug_lock
+ *		->acpi_ioapic_rwsem
+ *			->ioapic_lock
+ * Interrupt mapping side:
+ *	->acpi_ioapic_rwsem
+ *		->ioapic_mutex
+ *			->ioapic_lock
+ */
+static DECLARE_RWSEM(acpi_ioapic_rwsem);
+
 /* --------------------------------------------------------------------------
                               Boot-time Configuration
    -------------------------------------------------------------------------- */

@@ -604,8 +617,11 @@ void __init acpi_pic_sci_set_trigger(unsigned int irq, u16 trigger)
 
 int acpi_gsi_to_irq(u32 gsi, unsigned int *irqp)
 {
-	int irq = mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC | IOAPIC_MAP_CHECK);
+	int irq;
 
+	down_read(&acpi_ioapic_rwsem);
+	irq = mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC | IOAPIC_MAP_CHECK);
+	up_read(&acpi_ioapic_rwsem);
 	if (irq >= 0) {
 		*irqp = irq;
 		return 0;

@@ -646,7 +662,9 @@ static int acpi_register_gsi_ioapic(struct device *dev, u32 gsi,
 	int irq = gsi;
 
 #ifdef CONFIG_X86_IO_APIC
+	down_read(&acpi_ioapic_rwsem);
 	irq = mp_register_gsi(dev, gsi, trigger, polarity);
+	up_read(&acpi_ioapic_rwsem);
 #endif
 
 	return irq;

@@ -655,7 +673,9 @@ static int acpi_register_gsi_ioapic(struct device *dev, u32 gsi,
 static void acpi_unregister_gsi_ioapic(u32 gsi)
 {
 #ifdef CONFIG_X86_IO_APIC
+	down_read(&acpi_ioapic_rwsem);
 	mp_unregister_gsi(gsi);
+	up_read(&acpi_ioapic_rwsem);
 #endif
 }
 

@@ -1181,7 +1201,9 @@ static void __init acpi_process_madt(void)
 			/*
 			 * Parse MADT IO-APIC entries
 			 */
+			down_write(&acpi_ioapic_rwsem);
 			error = acpi_parse_madt_ioapic_entries();
+			up_write(&acpi_ioapic_rwsem);
 			if (!error) {
 				acpi_set_irq_model_ioapic();
 

index c598fd7604d5..238962e7de70 100644
@@ -775,8 +775,35 @@ EXPORT_SYMBOL(acpi_unmap_lsapic);
 
 int acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base)
 {
-	/* TBD */
-	return -EINVAL;
+	int ret = -ENOSYS;
+#ifdef CONFIG_ACPI_HOTPLUG_IOAPIC
+	int ioapic_id;
+	u64 addr;
+	struct ioapic_domain_cfg cfg = {
+		.type = IOAPIC_DOMAIN_DYNAMIC,
+		.ops = &acpi_irqdomain_ops,
+	};
+
+	ioapic_id = acpi_get_ioapic_id(handle, gsi_base, &addr);
+	if (ioapic_id < 0) {
+		unsigned long long uid;
+		acpi_status status;
+
+		status = acpi_evaluate_integer(handle, METHOD_NAME__UID,
+					       NULL, &uid);
+		if (ACPI_FAILURE(status)) {
+			acpi_handle_warn(handle, "failed to get IOAPIC ID.\n");
+			return -EINVAL;
+		}
+		ioapic_id = (int)uid;
+	}
+
+	down_write(&acpi_ioapic_rwsem);
+	ret  = mp_register_ioapic(ioapic_id, phys_addr, gsi_base, &cfg);
+	up_write(&acpi_ioapic_rwsem);
+#endif
+
+	return ret;
 }
 
