diff options
Diffstat (limited to 'arch/powerpc')
107 files changed, 7874 insertions, 2510 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 2729c6663d8..cdf7a0a6440 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -134,6 +134,7 @@ config PPC select GENERIC_IRQ_SHOW_LEVEL select HAVE_RCU_TABLE_FREE if SMP select HAVE_SYSCALL_TRACEPOINTS + select HAVE_BPF_JIT if (PPC64 && NET) config EARLY_PRINTK bool diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index b7212b619c5..b94740f36b1 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -154,7 +154,8 @@ core-y += arch/powerpc/kernel/ \ arch/powerpc/lib/ \ arch/powerpc/sysdev/ \ arch/powerpc/platforms/ \ - arch/powerpc/math-emu/ + arch/powerpc/math-emu/ \ + arch/powerpc/net/ core-$(CONFIG_XMON) += arch/powerpc/xmon/ core-$(CONFIG_KVM) += arch/powerpc/kvm/ diff --git a/arch/powerpc/include/asm/8253pit.h b/arch/powerpc/include/asm/8253pit.h deleted file mode 100644 index a71c9c1455a..00000000000 --- a/arch/powerpc/include/asm/8253pit.h +++ /dev/null @@ -1,3 +0,0 @@ -/* - * 8253/8254 Programmable Interval Timer - */ diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index c0d842cfd01..e30442c539c 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -179,8 +179,9 @@ extern const char *powerpc_base_platform; #define LONG_ASM_CONST(x) 0 #endif - -#define CPU_FTR_HVMODE_206 LONG_ASM_CONST(0x0000000800000000) +#define CPU_FTR_HVMODE LONG_ASM_CONST(0x0000000200000000) +#define CPU_FTR_ARCH_201 LONG_ASM_CONST(0x0000000400000000) +#define CPU_FTR_ARCH_206 LONG_ASM_CONST(0x0000000800000000) #define CPU_FTR_CFAR LONG_ASM_CONST(0x0000001000000000) #define CPU_FTR_IABR LONG_ASM_CONST(0x0000002000000000) #define CPU_FTR_MMCRA LONG_ASM_CONST(0x0000004000000000) @@ -401,9 +402,10 @@ extern const char *powerpc_base_platform; CPU_FTR_MMCRA | CPU_FTR_CP_USE_DCBTZ | \ CPU_FTR_STCX_CHECKS_ADDRESS) #define CPU_FTRS_PPC970 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ - CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ + CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | CPU_FTR_ARCH_201 | \ CPU_FTR_ALTIVEC_COMP | CPU_FTR_CAN_NAP | CPU_FTR_MMCRA | \ - CPU_FTR_CP_USE_DCBTZ | CPU_FTR_STCX_CHECKS_ADDRESS) + CPU_FTR_CP_USE_DCBTZ | CPU_FTR_STCX_CHECKS_ADDRESS | \ + CPU_FTR_HVMODE) #define CPU_FTRS_POWER5 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ CPU_FTR_MMCRA | CPU_FTR_SMT | \ @@ -417,13 +419,13 @@ extern const char *powerpc_base_platform; CPU_FTR_DSCR | CPU_FTR_UNALIGNED_LD_STD | \ CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_CFAR) #define CPU_FTRS_POWER7 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ - CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | CPU_FTR_HVMODE_206 |\ + CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | CPU_FTR_ARCH_206 |\ CPU_FTR_MMCRA | CPU_FTR_SMT | \ CPU_FTR_COHERENT_ICACHE | \ CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \ CPU_FTR_DSCR | CPU_FTR_SAO | CPU_FTR_ASYM_SMT | \ CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \ - CPU_FTR_ICSWX | CPU_FTR_CFAR) + CPU_FTR_ICSWX | CPU_FTR_CFAR | CPU_FTR_HVMODE) #define CPU_FTRS_CELL (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ CPU_FTR_ALTIVEC_COMP | CPU_FTR_MMCRA | CPU_FTR_SMT | \ diff --git a/arch/powerpc/include/asm/emulated_ops.h b/arch/powerpc/include/asm/emulated_ops.h index 45921672b97..2cc41c715d2 100644 --- a/arch/powerpc/include/asm/emulated_ops.h +++ b/arch/powerpc/include/asm/emulated_ops.h @@ -78,14 +78,14 @@ extern void ppc_warn_emulated_print(const char *type); #define PPC_WARN_EMULATED(type, regs) \ do { \ perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, \ - 1, 0, regs, 0); \ + 1, regs, 0); \ __PPC_WARN_EMULATED(type); \ } while (0) #define PPC_WARN_ALIGNMENT(type, regs) \ do { \ perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, \ - 1, 0, regs, regs->dar); \ + 1, regs, regs->dar); \ __PPC_WARN_EMULATED(type); \ } while (0) diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index f5dfe3411f6..8057f4f6980 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -61,19 +61,22 @@ #define EXC_HV H #define EXC_STD -#define EXCEPTION_PROLOG_1(area) \ +#define __EXCEPTION_PROLOG_1(area, extra, vec) \ GET_PACA(r13); \ std r9,area+EX_R9(r13); /* save r9 - r12 */ \ std r10,area+EX_R10(r13); \ - std r11,area+EX_R11(r13); \ - std r12,area+EX_R12(r13); \ BEGIN_FTR_SECTION_NESTED(66); \ mfspr r10,SPRN_CFAR; \ std r10,area+EX_CFAR(r13); \ END_FTR_SECTION_NESTED(CPU_FTR_CFAR, CPU_FTR_CFAR, 66); \ - GET_SCRATCH0(r9); \ - std r9,area+EX_R13(r13); \ - mfcr r9 + mfcr r9; \ + extra(vec); \ + std r11,area+EX_R11(r13); \ + std r12,area+EX_R12(r13); \ + GET_SCRATCH0(r10); \ + std r10,area+EX_R13(r13) +#define EXCEPTION_PROLOG_1(area, extra, vec) \ + __EXCEPTION_PROLOG_1(area, extra, vec) #define __EXCEPTION_PROLOG_PSERIES_1(label, h) \ ld r12,PACAKBASE(r13); /* get high part of &label */ \ @@ -85,13 +88,65 @@ mtspr SPRN_##h##SRR1,r10; \ h##rfid; \ b . /* prevent speculative execution */ -#define EXCEPTION_PROLOG_PSERIES_1(label, h) \ +#define EXCEPTION_PROLOG_PSERIES_1(label, h) \ __EXCEPTION_PROLOG_PSERIES_1(label, h) -#define EXCEPTION_PROLOG_PSERIES(area, label, h) \ - EXCEPTION_PROLOG_1(area); \ +#define EXCEPTION_PROLOG_PSERIES(area, label, h, extra, vec) \ + EXCEPTION_PROLOG_1(area, extra, vec); \ EXCEPTION_PROLOG_PSERIES_1(label, h); +#define __KVMTEST(n) \ + lbz r10,HSTATE_IN_GUEST(r13); \ + cmpwi r10,0; \ + bne do_kvm_##n + +#define __KVM_HANDLER(area, h, n) \ +do_kvm_##n: \ + ld r10,area+EX_R10(r13); \ + stw r9,HSTATE_SCRATCH1(r13); \ + ld r9,area+EX_R9(r13); \ + std r12,HSTATE_SCRATCH0(r13); \ + li r12,n; \ + b kvmppc_interrupt + +#define __KVM_HANDLER_SKIP(area, h, n) \ +do_kvm_##n: \ + cmpwi r10,KVM_GUEST_MODE_SKIP; \ + ld r10,area+EX_R10(r13); \ + beq 89f; \ + stw r9,HSTATE_SCRATCH1(r13); \ + ld r9,area+EX_R9(r13); \ + std r12,HSTATE_SCRATCH0(r13); \ + li r12,n; \ + b kvmppc_interrupt; \ +89: mtocrf 0x80,r9; \ + ld r9,area+EX_R9(r13); \ + b kvmppc_skip_##h##interrupt + +#ifdef CONFIG_KVM_BOOK3S_64_HANDLER +#define KVMTEST(n) __KVMTEST(n) +#define KVM_HANDLER(area, h, n) __KVM_HANDLER(area, h, n) +#define KVM_HANDLER_SKIP(area, h, n) __KVM_HANDLER_SKIP(area, h, n) + +#else +#define KVMTEST(n) +#define KVM_HANDLER(area, h, n) +#define KVM_HANDLER_SKIP(area, h, n) +#endif + +#ifdef CONFIG_KVM_BOOK3S_PR +#define KVMTEST_PR(n) __KVMTEST(n) +#define KVM_HANDLER_PR(area, h, n) __KVM_HANDLER(area, h, n) +#define KVM_HANDLER_PR_SKIP(area, h, n) __KVM_HANDLER_SKIP(area, h, n) + +#else +#define KVMTEST_PR(n) +#define KVM_HANDLER_PR(area, h, n) +#define KVM_HANDLER_PR_SKIP(area, h, n) +#endif + +#define NOTEST(n) + /* * The common exception prolog is used for all except a few exceptions * such as a segment miss on a kernel address. We have to be prepared @@ -164,57 +219,58 @@ .globl label##_pSeries; \ label##_pSeries: \ HMT_MEDIUM; \ - DO_KVM vec; \ SET_SCRATCH0(r13); /* save r13 */ \ - EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label##_common, EXC_STD) + EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label##_common, \ + EXC_STD, KVMTEST_PR, vec) #define STD_EXCEPTION_HV(loc, vec, label) \ . = loc; \ .globl label##_hv; \ label##_hv: \ HMT_MEDIUM; \ - DO_KVM vec; \ - SET_SCRATCH0(r13); /* save r13 */ \ - EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label##_common, EXC_HV) + SET_SCRATCH0(r13); /* save r13 */ \ + EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label##_common, \ + EXC_HV, KVMTEST, vec) -#define __MASKABLE_EXCEPTION_PSERIES(vec, label, h) \ - HMT_MEDIUM; \ - DO_KVM vec; \ - SET_SCRATCH0(r13); /* save r13 */ \ - GET_PACA(r13); \ - std r9,PACA_EXGEN+EX_R9(r13); /* save r9, r10 */ \ - std r10,PACA_EXGEN+EX_R10(r13); \ +#define __SOFTEN_TEST(h) \ lbz r10,PACASOFTIRQEN(r13); \ - mfcr r9; \ cmpwi r10,0; \ - beq masked_##h##interrupt; \ - GET_SCRATCH0(r10); \ - std r10,PACA_EXGEN+EX_R13(r13); \ - std r11,PACA_EXGEN+EX_R11(r13); \ - std r12,PACA_EXGEN+EX_R12(r13); \ - ld r12,PACAKBASE(r13); /* get high part of &label */ \ - ld r10,PACAKMSR(r13); /* get MSR value for kernel */ \ - mfspr r11,SPRN_##h##SRR0; /* save SRR0 */ \ - LOAD_HANDLER(r12,label##_common) \ - mtspr SPRN_##h##SRR0,r12; \ - mfspr r12,SPRN_##h##SRR1; /* and SRR1 */ \ - mtspr SPRN_##h##SRR1,r10; \ - h##rfid; \ - b . /* prevent speculative execution */ -#define _MASKABLE_EXCEPTION_PSERIES(vec, label, h) \ - __MASKABLE_EXCEPTION_PSERIES(vec, label, h) + beq masked_##h##interrupt +#define _SOFTEN_TEST(h) __SOFTEN_TEST(h) + +#define SOFTEN_TEST_PR(vec) \ + KVMTEST_PR(vec); \ + _SOFTEN_TEST(EXC_STD) + +#define SOFTEN_TEST_HV(vec) \ + KVMTEST(vec); \ + _SOFTEN_TEST(EXC_HV) + +#define SOFTEN_TEST_HV_201(vec) \ + KVMTEST(vec); \ + _SOFTEN_TEST(EXC_STD) + +#define __MASKABLE_EXCEPTION_PSERIES(vec, label, h, extra) \ + HMT_MEDIUM; \ + SET_SCRATCH0(r13); /* save r13 */ \ + __EXCEPTION_PROLOG_1(PACA_EXGEN, extra, vec); \ + EXCEPTION_PROLOG_PSERIES_1(label##_common, h); +#define _MASKABLE_EXCEPTION_PSERIES(vec, label, h, extra) \ + __MASKABLE_EXCEPTION_PSERIES(vec, label, h, extra) #define MASKABLE_EXCEPTION_PSERIES(loc, vec, label) \ . = loc; \ .globl label##_pSeries; \ label##_pSeries: \ - _MASKABLE_EXCEPTION_PSERIES(vec, label, EXC_STD) + _MASKABLE_EXCEPTION_PSERIES(vec, label, \ + EXC_STD, SOFTEN_TEST_PR) #define MASKABLE_EXCEPTION_HV(loc, vec, label) \ . = loc; \ .globl label##_hv; \ label##_hv: \ - _MASKABLE_EXCEPTION_PSERIES(vec, label, EXC_HV) + _MASKABLE_EXCEPTION_PSERIES(vec, label, \ + EXC_HV, SOFTEN_TEST_HV) #ifdef CONFIG_PPC_ISERIES #define DISABLE_INTS \ diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index fd8201dddd4..1c324ff55ea 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -29,6 +29,10 @@ #define H_LONG_BUSY_ORDER_100_SEC 9905 /* Long busy, hint that 100sec \ is a good time to retry */ #define H_LONG_BUSY_END_RANGE 9905 /* End of long busy range */ + +/* Internal value used in book3s_hv kvm support; not returned to guests */ +#define H_TOO_HARD 9999 + #define H_HARDWARE -1 /* Hardware error */ #define H_FUNCTION -2 /* Function not supported */ #define H_PRIVILEGE -3 /* Caller not privileged */ @@ -100,6 +104,7 @@ #define H_PAGE_SET_ACTIVE H_PAGE_STATE_CHANGE #define H_AVPN (1UL<<(63-32)) /* An avpn is provided as a sanity test */ #define H_ANDCOND (1UL<<(63-33)) +#define H_LOCAL (1UL<<(63-35)) #define H_ICACHE_INVALIDATE (1UL<<(63-40)) /* icbi, etc. (ignored for IO pages) */ #define H_ICACHE_SYNCHRONIZE (1UL<<(63-41)) /* dcbst, icbi, etc (ignored for IO pages */ #define H_COALESCE_CAND (1UL<<(63-42)) /* page is a good candidate for coalescing */ diff --git a/arch/powerpc/include/asm/hw_breakpoint.h b/arch/powerpc/include/asm/hw_breakpoint.h index 1c33ec17ca3..80fd4d2b4a6 100644 --- a/arch/powerpc/include/asm/hw_breakpoint.h +++ b/arch/powerpc/include/asm/hw_breakpoint.h @@ -57,7 +57,7 @@ void hw_breakpoint_pmu_read(struct perf_event *bp); extern void flush_ptrace_hw_breakpoint(struct task_struct *tsk); extern struct pmu perf_ops_bp; -extern void ptrace_triggered(struct perf_event *bp, int nmi, +extern void ptrace_triggered(struct perf_event *bp, struct perf_sample_data *data, struct pt_regs *regs); static inline void hw_breakpoint_disable(void) { diff --git a/arch/powerpc/include/asm/kvm.h b/arch/powerpc/include/asm/kvm.h index d2ca5ed3877..a4f6c85431f 100644 --- a/arch/powerpc/include/asm/kvm.h +++ b/arch/powerpc/include/asm/kvm.h @@ -22,6 +22,10 @@ #include <linux/types.h> +/* Select powerpc specific features in <linux/kvm.h> */ +#define __KVM_HAVE_SPAPR_TCE +#define __KVM_HAVE_PPC_SMT + struct kvm_regs { __u64 pc; __u64 cr; @@ -272,4 +276,15 @@ struct kvm_guest_debug_arch { #define KVM_INTERRUPT_UNSET -2U #define KVM_INTERRUPT_SET_LEVEL -3U +/* for KVM_CAP_SPAPR_TCE */ +struct kvm_create_spapr_tce { + __u64 liobn; + __u32 window_size; +}; + +/* for KVM_ALLOCATE_RMA */ +struct kvm_allocate_rma { + __u64 rma_size; +}; + #endif /* __LINUX_KVM_POWERPC_H */ diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h index 0951b17f4eb..7b1f0e0fc65 100644 --- a/arch/powerpc/include/asm/kvm_asm.h +++ b/arch/powerpc/include/asm/kvm_asm.h @@ -64,8 +64,12 @@ #define BOOK3S_INTERRUPT_PROGRAM 0x700 #define BOOK3S_INTERRUPT_FP_UNAVAIL 0x800 #define BOOK3S_INTERRUPT_DECREMENTER 0x900 +#define BOOK3S_INTERRUPT_HV_DECREMENTER 0x980 #define BOOK3S_INTERRUPT_SYSCALL 0xc00 #define BOOK3S_INTERRUPT_TRACE 0xd00 +#define BOOK3S_INTERRUPT_H_DATA_STORAGE 0xe00 +#define BOOK3S_INTERRUPT_H_INST_STORAGE 0xe20 +#define BOOK3S_INTERRUPT_H_EMUL_ASSIST 0xe40 #define BOOK3S_INTERRUPT_PERFMON 0xf00 #define BOOK3S_INTERRUPT_ALTIVEC 0xf20 #define BOOK3S_INTERRUPT_VSX 0xf40 diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index d62e703f121..98da010252a 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -24,20 +24,6 @@ #include <linux/kvm_host.h> #include <asm/kvm_book3s_asm.h> -struct kvmppc_slb { - u64 esid; - u64 vsid; - u64 orige; - u64 origv; - bool valid : 1; - bool Ks : 1; - bool Kp : 1; - bool nx : 1; - bool large : 1; /* PTEs are 16MB */ - bool tb : 1; /* 1TB segment */ - bool class : 1; -}; - struct kvmppc_bat { u64 raw; u32 bepi; @@ -67,11 +53,22 @@ struct kvmppc_sid_map { #define VSID_POOL_SIZE (SID_CONTEXTS * 16) #endif +struct hpte_cache { + struct hlist_node list_pte; + struct hlist_node list_pte_long; + struct hlist_node list_vpte; + struct hlist_node list_vpte_long; + struct rcu_head rcu_head; + u64 host_va; + u64 pfn; + ulong slot; + struct kvmppc_pte pte; +}; + 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 { u64 esid; u64 vsid; @@ -81,7 +78,6 @@ struct kvmppc_vcpu_book3s { struct kvmppc_bat dbat[8]; u64 hid[6]; u64 gqr[8]; - int slb_nr; u64 sdr1; u64 hior; u64 msr_mask; @@ -93,7 +89,13 @@ struct kvmppc_vcpu_book3s { u64 vsid_max; #endif int context_id[SID_CONTEXTS]; - ulong prog_flags; /* flags to inject when giving a 700 trap */ + + struct hlist_head hpte_hash_pte[HPTEG_HASH_NUM_PTE]; + struct hlist_head hpte_hash_pte_long[HPTEG_HASH_NUM_PTE_LONG]; + struct hlist_head hpte_hash_vpte[HPTEG_HASH_NUM_VPTE]; + struct hlist_head hpte_hash_vpte_long[HPTEG_HASH_NUM_VPTE_LONG]; + int hpte_cache_count; + spinlock_t mmu_lock; }; #define CONTEXT_HOST 0 @@ -110,8 +112,10 @@ extern void kvmppc_mmu_pte_flush(struct kvm_vcpu *vcpu, ulong ea, ulong ea_mask) extern void kvmppc_mmu_pte_vflush(struct kvm_vcpu *vcpu, u64 vp, u64 vp_mask); extern void kvmppc_mmu_pte_pflush(struct kvm_vcpu *vcpu, ulong pa_start, ulong pa_end); extern void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 new_msr); +extern void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr); extern void kvmppc_mmu_book3s_64_init(struct kvm_vcpu *vcpu); extern void kvmppc_mmu_book3s_32_init(struct kvm_vcpu *vcpu); +extern void kvmppc_mmu_book3s_hv_init(struct kvm_vcpu *vcpu); extern int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte); extern int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr); extern void kvmppc_mmu_flush_segments(struct kvm_vcpu *vcpu); @@ -123,19 +127,22 @@ extern int kvmppc_mmu_hpte_init(struct kvm_vcpu *vcpu); extern void kvmppc_mmu_invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte); extern int kvmppc_mmu_hpte_sysinit(void); extern void kvmppc_mmu_hpte_sysexit(void); +extern int kvmppc_mmu_hv_init(void); extern int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, bool data); extern int kvmppc_st(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, bool data); extern void kvmppc_book3s_queue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec); +extern void kvmppc_inject_interrupt(struct kvm_vcpu *vcpu, int vec, u64 flags); extern void kvmppc_set_bat(struct