diff options
Diffstat (limited to 'arch/powerpc')
79 files changed, 2360 insertions, 1119 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 155d571f5e2..8a54eb8e376 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -672,6 +672,9 @@ config ZONE_DMA bool default y +config NEED_DMA_MAP_STATE + def_bool (PPC64 || NOT_COHERENT_CACHE) + config GENERIC_ISA_DMA bool depends on PPC64 || POWER4 || 6xx && !CPM2 diff --git a/arch/powerpc/boot/dts/gef_ppc9a.dts b/arch/powerpc/boot/dts/gef_ppc9a.dts index 977f260d5e6..83f4b79dff8 100644 --- a/arch/powerpc/boot/dts/gef_ppc9a.dts +++ b/arch/powerpc/boot/dts/gef_ppc9a.dts @@ -1,7 +1,7 @@ /* - * GE Fanuc PPC9A Device Tree Source + * GE PPC9A Device Tree Source * - * Copyright 2008 GE Fanuc Intelligent Platforms Embedded Systems, Inc. + * Copyright 2008 GE Intelligent Platforms Embedded Systems, Inc. * * 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 diff --git a/arch/powerpc/boot/dts/gef_sbc310.dts b/arch/powerpc/boot/dts/gef_sbc310.dts index 8e4efff3bda..fc3a331dd39 100644 --- a/arch/powerpc/boot/dts/gef_sbc310.dts +++ b/arch/powerpc/boot/dts/gef_sbc310.dts @@ -1,7 +1,7 @@ /* - * GE Fanuc SBC310 Device Tree Source + * GE SBC310 Device Tree Source * - * Copyright 2008 GE Fanuc Intelligent Platforms Embedded Systems, Inc. + * Copyright 2008 GE Intelligent Platforms Embedded Systems, Inc. * * 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 diff --git a/arch/powerpc/boot/dts/gef_sbc610.dts b/arch/powerpc/boot/dts/gef_sbc610.dts index bb7060078fb..c0671cc9812 100644 --- a/arch/powerpc/boot/dts/gef_sbc610.dts +++ b/arch/powerpc/boot/dts/gef_sbc610.dts @@ -1,7 +1,7 @@ /* - * GE Fanuc SBC610 Device Tree Source + * GE SBC610 Device Tree Source * - * Copyright 2008 GE Fanuc Intelligent Platforms Embedded Systems, Inc. + * Copyright 2008 GE Intelligent Platforms Embedded Systems, Inc. * * 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 diff --git a/arch/powerpc/boot/dts/kmeter1.dts b/arch/powerpc/boot/dts/kmeter1.dts index 65b8b4f27ef..d8b5d12fb66 100644 --- a/arch/powerpc/boot/dts/kmeter1.dts +++ b/arch/powerpc/boot/dts/kmeter1.dts @@ -490,7 +490,7 @@ compatible = "cfi-flash"; /* * The Intel P30 chip has 2 non-identical chips on - * one die, so we need to define 2 seperate regions + * one die, so we need to define 2 separate regions * that are scanned by physmap_of independantly. */ reg = <0 0x00000000 0x02000000 diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h index 4774c2f9223..396d21a8005 100644 --- a/arch/powerpc/include/asm/compat.h +++ b/arch/powerpc/include/asm/compat.h @@ -7,7 +7,8 @@ #include <linux/types.h> #include <linux/sched.h> -#define COMPAT_USER_HZ 100 +#define COMPAT_USER_HZ 100 +#define COMPAT_UTS_MACHINE "ppc\0\0" typedef u32 compat_size_t; typedef s32 compat_ssize_t; diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h index 80a973bb9e7..c85ef230135 100644 --- a/arch/powerpc/include/asm/dma-mapping.h +++ b/arch/powerpc/include/asm/dma-mapping.h @@ -127,9 +127,6 @@ static inline int dma_supported(struct device *dev, u64 mask) return dma_ops->dma_supported(dev, mask); } -/* We have our own implementation of pci_set_dma_mask() */ -#define HAVE_ARCH_PCI_SET_DMA_MASK - static inline int dma_set_mask(struct device *dev, u64 dma_mask) { struct dma_map_ops *dma_ops = get_dma_ops(dev); diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h index af2abe74f54..aadf2dd6f84 100644 --- a/arch/powerpc/include/asm/kvm_asm.h +++ b/arch/powerpc/include/asm/kvm_asm.h @@ -97,4 +97,10 @@ #define RESUME_HOST RESUME_FLAG_HOST #define RESUME_HOST_NV (RESUME_FLAG_HOST|RESUME_FLAG_NV) +#define KVM_GUEST_MODE_NONE 0 +#define KVM_GUEST_MODE_GUEST 1 +#define KVM_GUEST_MODE_SKIP 2 + +#define KVM_INST_FETCH_FAILED -1 + #endif /* __POWERPC_KVM_ASM_H__ */ diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index 74b7369770d..db7db0a9696 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -22,7 +22,7 @@ #include <linux/types.h> #include <linux/kvm_host.h> -#include <asm/kvm_ppc.h> +#include <asm/kvm_book3s_64_asm.h> struct kvmppc_slb { u64 esid; @@ -33,7 +33,8 @@ struct kvmppc_slb { bool Ks; bool Kp; bool nx; - bool large; + bool large; /* PTEs are 16MB */ + bool tb; /* 1TB segment */ bool class; }; @@ -69,6 +70,7 @@ struct kvmppc_sid_map { struct kvmppc_vcpu_book3s { struct kvm_vcpu vcpu; + struct kvmppc_book3s_shadow_vcpu shadow_vcpu; struct kvmppc_sid_map sid_map[SID_MAP_NUM]; struct kvmppc_slb slb[64]; struct { @@ -89,6 +91,7 @@ struct kvmppc_vcpu_book3s { u64 vsid_next; u64 vsid_max; int context_id; + ulong prog_flags; /* flags to inject when giving a 700 trap */ }; #define CONTEXT_HOST 0 @@ -119,6 +122,10 @@ extern void kvmppc_set_bat(struct kvm_vcpu *vcpu, struct kvmppc_bat *bat, extern u32 kvmppc_trampoline_lowmem; extern u32 kvmppc_trampoline_enter; +extern void kvmppc_rmcall(ulong srr0, ulong srr1); +extern void kvmppc_load_up_fpu(void); +extern void kvmppc_load_up_altivec(void); +extern void kvmppc_load_up_vsx(void); static inline struct kvmppc_vcpu_book3s *to_book3s(struct kvm_vcpu *vcpu) { diff --git a/arch/powerpc/include/asm/kvm_book3s_64_asm.h b/arch/powerpc/include/asm/kvm_book3s_64_asm.h index 2e06ee8184e..183461b4840 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64_asm.h +++ b/arch/powerpc/include/asm/kvm_book3s_64_asm.h @@ -20,6 +20,8 @@ #ifndef __ASM_KVM_BOOK3S_ASM_H__ #define __ASM_KVM_BOOK3S_ASM_H__ +#ifdef __ASSEMBLY__ + #ifdef CONFIG_KVM_BOOK3S_64_HANDLER #include <asm/kvm_asm.h> @@ -55,4 +57,20 @@ kvmppc_resume_\intno: #endif /* CONFIG_KVM_BOOK3S_64_HANDLER */ +#else /*__ASSEMBLY__ */ + +struct kvmppc_book3s_shadow_vcpu { + ulong gpr[14]; + u32 cr; + u32 xer; + ulong host_r1; + ulong host_r2; + ulong handler; + ulong scratch0; + ulong scratch1; + ulong vmhandler; +}; + +#endif /*__ASSEMBLY__ */ + #endif /* __ASM_KVM_BOOK3S_ASM_H__ */ diff --git a/arch/powerpc/include/asm/kvm_e500.h b/arch/powerpc/include/asm/kvm_e500.h index 9d497ce4972..7fea26fffb2 100644 --- a/arch/powerpc/include/asm/kvm_e500.h +++ b/arch/powerpc/include/asm/kvm_e500.h @@ -52,9 +52,12 @@ struct kvmppc_vcpu_e500 { u32 mas5; u32 mas6; u32 mas7; + u32 l1csr0; u32 l1csr1; u32 hid0; u32 hid1; + u32 tlb0cfg; + u32 tlb1cfg; struct kvm_vcpu vcpu; }; diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 1201f62d0d7..5e5bae7e152 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -167,23 +167,40 @@ struct kvm_vcpu_arch { ulong trampoline_lowmem; ulong trampoline_enter; ulong highmem_handler; + ulong rmcall; ulong host_paca_phys; struct kvmppc_mmu mmu; #endif - u64 fpr[32]; ulong gpr[32]; + u64 fpr[32]; + u32 fpscr; + +#ifdef CONFIG_ALTIVEC + vector128 vr[32]; + vector128 vscr; +#endif + +#ifdef CONFIG_VSX + u64 vsr[32]; +#endif + ulong pc; - u32 cr; ulong ctr; ulong lr; + +#ifdef CONFIG_BOOKE ulong xer; + u32 cr; +#endif ulong msr; #ifdef CONFIG_PPC64 ulong shadow_msr; + ulong shadow_srr1; ulong hflags; + ulong guest_owned_ext; #endif u32 mmucr; ulong sprg0; @@ -242,6 +259,8 @@ struct kvm_vcpu_arch { #endif ulong fault_dear; ulong fault_esr; + ulong queued_dear; + ulong queued_esr; gpa_t paddr_accessed; u8 io_gpr; /* GPR used as IO source/target */ diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index 269ee46ab02..e2642829e43 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -28,6 +28,9 @@ #include <linux/types.h> #include <linux/kvm_types.h> #include <linux/kvm_host.h> +#ifdef CONFIG_PPC_BOOK3S +#include <asm/kvm_book3s.h> +#endif enum emulation_result { EMULATE_DONE, /* no further processing */ @@ -80,8 +83,9 @@ extern void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu); extern void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu); extern int kvmppc_core_pending_dec(struct kvm_vcpu *vcpu); -extern void kvmppc_core_queue_program(struct kvm_vcpu *vcpu); +extern void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong flags); extern void kvmppc_core_queue_dec(struct kvm_vcpu *vcpu); +extern void kvmppc_core_dequeue_dec(struct kvm_vcpu *vcpu); extern void kvmppc_core_queue_external(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq); @@ -95,4 +99,81 @@ extern void kvmppc_booke_exit(void); extern void kvmppc_core_destroy_mmu(struct kvm_vcpu *vcpu); +#ifdef CONFIG_PPC_BOOK3S + +/* We assume we're always acting on the current vcpu */ + +static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val) +{ + if ( num < 14 ) { + get_paca()->shadow_vcpu.gpr[num] = val; + to_book3s(vcpu)->shadow_vcpu.gpr[num] = val; + } else + vcpu->arch.gpr[num] = val; +} + +static inline ulong kvmppc_get_gpr(struct kvm_vcpu *vcpu, int num) +{ + if ( num < 14 ) + return get_paca()->shadow_vcpu.gpr[num]; + else + return vcpu->arch.gpr[num]; +} + +static inline void kvmppc_set_cr(struct kvm_vcpu *vcpu, u32 val) +{ + get_paca()->shadow_vcpu.cr = val; + to_book3s(vcpu)->shadow_vcpu.cr = val; +} + +static inline u32 kvmppc_get_cr(struct kvm_vcpu *vcpu) +{ + return get_paca()->shadow_vcpu.cr; +} + +static inline void kvmppc_set_xer(struct kvm_vcpu *vcpu, u32 val) +{ + get_paca()->shadow_vcpu.xer = val; + to_book3s(vcpu)->shadow_vcpu.xer = val; +} + +static inline u32 kvmppc_get_xer(struct kvm_vcpu *vcpu) +{ + return get_paca()->shadow_vcpu.xer; +} + +#else + +static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val) +{ + vcpu->arch.gpr[num] = val; +} + +static inline ulong kvmppc_get_gpr(struct kvm_vcpu *vcpu, int num) +{ + return vcpu->arch.gpr[num]; +} + +static inline void kvmppc_set_cr(struct kvm_vcpu *vcpu, u32 val) +{ + vcpu->arch.cr = val; +} + +static inline u32 kvmppc_get_cr(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.cr; +} + +static inline void kvmppc_set_xer(struct kvm_vcpu *vcpu, u32 val) +{ + vcpu->arch.xer = val; +} + +static inline u32 kvmppc_get_xer(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.xer; +} + +#endif + #endif /* __POWERPC_KVM_PPC_H__ */ diff --git a/arch/powerpc/include/asm/local.h b/arch/powerpc/include/asm/local.h index ce58c80e1bc..c2410af6bfd 100644 --- a/arch/powerpc/include/asm/local.h +++ b/arch/powerpc/include/asm/local.h @@ -172,29 +172,4 @@ static __inline__ long local_dec_if_positive(local_t *l) #define __local_add(i,l) ((l)->a.counter+=(i)) #define __local_sub(i,l) ((l)->a.counter-=(i)) -/* Need to disable preemption for the cpu local counters otherwise we could - still access a variable of a previous CPU in a non atomic way. */ -#define cpu_local_wrap_v(l) \ - ({ local_t res__; \ - preempt_disable(); \ - res__ = (l); \ - preempt_enable(); \ - res__; }) -#define cpu_local_wrap(l) \ - ({ preempt_disable(); \ - l; \ - preempt_enable(); }) \ - -#define cpu_local_read(l) cpu_local_wrap_v(local_read(&__get_cpu_var(l))) -#define cpu_local_set(l, i) cpu_local_wrap(local_set(&__get_cpu_var(l), (i))) -#define cpu_local_inc(l) cpu_local_wrap(local_inc(&__get_cpu_var(l))) -#define cpu_local_dec(l) cpu_local_wrap(local_dec(&__get_cpu_var(l))) -#define cpu_local_add(i, l) cpu_local_wrap(local_add((i), &__get_cpu_var(l))) -#define cpu_local_sub(i, l) cpu_local_wrap(local_sub((i), &__get_cpu_var(l))) - -#define __cpu_local_inc(l) cpu_local_inc(l) -#define __cpu_local_dec(l) cpu_local_dec(l) -#define __cpu_local_add(i, l) cpu_local_add((i), (l)) -#define __cpu_local_sub(i, l) cpu_local_sub((i), (l)) - #endif /* _ARCH_POWERPC_LOCAL_H */ diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index 5e9b4ef7141..a011603d407 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -14,11 +14,17 @@ #define _ASM_POWERPC_PACA_H #ifdef __KERNEL__ +#ifdef CONFIG_PPC64 + +#include <linux/init.h> #include <asm/types.h> #include <asm/lppaca.h> #include <asm/mmu.h> #include <asm/page.h> #include <asm/exception-64e.h> +#ifdef CONFIG_KVM_BOOK3S_64_HANDLER +#include <asm/kvm_book3s_64_asm.h> +#endif register struct paca_struct *local_paca asm("r13"); @@ -135,13 +141,26 @@ struct paca_struct { u64 esid; u64 vsid; } kvm_slb[64]; /* guest SLB */ + /* We use this to store guest state in */ + struct kvmppc_book3s_shadow_vcpu shadow_vcpu; u8 kvm_slb_max; /* highest used guest slb entry */ u8 kvm_in_guest; /* are we inside the guest? */ #endif }; -extern struct paca_struct paca[]; -extern void initialise_pacas(void); +extern struct paca_struct *paca; +extern __initdata struct paca_struct boot_paca; +extern void initialise_paca(struct paca_struct *new_paca, int cpu); + +extern void allocate_pacas(void); +extern void free_unused_pacas(void); + +#else /* CONFIG_PPC64 */ + +static inline void allocate_pacas(void) { }; +static inline void free_unused_pacas(void) { }; + +#endif /* CONFIG_PPC64 */ #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_PACA_H */ diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h index b5ea626eea2..a20a9ad2258 100644 --- a/arch/powerpc/include/asm/pci.h +++ b/arch/powerpc/include/asm/pci.h @@ -141,38 +141,6 @@ extern int pci_mmap_legacy_page_range(struct pci_bus *bus, #define HAVE_PCI_LEGACY 1 -#if defined(CONFIG_PPC64) || defined(CONFIG_NOT_COHERENT_CACHE) -/* - * For 64-bit kernels, pci_unmap_{single,page} is not a nop. - * For 32-bit non-coherent kernels, pci_dma_sync_single_for_cpu() and - * so on are not nops. - * and thus... - */ -#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME) \ - dma_addr_t ADDR_NAME; -#define DECLARE_PCI_UNMAP_LEN(LEN_NAME) \ - __u32 LEN_NAME; -#define pci_unmap_addr(PTR, ADDR_NAME) \ - ((PTR)->ADDR_NAME) -#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) \ - (((PTR)->ADDR_NAME) = (VAL)) -#define pci_unmap_len(PTR, LEN_NAME) \ - ((PTR)->LEN_NAME) -#define pci_unmap_len_set(PTR, LEN_NAME, VAL) \ - (((PTR)->LEN_NAME) = (VAL)) - -#else /* 32-bit && coherent */ - -/* pci_unmap_{page,single} is a nop so... */ -#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME) -#define DECLARE_PCI_UNMAP_LEN(LEN_NAME) -#define pci_unmap_addr(PTR, ADDR_NAME) (0) -#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) do { } while (0) -#define pci_unmap_len(PTR, LEN_NAME) (0) -#define pci_unmap_len_set(PTR, LEN_NAME, VAL) do { } while (0) - -#endif /* CONFIG_PPC64 || CONFIG_NOT_COHERENT_CACHE */ - #ifdef CONFIG_PPC64 /* The PCI address space does not equal the physical memory address diff --git a/arch/powerpc/include/asm/perf_event.h b/arch/powerpc/include/asm/perf_event.h index 3288ce3997e..e6d4ce69b12 100644 --- a/arch/powerpc/include/asm/perf_event.h +++ b/arch/powerpc/include/asm/perf_event.h @@ -1,110 +1,23 @@ /* - * Performance event support - PowerPC-specific definitions. + * Performance event support - hardware-specific disambiguation * - * Copyright 2008-2009 Paul Mackerras, IBM Corporation. + * For now this is a compile-time decision, but eventually it should be + * runtime. This would allow multiplatform perf event support for e300 (fsl + * embedded perf counters) plus server/classic, and would accommodate + * devices other than the core which provide their own performance counters. + * + * Copyright 2010 Freescale Semiconductor, Inc. * * 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/types.h> - -#include <asm/hw_irq.h> - -#define MAX_HWEVENTS 8 -#define MAX_EVENT_ALTERNATIVES 8 -#define MAX_LIMITED_HWCOUNTERS 2 - -/* - * This struct provides the constants and functions needed to - * describe the PMU on a particular POWER-family CPU. - */ -struct power_pmu { - const char *name; - int n_counter; - int max_alternatives; - unsigned long add_fields; - unsigned long test_adder; - int (*compute_mmcr)(u64 events[], int n_ev, - unsigned int hwc[], unsigned long mmcr[]); - int (*get_constraint)(u64 event_id, unsigned long *mskp, - unsigned long *valp); - int (*get_alternatives)(u64 event_id, unsigned int flags, - u64 alt[]); - void (*disable_pmc)(unsigned int pmc, unsigned long mmcr[]); - int (*limited_pmc_event)(u64 event_id); - u32 flags; - int n_generic; - int *generic_events; - int (*cache_events)[PERF_COUNT_HW_CACHE_MAX] - [PERF_COUNT_HW_CACHE_OP_MAX] - [PERF_COUNT_HW_CACHE_RESULT_MAX]; -}; - -/* - * Values for power_pmu.flags - */ -#define PPMU_LIMITED_PMC5_6 1 /* PMC5/6 have limited function */ -#define PPMU_ALT_SIPR 2 /* uses alternate posn for SIPR/HV */ - -/* - * Values for flags to get_alternatives() - */ -#define PPMU_LIMITED_PMC_OK 1 /* can put this on a limited PMC */ -#define PPMU_LIMITED_PMC_REQD 2 /* have to put this on a limited PMC */ -#define PPMU_ONLY_COUNT_RUN 4 /* only counting in run state */ - -extern int register_power_pmu(struct power_pmu *); -struct pt_regs; -extern unsigned long perf_misc_flags(struct pt_regs *regs); -extern unsigned long perf_instruction_pointer(struct pt_regs *regs); - -#define PERF_EVENT_INDEX_OFFSET 1 - -/* - * Only override the default definitions in include/linux/perf_event.h - * if we have hardware PMU support. - */ #ifdef CONFIG_PPC_PERF_CTRS -#define perf_misc_flags(regs) perf_misc_flags(regs) +#include <asm/perf_event_server.h> #endif -/* - * The power_pmu.get_constraint function returns a 32/64-bit value and - * a 32/64-bit mask that express the constraints between this event_id and - * other events. - * - * The value and mask are divided up into (non-overlapping) bitfields - * of three different types: - * - * Select field: this expresses the constraint that some set of bits - * in MMCR* needs to be set to a specific value for this event_id. For a - * select field, the mask contains 1s in every bit of the field, and - * the value contains a unique value for each possible setting of the - * MMCR* bits. The constraint checking code will ensure that two events - * that set the same field in their masks have the same value in their - * value dwords. - * - * Add field: this expresses the constraint that there can be at most - * N events in a particular class. A field of k bits can be used for - * N <= 2^(k-1) - 1. The mask has the most significant bit of the field - * set (and the other bits 0), and the value has only the least significant - * bit of the field set. In addition, the 'add_fields' and 'test_adder' - * in the struct power_pmu for this processor come into play. The - * add_fields value contains 1 in the LSB of the field, and the - * test_adder contains 2^(k-1) - 1 - N in the field. - * - * NAND field: this expresses the constraint that you may not have events - * in all of a set of classes. (For example, on PPC970, you can't select - * events from the FPU, ISU and IDU simultaneously, although any two are - * possible.) For N classes, the field is N+1 bits wide, and each class - * is assigned one bit from the least-significant N bits. The mask has - * only the most-significant bit set, and the value has only the bit - * for the event_id's class set. The test_adder has the least significant - * bit set in the field. - * - * If an event_id is not subject to the constraint expressed by a particular - * field, then it will have 0 in both the mask and value for that field. - */ +#ifdef CONFIG_FSL_EMB_PERF_EVENT +#include <asm/perf_event_fsl_emb.h> +#endif diff --git a/arch/powerpc/include/asm/perf_event_fsl_emb.h b/arch/powerpc/include/asm/perf_event_fsl_emb.h new file mode 100644 index 00000000000..718a9fa94e6 --- /dev/null +++ b/arch/powerpc/include/asm/perf_event_fsl_emb.h @@ -0,0 +1,50 @@ +/* + * Performance event support - Freescale embedded specific definitions. + * + * Copyright 2008-2009 Paul Mackerras, IBM Corporation. + * Copyright 2010 Freescale Semiconductor, Inc. + * + * 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/types.h> +#include <asm/hw_irq.h> + +#define MAX_HWEVENTS 4 + +/* event flags */ +#define FSL_EMB_EVENT_VALID 1 +#define FSL_EMB_EVENT_RESTRICTED 2 + +/* upper half of event flags is PMLCb */ +#define FSL_EMB_EVENT_THRESHMUL 0x0000070000000000ULL +#define FSL_EMB_EVENT_THRESH 0x0000003f00000000ULL + +struct fsl_emb_pmu { + const char *name; + int n_counter; /* total number of counters */ + + /* + * The number of contiguous counters starting at zero that + * can hold restricted events, or zero if there are no + * restricted events. + * + * This isn't a very flexible method of expressing constraints, + * but it's very simple and is adequate for existing chips. + */ + int n_restricted; + + /* Returns event flags and PMLCb (FSL_EMB_EVENT_*) */ + u64 (*xlate_event)(u64 event_id); + + int n_generic; + int *generic_events; + int (*cache_events)[PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX]; +}; + +int register_fsl_emb_pmu(struct fsl_emb_pmu *); diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h new file mode 100644 index 00000000000..8f1df1208d2 --- /dev/null +++ b/arch/powerpc/include/asm/perf_event_server.h @@ -0,0 +1,110 @@ +/* + * Performance event support - PowerPC classic/server specific definitions. + * + * Copyright 2008-2009 Paul Mackerras, IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/types.h> +#include <asm/hw_irq.h> + +#define MAX_HWEVENTS 8 +#define MAX_EVENT_ALTERNATIVES 8 +#define MAX_LIMITED_HWCOUNTERS 2 + +/* + * This struct provides the constants and functions needed to + * describe the PMU on a particular POWER-family CPU. + */ +struct power_pmu { + const char *name; + int n_counter; + int max_alternatives; + unsigned long add_fields; + unsigned long test_adder; + int (*compute_mmcr)(u64 events[], int n_ev, + unsigned int hwc[], unsigned long mmcr[]); + int (*get_constraint)(u64 event_id, unsigned long *mskp, + unsigned long *valp); + int (*get_alternatives)(u64 event_id, unsigned int flags, + u64 alt[]); + void (*disable_pmc)(unsigned int pmc, unsigned long mmcr[]); + int (*limited_pmc_event)(u64 event_id); + u32 flags; + int n_generic; + int *generic_events; + int (*cache_events)[PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX]; +}; + +/* + * Values for power_pmu.flags + */ +#define PPMU_LIMITED_PMC5_6 1 /* PMC5/6 have limited function */ +#define PPMU_ALT_SIPR 2 /* uses alternate posn for SIPR/HV */ + +/* + * Values for flags to get_alternatives() + */ +#define PPMU_LIMITED_PMC_OK 1 /* can put this on a limited PMC */ +#define PPMU_LIMITED_PMC_REQD 2 /* have to put this on a limited PMC */ +#define PPMU_ONLY_COUNT_RUN 4 /* only counting in run state */ + +extern int register_power_pmu(struct power_pmu *); + +struct pt_regs; +extern unsigned long perf_misc_flags(struct pt_regs *regs); +extern unsigned long perf_instruction_pointer(struct pt_regs *regs); + +#define PERF_EVENT_INDEX_OFFSET 1 + +/* + * Only override the default definitions in include/linux/perf_event.h + * if we have hardware PMU support. + */ +#ifdef CONFIG_PPC_PERF_CTRS +#define perf_misc_flags(regs) perf_misc_flags(regs) +#endif + +/* + * The power_pmu.get_constraint function returns a 32/64-bit value and + * a 32/64-bit mask that express the constraints between this event_id and + * other events. + * + * The value and mask are divided up into (non-overlapping) bitfields + * of three different types: + * + * Select field: this expresses the constraint that some set of bits + * in MMCR* needs to be set to a specific value for this event_id. For a + * select field, the mask contains 1s in every bit of the field, and + * the value contains a unique value for each possible setting of the + * MMCR* bits. The constraint checking code will ensure that two events + * that set the same field in their masks have the same value in their + * value dwords. + * + * Add field: this expresses the constraint that there can be at most + * N events in a particular class. A field of k bits can be used for + * N <= 2^(k-1) - 1. The mask has the most significant bit of the field + * set (and the other bits 0), and the value has only the least significant + * bit of the field set. In addition, the 'add_fields' and 'test_adder' + * in the struct power_pmu for this processor come into play. The + * add_fields value contains 1 in the LSB of the field, and the + * test_adder contains 2^(k-1) - 1 - N in the field. + * + * NAND field: this expresses the constraint that you may not have events + * in all of a set of classes. (For example, on PPC970, you can't select + * events from the FPU, ISU and IDU simultaneously, although any two are + * possible.) For N classes, the field is N+1 bits wide, and each class + * is assigned one bit from the least-significant N bits. The mask has + * only the most-significant bit set, and the value has only the bit + * for the event_id's class set. The test_adder has the least significant + * bit set in the field. + * + * If an event_id is not subject to the constraint expressed by a particular + * field, then it will have 0 in both the mask and value for that field. + */ diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h index b4510812656..9e2d84c06b7 100644 --- a/arch/powerpc/include/asm/ptrace.h +++ b/arch/powerpc/include/asm/ptrace.h @@ -137,15 +137,8 @@ do { \ } while (0) #endif /* __powerpc64__ */ -/* - * These are defined as per linux/ptrace.h, which see. - */ #define arch_has_single_step() (1) #define arch_has_block_step() (!cpu_has_feature(CPU_FTR_601)) -extern void user_enable_single_step(struct task_struct *); -extern void user_enable_block_step(struct task_struct *); -extern void user_disable_single_step(struct task_struct *); - #define ARCH_HAS_USER_SINGLE_STEP_INFO #endif /* __ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index bc8dd53f718..5572e86223f 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -426,6 +426,10 @@ #define SRR1_WAKEMT 0x00280000 /* mtctrl */ #define SRR1_WAKEDEC 0x00180000 /* Decrementer interrupt */ #define SRR1_WAKETHERM 0x00100000 /* Thermal management interrupt */ +#define SRR1_PROGFPE 0x00100000 /* Floating Point Enabled */ +#define SRR1_PROGPRIV 0x00040000 /* Privileged instruction */ +#define SRR1_PROGTRAP 0x00020000 /* Trap */ +#define SRR1_PROGADDR 0x00010000 /* SRR0 contains subsequent addr */ #define SPRN_HSRR0 0x13A /* Save/Restore Register 0 */ #define SPRN_HSRR1 0x13B /* Save/Restore Register 1 */ diff --git a/arch/powerpc/include/asm/reg_booke.h b/arch/powerpc/include/asm/reg_booke.h index 8808d307fe7..414d434a66d 100644 --- a/arch/powerpc/include/asm/reg_booke.h +++ b/arch/powerpc/include/asm/reg_booke.h @@ -421,8 +421,8 @@ /* Bit definitions related to the DBCR2. */ #define DBCR2_DAC1US 0xC0000000 /* Data Addr Cmp 1 Sup/User */ #define DBCR2_DAC1ER 0x30000000 /* Data Addr Cmp 1 Eff/Real */ -#define DBCR2_DAC2US 0x00000000 /* Data Addr Cmp 2 Sup/User */ -#define DBCR2_DAC2ER 0x00000000 /* Data Addr Cmp 2 Eff/Real */ +#define DBCR2_DAC2US 0x0C000000 /* Data Addr Cmp 2 Sup/User */ +#define DBCR2_DAC2ER 0x03000000 /* Data Addr Cmp 2 Eff/Real */ #define DBCR2_DAC12M 0x00800000 /* DAC 1-2 range enable */ #define DBCR2_DAC12MM 0x00400000 /* DAC 1-2 Mask mode*/ #define DBCR2_DAC12MX 0x00C00000 /* DAC 1-2 range eXclusive */ diff --git a/arch/powerpc/include/asm/reg_fsl_emb.h b/arch/powerpc/include/asm/reg_fsl_emb.h index 0de404dfee8..77bb71cfd99 100644 --- a/arch/powerpc/include/asm/reg_fsl_emb.h +++ b/arch/powerpc/include/asm/reg_fsl_emb.h @@ -31,7 +31,7 @@ #define PMLCA_FCM0 0x08000000 /* Freeze when PMM==0 */ #define PMLCA_CE 0x04000000 /* Condition Enable */ -#define PMLCA_EVENT_MASK 0x007f0000 /* Event field */ +#define PMLCA_EVENT_MASK 0x00ff0000 /* Event field */ #define PMLCA_EVENT_SHIFT 16 #define PMRN_PMLCB0 0x110 /* PM Local Control B0 */ diff --git a/arch/powerpc/include/asm/syscalls.h b/arch/powerpc/include/asm/syscalls.h index eb8eb400c66..4084e567d28 100644 --- a/arch/powerpc/include/asm/syscalls.h +++ b/arch/powerpc/include/asm/syscalls.h @@ -7,7 +7,6 @@ #include <linux/types.h> #include <asm/signal.h> -struct new_utsname; struct pt_regs; struct rtas_args; struct sigaction; @@ -35,12 +34,9 @@ asmlinkage long sys_pipe2(int __user *fildes, int flags); asmlinkage long sys_rt_sigaction(int sig, const struct sigaction __user *act, struct sigaction __user *oact, size_t sigsetsize); -asmlinkage int sys_ipc(uint call, int first, unsigned long second, - long third, void __user *ptr, long fifth); asmlinkage long ppc64_personality(unsigned long personality); asmlinkage int ppc_rtas(struct rtas_args __user *uargs); asmlinkage time_t sys64_time(time_t __user * tloc); -asmlinkage long ppc_newuname(struct new_utsname __user * name); asmlinkage long sys_rt_sigsuspend(sigset_t __user *unewset, size_t sigsetsize); diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h index 07d2d19ab5e..a5ee345b6a5 100644 --- a/arch/powerpc/include/asm/systbl.h +++ b/arch/powerpc/include/asm/systbl.h @@ -125,7 +125,7 @@ SYSCALL_SPU(fsync) SYS32ONLY(sigreturn) PPC_SYS(clone) COMPAT_SYS_SPU(setdomainname) -PPC_SYS_SPU(newuname) +SYSCALL_SPU(newuname) SYSCALL(ni_syscall) COMPAT_SYS_SPU(adjtimex) SYSCALL_SPU(mprotect) diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h index f6ca7617676..f0a10266e7f 100644 --- a/arch/powerpc/include/asm/unistd.h +++ b/arch/powerpc/include/asm/unistd.h @@ -364,6 +364,7 @@ #define __ARCH_WANT_STAT64 #define __ARCH_WANT_SYS_ALARM #define __ARCH_WANT_SYS_GETHOSTNAME +#define __ARCH_WANT_SYS_IPC #define __ARCH_WANT_SYS_PAUSE #define __ARCH_WANT_SYS_SGETMASK #define __ARCH_WANT_SYS_SIGNAL @@ -376,6 +377,7 @@ #define __ARCH_WANT_SYS_LLSEEK #define __ARCH_WANT_SYS_NICE #define __ARCH_WANT_SYS_OLD_GETRLIMIT +#define __ARCH_WANT_SYS_OLD_UNAME #define __ARCH_WANT_SYS_OLDUMOUNT #define __ARCH_WANT_SYS_SIGPENDING #define __ARCH_WANT_SYS_SIGPROCMASK diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index c002b041021..877326320e7 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -98,11 +98,16 @@ obj64-$(CONFIG_AUDIT) += compat_audit.o obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o -obj-$(CONFIG_PPC_PERF_CTRS) += perf_event.o perf_callchain.o +obj-$(CONFIG_PERF_EVENTS) += perf_callchain.o + +obj-$(CONFIG_PPC_PERF_CTRS) += perf_event.o obj64-$(CONFIG_PPC_PERF_CTRS) += power4-pmu.o ppc970-pmu.o power5-pmu.o \ power5+-pmu.o power6-pmu.o power7-pmu.o obj32-$(CONFIG_PPC_PERF_CTRS) += mpc7450-pmu.o +obj-$(CONFIG_FSL_EMB_PERF_EVENT) += perf_event_fsl_emb.o +obj-$(CONFIG_FSL_EMB_PERF_EVENT_E500) += e500-pmu.o + obj-$(CONFIG_8XX_MINIMAL_FPEMU) += softemu8xx.o ifneq ($(CONFIG_PPC_INDIRECT_IO),y) diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index a6c2b63227b..957ceb7059c 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -194,6 +194,30 @@ int main(void) DEFINE(PACA_KVM_IN_GUEST, offsetof(struct paca_struct, kvm_in_guest)); DEFINE(PACA_KVM_SLB, offsetof(struct paca_struct, kvm_slb)); DEFINE(PACA_KVM_SLB_MAX, offsetof(struct paca_struct, kvm_slb_max)); + DEFINE(PACA_KVM_CR, offsetof(struct paca_struct, shadow_vcpu.cr)); + DEFINE(PACA_KVM_XER, offsetof(struct paca_struct, shadow_vcpu.xer)); + DEFINE(PACA_KVM_R0, offsetof(struct paca_struct, shadow_vcpu.gpr[0])); + DEFINE(PACA_KVM_R1, offsetof(struct paca_struct, shadow_vcpu.gpr[1])); + DEFINE(PACA_KVM_R2, offsetof(struct paca_struct, shadow_vcpu.gpr[2])); + DEFINE(PACA_KVM_R3, offsetof(struct paca_struct, shadow_vcpu.gpr[3])); + DEFINE(PACA_KVM_R4, offsetof(struct paca_struct, shadow_vcpu.gpr[4])); + DEFINE(PACA_KVM_R5, offsetof(struct paca_struct, shadow_vcpu.gpr[5])); + DEFINE(PACA_KVM_R6, offsetof(struct paca_struct, shadow_vcpu.gpr[6])); + DEFINE(PACA_KVM_R7, offsetof(struct paca_struct, shadow_vcpu.gpr[7])); + DEFINE(PACA_KVM_R8, offsetof(struct paca_struct, shadow_vcpu.gpr[8])); + DEFINE(PACA_KVM_R9, offsetof(struct paca_struct, shadow_vcpu.gpr[9])); + DEFINE(PACA_KVM_R10, offsetof(struct paca_struct, shadow_vcpu.gpr[10])); + DEFINE(PACA_KVM_R11, offsetof(struct paca_struct, shadow_vcpu.gpr[11])); + DEFINE(PACA_KVM_R12, offsetof(struct paca_struct, shadow_vcpu.gpr[12])); + DEFINE(PACA_KVM_R13, offsetof(struct paca_struct, shadow_vcpu.gpr[13])); + DEFINE(PACA_KVM_HOST_R1, offsetof(struct paca_struct, shadow_vcpu.host_r1)); + DEFINE(PACA_KVM_HOST_R2, offsetof(struct paca_struct, shadow_vcpu.host_r2)); + DEFINE(PACA_KVM_VMHANDLER, offsetof(struct paca_struct, + shadow_vcpu.vmhandler)); + DEFINE(PACA_KVM_SCRATCH0, offsetof(struct paca_struct, + shadow_vcpu.scratch0)); + DEFINE(PACA_KVM_SCRATCH1, offsetof(struct paca_struct, + shadow_vcpu.scratch1)); #endif #endif /* CONFIG_PPC64 */ @@ -389,8 +413,6 @@ int main(void) DEFINE(VCPU_HOST_PID, offsetof(struct kvm_vcpu, arch.host_pid)); DEFINE(VCPU_GPRS, offsetof(struct kvm_vcpu, arch.gpr)); DEFINE(VCPU_LR, offsetof(struct kvm_vcpu, arch.lr)); - DEFINE(VCPU_CR, offsetof(struct kvm_vcpu, arch.cr)); - DEFINE(VCPU_XER, offsetof(struct kvm_vcpu, arch.xer)); DEFINE(VCPU_CTR, offsetof(struct kvm_vcpu, arch.ctr)); DEFINE(VCPU_PC, offsetof(struct kvm_vcpu, arch.pc)); DEFINE(VCPU_MSR, offsetof(struct kvm_vcpu, arch.msr)); @@ -411,11 +433,16 @@ int main(void) DEFINE(VCPU_HOST_R2, offsetof(struct kvm_vcpu, arch.host_r2)); DEFINE(VCPU_HOST_MSR, offsetof(struct kvm_vcpu, arch.host_msr)); DEFINE(VCPU_SHADOW_MSR, offsetof(struct kvm_vcpu, arch.shadow_msr)); + DEFINE(VCPU_SHADOW_SRR1, offsetof(struct kvm_vcpu, arch.shadow_srr1)); DEFINE(VCPU_TRAMPOLINE_LOWMEM, offsetof(struct kvm_vcpu, arch.trampoline_lowmem)); DEFINE(VCPU_TRAMPOLINE_ENTER, offsetof(struct kvm_vcpu, arch.trampoline_enter)); DEFINE(VCPU_HIGHMEM_HANDLER, offsetof(struct kvm_vcpu, arch.highmem_handler)); + DEFINE(VCPU_RMCALL, offsetof(struct kvm_vcpu, arch.rmcall)); DEFINE(VCPU_HFLAGS, offsetof(struct kvm_vcpu, arch.hflags)); -#endif +#else + DEFINE(VCPU_CR, offsetof(struct kvm_vcpu, arch.cr)); + DEFINE(VCPU_XER, offsetof(struct kvm_vcpu, arch.xer)); +#endif /* CONFIG_PPC64 */ #endif #ifdef CONFIG_44x DEFINE(PGD_T_LOG2, PGD_T_LOG2); diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c index bb37b1d19a5..01fe9ce2837 100644 --- a/arch/powerpc/kernel/cacheinfo.c +++ b/arch/powerpc/kernel/cacheinfo.c @@ -642,7 +642,7 @@ static struct kobj_attribute *cache_index_opt_attrs[] = { &cache_assoc_attr, }; -static struct sysfs_ops cache_index_ops = { +static const struct sysfs_ops cache_index_ops = { .show = cache_index_show, }; diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 2fc82bac3bb..8af4949434b 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -1808,7 +1808,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .icache_bsize = 64, .dcache_bsize = 64, .num_pmcs = 4, - .oprofile_cpu_type = "ppc/e500", /* xxx - galak, e500mc? */ + .oprofile_cpu_type = "ppc/e500mc", .oprofile_type = PPC_OPROFILE_FSL_EMB, .cpu_setup = __setup_cpu_e500mc, .machine_check = machine_check_e500, diff --git a/arch/powerpc/kernel/e500-pmu.c b/arch/powerpc/kernel/e500-pmu.c new file mode 100644 index 00000000000..7c07de0d894 --- /dev/null +++ b/arch/powerpc/kernel/e500-pmu.c @@ -0,0 +1,129 @@ +/* + * Performance counter support for e500 family processors. + * + * Copyright 2008-2009 Paul Mackerras, IBM Corporation. + * Copyright 2010 Freescale Semiconductor, Inc. + * + * 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/string.h> +#include <linux/perf_event.h> +#include <asm/reg.h> +#include <asm/cputable.h> + +/* + * Map of generic hardware event types to hardware events + * Zero if unsupported + */ +static int e500_generic_events[] = { + [PERF_COUNT_HW_CPU_CYCLES] = 1, + [PERF_COUNT_HW_INSTRUCTIONS] = 2, + [PERF_COUNT_HW_CACHE_MISSES] = 41, /* Data L1 cache reloads */ + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 12, + [PERF_COUNT_HW_BRANCH_MISSES] = 15, +}; + +#define C(x) PERF_COUNT_HW_CACHE_##x + +/* + * Table of generalized cache-related events. + * 0 means not supported, -1 means nonsensical, other values + * are event codes. + */ +static int e500_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { + /* + * D-cache misses are not split into read/write/prefetch; + * use raw event 41. + */ + [C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 27, 0 }, + [C(OP_WRITE)] = { 28, 0 }, + [C(OP_PREFETCH)] = { 29, 0 }, + }, + [C(L1I)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 2, 60 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { 0, 0 }, + }, + /* + * Assuming LL means L2, it's not a good match for this model. + * It allocates only on L1 castout or explicit prefetch, and + * does not have separate read/write events (but it does have + * separate instruction/data events). + */ + [C(LL)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0 }, + [C(OP_WRITE)] = { 0, 0 }, + [C(OP_PREFETCH)] = { 0, 0 }, + }, + /* + * There are data/instruction MMU misses, but that's a miss on + * the chip's internal level-one TLB which is probably not + * what the user wants. Instead, unified level-two TLB misses + * are reported here. + */ + [C(DTLB)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 26, 66 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, + [C(BPU)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 12, 15 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, +}; + +static int num_events = 128; + +/* Upper half of event id is PMLCb, for threshold events */ +static u64 e500_xlate_event(u64 event_id) +{ + u32 event_low = (u32)event_id; + u64 ret; + + if (event_low >= num_events) + return 0; + + ret = FSL_EMB_EVENT_VALID; + + if (event_low >= 76 && event_low <= 81) { + ret |= FSL_EMB_EVENT_RESTRICTED; + ret |= event_id & + (FSL_EMB_EVENT_THRESHMUL | FSL_EMB_EVENT_THRESH); + } else if (event_id & + (FSL_EMB_EVENT_THRESHMUL | FSL_EMB_EVENT_THRESH)) { + /* Threshold requested on non-threshold event */ + return 0; + } + + return ret; +} + +static struct fsl_emb_pmu e500_pmu = { + .name = "e500 family", + .n_counter = 4, + .n_restricted = 2, + .xlate_event = e500_xlate_event, + .n_generic = ARRAY_SIZE(e500_generic_events), + .generic_events = e500_generic_events, + .cache_events = &e500_cache_events, +}; + +static int init_e500_pmu(void) +{ + if (!cur_cpu_spec->oprofile_cpu_type) + return -ENODEV; + + if (!strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc/e500mc")) + num_events = 256; + else if (strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc/e500")) + return -ENODEV; + + return register_fsl_emb_pmu(&e500_pmu); +} + +arch_initcall(init_e500_pmu); diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 92580748802..bed9a29ee38 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -219,7 +219,8 @@ generic_secondary_common_init: * physical cpu id in r24, we need to search the pacas to find * which logical id maps to our physical one. */ - LOAD_REG_ADDR(r13, paca) /* Get base vaddr of paca array */ + LOAD_REG_ADDR(r13, paca) /* Load paca pointer */ + ld r13,0(r13) /* Get base vaddr of paca array */ li r5,0 /* logical cpu id */ 1: lhz r6,PACAHWCPUID(r13) /* Load HW procid from paca */ cmpw r6,r24 /* Compare to our id */ @@ -536,7 +537,8 @@ _GLOBAL(pmac_secondary_start) mtmsrd r3 /* RI on */ /* Set up a paca value for this processor. */ - LOAD_REG_ADDR(r4,paca) /* Get base vaddr of paca array */ + LOAD_REG_ADDR(r4,paca) /* Load paca pointer */ + ld r4,0(r4) /* Get base vaddr of paca array */ mulli r13,r24,PACA_SIZE /* Calculate vaddr of right paca */ add r13,r13,r4 /* for this processor. */ mtspr SPRN_SPRG_PACA,r13 /* Save vaddr of paca in an SPRG*/ @@ -615,6 +617,17 @@ _GLOBAL(start_secondary_prolog) std r3,0(r1) /* Zero the stack frame pointer */ bl .start_secondary b . +/* + * Reset stack pointer and call start_secondary + * to continue with online operation when woken up + * from cede in cpu offline. + */ +_GLOBAL(start_secondary_resume) + ld r1,PACAKSAVE(r13) /* Reload kernel stack pointer */ + li r3,0 + std r3,0(r1) /* Zero the stack frame pointer */ + bl .start_secondary + b . #endif /* diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c index 9ddfaef1a18..035ada5443e 100644 --- a/arch/powerpc/kernel/legacy_serial.c +++ b/arch/powerpc/kernel/legacy_serial.c @@ -469,7 +469,7 @@ static int __init serial_dev_init(void) return -ENODEV; /* - * Before we register the platfrom serial devices, we need + * Before we register the platform serial devices, we need * to fixup their interrupts and their IO ports. */ DBG("Fixing serial ports interrupts and IO ports ...\n"); diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index d16b1ea55d4..0c40c6f476f 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -9,11 +9,15 @@ #include <linux/threads.h> #include <linux/module.h> +#include <linux/lmb.h> +#include <asm/firmware.h> #include <asm/lppaca.h> #include <asm/paca.h> #include <asm/sections.h> #include <asm/pgtable.h> +#include <asm/iseries/lpar_map.h> +#include <asm/iseries/hv_types.h> /* This symbol is provided by the linker - let it fill in the paca * field correctly */ @@ -70,37 +74,82 @@ struct slb_shadow slb_shadow[] __cacheline_aligned = { * processors. The processor VPD array needs one entry per physical * processor (not thread). */ -struct paca_struct paca[NR_CPUS]; +struct paca_struct *paca; EXPORT_SYMBOL(paca); -void __init initialise_pacas(void) -{ - int cpu; +struct paca_struct boot_paca; - /* The TOC register (GPR2) points 32kB into the TOC, so that 64kB - * of the TOC can be addressed using a single machine instruction. - */ +void __init initialise_paca(struct paca_struct *new_paca, int cpu) +{ + /* The TOC register (GPR2) points 32kB into the TOC, so that 64kB + * of the TOC can be addressed using a single machine instruction. + */ unsigned long kernel_toc = (unsigned long)(&__toc_start) + 0x8000UL; - /* Can't use for_each_*_cpu, as they aren't functional yet */ - for (cpu = 0; cpu < NR_CPUS; cpu++) { - struct paca_struct *new_paca = &paca[cpu]; - #ifdef CONFIG_PPC_BOOK3S - new_paca->lppaca_ptr = &lppaca[cpu]; + new_paca->lppaca_ptr = &lppaca[cpu]; #else - new_paca->kernel_pgd = swapper_pg_dir; + new_paca->kernel_pgd = swapper_pg_dir; #endif - new_paca->lock_token = 0x8000; - new_paca->paca_index = cpu; - new_paca->kernel_toc = kernel_toc; - new_paca->kernelbase = (unsigned long) _stext; - new_paca->kernel_msr = MSR_KERNEL; - new_paca->hw_cpu_id = 0xffff; - new_paca->__current = &init_task; + new_paca->lock_token = 0x8000; + new_paca->paca_index = cpu; + new_paca->kernel_toc = kernel_toc; + new_paca->kernelbase = (unsigned long) _stext; + new_paca->kernel_msr = MSR_KERNEL; + new_paca->hw_cpu_id = 0xffff; + new_paca->__current = &init_task; #ifdef CONFIG_PPC_STD_MMU_64 - new_paca->slb_shadow_ptr = &slb_shadow[cpu]; + new_paca->slb_shadow_ptr = &slb_shadow[cpu]; #endif /* CONFIG_PPC_STD_MMU_64 */ +} + +static int __initdata paca_size; + +void __init allocate_pacas(void) +{ + int nr_cpus, cpu, limit; + + /* + * We can't take SLB misses on the paca, and we want to access them + * in real mode, so allocate them within the RMA and also within + * the first segment. On iSeries they must be within the area mapped + * by the HV, which is HvPagesToMap * HVPAGESIZE bytes. + */ + limit = min(0x10000000ULL, lmb.rmo_size); + if (firmware_has_feature(FW_FEATURE_ISERIES)) + limit = min(limit, HvPagesToMap * HVPAGESIZE); + + nr_cpus = NR_CPUS; + /* On iSeries we know we can never have more than 64 cpus */ + if (firmware_has_feature(FW_FEATURE_ISERIES)) + nr_cpus = min(64, nr_cpus); + + paca_size = PAGE_ALIGN(sizeof(struct paca_struct) * nr_cpus); + + paca = __va(lmb_alloc_base(paca_size, PAGE_SIZE, limit)); + memset(paca, 0, paca_size); + + printk(KERN_DEBUG "Allocated %u bytes for %d pacas at %p\n", + paca_size, nr_cpus, paca); + + /* Can't use for_each_*_cpu, as they aren't functional yet */ + for (cpu = 0; cpu < nr_cpus; cpu++) + initialise_paca(&paca[cpu], cpu); +} + +void __init free_unused_pacas(void) +{ + int new_size; + + new_size = PAGE_ALIGN(sizeof(struct paca_struct) * num_possible_cpus()); + + if (new_size >= paca_size) + return; + + lmb_free(__pa(paca) + new_size, paca_size - new_size); + + printk(KERN_DEBUG "Freed %u bytes for unused pacas\n", + paca_size - new_size); - } + paca_size = new_size; } diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 2597f9545d8..f3c42ce516e 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -63,21 +63,6 @@ struct dma_map_ops *get_pci_dma_ops(void) } EXPORT_SYMBOL(get_pci_dma_ops); -int pci_set_dma_mask(struct pci_dev *dev, u64 mask) -{ - return dma_set_mask(&dev->dev, mask); -} - -int pci_set_consistent_dma_mask(struct pci_dev *dev, u64 mask) -{ - int rc; - - rc = dma_set_mask(&dev->dev, mask); - dev->dev.coherent_dma_mask = dev->dma_mask; - - return rc; -} - struct pci_controller *pcibios_alloc_controller(struct device_node *dev) { struct pci_controller *phb; diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c index b6cf8f1f4d3..5120bd44f69 100644 --- a/arch/powerpc/kernel/perf_event.c +++ b/arch/powerpc/kernel/perf_event.c @@ -1164,10 +1164,10 @@ static void record_and_restart(struct perf_event *event, unsigned long val, * Finally record data if requested. */ if (record) { - struct perf_sample_data