linux_old1/arch/x86/pci/common.c

701 lines
16 KiB
C
Raw Normal View History

/*
* Low-Level PCI Support for PC
*
* (c) 1999--2000 Martin Mares <mj@ucw.cz>
*/
#include <linux/sched.h>
#include <linux/pci.h>
#include <linux/pci-acpi.h>
#include <linux/ioport.h>
#include <linux/init.h>
[PATCH] PCI: PCI/Cardbus cards hidden, needs pci=assign-busses to fix "In some cases, especially on modern laptops with a lot of PCI and cardbus bridges, we're unable to assign correct secondary/subordinate bus numbers to all cardbus bridges due to BIOS limitations unless we are using "pci=assign-busses" boot option." -- Ivan Kokshaysky (from a patch comment) Without it, Cardbus cards inserted are never seen by PCI because the parent PCI-PCI Bridge of the Cardbus bridge will not pass and translate Type 1 PCI configuration cycles correctly and the system will fail to find and initialise the PCI devices in the system. Reference: PCI-PCI Bridges: PCI Configuration Cycles and PCI Bus Numbering: http://www.science.unitn.it/~fiorella/guidelinux/tlk/node72.html The reason for this is that: ``All PCI busses located behind a PCI-PCI bridge must reside between the secondary bus number and the subordinate bus number (inclusive).'' "pci=assign-busses" makes pcibios_assign_all_busses return 1 and this turns on PCI renumbering during PCI probing. Alan suggested to use DMI automatically set assign-busses on problem systems. The only question for me was where to put it. I put it directly before scanning PCI bus into pcibios_scan_root() because it's called from legacy, acpi and numa and so it can be one place for all systems and configurations which may need it. AMD64 Laptops are also affected and fixed by assign-busses, and the code is also incuded from arch/x86_64/pci/ that place will also work for x86_64 kernels, I only ifdef'-ed the x86-only Laptop in this example. Affected and known or assumed to be fixed with it are (found by googling): * ASUS Z71V and L3s * Samsung X20 * Compaq R3140us and all Compaq R3000 series laptops with TI1620 Controller, also Compaq R4000 series (from a kernel.org bugreport) * HP zv5000z (AMD64 3700+, known that fixup_parent_subordinate_busnr fixes it) * HP zv5200z * IBM ThinkPad 240 * An IBM ThinkPad (1.8 GHz Pentium M) debugged by Pavel Machek gives the correspondig message which detects the possible problem. * MSI S260 / Medion SIM 2100 MD 95600 The patch also expands the "try pci=assign-busses" warning so testers will help us to update the DMI table. Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Russell King <rmk@arm.linux.org.uk> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2006-02-18 17:36:55 +08:00
#include <linux/dmi.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <asm-generic/pci-bridge.h>
#include <asm/acpi.h>
#include <asm/segment.h>
#include <asm/io.h>
#include <asm/smp.h>
#include <asm/pci_x86.h>
#include <asm/setup.h>
unsigned int pci_probe = PCI_PROBE_BIOS | PCI_PROBE_CONF1 | PCI_PROBE_CONF2 |
PCI_PROBE_MMCONF;
unsigned int pci_early_dump_regs;
static int pci_bf_sort;
static int smbios_type_b1_flag;
int pci_routeirq;
int noioapicquirk;
#ifdef CONFIG_X86_REROUTE_FOR_BROKEN_BOOT_IRQS
int noioapicreroute = 0;
#else
int noioapicreroute = 1;
#endif
int pcibios_last_bus = -1;
unsigned long pirq_table_addr;
const struct pci_raw_ops *__read_mostly raw_pci_ops;
const struct pci_raw_ops *__read_mostly raw_pci_ext_ops;
int raw_pci_read(unsigned int domain, unsigned int bus, unsigned int devfn,
int reg, int len, u32 *val)
{
if (domain == 0 && reg < 256 && raw_pci_ops)
return raw_pci_ops->read(domain, bus, devfn, reg, len, val);
if (raw_pci_ext_ops)
return raw_pci_ext_ops->read(domain, bus, devfn, reg, len, val);
return -EINVAL;
}
int raw_pci_write(unsigned int domain, unsigned int bus, unsigned int devfn,
int reg, int len, u32 val)
{
if (domain == 0 && reg < 256 && raw_pci_ops)
return raw_pci_ops->write(domain, bus, devfn, reg, len, val);
if (raw_pci_ext_ops)
return raw_pci_ext_ops->write(domain, bus, devfn, reg, len, val);
return -EINVAL;
}
static int pci_read(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 *value)
{
return raw_pci_read(pci_domain_nr(bus), bus->number,
devfn, where, size, value);
}
static int pci_write(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 value)
{
return raw_pci_write(pci_domain_nr(bus), bus->number,
devfn, where, size, value);
}
struct pci_ops pci_root_ops = {
.read = pci_read,
.write = pci_write,
};
/*
* This interrupt-safe spinlock protects all accesses to PCI
* configuration space.
*/
DEFINE_RAW_SPINLOCK(pci_config_lock);
static int __init can_skip_ioresource_align(const 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 const struct dmi_system_id can_skip_pciprobe_dmi_table[] __initconst = {
/*
* 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"),
},
},
{}
};
void __init dmi_check_skip_isa_align(void)
{
dmi_check_system(can_skip_pciprobe_dmi_table);
}
static void pcibios_fixup_device_resources(struct pci_dev *dev)
PCI: boot parameter to avoid expansion ROM memory allocation Contention for scarce PCI memory resources has been growing due to an increasing number of PCI slots in large multi-node systems. The kernel currently attempts by default to allocate memory for all PCI expansion ROMs so there has also been an increasing number of PCI memory allocation failures seen on these systems. This occurs because the BIOS either (1) provides insufficient PCI memory resource for all the expansion ROMs or (2) provides adequate PCI memory resource for expansion ROMs but provides the space in kernel unexpected BIOS assigned P2P non-prefetch windows. The resulting PCI memory allocation failures may be benign when related to memory requests for expansion ROMs themselves but in some cases they can occur when attempting to allocate space for more critical BARs. This can happen when a successful expansion ROM allocation request consumes memory resource that was intended for a non-ROM BAR. We have seen this happen during PCI hotplug of an adapter that contains a P2P bridge where successful memory allocation for an expansion ROM BAR on device behind the bridge consumed memory that was intended for a non-ROM BAR on the P2P bridge. In all cases the allocation failure messages can be very confusing for users. This patch provides a new 'pci=norom' kernel boot parameter that can be used to disable the default PCI expansion ROM memory resource allocation. This provides a way to avoid the above described issues on systems that do not contain PCI devices for which drivers or user-level applications depend on the default PCI expansion ROM memory resource allocation behavior. Signed-off-by: Gary Hade <garyhade@us.ibm.com> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2008-05-13 04:57:46 +08:00
{
struct resource *rom_r = &dev->resource[PCI_ROM_RESOURCE];
struct resource *bar_r;
int bar;
if (pci_probe & PCI_NOASSIGN_BARS) {
/*
* If the BIOS did not assign the BAR, zero out the
* resource so the kernel doesn't attmept to assign
* it later on in pci_assign_unassigned_resources
*/
for (bar = 0; bar <= PCI_STD_RESOURCE_END; bar++) {
bar_r = &dev->resource[bar];
if (bar_r->start == 0 && bar_r->end != 0) {
bar_r->flags = 0;
bar_r->end = 0;
}
}
}
PCI: boot parameter to avoid expansion ROM memory allocation Contention for scarce PCI memory resources has been growing due to an increasing number of PCI slots in large multi-node systems. The kernel currently attempts by default to allocate memory for all PCI expansion ROMs so there has also been an increasing number of PCI memory allocation failures seen on these systems. This occurs because the BIOS either (1) provides insufficient PCI memory resource for all the expansion ROMs or (2) provides adequate PCI memory resource for expansion ROMs but provides the space in kernel unexpected BIOS assigned P2P non-prefetch windows. The resulting PCI memory allocation failures may be benign when related to memory requests for expansion ROMs themselves but in some cases they can occur when attempting to allocate space for more critical BARs. This can happen when a successful expansion ROM allocation request consumes memory resource that was intended for a non-ROM BAR. We have seen this happen during PCI hotplug of an adapter that contains a P2P bridge where successful memory allocation for an expansion ROM BAR on device behind the bridge consumed memory that was intended for a non-ROM BAR on the P2P bridge. In all cases the allocation failure messages can be very confusing for users. This patch provides a new 'pci=norom' kernel boot parameter that can be used to disable the default PCI expansion ROM memory resource allocation. This provides a way to avoid the above described issues on systems that do not contain PCI devices for which drivers or user-level applications depend on the default PCI expansion ROM memory resource allocation behavior. Signed-off-by: Gary Hade <garyhade@us.ibm.com> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2008-05-13 04:57:46 +08:00
if (pci_probe & PCI_NOASSIGN_ROMS) {
if (rom_r->parent)
return;
if (rom_r->start) {
/* we deal with BIOS assigned ROM later */
return;
}
rom_r->start = rom_r->end = rom_r->flags = 0;
}
}
/*
* Called after each bus is probed, but before its children
* are examined.
