linux_dsm_epyc7002/arch/powerpc/include/asm/eeh.h
Wei Yang 2a58222f82 powerpc/eeh: Fix kernel crash when passing through VF
When doing vfio passthrough a VF, the kernel will crash with following
message:

[  442.656459] Unable to handle kernel paging request for data at address 0x00000060
[  442.656593] Faulting instruction address: 0xc000000000038b88
[  442.656706] Oops: Kernel access of bad area, sig: 11 [#1]
[  442.656798] SMP NR_CPUS=1024 NUMA PowerNV
[  442.656890] Modules linked in: vfio_pci mlx4_core nf_conntrack_netbios_ns nf_conntrack_broadcast ipt_MASQUERADE ip6t_REJECT xt_conntrack bnep bluetooth rfkill ebtable_nat ebtable_broute bridge stp llc ebtable_filter ebtables ip6table_nat nf_conntrack_ipv6 nf_defrag_ipv6 nf_nat_ipv6 ip6table_mangle ip6table_security ip6table_raw ip6table_filter ip6_tables iptable_nat nf_conntrack_ipv4 nf_defrag_ipv4 nf_nat_ipv4 nf_nat nf_conntrack iptable_mangle iptable_security iptable_raw tg3 nfsd be2net nfs_acl ses lockd ptp enclosure pps_core kvm_hv kvm_pr shpchp binfmt_misc kvm sunrpc uinput lpfc scsi_transport_fc ipr scsi_tgt [last unloaded: mlx4_core]
[  442.658152] CPU: 40 PID: 14948 Comm: qemu-system-ppc Not tainted 3.10.42yw-pkvm+ #37
[  442.658219] task: c000000f7e2a9a00 ti: c000000f6dc3c000 task.ti: c000000f6dc3c000
[  442.658287] NIP: c000000000038b88 LR: c0000000004435a8 CTR: c000000000455bc0
[  442.658352] REGS: c000000f6dc3f580 TRAP: 0300   Not tainted  (3.10.42yw-pkvm+)
[  442.658419] MSR: 9000000000009032 <SF,HV,EE,ME,IR,DR,RI>  CR: 28004882  XER: 20000000
[  442.658577] CFAR: c00000000000908c DAR: 0000000000000060 DSISR: 40000000 SOFTE: 1
GPR00: c0000000004435a8 c000000f6dc3f800 c0000000012b1c10 c00000000da24000
GPR04: 0000000000000003 0000000000001004 00000000000015b3 000000000000ffff
GPR08: c00000000127f5d8 0000000000000000 000000000000ffff 0000000000000000
GPR12: c000000000068078 c00000000fdd6800 000001003c320c80 000001003c3607f0
GPR16: 0000000000000001 00000000105480c8 000000001055aaa8 000001003c31ab18
GPR20: 000001003c10fb40 000001003c360ae8 000000001063bcf0 000000001063bdb0
GPR24: 000001003c15ed70 0000000010548f40 c000001fe5514c88 c000001fe5514cb0
GPR28: c00000000da24000 0000000000000000 c00000000da24000 0000000000000003
[  442.659471] NIP [c000000000038b88] .pcibios_set_pcie_reset_state+0x28/0x130
[  442.659530] LR [c0000000004435a8] .pci_set_pcie_reset_state+0x28/0x40
[  442.659585] Call Trace:
[  442.659610] [c000000f6dc3f800] [00000000000719e0] 0x719e0 (unreliable)
[  442.659677] [c000000f6dc3f880] [c0000000004435a8] .pci_set_pcie_reset_state+0x28/0x40
[  442.659757] [c000000f6dc3f900] [c000000000455bf8] .reset_fundamental+0x38/0x80
[  442.659835] [c000000f6dc3f980] [c0000000004562a8] .pci_dev_specific_reset+0xa8/0xf0
[  442.659913] [c000000f6dc3fa00] [c0000000004448c4] .__pci_dev_reset+0x44/0x430
[  442.659980] [c000000f6dc3fab0] [c000000000444d5c] .pci_reset_function+0x7c/0xc0
[  442.660059] [c000000f6dc3fb30] [d00000001c141ab8] .vfio_pci_open+0xe8/0x2b0 [vfio_pci]
[  442.660139] [c000000f6dc3fbd0] [c000000000586c30] .vfio_group_fops_unl_ioctl+0x3a0/0x630
[  442.660219] [c000000f6dc3fc90] [c000000000255fbc] .do_vfs_ioctl+0x4ec/0x7c0
[  442.660286] [c000000f6dc3fd80] [c000000000256364] .SyS_ioctl+0xd4/0xf0
[  442.660354] [c000000f6dc3fe30] [c000000000009e54] syscall_exit+0x0/0x98
[  442.660420] Instruction dump:
[  442.660454] 4bfffce9 4bfffee4 7c0802a6 fbc1fff0 fbe1fff8 f8010010 f821ff81 7c7e1b78
[  442.660566] 7c9f2378 60000000 60000000 e93e02c8 <e8690060> 2fa30000 41de00c4 2b9f0002
[  442.660679] ---[ end trace a64ac9546bcf0328 ]---
[  442.660724]

The reason is current VF is not EEH enabled.

