2005-04-16 18:20:36 -04:00
|
|
|
/*
|
|
|
|
* Low-Level PCI Access for i386 machines.
|
|
|
|
*
|
|
|
|
* (c) 1999 Martin Mares <mj@ucw.cz>
|
|
|
|
*/
|
|
|
|
|
|
|
|
#undef DEBUG
|
|
|
|
|
|
|
|
#ifdef DEBUG
|
|
|
|
#define DBG(x...) printk(x)
|
|
|
|
#else
|
|
|
|
#define DBG(x...)
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#define PCI_PROBE_BIOS 0x0001
|
|
|
|
#define PCI_PROBE_CONF1 0x0002
|
|
|
|
#define PCI_PROBE_CONF2 0x0004
|
|
|
|
#define PCI_PROBE_MMCONF 0x0008
|
2006-09-19 11:15:22 -04:00
|
|
|
#define PCI_PROBE_MASK 0x000f
|
2006-09-26 04:52:41 -04:00
|
|
|
#define PCI_PROBE_NOEARLY 0x0010
|
2005-04-16 18:20:36 -04:00
|
|
|
|
|
|
|
#define PCI_NO_SORT 0x0100
|
|
|
|
#define PCI_BIOS_SORT 0x0200
|
|
|
|
#define PCI_NO_CHECKS 0x0400
|
|
|
|
#define PCI_USE_PIRQ_MASK 0x0800
|
|
|
|
#define PCI_ASSIGN_ROMS 0x1000
|
|
|
|
#define PCI_BIOS_IRQ_SCAN 0x2000
|
|
|
|
#define PCI_ASSIGN_ALL_BUSSES 0x4000
|
2007-10-03 18:56:14 -04:00
|
|
|
#define PCI_CAN_SKIP_ISA_ALIGN 0x8000
|
2007-10-03 18:56:51 -04:00
|
|
|
#define PCI_USE__CRS 0x10000
|
2005-04-16 18:20:36 -04:00
|
|
|
|
|
|
|
extern unsigned int pci_probe;
|
2005-03-21 23:20:42 -05:00
|
|
|
extern unsigned long pirq_table_addr;
|
2005-04-16 18:20:36 -04:00
|
|
|
|
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>
2006-09-29 16:23:23 -04:00
|
|
|
enum pci_bf_sort_state {
|
|
|
|
pci_bf_sort_default,
|
|
|
|
pci_force_nobf,
|
|
|
|
pci_force_bf,
|
|
|
|
pci_dmi_bf,
|
|
|
|
};
|
|
|
|
|
2005-04-16 18:20:36 -04:00
|
|
|
/* pci-i386.c */
|
|
|
|
|
|
|
|
extern unsigned int pcibios_max_latency;
|
|
|
|
|
|
|
|
void pcibios_resource_survey(void);
|
|
|
|
int pcibios_enable_resources(struct pci_dev *, int);
|
|
|
|
|
|
|
|
/* pci-pc.c */
|
|
|
|
|
|
|
|
extern int pcibios_last_bus;
|
|
|
|
extern struct pci_bus *pci_root_bus;
|
|
|
|
extern struct pci_ops pci_root_ops;
|
|
|
|
|
|
|
|
/* pci-irq.c */
|
|
|
|
|
|
|
|
struct irq_info {
|
|
|
|
u8 bus, devfn; /* Bus, device and function */
|
|
|
|
struct {
|
|
|
|
u8 link; /* IRQ line ID, chipset dependent, 0=not routed */
|
|
|
|
u16 bitmap; /* Available IRQs */
|
|
|
|
} __attribute__((packed)) irq[4];
|
|
|
|
u8 slot; /* Slot number, 0=onboard */
|
|
|
|
u8 rfu;
|
|
|
|
} __attribute__((packed));
|
|
|
|
|
|
|
|
struct irq_routing_table {
|
|
|
|
u32 signature; /* PIRQ_SIGNATURE should be here */
|
|
|
|
u16 version; /* PIRQ_VERSION */
|
|
|
|
u16 size; /* Table size in bytes */
|
|
|
|
u8 rtr_bus, rtr_devfn; /* Where the interrupt router lies */
|
|
|
|
u16 exclusive_irqs; /* IRQs devoted exclusively to PCI usage */
|
|
|
|
u16 rtr_vendor, rtr_device; /* Vendor and device ID of interrupt router */
|
|
|
|
u32 miniport_data; /* Crap */
|
|
|
|
u8 rfu[11];
|
|
|
|
u8 checksum; /* Modulo 256 checksum must give zero */
|
|
|
|
struct irq_info slots[0];
|
|
|
|
} __attribute__((packed));
|
|
|
|
|
|
|
|
extern unsigned int pcibios_irq_mask;