*/
void pcibios_fixup_bus(struct pci_bus *b)
{
PCI: boot parameter to avoid expansion ROM memory allocation Contention for scarce PCI memory resources has been growing due to an increasing number of PCI slots in large multi-node systems. The kernel currently attempts by default to allocate memory for all PCI expansion ROMs so there has also been an increasing number of PCI memory allocation failures seen on these systems. This occurs because the BIOS either (1) provides insufficient PCI memory resource for all the expansion ROMs or (2) provides adequate PCI memory resource for expansion ROMs but provides the space in kernel unexpected BIOS assigned P2P non-prefetch windows. The resulting PCI memory allocation failures may be benign when related to memory requests for expansion ROMs themselves but in some cases they can occur when attempting to allocate space for more critical BARs. This can happen when a successful expansion ROM allocation request consumes memory resource that was intended for a non-ROM BAR. We have seen this happen during PCI hotplug of an adapter that contains a P2P bridge where successful memory allocation for an expansion ROM BAR on device behind the bridge consumed memory that was intended for a non-ROM BAR on the P2P bridge. In all cases the allocation failure messages can be very confusing for users. This patch provides a new 'pci=norom' kernel boot parameter that can be used to disable the default PCI expansion ROM memory resource allocation. This provides a way to avoid the above described issues on systems that do not contain PCI devices for which drivers or user-level applications depend on the default PCI expansion ROM memory resource allocation behavior. Signed-off-by: Gary Hade <garyhade@us.ibm.com> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2008-05-13 04:57:46 +08:00
struct pci_dev *dev;
pci_read_bridge_bases(b);
PCI: boot parameter to avoid expansion ROM memory allocation Contention for scarce PCI memory resources has been growing due to an increasing number of PCI slots in large multi-node systems. The kernel currently attempts by default to allocate memory for all PCI expansion ROMs so there has also been an increasing number of PCI memory allocation failures seen on these systems. This occurs because the BIOS either (1) provides insufficient PCI memory resource for all the expansion ROMs or (2) provides adequate PCI memory resource for expansion ROMs but provides the space in kernel unexpected BIOS assigned P2P non-prefetch windows. The resulting PCI memory allocation failures may be benign when related to memory requests for expansion ROMs themselves but in some cases they can occur when attempting to allocate space for more critical BARs. This can happen when a successful expansion ROM allocation request consumes memory resource that was intended for a non-ROM BAR. We have seen this happen during PCI hotplug of an adapter that contains a P2P bridge where successful memory allocation for an expansion ROM BAR on device behind the bridge consumed memory that was intended for a non-ROM BAR on the P2P bridge. In all cases the allocation failure messages can be very confusing for users. This patch provides a new 'pci=norom' kernel boot parameter that can be used to disable the default PCI expansion ROM memory resource allocation. This provides a way to avoid the above described issues on systems that do not contain PCI devices for which drivers or user-level applications depend on the default PCI expansion ROM memory resource allocation behavior. Signed-off-by: Gary Hade <garyhade@us.ibm.com> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2008-05-13 04:57:46 +08:00
list_for_each_entry(dev, &b->devices, bus_list)
pcibios_fixup_device_resources(dev);
}
void pcibios_add_bus(struct pci_bus *bus)
{
acpi_pci_add_bus(bus);
}
void pcibios_remove_bus(struct pci_bus *bus)
{
acpi_pci_remove_bus(bus);
}
PCI: optionally sort device lists breadth-first Problem: New Dell PowerEdge servers have 2 embedded ethernet ports, which are labeled NIC1 and NIC2 on the chassis, in the BIOS setup screens, and in the printed documentation. Assuming no other add-in ethernet ports in the system, Linux 2.4 kernels name these eth0 and eth1 respectively. Many people have come to expect this naming. Linux 2.6 kernels name these eth1 and eth0 respectively (backwards from expectations). I also have reports that various Sun and HP servers have similar behavior. Root cause: Linux 2.4 kernels walk the pci_devices list, which happens to be sorted in breadth-first order (or pcbios_find_device order on i386, which most often is breadth-first also). 2.6 kernels have both the pci_devices list and the pci_bus_type.klist_devices list, the latter is what is walked at driver load time to match the pci_id tables; this klist happens to be in depth-first order. On systems where, for physical routing reasons, NIC1 appears on a lower bus number than NIC2, but NIC2's bridge is discovered first in the depth-first ordering, NIC2 will be discovered before NIC1. If the list were sorted breadth-first, NIC1 would be discovered before NIC2. A PowerEdge 1955 system has the following topology which easily exhibits the difference between depth-first and breadth-first device lists. -[0000:00]-+-00.0 Intel Corporation 5000P Chipset Memory Controller Hub +-02.0-[0000:03-08]--+-00.0-[0000:04-07]--+-00.0-[0000:05-06]----00.0-[0000:06]----00.0 Broadcom Corporation NetXtreme II BCM5708S Gigabit Ethernet (labeled NIC2, 2.4 kernel name eth1, 2.6 kernel name eth0) +-1c.0-[0000:01-02]----00.0-[0000:02]----00.0 Broadcom Corporation NetXtreme II BCM5708S Gigabit Ethernet (labeled NIC1, 2.4 kernel name eth0, 2.6 kernel name eth1) Other factors, such as device driver load order and the presence of PCI slots at various points in the bus hierarchy further complicate this problem; I'm not trying to solve those here, just restore the device order, and thus basic behavior, that 2.4 kernels had. Solution: The solution can come in multiple steps. Suggested fix #1: kernel Patch below optionally sorts the two device lists into breadth-first ordering to maintain compatibility with 2.4 kernels. It adds two new command line options: pci=bfsort pci=nobfsort to force the sort order, or not, as you wish. It also adds DMI checks for the specific Dell systems which exhibit "backwards" ordering, to make them "right". Suggested fix #2: udev rules from userland Many people also have the expectation that embedded NICs are always discovered before add-in NICs (which this patch does not try to do). Using the PCI IRQ Routing Table provided by system BIOS, it's easy to determine which PCI devices are embedded, or if add-in, which PCI slot they're in. I'm working on a tool that would allow udev to name ethernet devices in ascending embedded, slot 1 .. slot N order, subsort by PCI bus/dev/fn breadth-first. It'll be possible to use it independent of udev as well for those distributions that don't use udev in their installers. Suggested fix #3: system board routing rules One can constrain the system board layout to put NIC1 ahead of NIC2 regardless of breadth-first or depth-first discovery order. This adds a significant level of complexity to board routing, and may not be possible in all instances (witness the above systems from several major manufacturers). I don't want to encourage this particular train of thought too far, at the expense of not doing #1 or #2 above. Feedback appreciated. Patch tested on a Dell PowerEdge 1955 blade with 2.6.18. You'll also note I took some liberty and temporarily break the klist abstraction to simplify and speed up the sort algorithm. I think that's both safe and appropriate in this instance. Signed-off-by: Matt Domsch <Matt_Domsch@dell.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2006-09-30 04:23:23 +08:00
/*
* Only use DMI information to set this if nothing was passed
* on the kernel command line (which was parsed earlier).
