diff options
Diffstat (limited to 'arch')
78 files changed, 1877 insertions, 1046 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 352f416269c..98e513b6270 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -239,6 +239,9 @@ config PPC_OF_PLATFORM_PCI config ARCH_SUPPORTS_DEBUG_PAGEALLOC def_bool y +config ARCH_SUPPORTS_UPROBES + def_bool y + config PPC_ADV_DEBUG_REGS bool depends on 40x || BOOKE diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index b7d833382be..6a15c968d21 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -107,6 +107,7 @@ src-boot := $(addprefix $(obj)/, $(src-boot)) obj-boot := $(addsuffix .o, $(basename $(src-boot))) obj-wlib := $(addsuffix .o, $(basename $(addprefix $(obj)/, $(src-wlib)))) obj-plat := $(addsuffix .o, $(basename $(addprefix $(obj)/, $(src-plat)))) +obj-plat: $(libfdt) quiet_cmd_copy_zlib = COPY $@ cmd_copy_zlib = sed "s@__used@@;s@<linux/\([^>]*\).*@\"\1\"@" $< > $@ diff --git a/arch/powerpc/include/asm/abs_addr.h b/arch/powerpc/include/asm/abs_addr.h deleted file mode 100644 index 9d92ba04b03..00000000000 --- a/arch/powerpc/include/asm/abs_addr.h +++ /dev/null @@ -1,56 +0,0 @@ -#ifndef _ASM_POWERPC_ABS_ADDR_H -#define _ASM_POWERPC_ABS_ADDR_H -#ifdef __KERNEL__ - - -/* - * c 2001 PPC 64 Team, IBM Corp - * - * 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/memblock.h> - -#include <asm/types.h> -#include <asm/page.h> -#include <asm/prom.h> - -struct mschunks_map { - unsigned long num_chunks; - unsigned long chunk_size; - unsigned long chunk_shift; - unsigned long chunk_mask; - u32 *mapping; -}; - -extern struct mschunks_map mschunks_map; - -/* Chunks are 256 KB */ -#define MSCHUNKS_CHUNK_SHIFT (18) -#define MSCHUNKS_CHUNK_SIZE (1UL << MSCHUNKS_CHUNK_SHIFT) -#define MSCHUNKS_OFFSET_MASK (MSCHUNKS_CHUNK_SIZE - 1) - -static inline unsigned long chunk_to_addr(unsigned long chunk) -{ - return chunk << MSCHUNKS_CHUNK_SHIFT; -} - -static inline unsigned long addr_to_chunk(unsigned long addr) -{ - return addr >> MSCHUNKS_CHUNK_SHIFT; -} - -static inline unsigned long phys_to_abs(unsigned long pa) -{ - return pa; -} - -/* Convenience macros */ -#define virt_to_abs(va) phys_to_abs(__pa(va)) -#define abs_to_virt(aa) __va(aa) - -#endif /* __KERNEL__ */ -#endif /* _ASM_POWERPC_ABS_ADDR_H */ diff --git a/arch/powerpc/include/asm/debug.h b/arch/powerpc/include/asm/debug.h index 716d2f089eb..32de2577bb6 100644 --- a/arch/powerpc/include/asm/debug.h +++ b/arch/powerpc/include/asm/debug.h @@ -44,7 +44,7 @@ static inline int debugger_dabr_match(struct pt_regs *regs) { return 0; } static inline int debugger_fault_handler(struct pt_regs *regs) { return 0; } #endif -extern int set_dabr(unsigned long dabr); +extern int set_dabr(unsigned long dabr, unsigned long dabrx); #ifdef CONFIG_PPC_ADV_DEBUG_REGS extern void do_send_trap(struct pt_regs *regs, unsigned long address, unsigned long error_code, int signal_code, int brkpt); diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index d60f99814ff..58c5ee61e70 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -32,27 +32,61 @@ struct device_node; #ifdef CONFIG_EEH /* + * 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_PHB 1 /* PHB PE */ +#define EEH_PE_DEVICE 2 /* Device PE */ +#define EEH_PE_BUS 3 /* Bus PE */ + +#define EEH_PE_ISOLATED (1 << 0) /* Isolated PE */ +#define EEH_PE_RECOVERING (1 << 1) /* Recovering PE */ + +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 */ + int check_count; /* Times of ignored error */ + int freeze_count; /* Times of froze up */ + int false_positives; /* Times of reported #ff's */ + struct eeh_pe *parent; /* Parent PE */ + 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) \ + list_for_each_entry(edev, &pe->edevs, list) + +/* * 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_MODE_SUPPORTED (1<<0) /* EEH supported on the device */ -#define EEH_MODE_NOCHECK (1<<1) /* EEH check should be skipped */ -#define EEH_MODE_ISOLATED (1<<2) /* The device has been isolated */ -#define EEH_MODE_RECOVERING (1<<3) /* Recovering the device */ -#define EEH_MODE_IRQ_DISABLED (1<<4) /* Interrupt disabled */ +#define EEH_DEV_IRQ_DISABLED (1<<0) /* Interrupt disabled */ 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 */ - int check_count; /* Times of ignored error */ - int freeze_count; /* Times of froze up */ - int false_positives; /* Times of reported #ff's */ u32 config_space[16]; /* Saved PCI config space */ + 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 */ @@ -95,19 +129,51 @@ static inline struct pci_dev *eeh_dev_to_pci_dev(struct eeh_dev *edev) struct eeh_ops { char *name; int (*init)(void); - int (*set_option)(struct device_node *dn, int option); - int (*get_pe_addr)(struct device_node *dn); - int (*get_state)(struct device_node *dn, int *state); - int (*reset)(struct device_node *dn, int option); - int (*wait_state)(struct device_node *dn, int max_wait); - int (*get_log)(struct device_node *dn, int severity, char *drv_log, unsigned long len); - int (*configure_bridge)(struct device_node *dn); + void* (*of_probe)(struct device_node *dn, void *flag); + void* (*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); }; extern struct eeh_ops *eeh_ops; extern int eeh_subsystem_enabled; +extern struct mutex eeh_mutex; +extern int eeh_probe_mode; + +#define EEH_PROBE_MODE_DEV (1<<0) /* From PCI device */ +#define EEH_PROBE_MODE_DEVTREE (1<<1) /* From device tree */ + +static inline void eeh_probe_mode_set(int flag) +{ + eeh_probe_mode = flag; +} + +static inline int eeh_probe_mode_devtree(void) +{ + return (eeh_probe_mode == EEH_PROBE_MODE_DEVTREE); +} + +static inline int eeh_probe_mode_dev(void) +{ + return (eeh_probe_mode == EEH_PROBE_MODE_DEV); +} + +static inline void eeh_lock(void) +{ + mutex_lock(&eeh_mutex); +} + +static inline void eeh_unlock(void) +{ + mutex_unlock(&eeh_mutex); +} /* * Max number of EEH freezes allowed before we consider the device @@ -115,19 +181,23 @@ extern int eeh_subsystem_enabled; */ #define EEH_MAX_ALLOWED_FREEZES 5 +typedef void *(*eeh_traverse_func)(void *data, void *flag); +int __devinit eeh_phb_pe_create(struct pci_controller *phb); +int eeh_add_to_parent_pe(struct eeh_dev *edev); +int eeh_rmv_from_parent_pe(struct eeh_dev *edev); +void *eeh_pe_dev_traverse(struct eeh_pe *root, + eeh_traverse_func fn, void *flag); +void eeh_pe_restore_bars(struct eeh_pe *pe); +struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe); + void * __devinit eeh_dev_init(struct device_node *dn, void *data); void __devinit eeh_dev_phb_init_dynamic(struct pci_controller *phb); -void __init eeh_dev_phb_init(void); -void __init eeh_init(void); -#ifdef CONFIG_PPC_PSERIES -int __init eeh_pseries_init(void); -#endif 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_dn_check_failure(struct device_node *dn, struct pci_dev *dev); -void __init pci_addr_cache_build(void); +int eeh_dev_check_failure(struct eeh_dev *edev); +void __init eeh_addr_cache_build(void); void eeh_add_device_tree_early(struct device_node *); void eeh_add_device_tree_late(struct pci_bus *); void eeh_remove_bus_device(struct pci_dev *); @@ -156,34 +226,24 @@ static inline void *eeh_dev_init(struct device_node *dn, void *data) static inline void eeh_dev_phb_init_dynamic(struct pci_controller *phb) { } -static inline void eeh_dev_phb_init(void) { } - -static inline void eeh_init(void) { } - -#ifdef CONFIG_PPC_PSERIES -static inline int eeh_pseries_init(void) -{ - return 0; -} -#endif /* CONFIG_PPC_PSERIES */ - static inline unsigned long eeh_check_failure(const volatile void __iomem *token, unsigned long val) { return val; } -static inline int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev) -{ - return 0; -} +#define eeh_dev_check_failure(x) (0) -static inline void pci_addr_cache_build(void) { } +static inline void eeh_addr_cache_build(void) { } static inline void eeh_add_device_tree_early(struct device_node *dn) { } static inline void eeh_add_device_tree_late(struct pci_bus *bus) { } static inline void eeh_remove_bus_device(struct pci_dev *dev) { } + +static inline void eeh_lock(void) { } +static inline void eeh_unlock(void) { } + #define EEH_POSSIBLE_ERROR(val, type) (0) #define EEH_IO_ERROR_VALUE(size) (-1UL) #endif /* CONFIG_EEH */ diff --git a/arch/powerpc/include/asm/eeh_event.h b/arch/powerpc/include/asm/eeh_event.h index c68b012b779..de67d830151 100644 --- a/arch/powerpc/include/asm/eeh_event.h +++ b/arch/powerpc/include/asm/eeh_event.h @@ -28,11 +28,11 @@ */ struct eeh_event { struct list_head list; /* to form event queue */ - struct eeh_dev *edev; /* EEH device */ + struct eeh_pe *pe; /* EEH PE */ }; -int eeh_send_failure_event(struct eeh_dev *edev); -struct eeh_dev *handle_eeh_events(struct eeh_event *); +int eeh_send_failure_event(struct eeh_pe *pe); +void eeh_handle_event(struct eeh_pe *pe); #endif /* __KERNEL__ */ #endif /* ASM_POWERPC_EEH_EVENT_H */ diff --git a/arch/powerpc/include/asm/exception-64e.h b/arch/powerpc/include/asm/exception-64e.h index ac13addb849..51fa43e536b 100644 --- a/arch/powerpc/include/asm/exception-64e.h +++ b/arch/powerpc/include/asm/exception-64e.h @@ -37,6 +37,7 @@ * critical data */ +#define PACA_EXGDBELL PACA_EXGEN /* We are out of SPRGs so we save some things in the PACA. The normal * exception frame is smaller than the CRIT or MC one though @@ -45,8 +46,9 @@ #define EX_CR (1 * 8) #define EX_R10 (2 * 8) #define EX_R11 (3 * 8) -#define EX_R14 (4 * 8) -#define EX_R15 (5 * 8) +#define EX_R13 (4 * 8) +#define EX_R14 (5 * 8) +#define EX_R15 (6 * 8) /* * The TLB miss exception uses different slots. diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index 423cf9eaf4a..7a867065db7 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -152,11 +152,6 @@ #define H_VASI_RESUMED 5 #define H_VASI_COMPLETED 6 -/* DABRX flags */ -#define H_DABRX_HYPERVISOR (1UL<<(63-61)) -#define H_DABRX_KERNEL (1UL<<(63-62)) -#define H_DABRX_USER (1UL<<(63-63)) - /* Each control block has to be on a 4K boundary */ #define H_CB_ALIGNMENT 4096 diff --git a/arch/powerpc/include/asm/hw_breakpoint.h b/arch/powerpc/include/asm/hw_breakpoint.h index be04330af75..423424599da 100644 --- a/arch/powerpc/include/asm/hw_breakpoint.h +++ b/arch/powerpc/include/asm/hw_breakpoint.h @@ -27,10 +27,11 @@ #ifdef CONFIG_HAVE_HW_BREAKPOINT struct arch_hw_breakpoint { - bool extraneous_interrupt; - u8 len; /* length of the target data symbol */ - int type; unsigned long address; + unsigned long dabrx; + int type; + u8 len; /* length of the target data symbol */ + bool extraneous_interrupt; }; #include <linux/kdebug.h> @@ -61,7 +62,7 @@ extern void ptrace_triggered(struct perf_event *bp, struct perf_sample_data *data, struct pt_regs *regs); static inline void hw_breakpoint_disable(void) { - set_dabr(0); + set_dabr(0, 0); } extern void thread_change_pc(struct task_struct *tsk, struct pt_regs *regs); diff --git a/arch/powerpc/include/asm/kprobes.h b/arch/powerpc/include/asm/kprobes.h index be0171afdc0..7b6feab6fd2 100644 --- a/arch/powerpc/include/asm/kprobes.h +++ b/arch/powerpc/include/asm/kprobes.h @@ -29,21 +29,16 @@ #include <linux/types.h> #include <linux/ptrace.h> #include <linux/percpu.h> +#include <asm/probes.h> #define __ARCH_WANT_KPROBES_INSN_SLOT struct pt_regs; struct kprobe; -typedef unsigned int kprobe_opcode_t; -#define BREAKPOINT_INSTRUCTION 0x7fe00008 /* trap */ +typedef ppc_opcode_t kprobe_opcode_t; #define MAX_INSN_SIZE 1 -#define IS_TW(instr) (((instr) & 0xfc0007fe) == 0x7c000008) -#define IS_TD(instr) (((instr) & 0xfc0007fe) == 0x7c000088) -#define IS_TDI(instr) (((instr) & 0xfc000000) == 0x08000000) -#define IS_TWI(instr) (((instr) & 0xfc000000) == 0x0c000000) - #ifdef CONFIG_PPC64 /* * 64bit powerpc uses function descriptors. @@ -72,12 +67,6 @@ typedef unsigned int kprobe_opcode_t; addr = (kprobe_opcode_t *)kallsyms_lookup_name(dot_name); \ } \ } - -#define is_trap(instr) (IS_TW(instr) || IS_TD(instr) || \ - IS_TWI(instr) || IS_TDI(instr)) -#else -/* Use stock kprobe_lookup_name since ppc32 doesn't use function descriptors */ -#define is_trap(instr) (IS_TW(instr) || IS_TWI(instr)) #endif #define flush_insn_slot(p) do { } while (0) diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h index bfcd00c1485..88609b23b77 100644 --- a/arch/powerpc/include/asm/kvm_book3s_asm.h +++ b/arch/powerpc/include/asm/kvm_book3s_asm.h @@ -74,7 +74,6 @@ struct kvmppc_host_state { ulong vmhandler; ulong scratch0; ulong scratch1; - ulong sprg3; u8 in_guest; u8 restore_hid5; u8 napping; diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index f7706d722b3..8111e1b78f7 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -180,7 +180,8 @@ struct machdep_calls { void (*enable_pmcs)(void); /* Set DABR for this platform, leave empty for default implemenation */ - int (*set_dabr)(unsigned long dabr); + int (*set_dabr)(unsigned long dabr, + unsigned long dabrx); #ifdef CONFIG_PPC32 /* XXX for now */ /* A general init function, called by ppc_init in init/main.c. diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index daf813fea91..7796519fd23 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -136,6 +136,7 @@ struct paca_struct { u8 io_sync; /* writel() needs spin_unlock sync */ u8 irq_work_pending; /* IRQ_WORK interrupt while soft-disable */ u8 nap_state_lost; /* NV GPR values lost in power7_idle */ + u64 sprg3; /* Saved user-visible sprg */ #ifdef CONFIG_PPC_POWERNV /* Pointer to OPAL machine check event structure set by the diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h index 8cccbee6151..973df4d9d36 100644 --- a/arch/powerpc/include/asm/pci-bridge.h +++ b/arch/powerpc/include/asm/pci-bridge.h @@ -184,6 +184,8 @@ static inline struct eeh_dev *of_node_to_eeh_dev(struct device_node *dn) { return PCI_DN(dn)->edev; } +#else +#define of_node_to_eeh_dev(x) (NULL) #endif /** Find the bus corresponding to the indicated device node */ diff --git a/arch/powerpc/include/asm/ppc-pci.h b/arch/powerpc/include/asm/ppc-pci.h index 80fa704d410..ed57fa7920c 100644 --- a/arch/powerpc/include/asm/ppc-pci.h +++ b/arch/powerpc/include/asm/ppc-pci.h @@ -47,19 +47,17 @@ extern int rtas_setup_phb(struct pci_controller *phb); #ifdef CONFIG_EEH -void pci_addr_cache_build(void); -void pci_addr_cache_insert_device(struct pci_dev *dev); -void pci_addr_cache_remove_device(struct pci_dev *dev); -struct pci_dev *pci_addr_cache_get_device(unsigned long addr); -void eeh_slot_error_detail(struct eeh_dev *edev, int severity); -int eeh_pci_enable(struct eeh_dev *edev, int function); -int eeh_reset_pe(struct eeh_dev *); -void eeh_restore_bars(struct eeh_dev *); +void eeh_addr_cache_insert_dev(struct pci_dev *dev); +void eeh_addr_cache_rmv_dev(struct pci_dev *dev); +struct eeh_dev *eeh_addr_cache_get_dev(unsigned long addr); +void eeh_slot_error_detail(struct eeh_pe *pe, int severity); +int eeh_pci_enable(struct eeh_pe *pe, int function); +int eeh_reset_pe(struct eeh_pe *); +void eeh_save_bars(struct eeh_dev *edev); int rtas_write_config(struct pci_dn *, int where, int size, u32 val); int rtas_read_config(struct pci_dn *, int where, int size, u32 *val); -void eeh_mark_slot(struct device_node *dn, int mode_flag); -void eeh_clear_slot(struct device_node *dn, int mode_flag); -struct device_node *eeh_find_device_pe(struct device_node *dn); +void eeh_pe_state_mark(struct eeh_pe *pe, int state); +void eeh_pe_state_clear(struct eeh_pe *pe, int state); void eeh_sysfs_add_device(struct pci_dev *pdev); void eeh_sysfs_remove_device(struct pci_dev *pdev); diff --git a/arch/powerpc/include/asm/probes.h b/arch/powerpc/include/asm/probes.h new file mode 100644 index 00000000000..5f1e15b6870 --- /dev/null +++ b/arch/powerpc/include/asm/probes.h @@ -0,0 +1,42 @@ +#ifndef _ASM_POWERPC_PROBES_H +#define _ASM_POWERPC_PROBES_H +#ifdef __KERNEL__ +/* + * Definitions common to probes files + * + * 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. + * + * Copyright IBM Corporation, 2012 + */ +#include <linux/types.h> + +typedef u32 ppc_opcode_t; +#define BREAKPOINT_INSTRUCTION 0x7fe00008 /* trap */ + +/* Trap definitions per ISA */ +#define IS_TW(instr) (((instr) & 0xfc0007fe) == 0x7c000008) +#define IS_TD(instr) (((instr) & 0xfc0007fe) == 0x7c000088) +#define IS_TDI(instr) (((instr) & 0xfc000000) == 0x08000000) +#define IS_TWI(instr) (((instr) & 0xfc000000) == 0x0c000000) + +#ifdef CONFIG_PPC64 +#define is_trap(instr) (IS_TW(instr) || IS_TD(instr) || \ + IS_TWI(instr) || IS_TDI(instr)) +#else +#define is_trap(instr) (IS_TW(instr) || IS_TWI(instr)) +#endif /* CONFIG_PPC64 */ + +#endif /* __KERNEL__ */ +#endif /* _ASM_POWERPC_PROBES_H */ diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 54b73a28c20..83efc6e8154 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -219,6 +219,8 @@ struct thread_struct { #endif /* CONFIG_HAVE_HW_BREAKPOINT */ #endif unsigned long dabr; /* Data address breakpoint register */ + unsigned long dabrx; /* ... extension */ + unsigned long trap_nr; /* last trap # on this thread */ #ifdef CONFIG_ALTIVEC /* Complete AltiVec register set */ vector128 vr[32] __attribute__((aligned(16))); diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 638608677e2..121a90bbf77 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -208,6 +208,9 @@ #define SPRN_DABRX 0x3F7 /* Data Address Breakpoint Register Extension */ #define DABRX_USER (1UL << 0) #define DABRX_KERNEL (1UL << 1) +#define DABRX_HYP (1UL << 2) +#define DABRX_BTI (1UL << 3) +#define DABRX_ALL (DABRX_BTI | DABRX_HYP | DABRX_KERNEL | DABRX_USER) #define SPRN_DAR 0x013 /* Data Address Register */ #define SPRN_DBCR 0x136 /* e300 Data Breakpoint Control Reg */ #define SPRN_DSISR 0x012 /* Data Storage Interrupt Status Register */ @@ -761,7 +764,8 @@ * 64-bit embedded * - SPRG0 generic exception scratch * - SPRG2 TLB exception stack - * - SPRG3 CPU and NUMA node for VDSO getcpu (user visible) + * - SPRG3 critical exception scratch and + * CPU and NUMA node for VDSO getcpu (user visible) * - SPRG4 unused (user visible) * - SPRG6 TLB miss scratch (user visible, sorry !) * - SPRG7 critical exception scratch @@ -858,11 +862,12 @@ #ifdef CONFIG_PPC_BOOK3E_64 #define SPRN_SPRG_MC_SCRATCH SPRN_SPRG8 -#define SPRN_SPRG_CRIT_SCRATCH SPRN_SPRG7 +#define SPRN_SPRG_CRIT_SCRATCH SPRN_SPRG3 #define SPRN_SPRG_DBG_SCRATCH SPRN_SPRG9 #define SPRN_SPRG_TLB_EXFRAME SPRN_SPRG2 #define SPRN_SPRG_TLB_SCRATCH SPRN_SPRG6 #define SPRN_SPRG_GEN_SCRATCH SPRN_SPRG0 +#define SPRN_SPRG_GDBELL_SCRATCH SPRN_SPRG_GEN_SCRATCH #define SET_PACA(rX) mtspr SPRN_SPRG_PACA,rX #define GET_PACA(rX) mfspr rX,SPRN_SPRG_PACA @@ -937,7 +942,7 @@ #define PVR_VER(pvr) (((pvr) >> 16) & 0xFFFF) /* Version field */ #define PVR_REV(pvr) (((pvr) >> 0) & 0xFFFF) /* Revison field */ -#define __is_processor(pv) (PVR_VER(mfspr(SPRN_PVR)) == (pv)) +#define pvr_version_is(pvr) (PVR_VER(mfspr(SPRN_PVR)) == (pvr)) /* * IBM has further subdivided the standard PowerPC 16-bit version and @@ -1002,25 +1007,25 @@ #define PVR_476_ISS 0x00052000 /* 64-bit processors */ -/* XXX the prefix should be PVR_, we'll do a global sweep to fix it one day */ -#define PV_NORTHSTAR 0x0033 -#define PV_PULSAR 0x0034 -#define PV_POWER4 0x0035 -#define PV_ICESTAR 0x0036 -#define PV_SSTAR 0x0037 -#define PV_POWER4p 0x0038 -#define PV_970 0x0039 -#define PV_POWER5 0x003A -#define PV_POWER5p 0x003B -#define PV_970FX 0x003C -#define PV_POWER6 0x003E -#define PV_POWER7 0x003F -#define PV_630 0x0040 -#define PV_630p 0x0041 -#define PV_970MP 0x0044 -#define PV_970GX 0x0045 -#define PV_BE 0x0070 -#define PV_PA6T 0x0090 +#define PVR_NORTHSTAR 0x0033 +#define PVR_PULSAR 0x0034 +#define PVR_POWER4 0x0035 +#define PVR_ICESTAR 0x0036 +#define PVR_SSTAR 0x0037 +#define PVR_POWER4p 0x0038 +#define PVR_970 0x0039 +#define PVR_POWER5 0x003A +#define PVR_POWER5p 0x003B +#define PVR_970FX 0x003C +#define PVR_POWER6 0x003E +#define PVR_POWER7 0x003F +#define PVR_630 0x0040 +#define PVR_630p 0x0041 +#define PVR_970MP 0x0044 +#define PVR_970GX 0x0045 +#define PVR_POWER7p 0x004A +#define PVR_BE 0x0070 +#define PVR_PA6T 0x0090 /* Macros for setting and retrieving special purpose registers */ #ifndef __ASSEMBLY__ diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h index d084ce195fc..8b9a306260b 100644 --- a/arch/powerpc/include/asm/setup.h +++ b/arch/powerpc/include/asm/setup.h @@ -9,7 +9,7 @@ extern void ppc_printk_progress(char *s, unsigned short hex); extern unsigned int rtas_data; extern int mem_init_done; /* set on boot once kmalloc can be called */ extern int init_bootmem_done; /* set once bootmem is available */ -extern phys_addr_t memory_limit; +extern unsigned long long memory_limit; extern unsigned long klimit; extern void *zalloc_maybe_bootmem(size_t size, gfp_t mask); diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index faf93529cbf..e942203cd4a 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -102,6 +102,7 @@ static inline struct thread_info *current_thread_info(void) #define TIF_RESTOREALL 11 /* Restore all regs (implies NOERROR) */ #define TIF_NOERROR 12 /* Force successful syscall return */ #define TIF_NOTIFY_RESUME 13 /* callback before returning to user */ +#define TIF_UPROBE 14 /* breakpointed or single-stepping */ #define TIF_SYSCALL_TRACEPOINT 15 /* syscall tracepoint instrumentation */ /* as above, but as bit values */ @@ -118,12 +119,13 @@ static inline struct thread_info *current_thread_info(void) #define _TIF_RESTOREALL (1<<TIF_RESTOREALL) #define _TIF_NOERROR (1<<TIF_NOERROR) #define _TIF_NOTIFY_RESUME (1<<TIF_NOTIFY_RESUME) +#define _TIF_UPROBE (1<<TIF_UPROBE) #define _TIF_SYSCALL_TRACEPOINT (1<<TIF_SYSCALL_TRACEPOINT) #define _TIF_SYSCALL_T_OR_A (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \ _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT) #define _TIF_USER_WORK_MASK (_TIF_SIGPENDING | _TIF_NEED_RESCHED | \ - _TIF_NOTIFY_RESUME) + _TIF_NOTIFY_RESUME | _TIF_UPROBE) #define _TIF_PERSYSCALL_MASK (_TIF_RESTOREALL|_TIF_NOERROR) /* Bits in local_flags */ diff --git a/arch/powerpc/include/asm/uprobes.h b/arch/powerpc/include/asm/uprobes.h new file mode 100644 index 00000000000..b532060d091 --- /dev/null +++ b/arch/powerpc/include/asm/uprobes.h @@ -0,0 +1,54 @@ +#ifndef _ASM_UPROBES_H +#define _ASM_UPROBES_H +/* + * User-space Probes (UProbes) for powerpc + * + * 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. + * + * Copyright IBM Corporation, 2007-2012 + * + * Adapted from the x86 port by Ananth N Mavinakayanahalli <ananth@in.ibm.com> + */ + +#include <linux/notifier.h> +#include <asm/probes.h> + +typedef ppc_opcode_t uprobe_opcode_t; + +#define MAX_UINSN_BYTES 4 +#define UPROBE_XOL_SLOT_BYTES (MAX_UINSN_BYTES) + +/* The following alias is needed for reference from arch-agnostic code */ +#define UPROBE_SWBP_INSN BREAKPOINT_INSTRUCTION +#define UPROBE_SWBP_INSN_SIZE 4 /* swbp insn size in bytes */ + +struct arch_uprobe { + union { + u8 insn[MAX_UINSN_BYTES]; + u32 ainsn; + }; +}; + +struct arch_uprobe_task { + unsigned long saved_trap_nr; +}; + +extern int arch_uprobe_analyze_insn(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long addr); +extern int arch_uprobe_pre_xol(struct arch_uprobe *aup, struct pt_regs *regs); +extern int arch_uprobe_post_xol(struct arch_uprobe *aup, struct pt_regs *regs); +extern bool arch_uprobe_xol_was_trapped(struct task_struct *tsk); +extern int arch_uprobe_exception_notify(struct notifier_block *self, unsigned long val, void *data); +extern void arch_uprobe_abort_xol(struct arch_uprobe *aup, struct pt_regs *regs); +#endif /* _ASM_UPROBES_H */ diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index bb282dd8161..cde12f8a4eb 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -96,6 +96,7 @@ obj-$(CONFIG_MODULES) += ppc_ksyms.o obj-$(CONFIG_BOOTX_TEXT) += btext.o obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_KPROBES) += kprobes.o +obj-$(CONFIG_UPROBES) += uprobes.o obj-$(CONFIG_PPC_UDBG_16550) += legacy_serial.o udbg_16550.o obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-$(CONFIG_SWIOTLB) += dma-swiotlb.o diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index e8995727b1c..7523539cfe9 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -206,6 +206,7 @@ int main(void) DEFINE(PACA_SYSTEM_TIME, offsetof(struct paca_struct, system_time)); DEFINE(PACA_TRAP_SAVE, offsetof(struct paca_struct, trap_save)); DEFINE(PACA_NAPSTATELOST, offsetof(struct paca_struct, nap_state_lost)); + DEFINE(PACA_SPRG3, offsetof(struct paca_struct, sprg3)); #endif /* CONFIG_PPC64 */ /* RTAS */ @@ -534,7 +535,6 @@ int main(void) HSTATE_FIELD(HSTATE_VMHANDLER, vmhandler); HSTATE_FIELD(HSTATE_SCRATCH0, scratch0); HSTATE_FIELD(HSTATE_SCRATCH1, scratch1); - HSTATE_FIELD(HSTATE_SPRG3, sprg3); HSTATE_FIELD(HSTATE_IN_GUEST, in_guest); HSTATE_FIELD(HSTATE_RESTORE_HID5, restore_hid5); HSTATE_FIELD(HSTATE_NAPPING, napping); diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c index 46943651da2..a720b54b971 100644 --- a/arch/powerpc/kernel/dma-swiotlb.c +++ b/arch/powerpc/kernel/dma-swiotlb.c @@ -12,6 +12,7 @@ */ #include <linux/dma-mapping.h> +#include <linux/memblock.h> #include <linux/pfn.h> #include <linux/of_platform.h> #include <linux/platform_device.h> @@ -20,7 +21,6 @@ #include <asm/machdep.h> #include <asm/swiotlb.h> #include <asm/dma.h> -#include <asm/abs_addr.h> unsigned int ppc_swiotlb_enable; diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c index 355b9d84b0f..8032b97ccdc 100644 --- a/arch/powerpc/kernel/dma.c +++ b/arch/powerpc/kernel/dma.c @@ -14,7 +14,6 @@ #include <linux/pci.h> #include <asm/vio.h> #include <asm/bug.h> -#include <asm/abs_addr.h> #include <asm/machdep.h> /* @@ -50,7 +49,7 @@ void *dma_direct_alloc_coherent(struct device *dev, size_t size, return NULL; ret = page_address(page); memset(ret, 0, size); - *dma_handle = virt_to_abs(ret) + get_dma_offset(dev); + *dma_handle = __pa(ret) + get_dma_offset(dev); return ret; #endif diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index 98be7f0cd22..87a82fbdf05 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -25,6 +25,8 @@ #include <asm/ppc-opcode.h> #include <asm/mmu.h> #include <asm/hw_irq.h> +#include <asm/kvm_asm.h> +#include <asm/kvm_booke_hv_asm.h> /* XXX This will ultimately add space for a special exception save * structure used to save things like SRR0/SRR1, SPRGs, MAS, etc... @@ -35,16 +37,18 @@ #define SPECIAL_EXC_FRAME_SIZE INT_FRAME_SIZE /* Exception prolog code for all exceptions */ -#define EXCEPTION_PROLOG(n, type, addition) \ +#define EXCEPTION_PROLOG(n, intnum, type, addition) \ mtspr SPRN_SPRG_##type##_SCRATCH,r13; /* get spare registers */ \ mfspr r13,SPRN_SPRG_PACA; /* get PACA */ \ std r10,PACA_EX##type+EX_R10(r13); \ std r11,PACA_EX##type+EX_R11(r13); \ + PROLOG_STORE_RESTORE_SCRATCH_##type; \ mfcr r10; /* save CR */ \ + mfspr r11,SPRN_##type##_SRR1;/* what are we coming from */ \ + DO_KVM intnum,SPRN_##type##_SRR1; /* KVM hook */ \ + stw r10,PACA_EX##type+EX_CR(r13); /* save old CR in the PACA */ \ addition; /* additional code for that exc. */ \ std r1,PACA_EX##type+EX_R1(r13); /* save old r1 in the PACA */ \ - stw r10,PACA_EX##type+EX_CR(r13); /* save old CR in the PACA */ \ - mfspr r11,SPRN_##type##_SRR1;/* what are we coming from */ \ type##_SET_KSTACK; /* get special stack if necessary */\ andi. r10,r11,MSR_PR; /* save stack pointer */ \ beq 1f; /* branch around if supervisor */ \ @@ -59,6 +63,10 @@ #define SPRN_GEN_SRR0 SPRN_SRR0 #define SPRN_GEN_SRR1 SPRN_SRR1 +#define GDBELL_SET_KSTACK GEN_SET_KSTACK +#define SPRN_GDBELL_SRR0 SPRN_GSRR0 +#define SPRN_GDBELL_SRR1 SPRN_GSRR1 + #define CRIT_SET_KSTACK \ ld r1,PACA_CRIT_STACK(r13); \ subi r1,r1,SPECIAL_EXC_FRAME_SIZE; @@ -77,29 +85,46 @@ #define SPRN_MC_SRR0 SPRN_MCSRR0 #define SPRN_MC_SRR1 SPRN_MCSRR1 -#define NORMAL_EXCEPTION_PROLOG(n, addition) \ - EXCEPTION_PROLOG(n, GEN, addition##_GEN(n)) +#define NORMAL_EXCEPTION_PROLOG(n, intnum, addition) \ + EXCEPTION_PROLOG(n, intnum, GEN, addition##_GEN(n)) -#define CRIT_EXCEPTION_PROLOG(n, addition) \ - EXCEPTION_PROLOG(n, CRIT, addition##_CRIT(n)) +#define CRIT_EXCEPTION_PROLOG(n, intnum, addition) \ + EXCEPTION_PROLOG(n, intnum, CRIT, addition##_CRIT(n)) -#define DBG_EXCEPTION_PROLOG(n, addition) \ - EXCEPTION_PROLOG(n, DBG, addition##_DBG(n)) +#define DBG_EXCEPTION_PROLOG(n, intnum, addition) \ + EXCEPTION_PROLOG(n, intnum, DBG, addition##_DBG(n)) -#define MC_EXCEPTION_PROLOG(n, addition) \ - EXCEPTION_PROLOG(n, MC, addition##_MC(n)) +#define MC_EXCEPTION_PROLOG(n, intnum, addition) \ + EXCEPTION_PROLOG(n, intnum, MC, addition##_MC(n)) +#define GDBELL_EXCEPTION_PROLOG(n, intnum, addition) \ + EXCEPTION_PROLOG(n, intnum, GDBELL, addition##_GDBELL(n)) + +/* + * Store user-visible scratch in PACA exception slots and restore proper value + */ +#define PROLOG_STORE_RESTORE_SCRATCH_GEN +#define PROLOG_STORE_RESTORE_SCRATCH_GDBELL +#define PROLOG_STORE_RESTORE_SCRATCH_DBG +#define PROLOG_STORE_RESTORE_SCRATCH_MC + +#define PROLOG_STORE_RESTORE_SCRATCH_CRIT \ + mfspr r10,SPRN_SPRG_CRIT_SCRATCH; /* get r13 */ \ + std r10,PACA_EXCRIT+EX_R13(r13); \ + ld r11,PACA_SPRG3(r13); \ + mtspr SPRN_SPRG_CRIT_SCRATCH,r11; /* Variants of the "addition" argument for the prolog */ #define PROLOG_ADDITION_NONE_GEN(n) +#define PROLOG_ADDITION_NONE_GDBELL(n) #define PROLOG_ADDITION_NONE_CRIT(n) #define PROLOG_ADDITION_NONE_DBG(n) #define PROLOG_ADDITION_NONE_MC(n) #define PROLOG_ADDITION_MASKABLE_GEN(n) \ - lbz r11,PACASOFTIRQEN(r13); /* are irqs soft-disabled ? */ \ - cmpwi cr0,r11,0; /* yes -> go out of line */ \ + lbz r10,PACASOFTIRQEN(r13); /* are irqs soft-disabled ? */ \ + cmpwi cr0,r10,0; /* yes -> go out of line */ \ beq masked_interrupt_book3e_##n #define PROLOG_ADDITION_2REGS_GEN(n) \ @@ -233,9 +258,9 @@ exc_##n##_bad_stack: \ 1: -#define MASKABLE_EXCEPTION(trapnum, label, hdlr, ack) \ +#define MASKABLE_EXCEPTION(trapnum, intnum, label, hdlr, ack) \ START_EXCEPTION(label); \ - NORMAL_EXCEPTION_PROLOG(trapnum, PROLOG_ADDITION_MASKABLE) \ + NORMAL_EXCEPTION_PROLOG(trapnum, intnum, PROLOG_ADDITION_MASKABLE)\ EXCEPTION_COMMON(trapnum, PACA_EXGEN, INTS_DISABLE) \ ack(r8); \ CHECK_NAPPING(); \ @@ -286,7 +311,8 @@ interrupt_end_book3e: /* Critical Input Interrupt */ START_EXCEPTION(critical_input); - CRIT_EXCEPTION_PROLOG(0x100, PROLOG_ADDITION_NONE) + CRIT_EXCEPTION_PROLOG(0x100, BOOKE_INTERRUPT_CRITICAL, + PROLOG_ADDITION_NONE) // EXCEPTION_COMMON(0x100, PACA_EXCRIT, INTS_DISABLE) // bl special_reg_save_crit // CHECK_NAPPING(); @@ -297,7 +323,8 @@ interrupt_end_book3e: /* Machine Check Interrupt */ START_EXCEPTION(machine_check); - CRIT_EXCEPTION_PROLOG(0x200, PROLOG_ADDITION_NONE) + MC_EXCEPTION_PROLOG(0x200, BOOKE_INTERRUPT_MACHINE_CHECK, + PROLOG_ADDITION_NONE) // EXCEPTION_COMMON(0x200, PACA_EXMC, INTS_DISABLE) // bl special_reg_save_mc // addi r3,r1,STACK_FRAME_OVERHEAD @@ -308,7 +335,8 @@ interrupt_end_book3e: /* Data Storage Interrupt */ START_EXCEPTION(data_storage) - NORMAL_EXCEPTION_PROLOG(0x300, PROLOG_ADDITION_2REGS) + NORMAL_EXCEPTION_PROLOG(0x300, BOOKE_INTERRUPT_DATA_STORAGE, + PROLOG_ADDITION_2REGS) mfspr r14,SPRN_DEAR mfspr r15,SPRN_ESR EXCEPTION_COMMON(0x300, PACA_EXGEN, INTS_DISABLE) @@ -316,18 +344,21 @@ interrupt_end_book3e: /* Instruction Storage Interrupt */ START_EXCEPTION(instruction_storage); - NORMAL_EXCEPTION_PROLOG(0x400, PROLOG_ADDITION_2REGS) + NORMAL_EXCEPTION_PROLOG(0x400, BOOKE_INTERRUPT_INST_STORAGE, + PROLOG_ADDITION_2REGS) li r15,0 mr r14,r10 EXCEPTION_COMMON(0x400, PACA_EXGEN, INTS_DISABLE) b storage_fault_common /* External Input Interrupt */ - MASKABLE_EXCEPTION(0x500, external_input, .do_IRQ, ACK_NONE) + MASKABLE_EXCEPTION(0x500, BOOKE_INTERRUPT_EXTERNAL, + external_input, .do_IRQ, ACK_NONE) /* Alignment */ START_EXCEPTION(alignment); - NORMAL_EXCEPTION_PROLOG(0x600, PROLOG_ADDITION_2REGS) + NORMAL_EXCEPTION_PROLOG(0x600, BOOKE_INTERRUPT_ALIGNMENT, + PROLOG_ADDITION_2REGS) mfspr r14,SPRN_DEAR mfspr r15,SPRN_ESR EXCEPTION_COMMON(0x600, PACA_EXGEN, INTS_KEEP) @@ -335,7 +366,8 @@ interrupt_end_book3e: /* Program Interrupt */ START_EXCEPTION(program); - NORMAL_EXCEPTION_PROLOG(0x700, PROLOG_ADDITION_1REG) + NORMAL_EXCEPTION_PROLOG(0x700, BOOKE_INTERRUPT_PROGRAM, + PROLOG_ADDITION_1REG) mfspr r14,SPRN_ESR EXCEPTION_COMMON(0x700, PACA_EXGEN, INTS_DISABLE) std r14,_DSISR(r1) @@ -347,7 +379,8 @@ interrupt_end_book3e: /* Floating Point Unavailable Interrupt */ START_EXCEPTION(fp_unavailable); - NORMAL_EXCEPTION_PROLOG(0x800, PROLOG_ADDITION_NONE) + NORMAL_EXCEPTION_PROLOG(0x800, BOOKE_INTERRUPT_FP_UNAVAIL, + PROLOG_ADDITION_NONE) /* we can probably do a shorter exception entry for that one... */ EXCEPTION_COMMON(0x800, PACA_EXGEN, INTS_KEEP) ld r12,_MSR(r1) @@ -362,14 +395,17 @@ interrupt_end_book3e: b .ret_from_except /* Decrementer Interrupt */ - MASKABLE_EXCEPTION(0x900, decrementer, .timer_interrupt, ACK_DEC) + MASKABLE_EXCEPTION(0x900, BOOKE_INTERRUPT_DECREMENTER, + decrementer, .timer_interrupt, ACK_DEC) /* Fixed Interval Timer Interrupt */ - MASKABLE_EXCEPTION(0x980, fixed_interval, .unknown_exception, ACK_FIT) + MASKABLE_EXCEPTION(0x980, BOOKE_INTERRUPT_FIT, + fixed_interval, .unknown_exception, ACK_FIT) /* Watchdog Timer Interrupt */ START_EXCEPTION(watchdog); - CRIT_EXCEPTION_PROLOG(0x9f0, PROLOG_ADDITION_NONE) + CRIT_EXCEPTION_PROLOG(0x9f0, BOOKE_INTERRUPT_WATCHDOG, + PROLOG_ADDITION_NONE) // EXCEPTION_COMMON(0x9f0, PACA_EXCRIT, INTS_DISABLE) // bl special_reg_save_crit // CHECK_NAPPING(); @@ -388,7 +424,8 @@ interrupt_end_book3e: /* Auxiliary Processor Unavailable Interrupt */ START_EXCEPTION(ap_unavailable); - NORMAL_EXCEPTION_PROLOG(0xf20, PROLOG_ADDITION_NONE) + NORMAL_EXCEPTION_PROLOG(0xf20, BOOKE_INTERRUPT_AP_UNAVAIL, + PROLOG_ADDITION_NONE) EXCEPTION_COMMON(0xf20, PACA_EXGEN, INTS_DISABLE) bl .save_nvgprs addi r3,r1,STACK_FRAME_OVERHEAD @@ -397,7 +434,8 @@ interrupt_end_book3e: /* Debug exception as a critical interrupt*/ START_EXCEPTION(debug_crit); - CRIT_EXCEPTION_PROLOG(0xd00, PROLOG_ADDITION_2REGS) + CRIT_EXCEPTION_PROLOG(0xd00, BOOKE_INTERRUPT_DEBUG, + PROLOG_ADDITION_2REGS) /* * If there is a single step or branch-taken exception in an @@ -431,7 +469,7 @@ interrupt_end_book3e: mtcr r10 ld r10,PACA_EXCRIT+EX_R10(r13) /* restore registers */ ld r11,PACA_EXCRIT+EX_R11(r13) - mfspr r13,SPRN_SPRG_CRIT_SCRATCH + ld r13,PACA_EXCRIT+EX_R13(r13) rfci /* Normal debug exception */ @@ -444,7 +482,7 @@ interrupt_end_book3e: /* Now we mash up things to make it look like we are coming on a * normal exception */ - mfspr r15,SPRN_SPRG_CRIT_SCRATCH + ld r15,PACA_EXCRIT+EX_R13(r13) mtspr SPRN_SPRG_GEN_SCRATCH,r15 mfspr r14,SPRN_DBSR EXCEPTION_COMMON(0xd00, PACA_EXCRIT, INTS_DISABLE) @@ -462,7 +500,8 @@ kernel_dbg_exc: /* Debug exception as a debug interrupt*/ START_EXCEPTION(debug_debug); - DBG_EXCEPTION_PROLOG(0xd08, PROLOG_ADDITION_2REGS) + DBG_EXCEPTION_PROLOG(0xd00, BOOKE_INTERRUPT_DEBUG, + PROLOG_ADDITION_2REGS) /* * If there is a single step or branch-taken exception in an @@ -523,18 +562,21 @@ kernel_dbg_exc: b .ret_from_except START_EXCEPTION(perfmon); - NORMAL_EXCEPTION_PROLOG(0x260, PROLOG_ADDITION_NONE) + NORMAL_EXCEPTION_PROLOG(0x260, BOOKE_INTERRUPT_PERFORMANCE_MONITOR, + PROLOG_ADDITION_NONE) EXCEPTION_COMMON(0x260, PACA_EXGEN, INTS_DISABLE) addi r3,r1,STACK_FRAME_OVERHEAD bl .performance_monitor_exception b .ret_from_except_lite /* Doorbell interrupt */ - MASKABLE_EXCEPTION(0x280, doorbell, .doorbell_exception, ACK_NONE) + MASKABLE_EXCEPTION(0x280, BOOKE_INTERRUPT_DOORBELL, + doorbell, .doorbell_exception, ACK_NONE) /* Doorbell critical Interrupt */ START_EXCEPTION(doorbell_crit); - CRIT_EXCEPTION_PROLOG(0x2a0, PROLOG_ADDITION_NONE) + CRIT_EXCEPTION_PROLOG(0x2a0, BOOKE_INTERRUPT_DOORBELL_CRITICAL, + PROLOG_ADDITION_NONE) // EXCEPTION_COMMON(0x2a0, PACA_EXCRIT, INTS_DISABLE) // bl special_reg_save_crit // CHECK_NAPPING(); @@ -543,12 +585,24 @@ kernel_dbg_exc: // b ret_from_crit_except b . -/* Guest Doorbell */ - MASKABLE_EXCEPTION(0x2c0, guest_doorbell, .unknown_exception, ACK_NONE) +/* + * Guest doorbell interrupt + * This general exception use GSRRx save/restore registers + */ + START_EXCEPTION(guest_doorbell); + GDBELL_EXCEPTION_PROLOG(0x2c0, BOOKE_INTERRUPT_GUEST_DBELL, + PROLOG_ADDITION_NONE) + EXCEPTION_COMMON(0x2c0, PACA_EXGEN, INTS_KEEP) + addi r3,r1,STACK_FRAME_OVERHEAD + bl .save_nvgprs + INTS_RESTORE_HARD + bl .unknown_exception + b .ret_from_except /* Guest Doorbell critical Interrupt */ START_EXCEPTION(guest_doorbell_crit); - CRIT_EXCEPTION_PROLOG(0x2e0, PROLOG_ADDITION_NONE) + CRIT_EXCEPTION_PROLOG(0x2e0, BOOKE_INTERRUPT_GUEST_DBELL_CRIT, + PROLOG_ADDITION_NONE) // EXCEPTION_COMMON(0x2e0, PACA_EXCRIT, INTS_DISABLE) // bl special_reg_save_crit // CHECK_NAPPING(); @@ -559,7 +613,8 @@ kernel_dbg_exc: /* Hypervisor call */ START_EXCEPTION(hypercall); - NORMAL_EXCEPTION_PROLOG(0x310, PROLOG_ADDITION_NONE) + NORMAL_EXCEPTION_PROLOG(0x310, BOOKE_INTERRUPT_HV_SYSCALL, + PROLOG_ADDITION_NONE) EXCEPTION_COMMON(0x310, PACA_EXGEN, INTS_KEEP) addi r3,r1,STACK_FRAME_OVERHEAD bl .save_nvgprs @@ -569,7 +624,8 @@ kernel_dbg_exc: /* Embedded Hypervisor priviledged */ START_EXCEPTION(ehpriv); - NORMAL_EXCEPTION_PROLOG(0x320, PROLOG_ADDITION_NONE) + NORMAL_EXCEPTION_PROLOG(0x320, BOOKE_INTERRUPT_HV_PRIV, + PROLOG_ADDITION_NONE) EXCEPTION_COMMON(0x320, PACA_EXGEN, INTS_KEEP) addi r3,r1,STACK_FRAME_OVERHEAD bl .save_nvgprs @@ -582,44 +638,42 @@ kernel_dbg_exc: * accordingly and if the interrupt is level sensitive, we hard disable */ +.macro masked_interrupt_book3e paca_irq full_mask + lbz r10,PACAIRQHAPPENED(r13) + ori r10,r10,\paca_irq + stb r10,PACAIRQHAPPENED(r13) + + .if \full_mask == 1 + rldicl r10,r11,48,1 /* clear MSR_EE */ + rotldi r11,r10,16 + mtspr SPRN_SRR1,r11 + .endif + + lwz r11,PACA_EXGEN+EX_CR(r13) + mtcr r11 + ld r10,PACA_EXGEN+EX_R10(r13) + ld r11,PACA_EXGEN+EX_R11(r13) + mfspr r13,SPRN_SPRG_GEN_SCRATCH + rfi + b . +.endm + masked_interrupt_book3e_0x500: - /* XXX When adding support for EPR, use PACA_IRQ_EE_EDGE */ - li r11,PACA_IRQ_EE - b masked_interrupt_book3e_full_mask + // XXX When adding support for EPR, use PACA_IRQ_EE_EDGE + masked_interrupt_book3e PACA_IRQ_EE 1 masked_interrupt_book3e_0x900: - ACK_DEC(r11); - li r11,PACA_IRQ_DEC - b masked_interrupt_book3e_no_mask + ACK_DEC(r10); + masked_interrupt_book3e PACA_IRQ_DEC 0 + masked_interrupt_book3e_0x980: - ACK_FIT(r11); - li r11,PACA_IRQ_DEC - b masked_interrupt_book3e_no_mask + ACK_FIT(r10); + masked_interrupt_book3e PACA_IRQ_DEC 0 + masked_interrupt_book3e_0x280: masked_interrupt_book3e_0x2c0: - li r11,PACA_IRQ_DBELL - b masked_interrupt_book3e_no_mask + masked_interrupt_book3e PACA_IRQ_DBELL 0 -masked_interrupt_book3e_no_mask: - mtcr r10 - lbz r10,PACAIRQHAPPENED(r13) - or r10,r10,r11 - stb r10,PACAIRQHAPPENED(r13) - b 1f -masked_interrupt_book3e_full_mask: - mtcr r10 - lbz r10,PACAIRQHAPPENED(r13) - or r10,r10,r11 - stb r10,PACAIRQHAPPENED(r13) - mfspr r10,SPRN_SRR1 - rldicl r11,r10,48,1 /* clear MSR_EE */ - rotldi r10,r11,16 - mtspr SPRN_SRR1,r10 -1: ld r10,PACA_EXGEN+EX_R10(r13); - ld r11,PACA_EXGEN+EX_R11(r13); - mfspr r13,SPRN_SPRG_GEN_SCRATCH; - rfi - b . /* * Called from arch_local_irq_enable when an interrupt needs * to be resent. r3 contains either 0x500,0x900,0x260 or 0x280 diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index 18bdf74fa16..06c8202a69c 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -289,8 +289,7 @@ int __init fadump_reserve_mem(void) else memory_limit = memblock_end_of_DRAM(); printk(KERN_INFO "Adjusted memory_limit for firmware-assisted" - " dump, now %#016llx\n", - (unsigned long long)memory_limit); + " dump, now %#016llx\n", memory_limit); } if (memory_limit) memory_boundary = memory_limit; diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index 956a4c496de..a89cae481b0 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -73,7 +73,7 @@ int arch_install_hw_breakpoint(struct perf_event *bp) * If so, DABR will be populated in single_step_dabr_instruction(). */ if (current->thread.last_hit_ubp != bp) - set_dabr(info->address | info->type | DABR_TRANSLATION); + set_dabr(info->address | info->type | DABR_TRANSLATION, info->dabrx); return 0; } @@ -97,7 +97,7 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp) } *slot = NULL; - set_dabr(0); + set_dabr(0, 0); } /* @@ -170,6 +170,13 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) info->address = bp->attr.bp_addr; info->len = bp->attr.bp_len; + info->dabrx = DABRX_ALL; + if (bp->attr.exclude_user) + info->dabrx &= ~DABRX_USER; + if (bp->attr.exclude_kernel) + info->dabrx &= ~DABRX_KERNEL; + if (bp->attr.exclude_hv) + info->dabrx &= ~DABRX_HYP; /* * Since breakpoint length can be a maximum of HW_BREAKPOINT_LEN(8) @@ -197,7 +204,7 @@ void thread_change_pc(struct task_struct *tsk, struct pt_regs *regs) info = counter_arch_bp(tsk->thread.last_hit_ubp); regs->msr &= ~MSR_SE; - set_dabr(info->address | info->type | DABR_TRANSLATION); + set_dabr(info->address | info->type | DABR_TRANSLATION, info->dabrx); tsk->thread.last_hit_ubp = NULL; } @@ -215,7 +222,7 @@ int __kprobes hw_breakpoint_handler(struct die_args *args) unsigned long dar = regs->dar; /* Disable breakpoints during exception handling */ - set_dabr(0); + set_dabr(0, 0); /* * The counter may be concurrently released but that can only @@ -281,7 +288,7 @@ int __kprobes hw_breakpoint_handler(struct die_args *args) if (!info->extraneous_interrupt) perf_bp_event(bp, regs); - set_dabr(info->address | info->type | DABR_TRANSLATION); + set_dabr(info->address | info->type | DABR_TRANSLATION, info->dabrx); out: rcu_read_unlock(); return rc; @@ -294,7 +301,7 @@ int __kprobes single_step_dabr_instruction(struct die_args *args) { struct pt_regs *regs = args->regs; struct perf_event *bp = NULL; - struct arch_hw_breakpoint *bp_info; + struct