This patch introduces a macro to convert eeh_dev to eeh_pe. By doing so, it
will prevent converting with NULL pointer.

Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
Acked-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
CC: Michael Ellerman <mpe@ellerman.id.au>

V3 -> V4:
   1. move the macro definition from include/linux/pci.h to
      arch/powerpc/include/asm/eeh.h

V2 -> V3:
   1. rebased on 3.17-rc4
   2. introduce a macro
   3. use this macro in several other places

V1 -> V2:
   1. code style and patch subject adjustment

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2014-09-25 23:14:56 +10:00

455 lines
14 KiB
C

/*
* Copyright (C) 2001 Dave Engebretsen & Todd Inglett IBM Corporation.
* Copyright 2001-2012 IBM Corporation.
*
* 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.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
#ifndef _POWERPC_EEH_H
#define _POWERPC_EEH_H
#ifdef __KERNEL__
#include <linux/init.h>
#include <linux/list.h>
#include <linux/string.h>
#include <linux/time.h>
#include <linux/atomic.h>
struct pci_dev;
struct pci_bus;
struct device_node;
#ifdef CONFIG_EEH
/* EEH subsystem flags */
#define EEH_ENABLED 0x01 /* EEH enabled */
#define EEH_FORCE_DISABLED 0x02 /* EEH disabled */
#define EEH_PROBE_MODE_DEV 0x04 /* From PCI device */
#define EEH_PROBE_MODE_DEVTREE 0x08 /* From device tree */
#define EEH_ENABLE_IO_FOR_LOG 0x10 /* Enable IO for log */
/*
* Delay for PE reset, all in ms
*
* PCI specification has reset hold time of 100 milliseconds.
* We have 250 milliseconds here. The PCI bus settlement time
* is specified as 1.5 seconds and we have 1.8 seconds.
*/
#define EEH_PE_RST_HOLD_TIME 250
#define EEH_PE_RST_SETTLE_TIME 1800
/*
* The struct is used to trace PE related EEH functionality.
* In theory, there will have one instance of the struct to
* be created against particular PE. In nature, PEs corelate
* to each other. the struct has to reflect that hierarchy in
* order to easily pick up those affected PEs when one particular
* PE has EEH errors.
*
* Also, one particular PE might be composed of PCI device, PCI
* bus and its subordinate components. The struct also need ship
* the information. Further more, one particular PE is only meaingful
* in the corresponding PHB. Therefore, the root PEs should be created
* against existing PHBs in on-to-one fashion.
*/
#define EEH_PE_INVALID (1 << 0) /* Invalid */
#define EEH_PE_PHB (1 << 1) /* PHB PE */
#define EEH_PE_DEVICE (1 << 2) /* Device PE */
#define EEH_PE_BUS (1 << 3) /* Bus PE */
#define EEH_PE_ISOLATED (1 << 0) /* Isolated PE */
#define EEH_PE_RECOVERING (1 << 1) /* Recovering PE */
#define EEH_PE_RESET (1 << 2) /* PE reset in progress */
#define EEH_PE_KEEP (1 << 8) /* Keep PE on hotplug */
struct eeh_pe {
int type; /* PE type: PHB/Bus/Device */
int state; /* PE EEH dependent mode */
int config_addr; /* Traditional PCI address */
int addr; /* PE configuration address */
struct pci_controller *phb; /* Associated PHB */
struct pci_bus *bus; /* Top PCI bus for bus PE */
int check_count; /* Times of ignored error */
int freeze_count; /* Times of froze up */
struct timeval tstamp; /* Time on first-time freeze */
int false_positives; /* Times of reported #ff's */
atomic_t pass_dev_cnt; /* Count of passed through devs */
struct eeh_pe *parent; /* Parent PE */
void *data; /* PE auxillary data */
struct list_head child_list; /* Link PE to the child list */
struct list_head edevs; /* Link list of EEH devices */
struct list_head child; /* Child PEs */
};
#define eeh_pe_for_each_dev(pe, edev, tmp) \