*/
static int __init set_bf_sort(const struct dmi_system_id *d)
PCI: optionally sort device lists breadth-first Problem: New Dell PowerEdge servers have 2 embedded ethernet ports, which are labeled NIC1 and NIC2 on the chassis, in the BIOS setup screens, and in the printed documentation. Assuming no other add-in ethernet ports in the system, Linux 2.4 kernels name these eth0 and eth1 respectively. Many people have come to expect this naming. Linux 2.6 kernels name these eth1 and eth0 respectively (backwards from expectations). I also have reports that various Sun and HP servers have similar behavior. Root cause: Linux 2.4 kernels walk the pci_devices list, which happens to be sorted in breadth-first order (or pcbios_find_device order on i386, which most often is breadth-first also). 2.6 kernels have both the pci_devices list and the pci_bus_type.klist_devices list, the latter is what is walked at driver load time to match the pci_id tables; this klist happens to be in depth-first order. On systems where, for physical routing reasons, NIC1 appears on a lower bus number than NIC2, but NIC2's bridge is discovered first in the depth-first ordering, NIC2 will be discovered before NIC1. If the list were sorted breadth-first, NIC1 would be discovered before NIC2. A PowerEdge 1955 system has the following topology which easily exhibits the difference between depth-first and breadth-first device lists. -[0000:00]-+-00.0 Intel Corporation 5000P Chipset Memory Controller Hub +-02.0-[0000:03-08]--+-00.0-[0000:04-07]--+-00.0-[0000:05-06]----00.0-[0000:06]----00.0 Broadcom Corporation NetXtreme II BCM5708S Gigabit Ethernet (labeled NIC2, 2.4 kernel name eth1, 2.6 kernel name eth0) +-1c.0-[0000:01-02]----00.0-[0000:02]----00.0 Broadcom Corporation NetXtreme II BCM5708S Gigabit Ethernet (labeled NIC1, 2.4 kernel name eth0, 2.6 kernel name eth1) Other factors, such as device driver load order and the presence of PCI slots at various points in the bus hierarchy further complicate this problem; I'm not trying to solve those here, just restore the device order, and thus basic behavior, that 2.4 kernels had. Solution: The solution can come in multiple steps. Suggested fix #1: kernel Patch below optionally sorts the two device lists into breadth-first ordering to maintain compatibility with 2.4 kernels. It adds two new command line options: pci=bfsort pci=nobfsort to force the sort order, or not, as you wish. It also adds DMI checks for the specific Dell systems which exhibit "backwards" ordering, to make them "right". Suggested fix #2: udev rules from userland Many people also have the expectation that embedded NICs are always discovered before add-in NICs (which this patch does not try to do). Using the PCI IRQ Routing Table provided by system BIOS, it's easy to determine which PCI devices are embedded, or if add-in, which PCI slot they're in. I'm working on a tool that would allow udev to name ethernet devices in ascending embedded, slot 1 .. slot N order, subsort by PCI bus/dev/fn breadth-first. It'll be possible to use it independent of udev as well for those distributions that don't use udev in their installers. Suggested fix #3: system board routing rules One can constrain the system board layout to put NIC1 ahead of NIC2 regardless of breadth-first or depth-first discovery order. This adds a significant level of complexity to board routing, and may not be possible in all instances (witness the above systems from several major manufacturers). I don't want to encourage this particular train of thought too far, at the expense of not doing #1 or #2 above. Feedback appreciated. Patch tested on a Dell PowerEdge 1955 blade with 2.6.18. You'll also note I took some liberty and temporarily break the klist abstraction to simplify and speed up the sort algorithm. I think that's both safe and appropriate in this instance. Signed-off-by: Matt Domsch <Matt_Domsch@dell.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2006-09-30 04:23:23 +08:00
{
if (pci_bf_sort == pci_bf_sort_default) {
pci_bf_sort = pci_dmi_bf;
printk(KERN_INFO "PCI: %s detected, enabling pci=bfsort.\n", d->ident);
}
return 0;
}
static void __init read_dmi_type_b1(const struct dmi_header *dm,
void *private_data)
{
u8 *d = (u8 *)dm + 4;
if (dm->type != 0xB1)
return;
switch (((*(u32 *)d) >> 9) & 0x03) {
case 0x00:
printk(KERN_INFO "dmi type 0xB1 record - unknown flag\n");
break;
case 0x01: /* set pci=bfsort */
smbios_type_b1_flag = 1;
break;
case 0x02: /* do not set pci=bfsort */
smbios_type_b1_flag = 2;
break;
default:
break;
}
}
static int __init find_sort_method(const struct dmi_system_id *d)
{
dmi_walk(read_dmi_type_b1, NULL);
if (smbios_type_b1_flag == 1) {
set_bf_sort(d);
return 0;
}
return -1;
}
[PATCH] PCI: PCI/Cardbus cards hidden, needs pci=assign-busses to fix "In some cases, especially on modern laptops with a lot of PCI and cardbus bridges, we're unable to assign correct secondary/subordinate bus numbers to all cardbus bridges due to BIOS limitations unless we are using "pci=assign-busses" boot option." -- Ivan Kokshaysky (from a patch comment) Without it, Cardbus cards inserted are never seen by PCI because the parent PCI-PCI Bridge of the Cardbus bridge will not pass and translate Type 1 PCI configuration cycles correctly and the system will fail to find and initialise the PCI devices in the system. Reference: PCI-PCI Bridges: PCI Configuration Cycles and PCI Bus Numbering: http://www.science.unitn.it/~fiorella/guidelinux/tlk/node72.html The reason for this is that: ``All PCI busses located behind a PCI-PCI bridge must reside between the secondary bus number and the subordinate bus number (inclusive).'' "pci=assign-busses" makes pcibios_assign_all_busses return 1 and this turns on PCI renumbering during PCI probing. Alan suggested to use DMI automatically set assign-busses on problem systems. The only question for me was where to put it. I put it directly before scanning PCI bus into pcibios_scan_root() because it's called from legacy, acpi and numa and so it can be one place for all systems and configurations which may need it. AMD64 Laptops are also affected and fixed by assign-busses, and the code is also incuded from arch/x86_64/pci/ that place will also work for x86_64 kernels, I only ifdef'-ed the x86-only Laptop in this example. Affected and known or assumed to be fixed with it are (found by googling): * ASUS Z71V and L3s * Samsung X20 * Compaq R3140us and all Compaq R3000 series laptops with TI1620 Controller, also Compaq R4000 series (from a kernel.org bugreport) * HP zv5000z (AMD64 3700+, known that fixup_parent_subordinate_busnr fixes it) * HP zv5200z * IBM ThinkPad 240 * An IBM ThinkPad (1.8 GHz Pentium M) debugged by Pavel Machek gives the correspondig message which detects the possible problem. * MSI S260 / Medion SIM 2100 MD 95600 The patch also expands the "try pci=assign-busses" warning so testers will help us to update the DMI table. Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Russell King <rmk@arm.linux.org.uk> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2006-02-18 17:36:55 +08:00
/*
* Enable renumbering of PCI bus# ranges to reach all PCI busses (Cardbus)
*/
#ifdef __i386__
static int __init assign_all_busses(const struct dmi_system_id *d)
