linux_dsm_epyc7002/arch/powerpc/include/asm/pci-bridge.h
Gavin Shan 1e38b71401 powerpc/eeh: Fix crash on converting OF node to edev
The kernel crash was reported by Alexy. He was testing some feature
with private kernel, in which Alexy added some code in pci_pm_reset()
to read the CSR after writting it. The bug could be reproduced on
Fiber Channel card (Fibre Channel: Emulex Corporation Saturn-X:
LightPulse Fibre Channel Host Adapter (rev 03)) by the following
commands.

	# echo 1 > /sys/devices/pci0004:01/0004:01:00.0/reset
	# rmmod lpfc
	# modprobe lpfc

The history behind the test case is that those additional config
space reading operations in pci_pm_reset() would cause EEH error,
but we didn't detect EEH error until "modprobe lpfc". For the case,
all the PCI devices on PCI bus (0004:01) were removed and added after
PE reset. Then the EEH devices would be figured out again based on
the OF nodes. Unfortunately, there were some child OF nodes under
PCI device (0004:01:00.0), but they didn't have attached PCI_DN since
they're invisible from PCI domain. However, we were still trying to
convert OF node to EEH device without checking on the attached PCI_DN.
Eventually, it caused the kernel crash as follows:

Unable to handle kernel paging request for data at address 0x00000030
Faulting instruction address: 0xc00000000004d888
cpu 0x0: Vector: 300 (Data Access) at [c000000fc797b950]
    pc: c00000000004d888: .eeh_add_device_tree_early+0x78/0x140
    lr: c00000000004d880: .eeh_add_device_tree_early+0x70/0x140
    sp: c000000fc797bbd0
   msr: 8000000000009032
   dar: 30
 dsisr: 40000000
  current = 0xc000000fc78d9f70
  paca    = 0xc00000000edb0000   softe: 0        irq_happened: 0x00
    pid   = 2951, comm = eehd
enter ? for help
[c000000fc797bc50] c00000000004d848 .eeh_add_device_tree_early+0x38/0x140
[c000000fc797bcd0] c00000000004d848 .eeh_add_device_tree_early+0x38/0x140
[c000000fc797bd50] c000000000051b54 .pcibios_add_pci_devices+0x34/0x190
[c000000fc797bde0] c00000000004fb10 .eeh_reset_device+0x100/0x160
[c000000fc797be70] c0000000000502dc .eeh_handle_event+0x19c/0x300
[c000000fc797bf00] c000000000050570 .eeh_event_handler+0x130/0x1a0
[c000000fc797bf90] c000000000020138 .kernel_thread+0x54/0x70

The patch changes of_node_to_eeh_dev() and just returns NULL if the
passed OF node doesn't have attached PCI_DN.

Cc: stable@vger.kernel.org
Reported-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Gavin Shan <shangw@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2012-09-18 15:32:51 +10:00