list_for_each_entry_safe(edev, tmp, &pe->edevs, list)
static inline bool eeh_pe_passed(struct eeh_pe *pe)
{
return pe ? !!atomic_read(&pe->pass_dev_cnt) : false;
}
/*
* The struct is used to trace EEH state for the associated
* PCI device node or PCI device. In future, it might
* represent PE as well so that the EEH device to form
* another tree except the currently existing tree of PCI
* buses and PCI devices
*/
#define EEH_DEV_BRIDGE (1 << 0) /* PCI bridge */
#define EEH_DEV_ROOT_PORT (1 << 1) /* PCIe root port */
#define EEH_DEV_DS_PORT (1 << 2) /* Downstream port */
#define EEH_DEV_IRQ_DISABLED (1 << 3) /* Interrupt disabled */
#define EEH_DEV_DISCONNECTED (1 << 4) /* Removing from PE */
#define EEH_DEV_NO_HANDLER (1 << 8) /* No error handler */
#define EEH_DEV_SYSFS (1 << 9) /* Sysfs created */
#define EEH_DEV_REMOVED (1 << 10) /* Removed permanently */
struct eeh_dev {
int mode; /* EEH mode */
int class_code; /* Class code of the device */
int config_addr; /* Config address */
int pe_config_addr; /* PE config address */
u32 config_space[16]; /* Saved PCI config space */
int pcix_cap; /* Saved PCIx capability */
int pcie_cap; /* Saved PCIe capability */
int aer_cap; /* Saved AER capability */
struct eeh_pe *pe; /* Associated PE */
struct list_head list; /* Form link list in the PE */
struct pci_controller *phb; /* Associated PHB */
struct device_node *dn; /* Associated device node */
struct pci_dev *pdev; /* Associated PCI device */
struct pci_bus *bus; /* PCI bus for partial hotplug */
};
static inline struct device_node *eeh_dev_to_of_node(struct eeh_dev *edev)
{
return edev ? edev->dn : NULL;
}
static inline struct pci_dev *eeh_dev_to_pci_dev(struct eeh_dev *edev)
{
return edev ? edev->pdev : NULL;
}
static inline struct eeh_pe *eeh_dev_to_pe(struct eeh_dev* edev)
{
return edev ? edev->pe : NULL;
}
/* Return values from eeh_ops::next_error */
enum {
EEH_NEXT_ERR_NONE = 0,
EEH_NEXT_ERR_INF,
EEH_NEXT_ERR_FROZEN_PE,
EEH_NEXT_ERR_FENCED_PHB,
EEH_NEXT_ERR_DEAD_PHB,
EEH_NEXT_ERR_DEAD_IOC
};
/*
* The struct is used to trace the registered EEH operation
* callback functions. Actually, those operation callback
* functions are heavily platform dependent. That means the
* platform should register its own EEH operation callback
* functions before any EEH further operations.
*/
#define EEH_OPT_DISABLE 0 /* EEH disable */
#define EEH_OPT_ENABLE 1 /* EEH enable */
#define EEH_OPT_THAW_MMIO 2 /* MMIO enable */
#define EEH_OPT_THAW_DMA 3 /* DMA enable */
#define EEH_STATE_UNAVAILABLE (1 << 0) /* State unavailable */
#define EEH_STATE_NOT_SUPPORT (1 << 1) /* EEH not supported */
#define EEH_STATE_RESET_ACTIVE (1 << 2) /* Active reset */
#define EEH_STATE_MMIO_ACTIVE (1 << 3) /* Active MMIO */
#define EEH_STATE_DMA_ACTIVE (1 << 4) /* Active DMA */
#define EEH_STATE_MMIO_ENABLED (1 << 5) /* MMIO enabled */
#define EEH_STATE_DMA_ENABLED (1 << 6) /* DMA enabled */
#define EEH_PE_STATE_NORMAL 0 /* Normal state */
#define EEH_PE_STATE_RESET 1 /* PE reset asserted */
#define EEH_PE_STATE_STOPPED_IO_DMA 2 /* Frozen PE */
#define EEH_PE_STATE_STOPPED_DMA 4 /* Stopped DMA, Enabled IO */
#define EEH_PE_STATE_UNAVAIL 5 /* Unavailable */
#define EEH_RESET_DEACTIVATE 0 /* Deactivate the PE reset */
#define EEH_RESET_HOT 1 /* Hot reset */
#define EEH_RESET_FUNDAMENTAL 3 /* Fundamental reset */
#define EEH_LOG_TEMP 1 /* EEH temporary error log */
#define EEH_LOG_PERM 2 /* EEH permanent error log */
struct eeh_ops {
char *name;
int (*init)(void);
int (*post_init)(void);
void* (*of_probe)(struct device_node *dn, void *flag);