[PATCH] PCI: PCI/Cardbus cards hidden, needs pci=assign-busses to fix "In some cases, especially on modern laptops with a lot of PCI and cardbus bridges, we're unable to assign correct secondary/subordinate bus numbers to all cardbus bridges due to BIOS limitations unless we are using "pci=assign-busses" boot option." -- Ivan Kokshaysky (from a patch comment) Without it, Cardbus cards inserted are never seen by PCI because the parent PCI-PCI Bridge of the Cardbus bridge will not pass and translate Type 1 PCI configuration cycles correctly and the system will fail to find and initialise the PCI devices in the system. Reference: PCI-PCI Bridges: PCI Configuration Cycles and PCI Bus Numbering: http://www.science.unitn.it/~fiorella/guidelinux/tlk/node72.html The reason for this is that: ``All PCI busses located behind a PCI-PCI bridge must reside between the secondary bus number and the subordinate bus number (inclusive).'' "pci=assign-busses" makes pcibios_assign_all_busses return 1 and this turns on PCI renumbering during PCI probing. Alan suggested to use DMI automatically set assign-busses on problem systems. The only question for me was where to put it. I put it directly before scanning PCI bus into pcibios_scan_root() because it's called from legacy, acpi and numa and so it can be one place for all systems and configurations which may need it. AMD64 Laptops are also affected and fixed by assign-busses, and the code is also incuded from arch/x86_64/pci/ that place will also work for x86_64 kernels, I only ifdef'-ed the x86-only Laptop in this example. Affected and known or assumed to be fixed with it are (found by googling): * ASUS Z71V and L3s * Samsung X20 * Compaq R3140us and all Compaq R3000 series laptops with TI1620 Controller, also Compaq R4000 series (from a kernel.org bugreport) * HP zv5000z (AMD64 3700+, known that fixup_parent_subordinate_busnr fixes it) * HP zv5200z * IBM ThinkPad 240 * An IBM ThinkPad (1.8 GHz Pentium M) debugged by Pavel Machek gives the correspondig message which detects the possible problem. * MSI S260 / Medion SIM 2100 MD 95600 The patch also expands the "try pci=assign-busses" warning so testers will help us to update the DMI table. Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Russell King <rmk@arm.linux.org.uk> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2006-02-18 17:36:55 +08:00
{
pci_probe |= PCI_ASSIGN_ALL_BUSSES;
printk(KERN_INFO "%s detected: enabling PCI bus# renumbering"
" (pci=assign-busses)\n", d->ident);
return 0;
}
#endif
static int __init set_scan_all(const struct dmi_system_id *d)
{
printk(KERN_INFO "PCI: %s detected, enabling pci=pcie_scan_all\n",
d->ident);
pci_add_flags(PCI_SCAN_ALL_PCIE_DEVS);
return 0;
}
static const struct dmi_system_id pciprobe_dmi_table[] __initconst = {
PCI: optionally sort device lists breadth-first Problem: New Dell PowerEdge servers have 2 embedded ethernet ports, which are labeled NIC1 and NIC2 on the chassis, in the BIOS setup screens, and in the printed documentation. Assuming no other add-in ethernet ports in the system, Linux 2.4 kernels name these eth0 and eth1 respectively. Many people have come to expect this naming. Linux 2.6 kernels name these eth1 and eth0 respectively (backwards from expectations). I also have reports that various Sun and HP servers have similar behavior. Root cause: Linux 2.4 kernels walk the pci_devices list, which happens to be sorted in breadth-first order (or pcbios_find_device order on i386, which most often is breadth-first also). 2.6 kernels have both the pci_devices list and the pci_bus_type.klist_devices list, the latter is what is walked at driver load time to match the pci_id tables; this klist happens to be in depth-first order. On systems where, for physical routing reasons, NIC1 appears on a lower bus number than NIC2, but NIC2's bridge is discovered first in the depth-first ordering, NIC2 will be discovered before NIC1. If the list were sorted breadth-first, NIC1 would be discovered before NIC2. A PowerEdge 1955 system has the following topology which easily exhibits the difference between depth-first and breadth-first device lists. -[0000:00]-+-00.0 Intel Corporation 5000P Chipset Memory Controller Hub +-02.0-[0000:03-08]--+-00.0-[0000:04-07]--+-00.0-[0000:05-06]----00.0-[0000:06]----00.0 Broadcom Corporation NetXtreme II BCM5708S Gigabit Ethernet (labeled NIC2, 2.4 kernel name eth1, 2.6 kernel name eth0) +-1c.0-[0000:01-02]----00.0-[0000:02]----00.0 Broadcom Corporation NetXtreme II BCM5708S Gigabit Ethernet (labeled NIC1, 2.4 kernel name eth0, 2.6 kernel name eth1) Other factors, such as device driver load order and the presence of PCI slots at various points in the bus hierarchy further complicate this problem; I'm not trying to solve those here, just restore the device order, and thus basic behavior, that 2.4 kernels had. Solution: The solution can come in multiple steps. Suggested fix #1: kernel Patch below optionally sorts the two device lists into breadth-first ordering to maintain compatibility with 2.4 kernels. It adds two new command line options: pci=bfsort pci=nobfsort to force the sort order, or not, as you wish. It also adds DMI checks for the specific Dell systems which exhibit "backwards" ordering, to make them "right". Suggested fix #2: udev rules from userland Many people also have the expectation that embedded NICs are always discovered before add-in NICs (which this patch does not try to do). Using the PCI IRQ Routing Table provided by system BIOS, it's easy to determine which PCI devices are embedded, or if add-in, which PCI slot they're in. I'm working on a tool that would allow udev to name ethernet devices in ascending embedded, slot 1 .. slot N order, subsort by PCI bus/dev/fn breadth-first. It'll be possible to use it independent of udev as well for those distributions that don't use udev in their installers. Suggested fix #3: system board routing rules One can constrain the system board layout to put NIC1 ahead of NIC2 regardless of breadth-first or depth-first discovery order. This adds a significant level of complexity to board routing, and may not be possible in all instances (witness the above systems from several major manufacturers). I don't want to encourage this particular train of thought too far, at the expense of not doing #1 or #2 above. Feedback appreciated. Patch tested on a Dell PowerEdge 1955 blade with 2.6.18. You'll also note I took some liberty and temporarily break the klist abstraction to simplify and speed up the sort algorithm. I think that's both safe and appropriate in this instance. Signed-off-by: Matt Domsch <Matt_Domsch@dell.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2006-09-30 04:23:23 +08:00
#ifdef __i386__
[PATCH] PCI: PCI/Cardbus cards hidden, needs pci=assign-busses to fix "In some cases, especially on modern laptops with a lot of PCI and cardbus bridges, we're unable to assign correct secondary/subordinate bus numbers to all cardbus bridges due to BIOS limitations unless we are using "pci=assign-busses" boot option." -- Ivan Kokshaysky (from a patch comment) Without it, Cardbus cards inserted are never seen by PCI because the parent PCI-PCI Bridge of the Cardbus bridge will not pass and translate Type 1 PCI configuration cycles correctly and the system will fail to find and initialise the PCI devices in the system. Reference: PCI-PCI Bridges: PCI Configuration Cycles and PCI Bus Numbering: http://www.science.unitn.it/~fiorella/guidelinux/tlk/node72.html The reason for this is that: ``All PCI busses located behind a PCI-PCI bridge must reside between the secondary bus number and the subordinate bus number (inclusive).'' "pci=assign-busses" makes pcibios_assign_all_busses return 1 and this turns on PCI renumbering during PCI probing. Alan suggested to use DMI automatically set assign-busses on problem systems. The only question for me was where to put it. I put it directly before scanning PCI bus into pcibios_scan_root() because it's called from legacy, acpi and numa and so it can be one place for all systems and configurations which may need it. AMD64 Laptops are also affected and fixed by assign-busses, and the code is also incuded from arch/x86_64/pci/ that place will also work for x86_64 kernels, I only ifdef'-ed the x86-only Laptop in this example. Affected and known or assumed to be fixed with it are (found by googling): * ASUS Z71V and L3s * Samsung X20 * Compaq R3140us and all Compaq R3000 series laptops with TI1620 Controller, also Compaq R4000 series (from a kernel.org bugreport) * HP zv5000z (AMD64 3700+, known that fixup_parent_subordinate_busnr fixes it) * HP zv5200z * IBM ThinkPad 240 * An IBM ThinkPad (1.8 GHz Pentium M) debugged by Pavel Machek gives the correspondig message which detects the possible problem. * MSI S260 / Medion SIM 2100 MD 95600 The patch also expands the "try pci=assign-busses" warning so testers will help us to update the DMI table. Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Russell King <rmk@arm.linux.org.uk> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2006-02-18 17:36:55 +08:00