arch_hw_breakpoint *info; bp = current->thread.last_hit_ubp; /* @@ -304,16 +311,16 @@ int __kprobes single_step_dabr_instruction(struct die_args *args) if (!bp) return NOTIFY_DONE; - bp_info = counter_arch_bp(bp); + info = counter_arch_bp(bp); /* * We shall invoke the user-defined callback function in the single * stepping handler to confirm to 'trigger-after-execute' semantics */ - if (!bp_info->extraneous_interrupt) + if (!info->extraneous_interrupt) perf_bp_event(bp, regs); - set_dabr(bp_info->address | bp_info->type | DABR_TRANSLATION); + set_dabr(info->address | info->type | DABR_TRANSLATION, info->dabrx); current->thread.last_hit_ubp = NULL; /* diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c index b01d14eeca8..8220baa46fa 100644 --- a/arch/powerpc/kernel/ibmebus.c +++ b/arch/powerpc/kernel/ibmebus.c @@ -47,7 +47,6 @@ #include <linux/stat.h> #include <linux/of_platform.h> #include <asm/ibmebus.h> -#include <asm/abs_addr.h> static struct device ibmebus_bus_device = { /* fake "parent" device */ .init_name = "ibmebus", diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c index 5df77779440..fa9f6c72f55 100644 --- a/arch/powerpc/kernel/machine_kexec.c +++ b/arch/powerpc/kernel/machine_kexec.c @@ -165,7 +165,7 @@ void __init reserve_crashkernel(void) if (memory_limit && memory_limit <= crashk_res.end) { memory_limit = crashk_res.end + 1; printk("Adjusted memory limit for crashkernel, now 0x%llx\n", - (unsigned long long)memory_limit); + memory_limit); } printk(KERN_INFO "Reserving %ldMB of memory at %ldMB " @@ -204,6 +204,12 @@ static struct property crashk_size_prop = { .value = &crashk_size, }; +static struct property memory_limit_prop = { + .name = "linux,memory-limit", + .length = sizeof(unsigned long long), + .value = &memory_limit, +}; + static void __init export_crashk_values(struct device_node *node) { struct property *prop; @@ -223,6 +229,12 @@ static void __init export_crashk_values(struct device_node *node) crashk_size = resource_size(&crashk_res); prom_add_property(node, &crashk_size_prop); } + + /* + * memory_limit is required by the kexec-tools to limit the + * crash regions to the actual memory used. + */ + prom_update_property(node, &memory_limit_prop); } static int __init kexec_setup(void) diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index fbe1a12dc7f..cd6da855090 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -142,6 +142,7 @@ void __init initialise_paca(struct paca_struct *new_paca, int cpu) new_paca->hw_cpu_id = 0xffff; new_paca->kexec_state = KEXEC_STATE_NONE; new_paca->__current = &init_task; + new_paca->data_offset = 0xfeeeeeeeeeeeeeeeULL; #ifdef CONFIG_PPC_STD_MMU_64 new_paca->slb_shadow_ptr = &slb_shadow[cpu]; #endif /* CONFIG_PPC_STD_MMU_64 */ diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 43fea543d68..7f94f760dd0 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -980,13 +980,14 @@ static void __devinit pcibios_fixup_bridge(struct pci_bus *bus) if (i >= 3 && bus->self->transparent) continue; - /* If we are going to re-assign everything, mark the resource - * as unset and move it down to 0 + /* If we're going to reassign everything, we can + * shrink the P2P resource to have size as being + * of 0 in order to save space. */ if (pci_has_flag(PCI_REASSIGN_ALL_RSRC)) { res->flags |= IORESOURCE_UNSET; - res->end -= res->start; res->start = 0; + res->end = -1; continue; } @@ -1248,7 +1249,14 @@ void pcibios_allocate_bus_resources(struct pci_bus *bus) pr_warning("PCI: Cannot allocate resource region " "%d of PCI bridge %d, will remap\n", i, bus->number); clear_resource: - res->start = res->end = 0; + /* The resource might be figured out when doing + * reassignment based on the resources required + * by the downstream PCI devices. Here we set + * the size of the resource to be 0 in order to + * save more space. + */ + res->start = 0; + res->end = -1; res->flags = 0; } diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 1a1f2ddfb58..50e504c29bb 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -258,6 +258,7 @@ void do_send_trap(struct pt_regs *regs, unsigned long address, { siginfo_t info; + current->thread.trap_nr = signal_code; if (notify_die(DIE_DABR_MATCH, "dabr_match", regs, error_code, 11, SIGSEGV) == NOTIFY_STOP) return; @@ -275,6 +276,7 @@ void do_dabr(struct pt_regs *regs, unsigned long address, { siginfo_t info; + current->thread.trap_nr = TRAP_HWBKPT; if (notify_die(DIE_DABR_MATCH, "dabr_match", regs, error_code, 11, SIGSEGV) == NOTIFY_STOP) return; @@ -283,7 +285,7 @@ void do_dabr(struct pt_regs *regs, unsigned long address, return; /* Clear the DABR */ - set_dabr(0); + set_dabr(0, 0); /* Deliver the signal to userspace */ info.si_signo = SIGTRAP; @@ -364,18 +366,19 @@ static void set_debug_reg_defaults(struct thread_struct *thread) { if (thread->dabr) { thread->dabr = 0; - set_dabr(0); + thread->dabrx = 0; + set_dabr(0, 0); } } #endif /* !CONFIG_HAVE_HW_BREAKPOINT */ #endif /* CONFIG_PPC_ADV_DEBUG_REGS */ -int set_dabr(unsigned long dabr) +int set_dabr(unsigned long dabr, unsigned long dabrx) { __get_cpu_var(current_dabr) = dabr; if (ppc_md.set_dabr) - return ppc_md.set_dabr(dabr); + return ppc_md.set_dabr(dabr, dabrx); /* XXX should we have a CPU_FTR_HAS_DABR ? */ #ifdef CONFIG_PPC_ADV_DEBUG_REGS @@ -385,9 +388,8 @@ int set_dabr(unsigned long dabr) #endif #elif defined(CONFIG_PPC_BOOK3S) mtspr(SPRN_DABR, dabr); + mtspr(SPRN_DABRX, dabrx); #endif - - return 0; } @@ -480,7 +482,7 @@ struct task_struct *__switch_to(struct task_struct *prev, */ #ifndef CONFIG_HAVE_HW_BREAKPOINT if (unlikely(__get_cpu_var(current_dabr) != new->thread.dabr)) - set_dabr(new->thread.dabr); + set_dabr(new->thread.dabr, new->thread.dabrx); #endif /* CONFIG_HAVE_HW_BREAKPOINT */ #endif diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index f191bf02943..37725e86651 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -78,7 +78,7 @@ static int __init early_parse_mem(char *p) return 1; memory_limit = PAGE_ALIGN(memparse(p, &p)); - DBG("memory limit = 0x%llx\n", (unsigned long long)memory_limit); + DBG("memory limit = 0x%llx\n", memory_limit); return 0; } @@ -661,7 +661,7 @@ void __init early_init_devtree(void *params) /* make sure we've parsed cmdline for mem= before this */ if (memory_limit) - first_memblock_size = min(first_memblock_size, memory_limit); + first_memblock_size = min_t(u64, first_memblock_size, memory_limit); setup_initial_memory_limit(memstart_addr, first_memblock_size); /* Reserve MEMBLOCK regions used by kernel, initrd, dt, etc... */ memblock_reserve(PHYSICAL_START, __pa(klimit) - PHYSICAL_START); diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 0794a3017b1..ce68278a5d7 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -1691,7 +1691,7 @@ static void __init prom_initialize_tce_table(void) * else will impact performance, so we always allocate 8MB. * Anton */ - if (__is_processor(PV_POWER4) || __is_processor(PV_POWER4p)) + if (pvr_version_is(PVR_POWER4) || pvr_version_is(PVR_POWER4p)) minsize = 8UL << 20; else minsize = 4UL << 20; diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index c10fc28b909..79d8e56470d 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -960,6 +960,7 @@ int ptrace_set_debugreg(struct task_struct *task, unsigned long addr, thread->ptrace_bps[0] = bp; ptrace_put_breakpoints(task); thread->dabr = data; + thread->dabrx = DABRX_ALL; return 0; } @@ -983,6 +984,7 @@ int ptrace_set_debugreg(struct task_struct *task, unsigned long addr, /* Move contents to the DABR register */ task->thread.dabr = data; + task->thread.dabrx = DABRX_ALL; #else /* CONFIG_PPC_ADV_DEBUG_REGS */ /* As described above, it was assumed 3 bits were passed with the data * address, but we will assume only the mode bits will be passed @@ -1397,6 +1399,7 @@ static long ppc_set_hwdebug(struct task_struct *child, dabr |= DABR_DATA_WRITE; child->thread.dabr = dabr; + child->thread.dabrx = DABRX_ALL; return 1; #endif /* !CONFIG_PPC_ADV_DEBUG_DVCS */ diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c index 2c0ee640563..20b0120db0c 100644 --- a/arch/powerpc/kernel/rtas_flash.c +++ b/arch/powerpc/kernel/rtas_flash.c @@ -21,7 +21,6 @@ #include <asm/delay.h> #include <asm/uaccess.h> #include <asm/rtas.h> -#include <asm/abs_addr.h> #define MODULE_VERS "1.0" #define MODULE_NAME "rtas_flash" @@ -582,7 +581,7 @@ static void rtas_flash_firmware(int reboot_type) flist = (struct flash_block_list *)&rtas_data_buf[0]; flist->num_blocks = 0; flist->next = rtas_firmware_flash_list; - rtas_block_list = virt_to_abs(flist); + rtas_block_list = __pa(flist); if (rtas_block_list >= 4UL*1024*1024*1024) { printk(KERN_ALERT "FLASH: kernel bug...flash list header addr above 4GB\n"); spin_unlock(&rtas_data_buf_lock); @@ -596,13 +595,13 @@ static void rtas_flash_firmware(int reboot_type) for (f = flist; f; f = next) { /* Translate data addrs to absolute */ for (i = 0; i < f->num_blocks; i++) { - f->blocks[i].data = (char *)virt_to_abs(f->blocks[i].data); + f->blocks[i].data = (char *)__pa(f->blocks[i].data); image_size += f->blocks[i].length; } next = f->next; /* Don't translate NULL pointer for last entry */ if (f->next) - f->next = (struct flash_block_list *)virt_to_abs(f->next); + f->next = (struct flash_block_list *)__pa(f->next); else f->next = NULL; /* make num_blocks into the version/length field */ diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c index 179af906dcd..6de63e3250b 100644 --- a/arch/powerpc/kernel/rtas_pci.c +++ b/arch/powerpc/kernel/rtas_pci.c @@ -81,7 +81,7 @@ int rtas_read_config(struct pci_dn *pdn, int where, int size, u32 *val) return PCIBIOS_DEVICE_NOT_FOUND; if (returnval == EEH_IO_ERROR_VALUE(size) && - eeh_dn_check_failure (pdn->node, NULL)) + eeh_dev_check_failure(of_node_to_eeh_dev(pdn->node))) return PCIBIOS_DEVICE_NOT_FOUND; return PCIBIOS_SUCCESSFUL; @@ -275,9 +275,6 @@ void __init find_and_init_phbs(void) of_node_put(root); pci_devs_phb_init(); - /* Create EEH devices for all PHBs */ - eeh_dev_phb_init(); - /* * PCI_PROBE_ONLY and PCI_REASSIGN_ALL_BUS can be set via properties * in chosen. diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index 5c023c9cf16..a2dc75793bd 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -11,6 +11,7 @@ #include <linux/tracehook.h> #include <linux/signal.h> +#include <linux/uprobes.h> #include <linux/key.h> #include <asm/hw_breakpoint.h> #include <asm/uaccess.h> @@ -130,7 +131,7 @@ static int do_signal(struct pt_regs *regs) * triggered inside the kernel. */ if (current->thread.dabr) - set_dabr(current->thread.dabr); + set_dabr(current->thread.dabr, current->thread.dabrx); #endif /* Re-enable the breakpoints for the signal stack */ thread_change_pc(current, regs); @@ -157,6 +158,11 @@ static int do_signal(struct pt_regs *regs) void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags) { + if (thread_info_flags & _TIF_UPROBE) { + clear_thread_flag(TIF_UPROBE); + uprobe_notify_resume(regs); + } + if (thread_info_flags & _TIF_SIGPENDING) do_signal(regs); diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index ae0843fa7a6..32518401af6 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -251,6 +251,7 @@ void _exception(int signr, struct pt_regs *regs, int code, unsigned long addr) if (arch_irqs_disabled() && !arch_irq_disabled_regs(regs)) local_irq_enable(); + current->thread.trap_nr = code; memset(&info, 0, sizeof(info)); info.si_signo = signr; info.si_code = code; diff --git a/arch/powerpc/kernel/uprobes.c b/arch/powerpc/kernel/uprobes.c new file mode 100644 index 00000000000..d2d46d1014f --- /dev/null +++ b/arch/powerpc/kernel/uprobes.c @@ -0,0 +1,184 @@ +/* + * User-space Probes (UProbes) for powerpc + * + * 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. + * + * Copyright IBM Corporation, 2007-2012 + * + * Adapted from the x86 port by Ananth N Mavinakayanahalli <ananth@in.ibm.com> + */ +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/ptrace.h> +#include <linux/uprobes.h> +#include <linux/uaccess.h> +#include <linux/kdebug.h> + +#include <asm/sstep.h> + +#define UPROBE_TRAP_NR UINT_MAX + +/** + * arch_uprobe_analyze_insn + * @mm: the probed address space. + * @arch_uprobe: the probepoint information. + * @addr: vaddr to probe. + * Return 0 on success or a -ve number on error. + */ +int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, + struct mm_struct *mm, unsigned long addr) +{ + if (addr & 0x03) + return -EINVAL; + + /* + * We currently don't support a uprobe on an already + * existing breakpoint instruction underneath + */ + if (is_trap(auprobe->ainsn)) + return -ENOTSUPP; + return 0; +} + +/* + * arch_uprobe_pre_xol - prepare to execute out of line. + * @auprobe: the probepoint information. + * @regs: reflects the saved user state of current task. + */ +int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) +{ + struct arch_uprobe_task *autask = ¤t->utask->autask; + + autask->saved_trap_nr = current->thread.trap_nr; + current->thread.trap_nr = UPROBE_TRAP_NR; + regs->nip = current->utask->xol_vaddr; + return 0; +} + +/** + * uprobe_get_swbp_addr - compute address of swbp given post-swbp regs + * @regs: Reflects the saved state of the task after it has hit a breakpoint + * instruction. + * Return the address of the breakpoint instruction. + */ +unsigned long uprobe_get_swbp_addr(struct pt_regs *regs) +{ + return instruction_pointer(regs); +} + +/* + * If xol insn itself traps and generates a signal (SIGILL/SIGSEGV/etc), + * then detect the case where a singlestepped instruction jumps back to its + * own address. It is assumed that anything like do_page_fault/do_trap/etc + * sets thread.trap_nr != UINT_MAX. + * + * arch_uprobe_pre_xol/arch_uprobe_post_xol save/restore thread.trap_nr, + * arch_uprobe_xol_was_trapped() simply checks that ->trap_nr is not equal to + * UPROBE_TRAP_NR == UINT_MAX set by arch_uprobe_pre_xol(). + */ +bool arch_uprobe_xol_was_trapped(struct task_struct *t) +{ + if (t->thread.trap_nr != UPROBE_TRAP_NR) + return true; + + return false; +} + +/* + * Called after single-stepping. To avoid the SMP problems that can + * occur when we temporarily put back the original opcode to + * single-step, we single-stepped a copy of the instruction. + * + * This function prepares to resume execution after the single-step. + */ +int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) +{ + struct uprobe_task *utask = current->utask; + + WARN_ON_ONCE(current->thread.trap_nr != UPROBE_TRAP_NR); + + current->thread.trap_nr = utask->autask.saved_trap_nr; + + /* + * On powerpc, except for loads and stores, most instructions + * including ones that alter code flow (branches, calls, returns) + * are emulated in the kernel. We get here only if the emulation + * support doesn't exist and have to fix-up the next instruction + * to be executed. + */ + regs->nip = utask->vaddr + MAX_UINSN_BYTES; + return 0; +} + +/* callback routine for handling exceptions. */ +int arch_uprobe_exception_notify(struct notifier_block *self, + unsigned long val, void *data) +{ + struct die_args *args = data; + struct pt_regs *regs = args->regs; + + /* regs == NULL is a kernel bug */ + if (WARN_ON(!regs)) + return NOTIFY_DONE; + + /* We are only interested in userspace traps */ + if (!user_mode(regs)) + return NOTIFY_DONE; + + switch (val) { + case DIE_BPT: + if (uprobe_pre_sstep_notifier(regs)) + return NOTIFY_STOP; + break; + case DIE_SSTEP: + if (uprobe_post_sstep_notifier(regs)) + return NOTIFY_STOP; + default: + break; + } + return NOTIFY_DONE; +} + +/* + * This function gets called when XOL instruction either gets trapped or + * the thread has a fatal signal, so reset the instruction pointer to its + * probed address. + */ +void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) +{ + struct uprobe_task *utask = current->utask; + + current->thread.trap_nr = utask->autask.saved_trap_nr; + instruction_pointer_set(regs, utask->vaddr); +} + +/* + * See if the instruction can be emulated. + * Returns true if instruction was emulated, false otherwise. + */ +bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) +{ + int ret; + + /* + * emulate_step() returns 1 if the insn was successfully emulated. + * For all other cases, we need to single-step in hardware. + */ + ret = emulate_step(regs, auprobe->ainsn); + if (ret > 0) + return true; + + return false; +} diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index b67db22e102..1b2076f049c 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -723,9 +723,7 @@ int __cpuinit vdso_getcpu_init(void) val = (cpu & 0xfff) | ((node & 0xffff) << 16); mtspr(SPRN_SPRG3, val); -#ifdef CONFIG_KVM_BOOK3S_HANDLER - get_paca()->kvm_hstate.sprg3 = val; -#endif + get_paca()->sprg3 = val; put_cpu(); diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c index 02b32216bbc..201ba59738b 100644 --- a/arch/powerpc/kernel/vio.c +++ b/arch/powerpc/kernel/vio.c @@ -33,7 +33,6 @@ #include <asm/prom.h> #include <asm/firmware.h> #include <asm/tce.h> -#include <asm/abs_addr.h> #include <asm/page.h> #include <asm/hvcall.h> diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 44b72feaff7..74a24bbb963 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -1065,7 +1065,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) mtspr SPRN_DABRX,r6 /* Restore SPRG3 */ - ld r3,HSTATE_SPRG3(r13) + ld r3,PACA_SPRG3(r13) mtspr SPRN_SPRG3,r3 /* diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 08ffcf52a85..995f924e007 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -133,6 +133,7 @@ static int do_sigbus(struct pt_regs *regs, unsigned long address) up_read(¤t->mm->mmap_sem); if (user_mode(regs)) { + current->thread.trap_nr = BUS_ADRERR; info.si_signo = SIGBUS; info.si_errno = 0; info.si_code = BUS_ADRERR; diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c index 90039bc6411..f21e8ce8db3 100644 --- a/arch/powerpc/mm/hash_native_64.c +++ b/arch/powerpc/mm/hash_native_64.c @@ -14,10 +14,10 @@ #include <linux/spinlock.h> #include <linux/bitops.h> +#include <linux/of.h> #include <linux/threads.h> #include <linux/smp.h> -#include <asm/abs_addr.h> #include <asm/machdep.h> #include <asm/mmu.h> #include <asm/mmu_context.h> diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index 377e5cbedbb..ba45739bdfe 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -43,7 +43,6 @@ #include <asm/uaccess.h> #include <asm/machdep.h> #include <asm/prom.h> -#include <asm/abs_addr.h> #include <asm/tlbflush.h> #include <asm/io.h> #include <asm/eeh.h> @@ -651,7 +650,7 @@ static void __init htab_initialize(void) DBG("Hash table allocated at %lx, size: %lx\n", table, htab_size_bytes); - htab_address = abs_to_virt(table); + htab_address = __va(table); /* htab absolute addr + encoded htabsize */ _SDR1 = table + __ilog2(pteg_count) - 11; diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index 620b7acd2fd..95a45293e5a 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -62,7 +62,6 @@ #include <asm/cputable.h> #include <asm/sections.h> #include <asm/iommu.h> -#include <asm/abs_addr.h> #include <asm/vdso.h> #include "mmu_decl.h" diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index fbdad0e3929..44cf2b20503 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -62,7 +62,7 @@ int init_bootmem_done; int mem_init_done; -phys_addr_t memory_limit; +unsigned long long memory_limit; #ifdef CONFIG_HIGHMEM pte_t *kmap_pte; diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index 249a0631c4d..297d49547ea 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -51,7 +51,6 @@ #include <asm/processor.h> #include <asm/cputable.h> #include <asm/sections.h> -#include <asm/abs_addr.h> #include <asm/firmware.h> #include "mmu_decl.h" diff --git a/arch/powerpc/mm/stab.c b/arch/powerpc/mm/stab.c index 9106ebb118f..3f8efa6f299 100644 --- a/arch/powerpc/mm/stab.c +++ b/arch/powerpc/mm/stab.c @@ -20,7 +20,6 @@ #include <asm/paca.h> #include <asm/cputable.h> #include <asm/prom.h> -#include <asm/abs_addr.h> struct stab_entry { unsigned long esid_data; @@ -257,7 +256,7 @@ void __init stabs_alloc(void) memset((void *)newstab, 0, HW_PAGE_SIZE); paca[cpu].stab_addr = newstab; - paca[cpu].stab_real = virt_to_abs(newstab); + paca[cpu].stab_real = __pa(newstab); printk(KERN_INFO "Segment table for CPU %d at 0x%llx " "virtual, 0x%llx absolute\n", cpu, paca[cpu].stab_addr, paca[cpu].stab_real); diff --git a/arch/powerpc/mm/subpage-prot.c b/arch/powerpc/mm/subpage-prot.c index e4f8f1fc81a..7c415ddde94 100644 --- a/arch/powerpc/mm/subpage-prot.c +++ b/arch/powerpc/mm/subpage-prot.c @@ -95,7 +95,8 @@ static void subpage_prot_clear(unsigned long addr, unsigned long len) struct mm_struct *mm = current->mm; struct subpage_prot_table *spt = &mm->context.spt; u32 **spm, *spp; - int i, nw; + unsigned long i; + size_t nw; unsigned long next, limit; down_write(&mm->mmap_sem); @@ -144,7 +145,8 @@ long sys_subpage_prot(unsigned