data = { - .addr = ~0ULL, - .period = event->hw.last_period, - }; + struct perf_sample_data data; + + perf_sample_data_init(&data, ~0ULL); + data.period = event->hw.last_period; if (event->attr.sample_type & PERF_SAMPLE_ADDR) perf_get_data_addr(regs, &data.addr); diff --git a/arch/powerpc/kernel/perf_event_fsl_emb.c b/arch/powerpc/kernel/perf_event_fsl_emb.c new file mode 100644 index 00000000000..369872f6cf7 --- /dev/null +++ b/arch/powerpc/kernel/perf_event_fsl_emb.c @@ -0,0 +1,654 @@ +/* + * Performance event support - Freescale Embedded Performance Monitor + * + * Copyright 2008-2009 Paul Mackerras, IBM Corporation. + * Copyright 2010 Freescale Semiconductor, Inc. + * + * 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/kernel.h> +#include <linux/sched.h> +#include <linux/perf_event.h> +#include <linux/percpu.h> +#include <linux/hardirq.h> +#include <asm/reg_fsl_emb.h> +#include <asm/pmc.h> +#include <asm/machdep.h> +#include <asm/firmware.h> +#include <asm/ptrace.h> + +struct cpu_hw_events { + int n_events; + int disabled; + u8 pmcs_enabled; + struct perf_event *event[MAX_HWEVENTS]; +}; +static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events); + +static struct fsl_emb_pmu *ppmu; + +/* Number of perf_events counting hardware events */ +static atomic_t num_events; +/* Used to avoid races in calling reserve/release_pmc_hardware */ +static DEFINE_MUTEX(pmc_reserve_mutex); + +/* + * If interrupts were soft-disabled when a PMU interrupt occurs, treat + * it as an NMI. + */ +static inline int perf_intr_is_nmi(struct pt_regs *regs) +{ +#ifdef __powerpc64__ + return !regs->softe; +#else + return 0; +#endif +} + +static void perf_event_interrupt(struct pt_regs *regs); + +/* + * Read one performance monitor counter (PMC). + */ +static unsigned long read_pmc(int idx) +{ + unsigned long val; + + switch (idx) { + case 0: + val = mfpmr(PMRN_PMC0); + break; + case 1: + val = mfpmr(PMRN_PMC1); + break; + case 2: + val = mfpmr(PMRN_PMC2); + break; + case 3: + val = mfpmr(PMRN_PMC3); + break; + default: + printk(KERN_ERR "oops trying to read PMC%d\n", idx); + val = 0; + } + return val; +} + +/* + * Write one PMC. + */ +static void write_pmc(int idx, unsigned long val) +{ + switch (idx) { + case 0: + mtpmr(PMRN_PMC0, val); + break; + case 1: + mtpmr(PMRN_PMC1, val); + break; + case 2: + mtpmr(PMRN_PMC2, val); + break; + case 3: + mtpmr(PMRN_PMC3, val); + break; + default: + printk(KERN_ERR "oops trying to write PMC%d\n", idx); + } + + isync(); +} + +/* + * Write one local control A register + */ +static void write_pmlca(int idx, unsigned long val) +{ + switch (idx) { + case 0: + mtpmr(PMRN_PMLCA0, val); + break; + case 1: + mtpmr(PMRN_PMLCA1, val); + break; + case 2: + mtpmr(PMRN_PMLCA2, val); + break; + case 3: + mtpmr(PMRN_PMLCA3, val); + break; + default: + printk(KERN_ERR "oops trying to write PMLCA%d\n", idx); + } + + isync(); +} + +/* + * Write one local control B register + */ +static void write_pmlcb(int idx, unsigned long val) +{ + switch (idx) { + case 0: + mtpmr(PMRN_PMLCB0, val); + break; + case 1: + mtpmr(PMRN_PMLCB1, val); + break; + case 2: + mtpmr(PMRN_PMLCB2, val); + break; + case 3: + mtpmr(PMRN_PMLCB3, val); + break; + default: + printk(KERN_ERR "oops trying to write PMLCB%d\n", idx); + } + + isync(); +} + +static void fsl_emb_pmu_read(struct perf_event *event) +{ + s64 val, delta, prev; + + /* + * Performance monitor interrupts come even when interrupts + * are soft-disabled, as long as interrupts are hard-enabled. + * Therefore we treat them like NMIs. + */ + do { + prev = atomic64_read(&event->hw.prev_count); + barrier(); + val = read_pmc(event->hw.idx); + } while (atomic64_cmpxchg(&event->hw.prev_count, prev, val) != prev); + + /* The counters are only 32 bits wide */ + delta = (val - prev) & 0xfffffffful; + atomic64_add(delta, &event->count); + atomic64_sub(delta, &event->hw.period_left); +} + +/* + * Disable all events to prevent PMU interrupts and to allow + * events to be added or removed. + */ +void hw_perf_disable(void) +{ + struct cpu_hw_events *cpuhw; + unsigned long flags; + + local_irq_save(flags); + cpuhw = &__get_cpu_var(cpu_hw_events); + + if (!cpuhw->disabled) { + cpuhw->disabled = 1; + + /* + * Check if we ever enabled the PMU on this cpu. + */ + if (!cpuhw->pmcs_enabled) { + ppc_enable_pmcs(); + cpuhw->pmcs_enabled = 1; + } + + if (atomic_read(&num_events)) { + /* + * Set the 'freeze all counters' bit, and disable + * interrupts. The barrier is to make sure the + * mtpmr has been executed and the PMU has frozen + * the events before we return. + */ + + mtpmr(PMRN_PMGC0, PMGC0_FAC); + isync(); + } + } + local_irq_restore(flags); +} + +/* + * Re-enable all events if disable == 0. + * If we were previously disabled and events were added, then + * put the new config on the PMU. + */ +void hw_perf_enable(void) +{ + struct cpu_hw_events *cpuhw; + unsigned long flags; + + local_irq_save(flags); + cpuhw = &__get_cpu_var(cpu_hw_events); + if (!cpuhw->disabled) + goto out; + + cpuhw->disabled = 0; + ppc_set_pmu_inuse(cpuhw->n_events != 0); + + if (cpuhw->n_events > 0) { + mtpmr(PMRN_PMGC0, PMGC0_PMIE | PMGC0_FCECE); + isync(); + } + + out: + local_irq_restore(flags); +} + +static int collect_events(struct perf_event *group, int max_count, + struct perf_event *ctrs[]) +{ + int n = 0; + struct perf_event *event; + + if (!is_software_event(group)) { + if (n >= max_count) + return -1; + ctrs[n] = group; + n++; + } + list_for_each_entry(event, &group->sibling_list, group_entry) { + if (!is_software_event(event) && + event->state != PERF_EVENT_STATE_OFF) { + if (n >= max_count) + return -1; + ctrs[n] = event; + n++; + } + } + return n; +} + +/* perf must be disabled, context locked on entry */ +static int fsl_emb_pmu_enable(struct perf_event *event) +{ + struct cpu_hw_events *cpuhw; + int ret = -EAGAIN; + int num_counters = ppmu->n_counter; + u64 val; + int i; + + cpuhw = &get_cpu_var(cpu_hw_events); + + if (event->hw.config & FSL_EMB_EVENT_RESTRICTED) + num_counters = ppmu->n_restricted; + + /* + * Allocate counters from top-down, so that restricted-capable + * counters are kept free as long as possible. + */ + for (i = num_counters - 1; i >= 0; i--) { + if (cpuhw->event[i]) + continue; + + break; + } + + if (i < 0) + goto out; + + event->hw.idx = i; + cpuhw->event[i] = event; + ++cpuhw->n_events; + + val = 0; + if (event->hw.sample_period) { + s64 left = atomic64_read(&event->hw.period_left); + if (left < 0x80000000L) + val = 0x80000000L - left; + } + atomic64_set(&event->hw.prev_count, val); + write_pmc(i, val); + perf_event_update_userpage(event); + + write_pmlcb(i, event->hw.config >> 32); + write_pmlca(i, event->hw.config_base); + + ret = 0; + out: + put_cpu_var(cpu_hw_events); + return ret; +} + +/* perf must be disabled, context locked on entry */ +static void fsl_emb_pmu_disable(struct perf_event *event) +{ + struct cpu_hw_events *cpuhw; + int i = event->hw.idx; + + if (i < 0) + goto out; + + fsl_emb_pmu_read(event); + + cpuhw = &get_cpu_var(cpu_hw_events); + + WARN_ON(event != cpuhw->event[event->hw.idx]); + + write_pmlca(i, 0); + write_pmlcb(i, 0); + write_pmc(i, 0); + + cpuhw->event[i] = NULL; + event->hw.idx = -1; + + /* + * TODO: if at least one restricted event exists, and we + * just freed up a non-restricted-capable counter, and + * there is a restricted-capable counter occupied by + * a non-restricted event, migrate that event to the + * vacated counter. + */ + + cpuhw->n_events--; + + out: + put_cpu_var(cpu_hw_events); +} + +/* + * Re-enable interrupts on a event after they were throttled + * because they were coming too fast. + * + * Context is locked on entry, but perf is not disabled. + */ +static void fsl_emb_pmu_unthrottle(struct perf_event *event) +{ + s64 val, left; + unsigned long flags; + + if (event->hw.idx < 0 || !event->hw.sample_period) + return; + local_irq_save(flags); + perf_disable(); + fsl_emb_pmu_read(event); + left = event->hw.sample_period; + event->hw.last_period = left; + val = 0; + if (left < 0x80000000L) + val = 0x80000000L - left; + write_pmc(event->hw.idx, val); + atomic64_set(&event->hw.prev_count, val); + atomic64_set(&event->hw.period_left, left); + perf_event_update_userpage(event); + perf_enable(); + local_irq_restore(flags); +} + +static struct pmu fsl_emb_pmu = { + .enable = fsl_emb_pmu_enable, + .disable = fsl_emb_pmu_disable, + .read = fsl_emb_pmu_read, + .unthrottle = fsl_emb_pmu_unthrottle, +}; + +/* + * Release the PMU if this is the last perf_event. + */ +static void hw_perf_event_destroy(struct perf_event *event) +{ + if (!atomic_add_unless(&num_events, -1, 1)) { + mutex_lock(&pmc_reserve_mutex); + if (atomic_dec_return(&num_events) == 0) + release_pmc_hardware(); + mutex_unlock(&pmc_reserve_mutex); + } +} + +/* + * Translate a generic cache event_id config to a raw event_id code. + */ +static int hw_perf_cache_event(u64 config, u64 *eventp) +{ + unsigned long type, op, result; + int ev; + + if (!ppmu->cache_events) + return -EINVAL; + + /* unpack config */ + type = config & 0xff; + op = (config >> 8) & 0xff; + result = (config >> 16) & 0xff; + + if (type >= PERF_COUNT_HW_CACHE_MAX || + op >= PERF_COUNT_HW_CACHE_OP_MAX || + result >= PERF_COUNT_HW_CACHE_RESULT_MAX) + return -EINVAL; + + ev = (*ppmu->cache_events)[type][op][result]; + if (ev == 0) + return -EOPNOTSUPP; + if (ev == -1) + return -EINVAL; + *eventp = ev; + return 0; +} + +const struct pmu *hw_perf_event_init(struct perf_event *event) +{ + u64 ev; + struct perf_event *events[MAX_HWEVENTS]; + int n; + int err; + int num_restricted; + int i; + + switch (event->attr.type) { + case PERF_TYPE_HARDWARE: + ev = event->attr.config; + if (ev >= ppmu->n_generic || ppmu->generic_events[ev] == 0) + return ERR_PTR(-EOPNOTSUPP); + ev = ppmu->generic_events[ev]; + break; + + case PERF_TYPE_HW_CACHE: + err = hw_perf_cache_event(event->attr.config, &ev); + if (err) + return ERR_PTR(err); + break; + + case PERF_TYPE_RAW: + ev = event->attr.config; + break; + + default: + return ERR_PTR(-EINVAL); + } + + event->hw.config = ppmu->xlate_event(ev); + if (!(event->hw.config & FSL_EMB_EVENT_VALID)) + return ERR_PTR(-EINVAL); + + /* + * If this is in a group, check if it can go on with all the + * other hardware events in the group. We assume the event + * hasn't been linked into its leader's sibling list at this point. + */ + n = 0; + if (event->group_leader != event) { + n = collect_events(event->group_leader, + ppmu->n_counter - 1, events); + if (n < 0) + return ERR_PTR(-EINVAL); + } + + if (event->hw.config & FSL_EMB_EVENT_RESTRICTED) { + num_restricted = 0; + for (i = 0; i < n; i++) { + if (events[i]->hw.config & FSL_EMB_EVENT_RESTRICTED) + num_restricted++; + } + + if (num_restricted >= ppmu->n_restricted) + return ERR_PTR(-EINVAL); + } + + event->hw.idx = -1; + + event->hw.config_base = PMLCA_CE | PMLCA_FCM1 | + (u32)((ev << 16) & PMLCA_EVENT_MASK); + + if (event->attr.exclude_user) + event->hw.config_base |= PMLCA_FCU; + if (event->attr.exclude_kernel) + event->hw.config_base |= PMLCA_FCS; + if (event->attr.exclude_idle) + return ERR_PTR(-ENOTSUPP); + + event->hw.last_period = event->hw.sample_period; + atomic64_set(&event->hw.period_left, event->hw.last_period); + + /* + * See if we need to reserve the PMU. + * If no events are currently in use, then we have to take a + * mutex to ensure that we don't race with another task doing + * reserve_pmc_hardware or release_pmc_hardware. + */ + err = 0; + if (!atomic_inc_not_zero(&num_events)) { + mutex_lock(&pmc_reserve_mutex); + if (atomic_read(&num_events) == 0 && + reserve_pmc_hardware(perf_event_interrupt)) + err = -EBUSY; + else + atomic_inc(&num_events); + mutex_unlock(&pmc_reserve_mutex); + + mtpmr(PMRN_PMGC0, PMGC0_FAC); + isync(); + } + event->destroy = hw_perf_event_destroy; + + if (err) + return ERR_PTR(err); + return &fsl_emb_pmu; +} + +/* + * A counter has overflowed; update its count and record + * things if requested. Note that interrupts are hard-disabled + * here so there is no possibility of being interrupted. + */ +static void record_and_restart(struct perf_event *event, unsigned long val, + struct pt_regs *regs, int nmi) +{ + u64 period = event->hw.sample_period; + s64 prev, delta, left; + int record = 0; + + /* we don't have to worry about interrupts here */ + prev = atomic64_read(&event->hw.prev_count); + delta = (val - prev) & 0xfffffffful; + atomic64_add(delta, &event->count); + + /* + * See if the total period for this event has expired, + * and update for the next period. + */ + val = 0; + left = atomic64_read(&event->hw.period_left) - delta; + if (period) { + if (left <= 0) { + left += period; + if (left <= 0) + left = period; + record = 1; + } + if (left < 0x80000000LL) + val = 0x80000000LL - left; + } + + /* + * Finally record data if requested. + */ + if (record) { + struct perf_sample_data data = { + .period = event->hw.last_period, + }; + + if (perf_event_overflow(event, nmi, &data, regs)) { + /* + * Interrupts are coming too fast - throttle them + * by setting the event to 0, so it will be + * at least 2^30 cycles until the next interrupt + * (assuming each event counts at most 2 counts + * per cycle). + */ + val = 0; + left = ~0ULL >> 1; + } + } + + write_pmc(event->hw.idx, val); + atomic64_set(&event->hw.prev_count, val); + atomic64_set(&event->hw.period_left, left); + perf_event_update_userpage(event); +} + +static void perf_event_interrupt(struct pt_regs *regs) +{ + int i; + struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); + struct perf_event *event; + unsigned long val; + int found = 0; + int nmi; + + nmi = perf_intr_is_nmi(regs); + if (nmi) + nmi_enter(); + else + irq_enter(); + + for (i = 0; i < ppmu->n_counter; ++i) { + event = cpuhw->event[i]; + + val = read_pmc(i); + if ((int)val < 0) { + if (event) { + /* event has overflowed */ + found = 1; + record_and_restart(event, val, regs, nmi); + } else { + /* + * Disabled counter is negative, + * reset it just in case. + */ + write_pmc(i, 0); + } + } + } + + /* PMM will keep counters frozen until we return from the interrupt. */ + mtmsr(mfmsr() | MSR_PMM); + mtpmr(PMRN_PMGC0, PMGC0_PMIE | PMGC0_FCECE); + isync(); + + if (nmi) + nmi_exit(); + else + irq_exit(); +} + +void hw_perf_event_setup(int cpu) +{ + struct cpu_hw_events *cpuhw = &per_cpu(cpu_hw_events, cpu); + + memset(cpuhw, 0, sizeof(*cpuhw)); +} + +int register_fsl_emb_pmu(struct fsl_emb_pmu *pmu) +{ + if (ppmu) + return -EBUSY; /* something's already registered */ + + ppmu = pmu; + pr_info("%s performance monitor hardware support registered\n", + pmu->name); + + return 0; +} diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c index 425451453e9..ab3e392ac63 100644 --- a/arch/powerpc/kernel/ppc_ksyms.c +++ b/arch/powerpc/kernel/ppc_ksyms.c @@ -107,6 +107,7 @@ EXPORT_SYMBOL(giveup_altivec); #endif /* CONFIG_ALTIVEC */ #ifdef CONFIG_VSX EXPORT_SYMBOL(giveup_vsx); +EXPORT_SYMBOL_GPL(__giveup_vsx); #endif /* CONFIG_VSX */ #ifdef CONFIG_SPE EXPORT_SYMBOL(giveup_spe); diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 43238b2054b..05131d634e7 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -43,6 +43,7 @@ #include <asm/smp.h> #include <asm/system.h> #include <asm/mmu.h> +#include <asm/paca.h> #include <asm/pgtable.h> #include <asm/pci.h> #include <asm/iommu.h> @@ -721,6 +722,8 @@ void __init early_init_devtree(void *params) * FIXME .. and the initrd too? */ move_device_tree(); + allocate_pacas(); + DBG("Scanning CPUs ...\n"); /* Retreive CPU related informations from the flat tree diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index d9b05866615..ed2cfe17d25 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -940,7 +940,7 @@ static int del_instruction_bp(struct task_struct *child, int slot) { switch (slot) { case 1: - if (child->thread.iac1 == 0) + if ((child->thread.dbcr0 & DBCR0_IAC1) == 0) return -ENOENT; if (dbcr_iac_range(child) & DBCR_IAC12MODE) { @@ -952,7 +952,7 @@ static int del_instruction_bp(struct task_struct *child, int slot) child->thread.dbcr0 &= ~DBCR0_IAC1; break; case 2: - if (child->thread.iac2 == 0) + if ((child->thread.dbcr0 & DBCR0_IAC2) == 0) return -ENOENT; if (dbcr_iac_range(child) & DBCR_IAC12MODE) @@ -963,7 +963,7 @@ static int del_instruction_bp(struct task_struct *child, int slot) break; #if CONFIG_PPC_ADV_DEBUG_IACS > 2 case 3: - if (child->thread.iac3 == 0) + if ((child->thread.dbcr0 & DBCR0_IAC3) == 0) return -ENOENT; if (dbcr_iac_range(child) & DBCR_IAC34MODE) { @@ -975,7 +975,7 @@ static int del_instruction_bp(struct task_struct *child, int slot) child->thread.dbcr0 &= ~DBCR0_IAC3; break; case 4: - if (child->thread.iac4 == 0) + if ((child->thread.dbcr0 & DBCR0_IAC4) == 0) return -ENOENT; if (dbcr_iac_range(child) & DBCR_IAC34MODE) @@ -1054,7 +1054,7 @@ static int set_dac(struct task_struct *child, struct ppc_hw_breakpoint *bp_info) static int del_dac(struct task_struct *child, int slot) { if (slot == 1) { - if (child->thread.dac1 == 0) + if ((dbcr_dac(child) & (DBCR_DAC1R | DBCR_DAC1W)) == 0) return -ENOENT; child->thread.dac1 = 0; @@ -1070,7 +1070,7 @@ static int del_dac(struct task_struct *child, int slot) child->thread.dvc1 = 0; #endif } else if (slot == 2) { - if (child->thread.dac1 == 0) + if ((dbcr_dac(child) & (DBCR_DAC2R | DBCR_DAC2W)) == 0) return -ENOENT; #ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 03dd6a24819..48f0a008b20 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -36,6 +36,7 @@ #include <linux/lmb.h> #include <linux/of_platform.h> #include <asm/io.h> +#include <asm/paca.h> #include <asm/prom.h> #include <asm/processor.h> #include <asm/vdso_datapage.h> @@ -493,6 +494,8 @@ void __init smp_setup_cpu_maps(void) * here will have to be reworked */ cpu_init_thread_core_maps(nthreads); + + free_unused_pacas(); } #endif /* CONFIG_SMP */ diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 6568406b2a3..63547394048 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -144,9 +144,9 @@ early_param("smt-enabled", early_smt_enabled); #endif /* CONFIG_SMP */ /* Put the paca pointer into r13 and SPRG_PACA */ -void __init setup_paca(int cpu) +static void __init setup_paca(struct paca_struct *new_paca) { - local_paca = &paca[cpu]; + local_paca = new_paca; mtspr(SPRN_SPRG_PACA, local_paca); #ifdef CONFIG_PPC_BOOK3E mtspr(SPRN_SPRG_TLB_EXFRAME, local_paca->extlb); @@ -176,14 +176,12 @@ void __init early_setup(unsigned long dt_ptr) { /* -------- printk is _NOT_ safe to use here ! ------- */ - /* Fill in any unititialised pacas */ - initialise_pacas(); - /* Identify CPU type */ identify_cpu(0, mfspr(SPRN_PVR)); /* Assume we're on cpu 0 for now. Don't write to the paca yet! */ - setup_paca(0); + initialise_paca(&boot_paca, 0); + setup_paca(&boot_paca); /* Initialize lockdep early or else spinlocks will blow */ lockdep_init(); @@ -203,7 +201,7 @@ void __init early_setup(unsigned long dt_ptr) early_init_devtree(__va(dt_ptr)); /* Now we know the logical id of our boot cpu, setup the paca. */ - setup_paca(boot_cpuid); + setup_paca(&paca[boot_cpuid]); /* Fix up paca fields required for the boot cpu */ get_paca()->cpu_start = 1; diff --git a/arch/powerpc/kernel/syscalls.c b/arch/powerpc/kernel/syscalls.c index 3370e62e43d..f2496f2faec 100644 --- a/arch/powerpc/kernel/syscalls.c +++ b/arch/powerpc/kernel/syscalls.c @@ -42,100 +42,6 @@ #include <asm/time.h> #include <asm/unistd.h> -/* - * sys_ipc() is the de-multiplexer for the SysV IPC calls.. - * - * This is really horribly ugly. - */ -int sys_ipc(uint call, int first, unsigned long second, long third, - void __user *ptr, long fifth) -{ - int version, ret; - - version = call >> 16; /* hack for backward compatibility */ - call &= 0xffff; - - ret = -ENOSYS; - switch (call) { - case SEMOP: - ret = sys_semtimedop(first, (struct sembuf __user *)ptr, - (unsigned)second, NULL); - break; - case SEMTIMEDOP: - ret = sys_semtimedop(first, (struct sembuf __user *)ptr, - (unsigned)second, - (const struct timespec __user *) fifth); - break; - case SEMGET: - ret = sys_semget (first, (int)second, third); - break; - case SEMCTL: { - union semun fourth; - - ret = -EINVAL; - if (!ptr) - break; - if ((ret = get_user(fourth.