/*
* Laptops which need pci=assign-busses to see Cardbus cards
*/
{
.callback = assign_all_busses,
.ident = "Samsung X20 Laptop",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Samsung Electronics"),
DMI_MATCH(DMI_PRODUCT_NAME, "SX20S"),
},
},
#endif /* __i386__ */
PCI: optionally sort device lists breadth-first Problem: New Dell PowerEdge servers have 2 embedded ethernet ports, which are labeled NIC1 and NIC2 on the chassis, in the BIOS setup screens, and in the printed documentation. Assuming no other add-in ethernet ports in the system, Linux 2.4 kernels name these eth0 and eth1 respectively. Many people have come to expect this naming. Linux 2.6 kernels name these eth1 and eth0 respectively (backwards from expectations). I also have reports that various Sun and HP servers have similar behavior. Root cause: Linux 2.4 kernels walk the pci_devices list, which happens to be sorted in breadth-first order (or pcbios_find_device order on i386, which most often is breadth-first also). 2.6 kernels have both the pci_devices list and the pci_bus_type.klist_devices list, the latter is what is walked at driver load time to match the pci_id tables; this klist happens to be in depth-first order. On systems where, for physical routing reasons, NIC1 appears on a lower bus number than NIC2, but NIC2's bridge is discovered first in the depth-first ordering, NIC2 will be discovered before NIC1. If the list were sorted breadth-first, NIC1 would be discovered before NIC2. A PowerEdge 1955 system has the following topology which easily exhibits the difference between depth-first and breadth-first device lists. -[0000:00]-+-00.0 Intel Corporation 5000P Chipset Memory Controller Hub +-02.0-[0000:03-08]--+-00.0-[0000:04-07]--+-00.0-[0000:05-06]----00.0-[0000:06]----00.0 Broadcom Corporation NetXtreme II BCM5708S Gigabit Ethernet (labeled NIC2, 2.4 kernel name eth1, 2.6 kernel name eth0) +-1c.0-[0000:01-02]----00.0-[0000:02]----00.0 Broadcom Corporation NetXtreme II BCM5708S Gigabit Ethernet (labeled NIC1, 2.4 kernel name eth0, 2.6 kernel name eth1) Other factors, such as device driver load order and the presence of PCI slots at various points in the bus hierarchy further complicate this problem; I'm not trying to solve those here, just restore the device order, and thus basic behavior, that 2.4 kernels had. Solution: The solution can come in multiple steps. Suggested fix #1: kernel Patch below optionally sorts the two device lists into breadth-first ordering to maintain compatibility with 2.4 kernels. It adds two new command line options: pci=bfsort pci=nobfsort to force the sort order, or not, as you wish. It also adds DMI checks for the specific Dell systems which exhibit "backwards" ordering, to make them "right". Suggested fix #2: udev rules from userland Many people also have the expectation that embedded NICs are always discovered before add-in NICs (which this patch does not try to do). Using the PCI IRQ Routing Table provided by system BIOS, it's easy to determine which PCI devices are embedded, or if add-in, which PCI slot they're in. I'm working on a tool that would allow udev to name ethernet devices in ascending embedded, slot 1 .. slot N order, subsort by PCI bus/dev/fn breadth-first. It'll be possible to use it independent of udev as well for those distributions that don't use udev in their installers. Suggested fix #3: system board routing rules One can constrain the system board layout to put NIC1 ahead of NIC2 regardless of breadth-first or depth-first discovery order. This adds a significant level of complexity to board routing, and may not be possible in all instances (witness the above systems from several major manufacturers). I don't want to encourage this particular train of thought too far, at the expense of not doing #1 or #2 above. Feedback appreciated. Patch tested on a Dell PowerEdge 1955 blade with 2.6.18. You'll also note I took some liberty and temporarily break the klist abstraction to simplify and speed up the sort algorithm. I think that's both safe and appropriate in this instance. Signed-off-by: Matt Domsch <Matt_Domsch@dell.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2006-09-30 04:23:23 +08:00
{
.callback = set_bf_sort,
.ident = "Dell PowerEdge 1950",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell"),
DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge 1950"),
},
},
{
.callback = set_bf_sort,
.ident = "Dell PowerEdge 1955",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell"),
DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge 1955"),
},
},
{
.callback = set_bf_sort,
.ident = "Dell PowerEdge 2900",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell"),
DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge 2900"),
},
},
{
.callback = set_bf_sort,
.ident = "Dell PowerEdge 2950",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell"),
DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge 2950"),
},
},
{
.callback = set_bf_sort,
.ident = "Dell PowerEdge R900",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell"),
DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R900"),
},
},
{
.callback = find_sort_method,
.ident = "Dell System",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc"),
},
},
{
.callback = set_bf_sort,
.ident = "HP ProLiant BL20p G3",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "HP"),
DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant BL20p G3"),
},
},
{
.callback = set_bf_sort,
.ident = "HP ProLiant BL20p G4",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "HP"),
DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant BL20p G4"),
},
},
{
.callback = set_bf_sort,
.ident = "HP ProLiant BL30p G1",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "HP"),
DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant BL30p G1"),
},
},
{
.callback = set_bf_sort,
.ident = "HP ProLiant BL25p G1",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "HP"),
DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant BL25p G1"),
},
},
{
.callback = set_bf_sort,
.ident = "HP ProLiant BL35p G1",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "HP"),
DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant BL35p G1"),
},
},
{
.callback = set_bf_sort,
.ident = "HP ProLiant BL45p G1",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "HP"),
DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant BL45p G1"),
},
},
{
.callback = set_bf_sort,
.ident = "HP ProLiant BL45p G2",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "HP"),
DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant BL45p G2"),
},
},
{
.callback = set_bf_sort,
.ident = "HP ProLiant BL460c G1",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "HP"),
DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant BL460c G1"),
},
},
{
.callback = set_bf_sort,
.ident = "HP ProLiant BL465c G1",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "HP"),
DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant BL465c G1"),
},
},
{
.callback = set_bf_sort,
.ident = "HP ProLiant BL480c G1",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "HP"),
DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant BL480c G1"),
},
},
{
.callback = set_bf_sort,
.ident = "HP ProLiant BL685c G1",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "HP"),
DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant BL685c G1"),
},
},
{
.callback = set_bf_sort,
.ident = "HP ProLiant DL360",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "HP"),
DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL360"),
},
},
{
.callback = set_bf_sort,