long addr, unsigned long len, u32 __user *map) struct mm_struct *mm = current->mm; struct subpage_prot_table *spt = &mm->context.spt; u32 **spm, *spp; - int i, nw; + unsigned long i; + size_t nw; unsigned long next, limit; int err; diff --git a/arch/powerpc/mm/tlb_low_64e.S b/arch/powerpc/mm/tlb_low_64e.S index f09d48e3268..b4113bf8635 100644 --- a/arch/powerpc/mm/tlb_low_64e.S +++ b/arch/powerpc/mm/tlb_low_64e.S @@ -20,6 +20,8 @@ #include <asm/pgtable.h> #include <asm/exception-64e.h> #include <asm/ppc-opcode.h> +#include <asm/kvm_asm.h> +#include <asm/kvm_booke_hv_asm.h> #ifdef CONFIG_PPC_64K_PAGES #define VPTE_PMD_SHIFT (PTE_INDEX_SIZE+1) @@ -37,12 +39,18 @@ * * **********************************************************************/ -.macro tlb_prolog_bolted addr - mtspr SPRN_SPRG_TLB_SCRATCH,r13 +.macro tlb_prolog_bolted intnum addr + mtspr SPRN_SPRG_GEN_SCRATCH,r13 mfspr r13,SPRN_SPRG_PACA std r10,PACA_EXTLB+EX_TLB_R10(r13) mfcr r10 std r11,PACA_EXTLB+EX_TLB_R11(r13) +#ifdef CONFIG_KVM_BOOKE_HV +BEGIN_FTR_SECTION + mfspr r11, SPRN_SRR1 +END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV) +#endif + DO_KVM \intnum, SPRN_SRR1 std r16,PACA_EXTLB+EX_TLB_R16(r13) mfspr r16,\addr /* get faulting address */ std r14,PACA_EXTLB+EX_TLB_R14(r13) @@ -61,12 +69,12 @@ ld r15,PACA_EXTLB+EX_TLB_R15(r13) TLB_MISS_RESTORE_STATS_BOLTED ld r16,PACA_EXTLB+EX_TLB_R16(r13) - mfspr r13,SPRN_SPRG_TLB_SCRATCH + mfspr r13,SPRN_SPRG_GEN_SCRATCH .endm /* Data TLB miss */ START_EXCEPTION(data_tlb_miss_bolted) - tlb_prolog_bolted SPRN_DEAR + tlb_prolog_bolted BOOKE_INTERRUPT_DTLB_MISS SPRN_DEAR /* We need _PAGE_PRESENT and _PAGE_ACCESSED set */ @@ -214,7 +222,7 @@ itlb_miss_fault_bolted: /* Instruction TLB miss */ START_EXCEPTION(instruction_tlb_miss_bolted) - tlb_prolog_bolted SPRN_SRR0 + tlb_prolog_bolted BOOKE_INTERRUPT_ITLB_MISS SPRN_SRR0 rldicl. r10,r16,64-PGTABLE_EADDR_SIZE,PGTABLE_EADDR_SIZE+4 srdi r15,r16,60 /* get region */ diff --git a/arch/powerpc/oprofile/op_model_power4.c b/arch/powerpc/oprofile/op_model_power4.c index 95ae77dec3f..315f9495e9b 100644 --- a/arch/powerpc/oprofile/op_model_power4.c +++ b/arch/powerpc/oprofile/op_model_power4.c @@ -21,6 +21,13 @@ #include <asm/reg.h> #define dbg(args...) +#define OPROFILE_PM_PMCSEL_MSK 0xffULL +#define OPROFILE_PM_UNIT_SHIFT 60 +#define OPROFILE_PM_UNIT_MSK 0xfULL +#define OPROFILE_MAX_PMC_NUM 3 +#define OPROFILE_PMSEL_FIELD_WIDTH 8 +#define OPROFILE_UNIT_FIELD_WIDTH 4 +#define MMCRA_SIAR_VALID_MASK 0x10000000ULL static unsigned long reset_value[OP_MAX_COUNTER]; @@ -31,6 +38,61 @@ static int use_slot_nums; static u32 mmcr0_val; static u64 mmcr1_val; static u64 mmcra_val; +static u32 cntr_marked_events; + +static int power7_marked_instr_event(u64 mmcr1) +{ + u64 psel, unit; + int pmc, cntr_marked_events = 0; + + /* Given the MMCR1 value, look at the field for each counter to + * determine if it is a marked event. Code based on the function + * power7_marked_instr_event() in file arch/powerpc/perf/power7-pmu.c. + */ + for (pmc = 0; pmc < 4; pmc++) { + psel = mmcr1 & (OPROFILE_PM_PMCSEL_MSK + << (OPROFILE_MAX_PMC_NUM - pmc) + * OPROFILE_MAX_PMC_NUM); + psel = (psel >> ((OPROFILE_MAX_PMC_NUM - pmc) + * OPROFILE_PMSEL_FIELD_WIDTH)) & ~1ULL; + unit = mmcr1 & (OPROFILE_PM_UNIT_MSK + << (OPROFILE_PM_UNIT_SHIFT + - (pmc * OPROFILE_PMSEL_FIELD_WIDTH ))); + unit = unit >> (OPROFILE_PM_UNIT_SHIFT + - (pmc * OPROFILE_PMSEL_FIELD_WIDTH)); + + switch (psel >> 4) { + case 2: + cntr_marked_events |= (pmc == 1 || pmc == 3) << pmc; + break; + case 3: + if (psel == 0x3c) { + cntr_marked_events |= (pmc == 0) << pmc; + break; + } + + if (psel == 0x3e) { + cntr_marked_events |= (pmc != 1) << pmc; + break; + } + + cntr_marked_events |= 1 << pmc; + break; + case 4: + case 5: + cntr_marked_events |= (unit == 0xd) << pmc; + break; + case 6: + if (psel == 0x64) + cntr_marked_events |= (pmc >= 2) << pmc; + break; + case 8: + cntr_marked_events |= (unit == 0xd) << pmc; + break; + } + } + return cntr_marked_events; +} static int power4_reg_setup(struct op_counter_config *ctr, struct op_system_config *sys, @@ -47,6 +109,23 @@ static int power4_reg_setup(struct op_counter_config *ctr, mmcr1_val = sys->mmcr1; mmcra_val = sys->mmcra; + /* Power 7+ and newer architectures: + * Determine which counter events in the group (the group of events is + * specified by the bit settings in the MMCR1 register) are marked + * events for use in the interrupt handler. Do the calculation once + * before OProfile starts. Information is used in the interrupt + * handler. Starting with Power 7+ we only record the sample for + * marked events if the SIAR valid bit is set. For non marked events + * the sample is always recorded. + */ + if (pvr_version_is(PVR_POWER7p)) + cntr_marked_events = power7_marked_instr_event(mmcr1_val); + else + cntr_marked_events = 0; /* For older processors, set the bit map + * to zero so the sample will always be + * be recorded. + */ + for (i = 0; i < cur_cpu_spec->num_pmcs; ++i) reset_value[i] = 0x80000000UL - ctr[i].count; @@ -61,10 +140,10 @@ static int power4_reg_setup(struct op_counter_config *ctr, else mmcr0_val |= MMCR0_PROBLEM_DISABLE; - if (__is_processor(PV_POWER4) || __is_processor(PV_POWER4p) || - __is_processor(PV_970) || __is_processor(PV_970FX) || - __is_processor(PV_970MP) || __is_processor(PV_970GX) || - __is_processor(PV_POWER5) || __is_processor(PV_POWER5p)) + if (pvr_version_is(PVR_POWER4) || pvr_version_is(PVR_POWER4p) || + pvr_version_is(PVR_970) || pvr_version_is(PVR_970FX) || + pvr_version_is(PVR_970MP) || pvr_version_is(PVR_970GX) || + pvr_version_is(PVR_POWER5) || pvr_version_is(PVR_POWER5p)) use_slot_nums = 1; return 0; @@ -84,9 +163,9 @@ extern void ppc_enable_pmcs(void); */ static inline int mmcra_must_set_sample(void) { - if (__is_processor(PV_POWER4) || __is_processor(PV_POWER4p) || - __is_processor(PV_970) || __is_processor(PV_970FX) || - __is_processor(PV_970MP) || __is_processor(PV_970GX)) + if (pvr_version_is(PVR_POWER4) || pvr_version_is(PVR_POWER4p) || + pvr_version_is(PVR_970) || pvr_version_is(PVR_970FX) || + pvr_version_is(PVR_970MP) || pvr_version_is(PVR_970GX)) return 1; return 0; @@ -276,7 +355,7 @@ static bool pmc_overflow(unsigned long val) * PMCs because a user might set a period of less than 256 and we * don't want to mistakenly reset them. */ - if (__is_processor(PV_POWER7) && ((0x80000000 - val) <= 256)) + if (pvr_version_is(PVR_POWER7) && ((0x80000000 - val) <= 256)) return true; return false; @@ -291,6 +370,7 @@ static void power4_handle_interrupt(struct pt_regs *regs, int i; unsigned int mmcr0; unsigned long mmcra; + bool siar_valid = false; mmcra = mfspr(SPRN_MMCRA); @@ -300,11 +380,29 @@ static void power4_handle_interrupt(struct pt_regs *regs, /* set the PMM bit (see comment below) */ mtmsrd(mfmsr() | MSR_PMM); + /* Check that the SIAR valid bit in MMCRA is set to 1. */ + if ((mmcra & MMCRA_SIAR_VALID_MASK) == MMCRA_SIAR_VALID_MASK) + siar_valid = true; + for (i = 0; i < cur_cpu_spec->num_pmcs; ++i) { val = classic_ctr_read(i); if (pmc_overflow(val)) { if (oprofile_running && ctr[i].enabled) { - oprofile_add_ext_sample(pc, regs, i, is_kernel); + /* Power 7+ and newer architectures: + * If the event is a marked event, then only + * save the sample if the SIAR valid bit is + * set. If the event is not marked, then + * always save the sample. + * Note, the Sample enable bit in the MMCRA + * register must be set to 1 if the group + * contains a marked event. + */ + if ((siar_valid && + (cntr_marked_events & (1 << i))) + || !(cntr_marked_events & (1 << i))) + oprofile_add_ext_sample(pc, regs, i, + is_kernel); + classic_ctr_write(i, reset_value[i]); } else { classic_ctr_write(i, 0); diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 7cd2dbd6e4c..fb55da91aa4 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -1396,7 +1396,7 @@ static bool pmc_overflow(unsigned long val) * PMCs because a user might set a period of less than 256 and we * don't want to mistakenly reset them. */ - if (__is_processor(PV_POWER7) && ((0x80000000 - val) <= 256)) + if (pvr_version_is(PVR_POWER7) && ((0x80000000 - val) <= 256)) return true; return false; diff --git a/arch/powerpc/platforms/cell/beat.c b/arch/powerpc/platforms/cell/beat.c index 852592b2b71..affcf566d46 100644 --- a/arch/powerpc/platforms/cell/beat.c +++ b/arch/powerpc/platforms/cell/beat.c @@ -136,9 +136,9 @@ ssize_t beat_nvram_get_size(void) return BEAT_NVRAM_SIZE; } -int beat_set_xdabr(unsigned long dabr) +int beat_set_xdabr(unsigned long dabr, unsigned long dabrx) { - if (beat_set_dabr(dabr, DABRX_KERNEL | DABRX_USER)) + if (beat_set_dabr(dabr, dabrx)) return -1; return 0; } diff --git a/arch/powerpc/platforms/cell/beat.h b/arch/powerpc/platforms/cell/beat.h index 32c8efcedc8..bfcb8e351ae 100644 --- a/arch/powerpc/platforms/cell/beat.h +++ b/arch/powerpc/platforms/cell/beat.h @@ -32,7 +32,7 @@ void beat_get_rtc_time(struct rtc_time *); ssize_t beat_nvram_get_size(void); ssize_t beat_nvram_read(char *, size_t, loff_t *); ssize_t beat_nvram_write(char *, size_t, loff_t *); -int beat_set_xdabr(unsigned long); +int beat_set_xdabr(unsigned long, unsigned long); void beat_power_save(void); void beat_kexec_cpu_down(int, int); diff --git a/arch/powerpc/platforms/pasemi/iommu.c b/arch/powerpc/platforms/pasemi/iommu.c index 14943ef0191..7d2d036754b 100644 --- a/arch/powerpc/platforms/pasemi/iommu.c +++ b/arch/powerpc/platforms/pasemi/iommu.c @@ -19,12 +19,12 @@ #undef DEBUG +#include <linux/memblock.h> #include <linux/types.h> #include <linux/spinlock.h> #include <linux/pci.h> #include <asm/iommu.h> #include <asm/machdep.h> -#include <asm/abs_addr.h> #include <asm/firmware.h> #define IOBMAP_PAGE_SHIFT 12 @@ -99,7 +99,7 @@ static int iobmap_build(struct iommu_table *tbl, long index, ip = ((u32 *)tbl->it_base) + index; while (npages--) { - rpn = virt_to_abs(uaddr) >> IOBMAP_PAGE_SHIFT; + rpn = __pa(uaddr) >> IOBMAP_PAGE_SHIFT; *(ip++) = IOBMAP_L2E_V | rpn; /* invalidate tlb, can be optimized more */ @@ -258,7 +258,7 @@ void __init alloc_iobmap_l2(void) return; #endif /* For 2G space, 8x64 pages (2^21 bytes) is max total l2 size */ - iob_l2_base = (u32 *)abs_to_virt(memblock_alloc_base(1UL<<21, 1UL<<21, 0x80000000)); + iob_l2_base = (u32 *)__va(memblock_alloc_base(1UL<<21, 1UL<<21, 0x80000000)); printk(KERN_INFO "IOBMAP L2 allocated at: %p\n", iob_l2_base); } diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 0e7eccc0f88..cae7281e4e6 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -30,7 +30,6 @@ #include <asm/opal.h> #include <asm/iommu.h> #include <asm/tce.h> -#include <asm/abs_addr.h> #include "powernv.h" #include "pci.h" diff --git a/arch/powerpc/platforms/powernv/pci-p5ioc2.c b/arch/powerpc/platforms/powernv/pci-p5ioc2.c index 264967770c3..6b4bef4e9d8 100644 --- a/arch/powerpc/platforms/powernv/pci-p5ioc2.c +++ b/arch/powerpc/platforms/powernv/pci-p5ioc2.c @@ -30,7 +30,6 @@ #include <asm/opal.h> #include <asm/iommu.h> #include <asm/tce.h> -#include <asm/abs_addr.h> #include "powernv.h" #include "pci.h" diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index be3cfc5ceab..c01688a1a74 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -30,7 +30,6 @@ #include <asm/opal.h> #include <asm/iommu.h> #include <asm/tce.h> -#include <asm/abs_addr.h> #include <asm/firmware.h> #include "powernv.h" @@ -447,6 +446,11 @@ static void pnv_tce_free(struct iommu_table *tbl, long index, long npages) pnv_tce_invalidate(tbl, tces, tcep - 1); } +static unsigned long pnv_tce_get(struct iommu_table *tbl, long index) +{ + return ((u64 *)tbl->it_base)[index - tbl->it_offset]; +} + void pnv_pci_setup_iommu_table(struct iommu_table *tbl, void *tce_mem, u64 tce_size, u64 dma_offset) @@ -597,6 +601,7 @@ void __init pnv_pci_init(void) ppc_md.pci_dma_dev_setup = pnv_pci_dma_dev_setup; ppc_md.tce_build = pnv_tce_build; ppc_md.tce_free = pnv_tce_free; + ppc_md.tce_get = pnv_tce_get; ppc_md.pci_probe_mode = pnv_pci_probe_mode; set_pci_dma_ops(&dma_iommu_ops); diff --git a/arch/powerpc/platforms/ps3/setup.c b/arch/powerpc/platforms/ps3/setup.c index 2d664c5a83b..3f509f86432 100644 --- a/arch/powerpc/platforms/ps3/setup.c +++ b/arch/powerpc/platforms/ps3/setup.c @@ -184,11 +184,15 @@ early_param("ps3flash", early_parse_ps3flash); #define prealloc_ps3flash_bounce_buffer() do { } while (0) #endif -static int ps3_set_dabr(unsigned long dabr) +static int ps3_set_dabr(unsigned long dabr, unsigned long dabrx) { - enum {DABR_USER = 1, DABR_KERNEL = 2,}; + /* Have to set at least one bit in the DABRX */ + if (dabrx == 0 && dabr == 0) + dabrx = DABRX_USER; + /* hypervisor only allows us to set BTI, Kernel and user */ + dabrx &= DABRX_BTI | DABRX_KERNEL | DABRX_USER; - return lv1_set_dabr(dabr, DABR_KERNEL | DABR_USER) ? -1 : 0; + return lv1_set_dabr(dabr, dabrx) ? -1 : 0; } static void __init ps3_setup_arch(void) diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile index c222189f5bb..890622b87c8 100644 --- a/arch/powerpc/platforms/pseries/Makefile +++ b/arch/powerpc/platforms/pseries/Makefile @@ -6,8 +6,9 @@ obj-y := lpar.o hvCall.o nvram.o reconfig.o \ firmware.o power.o dlpar.o mobility.o obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_SCANLOG) += scanlog.o -obj-$(CONFIG_EEH) += eeh.o eeh_dev.o eeh_cache.o eeh_driver.o \ - eeh_event.o eeh_sysfs.o eeh_pseries.o +obj-$(CONFIG_EEH) += eeh.o eeh_pe.o eeh_dev.o eeh_cache.o \ + eeh_driver.o eeh_event.o eeh_sysfs.o \ + eeh_pseries.o obj-$(CONFIG_KEXEC) += kexec.o obj-$(CONFIG_PCI) += pci.o pci_dlpar.o obj-$(CONFIG_PSERIES_MSI) += msi.o diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c index ecd394cf34e..18c168b752d 100644 --- a/arch/powerpc/platforms/pseries/eeh.c +++ b/arch/powerpc/platforms/pseries/eeh.c @@ -92,6 +92,20 @@ struct eeh_ops *eeh_ops = NULL; int eeh_subsystem_enabled; EXPORT_SYMBOL(eeh_subsystem_enabled); +/* + * EEH probe mode support. The intention is to support multiple + * platforms for EEH. Some platforms like pSeries do PCI emunation + * based on device tree. However, other platforms like powernv probe + * PCI devices from hardware. The flag is used to distinguish that. + * In addition, struct eeh_ops::probe would be invoked for particular + * OF node or PCI device so that the corresponding PE would be created + * there. + */ +int eeh_probe_mode; + +/* Global EEH mutex */ +DEFINE_MUTEX(eeh_mutex); + /* Lock to avoid races due to multiple reports of an error */ static DEFINE_RAW_SPINLOCK(confirm_error_lock); @@ -204,22 +218,12 @@ static size_t eeh_gather_pci_data(struct eeh_dev *edev, char * buf, size_t len) } } - /* Gather status on devices under the bridge */ - if (dev->class >> 16 == PCI_BASE_CLASS_BRIDGE) { - struct device_node *child; - - for_each_child_of_node(dn, child) { - if (of_node_to_eeh_dev(child)) - n += eeh_gather_pci_data(of_node_to_eeh_dev(child), buf+n, len-n); - } - } - return n; } /** * eeh_slot_error_detail - Generate combined log including driver log and error log - * @edev: device to report error log for + * @pe: EEH PE * @severity: temporary or permanent error log * * This routine should be called to generate the combined log, which @@ -227,17 +231,22 @@ static size_t eeh_gather_pci_data(struct eeh_dev *edev, char * buf, size_t len) * out from the config space of the corresponding PCI device, while * the error log is fetched through platform dependent function call. */ -void eeh_slot_error_detail(struct eeh_dev *edev, int severity) +void eeh_slot_error_detail(struct eeh_pe *pe, int severity) { size_t loglen = 0; - pci_regs_buf[0] = 0; + struct eeh_dev *edev; - eeh_pci_enable(edev, EEH_OPT_THAW_MMIO); - eeh_ops->configure_bridge(eeh_dev_to_of_node(edev)); - eeh_restore_bars(edev); - loglen = eeh_gather_pci_data(edev, pci_regs_buf, EEH_PCI_REGS_LOG_LEN); + eeh_pci_enable(pe, EEH_OPT_THAW_MMIO); + eeh_ops->configure_bridge(pe); + eeh_pe_restore_bars(pe); - eeh_ops->get_log(eeh_dev_to_of_node(edev), severity, pci_regs_buf, loglen); + pci_regs_buf[0] = 0; + eeh_pe_for_each_dev(pe, edev) { + loglen += eeh_gather_pci_data(edev, pci_regs_buf, + EEH_PCI_REGS_LOG_LEN); + } + + eeh_ops->get_log(pe, severity, pci_regs_buf, loglen); } /** @@ -261,126 +270,8 @@ static inline unsigned long eeh_token_to_phys(unsigned long token) } /** - * eeh_find_device_pe - Retrieve the PE for the given device - * @dn: device node - * - * Return the PE under which this device lies - */ -struct device_node *eeh_find_device_pe(struct device_node *dn) -{ - while (dn->parent && of_node_to_eeh_dev(dn->parent) && - (of_node_to_eeh_dev(dn->parent)->mode & EEH_MODE_SUPPORTED)) { - dn = dn->parent; - } - return dn; -} - -/** - * __eeh_mark_slot - Mark all child devices as failed - * @parent: parent device - * @mode_flag: failure flag - * - * Mark all devices that are children of this device as failed. - * Mark the device driver too, so that it can see the failure - * immediately; this is critical, since some drivers poll - * status registers in interrupts ... If a driver is polling, - * and the slot is frozen, then the driver can deadlock in - * an interrupt context, which is bad. - */ -static void __eeh_mark_slot(struct device_node *parent, int mode_flag) -{ - struct device_node *dn; - - for_each_child_of_node(parent, dn) { - if (of_node_to_eeh_dev(dn)) { - /* Mark the pci device driver too */ - struct pci_dev *dev = of_node_to_eeh_dev(dn)->pdev; - - of_node_to_eeh_dev(dn)->mode |= mode_flag; - - if (dev && dev->driver) - dev->error_state = pci_channel_io_frozen; - - __eeh_mark_slot(dn, mode_flag); - } - } -} - -/** - * eeh_mark_slot - Mark the indicated device and its children as failed - * @dn: parent device - * @mode_flag: failure flag - * - * Mark the indicated device and its child devices as failed. - * The device drivers are marked as failed as well. - */ -void eeh_mark_slot(struct device_node *dn, int mode_flag) -{ - struct pci_dev *dev; - dn = eeh_find_device_pe(dn); - - /* Back up one, since config addrs might be shared */ - if (!pcibios_find_pci_bus(dn) && of_node_to_eeh_dev(dn->parent)) - dn = dn->parent; - - of_node_to_eeh_dev(dn)->mode |= mode_flag; - - /* Mark the pci device too */ - dev = of_node_to_eeh_dev(dn)->pdev; - if (dev) - dev->error_state = pci_channel_io_frozen; - - __eeh_mark_slot(dn, mode_flag); -} - -/** - * __eeh_clear_slot - Clear failure flag for the child devices - * @parent: parent device - * @mode_flag: flag to be cleared - * - * Clear failure flag for the child devices. - */ -static void __eeh_clear_slot(struct device_node *parent, int mode_flag) -{ - struct device_node *dn; - - for_each_child_of_node(parent, dn) { - if (of_node_to_eeh_dev(dn)) { - of_node_to_eeh_dev(dn)->mode &= ~mode_flag; - of_node_to_eeh_dev(dn)->check_count = 0; - __eeh_clear_slot(dn, mode_flag); - } - } -} - -/** - * eeh_clear_slot - Clear failure flag for the indicated device and its children - * @dn: parent device - * @mode_flag: flag to be cleared - * - * Clear failure flag for the indicated device and its children. - */ -void eeh_clear_slot(struct device_node *dn, int mode_flag) -{ - unsigned long flags; - raw_spin_lock_irqsave(&confirm_error_lock, flags); - - dn = eeh_find_device_pe(dn); - - /* Back up one, since config addrs might be shared */ - if (!pcibios_find_pci_bus(dn) && of_node_to_eeh_dev(dn->parent)) - dn = dn->parent; - - of_node_to_eeh_dev(dn)->mode &= ~mode_flag; - of_node_to_eeh_dev(dn)->check_count = 0; - __eeh_clear_slot(dn, mode_flag); - raw_spin_unlock_irqrestore(&confirm_error_lock, flags); -} - -/** - * eeh_dn_check_failure - Check if all 1's data is due to EEH slot freeze - * @dn: device node - * @dev: pci device, if known + * eeh_dev_check_failure - Check if all 1's data is due to EEH slot freeze + * @edev: eeh device * * Check for an EEH failure for the given device node. Call this * routine if the result of a read was all 0xff's and you want to @@ -392,11 +283,13 @@ void eeh_clear_slot(struct device_node *dn, int mode_flag) * * It is safe to call this routine in an interrupt context. */ -int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev) +int eeh_dev_check_failure(struct eeh_dev *edev) { int ret; unsigned long flags; - struct eeh_dev *edev; + struct device_node *dn; + struct pci_dev *dev; + struct eeh_pe *pe; int rc = 0; const char *location; @@ -405,23 +298,23 @@ int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev) if (!eeh_subsystem_enabled) return 0; - if (!dn) { + if (!edev) { eeh_stats.no_dn++; return 0; } - dn = eeh_find_device_pe(dn); - edev = of_node_to_eeh_dev(dn); + dn = eeh_dev_to_of_node(edev); + dev = eeh_dev_to_pci_dev(edev); + pe = edev->pe; /* Access to IO BARs might get this far and still not want checking. */ - if (!