 EXPORT_SYMBOL(acpi_register_ioapic);

index 9945eb974509..be499af10d1c 100644
@@ -3848,7 +3848,13 @@ static int bad_ioapic_register(int idx)
 
 static int find_free_ioapic_entry(void)
 {
-	return nr_ioapics;
+	int idx;
+
+	for (idx = 0; idx < MAX_IO_APICS; idx++)
+		if (ioapics[idx].nr_registers == 0)
+			return idx;
+
+	return MAX_IO_APICS;
 }
 
 /**

@@ -3864,6 +3870,7 @@ int mp_register_ioapic(int id, u32 address, u32 gsi_base,
 	u32 gsi_end;
 	int idx, ioapic, entries;
 	struct mp_ioapic_gsi *gsi_cfg;
+	bool hotplug = !!ioapic_initialized;
 
 	if (!address) {
 		pr_warn("Bogus (zero) I/O APIC address found, skipping!\n");

@@ -3922,6 +3929,19 @@ int mp_register_ioapic(int id, u32 address, u32 gsi_base,
 	ioapics[idx].irqdomain = NULL;
 	ioapics[idx].irqdomain_cfg = *cfg;
 
+	/*
+	 * If mp_register_ioapic() is called during early boot stage when
+	 * walking ACPI/SFI/DT tables, it's too early to create irqdomain,
+	 * we are still using bootmem allocator. So delay it to setup_IO_APIC().
+	 */
+	if (hotplug) {
+		if (mp_irqdomain_create(idx)) {
+			clear_fixmap(FIX_IO_APIC_BASE_0 + idx);
+			return -ENOMEM;
+		}
+		alloc_ioapic_saved_registers(idx);
+	}
+
 	if (gsi_cfg->gsi_end >= gsi_top)
 		gsi_top = gsi_cfg->gsi_end + 1;
 	if (nr_ioapics <= idx)

index 8741c1ea33c3..7c04b8ec22a4 100644
@@ -190,6 +190,7 @@ extern int mp_map_gsi_to_irq(u32 gsi, unsigned int flags);
 extern void mp_unmap_irq(int irq);
 extern int mp_register_ioapic(int id, u32 address, u32 gsi_base,
 			      struct ioapic_domain_cfg *cfg);
+extern int mp_unregister_ioapic(u32 gsi_base);
 extern int mp_irqdomain_map(struct irq_domain *domain, unsigned int virq,
 			    irq_hw_number_t hwirq);
 extern void mp_irqdomain_unmap(struct irq_domain *domain, unsigned int virq);

index 238962e7de70..0e67d792741d 100644
@@ -805,15 +805,20 @@ int acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base)
 
 	return ret;
 }
-
 EXPORT_SYMBOL(acpi_register_ioapic);
 
 int acpi_unregister_ioapic(acpi_handle handle, u32 gsi_base)
 {
-	/* TBD */
-	return -EINVAL;
-}
+	int ret = -ENOSYS;
+
+#ifdef CONFIG_ACPI_HOTPLUG_IOAPIC
+	down_write(&acpi_ioapic_rwsem);
+	ret  = mp_unregister_ioapic(gsi_base);
+	up_write(&acpi_ioapic_rwsem);
+#endif
 
+	return ret;
+}
 EXPORT_SYMBOL(acpi_unregister_ioapic);
 
 static int __init acpi_parse_sbf(struct acpi_table_header *table)

85 lines not on this page · raw message

index 7c04b8ec22a4..ca742d5249db 100644
@@ -191,6 +191,7 @@ extern void mp_unmap_irq(int irq);
 extern int mp_register_ioapic(int id, u32 address, u32 gsi_base,
 			      struct ioapic_domain_cfg *cfg);
 extern int mp_unregister_ioapic(u32 gsi_base);
+extern int mp_ioapic_registered(u32 gsi_base);
 extern int mp_irqdomain_map(struct irq_domain *domain, unsigned int virq,
 			    irq_hw_number_t hwirq);
 extern void mp_irqdomain_unmap(struct irq_domain *domain, unsigned int virq);

index 0e67d792741d..5a69df5dba56 100644
@@ -821,6 +821,28 @@ int acpi_unregister_ioapic(acpi_handle handle, u32 gsi_base)
 }
 EXPORT_SYMBOL(acpi_unregister_ioapic);
 