.ident = "HP ProLiant DL380",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "HP"),
DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL380"),
},
},
#ifdef __i386__
{
.callback = assign_all_busses,
.ident = "Compaq EVO N800c",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Compaq"),
DMI_MATCH(DMI_PRODUCT_NAME, "EVO N800c"),
},
},
#endif
{
.callback = set_bf_sort,
.ident = "HP ProLiant DL385 G2",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "HP"),
DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL385 G2"),
},
},
{
.callback = set_bf_sort,
.ident = "HP ProLiant DL585 G2",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "HP"),
DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL585 G2"),
},
},
{
.callback = set_scan_all,
.ident = "Stratus/NEC ftServer",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Stratus"),
DMI_MATCH(DMI_PRODUCT_NAME, "ftServer"),
},
},
{
.callback = set_scan_all,
.ident = "Stratus/NEC ftServer",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "NEC"),
DMI_MATCH(DMI_PRODUCT_NAME, "Express5800/R32"),
},
},
{
.callback = set_scan_all,
.ident = "Stratus/NEC ftServer",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "NEC"),
DMI_MATCH(DMI_PRODUCT_NAME, "Express5800/R31"),
},
},
[PATCH] PCI: PCI/Cardbus cards hidden, needs pci=assign-busses to fix "In some cases, especially on modern laptops with a lot of PCI and cardbus bridges, we're unable to assign correct secondary/subordinate bus numbers to all cardbus bridges due to BIOS limitations unless we are using "pci=assign-busses" boot option." -- Ivan Kokshaysky (from a patch comment) Without it, Cardbus cards inserted are never seen by PCI because the parent PCI-PCI Bridge of the Cardbus bridge will not pass and translate Type 1 PCI configuration cycles correctly and the system will fail to find and initialise the PCI devices in the system. Reference: PCI-PCI Bridges: PCI Configuration Cycles and PCI Bus Numbering: http://www.science.unitn.it/~fiorella/guidelinux/tlk/node72.html The reason for this is that: ``All PCI busses located behind a PCI-PCI bridge must reside between the secondary bus number and the subordinate bus number (inclusive).'' "pci=assign-busses" makes pcibios_assign_all_busses return 1 and this turns on PCI renumbering during PCI probing. Alan suggested to use DMI automatically set assign-busses on problem systems. The only question for me was where to put it. I put it directly before scanning PCI bus into pcibios_scan_root() because it's called from legacy, acpi and numa and so it can be one place for all systems and configurations which may need it. AMD64 Laptops are also affected and fixed by assign-busses, and the code is also incuded from arch/x86_64/pci/ that place will also work for x86_64 kernels, I only ifdef'-ed the x86-only Laptop in this example. Affected and known or assumed to be fixed with it are (found by googling): * ASUS Z71V and L3s * Samsung X20 * Compaq R3140us and all Compaq R3000 series laptops with TI1620 Controller, also Compaq R4000 series (from a kernel.org bugreport) * HP zv5000z (AMD64 3700+, known that fixup_parent_subordinate_busnr fixes it) * HP zv5200z * IBM ThinkPad 240 * An IBM ThinkPad (1.8 GHz Pentium M) debugged by Pavel Machek gives the correspondig message which detects the possible problem. * MSI S260 / Medion SIM 2100 MD 95600 The patch also expands the "try pci=assign-busses" warning so testers will help us to update the DMI table. Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Russell King <rmk@arm.linux.org.uk> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2006-02-18 17:36:55 +08:00
{}
};
void __init dmi_check_pciprobe(void)
{
dmi_check_system(pciprobe_dmi_table);
}
void pcibios_scan_root(int busnum)
{
struct pci_bus *bus;
struct pci_sysdata *sd;
LIST_HEAD(resources);
sd = kzalloc(sizeof(*sd), GFP_KERNEL);
if (!sd) {
printk(KERN_ERR "PCI: OOM, skipping PCI bus %02x\n", busnum);
return;
}
sd->node = x86_pci_root_bus_node(busnum);
x86_pci_root_bus_resources(busnum, &resources);
printk(KERN_DEBUG "PCI: Probing PCI hardware (bus %02x)\n", busnum);
bus = pci_scan_root_bus(NULL, busnum, &pci_root_ops, sd, &resources);
if (!bus) {
pci_free_resource_list(&resources);
kfree(sd);
PCI: Assign resources before drivers claim devices (pci_scan_root_bus()) Previously, pci_scan_root_bus() created a root PCI bus, enumerated the devices on it, and called pci_bus_add_devices(), which made the devices available for drivers to claim them. Most callers assigned resources to devices after pci_scan_root_bus() returns, which may be after drivers have claimed the devices. This is incorrect; the PCI core should not change device resources while a driver is managing the device. Remove pci_bus_add_devices() from pci_scan_root_bus() and do it after any resource assignment in the callers. Note that ARM's pci_common_init_dev() already called pci_bus_add_devices() after pci_scan_root_bus(), so we only need to remove the first call: pci_common_init_dev pcibios_init_hw pci_scan_root_bus pci_bus_add_devices # first call pci_bus_assign_resources pci_bus_add_devices # second call [bhelgaas: changelog, drop "root_bus" var in alpha common_init_pci(), return failure earlier in mn10300, add "return" in x86 pcibios_scan_root(), return early if xtensa platform_pcibios_fixup() fails] Signed-off-by: Yijing Wang <wangyijing@huawei.com> Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> CC: Richard Henderson <rth@twiddle.net> CC: Ivan Kokshaysky <ink@jurassic.park.msu.ru> CC: Matt Turner <mattst88@gmail.com> CC: David Howells <dhowells@redhat.com> CC: Tony Luck <tony.luck@intel.com> CC: Michal Simek <monstr@monstr.eu> CC: Ralf Baechle <ralf@linux-mips.org> CC: Koichi Yasutake <yasutake.koichi@jp.panasonic.com> CC: Sebastian Ott <sebott@linux.vnet.ibm.com> CC: "David S. Miller" <davem@davemloft.net> CC: Chris Metcalf <cmetcalf@ezchip.com> CC: Chris Zankel <chris@zankel.net> CC: Max Filippov <jcmvbkbc@gmail.com> CC: Thomas Gleixner <tglx@linutronix.de>
2015-03-16 11:18:56 +08:00
return;
}
PCI: Assign resources before drivers claim devices (pci_scan_root_bus()) Previously, pci_scan_root_bus() created a root PCI bus, enumerated the devices on it, and called pci_bus_add_devices(), which made the devices available for drivers to claim them. Most callers assigned resources to devices after pci_scan_root_bus() returns, which may be after drivers have claimed the devices. This is incorrect; the PCI core should not change device resources while a driver is managing the device. Remove pci_bus_add_devices() from pci_scan_root_bus() and do it after any resource assignment in the callers. Note that ARM's pci_common_init_dev() already called pci_bus_add_devices() after pci_scan_root_bus(), so we only need to remove the first call: pci_common_init_dev pcibios_init_hw pci_scan_root_bus pci_bus_add_devices # first call pci_bus_assign_resources pci_bus_add_devices # second call [bhelgaas: changelog, drop "root_bus" var in alpha common_init_pci(), return failure earlier in mn10300, add "return" in x86 pcibios_scan_root(), return early if xtensa platform_pcibios_fixup() fails] Signed-off-by: Yijing Wang <wangyijing@huawei.com> Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> CC: Richard Henderson <rth@twiddle.net> CC: Ivan Kokshaysky <ink@jurassic.park.msu.ru> CC: Matt Turner <mattst88@gmail.com> CC: David Howells <dhowells@redhat.com> CC: Tony Luck <tony.luck@intel.com> CC: Michal Simek <monstr@monstr.eu> CC: Ralf Baechle <ralf@linux-mips.org> CC: Koichi Yasutake <yasutake.koichi@jp.panasonic.com> CC: Sebastian Ott <sebott@linux.vnet.ibm.com> CC: "David S. Miller" <davem@davemloft.net> CC: Chris Metcalf <cmetcalf@ezchip.com> CC: Chris Zankel <chris@zankel.net> CC: Max Filippov <jcmvbkbc@gmail.com> CC: Thomas Gleixner <tglx@linutronix.de>
2015-03-16 11:18:56 +08:00
pci_bus_add_devices(bus);
}
void __init pcibios_set_cache_line_size(void)
{
struct cpuinfo_x86 *c = &boot_cpu_data;
/*
* Set PCI cacheline size to that of the CPU if the CPU has reported it.