253 lines
7.3 KiB
C

#ifndef _ASM_POWERPC_PCI_BRIDGE_H
#define _ASM_POWERPC_PCI_BRIDGE_H
#ifdef __KERNEL__
/*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <linux/pci.h>
#include <linux/list.h>
#include <linux/ioport.h>
#include <asm-generic/pci-bridge.h>
struct device_node;
/*
* Structure of a PCI controller (host bridge)
*/
struct pci_controller {
struct pci_bus *bus;
char is_dynamic;
#ifdef CONFIG_PPC64
int node;
#endif
struct device_node *dn;
struct list_head list_node;
struct device *parent;
int first_busno;
int last_busno;
int self_busno;
struct resource busn;
void __iomem *io_base_virt;
#ifdef CONFIG_PPC64
void *io_base_alloc;
#endif
resource_size_t io_base_phys;
resource_size_t pci_io_size;
/* Some machines (PReP) have a non 1:1 mapping of
* the PCI memory space in the CPU bus space
*/
resource_size_t pci_mem_offset;
/* Some machines have a special region to forward the ISA
* "memory" cycles such as VGA memory regions. Left to 0
* if unsupported
*/
resource_size_t isa_mem_phys;
resource_size_t isa_mem_size;
struct pci_ops *ops;
unsigned int __iomem *cfg_addr;
void __iomem *cfg_data;
/*
* Used for variants of PCI indirect handling and possible quirks:
* SET_CFG_TYPE - used on 4xx or any PHB that does explicit type0/1
* EXT_REG - provides access to PCI-e extended registers
* SURPRESS_PRIMARY_BUS - we suppress the setting of PCI_PRIMARY_BUS
* on Freescale PCI-e controllers since they used the PCI_PRIMARY_BUS
* to determine which bus number to match on when generating type0
* config cycles
* NO_PCIE_LINK - the Freescale PCI-e controllers have issues with
* hanging if we don't have link and try to do config cycles to
* anything but the PHB. Only allow talking to the PHB if this is
* set.
* BIG_ENDIAN - cfg_addr is a big endian register
* BROKEN_MRM - the 440EPx/GRx chips have an errata that causes hangs on
* the PLB4. Effectively disable MRM commands by setting this.
*/
#define PPC_INDIRECT_TYPE_SET_CFG_TYPE 0x00000001
#define PPC_INDIRECT_TYPE_EXT_REG 0x00000002
#define PPC_INDIRECT_TYPE_SURPRESS_PRIMARY_BUS 0x00000004
#define PPC_INDIRECT_TYPE_NO_PCIE_LINK 0x00000008
#define PPC_INDIRECT_TYPE_BIG_ENDIAN 0x00000010
#define PPC_INDIRECT_TYPE_BROKEN_MRM 0x00000020
u32 indirect_type;
/* Currently, we limit ourselves to 1 IO range and 3 mem
* ranges since the common pci_bus structure can't handle more
*/
struct resource io_resource;
struct resource mem_resources[3];
int global_number; /* PCI domain number */
resource_size_t dma_window_base_cur;
resource_size_t dma_window_size;
#ifdef CONFIG_PPC64
unsigned long buid;
void *private_data;
#endif /* CONFIG_PPC64 */
};
/* These are used for config access before all the PCI probing
has been done. */
extern int early_read_config_byte(struct pci_controller *hose, int bus,
int dev_fn, int where, u8 *val);
extern int early_read_config_word(struct pci_controller *hose, int bus,
int dev_fn, int where, u16 *val);
extern int early_read_config_dword(struct pci_controller *hose, int bus,
int dev_fn, int where, u32 *val);
extern int early_write_config_byte(struct pci_controller *hose, int bus,
int dev_fn, int where, u8 val);
extern int early_write_config_word(struct pci_controller *hose, int bus,
int dev_fn, int where, u16 val);
extern int early_write_config_dword(struct pci_controller *hose, int bus,
int dev_fn, int where, u32 val);
extern int early_find_capability(struct pci_controller *hose, int bus,
int dev_fn, int cap);
extern void setup_indirect_pci(struct pci_controller* hose,
resource_size_t cfg_addr,
resource_size_t cfg_data, u32 flags);
static inline struct pci_controller *pci_bus_to_host(const struct pci_bus *bus)
{
return bus->sysdata;
}
#ifndef CONFIG_PPC64
extern int pci_device_from_OF_node(struct device_node *node,
u8 *bus, u8 *devfn);
extern void pci_create_OF_bus_map(void);
static inline int isa_vaddr_is_ioport(void __iomem *address)
{
/* No specific ISA handling on ppc32 at this stage, it
* all goes through PCI
*/
return 0;
}
#else /* CONFIG_PPC64 */
/*
* PCI stuff, for nodes representing PCI devices, pointed to
* by device_node->data.
*/
struct iommu_table;
struct pci_dn {
int busno; /* pci bus number */
int devfn; /* pci device and function number */
struct pci_controller *phb; /* for pci devices */
struct iommu_table *iommu_table; /* for phb's or bridges */
struct device_node *node; /* back-pointer to the device_node */
int pci_ext_config_space; /* for pci devices */
struct pci_dev *pcidev; /* back-pointer to the pci device */
#ifdef CONFIG_EEH
struct eeh_dev *edev; /* eeh device */
#endif
#define IODA_INVALID_PE (-1)
#ifdef CONFIG_PPC_POWERNV
int pe_number;
#endif
};
/* Get the pointer to a device_node's pci_dn */
#define PCI_DN(dn) ((struct pci_dn *) (dn)->data)
extern void * update_dn_pci_info(struct device_node *dn, void *data);
static inline int pci_device_from_OF_node(struct device_node *np,
u8 *bus, u8 *devfn)
{
if (!PCI_DN(np))
return -ENODEV;
*bus = PCI_DN(np)->busno;
*devfn = PCI_DN(np)->devfn;
return 0;
}
#if defined(CONFIG_EEH)
static inline struct eeh_dev *of_node_to_eeh_dev(struct device_node *dn)
{
/*
* For those OF nodes whose parent isn't PCI bridge, they
* don't have PCI_DN actually. So we have to skip them for
* any EEH operations.
*/
if (!dn || !PCI_DN(dn))
return NULL;
return PCI_DN(dn)->edev;
}
#else
#define of_node_to_eeh_dev(x) (NULL)
#endif
/** Find the bus corresponding to the indicated device node */
extern struct pci_bus *pcibios_find_pci_bus(struct device_node *dn);
/** Remove all of the PCI devices under this bus */
extern void __pcibios_remove_pci_devices(struct pci_bus *bus, int purge_pe);
extern void pcibios_remove_pci_devices(struct pci_bus *bus);
/** Discover new pci devices under this bus, and add them */
extern void pcibios_add_pci_devices(struct pci_bus *bus);
extern void isa_bridge_find_early(struct pci_controller *hose);
static inline int isa_vaddr_is_ioport(void __iomem *address)
{
/* Check if address hits the reserved legacy IO range */
unsigned long ea = (unsigned long)address;
return ea >= ISA_IO_BASE && ea < ISA_IO_END;
}
extern int pcibios_unmap_io_space(struct pci_bus *bus);
extern int pcibios_map_io_space(struct pci_bus *bus);
#ifdef CONFIG_NUMA
#define PHB_SET_NODE(PHB, NODE) ((PHB)->node = (NODE))
#else
#define PHB_SET_NODE(PHB, NODE) ((PHB)->node = -1)
#endif
#endif /* CONFIG_PPC64 */
/* Get the PCI host controller for an OF device */
extern struct pci_controller *pci_find_hose_for_OF_device(
struct device_node* node);
/* Fill up host controller resources from the OF node */
extern void pci_process_bridge_OF_ranges(struct pci_controller *hose,
struct device_node *dev, int primary);
/* Allocate & free a PCI host bridge structure */
extern struct pci_controller *pcibios_alloc_controller(struct device_node *dev);
extern void pcibios_free_controller(struct pci_controller *phb);
#ifdef CONFIG_PCI
extern int pcibios_vaddr_is_ioport(void __iomem *address);
#else
static inline int pcibios_vaddr_is_ioport(void __iomem *address)
{
return 0;
}
#endif /* CONFIG_PCI */
#endif /* __KERNEL__ */
#endif /* _ASM_POWERPC_PCI_BRIDGE_H */