(edev->mode & EEH_MODE_SUPPORTED) || - edev->mode & EEH_MODE_NOCHECK) { + if (!pe) { eeh_stats.ignored_check++; - pr_debug("EEH: Ignored check (%x) for %s %s\n", - edev->mode, eeh_pci_name(dev), dn->full_name); + pr_debug("EEH: Ignored check for %s %s\n", + eeh_pci_name(dev), dn->full_name); return 0; } - if (!edev->config_addr && !edev->pe_config_addr) { + if (!pe->addr && !pe->config_addr) { eeh_stats.no_cfg_addr++; return 0; } @@ -434,13 +327,13 @@ int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev) */ raw_spin_lock_irqsave(&confirm_error_lock, flags); rc = 1; - if (edev->mode & EEH_MODE_ISOLATED) { - edev->check_count++; - if (edev->check_count % EEH_MAX_FAILS == 0) { + if (pe->state & EEH_PE_ISOLATED) { + pe->check_count++; + if (pe->check_count % EEH_MAX_FAILS == 0) { location = of_get_property(dn, "ibm,loc-code", NULL); printk(KERN_ERR "EEH: %d reads ignored for recovering device at " "location=%s driver=%s pci addr=%s\n", - edev->check_count, location, + pe->check_count, location, eeh_driver_name(dev), eeh_pci_name(dev)); printk(KERN_ERR "EEH: Might be infinite loop in %s driver\n", eeh_driver_name(dev)); @@ -456,7 +349,7 @@ int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev) * function zero of a multi-function device. * In any case they must share a common PHB. */ - ret = eeh_ops->get_state(dn, NULL); + ret = eeh_ops->get_state(pe, NULL); /* Note that config-io to empty slots may fail; * they are empty when they don't have children. @@ -469,7 +362,7 @@ int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev) (ret & (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) == (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) { eeh_stats.false_positives++; - edev->false_positives ++; + pe->false_positives++; rc = 0; goto dn_unlock; } @@ -480,10 +373,10 @@ int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev) * with other functions on this device, and functions under * bridges. */ - eeh_mark_slot(dn, EEH_MODE_ISOLATED); + eeh_pe_state_mark(pe, EEH_PE_ISOLATED); raw_spin_unlock_irqrestore(&confirm_error_lock, flags); - eeh_send_failure_event(edev); + eeh_send_failure_event(pe); /* Most EEH events are due to device driver bugs. Having * a stack trace will help the device-driver authors figure @@ -497,7 +390,7 @@ dn_unlock: return rc; } -EXPORT_SYMBOL_GPL(eeh_dn_check_failure); +EXPORT_SYMBOL_GPL(eeh_dev_check_failure); /** * eeh_check_failure - Check if all 1's data is due to EEH slot freeze @@ -514,21 +407,19 @@ EXPORT_SYMBOL_GPL(eeh_dn_check_failure); unsigned long eeh_check_failure(const volatile void __iomem *token, unsigned long val) { unsigned long addr; - struct pci_dev *dev; - struct device_node *dn; + struct eeh_dev *edev; /* Finding the phys addr + pci device; this is pretty quick. */ addr = eeh_token_to_phys((unsigned long __force) token); - dev = pci_addr_cache_get_device(addr); - if (!dev) { + edev = eeh_addr_cache_get_dev(addr); + if (!edev) { eeh_stats.no_device++; return val; } - dn = pci_device_to_OF_node(dev); - eeh_dn_check_failure(dn, dev); + eeh_dev_check_failure(edev); - pci_dev_put(dev); + pci_dev_put(eeh_dev_to_pci_dev(edev)); return val; } @@ -537,23 +428,22 @@ EXPORT_SYMBOL(eeh_check_failure); /** * eeh_pci_enable - Enable MMIO or DMA transfers for this slot - * @edev: pci device node + * @pe: EEH PE * * This routine should be called to reenable frozen MMIO or DMA * so that it would work correctly again. It's useful while doing * recovery or log collection on the indicated device. */ -int eeh_pci_enable(struct eeh_dev *edev, int function) +int eeh_pci_enable(struct eeh_pe *pe, int function) { int rc; - struct device_node *dn = eeh_dev_to_of_node(edev); - rc = eeh_ops->set_option(dn, function); + rc = eeh_ops->set_option(pe, function); if (rc) - printk(KERN_WARNING "EEH: Unexpected state change %d, err=%d dn=%s\n", - function, rc, dn->full_name); + pr_warning("%s: Unexpected state change %d on PHB#%d-PE#%x, err=%d\n", + __func__, function, pe->phb->global_number, pe->addr, rc); - rc = eeh_ops->wait_state(dn, PCI_BUS_RESET_WAIT_MSEC); + rc = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC); if (rc > 0 && (rc & EEH_STATE_MMIO_ENABLED) && (function == EEH_OPT_THAW_MMIO)) return 0; @@ -571,17 +461,24 @@ int eeh_pci_enable(struct eeh_dev *edev, int function) */ int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state state) { - struct device_node *dn = pci_device_to_OF_node(dev); + struct eeh_dev *edev = pci_dev_to_eeh_dev(dev); + struct eeh_pe *pe = edev->pe; + + if (!pe) { + pr_err("%s: No PE found on PCI device %s\n", + __func__, pci_name(dev)); + return -EINVAL; + } switch (state) { case pcie_deassert_reset: - eeh_ops->reset(dn, EEH_RESET_DEACTIVATE); + eeh_ops->reset(pe, EEH_RESET_DEACTIVATE); break; case pcie_hot_reset: - eeh_ops->reset(dn, EEH_RESET_HOT); + eeh_ops->reset(pe, EEH_RESET_HOT); break; case pcie_warm_reset: - eeh_ops->reset(dn, EEH_RESET_FUNDAMENTAL); + eeh_ops->reset(pe, EEH_RESET_FUNDAMENTAL); break; default: return -EINVAL; @@ -591,66 +488,37 @@ int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state stat } /** - * __eeh_set_pe_freset - Check the required reset for child devices - * @parent: parent device - * @freset: return value - * - * Each device might have its preferred reset type: fundamental or - * hot reset. The routine is used to collect the information from - * the child devices so that they could be reset accordingly. - */ -void __eeh_set_pe_freset(struct device_node *parent, unsigned int *freset) -{ - struct device_node *dn; - - for_each_child_of_node(parent, dn) { - if (of_node_to_eeh_dev(dn)) { - struct pci_dev *dev = of_node_to_eeh_dev(dn)->pdev; - - if (dev && dev->driver) - *freset |= dev->needs_freset; - - __eeh_set_pe_freset(dn, freset); - } - } -} - -/** - * eeh_set_pe_freset - Check the required reset for the indicated device and its children - * @dn: parent device - * @freset: return value + * eeh_set_pe_freset - Check the required reset for the indicated device + * @data: EEH device + * @flag: return value * * Each device might have its preferred reset type: fundamental or * hot reset. The routine is used to collected the information for * the indicated device and its children so that the bunch of the * devices could be reset properly. */ -void eeh_set_pe_freset(struct device_node *dn, unsigned int *freset) +static void *eeh_set_dev_freset(void *data, void *flag) { struct pci_dev *dev; - dn = eeh_find_device_pe(dn); - - /* Back up one, since config addrs might be shared */ - if (!pcibios_find_pci_bus(dn) && of_node_to_eeh_dev(dn->parent)) - dn = dn->parent; + unsigned int *freset = (unsigned int *)flag; + struct eeh_dev *edev = (struct eeh_dev *)data; - dev = of_node_to_eeh_dev(dn)->pdev; + dev = eeh_dev_to_pci_dev(edev); if (dev) *freset |= dev->needs_freset; - __eeh_set_pe_freset(dn, freset); + return NULL; } /** * eeh_reset_pe_once - Assert the pci #RST line for 1/4 second - * @edev: pci device node to be reset. + * @pe: EEH PE * * Assert the PCI #RST line for 1/4 second. */ -static void eeh_reset_pe_once(struct eeh_dev *edev) +static void eeh_reset_pe_once(struct eeh_pe *pe) { unsigned int freset = 0; - struct device_node *dn = eeh_dev_to_of_node(edev); /* Determine type of EEH reset required for * Partitionable Endpoint, a hot-reset (1) @@ -658,12 +526,12 @@ static void eeh_reset_pe_once(struct eeh_dev *edev) * A fundamental reset required by any device under * Partitionable Endpoint trumps hot-reset. */ - eeh_set_pe_freset(dn, &freset); + eeh_pe_dev_traverse(pe, eeh_set_dev_freset, &freset); if (freset) - eeh_ops->reset(dn, EEH_RESET_FUNDAMENTAL); + eeh_ops->reset(pe, EEH_RESET_FUNDAMENTAL); else - eeh_ops->reset(dn, EEH_RESET_HOT); + eeh_ops->reset(pe, EEH_RESET_HOT); /* The PCI bus requires that the reset be held high for at least * a 100 milliseconds. We wait a bit longer 'just in case'. @@ -675,9 +543,9 @@ static void eeh_reset_pe_once(struct eeh_dev *edev) * pci slot reset line is dropped. Make sure we don't miss * these, and clear the flag now. */ - eeh_clear_slot(dn, EEH_MODE_ISOLATED); + eeh_pe_state_clear(pe, EEH_PE_ISOLATED); - eeh_ops->reset(dn, EEH_RESET_DEACTIVATE); + eeh_ops->reset(pe, EEH_RESET_DEACTIVATE); /* After a PCI slot has been reset, the PCI Express spec requires * a 1.5 second idle time for the bus to stabilize, before starting @@ -689,116 +557,36 @@ static void eeh_reset_pe_once(struct eeh_dev *edev) /** * eeh_reset_pe - Reset the indicated PE - * @edev: PCI device associated EEH device + * @pe: EEH PE * * This routine should be called to reset indicated device, including * PE. A PE might include multiple PCI devices and sometimes PCI bridges * might be involved as well. */ -int eeh_reset_pe(struct eeh_dev *edev) +int eeh_reset_pe(struct eeh_pe *pe) { int i, rc; - struct device_node *dn = eeh_dev_to_of_node(edev); /* Take three shots at resetting the bus */ for (i=0; i<3; i++) { - eeh_reset_pe_once(edev); + eeh_reset_pe_once(pe); - rc = eeh_ops->wait_state(dn, PCI_BUS_RESET_WAIT_MSEC); + rc = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC); if (rc == (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) return 0; if (rc < 0) { - printk(KERN_ERR "EEH: unrecoverable slot failure %s\n", - dn->full_name); + pr_err("%s: Unrecoverable slot failure on PHB#%d-PE#%x", + __func__, pe->phb->global_number, pe->addr); return -1; } - printk(KERN_ERR "EEH: bus reset %d failed on slot %s, rc=%d\n", - i+1, dn->full_name, rc); + pr_err("EEH: bus reset %d failed on PHB#%d-PE#%x, rc=%d\n", + i+1, pe->phb->global_number, pe->addr, rc); } return -1; } -/** Save and restore of PCI BARs - * - * Although firmware will set up BARs during boot, it doesn't - * set up device BAR's after a device reset, although it will, - * if requested, set up bridge configuration. Thus, we need to - * configure the PCI devices ourselves. - */ - -/** - * eeh_restore_one_device_bars - Restore the Base Address Registers for one device - * @edev: PCI device associated EEH device - * - * Loads the PCI configuration space base address registers, - * the expansion ROM base address, the latency timer, and etc. - * from the saved values in the device node. - */ -static inline void eeh_restore_one_device_bars(struct eeh_dev *edev) -{ - int i; - u32 cmd; - struct device_node *dn = eeh_dev_to_of_node(edev); - - if (!edev->phb) - return; - - for (i=4; i<10; i++) { - eeh_ops->write_config(dn, i*4, 4, edev->config_space[i]); - } - - /* 12 == Expansion ROM Address */ - eeh_ops->write_config(dn, 12*4, 4, edev->config_space[12]); - -#define BYTE_SWAP(OFF) (8*((OFF)/4)+3-(OFF)) -#define SAVED_BYTE(OFF) (((u8 *)(edev->config_space))[BYTE_SWAP(OFF)]) - - eeh_ops->write_config(dn, PCI_CACHE_LINE_SIZE, 1, - SAVED_BYTE(PCI_CACHE_LINE_SIZE)); - - eeh_ops->write_config(dn, PCI_LATENCY_TIMER, 1, - SAVED_BYTE(PCI_LATENCY_TIMER)); - - /* max latency, min grant, interrupt pin and line */ - eeh_ops->write_config(dn, 15*4, 4, edev->config_space[15]); - - /* Restore PERR & SERR bits, some devices require it, - * don't touch the other command bits - */ - eeh_ops->read_config(dn, PCI_COMMAND, 4, &cmd); - if (edev->config_space[1] & PCI_COMMAND_PARITY) - cmd |= PCI_COMMAND_PARITY; - else - cmd &= ~PCI_COMMAND_PARITY; - if (edev->config_space[1] & PCI_COMMAND_SERR) - cmd |= PCI_COMMAND_SERR; - else - cmd &= ~PCI_COMMAND_SERR; - eeh_ops->write_config(dn, PCI_COMMAND, 4, cmd); -} - -/** - * eeh_restore_bars - Restore the PCI config space info - * @edev: EEH device - * - * This routine performs a recursive walk to the children - * of this device as well. - */ -void eeh_restore_bars(struct eeh_dev *edev) -{ - struct device_node *dn; - if (!edev) - return; - - if ((edev->mode & EEH_MODE_SUPPORTED) && !IS_BRIDGE(edev->class_code)) - eeh_restore_one_device_bars(edev); - - for_each_child_of_node(eeh_dev_to_of_node(edev), dn) - eeh_restore_bars(of_node_to_eeh_dev(dn)); -} - /** * eeh_save_bars - Save device bars * @edev: PCI device associated EEH device @@ -808,7 +596,7 @@ void eeh_restore_bars(struct eeh_dev *edev) * PCI devices are added individually; but, for the restore, * an entire slot is reset at a time. */ -static void eeh_save_bars(struct eeh_dev *edev) +void eeh_save_bars(struct eeh_dev *edev) { int i; struct device_node *dn; @@ -822,102 +610,6 @@ static void eeh_save_bars(struct eeh_dev *edev) } /** - * eeh_early_enable - Early enable EEH on the indicated device - * @dn: device node - * @data: BUID - * - * Enable EEH functionality on the specified PCI device. The function - * is expected to be called before real PCI probing is done. However, - * the PHBs have been initialized at this point. - */ -static void *eeh_early_enable(struct device_node *dn, void *data) -{ - int ret; - const u32 *class_code = of_get_property(dn, "class-code", NULL); - const u32 *vendor_id = of_get_property(dn, "vendor-id", NULL); - const u32 *device_id = of_get_property(dn, "device-id", NULL); - const u32 *regs; - int enable; - struct eeh_dev *edev = of_node_to_eeh_dev(dn); - - edev->class_code = 0; - edev->mode = 0; - edev->check_count = 0; - edev->freeze_count = 0; - edev->false_positives = 0; - - if (!of_device_is_available(dn)) - return NULL; - - /* Ignore bad nodes. */ - if (!class_code || !vendor_id || !device_id) - return NULL; - - /* There is nothing to check on PCI to ISA bridges */ - if (dn->type && !strcmp(dn->type, "isa")) { - edev->mode |= EEH_MODE_NOCHECK; - return NULL; - } - edev->class_code = *class_code; - - /* Ok... see if this device supports EEH. Some do, some don't, - * and the only way to find out is to check each and every one. - */ - regs = of_get_property(dn, "reg", NULL); - if (regs) { - /* First register entry is addr (00BBSS00) */ - /* Try to enable eeh */ - ret = eeh_ops->set_option(dn, EEH_OPT_ENABLE); - - enable = 0; - if (ret == 0) { - edev->config_addr = regs[0]; - - /* If the newer, better, ibm,get-config-addr-info is supported, - * then use that instead. - */ - edev->pe_config_addr = eeh_ops->get_pe_addr(dn); - - /* Some older systems (Power4) allow the - * ibm,set-eeh-option call to succeed even on nodes - * where EEH is not supported. Verify support - * explicitly. - */ - ret = eeh_ops->get_state(dn, NULL); - if (ret > 0 && ret != EEH_STATE_NOT_SUPPORT) - enable = 1; - } - - if (enable) { - eeh_subsystem_enabled = 1; - edev->mode |= EEH_MODE_SUPPORTED; - - pr_debug("EEH: %s: eeh enabled, config=%x pe_config=%x\n", - dn->full_name, edev->config_addr, - edev->pe_config_addr); - } else { - - /* This device doesn't support EEH, but it may have an - * EEH parent, in which case we mark it as supported. - */ - if (dn->parent && of_node_to_eeh_dev(dn->parent) && - (of_node_to_eeh_dev(dn->parent)->mode & EEH_MODE_SUPPORTED)) { - /* Parent supports EEH. */ - edev->mode |= EEH_MODE_SUPPORTED; - edev->config_addr = of_node_to_eeh_dev(dn->parent)->config_addr; - return NULL; - } - } - } else { - printk(KERN_WARNING "EEH: %s: unable to get reg property.\n", - dn->full_name); - } - - eeh_save_bars(edev); - return NULL; -} - -/** * eeh_ops_register - Register platform dependent EEH operations * @ops: platform dependent EEH operations * @@ -982,7 +674,7 @@ int __exit eeh_ops_unregister(const char *name) * Even if force-off is set, the EEH hardware is still enabled, so that * newer systems can boot. */ -void __init eeh_init(void) +static int __init eeh_init(void) { struct pci_controller *hose, *tmp; struct device_node *phb; @@ -992,27 +684,34 @@ void __init eeh_init(void) if (!eeh_ops) { pr_warning("%s: Platform EEH operation not found\n", __func__); - return; + return -EEXIST; } else if ((ret = eeh_ops->init())) { pr_warning("%s: Failed to call platform init function (%d)\n", __func__, ret); - return; + return ret; } raw_spin_lock_init(&confirm_error_lock); /* Enable EEH for all adapters */ - list_for_each_entry_safe(hose, tmp, &hose_list, list_node) { - phb = hose->dn; - traverse_pci_devices(phb, eeh_early_enable, NULL); + if (eeh_probe_mode_devtree()) { + list_for_each_entry_safe(hose, tmp, + &hose_list, list_node) { + phb = hose->dn; + traverse_pci_devices(phb, eeh_ops->of_probe, NULL); + } } if (eeh_subsystem_enabled) - printk(KERN_INFO "EEH: PCI Enhanced I/O Error Handling Enabled\n"); + pr_info("EEH: PCI Enhanced I/O Error Handling Enabled\n"); else - printk(KERN_WARNING "EEH: No capable adapters found\n"); + pr_warning("EEH: No capable adapters found\n"); + + return ret; } +core_initcall_sync(eeh_init); + /** * eeh_add_device_early - Enable EEH for the indicated device_node * @dn: device node for which to set up EEH @@ -1037,7 +736,8 @@ static void eeh_add_device_early(struct device_node *dn) if (NULL == phb || 0 == phb->buid) return; - eeh_early_enable(dn, NULL); + /* FIXME: hotplug support on POWERNV */ + eeh_ops->of_probe(dn, NULL); } /** @@ -1087,7 +787,7 @@ static void eeh_add_device_late(struct pci_dev *dev) edev->pdev = dev; dev->dev.archdata.edev = edev; - pci_addr_cache_insert_device(dev); + eeh_addr_cache_insert_dev(dev); eeh_sysfs_add_device(dev); } @@ -1143,7 +843,8 @@ static void eeh_remove_device(struct pci_dev *dev) dev->dev.archdata.edev = NULL; pci_dev_put(dev); - pci_addr_cache_remove_device(dev); + eeh_rmv_from_parent_pe(edev); + eeh_addr_cache_rmv_dev(dev); eeh_sysfs_remove_device(dev); } diff --git a/arch/powerpc/platforms/pseries/eeh_cache.c b/arch/powerpc/platforms/pseries/eeh_cache.c index e5ae1c687c6..5a4c8790305 100644 --- a/arch/powerpc/platforms/pseries/eeh_cache.c +++ b/arch/powerpc/platforms/pseries/eeh_cache.c @@ -50,6 +50,7 @@ struct pci_io_addr_range { struct rb_node rb_node; unsigned long addr_lo; unsigned long addr_hi; + struct eeh_dev *edev; struct pci_dev *pcidev; unsigned int flags; }; @@ -59,7 +60,7 @@ static struct pci_io_addr_cache { spinlock_t piar_lock; } pci_io_addr_cache_root; -static inline struct pci_dev *__pci_addr_cache_get_device(unsigned long addr) +static inline struct eeh_dev *__eeh_addr_cache_get_device(unsigned long addr) { struct rb_node *n = pci_io_addr_cache_root.rb_root.rb_node; @@ -74,7 +75,7 @@ static inline struct pci_dev *__pci_addr_cache_get_device(unsigned long addr) n = n->rb_right; } else { pci_dev_get(piar->pcidev); - return piar->pcidev; + return piar->edev; } } } @@ -83,7 +84,7 @@ static inline struct pci_dev *__pci_addr_cache_get_device(unsigned long addr) } /** - * pci_addr_cache_get_device - Get device, given only address + * eeh_addr_cache_get_dev - Get device, given only address * @addr: mmio (PIO) phys address or i/o port number * * Given an mmio phys address, or a port number, find a pci device @@ -92,15 +93,15 @@ static inline struct pci_dev *__pci_addr_cache_get_device(unsigned long addr) * from zero (that is, they do *not* have pci_io_addr added in). * It is safe to call this function within an interrupt. */ -struct pci_dev *pci_addr_cache_get_device(unsigned long addr) +struct eeh_dev *eeh_addr_cache_get_dev(unsigned long addr) { - struct pci_dev *dev; + struct eeh_dev *edev; unsigned long flags; spin_lock_irqsave(&pci_io_addr_cache_root.piar_lock, flags); - dev = __pci_addr_cache_get_device(addr); + edev = __eeh_addr_cache_get_device(addr); spin_unlock_irqrestore(&pci_io_addr_cache_root.piar_lock, flags); - return dev; + return edev; } #ifdef DEBUG @@ -108,7 +109,7 @@ struct pci_dev *pci_addr_cache_get_device(unsigned long addr) * Handy-dandy debug print routine, does nothing more * than print out the contents of our addr cache. */ -static void pci_addr_cache_print(struct pci_io_addr_cache *cache) +static void eeh_addr_cache_print(struct pci_io_addr_cache *cache) { struct rb_node *n; int cnt = 0; @@ -117,7 +118,7 @@ static void pci_addr_cache_print(struct pci_io_addr_cache *cache) while (n) { struct pci_io_addr_range *piar; piar = rb_entry(n, struct pci_io_addr_range, rb_node); - printk(KERN_DEBUG "PCI: %s addr range %d [%lx-%lx]: %s\n", + pr_debug("PCI: %s addr range %d [%lx-%lx]: %s\n", (piar->flags & IORESOURCE_IO) ? "i/o" : "mem", cnt, piar->addr_lo, piar->addr_hi, pci_name(piar->pcidev)); cnt++; @@ -128,7 +129,7 @@ static void pci_addr_cache_print(struct pci_io_addr_cache *cache) /* Insert address range into the rb tree. */ static struct pci_io_addr_range * -pci_addr_cache_insert(struct pci_dev *dev, unsigned long alo, +eeh_addr_cache_insert(struct pci_dev *dev, unsigned long alo, unsigned long ahi, unsigned int flags) { struct rb_node **p = &pci_io_addr_cache_root.rb_root.rb_node; @@ -146,23 +147,24 @@ pci_addr_cache_insert(struct pci_dev *dev, unsigned long alo, } else { if (dev != piar->pcidev || alo != piar->addr_lo || ahi != piar->addr_hi) { - printk(KERN_WARNING "PIAR: overlapping address range\n"); + pr_warning("PIAR: overlapping address range\n"); } return piar; } } - piar = kmalloc(sizeof(struct pci_io_addr_range), GFP_ATOMIC); + piar = kzalloc(sizeof(struct pci_io_addr_range), GFP_ATOMIC); if (!piar) return NULL; pci_dev_get(dev); piar->addr_lo = alo; piar->addr_hi = ahi; + piar->edev = pci_dev_to_eeh_dev(dev); piar->pcidev = dev; piar->flags = flags; #ifdef DEBUG - printk(KERN_DEBUG "PIAR: insert range=[%lx:%lx] dev=%s\n", + pr_debug("PIAR: insert range=[%lx:%lx] dev=%s\n", alo, ahi, pci_name(dev)); #endif @@ -172,7 +174,7 @@ pci_addr_cache_insert(struct pci_dev *dev, unsigned long alo, return piar; } -static void __pci_addr_cache_insert_device(struct pci_dev *dev) +static void __eeh_addr_cache_insert_dev(struct pci_dev *dev) { struct device_node *dn; struct eeh_dev *edev; @@ -180,7 +182,7 @@ static void __pci_addr_cache_insert_device(struct pci_dev *dev) dn = pci_device_to_OF_node(dev); if (!dn) { - printk(KERN_WARNING "PCI: no pci dn found for dev=%s\n", pci_name(dev)); + pr_warning("PCI: no pci dn found for dev=%s\n", pci_name(dev)); return; } @@ -192,8 +194,7 @@ static void __pci_addr_cache_insert_device(struct pci_dev *dev) } /* Skip any devices for which EEH is not enabled. */ - if (!