|
|
|
|
|
|
|
|
extern int pcibios_scanned;
|
|
|
|
extern spinlock_t pci_config_lock;
|
|
|
|
|
|
|
|
extern int (*pcibios_enable_irq)(struct pci_dev *dev);
|
2005-07-27 23:02:00 -04:00
|
|
|
extern void (*pcibios_disable_irq)(struct pci_dev *dev);
|
2005-12-13 01:17:10 -05:00
|
|
|
|
2008-02-10 09:45:28 -05:00
|
|
|
struct pci_raw_ops {
|
|
|
|
int (*read)(unsigned int domain, unsigned int bus, unsigned int devfn,
|
|
|
|
int reg, int len, u32 *val);
|
|
|
|
int (*write)(unsigned int domain, unsigned int bus, unsigned int devfn,
|
|
|
|
int reg, int len, u32 val);
|
|
|
|
};
|
|
|
|
|
|
|
|
extern struct pci_raw_ops *raw_pci_ops;
|
|
|
|
extern struct pci_raw_ops *raw_pci_ext_ops;
|
|
|
|
|
|
|
|
extern struct pci_raw_ops pci_direct_conf1;
|
2005-12-13 01:17:10 -05:00
|
|
|
|
2006-09-26 04:52:40 -04:00
|
|
|
extern int pci_direct_probe(void);
|
|
|
|
extern void pci_direct_init(int type);
|
2006-03-23 17:35:12 -05:00
|
|
|
extern void pci_pcbios_init(void);
|
2006-09-26 04:52:40 -04:00
|
|
|
extern void pci_mmcfg_init(int type);
|
2006-06-28 12:54:33 -04:00
|
|
|
extern void pcibios_sort(void);
|
2006-09-26 04:52:40 -04:00
|
|
|
|
2007-02-13 07:26:20 -05:00
|
|
|
/* pci-mmconfig.c */
|
|
|
|
|
2007-02-13 07:26:20 -05:00
|
|
|
extern int __init pci_mmcfg_arch_init(void);
|
2007-08-10 16:30:59 -04:00
|
|
|
|
|
|
|
/*
|
|
|
|
* AMD Fam10h CPUs are buggy, and cannot access MMIO config space
|
|
|
|
* on their northbrige except through the * %eax register. As such, you MUST
|
|
|
|
* NOT use normal IOMEM accesses, you need to only use the magic mmio-config
|
|
|
|
* accessor functions.
|
|
|
|
* In fact just use pci_config_*, nothing else please.
|
|
|
|
*/
|
|
|
|
static inline unsigned char mmio_config_readb(void __iomem *pos)
|
|
|
|
{
|
|
|
|
u8 val;
|
|
|
|
asm volatile("movb (%1),%%al" : "=a" (val) : "r" (pos));
|
|
|
|
return val;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline unsigned short mmio_config_readw(void __iomem *pos)
|
|
|
|
{
|
|
|
|
u16 val;
|
|
|
|
asm volatile("movw (%1),%%ax" : "=a" (val) : "r" (pos));
|
|
|
|
return val;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline unsigned int mmio_config_readl(void __iomem *pos)
|
|
|
|
{
|
|
|
|
u32 val;
|
|
|
|
asm volatile("movl (%1),%%eax" : "=a" (val) : "r" (pos));
|
|
|
|
return val;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void mmio_config_writeb(void __iomem *pos, u8 val)
|
|
|
|
{
|
|
|
|
asm volatile("movb %%al,(%1)" :: "a" (val), "r" (pos) : "memory");
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void mmio_config_writew(void __iomem *pos, u16 val)
|
|
|
|
{
|
|
|
|
asm volatile("movw %%ax,(%1)" :: "a" (val), "r" (pos) : "memory");
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void mmio_config_writel(void __iomem *pos, u32 val)
|
|
|
|
{
|
|
|
|
asm volatile("movl %%eax,(%1)" :: "a" (val), "r" (pos) : "memory");
|
|
|
|
}
|