* (For older CPUs that don't support cpuid, we se it to 32 bytes
* It's also good for 386/486s (which actually have 16)
* as quite a few PCI devices do not support smaller values.
*/
if (c->x86_clflush_size > 0) {
pci_dfl_cache_line_size = c->x86_clflush_size >> 2;
printk(KERN_DEBUG "PCI: pci_cache_line_size set to %d bytes\n",
pci_dfl_cache_line_size << 2);
} else {
pci_dfl_cache_line_size = 32 >> 2;
printk(KERN_DEBUG "PCI: Unknown cacheline size. Setting to 32 bytes\n");
}
}
int __init pcibios_init(void)
{
if (!raw_pci_ops) {
printk(KERN_WARNING "PCI: System does not support PCI\n");
return 0;
}
pcibios_set_cache_line_size();
pcibios_resource_survey();
PCI: optionally sort device lists breadth-first Problem: New Dell PowerEdge servers have 2 embedded ethernet ports, which are labeled NIC1 and NIC2 on the chassis, in the BIOS setup screens, and in the printed documentation. Assuming no other add-in ethernet ports in the system, Linux 2.4 kernels name these eth0 and eth1 respectively. Many people have come to expect this naming. Linux 2.6 kernels name these eth1 and eth0 respectively (backwards from expectations). I also have reports that various Sun and HP servers have similar behavior. Root cause: Linux 2.4 kernels walk the pci_devices list, which happens to be sorted in breadth-first order (or pcbios_find_device order on i386, which most often is breadth-first also). 2.6 kernels have both the pci_devices list and the pci_bus_type.klist_devices list, the latter is what is walked at driver load time to match the pci_id tables; this klist happens to be in depth-first order. On systems where, for physical routing reasons, NIC1 appears on a lower bus number than NIC2, but NIC2's bridge is discovered first in the depth-first ordering, NIC2 will be discovered before NIC1. If the list were sorted breadth-first, NIC1 would be discovered before NIC2. A PowerEdge 1955 system has the following topology which easily exhibits the difference between depth-first and breadth-first device lists. -[0000:00]-+-00.0 Intel Corporation 5000P Chipset Memory Controller Hub +-02.0-[0000:03-08]--+-00.0-[0000:04-07]--+-00.0-[0000:05-06]----00.0-[0000:06]----00.0 Broadcom Corporation NetXtreme II BCM5708S Gigabit Ethernet (labeled NIC2, 2.4 kernel name eth1, 2.6 kernel name eth0) +-1c.0-[0000:01-02]----00.0-[0000:02]----00.0 Broadcom Corporation NetXtreme II BCM5708S Gigabit Ethernet (labeled NIC1, 2.4 kernel name eth0, 2.6 kernel name eth1) Other factors, such as device driver load order and the presence of PCI slots at various points in the bus hierarchy further complicate this problem; I'm not trying to solve those here, just restore the device order, and thus basic behavior, that 2.4 kernels had. Solution: The solution can come in multiple steps. Suggested fix #1: kernel Patch below optionally sorts the two device lists into breadth-first ordering to maintain compatibility with 2.4 kernels. It adds two new command line options: pci=bfsort pci=nobfsort to force the sort order, or not, as you wish. It also adds DMI checks for the specific Dell systems which exhibit "backwards" ordering, to make them "right". Suggested fix #2: udev rules from userland Many people also have the expectation that embedded NICs are always discovered before add-in NICs (which this patch does not try to do). Using the PCI IRQ Routing Table provided by system BIOS, it's easy to determine which PCI devices are embedded, or if add-in, which PCI slot they're in. I'm working on a tool that would allow udev to name ethernet devices in ascending embedded, slot 1 .. slot N order, subsort by PCI bus/dev/fn breadth-first. It'll be possible to use it independent of udev as well for those distributions that don't use udev in their installers. Suggested fix #3: system board routing rules One can constrain the system board layout to put NIC1 ahead of NIC2 regardless of breadth-first or depth-first discovery order. This adds a significant level of complexity to board routing, and may not be possible in all instances (witness the above systems from several major manufacturers). I don't want to encourage this particular train of thought too far, at the expense of not doing #1 or #2 above. Feedback appreciated. Patch tested on a Dell PowerEdge 1955 blade with 2.6.18. You'll also note I took some liberty and temporarily break the klist abstraction to simplify and speed up the sort algorithm. I think that's both safe and appropriate in this instance. Signed-off-by: Matt Domsch <Matt_Domsch@dell.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2006-09-30 04:23:23 +08:00
if (pci_bf_sort >= pci_force_bf)
pci_sort_breadthfirst();
return 0;
}
char *__init pcibios_setup(char *str)
{
if (!strcmp(str, "off")) {
pci_probe = 0;
return NULL;
PCI: optionally sort device lists breadth-first Problem: New Dell PowerEdge servers have 2 embedded ethernet ports, which are labeled NIC1 and NIC2 on the chassis, in the BIOS setup screens, and in the printed documentation. Assuming no other add-in ethernet ports in the system, Linux 2.4 kernels name these eth0 and eth1 respectively. Many people have come to expect this naming. Linux 2.6 kernels name these eth1 and eth0 respectively (backwards from expectations). I also have reports that various Sun and HP servers have similar behavior. Root cause: Linux 2.4 kernels walk the pci_devices list, which happens to be sorted in breadth-first order (or pcbios_find_device order on i386, which most often is breadth-first also). 2.6 kernels have both the pci_devices list and the pci_bus_type.klist_devices list, the latter is what is walked at driver load time to match the pci_id tables; this klist happens to be in depth-first order. On systems where, for physical routing reasons, NIC1 appears on a lower bus number than NIC2, but NIC2's bridge is discovered first in the depth-first ordering, NIC2 will be discovered before NIC1. If the list were sorted breadth-first, NIC1 would be discovered before NIC2. A PowerEdge 1955 system has the following topology which easily exhibits the difference between depth-first and breadth-first device lists. -[0000:00]-+-00.0 Intel Corporation 5000P Chipset Memory Controller Hub +-02.0-[0000:03-08]--+-00.0-[0000:04-07]--+-00.0-[0000:05-06]----00.0-[0000:06]----00.0 Broadcom Corporation NetXtreme II BCM5708S Gigabit Ethernet (labeled NIC2, 2.4 kernel name eth1, 2.6 kernel name eth0) +-1c.0-[0000:01-02]----00.0-[0000:02]----00.0 Broadcom Corporation NetXtreme II BCM5708S Gigabit Ethernet (labeled NIC1, 2.4 kernel name eth0, 2.6 kernel name eth1) Other factors, such as device driver load order and the presence of PCI slots at various points in the bus hierarchy further complicate this problem; I'm not trying to solve those here, just restore the device order, and thus basic behavior, that 2.4 kernels had. Solution: The solution can come in multiple steps. Suggested fix #1: kernel Patch below optionally sorts the two device lists into breadth-first ordering to maintain compatibility