int (*dev_probe)(struct pci_dev *dev, void *flag);
int (*set_option)(struct eeh_pe *pe, int option);
int (*get_pe_addr)(struct eeh_pe *pe);
int (*get_state)(struct eeh_pe *pe, int *state);
int (*reset)(struct eeh_pe *pe, int option);
int (*wait_state)(struct eeh_pe *pe, int max_wait);
int (*get_log)(struct eeh_pe *pe, int severity, char *drv_log, unsigned long len);
int (*configure_bridge)(struct eeh_pe *pe);
int (*read_config)(struct device_node *dn, int where, int size, u32 *val);
int (*write_config)(struct device_node *dn, int where, int size, u32 val);
int (*next_error)(struct eeh_pe **pe);
int (*restore_config)(struct device_node *dn);
};
extern int eeh_subsystem_flags;
extern struct eeh_ops *eeh_ops;
extern raw_spinlock_t confirm_error_lock;
static inline void eeh_add_flag(int flag)
{
eeh_subsystem_flags |= flag;
}
static inline void eeh_clear_flag(int flag)
{
eeh_subsystem_flags &= ~flag;
}
static inline bool eeh_has_flag(int flag)
{
return !!(eeh_subsystem_flags & flag);
}
static inline bool eeh_enabled(void)
{
if (eeh_has_flag(EEH_FORCE_DISABLED) ||
!eeh_has_flag(EEH_ENABLED))
return false;
return true;
}
static inline void eeh_serialize_lock(unsigned long *flags)
{
raw_spin_lock_irqsave(&confirm_error_lock, *flags);
}
static inline void eeh_serialize_unlock(unsigned long flags)
{
raw_spin_unlock_irqrestore(&confirm_error_lock, flags);
}
/*
* Max number of EEH freezes allowed before we consider the device
* to be permanently disabled.
*/
#define EEH_MAX_ALLOWED_FREEZES 5
typedef void *(*eeh_traverse_func)(void *data, void *flag);
void eeh_set_pe_aux_size(int size);
int eeh_phb_pe_create(struct pci_controller *phb);
struct eeh_pe *eeh_phb_pe_get(struct pci_controller *phb);
struct eeh_pe *eeh_pe_get(struct eeh_dev *edev);
int eeh_add_to_parent_pe(struct eeh_dev *edev);
int eeh_rmv_from_parent_pe(struct eeh_dev *edev);
void eeh_pe_update_time_stamp(struct eeh_pe *pe);
void *eeh_pe_traverse(struct eeh_pe *root,
eeh_traverse_func fn, void *flag);
void *eeh_pe_dev_traverse(struct eeh_pe *root,
eeh_traverse_func fn, void *flag);
void eeh_pe_restore_bars(struct eeh_pe *pe);
const char *eeh_pe_loc_get(struct eeh_pe *pe);
struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe);
void *eeh_dev_init(struct device_node *dn, void *data);
void eeh_dev_phb_init_dynamic(struct pci_controller *phb);
int eeh_init(void);
int __init eeh_ops_register(struct eeh_ops *ops);
int __exit eeh_ops_unregister(const char *name);
unsigned long eeh_check_failure(const volatile void __iomem *token,
unsigned long val);
int eeh_dev_check_failure(struct eeh_dev *edev);
void eeh_addr_cache_build(void);
void eeh_add_device_early(struct device_node *);
void eeh_add_device_tree_early(struct device_node *);
void eeh_add_device_late(struct pci_dev *);
void eeh_add_device_tree_late(struct pci_bus *);
void eeh_add_sysfs_files(struct pci_bus *);
void eeh_remove_device(struct pci_dev *);
int eeh_dev_open(struct pci_dev *pdev);
void eeh_dev_release(struct pci_dev *pdev);
struct eeh_pe *eeh_iommu_group_to_pe(struct iommu_group *group);
int eeh_pe_set_option(struct eeh_pe *pe, int option);
int eeh_pe_get_state(struct eeh_pe *pe);
int eeh_pe_reset(struct eeh_pe *pe, int option);
int eeh_pe_configure(struct eeh_pe *pe);
/**
* EEH_POSSIBLE_ERROR() -- test for possible MMIO failure.
*
* If this macro yields TRUE, the caller relays to eeh_check_failure()
* which does further tests out of line.
*/
#define EEH_POSSIBLE_ERROR(val, type) ((val) == (type)~0 && eeh_enabled())
/*
* Reads from a device which has been isolated by EEH will return