+/**
+ * acpi_ioapic_registered - Check whether IOAPIC assoicatied with @gsi_base
+ *			    has been registered
+ * @handle:	ACPI handle of the IOAPIC deivce
+ * @gsi_base:	GSI base associated with the IOAPIC
+ *
+ * Assume caller holds some type of lock to serialize acpi_ioapic_registered()
+ * with acpi_register_ioapic()/acpi_unregister_ioapic().
+ */
+int acpi_ioapic_registered(acpi_handle handle, u32 gsi_base)
+{
+	int ret = 0;
+
+#ifdef CONFIG_ACPI_HOTPLUG_IOAPIC
+	down_read(&acpi_ioapic_rwsem);
+	ret  = mp_ioapic_registered(gsi_base);
+	up_read(&acpi_ioapic_rwsem);
+#endif
+
+	return ret;
+}
+
 static int __init acpi_parse_sbf(struct acpi_table_header *table)
 {
 	struct acpi_table_boot *sb;

index 7fec2a8f72f3..eba25bccefd2 100644
@@ -4013,6 +4013,17 @@ int mp_unregister_ioapic(u32 gsi_base)
 	return 0;
 }
 
+int mp_ioapic_registered(u32 gsi_base)
+{
+	int ioapic;
+
+	for_each_ioapic(ioapic)
+		if (ioapics[ioapic].gsi_config.gsi_base == gsi_base)
+			return 1;
+
+	return 0;
+}
+
 int mp_irqdomain_map(struct irq_domain *domain, unsigned int virq,
 		     irq_hw_number_t hwirq)
 {

index 3574f137242e..e916cc9ca5a8 100644
@@ -152,6 +152,7 @@ int acpi_get_ioapic_id(acpi_handle handle, u32 gsi_base, u64 *phys_addr);
 
 int acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base);
 int acpi_unregister_ioapic(acpi_handle handle, u32 gsi_base);
+int acpi_ioapic_registered(acpi_handle handle, u32 gsi_base);
 void acpi_irq_stats_init(void);
 extern u32 acpi_irq_handled;
 extern u32 acpi_irq_not_handled;

index 4c5cf77e7576..817ab2d5975c 100644
@@ -34,6 +34,13 @@ void acpi_pnp_init(void);
 int acpi_sysfs_init(void);
 void acpi_container_init(void);
 void acpi_memory_hotplug_init(void);
+#ifdef	CONFIG_ACPI_HOTPLUG_IOAPIC
+int acpi_ioapic_add(struct acpi_pci_root *root);
+int acpi_ioapic_remove(struct acpi_pci_root *root);
+#else
+static inline int acpi_ioapic_add(struct acpi_pci_root *root) { return 0; }
+static inline int acpi_ioapic_remove(struct acpi_pci_root *root) { return 0; }
+#endif
 #ifdef CONFIG_ACPI_DOCK
 void register_dock_dependent_device(struct acpi_device *adev,
 				    acpi_handle dshandle);

235 lines not on this page · raw message

index e6ae603ed1a1..d83980b18f49 100644
@@ -600,6 +600,7 @@ static int acpi_pci_root_add(struct acpi_device *device,
 	if (system_state != SYSTEM_BOOTING) {
 		pcibios_resource_survey_bus(root->bus);
 		pci_assign_unassigned_root_bus_resources(root->bus);
+		acpi_ioapic_add(root);
 	}
 
 	pci_lock_rescan_remove();

@@ -620,6 +621,8 @@ static void acpi_pci_root_remove(struct acpi_device *device)
 
 	pci_stop_root_bus(root->bus);
 
+	WARN_ON(acpi_ioapic_remove(root));
+
 	device_set_run_wake(root->bus->bridge, false);
 	pci_acpi_remove_bus_pm_notifier(device);