__pad, (void __user * __user *)ptr))) - break; - ret = sys_semctl(first, (int)second, third, fourth); - break; - } - case MSGSND: - ret = sys_msgsnd(first, (struct msgbuf __user *)ptr, - (size_t)second, third); - break; - case MSGRCV: - switch (version) { - case 0: { - struct ipc_kludge tmp; - - ret = -EINVAL; - if (!ptr) - break; - if ((ret = copy_from_user(&tmp, - (struct ipc_kludge __user *) ptr, - sizeof (tmp)) ? -EFAULT : 0)) - break; - ret = sys_msgrcv(first, tmp.msgp, (size_t) second, - tmp.msgtyp, third); - break; - } - default: - ret = sys_msgrcv (first, (struct msgbuf __user *) ptr, - (size_t)second, fifth, third); - break; - } - break; - case MSGGET: - ret = sys_msgget((key_t)first, (int)second); - break; - case MSGCTL: - ret = sys_msgctl(first, (int)second, - (struct msqid_ds __user *)ptr); - break; - case SHMAT: { - ulong raddr; - ret = do_shmat(first, (char __user *)ptr, (int)second, &raddr); - if (ret) - break; - ret = put_user(raddr, (ulong __user *) third); - break; - } - case SHMDT: - ret = sys_shmdt((char __user *)ptr); - break; - case SHMGET: - ret = sys_shmget(first, (size_t)second, third); - break; - case SHMCTL: - ret = sys_shmctl(first, (int)second, - (struct shmid_ds __user *)ptr); - break; - } - - return ret; -} - static inline unsigned long do_mmap2(unsigned long addr, size_t len, unsigned long prot, unsigned long flags, unsigned long fd, unsigned long off, int shift) @@ -210,76 +116,6 @@ long ppc64_personality(unsigned long personality) } #endif -#ifdef CONFIG_PPC64 -#define OVERRIDE_MACHINE (personality(current->personality) == PER_LINUX32) -#else -#define OVERRIDE_MACHINE 0 -#endif - -static inline int override_machine(char __user *mach) -{ - if (OVERRIDE_MACHINE) { - /* change ppc64 to ppc */ - if (__put_user(0, mach+3) || __put_user(0, mach+4)) - return -EFAULT; - } - return 0; -} - -long ppc_newuname(struct new_utsname __user * name) -{ - int err = 0; - - down_read(&uts_sem); - if (copy_to_user(name, utsname(), sizeof(*name))) - err = -EFAULT; - up_read(&uts_sem); - if (!err) - err = override_machine(name->machine); - return err; -} - -int sys_uname(struct old_utsname __user *name) -{ - int err = 0; - - down_read(&uts_sem); - if (copy_to_user(name, utsname(), sizeof(*name))) - err = -EFAULT; - up_read(&uts_sem); - if (!err) - err = override_machine(name->machine); - return err; -} - -int sys_olduname(struct oldold_utsname __user *name) -{ - int error; - - if (!access_ok(VERIFY_WRITE, name, sizeof(struct oldold_utsname))) - return -EFAULT; - - down_read(&uts_sem); - error = __copy_to_user(&name->sysname, &utsname()->sysname, - __OLD_UTS_LEN); - error |= __put_user(0, name->sysname + __OLD_UTS_LEN); - error |= __copy_to_user(&name->nodename, &utsname()->nodename, - __OLD_UTS_LEN); - error |= __put_user(0, name->nodename + __OLD_UTS_LEN); - error |= __copy_to_user(&name->release, &utsname()->release, - __OLD_UTS_LEN); - error |= __put_user(0, name->release + __OLD_UTS_LEN); - error |= __copy_to_user(&name->version, &utsname()->version, - __OLD_UTS_LEN); - error |= __put_user(0, name->version + __OLD_UTS_LEN); - error |= __copy_to_user(&name->machine, &utsname()->machine, - __OLD_UTS_LEN); - error |= override_machine(name->machine); - up_read(&uts_sem); - - return error? -EFAULT: 0; -} - long ppc_fadvise64_64(int fd, int advice, u32 offset_high, u32 offset_low, u32 len_high, u32 len_low) { diff --git a/arch/powerpc/kvm/44x_emulate.c b/arch/powerpc/kvm/44x_emulate.c index 61af58fcece..65ea083a5b2 100644 --- a/arch/powerpc/kvm/44x_emulate.c +++ b/arch/powerpc/kvm/44x_emulate.c @@ -65,13 +65,14 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, */ switch (dcrn) { case DCRN_CPR0_CONFIG_ADDR: - vcpu->arch.gpr[rt] = vcpu->arch.cpr0_cfgaddr; + kvmppc_set_gpr(vcpu, rt, vcpu->arch.cpr0_cfgaddr); break; case DCRN_CPR0_CONFIG_DATA: local_irq_disable(); mtdcr(DCRN_CPR0_CONFIG_ADDR, vcpu->arch.cpr0_cfgaddr); - vcpu->arch.gpr[rt] = mfdcr(DCRN_CPR0_CONFIG_DATA); + kvmppc_set_gpr(vcpu, rt, + mfdcr(DCRN_CPR0_CONFIG_DATA)); local_irq_enable(); break; default: @@ -93,11 +94,11 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, /* emulate some access in kernel */ switch (dcrn) { case DCRN_CPR0_CONFIG_ADDR: - vcpu->arch.cpr0_cfgaddr = vcpu->arch.gpr[rs]; + vcpu->arch.cpr0_cfgaddr = kvmppc_get_gpr(vcpu, rs); break; default: run->dcr.dcrn = dcrn; - run->dcr.data = vcpu->arch.gpr[rs]; + run->dcr.data = kvmppc_get_gpr(vcpu, rs); run->dcr.is_write = 1; vcpu->arch.dcr_needed = 1; kvmppc_account_exit(vcpu, DCR_EXITS); @@ -146,13 +147,13 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs) switch (sprn) { case SPRN_PID: - kvmppc_set_pid(vcpu, vcpu->arch.gpr[rs]); break; + kvmppc_set_pid(vcpu, kvmppc_get_gpr(vcpu, rs)); break; case SPRN_MMUCR: - vcpu->arch.mmucr = vcpu->arch.gpr[rs]; break; + vcpu->arch.mmucr = kvmppc_get_gpr(vcpu, rs); break; case SPRN_CCR0: - vcpu->arch.ccr0 = vcpu->arch.gpr[rs]; break; + vcpu->arch.ccr0 = kvmppc_get_gpr(vcpu, rs); break; case SPRN_CCR1: - vcpu->arch.ccr1 = vcpu->arch.gpr[rs]; break; + vcpu->arch.ccr1 = kvmppc_get_gpr(vcpu, rs); break; default: emulated = kvmppc_booke_emulate_mtspr(vcpu, sprn, rs); } @@ -167,13 +168,13 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt) switch (sprn) { case SPRN_PID: - vcpu->arch.gpr[rt] = vcpu->arch.pid; break; + kvmppc_set_gpr(vcpu, rt, vcpu->arch.pid); break; case SPRN_MMUCR: - vcpu->arch.gpr[rt] = vcpu->arch.mmucr; break; + kvmppc_set_gpr(vcpu, rt, vcpu->arch.mmucr); break; case SPRN_CCR0: - vcpu->arch.gpr[rt] = vcpu->arch.ccr0; break; + kvmppc_set_gpr(vcpu, rt, vcpu->arch.ccr0); break; case SPRN_CCR1: - vcpu->arch.gpr[rt] = vcpu->arch.ccr1; break; + kvmppc_set_gpr(vcpu, rt, vcpu->arch.ccr1); break; default: emulated = kvmppc_booke_emulate_mfspr(vcpu, sprn, rt); } diff --git a/arch/powerpc/kvm/44x_tlb.c b/arch/powerpc/kvm/44x_tlb.c index ff3cb63b811..2570fcc7665 100644 --- a/arch/powerpc/kvm/44x_tlb.c +++ b/arch/powerpc/kvm/44x_tlb.c @@ -439,7 +439,7 @@ int kvmppc_44x_emul_tlbwe(struct kvm_vcpu *vcpu, u8 ra, u8 rs, u8 ws) struct kvmppc_44x_tlbe *tlbe; unsigned int gtlb_index; - gtlb_index = vcpu->arch.gpr[ra]; + gtlb_index = kvmppc_get_gpr(vcpu, ra); if (gtlb_index > KVM44x_GUEST_TLB_SIZE) { printk("%s: index %d\n", __func__, gtlb_index); kvmppc_dump_vcpu(vcpu); @@ -455,15 +455,15 @@ int kvmppc_44x_emul_tlbwe(struct kvm_vcpu *vcpu, u8 ra, u8 rs, u8 ws) switch (ws) { case PPC44x_TLB_PAGEID: tlbe->tid = get_mmucr_stid(vcpu); - tlbe->word0 = vcpu->arch.gpr[rs]; + tlbe->word0 = kvmppc_get_gpr(vcpu, rs); break; case PPC44x_TLB_XLAT: - tlbe->word1 = vcpu->arch.gpr[rs]; + tlbe->word1 = kvmppc_get_gpr(vcpu, rs); break; case PPC44x_TLB_ATTRIB: - tlbe->word2 = vcpu->arch.gpr[rs]; + tlbe->word2 = kvmppc_get_gpr(vcpu, rs); break; default: @@ -500,18 +500,20 @@ int kvmppc_44x_emul_tlbsx(struct kvm_vcpu *vcpu, u8 rt, u8 ra, u8 rb, u8 rc) unsigned int as = get_mmucr_sts(vcpu); unsigned int pid = get_mmucr_stid(vcpu); - ea = vcpu->arch.gpr[rb]; + ea = kvmppc_get_gpr(vcpu, rb); if (ra) - ea += vcpu->arch.gpr[ra]; + ea += kvmppc_get_gpr(vcpu, ra); gtlb_index = kvmppc_44x_tlb_index(vcpu, ea, pid, as); if (rc) { + u32 cr = kvmppc_get_cr(vcpu); + if (gtlb_index < 0) - vcpu->arch.cr &= ~0x20000000; + kvmppc_set_cr(vcpu, cr & ~0x20000000); else - vcpu->arch.cr |= 0x20000000; + kvmppc_set_cr(vcpu, cr | 0x20000000); } - vcpu->arch.gpr[rt] = gtlb_index; + kvmppc_set_gpr(vcpu, rt, gtlb_index); kvmppc_set_exit_type(vcpu, EMULATED_TLBSX_EXITS); return EMULATE_DONE; diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index fe037fdaf1b..60624cc9f4d 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -20,6 +20,7 @@ config KVM bool select PREEMPT_NOTIFIERS select ANON_INODES + select KVM_MMIO config KVM_BOOK3S_64_HANDLER bool diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index 3e294bd9b8c..9a271f0929c 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -33,12 +33,9 @@ /* #define EXIT_DEBUG */ /* #define EXIT_DEBUG_SIMPLE */ +/* #define DEBUG_EXT */ -/* Without AGGRESSIVE_DEC we only fire off a DEC interrupt when DEC turns 0. - * When set, we retrigger a DEC interrupt after that if DEC <= 0. - * PPC32 Linux runs faster without AGGRESSIVE_DEC, PPC64 Linux requires it. */ - -/* #define AGGRESSIVE_DEC */ +static void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr); struct kvm_stats_debugfs_item debugfs_entries[] = { { "exits", VCPU_STAT(sum_exits) }, @@ -72,16 +69,24 @@ void kvmppc_core_load_guest_debugstate(struct kvm_vcpu *vcpu) void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { memcpy(get_paca()->kvm_slb, to_book3s(vcpu)->slb_shadow, sizeof(get_paca()->kvm_slb)); + memcpy(&get_paca()->shadow_vcpu, &to_book3s(vcpu)->shadow_vcpu, + sizeof(get_paca()->shadow_vcpu)); get_paca()->kvm_slb_max = to_book3s(vcpu)->slb_shadow_max; } void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu) { memcpy(to_book3s(vcpu)->slb_shadow, get_paca()->kvm_slb, sizeof(get_paca()->kvm_slb)); + memcpy(&to_book3s(vcpu)->shadow_vcpu, &get_paca()->shadow_vcpu, + sizeof(get_paca()->shadow_vcpu)); to_book3s(vcpu)->slb_shadow_max = get_paca()->kvm_slb_max; + + kvmppc_giveup_ext(vcpu, MSR_FP); + kvmppc_giveup_ext(vcpu, MSR_VEC); + kvmppc_giveup_ext(vcpu, MSR_VSX); } -#if defined(AGGRESSIVE_DEC) || defined(EXIT_DEBUG) +#if defined(EXIT_DEBUG) static u32 kvmppc_get_dec(struct kvm_vcpu *vcpu) { u64 jd = mftb() - vcpu->arch.dec_jiffies; @@ -89,6 +94,23 @@ static u32 kvmppc_get_dec(struct kvm_vcpu *vcpu) } #endif +static void kvmppc_recalc_shadow_msr(struct kvm_vcpu *vcpu) +{ + vcpu->arch.shadow_msr = vcpu->arch.msr; + /* Guest MSR values */ + vcpu->arch.shadow_msr &= MSR_FE0 | MSR_FE1 | MSR_SF | MSR_SE | + MSR_BE | MSR_DE; + /* Process MSR values */ + vcpu->arch.shadow_msr |= MSR_ME | MSR_RI | MSR_IR | MSR_DR | MSR_PR | + MSR_EE; + /* External providers the guest reserved */ + vcpu->arch.shadow_msr |= (vcpu->arch.msr & vcpu->arch.guest_owned_ext); + /* 64-bit Process MSR values */ +#ifdef CONFIG_PPC_BOOK3S_64 + vcpu->arch.shadow_msr |= MSR_ISF | MSR_HV; +#endif +} + void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr) { ulong old_msr = vcpu->arch.msr; @@ -96,12 +118,10 @@ void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr) #ifdef EXIT_DEBUG printk(KERN_INFO "KVM: Set MSR to 0x%llx\n", msr); #endif + msr &= to_book3s(vcpu)->msr_mask; vcpu->arch.msr = msr; - vcpu->arch.shadow_msr = msr | MSR_USER32; - vcpu->arch.shadow_msr &= ( MSR_VEC | MSR_VSX | MSR_FP | MSR_FE0 | - MSR_USER64 | MSR_SE | MSR_BE | MSR_DE | - MSR_FE1); + kvmppc_recalc_shadow_msr(vcpu); if (msr & (MSR_WE|MSR_POW)) { if (!vcpu->arch.pending_exceptions) { @@ -125,11 +145,10 @@ void kvmppc_inject_interrupt(struct kvm_vcpu *vcpu, int vec, u64 flags) vcpu->arch.mmu.reset_msr(vcpu); } -void kvmppc_book3s_queue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec) +static int kvmppc_book3s_vec2irqprio(unsigned int vec) { unsigned int prio; - vcpu->stat.queue_intr++; switch (vec) { case 0x100: prio = BOOK3S_IRQPRIO_SYSTEM_RESET; break; case 0x200: prio = BOOK3S_IRQPRIO_MACHINE_CHECK; break; @@ -149,15 +168,31 @@ void kvmppc_book3s_queue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec) default: prio = BOOK3S_IRQPRIO_MAX; break; } - set_bit(prio, &vcpu->arch.pending_exceptions); + return prio; +} + +static void kvmppc_book3s_dequeue_irqprio(struct kvm_vcpu *vcpu, + unsigned int vec) +{ + clear_bit(kvmppc_book3s_vec2irqprio(vec), + &vcpu->arch.pending_exceptions); +} + +void kvmppc_book3s_queue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec) +{ + vcpu->stat.queue_intr++; + + set_bit(kvmppc_book3s_vec2irqprio(vec), + &vcpu->arch.pending_exceptions); #ifdef EXIT_DEBUG printk(KERN_INFO "Queueing interrupt %x\n", vec); #endif } -void kvmppc_core_queue_program(struct kvm_vcpu *vcpu) +void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong flags) { + to_book3s(vcpu)->prog_flags = flags; kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_PROGRAM); } @@ -171,6 +206,11 @@ int kvmppc_core_pending_dec(struct kvm_vcpu *vcpu) return test_bit(BOOK3S_INTERRUPT_DECREMENTER >> 7, &vcpu->arch.pending_exceptions); } +void kvmppc_core_dequeue_dec(struct kvm_vcpu *vcpu) +{ + kvmppc_book3s_dequeue_irqprio(vcpu, BOOK3S_INTERRUPT_DECREMENTER); +} + void kvmppc_core_queue_external(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq) { @@ -181,6 +221,7 @@ int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu, unsigned int priority) { int deliver = 1; int vec = 0; + ulong flags = 0ULL; switch (priority) { case BOOK3S_IRQPRIO_DECREMENTER: @@ -214,6 +255,7 @@ int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu, unsigned int priority) break; case BOOK3S_IRQPRIO_PROGRAM: vec = BOOK3S_INTERRUPT_PROGRAM; + flags = to_book3s(vcpu)->prog_flags; break; case BOOK3S_IRQPRIO_VSX: vec = BOOK3S_INTERRUPT_VSX; @@ -244,7 +286,7 @@ int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu, unsigned int priority) #endif if (deliver) - kvmppc_inject_interrupt(vcpu, vec, 0ULL); + kvmppc_inject_interrupt(vcpu, vec, flags); return deliver; } @@ -254,21 +296,15 @@ void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu) unsigned long *pending = &vcpu->arch.pending_exceptions; unsigned int priority; - /* XXX be more clever here - no need to mftb() on every entry */ - /* Issue DEC again if it's still active */ -#ifdef AGGRESSIVE_DEC - if (vcpu->arch.msr & MSR_EE) - if (kvmppc_get_dec(vcpu) & 0x80000000) - kvmppc_core_queue_dec(vcpu); -#endif - #ifdef EXIT_DEBUG if (vcpu->arch.pending_exceptions) printk(KERN_EMERG "KVM: Check pending: %lx\n", vcpu->arch.pending_exceptions); #endif priority = __ffs(*pending); while (priority <= (sizeof(unsigned int) * 8)) { - if (kvmppc_book3s_irqprio_deliver(vcpu, priority)) { + if (kvmppc_book3s_irqprio_deliver(vcpu, priority) && + (priority != BOOK3S_IRQPRIO_DECREMENTER)) { + /* DEC interrupts get cleared by mtdec */ clear_bit(priority, &vcpu->arch.pending_exceptions); break; } @@ -503,14 +539,14 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu, /* Page not found in guest PTE entries */ vcpu->arch.dear = vcpu->arch.fault_dear; to_book3s(vcpu)->dsisr = vcpu->arch.fault_dsisr; - vcpu->arch.msr |= (vcpu->arch.shadow_msr & 0x00000000f8000000ULL); + vcpu->arch.msr |= (vcpu->arch.shadow_srr1 & 0x00000000f8000000ULL); kvmppc_book3s_queue_irqprio(vcpu, vec); } else if (page_found == -EPERM) { /* Storage protection */ vcpu->arch.dear = vcpu->arch.fault_dear; to_book3s(vcpu)->dsisr = vcpu->arch.fault_dsisr & ~DSISR_NOHPTE; to_book3s(vcpu)->dsisr |= DSISR_PROTFAULT; - vcpu->arch.msr |= (vcpu->arch.shadow_msr & 0x00000000f8000000ULL); + vcpu->arch.msr |= (vcpu->arch.shadow_srr1 & 0x00000000f8000000ULL); kvmppc_book3s_queue_irqprio(vcpu, vec); } else if (page_found == -EINVAL) { /* Page not found in guest SLB */ @@ -532,13 +568,122 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu, r = kvmppc_emulate_mmio(run, vcpu); if ( r == RESUME_HOST_NV ) r = RESUME_HOST; - if ( r == RESUME_GUEST_NV ) - r = RESUME_GUEST; } return r; } +static inline int get_fpr_index(int i) +{ +#ifdef CONFIG_VSX + i *= 2; +#endif + return i; +} + +/* Give up external provider (FPU, Altivec, VSX) */ +static void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr) +{ + struct thread_struct *t = ¤t->thread; + u64 *vcpu_fpr = vcpu->arch.fpr; + u64 *vcpu_vsx = vcpu->arch.vsr; + u64 *thread_fpr = (u64*)t->fpr; + int i; + + if (!(vcpu->arch.guest_owned_ext & msr)) + return; + +#ifdef DEBUG_EXT + printk(KERN_INFO "Giving up ext 0x%lx\n", msr); +#endif + + switch (msr) { + case MSR_FP: + giveup_fpu(current); + for (i = 0; i < ARRAY_SIZE(vcpu->arch.fpr); i++) + vcpu_fpr[i] = thread_fpr[get_fpr_index(i)]; + + vcpu->arch.fpscr = t->fpscr.val; + break; + case MSR_VEC: +#ifdef CONFIG_ALTIVEC + giveup_altivec(current); + memcpy(vcpu->arch.vr, t->vr, sizeof(vcpu->arch.vr)); + vcpu->arch.vscr = t->vscr; +#endif + break; + case MSR_VSX: +#ifdef CONFIG_VSX + __giveup_vsx(current); + for (i = 0; i < ARRAY_SIZE(vcpu->arch.vsr); i++) + vcpu_vsx[i] = thread_fpr[get_fpr_index(i) + 1]; +#endif + break; + default: + BUG(); + } + + vcpu->arch.guest_owned_ext &= ~msr; + current->thread.regs->msr &= ~msr; + kvmppc_recalc_shadow_msr(vcpu); +} + +/* Handle external providers (FPU, Altivec, VSX) */ +static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr, + ulong msr) +{ + struct thread_struct *t = ¤t->thread; + u64 *vcpu_fpr = vcpu->arch.fpr; + u64 *vcpu_vsx = vcpu->arch.vsr; + u64 *thread_fpr = (u64*)t->fpr; + int i; + + if (!(vcpu->arch.msr & msr)) { + kvmppc_book3s_queue_irqprio(vcpu, exit_nr); + return RESUME_GUEST; + } + +#ifdef DEBUG_EXT + printk(KERN_INFO "Loading up ext 0x%lx\n", msr); +#endif + + current->thread.regs->msr |= msr; + + switch (msr) { + case MSR_FP: + for (i = 0; i < ARRAY_SIZE(vcpu->arch.fpr); i++) + thread_fpr[get_fpr_index(i)] = vcpu_fpr[i]; + + t->fpscr.val = vcpu->arch.fpscr; + t->fpexc_mode = 0; + kvmppc_load_up_fpu(); + break; + case MSR_VEC: +#ifdef CONFIG_ALTIVEC + memcpy(t->vr, vcpu->arch.vr, sizeof(vcpu->arch.vr)); + t->vscr = vcpu->arch.vscr; + t->vrsave = -1; + kvmppc_load_up_altivec(); +#endif + break; + case MSR_VSX: +#ifdef CONFIG_VSX + for (i = 0; i < ARRAY_SIZE(vcpu->arch.vsr); i++) + thread_fpr[get_fpr_index(i) + 1] = vcpu_vsx[i]; + kvmppc_load_up_vsx(); +#endif + break; + default: + BUG(); + } + + vcpu->arch.guest_owned_ext |= msr; + + kvmppc_recalc_shadow_msr(vcpu); + + return RESUME_GUEST; +} + int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, unsigned int exit_nr) { @@ -563,7 +708,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, case BOOK3S_INTERRUPT_INST_STORAGE: vcpu->stat.pf_instruc++; /* only care about PTEG not found errors, but leave NX alone */ - if (vcpu->arch.shadow_msr & 0x40000000) { + if (vcpu->arch.shadow_srr1 & 0x40000000) { r = kvmppc_handle_pagefault(run, vcpu, vcpu->arch.pc, exit_nr); vcpu->stat.sp_instruc++; } else if (vcpu->arch.mmu.is_dcbz32(vcpu) && @@ -575,7 +720,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, */ kvmppc_mmu_pte_flush(vcpu, vcpu->arch.pc, ~0xFFFULL); } else { - vcpu->arch.msr |= (vcpu->arch.shadow_msr & 0x58000000); + vcpu->arch.msr |= vcpu->arch.shadow_srr1 & 0x58000000; kvmppc_book3s_queue_irqprio(vcpu, exit_nr); kvmppc_mmu_pte_flush(vcpu, vcpu->arch.pc, ~0xFFFULL); r = RESUME_GUEST; @@ -621,6 +766,9 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, case BOOK3S_INTERRUPT_PROGRAM: { enum emulation_result er; + ulong flags; + + flags = vcpu->arch.shadow_srr1 & 0x1f0000ull; if (vcpu->arch.msr & MSR_PR) { #ifdef EXIT_DEBUG @@ -628,7 +776,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, #endif if ((vcpu->arch.last_inst & 0xff0007ff) != (INS_DCBZ & 0xfffffff7)) { - kvmppc_book3s_queue_irqprio(vcpu, exit_nr); + kvmppc_core_queue_program(vcpu, flags); r = RESUME_GUEST; break; } @@ -638,12 +786,12 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, er = kvmppc_emulate_instruction(run, vcpu); switch (er) { case EMULATE_DONE: - r = RESUME_GUEST; + r = RESUME_GUEST_NV; break; case EMULATE_FAIL: printk(KERN_CRIT "%s: emulation at %lx failed (%08x)\n", __func__, vcpu->arch.pc, vcpu->arch.last_inst); - kvmppc_book3s_queue_irqprio(vcpu, exit_nr); + kvmppc_core_queue_program(vcpu, flags); r = RESUME_GUEST; break; default: @@ -653,23 +801,30 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, } case BOOK3S_INTERRUPT_SYSCALL: #ifdef EXIT_DEBUG - printk(KERN_INFO "Syscall Nr %d\n", (int)vcpu->arch.gpr[0]); + printk(KERN_INFO "Syscall Nr %d\n", (int)kvmppc_get_gpr(vcpu, 0)); #endif vcpu->stat.syscall_exits++; kvmppc_book3s_queue_irqprio(vcpu, exit_nr); r = RESUME_GUEST; break; - case BOOK3S_INTERRUPT_MACHINE_CHECK: case BOOK3S_INTERRUPT_FP_UNAVAIL: - case BOOK3S_INTERRUPT_TRACE: + r = kvmppc_handle_ext(vcpu, exit_nr, MSR_FP); + break; case BOOK3S_INTERRUPT_ALTIVEC: + r = kvmppc_handle_ext(vcpu, exit_nr, MSR_VEC); + break; case BOOK3S_INTERRUPT_VSX: + r = kvmppc_handle_ext(vcpu, exit_nr, MSR_VSX); + break; + case BOOK3S_INTERRUPT_MACHINE_CHECK: + case BOOK3S_INTERRUPT_TRACE: kvmppc_book3s_queue_irqprio(vcpu, exit_nr); r = RESUME_GUEST; break; default: /* Ugh - bork here! What did we get? */ - printk(KERN_EMERG "exit_nr=0x%x | pc=0x%lx | msr=0x%lx\n", exit_nr, vcpu->arch.pc, vcpu->arch.shadow_msr); + printk(KERN_EMERG "exit_nr=0x%x | pc=0x%lx | msr=0x%lx\n", + exit_nr, vcpu->arch.pc, vcpu->arch.shadow_srr1); r = RESUME_HOST; BUG(); break; @@ -712,10 +867,10 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) int i; regs->pc = vcpu->arch.pc; - regs->cr = vcpu->arch.cr; + regs->cr = kvmppc_get_cr(vcpu); regs->ctr = vcpu->arch.ctr; regs->lr = vcpu->arch.lr; - regs->xer = vcpu->arch.xer; + regs->xer = kvmppc_get_xer(vcpu); regs->msr = vcpu->arch.msr; regs->srr0 = vcpu->arch.srr0; regs->srr1 = vcpu->arch.srr1; @@ -729,7 +884,7 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) regs->sprg7 = vcpu->arch.sprg6; for (i = 0; i < ARRAY_SIZE(regs->gpr); i++) - regs->gpr[i] = vcpu->arch.gpr[i]; + regs->gpr[i] = kvmppc_get_gpr(vcpu, i); return 0; } @@ -739,10 +894,10 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) int i; vcpu->arch.pc = regs->pc; - vcpu->arch.cr = regs->cr; + kvmppc_set_cr(vcpu, regs->cr); vcpu->arch.ctr = regs->ctr; vcpu->arch.lr = regs->lr; - vcpu->arch.xer = regs->xer; + kvmppc_set_xer(vcpu, regs->xer); kvmppc_set_msr(vcpu, regs->msr); vcpu->arch.srr0 = regs->srr0; vcpu->arch.srr1 = regs->srr1; @@ -754,8 +909,8 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) vcpu->arch.sprg6 = regs->sprg5; vcpu->arch.sprg7 = regs->sprg6; - for (i = 0; i < ARRAY_SIZE(vcpu->arch.gpr); i++) - vcpu->arch.gpr[i] = regs->gpr[i]; + for (i = 0; i < ARRAY_SIZE(regs->gpr); i++) + kvmppc_set_gpr(vcpu, i, regs->gpr[i]); return 0; } @@ -850,7 +1005,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, int is_dirty = 0; int r, n; - down_write(&kvm->slots_lock); + mutex_lock(&kvm->slots_lock); r = kvm_get_dirty_log(kvm, log, &is_dirty); if (r) @@ -858,7 +1013,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, /* If nothing is dirty, don't bother messing with page tables. */ if (is_dirty) { - memslot = &kvm->memslots[log->slot]; + memslot = &kvm->memslots->memslots[log->slot]; ga = memslot->base_gfn << PAGE_SHIFT; ga_end = ga + (memslot->npages << PAGE_SHIFT); @@ -872,7 +1027,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, r = 0; out: - up_write(&kvm->slots_lock); + mutex_unlock(&kvm->slots_lock); return r; } @@ -910,6 +1065,7 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id) vcpu->arch.trampoline_lowmem = kvmppc_trampoline_lowmem; vcpu->arch.trampoline_enter = kvmppc_trampoline_enter; vcpu->arch.highmem_handler = (ulong)kvmppc_handler_highmem; + vcpu->arch.rmcall = *(ulong*)kvmppc_rmcall; vcpu->arch.shadow_msr = MSR_USER64; @@ -943,6 +1099,10 @@ extern int __kvmppc_vcpu_entry(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu); int __kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) { int ret; + struct thread_struct ext_bkp; + bool save_vec = current->thread.used_vr; + bool save_vsx = current->thread.used_vsr; + ulong ext_msr; /* No need to go into the guest when all we do is going out */ if (signal_pending(current)) { @@ -950,6 +1110,35 @@ int __kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) return -EINTR; } + /* Save FPU state in stack */ + if (current->thread.regs->msr & MSR_FP) + giveup_fpu(current); + memcpy(ext_bkp.fpr, current->thread.fpr, sizeof(current->thread.fpr)); + ext_bkp.fpscr = current->thread.fpscr; + ext_bkp.fpexc_mode = current->thread.fpexc_mode; + +#ifdef CONFIG_ALTIVEC + /* Save Altivec state in stack */ + if (save_vec) { + if (current->thread.regs->msr & MSR_VEC) + giveup_altivec(current); + memcpy(ext_bkp.vr, current->thread.vr, sizeof(ext_bkp.vr)); + ext_bkp.vscr = current->thread.vscr; + ext_bkp.vrsave = current->thread.vrsave; + } + ext_bkp.used_vr = current->thread.used_vr; +#endif + +#ifdef CONFIG_VSX + /* Save VSX state in stack */ + if (save_vsx && (current->thread.regs->msr & MSR_VSX)) + __giveup_vsx(current); + ext_bkp.used_vsr = current->thread.used_vsr; +#endif + + /* Remember the MSR with disabled extensions */ + ext_msr = current->thread.regs->msr; + /* XXX we get called with irq disabled - change that! */ local_irq_enable(); @@ -957,6 +1146,32 @@ int __kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) local_irq_disable(); + current->thread.regs->msr = ext_msr; + + /* Make sure we save the guest FPU/Altivec/VSX state */ + kvmppc_giveup_ext(vcpu, MSR_FP); + kvmppc_giveup_ext(vcpu, MSR_VEC); + kvmppc_giveup_ext(vcpu, MSR_VSX); + + /* Restore FPU state from stack */ + memcpy(current->thread.fpr, ext_bkp.fpr, sizeof(ext_bkp.fpr)); + current->thread.fpscr = ext_bkp.fpscr; + current->thread.fpexc_mode = ext_bkp.fpexc_mode; + +#ifdef CONFIG_ALTIVEC + /* Restore Altivec state from stack */ + if (save_vec && current->thread.used_vr) { + memcpy(current->thread.vr, ext_bkp.vr, sizeof(ext_bkp.vr)); + current->thread.vscr = ext_bkp.vscr; + current->thread.vrsave= ext_bkp.vrsave; + } + current->thread.used_vr = ext_bkp.used_vr; +#endif + +#ifdef CONFIG_VSX + current->thread.used_vsr = ext_bkp.used_vsr; +#endif + return ret; } diff --git a/arch/powerpc/kvm/book3s_64_emulate.c b/arch/powerpc/kvm/book3s_64_emulate.c index 1027eac6d47..2b0ee7e040c 100644 --- a/arch/powerpc/kvm/book3s_64_emulate.c +++ b/arch/powerpc/kvm/book3s_64_emulate.c @@ -65,11 +65,11 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, case 31: switch (get_xop(inst)) { case OP_31_XOP_MFMSR: - vcpu->arch.gpr[get_rt(inst)] = vcpu->arch.msr; + kvmppc_set_gpr(vcpu, get_rt(inst), vcpu->arch.msr); break; case OP_31_XOP_MTMSRD: { - ulong rs = vcpu->arch.gpr[get_rs(inst)]; + ulong rs = kvmppc_get_gpr(vcpu, get_rs(inst)); if (inst & 0x10000) { vcpu->arch.msr &= ~(MSR_RI | MSR_EE); vcpu->arch.msr |= rs & (MSR_RI | MSR_EE); @@ -78,30 +78,30 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, break; } case OP_31_XOP_MTMSR: - kvmppc_set_msr(vcpu, vcpu->arch.gpr[get_rs(inst)]); + kvmppc_set_msr(vcpu, kvmppc_get_gpr(vcpu, get_rs(inst))); break; case OP_31_XOP_MFSRIN: { int srnum; - srnum = (vcpu->arch.gpr[get_rb(inst)] >> 28) & 0xf; + srnum = (kvmppc_get_gpr(vcpu, get_rb(inst)) >> 28) & 0xf; if (vcpu->arch.mmu.mfsrin) { u32 sr; sr = vcpu->arch.mmu.mfsrin(vcpu, srnum); - vcpu->arch.gpr[get_rt(inst)] = sr; + kvmppc_set_gpr(vcpu, get_rt(inst), sr); } break; } case OP_31_XOP_MTSRIN: vcpu->arch.mmu.mtsrin(vcpu, - (vcpu->arch.gpr[get_rb(inst)] >> 28) & 0xf, - vcpu->arch.gpr[get_rs(inst)]); + (kvmppc_get_gpr(vcpu, get_rb(inst)) >> 28) & 0xf, + kvmppc_get_gpr(vcpu, get_rs(inst))); break; case OP_31_XOP_TLBIE: case OP_31_XOP_TLBIEL: { bool large = (inst & 0x00200000) ? true : false; - ulong addr = vcpu->arch.gpr[get_rb(inst)]; + ulong addr = kvmppc_get_gpr(vcpu, get_rb(inst)); vcpu->arch.mmu.tlbie(vcpu, addr, large); break; } @@ -111,14 +111,16 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, if (!vcpu->arch.mmu.slbmte) return EMULATE_FAIL; - vcpu->arch.mmu.slbmte(vcpu, vcpu->arch.gpr[get_rs(inst)], - vcpu->arch.gpr[get_rb(inst)]); + vcpu->arch.mmu.slbmte(vcpu, + kvmppc_get_gpr(vcpu, get_rs(inst)), + kvmppc_get_gpr(vcpu, get_rb(inst))); break; case OP_31_XOP_SLBIE: if (!vcpu->arch.mmu.slbie) return EMULATE_FAIL; - vcpu->arch.mmu.slbie(vcpu, vcpu->arch.gpr[get_rb(inst)]); + vcpu->arch.mmu.slbie(vcpu, + kvmppc_get_gpr(vcpu, get_rb(inst))); break; case OP_31_XOP_SLBIA: if (!vcpu->arch.mmu.slbia) @@ -132,9 +134,9 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, } else { ulong t, rb; - rb = vcpu->arch.gpr[get_rb(inst)]; + rb = kvmppc_get_gpr(vcpu, get_rb(inst)); t = vcpu->arch.mmu.slbmfee(vcpu, rb); - vcpu->arch.gpr[get_rt(inst)] = t; + kvmppc_set_gpr(vcpu, get_rt(inst), t); } break; case OP_31_XOP_SLBMFEV: @@ -143,20 +145,20 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, } else { ulong t, rb; - rb = vcpu->arch.gpr[get_rb(inst)]; + rb = kvmppc_get_gpr(vcpu, get_rb(inst)); t = vcpu->arch.mmu.slbmfev(vcpu, rb); - vcpu->arch.gpr[get_rt(inst)] = t; + kvmppc_set_gpr(vcpu, get_rt(inst), t); } break; case OP_31_XOP_DCBZ: { - ulong rb = vcpu->arch.gpr[get_rb(inst)]; + ulong rb = kvmppc_get_gpr(vcpu, get_rb(inst)); ulong ra = 0; ulong addr; u32 zeros[8] = { 0, 0, 0, 0, 0, 0, 0, 0 }; if (get_ra(inst)) - ra = vcpu->arch.gpr[get_ra(inst)]; + ra = kvmppc_get_gpr(vcpu, get_ra(inst)); addr = (ra + rb) & ~31ULL; if (!(vcpu->arch.msr & MSR_SF)) @@ -233,43 +235,44 @@ static void kvmppc_write_bat(struct kvm_vcpu *vcpu, int sprn, u32 val) int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs) { int emulated = EMULATE_DONE; + ulong spr_val = kvmppc_get_gpr(vcpu, rs); switch (sprn) { case SPRN_SDR1: - to_book3s(vcpu)->sdr1 = vcpu->arch.gpr[rs]; + to_book3s(vcpu)->sdr1 = spr_val; break; case SPRN_DSISR: - to_book3s(vcpu)->dsisr = vcpu->arch.gpr[rs]; + to_book3s(vcpu)->dsisr = spr_val; break; case SPRN_DAR: - vcpu->arch.dear = vcpu->arch.gpr[rs]; + vcpu->arch.dear = spr_val; break; case SPRN_HIOR: - to_book3s(vcpu)->hior = vcpu->arch.gpr[rs]; + to_book3s(vcpu)->hior = spr_val; break; case SPRN_IBAT0U ... SPRN_IBAT3L: case SPRN_IBAT4U ... SPRN_IBAT7L: case SPRN_DBAT0U ... SPRN_DBAT3L: case SPRN_DBAT4U ... SPRN_DBAT7L: - kvmppc_write_bat(vcpu, sprn, (u32)vcpu->arch.gpr[rs]); + kvmppc_write_bat(vcpu, sprn, (u32)spr_val); /* BAT writes happen so rarely that we're ok to flush * everything here */ kvmppc_mmu_pte_flush(vcpu, 0, 0); break; case SPRN_HID0: - to_book3s(vcpu)->hid[0] = vcpu->arch.gpr[rs]; + to_book3s(vcpu)->hid[0] = spr_val; break; case SPRN_HID1: - to_book3s(vcpu)->hid[1] = vcpu->arch.gpr[rs]; + to_book3s(vcpu)->hid[1] = spr_val; break; case SPRN_HID2: - to_book3s(vcpu)->hid[2] = vcpu->arch.gpr[rs]; + to_book3s(vcpu)->hid[2] = spr_val; break; case SPRN_HID4: - to_book3s(vcpu)->hid[4] = vcpu->arch.gpr[rs]; + to_book3s(vcpu)->hid[4] = spr_val; break; case SPRN_HID5: - to_book3s(vcpu)->hid[5] = vcpu->arch.gpr[rs]; + to_book3s(vcpu)->hid[5] = spr_val; /* guest HID5 set can change is_dcbz32 */ if (vcpu->arch.mmu.is_dcbz32(vcpu) && (mfmsr() & MSR_HV)) @@ -299,38 +302,38 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt) switch (sprn) { case SPRN_SDR1: - vcpu->arch.gpr[rt] = to_book3s(vcpu)->sdr1; + kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->sdr1); break; case SPRN_DSISR: - vcpu->arch.gpr[rt] = to_book3s(vcpu)->dsisr; + kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->dsisr); break; case SPRN_DAR: - vcpu->arch.gpr[rt] = vcpu->arch.dear; + kvmppc_set_gpr(vcpu, rt, vcpu->arch.dear); break; case SPRN_HIOR: - vcpu->arch.gpr[rt] = to_book3s(vcpu)->hior; + kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hior); break; case SPRN_HID0: - vcpu->arch.gpr[rt] = to_book3s(vcpu)->hid[0]; + kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hid[0]); break; case SPRN_HID1: - vcpu->arch.gpr[rt] = to_book3s(vcpu)->hid[1]; + kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hid[1]); break; case SPRN_HID2: - vcpu->arch.gpr[rt] = to_book3s(vcpu)->hid[2]; + kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hid[2]); break; case SPRN_HID4: - vcpu->arch.gpr[rt] = to_book3s(vcpu)->hid[4]; + kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hid[4]); break; case SPRN_HID5: - vcpu->arch.gpr[rt] = to_book3s(vcpu)->hid[5]; + kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hid[5]); break; case SPRN_THRM1: case SPRN_THRM2: case SPRN_THRM3: case SPRN_CTRLF: case SPRN_CTRLT: - vcpu->arch.gpr[rt] = 0; + kvmppc_set_gpr(vcpu, rt, 0); break; default: printk(KERN_INFO "KVM: invalid SPR read: %d\n", sprn); diff --git a/arch/powerpc/kvm/book3s_64_exports.c b/arch/powerpc/kvm/book3s_64_exports.c index 5b2db38ed86..1dd5a1ddfd0 100644 --- a/arch/powerpc/kvm/book3s_64_exports.c +++ b/arch/powerpc/kvm/book3s_64_exports.c @@ -22,3 +22,11 @@ EXPORT_SYMBOL_GPL(kvmppc_trampoline_enter); EXPORT_SYMBOL_GPL(kvmppc_trampoline_lowmem); +EXPORT_SYMBOL_GPL(kvmppc_rmcall); +EXPORT_SYMBOL_GPL(kvmppc_load_up_fpu); +#ifdef CONFIG_ALTIVEC +EXPORT_SYMBOL_GPL(kvmppc_load_up_altivec); +#endif +#ifdef CONFIG_VSX +EXPORT_SYMBOL_GPL(kvmppc_load_up_vsx); +#endif diff --git a/arch/powerpc/kvm/book3s_64_interrupts.S b/arch/powerpc/kvm/book3s_64_interrupts.S index 7b55d8094c8..c1584d0cbce 100644 --- a/arch/powerpc/kvm/book3s_64_interrupts.S +++ b/arch/powerpc/kvm/book3s_64_interrupts.S @@ -28,11 +28,6 @@ #define ULONG_SIZE 8 #define VCPU_GPR(n) (VCPU_GPRS + (n * ULONG_SIZE)) -.macro mfpaca tmp_reg, src_reg, offset, vcpu_reg - ld \tmp_reg, (PACA_EXMC+\offset)(r13) - std \tmp_reg, VCPU_GPR(\src_reg)(\vcpu_reg) -.endm - .macro DISABLE_INTERRUPTS mfmsr r0 rldicl r0,r0,48,1 @@ -40,6 +35,26 @@ mtmsrd r0,1 .endm +#define VCPU_LOAD_NVGPRS(vcpu) \ + ld r14, VCPU_GPR(r14)(vcpu); \ + ld r15, VCPU_GPR(r15)(vcpu); \ + ld r16, VCPU_GPR(r16)(vcpu); \ + ld r17, VCPU_GPR(r17)(vcpu); \ + ld r18, VCPU_GPR(r18)(vcpu); \ + ld r19, VCPU_GPR(r19)(vcpu); \ + ld r20, VCPU_GPR(r20)(vcpu); \ + ld r21, VCPU_GPR(r21)(vcpu); \ + ld r22, VCPU_GPR(r22)(vcpu); \ + ld r23, VCPU_GPR(r23)(vcpu); \ + ld r24, VCPU_GPR(r24)(vcpu); \ + ld r25, VCPU_GPR(r25)(vcpu); \ + ld r26, VCPU_GPR(r26)(vcpu); \ + ld r27, VCPU_GPR(r27)(vcpu); \ + ld r28, VCPU_GPR(r28)(vcpu); \ + ld r29, VCPU_GPR(r29)(vcpu); \ + ld r30, VCPU_GPR(r30)(vcpu); \ + ld r31, VCPU_GPR(r31)(vcpu); \ + /***************************************************************************** * * * Guest entry / exit code that is in kernel module memory (highmem) * @@ -67,61 +82,32 @@ kvm_start_entry: SAVE_NVGPRS(r1) /* Save LR */ - mflr r14 - std r14, _LINK(r1) - -/* XXX optimize non-volatile loading away */ -kvm_start_lightweight: + std r0, _LINK(r1) - DISABLE_INTERRUPTS + /* Load non-volatile guest state from the vcpu */ + VCPU_LOAD_NVGPRS(r4) /* Save R1/R2 in the PACA */ - std r1, PACAR1(r13) - std r2, (PACA_EXMC+EX_SRR0)(r13) + std r1, PACA_KVM_HOST_R1(r13) + std r2, PACA_KVM_HOST_R2(r13) + + /* XXX swap in/out on load? */ ld r3, VCPU_HIGHMEM_HANDLER(r4) - std r3, PACASAVEDMSR(r13) + std r3, PACA_KVM_VMHANDLER(r13) - /* Load non-volatile guest state from the vcpu */ - ld r14, VCPU_GPR(r14)(r4) - ld r15, VCPU_GPR(r15)(r4) - ld r16, VCPU_GPR(r16)(r4) - ld r17, VCPU_GPR(r17)(r4) - ld r18, VCPU_GPR(r18)(r4) - ld r19, VCPU_GPR(r19)(r4) - ld r20, VCPU_GPR(r20)(r4) - ld r21, VCPU_GPR(r21)(r4) - ld r22, VCPU_GPR(r22)(r4) - ld r23, VCPU_GPR(r23)(r4) - ld r24, VCPU_GPR(r24)(r4) - ld r25, VCPU_GPR(r25)(r4) - ld r26, VCPU_GPR(r26)(r4) - ld r27, VCPU_GPR(r27)(r4) - ld r28, VCPU_GPR(r28)(r4) - ld r29, VCPU_GPR(r29)(r4) - ld r30, VCPU_GPR(r30)(r4) - ld r31, VCPU_GPR(r31)(r4) +kvm_start_lightweight: ld r9, VCPU_PC(r4) /* r9 = vcpu->arch.pc */ ld r10, VCPU_SHADOW_MSR(r4) /* r10 = vcpu->arch.shadow_msr */ - ld r3, VCPU_TRAMPOLINE_ENTER(r4) - mtsrr0 r3 - - LOAD_REG_IMMEDIATE(r3, MSR_KERNEL & ~(MSR_IR | MSR_DR)) - mtsrr1 r3 - - /* Load guest state in the respective registers */ - lwz r3, VCPU_CR(r4) /* r3 = vcpu->arch.cr */ - stw r3, (PACA_EXMC + EX_CCR)(r13) - - ld r3, VCPU_CTR(r4) /* r3 = vcpu->arch.ctr */ - mtctr r3 /* CTR = r3 */ + /* Load some guest state in the respective registers */ + ld r5, VCPU_CTR(r4) /* r5 = vcpu->arch.ctr */ + /* will be swapped in by rmcall */ ld r3, VCPU_LR(r4) /* r3 = vcpu->arch.lr */ mtlr r3 /* LR = r3 */ - ld r3, VCPU_XER(r4) /* r3 = vcpu->arch.xer */ - std r3, (PACA_EXMC + EX_R3)(r13) + DISABLE_INTERRUPTS /* Some guests may need to have dcbz set to 32 byte length. * @@ -141,36 +127,15 @@ kvm_start_lightweight: mtspr SPRN_HID5,r3 no_dcbz32_on: - /* Load guest GPRs */ - - ld r3, VCPU_GPR(r9)(r4) - std r3, (PACA_EXMC + EX_R9)(r13) - ld r3, VCPU_GPR(r10)(r4) - std r3, (PACA_EXMC + EX_R10)(r13) - ld r3, VCPU_GPR(r11)(r4) - std r3, (PACA_EXMC + EX_R11)(r13) - ld r3, VCPU_GPR(r12)(r4) - std r3, (PACA_EXMC + EX_R12)(r13) - ld r3, VCPU_GPR(r13)(r4) - std r3, (PACA_EXMC + EX_R13)(r13) - - ld r0, VCPU_GPR(r0)(r4) - ld r1, VCPU_GPR(r1)(r4) - ld r2, VCPU_GPR(r2)(r4) - ld r3, VCPU_GPR(r3)(r4) - ld r5, VCPU_GPR(r5)(r4) - ld r6, VCPU_GPR(r6)(r4) - ld r7, VCPU_GPR(r7)(r4) - ld r8, VCPU_GPR(r8)(r4) - ld r4, VCPU_GPR(r4)(r4) - - /* This sets the Magic value for the trampoline */ - - li r11, 1 - stb r11, PACA_KVM_IN_GUEST(r13) + + ld r6, VCPU_RMCALL(r4) + mtctr r6 + + ld r3, VCPU_TRAMPOLINE_ENTER(r4) + LOAD_REG_IMMEDIATE(r4, MSR_KERNEL & ~(MSR_IR | MSR_DR)) /* Jump to SLB patching handlder and into our guest */ - RFI + bctr /* * This is the handler in module memory. It gets jumped at from the @@ -184,125 +149,70 @@ kvmppc_handler_highmem: /* * Register usage at this point: * - * R00 = guest R13 - * R01 = host R1 - * R02 = host R2 - * R10 = guest PC - * R11 = guest MSR - * R12 = exit handler id - * R13 = PACA - * PACA.exmc.R9 = guest R1 - * PACA.exmc.R10 = guest R10 - * PACA.exmc.R11 = guest R11 - * PACA.exmc.R12 = guest R12 - * PACA.exmc.R13 = guest R2 - * PACA.exmc.DAR = guest DAR - * PACA.exmc.DSISR = guest DSISR - * PACA.exmc.LR = guest instruction - * PACA.exmc.CCR = guest CR - * PACA.exmc.SRR0 = guest R0 + * R0 = guest last inst + * R1 = host R1 + * R2 = host R2 + * R3 = guest PC + * R4 = guest MSR + * R5 = guest DAR + * R6 = guest DSISR + * R13 = PACA + * PACA.KVM.* = guest * * */ - std r3, (PACA_EXMC+EX_R3)(r13) + /* R7 = vcpu */ + ld r7, GPR4(r1) - /* save the exit id in R3 */ - mr r3, r12 + /* Now save the guest state */ - /* R12 = vcpu */ - ld r12, GPR4(r1) + stw r0, VCPU_LAST_INST(r7) - /* Now save the guest state */ + std r3, VCPU_PC(r7) + std r4, VCPU_SHADOW_SRR1(r7) + std r5, VCPU_FAULT_DEAR(r7) + std r6, VCPU_FAULT_DSISR(r7) - std r0, VCPU_GPR(r13)(r12) - std r4, VCPU_GPR(r4)(r12) - std r5, VCPU_GPR(r5)(r12) - std r6, VCPU_GPR(r6)(r12) - std r7, VCPU_GPR(r7)(r12) - std r8, VCPU_GPR(r8)(r12) - std r9, VCPU_GPR(r9)(r12) - - /* get registers from PACA */ - mfpaca r5, r0, EX_SRR0, r12 - mfpaca r5, r3, EX_R3, r12 - mfpaca r5, r1, EX_R9, r12 - mfpaca r5, r10, EX_R10, r12 - mfpaca r5, r11, EX_R11, r12 - mfpaca r5, r12, EX_R12, r12 - mfpaca r5, r2, EX_R13, r12 - - lwz r5, (PACA_EXMC+EX_LR)(r13) - stw r5, VCPU_LAST_INST(r12) - - lwz r5, (PACA_EXMC+EX_CCR)(r13) - stw r5, VCPU_CR(r12) - - ld r5, VCPU_HFLAGS(r12) + ld r5, VCPU_HFLAGS(r7) rldicl. r5, r5, 0, 63 /* CR = ((r5 & 1) == 0) */ beq no_dcbz32_off + li r4, 0 mfspr r5,SPRN_HID5 - rldimi r5,r5,6,56 + rldimi r5,r4,6,56 mtspr SPRN_HID5,r5 no_dcbz32_off: - /* XXX maybe skip on lightweight? */ - std r14, VCPU_GPR(r14)(r12) - std r15, VCPU_GPR(r15)(r12) - std r16, VCPU_GPR(r16)(r12) - std r17, VCPU_GPR(r17)(r12) - std r18, VCPU_GPR(r18)(r12) - std r19, VCPU_GPR(r19)(r12) - std r20, VCPU_GPR(r20)(r12) - std r21, VCPU_GPR(r21)(r12) - std r22, VCPU_GPR(r22)(r12) - std r23, VCPU_GPR(r23)(r12) - std r24, VCPU_GPR(r24)(r12) - std r25, VCPU_GPR(r25)(r12) - std r26, VCPU_GPR(r26)(r12) - std r27, VCPU_GPR(r27)(r12) - std r28, VCPU_GPR(r28)(r12) - std r29, VCPU_GPR(r29)(r12) - std r30, VCPU_GPR(r30)(r12) - std r31, VCPU_GPR(r31)(r12) - - /* Restore non-volatile host registers (r14 - r31) */ - REST_NVGPRS(r1) - - /* Save guest PC (R10) */ - std r10, VCPU_PC(r12) - - /* Save guest msr (R11) */ - std r11, VCPU_SHADOW_MSR(r12) - - /* Save guest CTR (in R12) */ + std r14, VCPU_GPR(r14)(r7) + std r15, VCPU_GPR(r15)(r7) + std r16, VCPU_GPR(r16)(r7) + std r17, VCPU_GPR(r17)(r7) + std r18, VCPU_GPR(r18)(r7) + std r19, VCPU_GPR(r19)(r7) + std r20, VCPU_GPR(r20)(r7) + std r21, VCPU_GPR(r21)(r7) + std r22, VCPU_GPR(r22)(r7) + std r23, VCPU_GPR(r23)(r7) + std r24, VCPU_GPR(r24)(r7) + std r25, VCPU_GPR(r25)(r7) + std r26, VCPU_GPR(r26)(r7) + std r27, VCPU_GPR(r27)(r7) + std r28, VCPU_GPR(r28)(r7) + std r29, VCPU_GPR(r29)(r7) + std r30, VCPU_GPR(r30)(r7) + std r31, VCPU_GPR(r31)(r7) + + /* Save guest CTR */ mfctr r5 - std r5, VCPU_CTR(r12) + std r5, VCPU_CTR(r7) /* Save guest LR */ mflr r5 - std r5, VCPU_LR(r12) - - /* Save guest XER */ - mfxer r5 - std r5, VCPU_XER(r12) - - /* Save guest DAR */ - ld r5, (PACA_EXMC+EX_DAR)(r13) - std r5, VCPU_FAULT_DEAR(r12) - - /* Save guest DSISR */ - lwz r5, (PACA_EXMC+EX_DSISR)(r13) - std r5, VCPU_FAULT_DSISR(r12) + std r5, VCPU_LR(r7) /* Restore host msr -> SRR1 */ - ld r7, VCPU_HOST_MSR(r12) - mtsrr1 r7 - - /* Restore host IP -> SRR0 */ - ld r6, VCPU_HOST_RETIP(r12) - mtsrr0 r6 + ld r6, VCPU_HOST_MSR(r7) /* * For some interrupts, we need to call the real Linux @@ -314,13 +224,14 @@ no_dcbz32_off: * r3 = address of interrupt handler (exit reason) */ - cmpwi r3, BOOK3S_INTERRUPT_EXTERNAL + cmpwi r12, BOOK3S_INTERRUPT_EXTERNAL beq call_linux_handler - cmpwi r3, BOOK3S_INTERRUPT_DECREMENTER + cmpwi r12, BOOK3S_INTERRUPT_DECREMENTER beq call_linux_handler - /* Back to Interruptable Mode! (goto kvm_return_point) */ - RFI + /* Back to EE=1 */ + mtmsr r6 + b kvm_return_point call_linux_handler: @@ -333,16 +244,22 @@ call_linux_handler: * interrupt handler! * * R3 still contains the exit code, - * R6 VCPU_HOST_RETIP and - * R7 VCPU_HOST_MSR + * R5 VCPU_HOST_RETIP and + * R6 VCPU_HOST_MSR */ - mtlr r3 + /* Restore host IP -> SRR0 */ + ld r5, VCPU_HOST_RETIP(r7) + + /* XXX Better move to a safe function? + * What if we get an HTAB flush in between mtsrr0 and mtsrr1? */ - ld r5, VCPU_TRAMPOLINE_LOWMEM(r12) - mtsrr0 r5 - LOAD_REG_IMMEDIATE(r5, MSR_KERNEL & ~(MSR_IR | MSR_DR)) - mtsrr1 r5 + mtlr r12 + + ld r4, VCPU_TRAMPOLINE_LOWMEM(r7) + mtsrr0 r4 + LOAD_REG_IMMEDIATE(r3, MSR_KERNEL & ~(MSR_IR | MSR_DR)) + mtsrr1 r3 RFI @@ -351,42 +268,51 @@ kvm_return_point: /* Jump back to lightweight entry if we're supposed to */ /* go back into the guest */ - mr r5, r3 + + /* Pass the exit number as 3rd argument to kvmppc_handle_exit */ + mr r5, r12 + /* Restore r3 (kvm_run) and r4 (vcpu) */ REST_2GPRS(3, r1) bl KVMPPC_HANDLE_EXIT -#if 0 /* XXX get lightweight exits back */ + /* If RESUME_GUEST, get back in the loop */ cmpwi r3, RESUME_GUEST - bne kvm_exit_heavyweight + beq kvm_loop_lightweight - /* put VCPU and KVM_RUN back into place and roll again! */ - REST_2GPRS(3, r1) - b kvm_start_lightweight + cmpwi r3, RESUME_GUEST_NV + beq kvm_loop_heavyweight -kvm_exit_heavyweight: - /* Restore non-volatile host registers */ - ld r14, _LINK(r1) - mtlr r14 - REST_NVGPRS(r1) +kvm_exit_loop: - addi r1, r1, SWITCH_FRAME_SIZE -#else ld r4, _LINK(r1) mtlr r4 - cmpwi r3, RESUME_GUEST - bne kvm_exit_heavyweight + /* Restore non-volatile host registers (r14 - r31) */ + REST_NVGPRS(r1) + + addi r1, r1, SWITCH_FRAME_SIZE + blr + +kvm_loop_heavyweight: + + ld r4, _LINK(r1) + std r4, (16 + SWITCH_FRAME_SIZE)(r1) + /* Load vcpu and cpu_run */ REST_2GPRS(3, r1) - addi r1, r1, SWITCH_FRAME_SIZE + /* Load non-volatile guest state from the vcpu */ + VCPU_LOAD_NVGPRS(r4) - b kvm_start_entry + /* Jump back into the beginning of this function */ + b kvm_start_lightweight -kvm_exit_heavyweight: +kvm_loop_lightweight: - addi r1, r1, SWITCH_FRAME_SIZE -#endif + /* We'll need the vcpu pointer */ + REST_GPR(4, r1) + + /* Jump back into the beginning of this function */ + b kvm_start_lightweight - blr diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c index e4beeb371a7..512dcff7755 100644 --- a/arch/powerpc/kvm/book3s_64_mmu.c +++ b/arch/powerpc/kvm/book3s_64_mmu.c @@ -54,7 +54,7 @@ static struct kvmppc_slb *kvmppc_mmu_book3s_64_find_slbe( if (!vcpu_book3s->slb[i].valid) continue; - if (vcpu_book3s->slb[i].large) + if (vcpu_book3s->slb[i].tb) cmp_esid = esid_1t; if (vcpu_book3s->slb[i].esid == cmp_esid) @@ -65,9 +65,10 @@ static struct kvmppc_slb *kvmppc_mmu_book3s_64_find_slbe( eaddr, esid, esid_1t); for (i = 0; i < vcpu_book3s->slb_nr; i++) { if (vcpu_book3s->slb[i].vsid) - dprintk(" %d: %c%c %llx %llx\n", i, + dprintk(" %d: %c%c%c %llx %llx\n", i, vcpu_book3s->slb[i].valid ? 'v' : ' ', vcpu_book3s->slb[i].large ? 'l' : ' ', + vcpu_book3s->slb[i].tb ? 't' : ' ', vcpu_book3s->slb[i].esid, vcpu_book3s->slb[i].vsid); } @@ -84,7 +85,7 @@ static u64 kvmppc_mmu_book3s_64_ea_to_vp(struct kvm_vcpu *vcpu, gva_t eaddr, if (!slb) return 0; - if (slb->large) + if (slb->tb) return (((u64)eaddr >> 12) & 0xfffffff) | (((u64)slb->vsid) << 28); @@ -309,7 +310,8 @@ static void kvmppc_mmu_book3s_64_slbmte(struct kvm_vcpu *vcpu, u64 rs, u64 rb) slbe = &vcpu_book3s->slb[slb_nr]; slbe->large = (rs & SLB_VSID_L) ? 1 : 0; - slbe->esid = slbe->large ? esid_1t : esid; + slbe->tb = (rs & SLB_VSID_B_1T) ? 1 : 0; + slbe->esid = slbe->tb ? esid_1t : esid; slbe->vsid = rs >> 12; slbe->valid = (rb & SLB_ESID_V) ? 1 : 0; slbe->Ks = (rs & SLB_VSID_KS) ? 