(edev->mode & EEH_MODE_SUPPORTED) || - edev->mode & EEH_MODE_NOCHECK) { + if (!edev->pe) { #ifdef DEBUG pr_info("PCI: skip building address cache for=%s - %s\n", pci_name(dev), dn->full_name); @@ -212,19 +213,19 @@ static void __pci_addr_cache_insert_device(struct pci_dev *dev) continue; if (start == 0 || ~start == 0 || end == 0 || ~end == 0) continue; - pci_addr_cache_insert(dev, start, end, flags); + eeh_addr_cache_insert(dev, start, end, flags); } } /** - * pci_addr_cache_insert_device - Add a device to the address cache + * eeh_addr_cache_insert_dev - Add a device to the address cache * @dev: PCI device whose I/O addresses we are interested in. * * In order to support the fast lookup of devices based on addresses, * we maintain a cache of devices that can be quickly searched. * This routine adds a device to that cache. */ -void pci_addr_cache_insert_device(struct pci_dev *dev) +void eeh_addr_cache_insert_dev(struct pci_dev *dev) { unsigned long flags; @@ -233,11 +234,11 @@ void pci_addr_cache_insert_device(struct pci_dev *dev) return; spin_lock_irqsave(&pci_io_addr_cache_root.piar_lock, flags); - __pci_addr_cache_insert_device(dev); + __eeh_addr_cache_insert_dev(dev); spin_unlock_irqrestore(&pci_io_addr_cache_root.piar_lock, flags); } -static inline void __pci_addr_cache_remove_device(struct pci_dev *dev) +static inline void __eeh_addr_cache_rmv_dev(struct pci_dev *dev) { struct rb_node *n; @@ -258,7 +259,7 @@ restart: } /** - * pci_addr_cache_remove_device - remove pci device from addr cache + * eeh_addr_cache_rmv_dev - remove pci device from addr cache * @dev: device to remove * * Remove a device from the addr-cache tree. @@ -266,17 +267,17 @@ restart: * the tree multiple times (once per resource). * But so what; device removal doesn't need to be that fast. */ -void pci_addr_cache_remove_device(struct pci_dev *dev) +void eeh_addr_cache_rmv_dev(struct pci_dev *dev) { unsigned long flags; spin_lock_irqsave(&pci_io_addr_cache_root.piar_lock, flags); - __pci_addr_cache_remove_device(dev); + __eeh_addr_cache_rmv_dev(dev); spin_unlock_irqrestore(&pci_io_addr_cache_root.piar_lock, flags); } /** - * pci_addr_cache_build - Build a cache of I/O addresses + * eeh_addr_cache_build - Build a cache of I/O addresses * * Build a cache of pci i/o addresses. This cache will be used to * find the pci device that corresponds to a given address. @@ -284,7 +285,7 @@ void pci_addr_cache_remove_device(struct pci_dev *dev) * Must be run late in boot process, after the pci controllers * have been scanned for devices (after all device resources are known). */ -void __init pci_addr_cache_build(void) +void __init eeh_addr_cache_build(void) { struct device_node *dn; struct eeh_dev *edev; @@ -293,7 +294,7 @@ void __init pci_addr_cache_build(void) spin_lock_init(&pci_io_addr_cache_root.piar_lock); for_each_pci_dev(dev) { - pci_addr_cache_insert_device(dev); + eeh_addr_cache_insert_dev(dev); dn = pci_device_to_OF_node(dev); if (!dn) @@ -312,7 +313,7 @@ void __init pci_addr_cache_build(void) #ifdef DEBUG /* Verify tree built up above, echo back the list of addrs. */ - pci_addr_cache_print(&pci_io_addr_cache_root); + eeh_addr_cache_print(&pci_io_addr_cache_root); #endif } diff --git a/arch/powerpc/platforms/pseries/eeh_dev.c b/arch/powerpc/platforms/pseries/eeh_dev.c index c4507d09590..66442341d3a 100644 --- a/arch/powerpc/platforms/pseries/eeh_dev.c +++ b/arch/powerpc/platforms/pseries/eeh_dev.c @@ -55,7 +55,7 @@ void * __devinit eeh_dev_init(struct device_node *dn, void *data) struct eeh_dev *edev; /* Allocate EEH device */ - edev = zalloc_maybe_bootmem(sizeof(*edev), GFP_KERNEL); + edev = kzalloc(sizeof(*edev), GFP_KERNEL); if (!edev) { pr_warning("%s: out of memory\n", __func__); return NULL; @@ -65,6 +65,7 @@ void * __devinit eeh_dev_init(struct device_node *dn, void *data) PCI_DN(dn)->edev = edev; edev->dn = dn; edev->phb = phb; + INIT_LIST_HEAD(&edev->list); return NULL; } @@ -80,6 +81,9 @@ void __devinit eeh_dev_phb_init_dynamic(struct pci_controller *phb) { struct device_node *dn = phb->dn; + /* EEH PE for PHB */ + eeh_phb_pe_create(phb); + /* EEH device for PHB */ eeh_dev_init(dn, phb); @@ -93,10 +97,16 @@ void __devinit eeh_dev_phb_init_dynamic(struct pci_controller *phb) * Scan all the existing PHBs and create EEH devices for their OF * nodes and their children OF nodes */ -void __init eeh_dev_phb_init(void) +static int __init eeh_dev_phb_init(void) { struct pci_controller *phb, *tmp; list_for_each_entry_safe(phb, tmp, &hose_list, list_node) eeh_dev_phb_init_dynamic(phb); + + pr_info("EEH: devices created\n"); + + return 0; } + +core_initcall(eeh_dev_phb_init); diff --git a/arch/powerpc/platforms/pseries/eeh_driver.c b/arch/powerpc/platforms/pseries/eeh_driver.c index baf92cd9dfa..8370ce7d593 100644 --- a/arch/powerpc/platforms/pseries/eeh_driver.c +++ b/arch/powerpc/platforms/pseries/eeh_driver.c @@ -93,7 +93,7 @@ static void eeh_disable_irq(struct pci_dev *dev) if (!irq_has_action(dev->irq)) return; - edev->mode |= EEH_MODE_IRQ_DISABLED; + edev->mode |= EEH_DEV_IRQ_DISABLED; disable_irq_nosync(dev->irq); } @@ -108,36 +108,43 @@ static void eeh_enable_irq(struct pci_dev *dev) { struct eeh_dev *edev = pci_dev_to_eeh_dev(dev); - if ((edev->mode) & EEH_MODE_IRQ_DISABLED) { - edev->mode &= ~EEH_MODE_IRQ_DISABLED; + if ((edev->mode) & EEH_DEV_IRQ_DISABLED) { + edev->mode &= ~EEH_DEV_IRQ_DISABLED; enable_irq(dev->irq); } } /** * eeh_report_error - Report pci error to each device driver - * @dev: PCI device + * @data: eeh device * @userdata: return value * * Report an EEH error to each device driver, collect up and * merge the device driver responses. Cumulative response * passed back in "userdata". */ -static int eeh_report_error(struct pci_dev *dev, void *userdata) +static void *eeh_report_error(void *data, void *userdata) { + struct eeh_dev *edev = (struct eeh_dev *)data; + struct pci_dev *dev = eeh_dev_to_pci_dev(edev); enum pci_ers_result rc, *res = userdata; struct pci_driver *driver = dev->driver; + /* We might not have the associated PCI device, + * then we should continue for next one. + */ + if (!dev) return NULL; + dev->error_state = pci_channel_io_frozen; if (!driver) - return 0; + return NULL; eeh_disable_irq(dev); if (!driver->err_handler || !driver->err_handler->error_detected) - return 0; + return NULL; rc = driver->err_handler->error_detected(dev, pci_channel_io_frozen); @@ -145,27 +152,31 @@ static int eeh_report_error(struct pci_dev *dev, void *userdata) if (rc == PCI_ERS_RESULT_NEED_RESET) *res = rc; if (*res == PCI_ERS_RESULT_NONE) *res = rc; - return 0; + return NULL; } /** * eeh_report_mmio_enabled - Tell drivers that MMIO has been enabled - * @dev: PCI device + * @data: eeh device * @userdata: return value * * Tells each device driver that IO ports, MMIO and config space I/O * are now enabled. Collects up and merges the device driver responses. * Cumulative response passed back in "userdata". */ -static int eeh_report_mmio_enabled(struct pci_dev *dev, void *userdata) +static void *eeh_report_mmio_enabled(void *data, void *userdata) { + struct eeh_dev *edev = (struct eeh_dev *)data; + struct pci_dev *dev = eeh_dev_to_pci_dev(edev); enum pci_ers_result rc, *res = userdata; - struct pci_driver *driver = dev->driver; + struct pci_driver *driver; - if (!driver || + if (!dev) return NULL; + + if (!(driver = dev->driver) || !driver->err_handler || !driver->err_handler->mmio_enabled) - return 0; + return NULL; rc = driver->err_handler->mmio_enabled(dev); @@ -173,12 +184,12 @@ static int eeh_report_mmio_enabled(struct pci_dev *dev, void *userdata) if (rc == PCI_ERS_RESULT_NEED_RESET) *res = rc; if (*res == PCI_ERS_RESULT_NONE) *res = rc; - return 0; + return NULL; } /** * eeh_report_reset - Tell device that slot has been reset - * @dev: PCI device + * @data: eeh device * @userdata: return value * * This routine must be called while EEH tries to reset particular @@ -186,13 +197,15 @@ static int eeh_report_mmio_enabled(struct pci_dev *dev, void *userdata) * some actions, usually to save data the driver needs so that the * driver can work again while the device is recovered. */ -static int eeh_report_reset(struct pci_dev *dev, void *userdata) +static void *eeh_report_reset(void *data, void *userdata) { + struct eeh_dev *edev = (struct eeh_dev *)data; + struct pci_dev *dev = eeh_dev_to_pci_dev(edev); enum pci_ers_result rc, *res = userdata; - struct pci_driver *driver = dev->driver; + struct pci_driver *driver; - if (!driver) - return 0; + if (!dev || !(driver = dev->driver)) + return NULL; dev->error_state = pci_channel_io_normal; @@ -200,7 +213,7 @@ static int eeh_report_reset(struct pci_dev *dev, void *userdata) if (!driver->err_handler || !driver->err_handler->slot_reset) - return 0; + return NULL; rc = driver->err_handler->slot_reset(dev); if ((*res == PCI_ERS_RESULT_NONE) || @@ -208,82 +221,89 @@ static int eeh_report_reset(struct pci_dev *dev, void *userdata) if (*res == PCI_ERS_RESULT_DISCONNECT && rc == PCI_ERS_RESULT_NEED_RESET) *res = rc; - return 0; + return NULL; } /** * eeh_report_resume - Tell device to resume normal operations - * @dev: PCI device + * @data: eeh device * @userdata: return value * * This routine must be called to notify the device driver that it * could resume so that the device driver can do some initialization * to make the recovered device work again. */ -static int eeh_report_resume(struct pci_dev *dev, void *userdata) +static void *eeh_report_resume(void *data, void *userdata) { - struct pci_driver *driver = dev->driver; + struct eeh_dev *edev = (struct eeh_dev *)data; + struct pci_dev *dev = eeh_dev_to_pci_dev(edev); + struct pci_driver *driver; + + if (!dev) return NULL; dev->error_state = pci_channel_io_normal; - if (!driver) - return 0; + if (!(driver = dev->driver)) + return NULL; eeh_enable_irq(dev); if (!driver->err_handler || !driver->err_handler->resume) - return 0; + return NULL; driver->err_handler->resume(dev); - return 0; + return NULL; } /** * eeh_report_failure - Tell device driver that device is dead. - * @dev: PCI device + * @data: eeh device * @userdata: return value * * This informs the device driver that the device is permanently * dead, and that no further recovery attempts will be made on it. */ -static int eeh_report_failure(struct pci_dev *dev, void *userdata) +static void *eeh_report_failure(void *data, void *userdata) { - struct pci_driver *driver = dev->driver; + struct eeh_dev *edev = (struct eeh_dev *)data; + struct pci_dev *dev = eeh_dev_to_pci_dev(edev); + struct pci_driver *driver; + + if (!dev) return NULL; dev->error_state = pci_channel_io_perm_failure; - if (!driver) - return 0; + if (!(driver = dev->driver)) + return NULL; eeh_disable_irq(dev); if (!driver->err_handler || !driver->err_handler->error_detected) - return 0; + return NULL; driver->err_handler->error_detected(dev, pci_channel_io_perm_failure); - return 0; + return NULL; } /** * eeh_reset_device - Perform actual reset of a pci slot - * @edev: PE associated EEH device + * @pe: EEH PE * @bus: PCI bus corresponding to the isolcated slot * * This routine must be called to do reset on the indicated PE. * During the reset, udev might be invoked because those affected * PCI devices will be removed and then added. */ -static int eeh_reset_device(struct eeh_dev *edev, struct pci_bus *bus) +static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus) { - struct device_node *dn; int cnt, rc; /* pcibios will clear the counter; save the value */ - cnt = edev->freeze_count; + cnt = pe->freeze_count; if (bus) pcibios_remove_pci_devices(bus); @@ -292,25 +312,13 @@ static int eeh_reset_device(struct eeh_dev *edev, struct pci_bus *bus) * Reconfigure bridges and devices. Don't try to bring the system * up if the reset failed for some reason. */ - rc = eeh_reset_pe(edev); + rc = eeh_reset_pe(pe); if (rc) return rc; - /* Walk over all functions on this device. */ - dn = eeh_dev_to_of_node(edev); - if (!pcibios_find_pci_bus(dn) && of_node_to_eeh_dev(dn->parent)) - dn = dn->parent->child; - - while (dn) { - struct eeh_dev *pedev = of_node_to_eeh_dev(dn); - - /* On Power4, always true because eeh_pe_config_addr=0 */ - if (edev->pe_config_addr == pedev->pe_config_addr) { - eeh_ops->configure_bridge(dn); - eeh_restore_bars(pedev); - } - dn = dn->sibling; - } + /* Restore PE */ + eeh_ops->configure_bridge(pe); + eeh_pe_restore_bars(pe); /* Give the system 5 seconds to finish running the user-space * hotplug shutdown scripts, e.g. ifdown for ethernet. Yes, @@ -322,7 +330,7 @@ static int eeh_reset_device(struct eeh_dev *edev, struct pci_bus *bus) ssleep(5); pcibios_add_pci_devices(bus); } - edev->freeze_count = cnt; + pe->freeze_count = cnt; return 0; } @@ -334,7 +342,7 @@ static int eeh_reset_device(struct eeh_dev *edev, struct pci_bus *bus) /** * eeh_handle_event - Reset a PCI device after hard lockup. - * @event: EEH event + * @pe: EEH PE * * While PHB detects address or data parity errors on particular PCI * slot, the associated PE will be frozen. Besides, DMA's occurring @@ -349,69 +357,24 @@ static int eeh_reset_device(struct eeh_dev *edev, struct pci_bus *bus) * drivers (which cause a second set of hotplug events to go out to * userspace). */ -struct eeh_dev *handle_eeh_events(struct eeh_event *event) +void eeh_handle_event(struct eeh_pe *pe) { - struct device_node *frozen_dn; - struct eeh_dev *frozen_edev; struct pci_bus *frozen_bus; int rc = 0; enum pci_ers_result result = PCI_ERS_RESULT_NONE; - const char *location, *pci_str, *drv_str, *bus_pci_str, *bus_drv_str; - - frozen_dn = eeh_find_device_pe(eeh_dev_to_of_node(event->edev)); - if (!frozen_dn) { - location = of_get_property(eeh_dev_to_of_node(event->edev), "ibm,loc-code", NULL); - location = location ? location : "unknown"; - printk(KERN_ERR "EEH: Error: Cannot find partition endpoint " - "for location=%s pci addr=%s\n", - location, eeh_pci_name(eeh_dev_to_pci_dev(event->edev))); - return NULL; - } - - frozen_bus = pcibios_find_pci_bus(frozen_dn); - location = of_get_property(frozen_dn, "ibm,loc-code", NULL); - location = location ? location : "unknown"; - - /* There are two different styles for coming up with the PE. - * In the old style, it was the highest EEH-capable device - * which was always an EADS pci bridge. In the new style, - * there might not be any EADS bridges, and even when there are, - * the firmware marks them as "EEH incapable". So another - * two-step is needed to find the pci bus.. - */ - if (!frozen_bus) - frozen_bus = pcibios_find_pci_bus(frozen_dn->parent); + frozen_bus = eeh_pe_bus_get(pe); if (!frozen_bus) { - printk(KERN_ERR "EEH: Cannot find PCI bus " - "for location=%s dn=%s\n", - location, frozen_dn->full_name); - return NULL; + pr_err("%s: Cannot find PCI bus for PHB#%d-PE#%x\n", + __func__, pe->phb->global_number, pe->addr); + return; } - frozen_edev = of_node_to_eeh_dev(frozen_dn); - frozen_edev->freeze_count++; - pci_str = eeh_pci_name(eeh_dev_to_pci_dev(event->edev)); - drv_str = eeh_pcid_name(eeh_dev_to_pci_dev(event->edev)); - - if (frozen_edev->freeze_count > EEH_MAX_ALLOWED_FREEZES) + pe->freeze_count++; + if (pe->freeze_count > EEH_MAX_ALLOWED_FREEZES) goto excess_failures; - - printk(KERN_WARNING - "EEH: This PCI device has failed %d times in the last hour:\n", - frozen_edev->freeze_count); - - if (frozen_edev->pdev) { - bus_pci_str = pci_name(frozen_edev->pdev); - bus_drv_str = eeh_pcid_name(frozen_edev->pdev); - printk(KERN_WARNING - "EEH: Bus location=%s driver=%s pci addr=%s\n", - location, bus_drv_str, bus_pci_str); - } - - printk(KERN_WARNING - "EEH: Device location=%s driver=%s pci addr=%s\n", - location, drv_str, pci_str); + pr_warning("EEH: This PCI device has failed %d times in the last hour\n", + pe->freeze_count); /* Walk the various device drivers attached to this slot through * a reset sequence, giving each an opportunity to do what it needs @@ -419,12 +382,12 @@ struct eeh_dev *handle_eeh_events(struct eeh_event *event) * status ... if any child can't handle the reset, then the entire * slot is dlpar removed and added. */ - pci_walk_bus(frozen_bus, eeh_report_error, &result); + eeh_pe_dev_traverse(pe, eeh_report_error, &result); /* Get the current PCI slot state. This can take a long time, * sometimes over 3 seconds for certain systems. */ - rc = eeh_ops->wait_state(eeh_dev_to_of_node(frozen_edev), MAX_WAIT_FOR_RECOVERY*1000); + rc = eeh_ops->wait_state(pe, MAX_WAIT_FOR_RECOVERY*1000); if (rc < 0 || rc == EEH_STATE_NOT_SUPPORT) { printk(KERN_WARNING "EEH: Permanent failure\n"); goto hard_fail; @@ -434,14 +397,14 @@ struct eeh_dev *handle_eeh_events(struct eeh_event *event) * don't post the error log until after all dev drivers * have been informed. */ - eeh_slot_error_detail(frozen_edev, EEH_LOG_TEMP); + eeh_slot_error_detail(pe, EEH_LOG_TEMP); /* If all device drivers were EEH-unaware, then shut * down all of the device drivers, and hope they * go down willingly, without panicing the system. */ if (result == PCI_ERS_RESULT_NONE) { - rc = eeh_reset_device(frozen_edev, frozen_bus); + rc = eeh_reset_device(pe, frozen_bus); if (rc) { printk(KERN_WARNING "EEH: Unable to reset, rc=%d\n", rc); goto hard_fail; @@ -450,7 +413,7 @@ struct eeh_dev *handle_eeh_events(struct eeh_event *event) /* If all devices reported they can proceed, then re-enable MMIO */ if (result == PCI_ERS_RESULT_CAN_RECOVER) { - rc = eeh_pci_enable(frozen_edev, EEH_OPT_THAW_MMIO); + rc = eeh_pci_enable(pe, EEH_OPT_THAW_MMIO); if (rc < 0) goto hard_fail; @@ -458,13 +421,13 @@ struct eeh_dev *handle_eeh_events(struct eeh_event *event) result = PCI_ERS_RESULT_NEED_RESET; } else { result = PCI_ERS_RESULT_NONE; - pci_walk_bus(frozen_bus, eeh_report_mmio_enabled, &result); + eeh_pe_dev_traverse(pe, eeh_report_mmio_enabled, &result); } } /* If all devices reported they can proceed, then re-enable DMA */ if (result == PCI_ERS_RESULT_CAN_RECOVER) { - rc = eeh_pci_enable(frozen_edev, EEH_OPT_THAW_DMA); + rc = eeh_pci_enable(pe, EEH_OPT_THAW_DMA); if (rc < 0) goto hard_fail; @@ -482,13 +445,13 @@ struct eeh_dev *handle_eeh_events(struct eeh_event *event) /* If any device called out for a reset, then reset the slot */ if (result == PCI_ERS_RESULT_NEED_RESET) { - rc = eeh_reset_device(frozen_edev, NULL); + rc = eeh_reset_device(pe, NULL); if (rc) { printk(KERN_WARNING "EEH: Cannot reset, rc=%d\n", rc); goto hard_fail; } result = PCI_ERS_RESULT_NONE; - pci_walk_bus(frozen_bus, eeh_report_reset, &result); + eeh_pe_dev_traverse(pe, eeh_report_reset, &result); } /* All devices should claim they have recovered by now. */ @@ -499,9 +462,9 @@ struct eeh_dev *handle_eeh_events(struct eeh_event *event) } /* Tell all device drivers that they can resume operations */ - pci_walk_bus(frozen_bus, eeh_report_resume, NULL); + eeh_pe_dev_traverse(pe, eeh_report_resume, NULL); - return frozen_edev; + return; excess_failures: /* @@ -509,30 +472,26 @@ excess_failures: * are due to poorly seated PCI cards. Only 10% or so are * due to actual, failed cards. */ - printk(KERN_ERR - "EEH: PCI device at location=%s driver=%s pci addr=%s\n" - "has failed %d times in the last hour " - "and has been permanently disabled.\n" - "Please try reseating this device or replacing it.\n", - location, drv_str, pci_str, frozen_edev->freeze_count); + pr_err("EEH: PHB#%d-PE#%x has failed %d times in the\n" + "last hour and has been permanently disabled.\n" + "Please try reseating or replacing it.\n", + pe->phb->global_number, pe->addr, + pe->freeze_count); goto perm_error; hard_fail: - printk(KERN_ERR - "EEH: Unable to recover from failure of PCI device " - "at location=%s driver=%s pci addr=%s\n" - "Please try reseating this device or replacing it.\n", - location, drv_str, pci_str); + pr_err("EEH: Unable to recover from failure from PHB#%d-PE#%x.