kvm_vcpu *vcpu, struct kvmppc_bat *bat, bool upper, u32 val); extern void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr); extern int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu); extern pfn_t kvmppc_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn); -extern ulong kvmppc_trampoline_lowmem; -extern ulong kvmppc_trampoline_enter; +extern void kvmppc_handler_lowmem_trampoline(void); +extern void kvmppc_handler_trampoline_enter(void); extern void kvmppc_rmcall(ulong srr0, ulong srr1); +extern void kvmppc_hv_entry_trampoline(void); extern void kvmppc_load_up_fpu(void); extern void kvmppc_load_up_altivec(void); extern void kvmppc_load_up_vsx(void); @@ -147,15 +154,32 @@ static inline struct kvmppc_vcpu_book3s *to_book3s(struct kvm_vcpu *vcpu) return container_of(vcpu, struct kvmppc_vcpu_book3s, vcpu); } -static inline ulong dsisr(void) +extern void kvm_return_point(void); + +/* Also add subarch specific defines */ + +#ifdef CONFIG_KVM_BOOK3S_32_HANDLER +#include <asm/kvm_book3s_32.h> +#endif +#ifdef CONFIG_KVM_BOOK3S_64_HANDLER +#include <asm/kvm_book3s_64.h> +#endif + +#ifdef CONFIG_KVM_BOOK3S_PR + +static inline unsigned long kvmppc_interrupt_offset(struct kvm_vcpu *vcpu) { - ulong r; - asm ( "mfdsisr %0 " : "=r" (r) ); - return r; + return to_book3s(vcpu)->hior; } -extern void kvm_return_point(void); -static inline struct kvmppc_book3s_shadow_vcpu *to_svcpu(struct kvm_vcpu *vcpu); +static inline void kvmppc_update_int_pending(struct kvm_vcpu *vcpu, + unsigned long pending_now, unsigned long old_pending) +{ + if (pending_now) + vcpu->arch.shared->int_pending = 1; + else if (old_pending) + vcpu->arch.shared->int_pending = 0; +} static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val) { @@ -244,6 +268,120 @@ static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu) return to_svcpu(vcpu)->fault_dar; } +static inline bool kvmppc_critical_section(struct kvm_vcpu *vcpu) +{ + ulong crit_raw = vcpu->arch.shared->critical; + ulong crit_r1 = kvmppc_get_gpr(vcpu, 1); + bool crit; + + /* Truncate crit indicators in 32 bit mode */ + if (!(vcpu->arch.shared->msr & MSR_SF)) { + crit_raw &= 0xffffffff; + crit_r1 &= 0xffffffff; + } + + /* Critical section when crit == r1 */ + crit = (crit_raw == crit_r1); + /* ... and we're in supervisor mode */ + crit = crit && !(vcpu->arch.shared->msr & MSR_PR); + + return crit; +} +#else /* CONFIG_KVM_BOOK3S_PR */ + +static inline unsigned long kvmppc_interrupt_offset(struct kvm_vcpu *vcpu) +{ + return 0; +} + +static inline void kvmppc_update_int_pending(struct kvm_vcpu *vcpu, + unsigned long pending_now, unsigned long old_pending) +{ +} + +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; +} + +static inline void kvmppc_set_ctr(struct kvm_vcpu *vcpu, ulong val) +{ + vcpu->arch.ctr = val; +} + +static inline ulong kvmppc_get_ctr(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.ctr; +} + +static inline void kvmppc_set_lr(struct kvm_vcpu *vcpu, ulong val) +{ + vcpu->arch.lr = val; +} + +static inline ulong kvmppc_get_lr(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.lr; +} + +static inline void kvmppc_set_pc(struct kvm_vcpu *vcpu, ulong val) +{ + vcpu->arch.pc = val; +} + +static inline ulong kvmppc_get_pc(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.pc; +} + +static inline u32 kvmppc_get_last_inst(struct kvm_vcpu *vcpu) +{ + ulong pc = kvmppc_get_pc(vcpu); + + /* Load the instruction manually if it failed to do so in the + * exit path */ + if (vcpu->arch.last_inst == KVM_INST_FETCH_FAILED) + kvmppc_ld(vcpu, &pc, sizeof(u32), &vcpu->arch.last_inst, false); + + return vcpu->arch.last_inst; +} + +static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.fault_dar; +} + +static inline bool kvmppc_critical_section(struct kvm_vcpu *vcpu) +{ + return false; +} +#endif + /* Magic register values loaded into r3 and r4 before the 'sc' assembly * instruction for the OSI hypercalls */ #define OSI_SC_MAGIC_R3 0x113724FA @@ -251,12 +389,4 @@ static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu) #define INS_DCBZ 0x7c0007ec -/* Also add subarch specific defines */ - -#ifdef CONFIG_PPC_BOOK3S_32 -#include <asm/kvm_book3s_32.h> -#else -#include <asm/kvm_book3s_64.h> -#endif - #endif /* __ASM_KVM_BOOK3S_H__ */ diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index 4cadd612d57..e43fe42b987 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -20,9 +20,13 @@ #ifndef __ASM_KVM_BOOK3S_64_H__ #define __ASM_KVM_BOOK3S_64_H__ +#ifdef CONFIG_KVM_BOOK3S_PR static inline struct kvmppc_book3s_shadow_vcpu *to_svcpu(struct kvm_vcpu *vcpu) { return &get_paca()->shadow_vcpu; } +#endif + +#define SPAPR_TCE_SHIFT 12 #endif /* __ASM_KVM_BOOK3S_64_H__ */ diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h index d5a8a386163..ef7b3688c3b 100644 --- a/arch/powerpc/include/asm/kvm_book3s_asm.h +++ b/arch/powerpc/include/asm/kvm_book3s_asm.h @@ -60,6 +60,36 @@ kvmppc_resume_\intno: #else /*__ASSEMBLY__ */ +/* + * This struct goes in the PACA on 64-bit processors. It is used + * to store host state that needs to be saved when we enter a guest + * and restored when we exit, but isn't specific to any particular + * guest or vcpu. It also has some scratch fields used by the guest + * exit code. + */ +struct kvmppc_host_state { + ulong host_r1; + ulong host_r2; + ulong host_msr; + ulong vmhandler; + ulong scratch0; + ulong scratch1; + u8 in_guest; + +#ifdef CONFIG_KVM_BOOK3S_64_HV + struct kvm_vcpu *kvm_vcpu; + struct kvmppc_vcore *kvm_vcore; + unsigned long xics_phys; + u64 dabr; + u64 host_mmcr[3]; + u32 host_pmc[8]; + u64 host_purr; + u64 host_spurr; + u64 host_dscr; + u64 dec_expires; +#endif +}; + struct kvmppc_book3s_shadow_vcpu { ulong gpr[14]; u32 cr; @@ -73,17 +103,12 @@ struct kvmppc_book3s_shadow_vcpu { ulong shadow_srr1; ulong fault_dar; - ulong host_r1; - ulong host_r2; - ulong handler; - ulong scratch0; - ulong scratch1; - ulong vmhandler; - u8 in_guest; - #ifdef CONFIG_PPC_BOOK3S_32 u32 sr[16]; /* Guest SRs */ + + struct kvmppc_host_state hstate; #endif + #ifdef CONFIG_PPC_BOOK3S_64 u8 slb_max; /* highest used guest slb entry */ struct { diff --git a/arch/powerpc/include/asm/kvm_booke.h b/arch/powerpc/include/asm/kvm_booke.h index 9c9ba3d59b1..a90e0918877 100644 --- a/arch/powerpc/include/asm/kvm_booke.h +++ b/arch/powerpc/include/asm/kvm_booke.h @@ -93,4 +93,8 @@ static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu) return vcpu->arch.fault_dear; } +static inline ulong kvmppc_get_msr(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.shared->msr; +} #endif /* __ASM_KVM_BOOKE_H__ */ diff --git a/arch/powerpc/include/asm/kvm_e500.h b/arch/powerpc/include/asm/kvm_e500.h index 7a2a565f88c..adbfca9dd10 100644 --- a/arch/powerpc/include/asm/kvm_e500.h +++ b/arch/powerpc/include/asm/kvm_e500.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2008 Freescale Semiconductor, Inc. All rights reserved. + * Copyright (C) 2008-2011 Freescale Semiconductor, Inc. All rights reserved. * * Author: Yu Liu, <yu.liu@freescale.com> * @@ -29,17 +29,25 @@ struct tlbe{ u32 mas7; }; +#define E500_TLB_VALID 1 +#define E500_TLB_DIRTY 2 + +struct tlbe_priv { + pfn_t pfn; + unsigned int flags; /* E500_TLB_* */ +}; + +struct vcpu_id_table; + struct kvmppc_vcpu_e500 { /* Unmodified copy of the guest's TLB. */ - struct tlbe *guest_tlb[E500_TLB_NUM]; - /* TLB that's actually used when the guest is running. */ - struct tlbe *shadow_tlb[E500_TLB_NUM]; - /* Pages which are referenced in the shadow TLB. */ - struct page **shadow_pages[E500_TLB_NUM]; + struct tlbe *gtlb_arch[E500_TLB_NUM]; - unsigned int guest_tlb_size[E500_TLB_NUM]; - unsigned int shadow_tlb_size[E500_TLB_NUM]; - unsigned int guest_tlb_nv[E500_TLB_NUM]; + /* KVM internal information associated with each guest TLB entry */ + struct tlbe_priv *gtlb_priv[E500_TLB_NUM]; + + unsigned int gtlb_size[E500_TLB_NUM]; + unsigned int gtlb_nv[E500_TLB_NUM]; u32 host_pid[E500_PID_NUM]; u32 pid[E500_PID_NUM]; @@ -53,6 +61,10 @@ struct kvmppc_vcpu_e500 { u32 mas5; u32 mas6; u32 mas7; + + /* vcpu id table */ + struct vcpu_id_table *idt; + u32 l1csr0; u32 l1csr1; u32 hid0; diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 186f150b9b8..cc22b282d75 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -25,15 +25,23 @@ #include <linux/interrupt.h> #include <linux/types.h> #include <linux/kvm_types.h> +#include <linux/threads.h> +#include <linux/spinlock.h> #include <linux/kvm_para.h> +#include <linux/list.h> +#include <linux/atomic.h> #include <asm/kvm_asm.h> +#include <asm/processor.h> -#define KVM_MAX_VCPUS 1 +#define KVM_MAX_VCPUS NR_CPUS +#define KVM_MAX_VCORES NR_CPUS #define KVM_MEMORY_SLOTS 32 /* memory slots that does not exposed to userspace */ #define KVM_PRIVATE_MEM_SLOTS 4 +#ifdef CONFIG_KVM_MMIO #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 +#endif /* We don't currently support large pages. */ #define KVM_HPAGE_GFN_SHIFT(x) 0 @@ -57,6 +65,10 @@ struct kvm; struct kvm_run; struct kvm_vcpu; +struct lppaca; +struct slb_shadow; +struct dtl; + struct kvm_vm_stat { u32 remote_tlb_flush; }; @@ -133,9 +145,74 @@ struct kvmppc_exit_timing { }; }; +struct kvmppc_pginfo { + unsigned long pfn; + atomic_t refcnt; +}; + +struct kvmppc_spapr_tce_table { + struct list_head list; + struct kvm *kvm; + u64 liobn; + u32 window_size; + struct page *pages[0]; +}; + +struct kvmppc_rma_info { + void *base_virt; + unsigned long base_pfn; + unsigned long npages; + struct list_head list; + atomic_t use_count; +}; + struct kvm_arch { +#ifdef CONFIG_KVM_BOOK3S_64_HV + unsigned long hpt_virt; + unsigned long ram_npages; + unsigned long ram_psize; + unsigned long ram_porder; + struct kvmppc_pginfo *ram_pginfo; + unsigned int lpid; + unsigned int host_lpid; + unsigned long host_lpcr; + unsigned long sdr1; + unsigned long host_sdr1; + int tlbie_lock; + int n_rma_pages; + unsigned long lpcr; + unsigned long rmor; + struct kvmppc_rma_info *rma; + struct list_head spapr_tce_tables; + unsigned short last_vcpu[NR_CPUS]; + struct kvmppc_vcore *vcores[KVM_MAX_VCORES]; +#endif /* CONFIG_KVM_BOOK3S_64_HV */ }; +/* + * Struct for a virtual core. + * Note: entry_exit_count combines an entry count in the bottom 8 bits + * and an exit count in the next 8 bits. This is so that we can + * atomically increment the entry count iff the exit count is 0 + * without taking the lock. + */ +struct kvmppc_vcore { + int n_runnable; + int n_blocked; + int num_threads; + int entry_exit_count; + int n_woken; + int nap_count; + u16 pcpu; + u8 vcore_running; + u8 in_guest; + struct list_head runnable_threads; + spinlock_t lock; +}; + +#define VCORE_ENTRY_COUNT(vc) ((vc)->entry_exit_count & 0xff) +#define VCORE_EXIT_COUNT(vc) ((vc)->entry_exit_count >> 8) + struct kvmppc_pte { ulong eaddr; u64 vpage; @@ -163,16 +240,18 @@ struct kvmppc_mmu { bool (*is_dcbz32)(struct kvm_vcpu *vcpu); }; -struct hpte_cache { - struct hlist_node list_pte; - struct hlist_node list_pte_long; - struct hlist_node list_vpte; - struct hlist_node list_vpte_long; - struct rcu_head rcu_head; - u64 host_va; - u64 pfn; - ulong slot; - struct kvmppc_pte pte; +struct kvmppc_slb { + u64 esid; + u64 vsid; + u64 orige; + u64 origv; + bool valid : 1; + bool Ks : 1; + bool Kp : 1; + bool nx : 1; + bool large : 1; /* PTEs are 16MB */ + bool tb : 1; /* 1TB segment */ + bool class : 1; }; struct kvm_vcpu_arch { @@ -187,6 +266,9 @@ struct kvm_vcpu_arch { ulong highmem_handler; ulong rmcall; ulong host_paca_phys; + struct kvmppc_slb slb[64]; + int slb_max; /* 1 + index of last valid entry in slb[] */ + int slb_nr; /* total number of entries in SLB */ struct kvmppc_mmu mmu; #endif @@ -195,13 +277,19 @@ struct kvm_vcpu_arch { u64 