1 : 0; diff --git a/arch/powerpc/kvm/book3s_64_rmhandlers.S b/arch/powerpc/kvm/book3s_64_rmhandlers.S index fb7dd2e9ac8..c83c60ad96c 100644 --- a/arch/powerpc/kvm/book3s_64_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_64_rmhandlers.S @@ -45,36 +45,25 @@ kvmppc_trampoline_\intno: * To distinguish, we check a magic byte in the PACA */ mfspr r13, SPRN_SPRG_PACA /* r13 = PACA */ - std r12, (PACA_EXMC + EX_R12)(r13) + std r12, PACA_KVM_SCRATCH0(r13) mfcr r12 - stw r12, (PACA_EXMC + EX_CCR)(r13) + stw r12, PACA_KVM_SCRATCH1(r13) lbz r12, PACA_KVM_IN_GUEST(r13) - cmpwi r12, 0 + cmpwi r12, KVM_GUEST_MODE_NONE bne ..kvmppc_handler_hasmagic_\intno /* No KVM guest? Then jump back to the Linux handler! */ - lwz r12, (PACA_EXMC + EX_CCR)(r13) + lwz r12, PACA_KVM_SCRATCH1(r13) mtcr r12 - ld r12, (PACA_EXMC + EX_R12)(r13) + ld r12, PACA_KVM_SCRATCH0(r13) mfspr r13, SPRN_SPRG_SCRATCH0 /* r13 = original r13 */ b kvmppc_resume_\intno /* Get back original handler */ /* Now we know we're handling a KVM guest */ ..kvmppc_handler_hasmagic_\intno: - /* Unset guest state */ - li r12, 0 - stb r12, PACA_KVM_IN_GUEST(r13) - std r1, (PACA_EXMC+EX_R9)(r13) - std r10, (PACA_EXMC+EX_R10)(r13) - std r11, (PACA_EXMC+EX_R11)(r13) - std r2, (PACA_EXMC+EX_R13)(r13) - - mfsrr0 r10 - mfsrr1 r11 - - /* Restore R1/R2 so we can handle faults */ - ld r1, PACAR1(r13) - ld r2, (PACA_EXMC+EX_SRR0)(r13) + /* Should we just skip the faulting instruction? */ + cmpwi r12, KVM_GUEST_MODE_SKIP + beq kvmppc_handler_skip_ins /* Let's store which interrupt we're handling */ li r12, \intno @@ -102,23 +91,107 @@ INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_ALTIVEC INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_VSX /* + * Bring us back to the faulting code, but skip the + * faulting instruction. + * + * This is a generic exit path from the interrupt + * trampolines above. + * + * Input Registers: + * + * R12 = free + * R13 = PACA + * PACA.KVM.SCRATCH0 = guest R12 + * PACA.KVM.SCRATCH1 = guest CR + * SPRG_SCRATCH0 = guest R13 + * + */ +kvmppc_handler_skip_ins: + + /* Patch the IP to the next instruction */ + mfsrr0 r12 + addi r12, r12, 4 + mtsrr0 r12 + + /* Clean up all state */ + lwz r12, PACA_KVM_SCRATCH1(r13) + mtcr r12 + ld r12, PACA_KVM_SCRATCH0(r13) + mfspr r13, SPRN_SPRG_SCRATCH0 + + /* And get back into the code */ + RFI + +/* * This trampoline brings us back to a real mode handler * * Input Registers: * - * R6 = SRR0 - * R7 = SRR1 + * R5 = SRR0 + * R6 = SRR1 * LR = real-mode IP * */ .global kvmppc_handler_lowmem_trampoline kvmppc_handler_lowmem_trampoline: - mtsrr0 r6 - mtsrr1 r7 + mtsrr0 r5 + mtsrr1 r6 blr kvmppc_handler_lowmem_trampoline_end: +/* + * Call a function in real mode + * + * Input Registers: + * + * R3 = function + * R4 = MSR + * R5 = CTR + * + */ +_GLOBAL(kvmppc_rmcall) + mtmsr r4 /* Disable relocation, so mtsrr + doesn't get interrupted */ + mtctr r5 + mtsrr0 r3 + mtsrr1 r4 + RFI + +/* + * Activate current's external feature (FPU/Altivec/VSX) + */ +#define define_load_up(what) \ + \ +_GLOBAL(kvmppc_load_up_ ## what); \ + subi r1, r1, INT_FRAME_SIZE; \ + mflr r3; \ + std r3, _LINK(r1); \ + mfmsr r4; \ + std r31, GPR3(r1); \ + mr r31, r4; \ + li r5, MSR_DR; \ + oris r5, r5, MSR_EE@h; \ + andc r4, r4, r5; \ + mtmsr r4; \ + \ + bl .load_up_ ## what; \ + \ + mtmsr r31; \ + ld r3, _LINK(r1); \ + ld r31, GPR3(r1); \ + addi r1, r1, INT_FRAME_SIZE; \ + mtlr r3; \ + blr + +define_load_up(fpu) +#ifdef CONFIG_ALTIVEC +define_load_up(altivec) +#endif +#ifdef CONFIG_VSX +define_load_up(vsx) +#endif + .global kvmppc_trampoline_lowmem kvmppc_trampoline_lowmem: .long kvmppc_handler_lowmem_trampoline - _stext diff --git a/arch/powerpc/kvm/book3s_64_slb.S b/arch/powerpc/kvm/book3s_64_slb.S index ecd237a03fd..35b76272218 100644 --- a/arch/powerpc/kvm/book3s_64_slb.S +++ b/arch/powerpc/kvm/book3s_64_slb.S @@ -31,7 +31,7 @@ #define REBOLT_SLB_ENTRY(num) \ ld r10, SHADOW_SLB_ESID(num)(r11); \ cmpdi r10, 0; \ - beq slb_exit_skip_1; \ + beq slb_exit_skip_ ## num; \ oris r10, r10, SLB_ESID_V@h; \ ld r9, SHADOW_SLB_VSID(num)(r11); \ slbmte r9, r10; \ @@ -51,23 +51,21 @@ kvmppc_handler_trampoline_enter: * * MSR = ~IR|DR * R13 = PACA + * R1 = host R1 + * R2 = host R2 * R9 = guest IP * R10 = guest MSR - * R11 = free - * R12 = free - * PACA[PACA_EXMC + EX_R9] = guest R9 - * PACA[PACA_EXMC + EX_R10] = guest R10 - * PACA[PACA_EXMC + EX_R11] = guest R11 - * PACA[PACA_EXMC + EX_R12] = guest R12 - * PACA[PACA_EXMC + EX_R13] = guest R13 - * PACA[PACA_EXMC + EX_CCR] = guest CR - * PACA[PACA_EXMC + EX_R3] = guest XER + * all other GPRS = free + * PACA[KVM_CR] = guest CR + * PACA[KVM_XER] = guest XER */ mtsrr0 r9 mtsrr1 r10 - mtspr SPRN_SPRG_SCRATCH0, r0 + /* Activate guest mode, so faults get handled by KVM */ + li r11, KVM_GUEST_MODE_GUEST + stb r11, PACA_KVM_IN_GUEST(r13) /* Remove LPAR shadow entries */ @@ -131,20 +129,27 @@ slb_do_enter: /* Enter guest */ - mfspr r0, SPRN_SPRG_SCRATCH0 - - ld r9, (PACA_EXMC+EX_R9)(r13) - ld r10, (PACA_EXMC+EX_R10)(r13) - ld r12, (PACA_EXMC+EX_R12)(r13) - - lwz r11, (PACA_EXMC+EX_CCR)(r13) + ld r0, (PACA_KVM_R0)(r13) + ld r1, (PACA_KVM_R1)(r13) + ld r2, (PACA_KVM_R2)(r13) + ld r3, (PACA_KVM_R3)(r13) + ld r4, (PACA_KVM_R4)(r13) + ld r5, (PACA_KVM_R5)(r13) + ld r6, (PACA_KVM_R6)(r13) + ld r7, (PACA_KVM_R7)(r13) + ld r8, (PACA_KVM_R8)(r13) + ld r9, (PACA_KVM_R9)(r13) + ld r10, (PACA_KVM_R10)(r13) + ld r12, (PACA_KVM_R12)(r13) + + lwz r11, (PACA_KVM_CR)(r13) mtcr r11 - ld r11, (PACA_EXMC+EX_R3)(r13) + ld r11, (PACA_KVM_XER)(r13) mtxer r11 - ld r11, (PACA_EXMC+EX_R11)(r13) - ld r13, (PACA_EXMC+EX_R13)(r13) + ld r11, (PACA_KVM_R11)(r13) + ld r13, (PACA_KVM_R13)(r13) RFI kvmppc_handler_trampoline_enter_end: @@ -162,28 +167,54 @@ kvmppc_handler_trampoline_exit: /* Register usage at this point: * - * SPRG_SCRATCH0 = guest R13 - * R01 = host R1 - * R02 = host R2 - * R10 = guest PC - * R11 = guest MSR - * R12 = exit handler id - * R13 = PACA - * PACA.exmc.CCR = guest CR - * PACA.exmc.R9 = guest R1 - * PACA.exmc.R10 = guest R10 - * PACA.exmc.R11 = guest R11 - * PACA.exmc.R12 = guest R12 - * PACA.exmc.R13 = guest R2 + * SPRG_SCRATCH0 = guest R13 + * R12 = exit handler id + * R13 = PACA + * PACA.KVM.SCRATCH0 = guest R12 + * PACA.KVM.SCRATCH1 = guest CR * */ /* Save registers */ - std r0, (PACA_EXMC+EX_SRR0)(r13) - std r9, (PACA_EXMC+EX_R3)(r13) - std r10, (PACA_EXMC+EX_LR)(r13) - std r11, (PACA_EXMC+EX_DAR)(r13) + std r0, PACA_KVM_R0(r13) + std r1, PACA_KVM_R1(r13) + std r2, PACA_KVM_R2(r13) + std r3, PACA_KVM_R3(r13) + std r4, PACA_KVM_R4(r13) + std r5, PACA_KVM_R5(r13) + std r6, PACA_KVM_R6(r13) + std r7, PACA_KVM_R7(r13) + std r8, PACA_KVM_R8(r13) + std r9, PACA_KVM_R9(r13) + std r10, PACA_KVM_R10(r13) + std r11, PACA_KVM_R11(r13) + + /* Restore R1/R2 so we can handle faults */ + ld r1, PACA_KVM_HOST_R1(r13) + ld r2, PACA_KVM_HOST_R2(r13) + + /* Save guest PC and MSR in GPRs */ + mfsrr0 r3 + mfsrr1 r4 + + /* Get scratch'ed off registers */ + mfspr r9, SPRN_SPRG_SCRATCH0 + std r9, PACA_KVM_R13(r13) + + ld r8, PACA_KVM_SCRATCH0(r13) + std r8, PACA_KVM_R12(r13) + + lwz r7, PACA_KVM_SCRATCH1(r13) + stw r7, PACA_KVM_CR(r13) + + /* Save more register state */ + + mfxer r6 + stw r6, PACA_KVM_XER(r13) + + mfdar r5 + mfdsisr r6 /* * In order for us to easily get the last instruction, @@ -202,17 +233,28 @@ kvmppc_handler_trampoline_exit: ld_last_inst: /* Save off the guest instruction we're at */ + + /* Set guest mode to 'jump over instruction' so if lwz faults + * we'll just continue at the next IP. */ + li r9, KVM_GUEST_MODE_SKIP + stb r9, PACA_KVM_IN_GUEST(r13) + /* 1) enable paging for data */ mfmsr r9 ori r11, r9, MSR_DR /* Enable paging for data */ mtmsr r11 /* 2) fetch the instruction */ - lwz r0, 0(r10) + li r0, KVM_INST_FETCH_FAILED /* In case lwz faults */ + lwz r0, 0(r3) /* 3) disable paging again */ mtmsr r9 no_ld_last_inst: + /* Unset guest mode */ + li r9, KVM_GUEST_MODE_NONE + stb r9, PACA_KVM_IN_GUEST(r13) + /* Restore bolted entries from the shadow and fix it along the way */ /* We don't store anything in entry 0, so we don't need to take care of it */ @@ -233,29 +275,27 @@ no_ld_last_inst: slb_do_exit: - /* Restore registers */ - - ld r11, (PACA_EXMC+EX_DAR)(r13) - ld r10, (PACA_EXMC+EX_LR)(r13) - ld r9, (PACA_EXMC+EX_R3)(r13) - - /* Save last inst */ - stw r0, (PACA_EXMC+EX_LR)(r13) - - /* Save DAR and DSISR before going to paged mode */ - mfdar r0 - std r0, (PACA_EXMC+EX_DAR)(r13) - mfdsisr r0 - stw r0, (PACA_EXMC+EX_DSISR)(r13) + /* Register usage at this point: + * + * R0 = guest last inst + * R1 = host R1 + * R2 = host R2 + * R3 = guest PC + * R4 = guest MSR + * R5 = guest DAR + * R6 = guest DSISR + * R12 = exit handler id + * R13 = PACA + * PACA.KVM.* = guest * + * + */ /* RFI into the highmem handler */ - mfmsr r0 - ori r0, r0, MSR_IR|MSR_DR|MSR_RI /* Enable paging */ - mtsrr1 r0 - ld r0, PACASAVEDMSR(r13) /* Highmem handler address */ - mtsrr0 r0 - - mfspr r0, SPRN_SPRG_SCRATCH0 + mfmsr r7 + ori r7, r7, MSR_IR|MSR_DR|MSR_RI /* Enable paging */ + mtsrr1 r7 + ld r8, PACA_KVM_VMHANDLER(r13) /* Highmem handler address */ + mtsrr0 r8 RFI kvmppc_handler_trampoline_exit_end: diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 06f5a9ecc42..4d686cc6b26 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -69,10 +69,10 @@ void kvmppc_dump_vcpu(struct kvm_vcpu *vcpu) for (i = 0; i < 32; i += 4) { printk("gpr%02d: %08lx %08lx %08lx %08lx\n", i, - vcpu->arch.gpr[i], - vcpu->arch.gpr[i+1], - vcpu->arch.gpr[i+2], - vcpu->arch.gpr[i+3]); + kvmppc_get_gpr(vcpu, i), + kvmppc_get_gpr(vcpu, i+1), + kvmppc_get_gpr(vcpu, i+2), + kvmppc_get_gpr(vcpu, i+3)); } } @@ -82,8 +82,32 @@ static void kvmppc_booke_queue_irqprio(struct kvm_vcpu *vcpu, set_bit(priority, &vcpu->arch.pending_exceptions); } -void kvmppc_core_queue_program(struct kvm_vcpu *vcpu) +static void kvmppc_core_queue_dtlb_miss(struct kvm_vcpu *vcpu, + ulong dear_flags, ulong esr_flags) { + vcpu->arch.queued_dear = dear_flags; + vcpu->arch.queued_esr = esr_flags; + kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_DTLB_MISS); +} + +static void kvmppc_core_queue_data_storage(struct kvm_vcpu *vcpu, + ulong dear_flags, ulong esr_flags) +{ + vcpu->arch.queued_dear = dear_flags; + vcpu->arch.queued_esr = esr_flags; + kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_DATA_STORAGE); +} + +static void kvmppc_core_queue_inst_storage(struct kvm_vcpu *vcpu, + ulong esr_flags) +{ + vcpu->arch.queued_esr = esr_flags; + kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_INST_STORAGE); +} + +void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong esr_flags) +{ + vcpu->arch.queued_esr = esr_flags; kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_PROGRAM); } @@ -97,6 +121,11 @@ int kvmppc_core_pending_dec(struct kvm_vcpu *vcpu) return test_bit(BOOKE_IRQPRIO_DECREMENTER, &vcpu->arch.pending_exceptions); } +void kvmppc_core_dequeue_dec(struct kvm_vcpu *vcpu) +{ + clear_bit(BOOKE_IRQPRIO_DECREMENTER, &vcpu->arch.pending_exceptions); +} + void kvmppc_core_queue_external(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq) { @@ -109,14 +138,19 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu, { int allowed = 0; ulong msr_mask; + bool update_esr = false, update_dear = false; switch (priority) { - case BOOKE_IRQPRIO_PROGRAM: case BOOKE_IRQPRIO_DTLB_MISS: - case BOOKE_IRQPRIO_ITLB_MISS: - case BOOKE_IRQPRIO_SYSCALL: case BOOKE_IRQPRIO_DATA_STORAGE: + update_dear = true; + /* fall through */ case BOOKE_IRQPRIO_INST_STORAGE: + case BOOKE_IRQPRIO_PROGRAM: + update_esr = true; + /* fall through */ + case BOOKE_IRQPRIO_ITLB_MISS: + case BOOKE_IRQPRIO_SYSCALL: case BOOKE_IRQPRIO_FP_UNAVAIL: case BOOKE_IRQPRIO_SPE_UNAVAIL: case BOOKE_IRQPRIO_SPE_FP_DATA: @@ -151,6 +185,10 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu, vcpu->arch.srr0 = vcpu->arch.pc; vcpu->arch.srr1 = vcpu->arch.msr; vcpu->arch.pc = vcpu->arch.ivpr | vcpu->arch.ivor[priority]; + if (update_esr == true) + vcpu->arch.esr = vcpu->arch.queued_esr; + if (update_dear == true) + vcpu->arch.dear = vcpu->arch.queued_dear; kvmppc_set_msr(vcpu, vcpu->arch.msr & msr_mask); clear_bit(priority, &vcpu->arch.pending_exceptions); @@ -223,8 +261,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, if (vcpu->arch.msr & MSR_PR) { /* Program traps generated by user-level software must be handled * by the guest kernel. */ - vcpu->arch.esr = vcpu->arch.fault_esr; - kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_PROGRAM); + kvmppc_core_queue_program(vcpu, vcpu->arch.fault_esr); r = RESUME_GUEST; kvmppc_account_exit(vcpu, USR_PR_INST); break; @@ -280,16 +317,14 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, break; case BOOKE_INTERRUPT_DATA_STORAGE: - vcpu->arch.dear = vcpu->arch.fault_dear; - vcpu->arch.esr = vcpu->arch.fault_esr; - kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_DATA_STORAGE); + kvmppc_core_queue_data_storage(vcpu, vcpu->arch.fault_dear, + vcpu->arch.fault_esr); kvmppc_account_exit(vcpu, DSI_EXITS); r = RESUME_GUEST; break; case BOOKE_INTERRUPT_INST_STORAGE: - vcpu->arch.esr = vcpu->arch.fault_esr; - kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_INST_STORAGE); + kvmppc_core_queue_inst_storage(vcpu, vcpu->arch.fault_esr); kvmppc_account_exit(vcpu, ISI_EXITS); r = RESUME_GUEST; break; @@ -310,9 +345,9 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, gtlb_index = kvmppc_mmu_dtlb_index(vcpu, eaddr); if (gtlb_index < 0) { /* The guest didn't have a mapping for it. */ - kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_DTLB_MISS); - vcpu->arch.dear = vcpu->arch.fault_dear; - vcpu->arch.esr = vcpu->arch.fault_esr; + kvmppc_core_queue_dtlb_miss(vcpu, + vcpu->arch.fault_dear, + vcpu->arch.fault_esr); kvmppc_mmu_dtlb_miss(vcpu); kvmppc_account_exit(vcpu, DTLB_REAL_MISS_EXITS); r = RESUME_GUEST; @@ -426,7 +461,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) { vcpu->arch.pc = 0; vcpu->arch.msr = 0; - vcpu->arch.gpr[1] = (16<<20) - 8; /* -8 for the callee-save LR slot */ + kvmppc_set_gpr(vcpu, 1, (16<<20) - 8); /* -8 for the callee-save LR slot */ vcpu->arch.shadow_pid = 1; @@ -444,10 +479,10 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) int i; regs->pc = vcpu->arch.pc; - regs->cr = vcpu->arch.cr; + regs->cr = kvmppc_get_cr(vcpu); regs->ctr = vcpu->arch.ctr; regs->lr = vcpu->arch.lr; - regs->xer = vcpu->arch.xer; + regs->xer = kvmppc_get_xer(vcpu); regs->msr = vcpu->arch.msr; regs->srr0 = vcpu->arch.srr0; regs->srr1 = vcpu->arch.srr1; @@ -461,7 +496,7 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) regs->sprg7 = vcpu->arch.sprg6; for (i = 0; i < ARRAY_SIZE(regs->gpr); i++) - regs->gpr[i] = vcpu->arch.gpr[i]; + regs->gpr[i] = kvmppc_get_gpr(vcpu, i); return 0; } @@ -471,10 +506,10 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) int i; vcpu->arch.pc = regs->pc; - vcpu->arch.cr = regs->cr; + kvmppc_set_cr(vcpu, regs->cr); vcpu->arch.ctr = regs->ctr; vcpu->arch.lr = regs->lr; - vcpu->arch.xer = regs->xer; + kvmppc_set_xer(vcpu, regs->xer); kvmppc_set_msr(vcpu, regs->msr); vcpu->arch.srr0 = regs->srr0; vcpu->arch.srr1 = regs->srr1; @@ -486,8 +521,8 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) vcpu->arch.sprg6 = regs->sprg5; vcpu->arch.sprg7 = regs->sprg6; - for (i = 0; i < ARRAY_SIZE(vcpu->arch.gpr); i++) - vcpu->arch.gpr[i] = regs->gpr[i]; + for (i = 0; i < ARRAY_SIZE(regs->gpr); i++) + kvmppc_set_gpr(vcpu, i, regs->gpr[i]); return 0; } diff --git a/arch/powerpc/kvm/booke_emulate.c b/arch/powerpc/kvm/booke_emulate.c index aebc65e93f4..cbc790ee192 100644 --- a/arch/powerpc/kvm/booke_emulate.c +++ b/arch/powerpc/kvm/booke_emulate.c @@ -62,20 +62,20 @@ int kvmppc_booke_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, case OP_31_XOP_MFMSR: rt = get_rt(inst); - vcpu->arch.gpr[rt] = vcpu->arch.msr; + kvmppc_set_gpr(vcpu, rt, vcpu->arch.msr); kvmppc_set_exit_type(vcpu, EMULATED_MFMSR_EXITS); break; case OP_31_XOP_MTMSR: rs = get_rs(inst); kvmppc_set_exit_type(vcpu, EMULATED_MTMSR_EXITS); - kvmppc_set_msr(vcpu, vcpu->arch.gpr[rs]); + kvmppc_set_msr(vcpu, kvmppc_get_gpr(vcpu, rs)); break; case OP_31_XOP_WRTEE: rs = get_rs(inst); vcpu->arch.msr = (vcpu->arch.msr & ~MSR_EE) - | (vcpu->arch.gpr[rs] & MSR_EE); + | (kvmppc_get_gpr(vcpu, rs) & MSR_EE); kvmppc_set_exit_type(vcpu, EMULATED_WRTEE_EXITS); break; @@ -101,22 +101,23 @@ int kvmppc_booke_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs) { int emulated = EMULATE_DONE; + ulong spr_val = kvmppc_get_gpr(vcpu, rs); switch (sprn) { case SPRN_DEAR: - vcpu->arch.dear = vcpu->arch.gpr[rs]; break; + vcpu->arch.dear = spr_val; break; case SPRN_ESR: - vcpu->arch.esr = vcpu->arch.gpr[rs]; break; + vcpu->arch.esr = spr_val; break; case SPRN_DBCR0: - vcpu->arch.dbcr0 = vcpu->arch.gpr[rs]; break; + vcpu->arch.dbcr0 = spr_val; break; case SPRN_DBCR1: - vcpu->arch.dbcr1 = vcpu->arch.gpr[rs]; break; + vcpu->arch.dbcr1 = spr_val; break; case SPRN_DBSR: - vcpu->arch.dbsr &= ~vcpu->arch.gpr[rs]; break; + vcpu->arch.dbsr &= ~spr_val; break; case SPRN_TSR: - vcpu->arch.tsr &= ~vcpu->arch.gpr[rs]; break; + vcpu->arch.tsr &= ~spr_val; break; case SPRN_TCR: - vcpu->arch.tcr = vcpu->arch.gpr[rs]; + vcpu->arch.tcr = spr_val; kvmppc_emulate_dec(vcpu); break; @@ -124,64 +125,64 @@ int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs) * loaded into the real SPRGs when resuming the * guest. */ case SPRN_SPRG4: - vcpu->arch.sprg4 = vcpu->arch.gpr[rs]; break; + vcpu->arch.sprg4 = spr_val; break; case SPRN_SPRG5: - vcpu->arch.sprg5 = vcpu->arch.gpr[rs]; break; + vcpu->arch.sprg5 = spr_val; break; case SPRN_SPRG6: - vcpu->arch.sprg6 = vcpu->arch.gpr[rs]; break; + vcpu->arch.sprg6 = spr_val; break; case SPRN_SPRG7: - vcpu->arch.sprg7 = vcpu->arch.gpr[rs]; break; + vcpu->arch.sprg7 = spr_val; break; case SPRN_IVPR: - vcpu->arch.ivpr = vcpu->arch.gpr[rs]; + vcpu->arch.ivpr = spr_val; break; case SPRN_IVOR0: - vcpu->arch.ivor[BOOKE_IRQPRIO_CRITICAL] = vcpu->arch.gpr[rs]; + vcpu->arch.ivor[BOOKE_IRQPRIO_CRITICAL] = spr_val; break; case SPRN_IVOR1: - vcpu->arch.ivor[BOOKE_IRQPRIO_MACHINE_CHECK] = vcpu->arch.gpr[rs]; + vcpu->arch.ivor[BOOKE_IRQPRIO_MACHINE_CHECK] = spr_val; break; case SPRN_IVOR2: - vcpu->arch.ivor[BOOKE_IRQPRIO_DATA_STORAGE] = vcpu->arch.gpr[rs]; + vcpu->arch.ivor[BOOKE_IRQPRIO_DATA_STORAGE] = spr_val; break; case SPRN_IVOR3: - vcpu->arch.ivor[BOOKE_IRQPRIO_INST_STORAGE] = vcpu->arch.gpr[rs]; + vcpu->arch.ivor[BOOKE_IRQPRIO_INST_STORAGE] = spr_val; break; case SPRN_IVOR4: - vcpu->arch.ivor[BOOKE_IRQPRIO_EXTERNAL] = vcpu->arch.gpr[rs]; + vcpu->arch.ivor[BOOKE_IRQPRIO_EXTERNAL] = spr_val; break; case SPRN_IVOR5: - vcpu->arch.ivor[BOOKE_IRQPRIO_ALIGNMENT] = vcpu->arch.gpr[rs]; + vcpu->arch.ivor[BOOKE_IRQPRIO_ALIGNMENT] = spr_val; break; case SPRN_IVOR6: - vcpu->arch.ivor[BOOKE_IRQPRIO_PROGRAM] = vcpu->arch.gpr[rs]; + vcpu->arch.ivor[BOOKE_IRQPRIO_PROGRAM] = spr_val; break; case SPRN_IVOR7: - vcpu->arch.ivor[BOOKE_IRQPRIO_FP_UNAVAIL] = vcpu->arch.gpr[rs]; + vcpu->arch.ivor[BOOKE_IRQPRIO_FP_UNAVAIL] = spr_val; break; case SPRN_IVOR8: - vcpu->arch.ivor[BOOKE_IRQPRIO_SYSCALL] = vcpu->arch.gpr[rs]; + vcpu->arch.ivor[BOOKE_IRQPRIO_SYSCALL] = spr_val; break; case SPRN_IVOR9: - vcpu->arch.ivor[BOOKE_IRQPRIO_AP_UNAVAIL] = vcpu->arch.gpr[rs]; + vcpu->arch.ivor[BOOKE_IRQPRIO_AP_UNAVAIL] = spr_val; break; case SPRN_IVOR10: - vcpu->arch.ivor[BOOKE_IRQPRIO_DECREMENTER] = vcpu->arch.gpr[rs]; + vcpu->arch.ivor[BOOKE_IRQPRIO_DECREMENTER] = spr_val; break; case SPRN_IVOR11: - vcpu->arch.ivor[BOOKE_IRQPRIO_FIT] = vcpu->arch.gpr[rs]; + vcpu->arch.ivor[BOOKE_IRQPRIO_FIT] = spr_val; break; case SPRN_IVOR12: - vcpu->arch.ivor[BOOKE_IRQPRIO_WATCHDOG] = vcpu->arch.gpr[rs]; + vcpu->arch.ivor[BOOKE_IRQPRIO_WATCHDOG] = spr_val; break; case SPRN_IVOR13: - vcpu->arch.ivor[BOOKE_IRQPRIO_DTLB_MISS] = vcpu->arch.gpr[rs]; + vcpu->arch.ivor[BOOKE_IRQPRIO_DTLB_MISS] = spr_val; break; case SPRN_IVOR14: - vcpu->arch.ivor[BOOKE_IRQPRIO_ITLB_MISS] = vcpu->arch.gpr[rs]; + vcpu->arch.ivor[BOOKE_IRQPRIO_ITLB_MISS] = spr_val; break; case SPRN_IVOR15: - vcpu->arch.ivor[BOOKE_IRQPRIO_DEBUG] = vcpu->arch.gpr[rs]; + vcpu->arch.ivor[BOOKE_IRQPRIO_DEBUG] = spr_val; break; default: @@ -197,65 +198,65 @@ int kvmppc_booke_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt) switch (sprn) { case SPRN_IVPR: - vcpu->arch.gpr[rt] = vcpu->arch.ivpr; break; + kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivpr); break; case SPRN_DEAR: - vcpu->arch.gpr[rt] = vcpu->arch.dear; break; + kvmppc_set_gpr(vcpu, rt, vcpu->arch.dear); break; case SPRN_ESR: - vcpu->arch.gpr[rt] = vcpu->arch.esr; break; + kvmppc_set_gpr(vcpu, rt, vcpu->arch.esr); break; case SPRN_DBCR0: - vcpu->arch.gpr[rt] = vcpu->arch.dbcr0; break; + kvmppc_set_gpr(vcpu, rt, vcpu->arch.dbcr0); break; case SPRN_DBCR1: - vcpu->arch.gpr[rt] = vcpu->arch.dbcr1; break; + kvmppc_set_gpr(vcpu, rt, vcpu->arch.dbcr1); break; case SPRN_DBSR: - vcpu->arch.gpr[rt] = vcpu->arch.dbsr; break; + kvmppc_set_gpr(vcpu, rt, vcpu->arch.dbsr); break; case SPRN_IVOR0: - vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_CRITICAL]; + kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_CRITICAL]); break; case SPRN_IVOR1: - vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_MACHINE_CHECK]; + kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_MACHINE_CHECK]); break; case SPRN_IVOR2: - vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_DATA_STORAGE]; + kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_DATA_STORAGE]); break; case SPRN_IVOR3: - vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_INST_STORAGE]; + kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_INST_STORAGE]); break; case SPRN_IVOR4: - vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_EXTERNAL]; + kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_EXTERNAL]); break; case SPRN_IVOR5: - vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_ALIGNMENT]; + kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_ALIGNMENT]); break; case SPRN_IVOR6: - vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_PROGRAM]; + kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_PROGRAM]); break; case SPRN_IVOR7: - vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_FP_UNAVAIL]; + kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_FP_UNAVAIL]); break; case SPRN_IVOR8: - vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_SYSCALL]; + kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_SYSCALL]); break; case SPRN_IVOR9: - vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_AP_UNAVAIL]; + kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_AP_UNAVAIL]); break; case SPRN_IVOR10: - vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_DECREMENTER]; + kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_DECREMENTER]); break; case SPRN_IVOR11: - vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_FIT]; + kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_FIT]); break; case SPRN_IVOR12: - vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_WATCHDOG]; + kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_WATCHDOG]); break; case SPRN_IVOR13: - vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_DTLB_MISS]; + kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_DTLB_MISS]); break; case SPRN_IVOR14: - vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_ITLB_MISS]; + kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_ITLB_MISS]); break; case SPRN_IVOR15: - vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_DEBUG]; + kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_DEBUG]); break; default: diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c index 64949eef43f..efa1198940a 100644 --- a/arch/powerpc/kvm/e500.c +++ b/arch/powerpc/kvm/e500.c @@ -60,6 +60,12 @@ int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu) kvmppc_e500_tlb_setup(vcpu_e500); + /* Registers init */ + vcpu->arch.pvr = mfspr(SPRN_PVR); + + /* Since booke kvm only support one core, update all vcpus' PIR to 0 */ + vcpu->vcpu_id = 0; + return 0; } diff --git a/arch/powerpc/kvm/e500_emulate.c b/arch/powerpc/kvm/e500_emulate.c index be95b8d8e3b..8e3edfbc963 100644 --- a/arch/powerpc/kvm/e500_emulate.c +++ b/arch/powerpc/kvm/e500_emulate.c @@ -74,54 +74,59 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs) { struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu); int