\n" + "Please try reseating or replacing it\n", + pe->phb->global_number, pe->addr); perm_error: - eeh_slot_error_detail(frozen_edev, EEH_LOG_PERM); + eeh_slot_error_detail(pe, EEH_LOG_PERM); /* Notify all devices that they're about to go down. */ - pci_walk_bus(frozen_bus, eeh_report_failure, NULL); + eeh_pe_dev_traverse(pe, eeh_report_failure, NULL); /* Shut down the device drivers for good. */ - pcibios_remove_pci_devices(frozen_bus); - - return NULL; + if (frozen_bus) + pcibios_remove_pci_devices(frozen_bus); } diff --git a/arch/powerpc/platforms/pseries/eeh_event.c b/arch/powerpc/platforms/pseries/eeh_event.c index fb506317ebb..51faaac8abe 100644 --- a/arch/powerpc/platforms/pseries/eeh_event.c +++ b/arch/powerpc/platforms/pseries/eeh_event.c @@ -57,7 +57,7 @@ static int eeh_event_handler(void * dummy) { unsigned long flags; struct eeh_event *event; - struct eeh_dev *edev; + struct eeh_pe *pe; set_task_comm(current, "eehd"); @@ -76,28 +76,23 @@ static int eeh_event_handler(void * dummy) /* Serialize processing of EEH events */ mutex_lock(&eeh_event_mutex); - edev = event->edev; - eeh_mark_slot(eeh_dev_to_of_node(edev), EEH_MODE_RECOVERING); - - printk(KERN_INFO "EEH: Detected PCI bus error on device %s\n", - eeh_pci_name(edev->pdev)); + pe = event->pe; + eeh_pe_state_mark(pe, EEH_PE_RECOVERING); + pr_info("EEH: Detected PCI bus error on PHB#%d-PE#%x\n", + pe->phb->global_number, pe->addr); set_current_state(TASK_INTERRUPTIBLE); /* Don't add to load average */ - edev = handle_eeh_events(event); - - if (edev) { - eeh_clear_slot(eeh_dev_to_of_node(edev), EEH_MODE_RECOVERING); - pci_dev_put(edev->pdev); - } + eeh_handle_event(pe); + eeh_pe_state_clear(pe, EEH_PE_RECOVERING); kfree(event); mutex_unlock(&eeh_event_mutex); /* If there are no new errors after an hour, clear the counter. */ - if (edev && edev->freeze_count>0) { + if (pe && pe->freeze_count > 0) { msleep_interruptible(3600*1000); - if (edev->freeze_count>0) - edev->freeze_count--; + if (pe->freeze_count > 0) + pe->freeze_count--; } @@ -119,36 +114,23 @@ static void eeh_thread_launcher(struct work_struct *dummy) /** * eeh_send_failure_event - Generate a PCI error event - * @edev: EEH device + * @pe: EEH PE * * This routine can be called within an interrupt context; * the actual event will be delivered in a normal context * (from a workqueue). */ -int eeh_send_failure_event(struct eeh_dev *edev) +int eeh_send_failure_event(struct eeh_pe *pe) { unsigned long flags; struct eeh_event *event; - struct device_node *dn = eeh_dev_to_of_node(edev); - const char *location; - - if (!mem_init_done) { - printk(KERN_ERR "EEH: event during early boot not handled\n"); - location = of_get_property(dn, "ibm,loc-code", NULL); - printk(KERN_ERR "EEH: device node = %s\n", dn->full_name); - printk(KERN_ERR "EEH: PCI location = %s\n", location); - return 1; - } - event = kmalloc(sizeof(*event), GFP_ATOMIC); - if (event == NULL) { - printk(KERN_ERR "EEH: out of memory, event not handled\n"); - return 1; - } - - if (edev->pdev) - pci_dev_get(edev->pdev); - event->edev = edev; + event = kzalloc(sizeof(*event), GFP_ATOMIC); + if (!event) { + pr_err("EEH: out of memory, event not handled\n"); + return -ENOMEM; + } + event->pe = pe; /* We may or may not be called in an interrupt context */ spin_lock_irqsave(&eeh_eventlist_lock, flags); diff --git a/arch/powerpc/platforms/pseries/eeh_pe.c b/arch/powerpc/platforms/pseries/eeh_pe.c new file mode 100644 index 00000000000..904123c7657 --- /dev/null +++ b/arch/powerpc/platforms/pseries/eeh_pe.c @@ -0,0 +1,591 @@ +/* + * The file intends to implement PE based on the information from + * platforms. Basically, there have 3 types of PEs: PHB/Bus/Device. + * All the PEs should be organized as hierarchy tree. The first level + * of the tree will be associated to existing PHBs since the particular + * PE is only meaningful in one PHB domain. + * + * Copyright Benjamin Herrenschmidt & Gavin Shan, IBM Corporation 2012. + * + * 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 + */ + +#include <linux/export.h> +#include <linux/gfp.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/pci.h> +#include <linux/string.h> + +#include <asm/pci-bridge.h> +#include <asm/ppc-pci.h> + +static LIST_HEAD(eeh_phb_pe); + +/** + * eeh_pe_alloc - Allocate PE + * @phb: PCI controller + * @type: PE type + * + * Allocate PE instance dynamically. + */ +static struct eeh_pe *eeh_pe_alloc(struct pci_controller *phb, int type) +{ + struct eeh_pe *pe; + + /* Allocate PHB PE */ + pe = kzalloc(sizeof(struct eeh_pe), GFP_KERNEL); + if (!pe) return NULL; + + /* Initialize PHB PE */ + pe->type = type; + pe->phb = phb; + INIT_LIST_HEAD(&pe->child_list); + INIT_LIST_HEAD(&pe->child); + INIT_LIST_HEAD(&pe->edevs); + + return pe; +} + +/** + * eeh_phb_pe_create - Create PHB PE + * @phb: PCI controller + * + * The function should be called while the PHB is detected during + * system boot or PCI hotplug in order to create PHB PE. + */ +int __devinit eeh_phb_pe_create(struct pci_controller *phb) +{ + struct eeh_pe *pe; + + /* Allocate PHB PE */ + pe = eeh_pe_alloc(phb, EEH_PE_PHB); + if (!pe) { + pr_err("%s: out of memory!\n", __func__); + return -ENOMEM; + } + + /* Put it into the list */ + eeh_lock(); + list_add_tail(&pe->child, &eeh_phb_pe); + eeh_unlock(); + + pr_debug("EEH: Add PE for PHB#%d\n", phb->global_number); + + return 0; +} + +/** + * eeh_phb_pe_get - Retrieve PHB PE based on the given PHB + * @phb: PCI controller + * + * The overall PEs form hierarchy tree. The first layer of the + * hierarchy tree is composed of PHB PEs. The function is used + * to retrieve the corresponding PHB PE according to the given PHB. + */ +static struct eeh_pe *eeh_phb_pe_get(struct pci_controller *phb) +{ + struct eeh_pe *pe; + + eeh_lock(); + + list_for_each_entry(pe, &eeh_phb_pe, child) { + /* + * Actually, we needn't check the type since + * the PE for PHB has been determined when that + * was created. + */ + if (pe->type == EEH_PE_PHB && + pe->phb == phb) { + eeh_unlock(); + return pe; + } + } + + eeh_unlock(); + + return NULL; +} + +/** + * eeh_pe_next - Retrieve the next PE in the tree + * @pe: current PE + * @root: root PE + * + * The function is used to retrieve the next PE in the + * hierarchy PE tree. + */ +static struct eeh_pe *eeh_pe_next(struct eeh_pe *pe, + struct eeh_pe *root) +{ + struct list_head *next = pe->child_list.next; + + if (next == &pe->child_list) { + while (1) { + if (pe == root) + return NULL; + next = pe->child.next; + if (next != &pe->parent->child_list) + break; + pe = pe->parent; + } + } + + return list_entry(next, struct eeh_pe, child); +} + +/** + * eeh_pe_traverse - Traverse PEs in the specified PHB + * @root: root PE + * @fn: callback + * @flag: extra parameter to callback + * + * The function is used to traverse the specified PE and its + * child PEs. The traversing is to be terminated once the + * callback returns something other than NULL, or no more PEs + * to be traversed. + */ +static void *eeh_pe_traverse(struct eeh_pe *root, + eeh_traverse_func fn, void *flag) +{ + struct eeh_pe *pe; + void *ret; + + for (pe = root; pe; pe = eeh_pe_next(pe, root)) { + ret = fn(pe, flag); + if (ret) return ret; + } + + return NULL; +} + +/** + * eeh_pe_dev_traverse - Traverse the devices from the PE + * @root: EEH PE + * @fn: function callback + * @flag: extra parameter to callback + * + * The function is used to traverse the devices of the specified + * PE and its child PEs. + */ +void *eeh_pe_dev_traverse(struct eeh_pe *root, + eeh_traverse_func fn, void *flag) +{ + struct eeh_pe *pe; + struct eeh_dev *edev; + void *ret; + + if (!root) { + pr_warning("%s: Invalid PE %p\n", __func__, root); + return NULL; + } + + /* Traverse root PE */ + for (pe = root; pe; pe = eeh_pe_next(pe, root)) { + eeh_pe_for_each_dev(pe, edev) { + ret = fn(edev, flag); + if (ret) return ret; + } + } + + return NULL; +} + +/** + * __eeh_pe_get - Check the PE address + * @data: EEH PE + * @flag: EEH device + * + * For one particular PE, it can be identified by PE address + * or tranditional BDF address. BDF address is composed of + * Bus/Device/Function number. The extra data referred by flag + * indicates which type of address should be used. + */ +static void *__eeh_pe_get(void *data, void *flag) +{ + struct eeh_pe *pe = (struct eeh_pe *)data; + struct eeh_dev *edev = (struct eeh_dev *)flag; + + /* Unexpected PHB PE */ + if (pe->type == EEH_PE_PHB) + return NULL; + + /* We prefer PE address */ + if (edev->pe_config_addr && + (edev->pe_config_addr == pe->addr)) + return pe; + + /* Try BDF address */ + if (edev->pe_config_addr && + (edev->config_addr == pe->config_addr)) + return pe; + + return NULL; +} + +/** + * eeh_pe_get - Search PE based on the given address + * @edev: EEH device + * + * Search the corresponding PE based on the specified address which + * is included in the eeh device. The function is used to check if + * the associated PE has been created against the PE address. It's + * notable that the PE address has 2 format: traditional PE address + * which is composed of PCI bus/device/function number, or unified + * PE address. + */ +static struct eeh_pe *eeh_pe_get(struct eeh_dev *edev) +{ + struct eeh_pe *root = eeh_phb_pe_get(edev->phb); + struct eeh_pe *pe; + + eeh_lock(); + pe = eeh_pe_traverse(root, __eeh_pe_get, edev); + eeh_unlock(); + + return pe; +} + +/** + * eeh_pe_get_parent - Retrieve the parent PE + * @edev: EEH device + * + * The whole PEs existing in the system are organized as hierarchy + * tree. The function is used to retrieve the parent PE according + * to the parent EEH device. + */ +static struct eeh_pe *eeh_pe_get_parent(struct eeh_dev *edev) +{ + struct device_node *dn; + struct eeh_dev *parent; + + /* + * It might have the case for the indirect parent + * EEH device already having associated PE, but + * the direct parent EEH device doesn't have yet. + */ + dn = edev->dn->parent; + while (dn) { + /* We're poking out of PCI territory */ + if (!PCI_DN(dn)) return NULL; + + parent = of_node_to_eeh_dev(dn); + /* We're poking out of PCI territory */ + if (!parent) return NULL; + + if (parent->pe) + return parent->pe; + + dn = dn->parent; + } + + return NULL; +} + +/** + * eeh_add_to_parent_pe - Add EEH device to parent PE + * @edev: EEH device + * + * Add EEH device to the parent PE. If the parent PE already + * exists, the PE type will be changed to EEH_PE_BUS. Otherwise, + * we have to create new PE to hold the EEH device and the new + * PE will be linked to its parent PE as well. + */ +int eeh_add_to_parent_pe(struct eeh_dev *edev) +{ + struct eeh_pe *pe, *parent; + + /* + * Search the PE has been existing or not according + * to the PE address. If that has been existing, the + * PE should be composed of PCI bus and its subordinate + * components. + */ + pe = eeh_pe_get(edev); + if (pe) { + if (!edev->pe_config_addr) { + pr_err("%s: PE with addr 0x%x already exists\n", + __func__, edev->config_addr); + return -EEXIST; + } + + /* Mark the PE as type of PCI bus */ + pe->type = EEH_PE_BUS; + edev->pe = pe; + + /* Put the edev to PE */ + list_add_tail(&edev->list, &pe->edevs); + pr_debug("EEH: Add %s to Bus PE#%x\n", + edev->dn->full_name, pe->addr); + + return 0; + } + + /* Create a new EEH PE */ + pe = eeh_pe_alloc(edev->phb, EEH_PE_DEVICE); + if (!pe) { + pr_err("%s: out of memory!\n", __func__); + return -ENOMEM; + } + pe->addr = edev->pe_config_addr; + pe->config_addr = edev->config_addr; + + /* + * Put the new EEH PE into hierarchy tree. If the parent + * can't be found, the newly created PE will be attached + * to PHB directly. Otherwise, we have to associate the + * PE with its parent. + */ + parent = eeh_pe_get_parent(edev); + if (!parent) { + parent = eeh_phb_pe_get(edev->phb); + if (!parent) { + pr_err("%s: No PHB PE is found (PHB Domain=%d)\n", + __func__, edev->phb->global_number); + edev->pe = NULL; + kfree(pe); + return -EEXIST; + } + } + pe->parent = parent; + + /* + * Put the newly created PE into the child list and + * link the EEH device accordingly. + */ + list_add_tail(&pe->child, &parent->child_list); + list_add_tail(&edev->list, &pe->edevs); + edev->pe = pe; + pr_debug("EEH: Add %s to Device PE#%x, Parent PE#%x\n", + edev->dn->full_name, pe->addr, pe->parent->addr); + + return 0; +} + +/** + * eeh_rmv_from_parent_pe - Remove one EEH device from the associated PE + * @edev: EEH device + * + * The PE hierarchy tree might be changed when doing PCI hotplug. + * Also, the PCI devices or buses could be removed from the system + * during EEH recovery. So we have to call the function remove the + * corresponding PE accordingly if necessary. + */ +int eeh_rmv_from_parent_pe(struct eeh_dev *edev) +{ + struct eeh_pe *pe, *parent; + + if (!edev->pe) { + pr_warning("%s: No PE found for EEH device %s\n", + __func__, edev->dn->full_name); + return -EEXIST; + } + + /* Remove the EEH device */ + pe = edev->pe; + edev->pe = NULL; + list_del(&edev->list); + + /* + * Check if the parent PE includes any EEH devices. + * If not, we should delete that. Also, we should + * delete the parent PE if it doesn't have associated + * child PEs and EEH devices. + */ + while (1) { + parent = pe->parent; + if (pe->type == EEH_PE_PHB) + break; + + if (list_empty(&pe->edevs) && + list_empty(&pe->child_list)) { + list_del(&pe->child); + kfree(pe); + } + + pe = parent; + } + + return 0; +} + +/** + * __eeh_pe_state_mark - Mark the state for the PE + * @data: EEH PE + * @flag: state + * + * The function is used to mark the indicated state for the given + * PE. Also, the associated PCI devices will be put into IO frozen + * state as well. + */ +static void *__eeh_pe_state_mark(void *data, void *flag) +{ + struct eeh_pe *pe = (struct eeh_pe *)data; + int state = *((int *)flag); + struct eeh_dev *tmp; + struct pci_dev *pdev; + + /* + * Mark the PE with the indicated state. Also, + * the associated PCI device will be put into + * I/O frozen state to avoid I/O accesses from + * the PCI device driver. + */ + pe->state |= state; + eeh_pe_for_each_dev(pe, tmp) { + pdev = eeh_dev_to_pci_dev(tmp); + if (pdev) + pdev->error_state = pci_channel_io_frozen; + } + + return NULL; +} + +/** + * eeh_pe_state_mark - Mark specified state for PE and its associated device + * @pe: EEH PE + * + * EEH error affects the current PE and its child PEs. The function + * is used to mark appropriate state for the affected PEs and the + * associated devices. + */ +void eeh_pe_state_mark(struct eeh_pe *pe, int state) +{ + eeh_pe_traverse(pe, __eeh_pe_state_mark, &state); +} + +/** + * __eeh_pe_state_clear - Clear state for the PE + * @data: EEH PE + * @flag: state + * + * The function is used to clear the indicated state from the + * given PE. Besides, we also clear the check count of the PE + * as well. + */ +static void *__eeh_pe_state_clear(void *data, void *flag) +{ + struct eeh_pe *pe = (struct eeh_pe *)data; + int state = *((int *)flag); + + pe->state &= ~state; + pe->check_count = 0; + + return NULL; +} + +/** + * eeh_pe_state_clear - Clear state for the PE and its children + * @pe: PE + * @state: state to be cleared + * + * When the PE and its children has been recovered from error, + * we need clear the error state for that. The function is used + * for the purpose. + */ +void eeh_pe_state_clear(struct eeh_pe *pe, int state) +{ + eeh_pe_traverse(pe, __eeh_pe_state_clear, &state); +} + +/** + * eeh_restore_one_device_bars - Restore the Base Address Registers for one device + * @data: EEH device + * @flag: Unused + * + * Loads the PCI configuration space base address registers, + * the expansion ROM base address, the latency timer, and etc. + * from the saved values in the device node. + */ +static void *eeh_restore_one_device_bars(void *data, void *flag) +{ + int i; + u32 cmd; + struct eeh_dev *edev = (struct eeh_dev *)data; + struct device_node *dn = eeh_dev_to_of_node(edev); + + for (i = 4; i < 10; i++) + eeh_ops->write_config(dn, i*4, 4, edev->config_space[i]); + /* 12 == Expansion ROM Address */ + eeh_ops->write_config(dn, 12*4, 4, edev->config_space[12]); + +#define BYTE_SWAP(OFF) (8*((OFF)/4)+3-(OFF)) +#define SAVED_BYTE(OFF) (((u8 *)(edev->config_space))[BYTE_SWAP(OFF)]) + + eeh_ops->write_config(dn, PCI_CACHE_LINE_SIZE, 1, + SAVED_BYTE(PCI_CACHE_LINE_SIZE)); + eeh_ops->write_config(dn, PCI_LATENCY_TIMER, 1, + SAVED_BYTE(PCI_LATENCY_TIMER)); + + /* max latency, min grant, interrupt pin and line */ + eeh_ops->write_config(dn, 15*4, 4, edev->config_space[15]); + + /* + * Restore PERR & SERR bits, some devices require it, + * don't touch the other command bits + */ + eeh_ops->read_config(dn, PCI_COMMAND, 4, &cmd); + if (edev->config_space[1] & PCI_COMMAND_PARITY) + cmd |= PCI_COMMAND_PARITY; + else + cmd &= ~PCI_COMMAND_PARITY; + if (edev->config_space[1] & PCI_COMMAND_SERR) + cmd |= PCI_COMMAND_SERR; + else + cmd &= ~PCI_COMMAND_SERR; + eeh_ops->write_config(dn, PCI_COMMAND, 4, cmd); + + return NULL; +} + +/** + * eeh_pe_restore_bars - Restore the PCI config space info + * @pe: EEH PE + * + * This routine performs a recursive walk to the children + * of this device as well. + */ +void eeh_pe_restore_bars(struct eeh_pe *pe) +{ + eeh_pe_dev_traverse(pe, eeh_restore_one_device_bars, NULL); +} + +/** + * eeh_pe_bus_get - Retrieve PCI bus according to the given PE + * @pe: EEH PE + * + * Retrieve the PCI bus according to the given PE. Basically, + * there're 3 types of PEs: PHB/Bus/Device. For PHB PE, the + * primary PCI bus will be retrieved. The parent bus will be + * returned for BUS PE. However, we don't have associated PCI + * bus for DEVICE PE. + */ +struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe) +{ + struct pci_bus *bus = NULL; + struct eeh_dev *edev; + struct pci_dev *pdev; + + if (pe->type == EEH_PE_PHB) { + bus = pe->phb->bus; + } else if (pe->type == EEH_PE_BUS) { + edev = list_first_entry(&pe->edevs, struct eeh_dev, list); + pdev = eeh_dev_to_pci_dev(edev); + if (pdev) + bus = pdev->bus; + } + + return bus; +} diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index c33360ec4f4..19506f93573 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -129,27 +129,117 @@ static int pseries_eeh_init(void) eeh_error_buf_size = RTAS_ERROR_LOG_MAX; } + /* Set EEH probe mode */ + eeh_probe_mode_set(EEH_PROBE_MODE_DEVTREE); + return 0; } /** + * pseries_eeh_of_probe - EEH probe on the given device + * @dn: OF node + * @flag: Unused + * + * When EEH module is installed during system boot, all PCI devices + * are checked one by one to see if it supports EEH. The function + * is introduced for the purpose. + */ +static void *pseries_eeh_of_probe(struct device_node *dn, void *flag) +{ + struct eeh_dev *edev; + struct eeh_pe pe; + const u32 *class_code, *vendor_id, *device_id; + const u32 *regs; + int enable = 0; + int ret; + + /* Retrieve OF node and eeh device */ + edev = of_node_to_eeh_dev(dn); + if (!of_device_is_available(dn)) + return NULL; + + /* Retrieve class/vendor/device IDs */ + class_code = of_get_property(dn, "class-code", NULL); + vendor_id = of_get_property(dn, "vendor-id", NULL); + device_id = of_get_property(dn, "device-id", NULL); + + /* Skip for bad OF node or PCI-ISA bridge */ + if (!class_code || !vendor_id || !device_id) + return NULL; + if (dn->type && !strcmp(dn->type, "isa")) + return NULL; + + /* Update class code and mode of eeh device */ + edev->class_code = *class_code; + edev->mode = 0; + + /* Retrieve the device address */ + regs = of_get_property(dn, "reg", NULL); + if (!regs) { + pr_warning("%s: OF node property %s::reg not found\n", + __func__, dn->full_name); + return NULL; + } + + /* Initialize the fake PE */ + memset(&pe, 0, sizeof(struct eeh_pe)); + pe.phb = edev->phb; + pe.config_addr = regs[0]; + + /* Enable EEH on the device */ + ret = eeh_ops->set_option(&pe, EEH_OPT_ENABLE); + if (!ret) { + edev->config_addr = regs[0]; + /* Retrieve PE address */ + edev->pe_config_addr = eeh_ops->get_pe_addr(&pe); + pe.addr = edev->pe_config_addr; + + /* Some older systems (Power4) allow the ibm,set-eeh-option + * call to succeed even on nodes where EEH is not supported. + * Verify support explicitly. + */ + ret = eeh_ops->get_state(&pe, NULL); + if (ret > 0 && ret != EEH_STATE_NOT_SUPPORT) + enable = 1; + + if (enable) { + eeh_subsystem_enabled = 1; + eeh_add_to_parent_pe(edev); + + pr_debug("%s: EEH enabled on %s PHB#%d-PE#%x, config addr#%x\n", + __func__, dn->full_name, pe.phb->global_number, + pe.addr, pe.config_addr); + } else if (dn->parent && of_node_to_eeh_dev(dn->parent) && + (of_node_to_eeh_dev(dn->parent))->pe) { + /* This device doesn't support EEH, but it may have an + * EEH parent, in which case we mark it as supported. + */ + edev->config_addr = of_node_to_eeh_dev(dn->parent)->config_addr; + edev->pe_config_addr = of_node_to_eeh_dev(dn->parent)->pe_config_addr; + eeh_add_to_parent_pe(edev); + } + } + + /* Save memory bars */ + eeh_save_bars(edev); + + return NULL; +} + +/** * pseries_eeh_set_option - Initialize EEH or MMIO/DMA reenable - * @dn: device node + * @pe: EEH PE * @option: operation to be issued * * The function is used to control the EEH functionality globally. * Currently, following options are support according to PAPR: * Enable EEH, Disable EEH, Enable MMIO and Enable DMA */ -static int pseries_eeh_set_option(struct device_node *dn, int option) +static int pseries_eeh_set_option(struct eeh_pe *pe, int option) { int ret = 0; - struct eeh_dev *edev; - const u32 *reg; int config_addr; - edev = of_node_to_eeh_dev(dn); - /* * When we're enabling or disabling EEH functioality on * the particular PE, the PE config address is possibly @@ -159,15 +249,11 @@ static int pseries_eeh_set_option(struct device_node *dn, int option) switch (option) { case EEH_OPT_DISABLE: case EEH_OPT_ENABLE: - reg = of_get_property(dn, "reg", NULL); - config_addr = reg[0]; - break; - case EEH_OPT_THAW_MMIO: case EEH_OPT_THAW_DMA: - config_addr = edev->config_addr; - if (edev->pe_config_addr) - config_addr = edev->pe_config_addr; + config_addr = pe->config_addr; + if (pe->addr) + config_addr = pe->addr; break; default: @@ -177,15 +263,15 @@ static int pseries_eeh_set_option(struct device_node *dn, int option) } ret = rtas_call(ibm_set_eeh_option, 4, 1, NULL, - config_addr, BUID_HI(edev->phb->buid), - BUID_LO(edev->phb->buid), option); + config_addr, BUID_HI(pe->phb->buid), + BUID_LO(pe->phb->buid), option); return ret; } /** * pseries_eeh_get_pe_addr - Retrieve PE address - * @dn: device node + * @pe: EEH PE * * Retrieve the assocated PE address. Actually, there're 2 RTAS * function calls dedicated for the purpose. We need implement @@ -196,14 +282,11 @@ static int pseries_eeh_set_option(struct device_node *dn, int option) * It's notable that zero'ed return value means invalid PE config * address. */ -static int pseries_eeh_get_pe_addr(struct device_node *dn) +static int pseries_eeh_get_pe_addr(struct eeh_pe *pe) { - struct eeh_dev *edev; int ret = 0; int rets[3]; - edev = of_node_to_eeh_dev(dn); - if (ibm_get_config_addr_info2 != RTAS_UNKNOWN_SERVICE) { /* * First of all, we need to make sure there has one PE @@ -211,18 +294,18 @@ static int pseries_eeh_get_pe_addr(struct device_node *dn) * meaningless. */ ret = rtas_call(ibm_get_config_addr_info2, 4, 2, rets, - edev->config_addr, BUID_HI(edev->phb->buid), - BUID_LO(edev->phb->buid), 1); + pe->config_addr, BUID_HI(pe->phb->buid), + BUID_LO(pe->phb->buid), 1); if (ret || (rets[0] == 0)) return 0; /* Retrieve the associated PE config address */ ret = rtas_call(ibm_get_config_addr_info2, 4, 2, rets, - edev->config_addr, BUID_HI(edev->phb->buid), - BUID_LO(edev->phb->buid), 0); + pe->config_addr, BUID_HI(pe->phb->buid), + BUID_LO(pe->phb->buid), 0); if (ret) { - pr_warning("%s: Failed to get PE address for %s\n", - __func__, dn->full_name); + pr_warning("%s: Failed to get address for PHB#%d-PE#%x\n", + __func__, pe->phb->global_number, pe->config_addr); return 0; } @@ -231,11 +314,11 @@ static int pseries_eeh_get_pe_addr(struct device_node *dn) if (ibm_get_config_addr_info != RTAS_UNKNOWN_SERVICE) { ret = rtas_call(ibm_get_config_addr_info, 4, 2, rets, - edev->config_addr, BUID_HI(edev->phb->buid), - BUID_LO(edev->phb->buid), 0); + pe->config_addr, BUID_HI(pe->phb->buid), + BUID_LO(pe->phb->buid), 0); if (ret) { - pr_warning("%s: Failed to get PE address for %s\n", - __func__, dn->full_name); + pr_warning("%s: Failed to get address for PHB#%d-PE#%x\n", + __func__, pe->phb->global_number, pe->config_addr); return 0; } @@ -247,7 +330,7 @@ static int pseries_eeh_get_pe_addr(struct device_node *dn) /** * pseries_eeh_get_state - Retrieve PE state - * @dn: PE associated device node + * @pe: EEH PE * @state: return value * * Retrieve the state of the specified PE. On RTAS compliant @@ -258,30 +341,28 @@ static int pseries_eeh_get_pe_addr(struct device_node *dn) * RTAS calls for the purpose, we need to try the new one and back * to the old one if the new one couldn't work properly. */ -static int pseries_eeh_get_state(struct device_node *dn, int *state) +static int pseries_eeh_get_state(struct eeh_pe *pe, int *state) { - struct eeh_dev *edev; int config_addr; int ret; int rets[4]; int result; /* Figure out PE config address if possible */ - edev = of_node_to_eeh_dev(dn); - config_addr = edev->config_addr; - if (edev->pe_config_addr) - config_addr = edev->pe_config_addr; + config_addr = pe->config_addr; + if (pe->addr) + config_addr = pe->addr; if (ibm_read_slot_reset_state2 != RTAS_UNKNOWN_SERVICE) { ret = rtas_call(ibm_read_slot_reset_state2, 3, 4, rets, - config_addr, BUID_HI(edev->phb->buid), - BUID_LO(edev->phb->buid)); + config_addr, BUID_HI(pe->phb->buid), + BUID_LO(pe->phb->buid)); } else if (ibm_read_slot_reset_state != RTAS_UNKNOWN_SERVICE) { /* Fake PE unavailable info */ rets[2] = 0; ret = rtas_call(ibm_read_slot_reset_state, 3, 3, rets, - config_addr, BUID_HI(edev->phb->buid), - BUID_LO(edev->phb->buid)); + config_addr, BUID_HI(pe->phb->buid), + BUID_LO(pe->phb->buid)); } else { return EEH_STATE_NOT_SUPPORT; } @@ -333,34 +414,32 @@ static int pseries_eeh_get_state(struct device_node *dn, int *state) /** * pseries_eeh_reset - Reset the specified PE - * @dn: PE associated device node + * @pe: EEH PE * @option: reset option * * Reset the specified PE */ -static int pseries_eeh_reset(struct device_node *dn, int option) +static int pseries_eeh_reset(struct eeh_pe *pe, int option) { - struct eeh_dev *edev; int config_addr; int ret; /* Figure out PE address */ - edev = of_node_to_eeh_dev(dn); - config_addr = edev->config_addr; - if (edev->pe_config_addr) - config_addr = edev->pe_config_addr; + config_addr = pe->config_addr; + if (pe->addr) + config_addr = pe->addr; /* Reset PE through RTAS call */ ret = rtas_call(ibm_set_slot_reset, 4, 1, NULL, - config_addr, BUID_HI(edev->phb->buid), - BUID_LO(edev->phb->buid), option); + config_addr, BUID_HI(pe->phb->buid), + BUID_LO(pe->phb->buid), option); /* If fundamental-reset not supported, try hot-reset */ if (option == EEH_RESET_FUNDAMENTAL && ret == -8) { ret = rtas_call(ibm_set_slot_reset, 4, 1, NULL, - config_addr, BUID_HI(edev->phb->buid), - BUID_LO(edev->phb->buid), EEH_RESET_HOT); + config_addr, BUID_HI(pe->phb->buid), + BUID_LO(pe->phb->buid), EEH_RESET_HOT); } return ret; @@ -368,13 +447,13 @@ static int pseries_eeh_reset(struct device_node *dn, int option) /** * pseries_eeh_wait_state - Wait for PE state - * @dn: PE associated device node + * @pe: EEH PE * @max_wait: maximal period in microsecond * * Wait for the state of associated PE. It might take some time * to retrieve the PE's state. */ -static int pseries_eeh_wait_state(struct device_node *dn, int max_wait) +static int pseries_eeh_wait_state(struct eeh_pe *pe, int max_wait) { int ret; int mwait; @@ -391,7 +470,7 @@ static int pseries_eeh_wait_state(struct device_node *dn, int max_wait) #define EEH_STATE_MAX_WAIT_TIME (300 * 1000) while (1) { - ret = pseries_eeh_get_state(dn, &mwait); + ret = pseries_eeh_get_state(pe, &mwait); /* * If the PE's state is temporarily unavailable, @@ -426,7 +505,7 @@ static int pseries_eeh_wait_state(struct device_node *dn, int max_wait) /** * pseries_eeh_get_log - Retrieve error log - * @dn: device node + * @pe: EEH PE * @severity: temporary or permanent error log * @drv_log: driver log to be combined with retrieved error log * @len: length of driver log @@ -435,24 +514,22 @@ static int pseries_eeh_wait_state(struct device_node *dn, int max_wait) * Actually, the error will be retrieved through the dedicated * RTAS call. */ -static int pseries_eeh_get_log(struct device_node *dn, int severity, char *drv_log, unsigned long len) +static int pseries_eeh_get_log(struct eeh_pe *pe, int severity, char *drv_log, unsigned long len) { - struct eeh_dev *edev; int config_addr; unsigned long flags; int ret; - edev = of_node_to_eeh_dev(dn); spin_lock_irqsave(&slot_errbuf_lock, flags); memset(slot_errbuf, 0, eeh_error_buf_size); /* Figure out the PE address */ - config_addr = edev->config_addr; - if (edev->pe_config_addr) - config_addr = edev->pe_config_addr; + config_addr = pe->config_addr; + if (pe->addr) + config_addr = pe->addr; ret = rtas_call(ibm_slot_error_detail, 8, 1, NULL, config_addr, - BUID_HI(edev->phb->buid), BUID_LO(edev->phb->buid), + BUID_HI(pe->phb->buid), BUID_LO(pe->phb->buid), virt_to_phys(drv_log), len, virt_to_phys(slot_errbuf), eeh_error_buf_size, severity); @@ -465,40 +542,38 @@ static int pseries_eeh_get_log(struct device_node *dn, int severity, char *drv_l /** * pseries_eeh_configure_bridge - Configure PCI bridges in the indicated PE - * @dn: PE associated device node + * @pe: EEH PE * * The function will be called to reconfigure the bridges included * in the specified PE so that the mulfunctional PE would be recovered * again. */ -static int pseries_eeh_configure_bridge(struct device_node *dn) +static int pseries_eeh_configure_bridge(struct eeh_pe *pe) { - struct eeh_dev *edev; int config_addr; int ret; /* Figure out the PE address */ - edev = of_node_to_eeh_dev(dn); - config_addr = edev->config_addr; - if (edev->pe_config_addr) - config_addr = edev->pe_config_addr; + config_addr = pe->config_addr; + if (pe->addr) + config_addr = pe->addr; /* Use new configure-pe function, if supported */ if (ibm_configure_pe != RTAS_UNKNOWN_SERVICE) { ret = rtas_call(ibm_configure_pe, 3, 1, NULL, - config_addr, BUID_HI(edev->phb->buid), - BUID_LO(edev->phb->buid)); + config_addr, BUID_HI(pe->phb->buid), + BUID_LO(pe->phb->buid)); } else if (ibm_configure_bridge != RTAS_UNKNOWN_SERVICE) { ret = rtas_call(ibm_configure_bridge, 3, 1, NULL, - config_addr, BUID_HI(edev->phb->buid), - BUID_LO(edev->phb->buid)); + config_addr, BUID_HI(pe->phb->buid), + BUID_LO(pe->phb->buid)); } else { return -EFAULT; } if (ret) - pr_warning("%s: Unable to configure bridge %d for %s\n", - __func__, ret, dn->full_name); + pr_warning("%s: Unable to configure bridge PHB#%d-PE#%x (%d)\n", + __func__, pe->phb->global_number, pe->addr, ret); return ret; } @@ -542,6 +617,8 @@ static int pseries_eeh_write_config(struct device_node *dn, int where, int size, static struct eeh_ops pseries_eeh_ops = { .name = "pseries", .init = pseries_eeh_init, + .of_probe = pseries_eeh_of_probe, + .dev_probe = NULL, .set_option = pseries_eeh_set_option, .get_pe_addr = pseries_eeh_get_pe_addr, .get_state = pseries_eeh_get_state, @@ -559,7 +636,21 @@ static struct eeh_ops pseries_eeh_ops = { * EEH initialization on pseries platform. This function should be * called before any EEH related functions. */ -int __init eeh_pseries_init(void) +static int __init eeh_pseries_init(void) { - return eeh_ops_register(&pseries_eeh_ops); + int ret = -EINVAL; + + if (!machine_is(pseries)) + return ret; + + ret = eeh_ops_register(&pseries_eeh_ops); + if (!ret) + pr_info("EEH: pSeries platform initialized\n"); + else + pr_info("EEH: pSeries platform initialization failure (%d)\n", + ret); + + return ret; } + +early_initcall(eeh_pseries_init); diff --git a/arch/powerpc/platforms/pseries/eeh_sysfs.c b/arch/powerpc/platforms/pseries/eeh_sysfs.c index 243b3510d70..d37708360f2 100644 --- a/arch/powerpc/platforms/pseries/eeh_sysfs.c +++ b/arch/powerpc/platforms/pseries/eeh_sysfs.c @@ -53,9 +53,6 @@ static DEVICE_ATTR(_name, S_IRUGO, eeh_show_##_name, NULL); EEH_SHOW_ATTR(eeh_mode, mode, "0x%x"); EEH_SHOW_ATTR(eeh_config_addr, config_addr, "0x%x"); EEH_SHOW_ATTR(eeh_pe_config_addr, pe_config_addr, "0x%x"); -EEH_SHOW_ATTR(eeh_check_count, check_count, "%d" ); -EEH_SHOW_ATTR(eeh_freeze_count, freeze_count, "%d" ); -EEH_SHOW_ATTR(eeh_false_positives, false_positives, "%d" ); void eeh_sysfs_add_device(struct pci_dev *pdev) { @@ -64,9 +61,6 @@ void eeh_sysfs_add_device(struct pci_dev *pdev) rc += device_create_file(&pdev->dev, &dev_attr_eeh_mode); rc += device_create_file(&pdev->dev, &dev_attr_eeh_config_addr); rc += device_create_file(&pdev->dev, &dev_attr_eeh_pe_config_addr); - rc += device_create_file(&pdev->dev, &dev_attr_eeh_check_count); - rc += device_create_file(&pdev->dev, &dev_attr_eeh_false_positives); - rc += device_create_file(&pdev->dev, &dev_attr_eeh_freeze_count); if (rc) printk(KERN_WARNING "EEH: Unable to create sysfs entries\n"); @@ -77,8 +71,5 @@ void eeh_sysfs_remove_device(struct pci_dev *pdev) device_remove_file(&pdev->dev, &dev_attr_eeh_mode); device_remove_file(&pdev->dev, &dev_attr_eeh_config_addr); device_remove_file(&pdev->dev, &dev_attr_eeh_pe_config_addr); - device_remove_file(&pdev->dev, &dev_attr_eeh_check_count); - device_remove_file(&pdev->dev, &dev_attr_eeh_false_positives); - device_remove_file(&pdev->dev, &dev_attr_eeh_freeze_count); } diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index bca220f2873..6153eea27ce 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -28,6 +28,7 @@ #include <linux/types.h> #include <linux/slab.h> #include <linux/mm.h> +#include <linux/memblock.h> #include <linux/spinlock.h> #include <linux/sched.h> /* for show_stack */ #include <linux/string.h> @@ -41,7 +42,6 @@ #include <asm/iommu.h> #include <asm/pci-bridge.h> #include <asm/machdep.h> -#include <asm/abs_addr.h> #include <asm/pSeries_reconfig.h> #include <asm/firmware.h> #include <asm/tce.h> @@ -99,7 +99,7 @@ static int tce_build_pSeries(struct iommu_table *tbl, long index, while (npages--) { /* can't move this out since we might cross MEMBLOCK boundary */ - rpn = (virt_to_abs(uaddr)) >> TCE_SHIFT; + rpn = __pa(uaddr) >> TCE_SHIFT; *tcep = proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT; uaddr += TCE_PAGE_SIZE; @@ -148,7 +148,7 @@ static int tce_build_pSeriesLP(struct iommu_table *tbl, long tcenum, int ret = 0; long tcenum_start = tcenum, npages_start = npages; - rpn = (virt_to_abs(uaddr)) >> TCE_SHIFT; + rpn = __pa(uaddr) >> TCE_SHIFT; proto_tce = TCE_PCI_READ; if (direction != DMA_TO_DEVICE) proto_tce |= TCE_PCI_WRITE; @@ -217,7 +217,7 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, __get_cpu_var(tce_page) = tcep; } - rpn = (virt_to_abs(uaddr)) >> TCE_SHIFT; + rpn = __pa(uaddr) >> TCE_SHIFT; proto_tce = TCE_PCI_READ; if (direction != DMA_TO_DEVICE) proto_tce |= TCE_PCI_WRITE; @@ -237,7 +237,7 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, rc = plpar_tce_put_indirect((u64)tbl->it_index, (u64)tcenum << 12, - (u64)virt_to_abs(tcep), + (u64)__pa(tcep), limit); npages -= limit; @@ -441,7 +441,7 @@ static int tce_setrange_multi_pSeriesLP(unsigned long start_pfn, rc = plpar_tce_put_indirect(liobn, dma_offset, - (u64)virt_to_abs(tcep), + (u64)__pa(tcep), limit); num_tce -= limit; diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 5f3ef876ded..177055d0186 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -31,7 +31,6 @@ #include <asm/page.h> #include <asm/pgtable.h> #include <asm/machdep.h> -#include <asm/abs_addr.h> #include <asm/mmu_context.h> #include <asm/iommu.h> #include <asm/tlbflush.h> diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c index 109fdb75578..d19f4977c83 100644 --- a/arch/powerpc/platforms/pseries/msi.c +++ b/arch/powerpc/platforms/pseries/msi.c @@ -210,6 +210,7 @@ static struct device_node *find_pe_total_msi(struct pci_dev *dev, int *total) static struct device_node *find_pe_dn(struct pci_dev *dev, int *total) { struct device_node *dn; + struct eeh_dev *edev; /* Found our PE and assume 8 at that point. */ @@ -217,7 +218,10 @@ static struct device_node *find_pe_dn(struct pci_dev *dev, int *total) if (!dn) return NULL; - dn = eeh_find_device_pe(dn); + /* Get the top level device in the PE */ + edev = of_node_to_eeh_dev(dn); + edev = list_first_entry(&edev->pe->edevs, struct eeh_dev, list); + dn = eeh_dev_to_of_node(edev); if (!dn) return NULL; @@ -387,12 +391,13 @@ static int check_msix_entries(struct pci_dev *pdev) return 0; } -static int rtas_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) +static int rtas_setup_msi_irqs(struct pci_dev *pdev, int nvec_in, int type) { struct pci_dn *pdn; int hwirq, virq, i, rc; struct msi_desc *entry; struct msi_msg msg; + int nvec = nvec_in; pdn = get_pdn(pdev); if (!pdn) @@ -402,10 +407,23 @@ static int rtas_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) return -EINVAL; /* + * Firmware currently refuse any non power of two allocation + * so we round up if the quota will allow it. + */ + if (type == PCI_CAP_ID_MSIX) { + int m = roundup_pow_of_two(nvec); + int quota = msi_quota_for_device(pdev, m); + + if (quota >= m) + nvec = m; + } + + /* * Try the new more explicit firmware interface, if that fails fall * back to the old interface. The old interface is known to never * return MSI-Xs. */ +again: if (type == PCI_CAP_ID_MSI) { rc = rtas_change_msi(pdn, RTAS_CHANGE_MSI_FN, nvec); @@ -417,6 +435,10 @@ static int rtas_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) rc = rtas_change_msi(pdn, RTAS_CHANGE_MSIX_FN, nvec); if (rc != nvec) { + if (nvec != nvec_in) { + nvec = nvec_in; + goto again; + } pr_debug("rtas_msi: rtas_change_msi() failed\n"); return rc; } diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c index 2c6ded29f73..56b864d777e 100644 --- a/arch/powerpc/platforms/pseries/pci.c +++ b/arch/powerpc/platforms/pseries/pci.c @@ -73,7 +73,7 @@ void __init pSeries_final_fixup(void) { pSeries_request_regions(); - pci_addr_cache_build(); + eeh_addr_cache_build(); } /* diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 51ecac920dd..e3cb7ae6165 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -388,10 +388,8 @@ static void __init pSeries_setup_arch(void) /* Find and initialize PCI host bridges */ init_pci_config_tokens(); - eeh_pseries_init(); find_and_init_phbs(); pSeries_reconfig_notifier_register(&pci_dn_reconfig_nb); - eeh_init(); pSeries_nvram_init(); @@ -416,16 +414,20 @@ static int __init pSeries_init_panel(void) } machine_arch_initcall(pseries, pSeries_init_panel); -static int pseries_set_dabr(unsigned long dabr) +static int pseries_set_dabr(unsigned long dabr, unsigned long dabrx) { return plpar_hcall_norets(H_SET_DABR, dabr); } -static int pseries_set_xdabr(unsigned long dabr) +static int pseries_set_xdabr(unsigned long dabr, unsigned long dabrx) { - /* We want to catch accesses from kernel and userspace */ - return plpar_hcall_norets(H_SET_XDABR, dabr, - H_DABRX_KERNEL | H_DABRX_USER); + /* Have to set at least one bit in the DABRX according to PAPR */ + if (dabrx == 0 && dabr == 0) + dabrx = DABRX_USER; + /* PAPR says we can only set kernel and user bits */ + dabrx &= DABRX_KERNEL | DABRX_USER; + + return plpar_hcall_norets(H_SET_XDABR, dabr, dabrx); } #define CMO_CHARACTERISTICS_TOKEN 44 @@ -529,10 +531,10 @@ static void __init pSeries_init_early(void) if (firmware_has_feature(FW_FEATURE_LPAR)) hvc_vio_init_early(); #endif - if (firmware_has_feature(FW_FEATURE_DABR)) - ppc_md.set_dabr = pseries_set_dabr; - else if (firmware_has_feature(FW_FEATURE_XDABR)) + if (firmware_has_feature(FW_FEATURE_XDABR)) ppc_md.set_dabr = pseries_set_xdabr; + else if (firmware_has_feature(FW_FEATURE_DABR)) + ppc_md.set_dabr = pseries_set_dabr; pSeries_cmo_feature_init(); iommu_init_early_pSeries(); diff --git a/arch/powerpc/sysdev/dart_iommu.c b/arch/powerpc/sysdev/dart_iommu.c index 4f2680f431b..8ef63a01e34 100644 --- a/arch/powerpc/sysdev/dart_iommu.c +++ b/arch/powerpc/sysdev/dart_iommu.c @@ -43,7 +43,6 @@ #include <asm/iommu.h> #include <asm/pci-bridge.h> #include <asm/machdep.h> -#include <asm/abs_addr.h> #include <asm/cacheflush.h> #include <asm/ppc-pci.h> @@ -167,7 +166,7 @@ static int dart_build(struct iommu_table *tbl, long index, */ l = npages; while (l--) { - rpn = virt_to_abs(uaddr) >> DART_PAGE_SHIFT; + rpn = __pa(uaddr) >> DART_PAGE_SHIFT; *(dp++) = DARTMAP_VALID | (rpn & DARTMAP_RPNMASK); @@ -244,7 +243,7 @@ static int __init dart_init(struct device_node *dart_node) panic("DART: Cannot map registers!"); /* Map in DART table */ - dart_vbase = ioremap(virt_to_abs(dart_tablebase), dart_tablesize); + dart_vbase = ioremap(__pa(dart_tablebase), dart_tablesize); /* Fill initial table */ for (i = 0; i < dart_tablesize/4; i++) @@ -463,7 +462,7 @@ void __init alloc_dart_table(void) * will blow up an entire large page anyway in the kernel mapping */ dart_tablebase = (unsigned long) - abs_to_virt(memblock_alloc_base(1UL<<24, 1UL<<24, 0x80000000L)); + __va(memblock_alloc_base(1UL<<24, 1UL<<24, 0x80000000L)); printk(KERN_INFO "DART table allocated at: %lx\n", dart_tablebase); } diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 9b49c65ee7a..987f441525c 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -740,7 +740,7 @@ static void insert_bpts(void) static void insert_cpu_bpts(void) { if (dabr.enabled) - set_dabr(dabr.address | (dabr.enabled & 7)); + set_dabr(dabr.address | (dabr.enabled & 7), DABRX_ALL); if (iabr && cpu_has_feature(CPU_FTR_IABR)) mtspr(SPRN_IABR, iabr->address | (iabr->enabled & (BP_IABR|BP_IABR_TE))); @@ -768,7 +768,7 @@ static void remove_bpts(void) static void remove_cpu_bpts(void) { - set_dabr(0); + set_dabr(0, 0); if (cpu_has_feature(CPU_FTR_IABR)) mtspr(SPRN_IABR, 0); } |