* all 1s. This macro gives an all-1s value of the given size (in
* bytes: 1, 2, or 4) for comparing with the result of a read.
*/
#define EEH_IO_ERROR_VALUE(size) (~0U >> ((4 - (size)) * 8))
#else /* !CONFIG_EEH */
static inline bool eeh_enabled(void)
{
return false;
}
static inline int eeh_init(void)
{
return 0;
}
static inline void *eeh_dev_init(struct device_node *dn, void *data)
{
return NULL;
}
static inline void eeh_dev_phb_init_dynamic(struct pci_controller *phb) { }
static inline unsigned long eeh_check_failure(const volatile void __iomem *token, unsigned long val)
{
return val;
}
#define eeh_dev_check_failure(x) (0)
static inline void eeh_addr_cache_build(void) { }
static inline void eeh_add_device_early(struct device_node *dn) { }
static inline void eeh_add_device_tree_early(struct device_node *dn) { }
static inline void eeh_add_device_late(struct pci_dev *dev) { }
static inline void eeh_add_device_tree_late(struct pci_bus *bus) { }
static inline void eeh_add_sysfs_files(struct pci_bus *bus) { }
static inline void eeh_remove_device(struct pci_dev *dev) { }
#define EEH_POSSIBLE_ERROR(val, type) (0)
#define EEH_IO_ERROR_VALUE(size) (-1UL)
#endif /* CONFIG_EEH */
#ifdef CONFIG_PPC64
/*
* MMIO read/write operations with EEH support.
*/
static inline u8 eeh_readb(const volatile void __iomem *addr)
{
u8 val = in_8(addr);
if (EEH_POSSIBLE_ERROR(val, u8))
return eeh_check_failure(addr, val);
return val;
}
static inline u16 eeh_readw(const volatile void __iomem *addr)
{
u16 val = in_le16(addr);
if (EEH_POSSIBLE_ERROR(val, u16))
return eeh_check_failure(addr, val);
return val;
}
static inline u32 eeh_readl(const volatile void __iomem *addr)
{
u32 val = in_le32(addr);
if (EEH_POSSIBLE_ERROR(val, u32))
return eeh_check_failure(addr, val);
return val;
}
static inline u64 eeh_readq(const volatile void __iomem *addr)
{
u64 val = in_le64(addr);
if (EEH_POSSIBLE_ERROR(val, u64))
return eeh_check_failure(addr, val);
return val;
}
static inline u16 eeh_readw_be(const volatile void __iomem *addr)
{
u16 val = in_be16(addr);
if (EEH_POSSIBLE_ERROR(val, u16))
return eeh_check_failure(addr, val);
return val;
}
static inline u32 eeh_readl_be(const volatile void __iomem *addr)
{
u32 val = in_be32(addr);
if (EEH_POSSIBLE_ERROR(val, u32))
return eeh_check_failure(addr, val);
return val;
}
static inline u64 eeh_readq_be(const volatile void __iomem *addr)
{
u64 val = in_be64(addr);
if (EEH_POSSIBLE_ERROR(val, u64))
return eeh_check_failure(addr, val);
return val;
}
static inline void eeh_memcpy_fromio(void *dest, const
volatile void __iomem *src,
unsigned long n)
{
_memcpy_fromio(dest, src, n);
/* Look for ffff's here at dest[n]. Assume that at least 4 bytes
* were copied. Check all four bytes.
*/
if (n >= 4 && EEH_POSSIBLE_ERROR(*((u32 *)(dest + n - 4)), u32))
eeh_check_failure(src, *((u32 *)(dest + n - 4)));
}
/* in-string eeh macros */
static inline void eeh_readsb(const volatile void __iomem *addr, void * buf,
int ns)
{
_insb(addr, buf, ns);
if (EEH_POSSIBLE_ERROR((*(((u8*)buf)+ns-1)), u8))
eeh_check_failure(addr, *(u8*)buf);
}
static inline void eeh_readsw(const volatile void __iomem *addr, void * buf,
int ns)
{
_insw(addr, buf, ns);
if (EEH_POSSIBLE_ERROR((*(((u16*)buf)+ns-1)), u16))
eeh_check_failure(addr, *(u16*)buf);
}
static inline void eeh_readsl(const volatile void __iomem *addr, void * buf,
int nl)
{
_insl(addr, buf, nl);
if (EEH_POSSIBLE_ERROR((*(((u32*)buf)+nl-1)), u32))
eeh_check_failure(addr, *(u32*)buf);
}
#endif /* CONFIG_PPC64 */
#endif /* __KERNEL__ */
#endif /* _POWERPC_EEH_H */