PCI: use _CRS for PCI resource allocation

Use _CRS for PCI resource allocation

This patch resolves an issue where incorrect PCI memory and i/o ranges
are being assigned to hotplugged PCI devices on some IBM systems.  The
resource mis-allocation not only makes the PCI device unuseable but
often makes the entire system unuseable due to resulting machine checks.

The hotplug capable PCI slots on the affected systems are not located
under a standard P2P bridge but are instead located under PCI root
bridges or subtractive decode P2P bridges.  For example, the IBM x3850
contains 2 hotplug capable PCI-X slots and 4 hotplug capable PCIe slots
with the PCI-X slots each located under a PCI root bridge and the PCIe
slots each located under a subtractive decode P2P bridge.

The current i386/x86_64 PCI resource allocation code does not use _CRS
returned resource information.  No other resource information source is
available for slots that are not below a standard P2P bridge so
incorrect ranges are being allocated from e820 hole causing the bad
result.

This patch causes the kernel to use _CRS returned resource info.  It is
roughly based on a change provided by Matthew Wilcox for the ia64 kernel
in 2005.  Due to possible buggy BIOS factor and possible yet to be
discovered kernel issues the function is disabled by default and can be
enabled with pci=use_crs.

Signed-off-by: Gary Hade <gary.hade@us.ibm.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

Documentation/kernel-parameters.txt

@@ -1318,6 +1318,8 @@ and is between 256 and 4096 characters. It is defined in the file
 				IRQ routing is enabled.
 		noacpi		[X86-32] Do not use ACPI for IRQ routing
 				or for PCI scanning.
+		use_crs		[X86-32] Use _CRS for PCI resource
+				allocation.
 		routeirq	Do IRQ routing for all PCI devices.
 				This is normally done in pci_enable_device(),
 				so this option is a temporary workaround

arch/x86/pci/acpi.c

@@ -45,6 +45,142 @@ static struct dmi_system_id acpi_pciprobe_dmi_table[] = {
 	{}
 };
 
+struct pci_root_info {
+	char *name;
+	unsigned int res_num;
+	struct resource *res;
+	struct pci_bus *bus;
+	int busnum;
+};
+
+static acpi_status
+resource_to_addr(struct acpi_resource *resource,
+			struct acpi_resource_address64 *addr)
+{
+	acpi_status status;
+
+	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 &&
+	    addr->producer_consumer == ACPI_PRODUCER) {
+		return AE_OK;
+	}
+	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;
+
+	status = resource_to_addr(acpi_res, &addr);
+	if (ACPI_SUCCESS(status))
+		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;
+	struct resource *root;
+
+	status = resource_to_addr(acpi_res, &addr);
+	if (!ACPI_SUCCESS(status))
+		return AE_OK;
+
+	if (addr.resource_type == ACPI_MEMORY_RANGE) {
+		root = &iomem_resource;
+		flags = IORESOURCE_MEM;
+		if (addr.info.mem.caching == ACPI_PREFETCHABLE_MEMORY)
+			flags |= IORESOURCE_PREFETCH;
+	} else if (addr.resource_type == ACPI_IO_RANGE) {
+		root = &ioport_resource;
+		flags = IORESOURCE_IO;
+	} else
+		return AE_OK;
+
+	res = &info->res[info->res_num];
+	res->name = info->name;
+	res->flags = flags;
+	res->start = addr.minimum + addr.translation_offset;
+	res->end = res->start + addr.address_length - 1;
+	res->child = NULL;
+
+	if (insert_resource(root, res)) {
+		printk(KERN_ERR "PCI: Failed to allocate 0x%lx-0x%lx "
+			"from %s for %s\n", (unsigned long) res->start,
+			(unsigned long) res->end, root->name, info->name);
+	} else {
+		info->bus->resource[info->res_num] = res;
+		info->res_num++;
+	}
+	return AE_OK;
+}
+
+static void
+adjust_transparent_bridge_resources(struct pci_bus *bus)
+{
+	struct pci_dev *dev;
+
+	list_for_each_entry(dev, &bus->devices, bus_list) {
+		int i;
+		u16 class = dev->class >> 8;
+
+		if (class == PCI_CLASS_BRIDGE_PCI && dev->transparent) {
+			for(i = 3; i < PCI_BUS_NUM_RESOURCES; i++)
+				dev->subordinate->resource[i] =
+						dev->bus->resource[i - 3];
+		}
+	}
+}
+
+static void
+get_current_resources(struct acpi_device *device, int busnum,
+			struct pci_bus *bus)
+{
+	struct pci_root_info info;
+	size_t size;
+
+	info.bus = bus;
+	info.res_num = 0;
+	acpi_walk_resources(device->handle, METHOD_NAME__CRS, count_resource,
+				&info);
+	if (!info.res_num)
+		return;
+
+	size = sizeof(*info.res) * info.res_num;
+	info.res = kmalloc(size, GFP_KERNEL);
+	if (!info.res)
+		goto res_alloc_fail;
+
+	info.name = kmalloc(12, GFP_KERNEL);
+	if (!info.name)
+		goto name_alloc_fail;
+	sprintf(info.name, "PCI Bus #%02x", busnum);
+
+	info.res_num = 0;
+	acpi_walk_resources(device->handle, METHOD_NAME__CRS, setup_resource,
+				&info);
+	if (info.res_num)
+		adjust_transparent_bridge_resources(bus);
+
+	return;
+
+name_alloc_fail:
+	kfree(info.res);
+res_alloc_fail:
+	return;
+}
+
 struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_device *device, int domain, int busnum)
 {
 	struct pci_bus *bus;
@@ -89,6 +225,9 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_device *device, int do
 		}
 	}
 #endif
+
+	if (bus && (pci_probe & PCI_USE__CRS))
+		get_current_resources(device, busnum, bus);
 	
 	return bus;
 }

arch/x86/pci/common.c

@@ -436,6 +436,9 @@ char * __devinit  pcibios_setup(char *str)
 	} else if (!strcmp(str, "assign-busses")) {
 		pci_probe |= PCI_ASSIGN_ALL_BUSSES;
 		return NULL;
+	} else if (!strcmp(str, "use_crs")) {
+		pci_probe |= PCI_USE__CRS;
+		return NULL;
 	} else if (!strcmp(str, "routeirq")) {
 		pci_routeirq = 1;
 		return NULL;

arch/x86/pci/pci.h

@@ -27,6 +27,7 @@
 #define PCI_BIOS_IRQ_SCAN	0x2000
 #define PCI_ASSIGN_ALL_BUSSES	0x4000
 #define PCI_CAN_SKIP_ISA_ALIGN	0x8000
+#define PCI_USE__CRS		0x10000
 
 extern unsigned int pci_probe;
 extern unsigned long pirq_table_addr;