emulated = EMULATE_DONE; + ulong spr_val = kvmppc_get_gpr(vcpu, rs); switch (sprn) { case SPRN_PID: vcpu_e500->pid[0] = vcpu->arch.shadow_pid = - vcpu->arch.pid = vcpu->arch.gpr[rs]; + vcpu->arch.pid = spr_val; break; case SPRN_PID1: - vcpu_e500->pid[1] = vcpu->arch.gpr[rs]; break; + vcpu_e500->pid[1] = spr_val; break; case SPRN_PID2: - vcpu_e500->pid[2] = vcpu->arch.gpr[rs]; break; + vcpu_e500->pid[2] = spr_val; break; case SPRN_MAS0: - vcpu_e500->mas0 = vcpu->arch.gpr[rs]; break; + vcpu_e500->mas0 = spr_val; break; case SPRN_MAS1: - vcpu_e500->mas1 = vcpu->arch.gpr[rs]; break; + vcpu_e500->mas1 = spr_val; break; case SPRN_MAS2: - vcpu_e500->mas2 = vcpu->arch.gpr[rs]; break; + vcpu_e500->mas2 = spr_val; break; case SPRN_MAS3: - vcpu_e500->mas3 = vcpu->arch.gpr[rs]; break; + vcpu_e500->mas3 = spr_val; break; case SPRN_MAS4: - vcpu_e500->mas4 = vcpu->arch.gpr[rs]; break; + vcpu_e500->mas4 = spr_val; break; case SPRN_MAS6: - vcpu_e500->mas6 = vcpu->arch.gpr[rs]; break; + vcpu_e500->mas6 = spr_val; break; case SPRN_MAS7: - vcpu_e500->mas7 = vcpu->arch.gpr[rs]; break; + vcpu_e500->mas7 = spr_val; break; + case SPRN_L1CSR0: + vcpu_e500->l1csr0 = spr_val; + vcpu_e500->l1csr0 &= ~(L1CSR0_DCFI | L1CSR0_CLFC); + break; case SPRN_L1CSR1: - vcpu_e500->l1csr1 = vcpu->arch.gpr[rs]; break; + vcpu_e500->l1csr1 = spr_val; break; case SPRN_HID0: - vcpu_e500->hid0 = vcpu->arch.gpr[rs]; break; + vcpu_e500->hid0 = spr_val; break; case SPRN_HID1: - vcpu_e500->hid1 = vcpu->arch.gpr[rs]; break; + vcpu_e500->hid1 = spr_val; break; case SPRN_MMUCSR0: emulated = kvmppc_e500_emul_mt_mmucsr0(vcpu_e500, - vcpu->arch.gpr[rs]); + spr_val); break; /* extra exceptions */ case SPRN_IVOR32: - vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_UNAVAIL] = vcpu->arch.gpr[rs]; + vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_UNAVAIL] = spr_val; break; case SPRN_IVOR33: - vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_DATA] = vcpu->arch.gpr[rs]; + vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_DATA] = spr_val; break; case SPRN_IVOR34: - vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_ROUND] = vcpu->arch.gpr[rs]; + vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_ROUND] = spr_val; break; case SPRN_IVOR35: - vcpu->arch.ivor[BOOKE_IRQPRIO_PERFORMANCE_MONITOR] = vcpu->arch.gpr[rs]; + vcpu->arch.ivor[BOOKE_IRQPRIO_PERFORMANCE_MONITOR] = spr_val; break; default: @@ -138,63 +143,57 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt) switch (sprn) { case SPRN_PID: - vcpu->arch.gpr[rt] = vcpu_e500->pid[0]; break; + kvmppc_set_gpr(vcpu, rt, vcpu_e500->pid[0]); break; case SPRN_PID1: - vcpu->arch.gpr[rt] = vcpu_e500->pid[1]; break; + kvmppc_set_gpr(vcpu, rt, vcpu_e500->pid[1]); break; case SPRN_PID2: - vcpu->arch.gpr[rt] = vcpu_e500->pid[2]; break; + kvmppc_set_gpr(vcpu, rt, vcpu_e500->pid[2]); break; case SPRN_MAS0: - vcpu->arch.gpr[rt] = vcpu_e500->mas0; break; + kvmppc_set_gpr(vcpu, rt, vcpu_e500->mas0); break; case SPRN_MAS1: - vcpu->arch.gpr[rt] = vcpu_e500->mas1; break; + kvmppc_set_gpr(vcpu, rt, vcpu_e500->mas1); break; case SPRN_MAS2: - vcpu->arch.gpr[rt] = vcpu_e500->mas2; break; + kvmppc_set_gpr(vcpu, rt, vcpu_e500->mas2); break; case SPRN_MAS3: - vcpu->arch.gpr[rt] = vcpu_e500->mas3; break; + kvmppc_set_gpr(vcpu, rt, vcpu_e500->mas3); break; case SPRN_MAS4: - vcpu->arch.gpr[rt] = vcpu_e500->mas4; break; + kvmppc_set_gpr(vcpu, rt, vcpu_e500->mas4); break; case SPRN_MAS6: - vcpu->arch.gpr[rt] = vcpu_e500->mas6; break; + kvmppc_set_gpr(vcpu, rt, vcpu_e500->mas6); break; case SPRN_MAS7: - vcpu->arch.gpr[rt] = vcpu_e500->mas7; break; + kvmppc_set_gpr(vcpu, rt, vcpu_e500->mas7); break; case SPRN_TLB0CFG: - vcpu->arch.gpr[rt] = mfspr(SPRN_TLB0CFG); - vcpu->arch.gpr[rt] &= ~0xfffUL; - vcpu->arch.gpr[rt] |= vcpu_e500->guest_tlb_size[0]; - break; - + kvmppc_set_gpr(vcpu, rt, vcpu_e500->tlb0cfg); break; case SPRN_TLB1CFG: - vcpu->arch.gpr[rt] = mfspr(SPRN_TLB1CFG); - vcpu->arch.gpr[rt] &= ~0xfffUL; - vcpu->arch.gpr[rt] |= vcpu_e500->guest_tlb_size[1]; - break; - + kvmppc_set_gpr(vcpu, rt, vcpu_e500->tlb1cfg); break; + case SPRN_L1CSR0: + kvmppc_set_gpr(vcpu, rt, vcpu_e500->l1csr0); break; case SPRN_L1CSR1: - vcpu->arch.gpr[rt] = vcpu_e500->l1csr1; break; + kvmppc_set_gpr(vcpu, rt, vcpu_e500->l1csr1); break; case SPRN_HID0: - vcpu->arch.gpr[rt] = vcpu_e500->hid0; break; + kvmppc_set_gpr(vcpu, rt, vcpu_e500->hid0); break; case SPRN_HID1: - vcpu->arch.gpr[rt] = vcpu_e500->hid1; break; + kvmppc_set_gpr(vcpu, rt, vcpu_e500->hid1); break; case SPRN_MMUCSR0: - vcpu->arch.gpr[rt] = 0; break; + kvmppc_set_gpr(vcpu, rt, 0); break; case SPRN_MMUCFG: - vcpu->arch.gpr[rt] = mfspr(SPRN_MMUCFG); break; + kvmppc_set_gpr(vcpu, rt, mfspr(SPRN_MMUCFG)); break; /* extra exceptions */ case SPRN_IVOR32: - vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_UNAVAIL]; + kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_UNAVAIL]); break; case SPRN_IVOR33: - vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_DATA]; + kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_DATA]); break; case SPRN_IVOR34: - vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_ROUND]; + kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_ROUND]); break; case SPRN_IVOR35: - vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_PERFORMANCE_MONITOR]; + kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_PERFORMANCE_MONITOR]); break; default: emulated = kvmppc_booke_emulate_mfspr(vcpu, sprn, rt); diff --git a/arch/powerpc/kvm/e500_tlb.c b/arch/powerpc/kvm/e500_tlb.c index fb1e1dc11ba..0d772e6b631 100644 --- a/arch/powerpc/kvm/e500_tlb.c +++ b/arch/powerpc/kvm/e500_tlb.c @@ -417,7 +417,7 @@ int kvmppc_e500_emul_tlbivax(struct kvm_vcpu *vcpu, int ra, int rb) int esel, tlbsel; gva_t ea; - ea = ((ra) ? vcpu->arch.gpr[ra] : 0) + vcpu->arch.gpr[rb]; + ea = ((ra) ? kvmppc_get_gpr(vcpu, ra) : 0) + kvmppc_get_gpr(vcpu, rb); ia = (ea >> 2) & 0x1; @@ -470,7 +470,7 @@ int kvmppc_e500_emul_tlbsx(struct kvm_vcpu *vcpu, int rb) struct tlbe *gtlbe = NULL; gva_t ea; - ea = vcpu->arch.gpr[rb]; + ea = kvmppc_get_gpr(vcpu, rb); for (tlbsel = 0; tlbsel < 2; tlbsel++) { esel = kvmppc_e500_tlb_index(vcpu_e500, ea, tlbsel, pid, as); @@ -728,6 +728,12 @@ int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500) if (vcpu_e500->shadow_pages[1] == NULL) goto err_out_page0; + /* Init TLB configuration register */ + vcpu_e500->tlb0cfg = mfspr(SPRN_TLB0CFG) & ~0xfffUL; + vcpu_e500->tlb0cfg |= vcpu_e500->guest_tlb_size[0]; + vcpu_e500->tlb1cfg = mfspr(SPRN_TLB1CFG) & ~0xfffUL; + vcpu_e500->tlb1cfg |= vcpu_e500->guest_tlb_size[1]; + return 0; err_out_page0: diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c index 4a9ac6640fa..cb72a65f4ec 100644 --- a/arch/powerpc/kvm/emulate.c +++ b/arch/powerpc/kvm/emulate.c @@ -83,6 +83,9 @@ void kvmppc_emulate_dec(struct kvm_vcpu *vcpu) pr_debug("mtDEC: %x\n", vcpu->arch.dec); #ifdef CONFIG_PPC64 + /* mtdec lowers the interrupt line when positive. */ + kvmppc_core_dequeue_dec(vcpu); + /* POWER4+ triggers a dec interrupt if the value is < 0 */ if (vcpu->arch.dec & 0x80000000) { hrtimer_try_to_cancel(&vcpu->arch.dec_timer); @@ -140,14 +143,18 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) pr_debug(KERN_INFO "Emulating opcode %d / %d\n", get_op(inst), get_xop(inst)); + /* Try again next time */ + if (inst == KVM_INST_FETCH_FAILED) + return EMULATE_DONE; + switch (get_op(inst)) { case OP_TRAP: #ifdef CONFIG_PPC64 case OP_TRAP_64: + kvmppc_core_queue_program(vcpu, SRR1_PROGTRAP); #else - vcpu->arch.esr |= ESR_PTR; + kvmppc_core_queue_program(vcpu, vcpu->arch.esr | ESR_PTR); #endif - kvmppc_core_queue_program(vcpu); advance = 0; break; @@ -167,14 +174,14 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) case OP_31_XOP_STWX: rs = get_rs(inst); emulated = kvmppc_handle_store(run, vcpu, - vcpu->arch.gpr[rs], + kvmppc_get_gpr(vcpu, rs), 4, 1); break; case OP_31_XOP_STBX: rs = get_rs(inst); emulated = kvmppc_handle_store(run, vcpu, - vcpu->arch.gpr[rs], + kvmppc_get_gpr(vcpu, rs), 1, 1); break; @@ -183,14 +190,14 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) ra = get_ra(inst); rb = get_rb(inst); - ea = vcpu->arch.gpr[rb]; + ea = kvmppc_get_gpr(vcpu, rb); if (ra) - ea += vcpu->arch.gpr[ra]; + ea += kvmppc_get_gpr(vcpu, ra); emulated = kvmppc_handle_store(run, vcpu, - vcpu->arch.gpr[rs], + kvmppc_get_gpr(vcpu, rs), 1, 1); - vcpu->arch.gpr[rs] = ea; + kvmppc_set_gpr(vcpu, rs, ea); break; case OP_31_XOP_LHZX: @@ -203,12 +210,12 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) ra = get_ra(inst); rb = get_rb(inst); - ea = vcpu->arch.gpr[rb]; + ea = kvmppc_get_gpr(vcpu, rb); if (ra) - ea += vcpu->arch.gpr[ra]; + ea += kvmppc_get_gpr(vcpu, ra); emulated = kvmppc_handle_load(run, vcpu, rt, 2, 1); - vcpu->arch.gpr[ra] = ea; + kvmppc_set_gpr(vcpu, ra, ea); break; case OP_31_XOP_MFSPR: @@ -217,47 +224,49 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) switch (sprn) { case SPRN_SRR0: - vcpu->arch.gpr[rt] = vcpu->arch.srr0; break; + kvmppc_set_gpr(vcpu, rt, vcpu->arch.srr0); break; case SPRN_SRR1: - vcpu->arch.gpr[rt] = vcpu->arch.srr1; break; + kvmppc_set_gpr(vcpu, rt, vcpu->arch.srr1); break; case SPRN_PVR: - vcpu->arch.gpr[rt] = vcpu->arch.pvr; break; + kvmppc_set_gpr(vcpu, rt, vcpu->arch.pvr); break; case SPRN_PIR: - vcpu->arch.gpr[rt] = vcpu->vcpu_id; break; + kvmppc_set_gpr(vcpu, rt, vcpu->vcpu_id); break; case SPRN_MSSSR0: - vcpu->arch.gpr[rt] = 0; break; + kvmppc_set_gpr(vcpu, rt, 0); break; /* Note: mftb and TBRL/TBWL are user-accessible, so * the guest can always access the real TB anyways. * In fact, we probably will never see these traps. */ case SPRN_TBWL: - vcpu->arch.gpr[rt] = get_tb() >> 32; break; + kvmppc_set_gpr(vcpu, rt, get_tb() >> 32); break; case SPRN_TBWU: - vcpu->arch.gpr[rt] = get_tb(); break; + kvmppc_set_gpr(vcpu, rt, get_tb()); break; case SPRN_SPRG0: - vcpu->arch.gpr[rt] = vcpu->arch.sprg0; break; + kvmppc_set_gpr(vcpu, rt, vcpu->arch.sprg0); break; case SPRN_SPRG1: - vcpu->arch.gpr[rt] = vcpu->arch.sprg1; break; + kvmppc_set_gpr(vcpu, rt, vcpu->arch.sprg1); break; case SPRN_SPRG2: - vcpu->arch.gpr[rt] = vcpu->arch.sprg2; break; + kvmppc_set_gpr(vcpu, rt, vcpu->arch.sprg2); break; case SPRN_SPRG3: - vcpu->arch.gpr[rt] = vcpu->arch.sprg3; break; + kvmppc_set_gpr(vcpu, rt, vcpu->arch.sprg3); break; /* Note: SPRG4-7 are user-readable, so we don't get * a trap. */ case SPRN_DEC: { u64 jd = get_tb() - vcpu->arch.dec_jiffies; - vcpu->arch.gpr[rt] = vcpu->arch.dec - jd; - pr_debug(KERN_INFO "mfDEC: %x - %llx = %lx\n", vcpu->arch.dec, jd, vcpu->arch.gpr[rt]); + kvmppc_set_gpr(vcpu, rt, vcpu->arch.dec - jd); + pr_debug(KERN_INFO "mfDEC: %x - %llx = %lx\n", + vcpu->arch.dec, jd, + kvmppc_get_gpr(vcpu, rt)); break; } default: emulated = kvmppc_core_emulate_mfspr(vcpu, sprn, rt); if (emulated == EMULATE_FAIL) { printk("mfspr: unknown spr %x\n", sprn); - vcpu->arch.gpr[rt] = 0; + kvmppc_set_gpr(vcpu, rt, 0); } break; } @@ -269,7 +278,7 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) rb = get_rb(inst); emulated = kvmppc_handle_store(run, vcpu, - vcpu->arch.gpr[rs], + kvmppc_get_gpr(vcpu, rs), 2, 1); break; @@ -278,14 +287,14 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) ra = get_ra(inst); rb = get_rb(inst); - ea = vcpu->arch.gpr[rb]; + ea = kvmppc_get_gpr(vcpu, rb); if (ra) - ea += vcpu->arch.gpr[ra]; + ea += kvmppc_get_gpr(vcpu, ra); emulated = kvmppc_handle_store(run, vcpu, - vcpu->arch.gpr[rs], + kvmppc_get_gpr(vcpu, rs), 2, 1); - vcpu->arch.gpr[ra] = ea; + kvmppc_set_gpr(vcpu, ra, ea); break; case OP_31_XOP_MTSPR: @@ -293,9 +302,9 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) rs = get_rs(inst); switch (sprn) { case SPRN_SRR0: - vcpu->arch.srr0 = vcpu->arch.gpr[rs]; break; + vcpu->arch.srr0 = kvmppc_get_gpr(vcpu, rs); break; case SPRN_SRR1: - vcpu->arch.srr1 = vcpu->arch.gpr[rs]; break; + vcpu->arch.srr1 = kvmppc_get_gpr(vcpu, rs); break; /* XXX We need to context-switch the timebase for * watchdog and FIT. */ @@ -305,18 +314,18 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) case SPRN_MSSSR0: break; case SPRN_DEC: - vcpu->arch.dec = vcpu->arch.gpr[rs]; + vcpu->arch.dec = kvmppc_get_gpr(vcpu, rs); kvmppc_emulate_dec(vcpu); break; case SPRN_SPRG0: - vcpu->arch.sprg0 = vcpu->arch.gpr[rs]; break; + vcpu->arch.sprg0 = kvmppc_get_gpr(vcpu, rs); break; case SPRN_SPRG1: - vcpu->arch.sprg1 = vcpu->arch.gpr[rs]; break; + vcpu->arch.sprg1 = kvmppc_get_gpr(vcpu, rs); break; case SPRN_SPRG2: - vcpu->arch.sprg2 = vcpu->arch.gpr[rs]; break; + vcpu->arch.sprg2 = kvmppc_get_gpr(vcpu, rs); break; case SPRN_SPRG3: - vcpu->arch.sprg3 = vcpu->arch.gpr[rs]; break; + vcpu->arch.sprg3 = kvmppc_get_gpr(vcpu, rs); break; default: emulated = kvmppc_core_emulate_mtspr(vcpu, sprn, rs); @@ -348,7 +357,7 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) rb = get_rb(inst); emulated = kvmppc_handle_store(run, vcpu, - vcpu->arch.gpr[rs], + kvmppc_get_gpr(vcpu, rs), 4, 0); break; @@ -363,7 +372,7 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) rb = get_rb(inst); emulated = kvmppc_handle_store(run, vcpu, - vcpu->arch.gpr[rs], + kvmppc_get_gpr(vcpu, rs), 2, 0); break; @@ -382,7 +391,7 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) ra = get_ra(inst); rt = get_rt(inst); emulated = kvmppc_handle_load(run, vcpu, rt, 4, 1); - vcpu->arch.gpr[ra] = vcpu->arch.paddr_accessed; + kvmppc_set_gpr(vcpu, ra, vcpu->arch.paddr_accessed); break; case OP_LBZ: @@ -394,35 +403,39 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) ra = get_ra(inst); rt = get_rt(inst); emulated = kvmppc_handle_load(run, vcpu, rt, 1, 1); - vcpu->arch.gpr[ra] = vcpu->arch.paddr_accessed; + kvmppc_set_gpr(vcpu, ra, vcpu->arch.paddr_accessed); break; case OP_STW: rs = get_rs(inst); - emulated = kvmppc_handle_store(run, vcpu, vcpu->arch.gpr[rs], + emulated = kvmppc_handle_store(run, vcpu, + kvmppc_get_gpr(vcpu, rs), 4, 1); break; case OP_STWU: ra = get_ra(inst); rs = get_rs(inst); - emulated = kvmppc_handle_store(run, vcpu, vcpu->arch.gpr[rs], + emulated = kvmppc_handle_store(run, vcpu, + kvmppc_get_gpr(vcpu, rs), 4, 1); - vcpu->arch.gpr[ra] = vcpu->arch.paddr_accessed; + kvmppc_set_gpr(vcpu, ra, vcpu->arch.paddr_accessed); break; case OP_STB: rs = get_rs(inst); - emulated = kvmppc_handle_store(run, vcpu, vcpu->arch.gpr[rs], + emulated = kvmppc_handle_store(run, vcpu, + kvmppc_get_gpr(vcpu, rs), 1, 1); break; case OP_STBU: ra = get_ra(inst); rs = get_rs(inst); - emulated = kvmppc_handle_store(run, vcpu, vcpu->arch.gpr[rs], + emulated = kvmppc_handle_store(run, vcpu, + kvmppc_get_gpr(vcpu, rs), 1, 1); - vcpu->arch.gpr[ra] = vcpu->arch.paddr_accessed; + kvmppc_set_gpr(vcpu, ra, vcpu->arch.paddr_accessed); break; case OP_LHZ: @@ -434,21 +447,23 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) ra = get_ra(inst); rt = get_rt(inst); emulated = kvmppc_handle_load(run, vcpu, rt, 2, 1); - vcpu->arch.gpr[ra] = vcpu->arch.paddr_accessed; + kvmppc_set_gpr(vcpu, ra, vcpu->arch.paddr_accessed); break; case OP_STH: rs = get_rs(inst); - emulated = kvmppc_handle_store(run, vcpu, vcpu->arch.gpr[rs], + emulated = kvmppc_handle_store(run, vcpu, + kvmppc_get_gpr(vcpu, rs), 2, 1); break; case OP_STHU: ra = get_ra(inst); rs = get_rs(inst); - emulated = kvmppc_handle_store(run, vcpu, vcpu->arch.gpr[rs], + emulated = kvmppc_handle_store(run, vcpu, + kvmppc_get_gpr(vcpu, rs), 2, 1); - vcpu->arch.gpr[ra] = vcpu->arch.paddr_accessed; + kvmppc_set_gpr(vcpu, ra, vcpu->arch.paddr_accessed); break; default: @@ -461,6 +476,7 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) advance = 0; printk(KERN_ERR "Couldn't emulate instruction 0x%08x " "(op %d xop %d)\n", inst, get_op(inst), get_xop(inst)); + kvmppc_core_queue_program(vcpu, 0); } } diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index f06cf93b178..51aedd7f16b 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -137,6 +137,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm) { kvmppc_free_vcpus(kvm); kvm_free_physmem(kvm); + cleanup_srcu_struct(&kvm->srcu); kfree(kvm); } @@ -165,14 +166,24 @@ long kvm_arch_dev_ioctl(struct file *filp, return -EINVAL; } -int kvm_arch_set_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem, - struct kvm_memory_slot old, - int user_alloc) +int kvm_arch_prepare_memory_region(struct kvm *kvm, + struct kvm_memory_slot *memslot, + struct kvm_memory_slot old, + struct kvm_userspace_memory_region *mem, + int user_alloc) { return 0; } +void kvm_arch_commit_memory_region(struct kvm *kvm, + struct kvm_userspace_memory_region *mem, + struct kvm_memory_slot old, + int user_alloc) +{ + return; +} + + void kvm_arch_flush_shadow(struct kvm *kvm) { } @@ -260,34 +271,35 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, static void kvmppc_complete_dcr_load(struct kvm_vcpu *vcpu, struct kvm_run *run) { - ulong *gpr = &vcpu->arch.gpr[vcpu->arch.io_gpr]; - *gpr = run->dcr.data; + kvmppc_set_gpr(vcpu, vcpu->arch.io_gpr, run->dcr.data); } static void kvmppc_complete_mmio_load(struct kvm_vcpu *vcpu, struct kvm_run *run) { - ulong *gpr = &vcpu->arch.gpr[vcpu->arch.io_gpr]; + ulong gpr; - if (run->mmio.len > sizeof(*gpr)) { + if (run->mmio.len > sizeof(gpr)) { printk(KERN_ERR "bad MMIO length: %d\n", run->mmio.len); return; } if (vcpu->arch.mmio_is_bigendian) { switch (run->mmio.len) { - case 4: *gpr = *(u32 *)run->mmio.data; break; - case 2: *gpr = *(u16 *)run->mmio.data; break; - case 1: *gpr = *(u8 *)run->mmio.data; break; + case 4: gpr = *(u32 *)run->mmio.data; break; + case 2: gpr = *(u16 *)run->mmio.data; break; + case 1: gpr = *(u8 *)run->mmio.data; break; } } else { /* Convert BE data from userland back to LE. */ switch (run->mmio.len) { - case 4: *gpr = ld_le32((u32 *)run->mmio.data); break; - case 2: *gpr = ld_le16((u16 *)run->mmio.data); break; - case 1: *gpr = *(u8 *)run->mmio.data; break; + case 4: gpr = ld_le32((u32 *)run->mmio.data); break; + case 2: gpr = ld_le16((u16 *)run->mmio.data); break; + case 1: gpr = *(u8 *)run->mmio.data; break; } } + + kvmppc_set_gpr(vcpu, vcpu->arch.io_gpr, gpr); } int kvmppc_handle_load(struct kvm_run *run, struct kvm_vcpu *vcpu, diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c index 4ec900af332..b1dbd9ee87c 100644 --- a/arch/powerpc/mm/init_32.c +++ b/arch/powerpc/mm/init_32.c @@ -47,7 +47,7 @@ #include "mmu_decl.h" #if defined(CONFIG_KERNEL_START_BOOL) || defined(CONFIG_LOWMEM_SIZE_BOOL) -/* The ammount of lowmem must be within 0xF0000000 - KERNELBASE. */ +/* The amount of lowmem must be within 0xF0000000 - KERNELBASE. */ #if (CONFIG_LOWMEM_SIZE > (0xF0000000 - PAGE_OFFSET)) #error "You must adjust CONFIG_LOWMEM_SIZE or CONFIG_START_KERNEL" #endif diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index b037d95eead..64c00227b99 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -451,7 +451,7 @@ static int __cpuinit numa_setup_cpu(unsigned long lcpu) nid = of_node_to_nid_single(cpu); if (nid < 0 || !node_online(nid)) - nid = any_online_node(NODE_MASK_ALL); + nid = first_online_node; out: map_cpu_to_node(lcpu, nid); @@ -1114,7 +1114,7 @@ int hot_add_scn_to_nid(unsigned long scn_addr) int nid, found = 0; if (!numa_enabled || (min_common_depth < 0)) - return any_online_node(NODE_MASK_ALL); + return first_online_node; memory = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory"); if (memory) { @@ -1125,7 +1125,7 @@ int hot_add_scn_to_nid(unsigned long scn_addr) } if (nid < 0 || !node_online(nid)) - nid = any_online_node(NODE_MASK_ALL); + nid = first_online_node; if (NODE_DATA(nid)->node_spanned_pages) return nid; diff --git a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c index 6f8ebe1085b..072b948b2e2 100644 --- a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c +++ b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c @@ -553,7 +553,7 @@ static ssize_t mpc52xx_wdt_write(struct file *file, const char __user *data, return 0; } -static struct watchdog_info mpc5200_wdt_info = { +static const struct watchdog_info mpc5200_wdt_info = { .options = WDIOF_SETTIMEOUT | WDIOF_KEEPALIVEPING, .identity = WDT_IDENTITY, }; diff --git a/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c b/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c index 9d962d7c72c..d4a09f8705b 100644 --- a/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c +++ b/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c @@ -24,7 +24,7 @@ #include "pq2.h" -static DEFINE_SPINLOCK(pci_pic_lock); +static DEFINE_RAW_SPINLOCK(pci_pic_lock); struct pq2ads_pci_pic { struct device_node *node; @@ -45,12 +45,12 @@ static void pq2ads_pci_mask_irq(unsigned int virq) if (irq != -1) { unsigned long flags; - spin_lock_irqsave(&pci_pic_lock, flags); + raw_spin_lock_irqsave(&pci_pic_lock, flags); setbits32(&priv->regs->mask, 1 << irq); mb(); - spin_unlock_irqrestore(&pci_pic_lock, flags); + raw_spin_unlock_irqrestore(&pci_pic_lock, flags); } } @@ -62,9 +62,9 @@ static void pq2ads_pci_unmask_irq(unsigned int virq) if (irq != -1) { unsigned long flags; - spin_lock_irqsave(&pci_pic_lock, flags); + raw_spin_lock_irqsave(&pci_pic_lock, flags); clrbits32(&priv->regs->mask, 1 << irq); - spin_unlock_irqrestore(&pci_pic_lock, flags); + raw_spin_unlock_irqrestore(&pci_pic_lock, flags); } } diff --git a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c index 42e87f08aa0..d48527ffc42 100644 --- a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c +++ b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c @@ -50,7 +50,7 @@ static struct socrates_fpga_irq_info fpga_irqs[SOCRATES_FPGA_NUM_IRQS] = { #define socrates_fpga_irq_to_hw(virq) ((unsigned int)irq_map[virq].hwirq) -static DEFINE_SPINLOCK(socrates_fpga_pic_lock); +static DEFINE_RAW_SPINLOCK(socrates_fpga_pic_lock); static void __iomem *socrates_fpga_pic_iobase; static struct irq_host *socrates_fpga_pic_irq_host; @@ -80,9 +80,9 @@ static inline unsigned int socrates_fpga_pic_get_irq(unsigned int irq) if (i == 3) return NO_IRQ; - spin_lock_irqsave(&socrates_fpga_pic_lock, flags); + raw_spin_lock_irqsave(&socrates_fpga_pic_lock, flags); cause = socrates_fpga_pic_read(FPGA_PIC_IRQMASK(i)); - spin_unlock_irqrestore(&socrates_fpga_pic_lock, flags); + raw_spin_unlock_irqrestore(&socrates_fpga_pic_lock, flags); for (i = SOCRATES_FPGA_NUM_IRQS - 1; i >= 0; i--) { if (cause >> (i + 16)) break; @@ -116,12 +116,12 @@ static void socrates_fpga_pic_ack(unsigned int virq) hwirq = socrates_fpga_irq_to_hw(virq); irq_line = fpga_irqs[hwirq].irq_line; - spin_lock_irqsave(&socrates_fpga_pic_lock, flags); + raw_spin_lock_irqsave(&socrates_fpga_pic_lock, flags); mask = socrates_fpga_pic_read(FPGA_PIC_IRQMASK(irq_line)) & SOCRATES_FPGA_IRQ_MASK; mask |= (1 << (hwirq + 16)); socrates_fpga_pic_write(FPGA_PIC_IRQMASK(irq_line), mask); - spin_unlock_irqrestore(&socrates_fpga_pic_lock, flags); + raw_spin_unlock_irqrestore(&socrates_fpga_pic_lock, flags); } static void socrates_fpga_pic_mask(unsigned int virq) @@ -134,12 +134,12 @@ static void socrates_fpga_pic_mask(unsigned int virq) hwirq = socrates_fpga_irq_to_hw(virq); irq_line = fpga_irqs[hwirq].irq_line; - spin_lock_irqsave(&socrates_fpga_pic_lock, flags); + raw_spin_lock_irqsave(&socrates_fpga_pic_lock, flags); mask = socrates_fpga_pic_read(FPGA_PIC_IRQMASK(irq_line)) & SOCRATES_FPGA_IRQ_MASK; mask &= ~(1 << hwirq); socrates_fpga_pic_write(FPGA_PIC_IRQMASK(irq_line), mask); - spin_unlock_irqrestore(&socrates_fpga_pic_lock, flags); + raw_spin_unlock_irqrestore(&socrates_fpga_pic_lock, flags); } static void socrates_fpga_pic_mask_ack(unsigned int virq) @@ -152,13 +152,13 @@ static void socrates_fpga_pic_mask_ack(unsigned int virq) hwirq = socrates_fpga_irq_to_hw(virq); irq_line = fpga_irqs[hwirq].irq_line; - spin_lock_irqsave(&socrates_fpga_pic_lock, flags); + raw_spin_lock_irqsave(&socrates_fpga_pic_lock, flags); mask = socrates_fpga_pic_read(FPGA_PIC_IRQMASK(irq_line)) & SOCRATES_FPGA_IRQ_MASK; mask &= ~(1 << hwirq); mask |= (1 << (hwirq + 16)); socrates_fpga_pic_write(FPGA_PIC_IRQMASK(irq_line), mask); - spin_unlock_irqrestore(&socrates_fpga_pic_lock, flags); + raw_spin_unlock_irqrestore(&socrates_fpga_pic_lock, flags); } static void socrates_fpga_pic_unmask(unsigned int virq) @@ -171,12 +171,12 @@ static void socrates_fpga_pic_unmask(unsigned int virq) hwirq = socrates_fpga_irq_to_hw(virq); irq_line = fpga_irqs[hwirq].irq_line; - spin_lock_irqsave(&socrates_fpga_pic_lock, flags); + raw_spin_lock_irqsave(&socrates_fpga_pic_lock, flags); mask = socrates_fpga_pic_read(FPGA_PIC_IRQMASK(irq_line)) & SOCRATES_FPGA_IRQ_MASK; mask |= (1 << hwirq); socrates_fpga_pic_write(FPGA_PIC_IRQMASK(irq_line), mask); - spin_unlock_irqrestore(&socrates_fpga_pic_lock, flags); + raw_spin_unlock_irqrestore(&socrates_fpga_pic_lock, flags); } static void socrates_fpga_pic_eoi(unsigned int virq) @@ -189,12 +189,12 @@ static void socrates_fpga_pic_eoi(unsigned int virq) hwirq = socrates_fpga_irq_to_hw(virq); irq_line = fpga_irqs[hwirq].irq_line; - spin_lock_irqsave(&socrates_fpga_pic_lock, flags); + raw_spin_lock_irqsave(&socrates_fpga_pic_lock, flags); mask = socrates_fpga_pic_read(FPGA_PIC_IRQMASK(irq_line)) & SOCRATES_FPGA_IRQ_MASK; mask |= (1 << (hwirq + 16)); socrates_fpga_pic_write(FPGA_PIC_IRQMASK(irq_line), mask); - spin_unlock_irqrestore(&socrates_fpga_pic_lock, flags); + raw_spin_unlock_irqrestore(&socrates_fpga_pic_lock, flags); } static int socrates_fpga_pic_set_type(unsigned int virq, @@ -220,14 +220,14 @@ static int socrates_fpga_pic_set_type(unsigned int virq, default: return -EINVAL; } - spin_lock_irqsave(&socrates_fpga_pic_lock, flags); + raw_spin_lock_irqsave(&socrates_fpga_pic_lock, flags); mask = socrates_fpga_pic_read(FPGA_PIC_IRQCFG); if (polarity) mask |= (1 << hwirq); else mask &= ~(1 << hwirq); socrates_fpga_pic_write(FPGA_PIC_IRQCFG, mask); - spin_unlock_irqrestore(&socrates_fpga_pic_lock, flags); + raw_spin_unlock_irqrestore(&socrates_fpga_pic_lock, flags); return 0; } @@ -314,14 +314,14 @@ void socrates_fpga_pic_init(struct device_node *pic) socrates_fpga_pic_iobase = of_iomap(pic, 0); - spin_lock_irqsave(&socrates_fpga_pic_lock, flags); + raw_spin_lock_irqsave(&socrates_fpga_pic_lock, flags); socrates_fpga_pic_write(FPGA_PIC_IRQMASK(0), SOCRATES_FPGA_IRQ_MASK << 16); socrates_fpga_pic_write(FPGA_PIC_IRQMASK(1), SOCRATES_FPGA_IRQ_MASK << 16); socrates_fpga_pic_write(FPGA_PIC_IRQMASK(2), SOCRATES_FPGA_IRQ_MASK << 16); - spin_unlock_irqrestore(&socrates_fpga_pic_lock, flags); + raw_spin_unlock_irqrestore(&socrates_fpga_pic_lock, flags); pr_info("FPGA PIC: Setting up Socrates FPGA PIC\n"); } diff --git a/arch/powerpc/platforms/86xx/Kconfig b/arch/powerpc/platforms/86xx/Kconfig index 2bbfd530d6d..fbe9f362142 100644 --- a/arch/powerpc/platforms/86xx/Kconfig +++ b/arch/powerpc/platforms/86xx/Kconfig @@ -33,32 +33,32 @@ config MPC8610_HPCD This option enables support for the MPC8610 HPCD board. config GEF_PPC9A - bool "GE Fanuc PPC9A" + bool "GE PPC9A" select DEFAULT_UIMAGE select MMIO_NVRAM select GENERIC_GPIO select ARCH_REQUIRE_GPIOLIB help - This option enables support for GE Fanuc's PPC9A. + This option enables support for the GE PPC9A. config GEF_SBC310 - bool "GE Fanuc SBC310" + bool "GE SBC310" select DEFAULT_UIMAGE select MMIO_NVRAM select GENERIC_GPIO select ARCH_REQUIRE_GPIOLIB help - This option enables support for GE Fanuc's SBC310. + This option enables support for the GE SBC310. config GEF_SBC610 - bool "GE Fanuc SBC610" + bool "GE SBC610" select DEFAULT_UIMAGE select MMIO_NVRAM select GENERIC_GPIO select ARCH_REQUIRE_GPIOLIB select HAS_RAPIDIO help - This option enables support for GE Fanuc's SBC610. + This option enables support for the GE SBC610. endif diff --git a/arch/powerpc/platforms/86xx/gef_gpio.c b/arch/powerpc/platforms/86xx/gef_gpio.c index b2ea8875adb..11f7b2b6f49 100644 --- a/arch/powerpc/platforms/86xx/gef_gpio.c +++ b/arch/powerpc/platforms/86xx/gef_gpio.c @@ -1,9 +1,9 @@ /* - * Driver for GE Fanuc's FPGA based GPIO pins + * Driver for GE FPGA based GPIO * - * Author: Martyn Welch <martyn.welch@gefanuc.com> + * Author: Martyn Welch <martyn.welch@ge.com> * - * 2008 (c) GE Fanuc Intelligent Platforms Embedded Systems, Inc. + * 2008 (c) GE Intelligent Platforms Embedded Systems, Inc. * * This file is licensed under the terms of the GNU General Public License * version 2. This program is licensed "as is" without any warranty of any @@ -164,6 +164,6 @@ static int __init gef_gpio_init(void) }; arch_initcall(gef_gpio_init); -MODULE_DESCRIPTION("GE Fanuc I/O FPGA GPIO driver"); -MODULE_AUTHOR("Martyn Welch <martyn.welch@gefanuc.com"); +MODULE_DESCRIPTION("GE I/O FPGA GPIO driver"); +MODULE_AUTHOR("Martyn Welch <martyn.welch@ge.com"); MODULE_LICENSE("GPL"); diff --git a/arch/powerpc/platforms/86xx/gef_pic.c b/arch/powerpc/platforms/86xx/gef_pic.c index 0110a8736d3..6df9e2561c0 100644 --- a/arch/powerpc/platforms/86xx/gef_pic.c +++ b/arch/powerpc/platforms/86xx/gef_pic.c @@ -1,9 +1,9 @@ /* - * Interrupt handling for GE Fanuc's FPGA based PIC + * Interrupt handling for GE FPGA based PIC * - * Author: Martyn Welch <martyn.welch@gefanuc.com> + * Author: Martyn Welch <martyn.welch@ge.com> * - * 2008 (c) GE Fanuc Intelligent Platforms Embedded Systems, Inc. + * 2008 (c) GE Intelligent Platforms Embedded Systems, Inc. * * This file is licensed under the terms of the GNU General Public License * version 2. This program is licensed "as is" without any warranty of any @@ -49,7 +49,7 @@ #define gef_irq_to_hw(virq) ((unsigned int)irq_map[virq].hwirq) -static DEFINE_SPINLOCK(gef_pic_lock); +static DEFINE_RAW_SPINLOCK(gef_pic_lock); static void __iomem *gef_pic_irq_reg_base; static struct irq_host *gef_pic_irq_host; @@ -118,11 +118,11 @@ static void gef_pic_mask(unsigned int virq) hwirq = gef_irq_to_hw(virq); - spin_lock_irqsave(&gef_pic_lock, flags); + raw_spin_lock_irqsave(&gef_pic_lock, flags); mask = in_be32(gef_pic_irq_reg_base + GEF_PIC_INTR_MASK(0)); mask &= ~(1 << hwirq); out_be32(gef_pic_irq_reg_base + GEF_PIC_INTR_MASK(0), mask); - spin_unlock_irqrestore(&gef_pic_lock, flags); + raw_spin_unlock_irqrestore(&gef_pic_lock, flags); } static void gef_pic_mask_ack(unsigned int virq) @@ -141,11 +141,11 @@ static void gef_pic_unmask(unsigned int virq) hwirq = gef_irq_to_hw(virq); - spin_lock_irqsave(&gef_pic_lock, flags); + raw_spin_lock_irqsave(&gef_pic_lock, flags); mask = in_be32(gef_pic_irq_reg_base + GEF_PIC_INTR_MASK(0)); mask |= (1 << hwirq); out_be32(gef_pic_irq_reg_base + GEF_PIC_INTR_MASK(0), mask); - spin_unlock_irqrestore(&gef_pic_lock, flags); + raw_spin_unlock_irqrestore(&gef_pic_lock, flags); } static struct irq_chip gef_pic_chip = { @@ -199,7 +199,7 @@ void __init gef_pic_init(struct device_node *np) /* Map the devices registers into memory */ gef_pic_irq_reg_base = of_iomap(np, 0); - spin_lock_irqsave(&gef_pic_lock, flags); + raw_spin_lock_irqsave(&gef_pic_lock, flags); /* Initialise everything as masked. */ out_be32(gef_pic_irq_reg_base + GEF_PIC_CPU0_INTR_MASK, 0); @@ -208,7 +208,7 @@ void __init gef_pic_init(struct device_node *np) out_be32(gef_pic_irq_reg_base + GEF_PIC_CPU0_MCP_MASK, 0); out_be32(gef_pic_irq_reg_base + GEF_PIC_CPU1_MCP_MASK, 0); - spin_unlock_irqrestore(&gef_pic_lock, flags); + raw_spin_unlock_irqrestore(&gef_pic_lock, flags); /* Map controller */ gef_pic_cascade_irq = irq_of_parse_and_map(np, 0); diff --git a/arch/powerpc/platforms/86xx/gef_ppc9a.c b/arch/powerpc/platforms/86xx/gef_ppc9a.c index a792e5d8581..60ce07e3910 100644 --- a/arch/powerpc/platforms/86xx/gef_ppc9a.c +++ b/arch/powerpc/platforms/86xx/gef_ppc9a.c @@ -1,9 +1,9 @@ /* - * GE Fanuc PPC9A board support + * GE PPC9A board support * - * Author: Martyn Welch <martyn.welch@gefanuc.com> + * Author: Martyn Welch <martyn.welch@ge.com> * - * Copyright 2008 GE Fanuc Intelligent Platforms Embedded Systems, Inc. + * Copyright 2008 GE Intelligent Platforms Embedded Systems, Inc. * * 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 @@ -82,7 +82,7 @@ static void __init gef_ppc9a_setup_arch(void) } #endif - printk(KERN_INFO "GE Fanuc Intelligent Platforms PPC9A 6U VME SBC\n"); + printk(KERN_INFO "GE Intelligent Platforms PPC9A 6U VME SBC\n"); #ifdef CONFIG_SMP mpc86xx_smp_init(); @@ -151,7 +151,7 @@ static void gef_ppc9a_show_cpuinfo(struct seq_file *m) { uint svid = mfspr(SPRN_SVR); - seq_printf(m, "Vendor\t\t: GE Fanuc Intelligent Platforms\n"); + seq_printf(m, "Vendor\t\t: GE Intelligent Platforms\n"); seq_printf(m, "Revision\t: %u%c\n", gef_ppc9a_get_pcb_rev(), ('A' + gef_ppc9a_get_board_rev())); @@ -235,7 +235,7 @@ static int __init declare_of_platform_devices(void) machine_device_initcall(gef_ppc9a, declare_of_platform_devices); define_machine(gef_ppc9a) { - .name = "GE Fanuc PPC9A", + .name = "GE PPC9A", .probe = gef_ppc9a_probe, .setup_arch = gef_ppc9a_setup_arch, .init_IRQ = gef_ppc9a_init_irq, diff --git a/arch/powerpc/platforms/86xx/gef_sbc310.c b/arch/powerpc/platforms/86xx/gef_sbc310.c index 6a1a613836c..3ecee25bf3e 100644 --- a/arch/powerpc/platforms/86xx/gef_sbc310.c +++ b/arch/powerpc/platforms/86xx/gef_sbc310.c @@ -1,9 +1,9 @@ /* - * GE Fanuc SBC310 board support + * GE SBC310 board support * - * Author: Martyn Welch <martyn.welch@gefanuc.com> + * Author: Martyn Welch <martyn.welch@ge.com> * - * Copyright 2008 GE Fanuc Intelligent Platforms Embedded Systems, Inc. + * Copyright 2008 GE Intelligent Platforms Embedded Systems, Inc. * * 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 @@ -82,7 +82,7 @@ static void __init gef_sbc310_setup_arch(void) } #endif - printk(KERN_INFO "GE Fanuc Intelligent Platforms SBC310 6U VPX SBC\n"); + printk(KERN_INFO "GE Intelligent Platforms SBC310 6U VPX SBC\n"); #ifdef CONFIG_SMP mpc86xx_smp_init(); @@ -142,7 +142,7 @@ static void gef_sbc310_show_cpuinfo(struct seq_file *m) { uint svid = mfspr(SPRN_SVR); - seq_printf(m, "Vendor\t\t: GE Fanuc Intelligent Platforms\n"); + seq_printf(m, "Vendor\t\t: GE Intelligent Platforms\n"); seq_printf(m, "Board ID\t: 0x%2.2x\n", gef_sbc310_get_board_id()); seq_printf(m, "Revision\t: %u%c\n", gef_sbc310_get_pcb_rev(), @@ -223,7 +223,7 @@ static int __init declare_of_platform_devices(void) machine_device_initcall(gef_sbc310, declare_of_platform_devices); define_machine(gef_sbc310) { - .name = "GE Fanuc SBC310", + .name = "GE SBC310", .probe = gef_sbc310_probe, .setup_arch = gef_sbc310_setup_arch, .init_IRQ = gef_sbc310_init_irq, diff --git a/arch/powerpc/platforms/86xx/gef_sbc610.c b/arch/powerpc/platforms/86xx/gef_sbc610.c index e10688a0fc4..5090d608d9e 100644 --- a/arch/powerpc/platforms/86xx/gef_sbc610.c +++ b/arch/powerpc/platforms/86xx/gef_sbc610.c @@ -1,9 +1,9 @@ /* - * GE Fanuc SBC610 board support + * GE SBC610 board support * - * Author: Martyn Welch <martyn.welch@gefanuc.com> + * Author: Martyn Welch <martyn.welch@ge.com> * - * Copyright 2008 GE Fanuc Intelligent Platforms Embedded Systems, Inc. + * Copyright 2008 GE Intelligent Platforms Embedded Systems, Inc. * * 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 @@ -82,7 +82,7 @@ static void __init gef_sbc610_setup_arch(void) } #endif - printk(KERN_INFO "GE Fanuc Intelligent Platforms SBC610 6U VPX SBC\n"); + printk(KERN_INFO "GE Intelligent Platforms SBC610 6U VPX SBC\n"); #ifdef CONFIG_SMP mpc86xx_smp_init(); @@ -133,7 +133,7 @@ static void gef_sbc610_show_cpuinfo(struct seq_file *m) { uint svid = mfspr(SPRN_SVR); - seq_printf(m, "Vendor\t\t: GE Fanuc Intelligent Platforms\n"); + seq_printf(m, "Vendor\t\t: GE Intelligent Platforms\n"); seq_printf(m, "Revision\t: %u%c\n", gef_sbc610_get_pcb_rev(), ('A' + gef_sbc610_get_board_rev() - 1)); @@ -212,7 +212,7 @@ static int __init declare_of_platform_devices(void) machine_device_initcall(gef_sbc610, declare_of_platform_devices); define_machine(gef_sbc610) { - .name = "GE Fanuc SBC610", + .name = "GE SBC610", .probe = gef_sbc610_probe, .setup_arch = gef_sbc610_setup_arch, .init_IRQ = gef_sbc610_init_irq, diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index fa0f690d386..a8aae0b5457 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -144,6 +144,16 @@ config FSL_EMB_PERFMON and some e300 cores (c3 and c4). Select this only if your core supports the Embedded Performance Monitor APU +config FSL_EMB_PERF_EVENT + bool + depends on FSL_EMB_PERFMON && PERF_EVENTS && !PPC_PERF_CTRS + default y + +config FSL_EMB_PERF_EVENT_E500 + bool + depends on FSL_EMB_PERF_EVENT && E500 + default y + config 4xx bool depends on 40x || 44x diff --git a/arch/powerpc/platforms/iseries/exception.S b/arch/powerpc/platforms/iseries/exception.S index 5369653dcf6..fba5bf91507 100644 --- a/arch/powerpc/platforms/iseries/exception.S +++ b/arch/powerpc/platforms/iseries/exception.S @@ -43,17 +43,14 @@ system_reset_iSeries: LOAD_REG_ADDR(r23, alpaca) li r0,ALPACA_SIZE sub r23,r13,r23 - divdu r23,r23,r0 /* r23 has cpu number */ - LOAD_REG_ADDR(r13, paca) - mulli r0,r23,PACA_SIZE - add r13,r13,r0 - mtspr SPRN_SPRG_PACA,r13 /* Save it away for the future */ - mfmsr r24 - ori r24,r24,MSR_RI - mtmsrd r24 /* RI on */ - mr r24,r23 + divdu r24,r23,r0 /* r24 has cpu number */ cmpwi 0,r24,0 /* Are we processor 0? */ bne 1f + LOAD_REG_ADDR(r13, boot_paca) + mtspr SPRN_SPRG_PACA,r13 /* Save it away for the future */ + mfmsr r23 + ori r23,r23,MSR_RI + mtmsrd r23 /* RI on */ b .__start_initialization_iSeries /* Start up the first processor */ 1: mfspr r4,SPRN_CTRLF li r5,CTRL_RUNLATCH /* Turn off the run light */ @@ -86,6 +83,16 @@ system_reset_iSeries: #endif 2: + /* Load our paca now that it's been allocated */ + LOAD_REG_ADDR(r13, paca) + ld r13,0(r13) + mulli r0,r24,PACA_SIZE + add r13,r13,r0 + mtspr SPRN_SPRG_PACA,r13 /* Save it away for the future */ + mfmsr r23 + ori r23,r23,MSR_RI + mtmsrd r23 /* RI on */ + HMT_LOW #ifdef CONFIG_SMP lbz r23,PACAPROCSTART(r13) /* Test if this processor diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index d1b124e44d7..a8e1d5d17a2 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -122,44 +122,32 @@ static void pseries_mach_cpu_die(void) if (!get_lppaca()->shared_proc) get_lppaca()->donate_dedicated_cpu = 1; - printk(KERN_INFO - "cpu %u (hwid %u) ceding for offline with hint %d\n", - cpu, hwcpu, cede_latency_hint); while (get_preferred_offline_state(cpu) == CPU_STATE_INACTIVE) { extended_cede_processor(cede_latency_hint); - printk(KERN_INFO "cpu %u (hwid %u) returned from cede.\n", - cpu, hwcpu); - printk(KERN_INFO - "Decrementer value = %x Timebase value = %llx\n", - get_dec(), get_tb()); } - printk(KERN_INFO "cpu %u (hwid %u) got prodded to go online\n", - cpu, hwcpu); - if (!get_lppaca()->shared_proc) get_lppaca()->donate_dedicated_cpu = 0; get_lppaca()->idle = 0; - } - if (get_preferred_offline_state(cpu) == CPU_STATE_ONLINE) { - unregister_slb_shadow(hwcpu, __pa(get_slb_shadow())); + if (get_preferred_offline_state(cpu) == CPU_STATE_ONLINE) { + unregister_slb_shadow(hwcpu, __pa(get_slb_shadow())); - /* - * NOTE: Calling start_secondary() here for now to - * start new context. - * However, need to do it cleanly by resetting the - * stack pointer. - */ - start_secondary(); + /* + * Call to start_secondary_resume() will not return. + * Kernel stack will be reset and start_secondary() + * will be called to continue the online operation. + */ + start_secondary_resume(); + } + } - } else if (get_preferred_offline_state(cpu) == CPU_STATE_OFFLINE) { + /* Requested state is CPU_STATE_OFFLINE at this point */ + WARN_ON(get_preferred_offline_state(cpu) != CPU_STATE_OFFLINE); - set_cpu_current_state(cpu, CPU_STATE_OFFLINE); - unregister_slb_shadow(hard_smp_processor_id(), - __pa(get_slb_shadow())); - rtas_stop_self(); - } + set_cpu_current_state(cpu, CPU_STATE_OFFLINE); + unregister_slb_shadow(hwcpu, __pa(get_slb_shadow())); + rtas_stop_self(); /* Should never get here... */ BUG(); diff --git a/arch/powerpc/platforms/pseries/offline_states.h b/arch/powerpc/platforms/pseries/offline_states.h index 22574e0d9d9..75a6f480d93 100644 --- a/arch/powerpc/platforms/pseries/offline_states.h +++ b/arch/powerpc/platforms/pseries/offline_states.h @@ -9,10 +9,31 @@ enum cpu_state_vals { CPU_MAX_OFFLINE_STATES }; +#ifdef CONFIG_HOTPLUG_CPU extern enum cpu_state_vals get_cpu_current_state(int cpu); extern void set_cpu_current_state(int cpu, enum cpu_state_vals state); -extern enum cpu_state_vals get_preferred_offline_state(int cpu); extern void set_preferred_offline_state(int cpu, enum cpu_state_vals state); extern void set_default_offline_state(int cpu); +#else +static inline enum cpu_state_vals get_cpu_current_state(int cpu) +{ + return CPU_STATE_ONLINE; +} + +static inline void set_cpu_current_state(int cpu, enum cpu_state_vals state) +{ +} + +static inline void set_preferred_offline_state(int cpu, enum cpu_state_vals state) +{ +} + +static inline void set_default_offline_state(int cpu) +{ +} +#endif + +extern enum cpu_state_vals get_preferred_offline_state(int cpu); extern int start_secondary(void); +extern void start_secondary_resume(void); #endif diff --git a/arch/powerpc/platforms/pseries/plpar_wrappers.h b/arch/powerpc/platforms/pseries/plpar_wrappers.h index 0603c91538a..a05f8d42785 100644 --- a/arch/powerpc/platforms/pseries/plpar_wrappers.h +++ b/arch/powerpc/platforms/pseries/plpar_wrappers.h @@ -259,12 +259,12 @@ static inline long plpar_ipi(unsigned long servernum, unsigned long mfrr) return plpar_hcall_norets(H_IPI, servernum, mfrr); } -static inline long plpar_xirr(unsigned long *xirr_ret) +static inline long plpar_xirr(unsigned long *xirr_ret, unsigned char cppr) { long rc; unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; - rc = plpar_hcall(H_XIRR, retbuf); + rc = plpar_hcall(H_XIRR, retbuf, cppr); *xirr_ret = retbuf[0]; diff --git a/arch/powerpc/platforms/pseries/xics.c b/arch/powerpc/platforms/pseries/xics.c index 4ca641042ec..1bcedd8b461 100644 --- a/arch/powerpc/platforms/pseries/xics.c +++ b/arch/powerpc/platforms/pseries/xics.c @@ -120,12 +120,12 @@ static inline void direct_qirr_info(int n_cpu, u8 value) /* LPAR low level accessors */ -static inline unsigned int lpar_xirr_info_get(void) +static inline unsigned int lpar_xirr_info_get(unsigned char cppr) { unsigned long lpar_rc; unsigned long return_value; - lpar_rc = plpar_xirr(&return_value); + lpar_rc = plpar_xirr(&return_value, cppr); if (lpar_rc != H_SUCCESS) panic(" bad return code xirr - rc = %lx\n", lpar_rc); return (unsigned int)return_value; @@ -331,7 +331,8 @@ static unsigned int xics_get_irq_direct(void) static unsigned int xics_get_irq_lpar(void) { - unsigned int xirr = lpar_xirr_info_get(); + struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr); + unsigned int xirr = lpar_xirr_info_get(os_cppr->stack[os_cppr->index]); unsigned int vec = xics_xirr_vector(xirr); unsigned int irq; diff --git a/arch/powerpc/sysdev/cpm2_pic.h b/arch/powerpc/sysdev/cpm2_pic.h index 30e5828a278..2c5f70c2448 100644 --- a/arch/powerpc/sysdev/cpm2_pic.h +++ b/arch/powerpc/sysdev/cpm2_pic.h @@ -3,6 +3,6 @@ extern unsigned int cpm2_get_irq(void); -extern void cpm2_pic_init(struct device_node*); +extern void cpm2_pic_init(struct device_node *); #endif /* _PPC_KERNEL_CPM2_H */ diff --git a/arch/powerpc/sysdev/qe_lib/qe_ic.c b/arch/powerpc/sysdev/qe_lib/qe_ic.c index d927da893ec..541ba986364 100644 --- a/arch/powerpc/sysdev/qe_lib/qe_ic.c +++ b/arch/powerpc/sysdev/qe_lib/qe_ic.c @@ -33,7 +33,7 @@ #include "qe_ic.h" -static DEFINE_SPINLOCK(qe_ic_lock); +static DEFINE_RAW_SPINLOCK(qe_ic_lock); static struct qe_ic_info qe_ic_info[] = { [1] = { @@ -201,13 +201,13 @@ static void qe_ic_unmask_irq(unsigned int virq) unsigned long flags; u32 temp; - spin_lock_irqsave(&qe_ic_lock, flags); + raw_spin_lock_irqsave(&qe_ic_lock, flags); temp = qe_ic_read(qe_ic->regs, qe_ic_info[src].mask_reg); qe_ic_write(qe_ic->regs, qe_ic_info[src].mask_reg, temp | qe_ic_info[src].mask); - spin_unlock_irqrestore(&qe_ic_lock, flags); + raw_spin_unlock_irqrestore(&qe_ic_lock, flags); } static void qe_ic_mask_irq(unsigned int virq) @@ -217,7 +217,7 @@ static void qe_ic_mask_irq(unsigned int virq) unsigned long flags; u32 temp; - spin_lock_irqsave(&qe_ic_lock, flags); + raw_spin_lock_irqsave(&qe_ic_lock, flags); temp = qe_ic_read(qe_ic->regs, qe_ic_info[src].mask_reg); qe_ic_write(qe_ic->regs, qe_ic_info[src].mask_reg, @@ -233,7 +233,7 @@ static void qe_ic_mask_irq(unsigned int virq) */ mb(); - spin_unlock_irqrestore(&qe_ic_lock, flags); + raw_spin_unlock_irqrestore(&qe_ic_lock, flags); } static struct irq_chip qe_ic_irq_chip = { |