with 2.4 kernels. It adds two new command line options: pci=bfsort pci=nobfsort to force the sort order, or not, as you wish. It also adds DMI checks for the specific Dell systems which exhibit "backwards" ordering, to make them "right". Suggested fix #2: udev rules from userland Many people also have the expectation that embedded NICs are always discovered before add-in NICs (which this patch does not try to do). Using the PCI IRQ Routing Table provided by system BIOS, it's easy to determine which PCI devices are embedded, or if add-in, which PCI slot they're in. I'm working on a tool that would allow udev to name ethernet devices in ascending embedded, slot 1 .. slot N order, subsort by PCI bus/dev/fn breadth-first. It'll be possible to use it independent of udev as well for those distributions that don't use udev in their installers. Suggested fix #3: system board routing rules One can constrain the system board layout to put NIC1 ahead of NIC2 regardless of breadth-first or depth-first discovery order. This adds a significant level of complexity to board routing, and may not be possible in all instances (witness the above systems from several major manufacturers). I don't want to encourage this particular train of thought too far, at the expense of not doing #1 or #2 above. Feedback appreciated. Patch tested on a Dell PowerEdge 1955 blade with 2.6.18. You'll also note I took some liberty and temporarily break the klist abstraction to simplify and speed up the sort algorithm. I think that's both safe and appropriate in this instance. Signed-off-by: Matt Domsch <Matt_Domsch@dell.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2006-09-30 04:23:23 +08:00
} else if (!strcmp(str, "bfsort")) {
pci_bf_sort = pci_force_bf;
return NULL;
} else if (!strcmp(str, "nobfsort")) {
pci_bf_sort = pci_force_nobf;
return NULL;
}
#ifdef CONFIG_PCI_BIOS
else if (!strcmp(str, "bios")) {
pci_probe = PCI_PROBE_BIOS;
return NULL;
} else if (!strcmp(str, "nobios")) {
pci_probe &= ~PCI_PROBE_BIOS;
return NULL;
} else if (!strcmp(str, "biosirq")) {
pci_probe |= PCI_BIOS_IRQ_SCAN;
return NULL;
} else if (!strncmp(str, "pirqaddr=", 9)) {
pirq_table_addr = simple_strtoul(str+9, NULL, 0);
return NULL;
}
#endif
#ifdef CONFIG_PCI_DIRECT
else if (!strcmp(str, "conf1")) {
pci_probe = PCI_PROBE_CONF1 | PCI_NO_CHECKS;
return NULL;
}
else if (!strcmp(str, "conf2")) {
pci_probe = PCI_PROBE_CONF2 | PCI_NO_CHECKS;
return NULL;
}
#endif
#ifdef CONFIG_PCI_MMCONFIG
else if (!strcmp(str, "nommconf")) {
pci_probe &= ~PCI_PROBE_MMCONF;
return NULL;
}
else if (!strcmp(str, "check_enable_amd_mmconf")) {
pci_probe |= PCI_CHECK_ENABLE_AMD_MMCONF;
return NULL;
}
#endif
else if (!strcmp(str, "noacpi")) {
acpi_noirq_set();
return NULL;
}
else if (!strcmp(str, "noearly")) {
pci_probe |= PCI_PROBE_NOEARLY;
return NULL;
}
else if (!strcmp(str, "usepirqmask")) {
pci_probe |= PCI_USE_PIRQ_MASK;
return NULL;
} else if (!strncmp(str, "irqmask=", 8)) {
pcibios_irq_mask = simple_strtol(str+8, NULL, 0);
return NULL;
} else if (!strncmp(str, "lastbus=", 8)) {
pcibios_last_bus = simple_strtol(str+8, NULL, 0);
return NULL;
} else if (!strcmp(str, "rom")) {
pci_probe |= PCI_ASSIGN_ROMS;
return NULL;
PCI: boot parameter to avoid expansion ROM memory allocation Contention for scarce PCI memory resources has been growing due to an increasing number of PCI slots in large multi-node systems. The kernel currently attempts by default to allocate memory for all PCI expansion ROMs so there has also been an increasing number of PCI memory allocation failures seen on these systems. This occurs because the BIOS either (1) provides insufficient PCI memory resource for all the expansion ROMs or (2) provides adequate PCI memory resource for expansion ROMs but provides the space in kernel unexpected BIOS assigned P2P non-prefetch windows. The resulting PCI memory allocation failures may be benign when related to memory requests for expansion ROMs themselves but in some cases they can occur when attempting to allocate space for more critical BARs. This can happen when a successful expansion ROM allocation request consumes memory resource that was intended for a non-ROM BAR. We have seen this happen during PCI hotplug of an adapter that contains a P2P bridge where successful memory allocation for an expansion ROM BAR on device behind the bridge consumed memory that was intended for a non-ROM BAR on the P2P bridge. In all cases the allocation failure messages can be very confusing for users. This patch provides a new 'pci=norom' kernel boot parameter that can be used to disable the default PCI expansion ROM memory resource allocation. This provides a way to avoid the above described issues on systems that do not contain PCI devices for which drivers or user-level applications depend on the default PCI expansion ROM memory resource allocation behavior. Signed-off-by: Gary Hade <garyhade@us.ibm.com> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2008-05-13 04:57:46 +08:00
} else if (!strcmp(str, "norom")) {
pci_probe |= PCI_NOASSIGN_ROMS;
return NULL;
} else if (!strcmp(str, "nobar")) {
pci_probe |= PCI_NOASSIGN_BARS;
return NULL;
} 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, "nocrs")) {
pci_probe |= PCI_ROOT_NO_CRS;
return NULL;
} else if (!strcmp(str, "earlydump")) {
pci_early_dump_regs = 1;
return NULL;
} else if (!strcmp(str, "routeirq")) {
pci_routeirq = 1;
return NULL;
} else if (!strcmp(str, "skip_isa_align")) {
pci_probe |= PCI_CAN_SKIP_ISA_ALIGN;
return NULL;
} else if (!strcmp(str, "noioapicquirk")) {
noioapicquirk = 1;
return NULL;
} else if (!strcmp(str, "ioapicreroute")) {
if (noioapicreroute != -1)
noioapicreroute = 0;
return NULL;
} else if (!strcmp(str, "noioapicreroute")) {
if (noioapicreroute != -1)
noioapicreroute = 1;
return NULL;
}
return str;
}
unsigned int pcibios_assign_all_busses(void)
{
return (pci_probe & PCI_ASSIGN_ALL_BUSSES) ? 1 : 0;
}
int pcibios_add_device(struct pci_dev *dev)
{
struct setup_data *data;
struct pci_setup_rom *rom;
u64 pa_data;
pa_data = boot_params.hdr.setup_data;
while (pa_data) {
data = ioremap(pa_data, sizeof(*rom));
if (!data)
return -ENOMEM;
if (data->type == SETUP_PCI) {
rom = (struct pci_setup_rom *)data;
if ((pci_domain_nr(dev->bus) == rom->segment) &&
(dev->bus->number == rom->bus) &&
(PCI_SLOT(dev->devfn) == rom->device) &&
(PCI_FUNC(dev->devfn) == rom->function) &&
(dev->vendor == rom->vendor) &&
(dev->device == rom->devid)) {
dev->rom = pa_data +
offsetof(struct pci_setup_rom, romdata);
dev->romlen = rom->pcilen;
}
}
pa_data = data->next;
iounmap(data);
}
return 0;
}
int pcibios_enable_device(struct pci_dev *dev, int mask)
{
int err;
if ((err = pci_enable_resources(dev, mask)) < 0)
return err;
if (!pci_dev_msi_enabled(dev))
return pcibios_enable_irq(dev);
return 0;
}
void pcibios_disable_device (struct pci_dev *dev)
{
if (!pci_dev_msi_enabled(dev) && pcibios_disable_irq)
pcibios_disable_irq(dev);
}
int pci_ext_cfg_avail(void)
{
if (raw_pci_ext_ops)
return 1;
else
return 0;
}