mirror of
https://github.com/FEX-Emu/linux.git
synced 2024-12-23 09:56:00 +00:00
62f420f828
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>
272 lines
6.1 KiB
C
272 lines
6.1 KiB
C
#include <linux/pci.h>
|
|
#include <linux/acpi.h>
|
|
#include <linux/init.h>
|
|
#include <linux/irq.h>
|
|
#include <linux/dmi.h>
|
|
#include <asm/numa.h>
|
|
#include "pci.h"
|
|
|
|
static int __devinit can_skip_ioresource_align(struct dmi_system_id *d)
|
|
{
|
|
pci_probe |= PCI_CAN_SKIP_ISA_ALIGN;
|
|
printk(KERN_INFO "PCI: %s detected, can skip ISA alignment\n", d->ident);
|
|
return 0;
|
|
}
|
|
|
|
static struct dmi_system_id acpi_pciprobe_dmi_table[] = {
|
|
/*
|
|
* Systems where PCI IO resource ISA alignment can be skipped
|
|
* when the ISA enable bit in the bridge control is not set
|
|
*/
|
|
{
|
|
.callback = can_skip_ioresource_align,
|
|
.ident = "IBM System x3800",
|
|
.matches = {
|
|
DMI_MATCH(DMI_SYS_VENDOR, "IBM"),
|
|
DMI_MATCH(DMI_PRODUCT_NAME, "x3800"),
|
|
},
|
|
},
|
|
{
|
|
.callback = can_skip_ioresource_align,
|
|
.ident = "IBM System x3850",
|
|
.matches = {
|
|
DMI_MATCH(DMI_SYS_VENDOR, "IBM"),
|
|
DMI_MATCH(DMI_PRODUCT_NAME, "x3850"),
|
|
},
|
|
},
|
|
{
|
|
.callback = can_skip_ioresource_align,
|
|
.ident = "IBM System x3950",
|
|
.matches = {
|
|
DMI_MATCH(DMI_SYS_VENDOR, "IBM"),
|
|
DMI_MATCH(DMI_PRODUCT_NAME, "x3950"),
|
|
},
|
|
},
|
|
{}
|
|
};
|
|
|
|
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;
|
|
struct pci_sysdata *sd;
|
|
int pxm;
|
|
|
|
dmi_check_system(acpi_pciprobe_dmi_table);
|
|
|
|
/* Allocate per-root-bus (not per bus) arch-specific data.
|
|
* TODO: leak; this memory is never freed.
|
|
* It's arguable whether it's worth the trouble to care.
|
|
*/
|
|
sd = kzalloc(sizeof(*sd), GFP_KERNEL);
|
|
if (!sd) {
|
|
printk(KERN_ERR "PCI: OOM, not probing PCI bus %02x\n", busnum);
|
|
return NULL;
|
|
}
|
|
|
|
if (domain != 0) {
|
|
printk(KERN_WARNING "PCI: Multiple domains not supported\n");
|
|
kfree(sd);
|
|
return NULL;
|
|
}
|
|
|
|
sd->node = -1;
|
|
|
|
pxm = acpi_get_pxm(device->handle);
|
|
#ifdef CONFIG_ACPI_NUMA
|
|
if (pxm >= 0)
|
|
sd->node = pxm_to_node(pxm);
|
|
#endif
|
|
|
|
bus = pci_scan_bus_parented(NULL, busnum, &pci_root_ops, sd);
|
|
if (!bus)
|
|
kfree(sd);
|
|
|
|
#ifdef CONFIG_ACPI_NUMA
|
|
if (bus != NULL) {
|
|
if (pxm >= 0) {
|
|
printk("bus %d -> pxm %d -> node %d\n",
|
|
busnum, pxm, sd->node);
|
|
}
|
|
}
|
|
#endif
|
|
|
|
if (bus && (pci_probe & PCI_USE__CRS))
|
|
get_current_resources(device, busnum, bus);
|
|
|
|
return bus;
|
|
}
|
|
|
|
extern int pci_routeirq;
|
|
static int __init pci_acpi_init(void)
|
|
{
|
|
struct pci_dev *dev = NULL;
|
|
|
|
if (pcibios_scanned)
|
|
return 0;
|
|
|
|
if (acpi_noirq)
|
|
return 0;
|
|
|
|
printk(KERN_INFO "PCI: Using ACPI for IRQ routing\n");
|
|
acpi_irq_penalty_init();
|
|
pcibios_scanned++;
|
|
pcibios_enable_irq = acpi_pci_irq_enable;
|
|
pcibios_disable_irq = acpi_pci_irq_disable;
|
|
|
|
if (pci_routeirq) {
|
|
/*
|
|
* PCI IRQ routing is set up by pci_enable_device(), but we
|
|
* also do it here in case there are still broken drivers that
|
|
* don't use pci_enable_device().
|
|
*/
|
|
printk(KERN_INFO "PCI: Routing PCI interrupts for all devices because \"pci=routeirq\" specified\n");
|
|
for_each_pci_dev(dev)
|
|
acpi_pci_irq_enable(dev);
|
|
} else
|
|
printk(KERN_INFO "PCI: If a device doesn't work, try \"pci=routeirq\". If it helps, post a report\n");
|
|
|
|
#ifdef CONFIG_X86_IO_APIC
|
|
if (acpi_ioapic)
|
|
print_IO_APIC();
|
|
#endif
|
|
|
|
return 0;
|
|
}
|
|
subsys_initcall(pci_acpi_init);
|