fpr[32]; u64 fpscr; +#ifdef CONFIG_SPE + ulong evr[32]; + ulong spefscr; + ulong host_spefscr; + u64 acc; +#endif #ifdef CONFIG_ALTIVEC vector128 vr[32]; vector128 vscr; #endif #ifdef CONFIG_VSX - u64 vsr[32]; + u64 vsr[64]; #endif #ifdef CONFIG_PPC_BOOK3S @@ -209,22 +297,27 @@ struct kvm_vcpu_arch { u32 qpr[32]; #endif -#ifdef CONFIG_BOOKE ulong pc; ulong ctr; ulong lr; ulong xer; u32 cr; -#endif #ifdef CONFIG_PPC_BOOK3S - ulong shadow_msr; ulong hflags; ulong guest_owned_ext; + ulong purr; + ulong spurr; + ulong dscr; + ulong amr; + ulong uamor; + u32 ctrl; + ulong dabr; #endif u32 vrsave; /* also USPRG0 */ u32 mmucr; + ulong shadow_msr; ulong sprg4; ulong sprg5; ulong sprg6; @@ -249,6 +342,7 @@ struct kvm_vcpu_arch { u32 pvr; u32 shadow_pid; + u32 shadow_pid1; u32 pid; u32 swap_pid; @@ -258,6 +352,9 @@ struct kvm_vcpu_arch { u32 dbcr1; u32 dbsr; + u64 mmcr[3]; + u32 pmc[8]; + #ifdef CONFIG_KVM_EXIT_TIMING struct mutex exit_timing_lock; struct kvmppc_exit_timing timing_exit; @@ -272,8 +369,12 @@ struct kvm_vcpu_arch { struct dentry *debugfs_exit_timing; #endif +#ifdef CONFIG_PPC_BOOK3S + ulong fault_dar; + u32 fault_dsisr; +#endif + #ifdef CONFIG_BOOKE - u32 last_inst; ulong fault_dear; ulong fault_esr; ulong queued_dear; @@ -288,25 +389,47 @@ struct kvm_vcpu_arch { u8 dcr_is_write; u8 osi_needed; u8 osi_enabled; + u8 hcall_needed; u32 cpr0_cfgaddr; /* holds the last set cpr0_cfgaddr */ struct hrtimer dec_timer; struct tasklet_struct tasklet; u64 dec_jiffies; + u64 dec_expires; unsigned long pending_exceptions; + u16 last_cpu; + u8 ceded; + u8 prodded; + u32 last_inst; + + struct lppaca *vpa; + struct slb_shadow *slb_shadow; + struct dtl *dtl; + struct dtl *dtl_end; + + struct kvmppc_vcore *vcore; + int ret; + int trap; + int state; + int ptid; + wait_queue_head_t cpu_run; + struct kvm_vcpu_arch_shared *shared; unsigned long magic_page_pa; /* phys addr to map the magic page to */ unsigned long magic_page_ea; /* effect. addr to map the magic page to */ -#ifdef CONFIG_PPC_BOOK3S - struct hlist_head hpte_hash_pte[HPTEG_HASH_NUM_PTE]; - struct hlist_head hpte_hash_pte_long[HPTEG_HASH_NUM_PTE_LONG]; - struct hlist_head hpte_hash_vpte[HPTEG_HASH_NUM_VPTE]; - struct hlist_head hpte_hash_vpte_long[HPTEG_HASH_NUM_VPTE_LONG]; - int hpte_cache_count; - spinlock_t mmu_lock; +#ifdef CONFIG_KVM_BOOK3S_64_HV + struct kvm_vcpu_arch_shared shregs; + + struct list_head run_list; + struct task_struct *run_task; + struct kvm_run *kvm_run; #endif }; +#define KVMPPC_VCPU_BUSY_IN_HOST 0 +#define KVMPPC_VCPU_BLOCKED 1 +#define KVMPPC_VCPU_RUNNABLE 2 + #endif /* __POWERPC_KVM_HOST_H__ */ diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index 9345238edec..d121f49d62b 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -33,6 +33,9 @@ #else #include <asm/kvm_booke.h> #endif +#ifdef CONFIG_KVM_BOOK3S_64_HANDLER +#include <asm/paca.h> +#endif enum emulation_result { EMULATE_DONE, /* no further processing */ @@ -42,6 +45,7 @@ enum emulation_result { EMULATE_AGAIN, /* something went wrong. go again */ }; +extern int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu); extern int __kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu); extern char kvmppc_handlers_start[]; extern unsigned long kvmppc_handler_len; @@ -109,6 +113,27 @@ extern void kvmppc_booke_exit(void); extern void kvmppc_core_destroy_mmu(struct kvm_vcpu *vcpu); extern int kvmppc_kvm_pv(struct kvm_vcpu *vcpu); +extern void kvmppc_map_magic(struct kvm_vcpu *vcpu); + +extern long kvmppc_alloc_hpt(struct kvm *kvm); +extern void kvmppc_free_hpt(struct kvm *kvm); +extern long kvmppc_prepare_vrma(struct kvm *kvm, + struct kvm_userspace_memory_region *mem); +extern void kvmppc_map_vrma(struct kvm *kvm, + struct kvm_userspace_memory_region *mem); +extern int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu); +extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm, + struct kvm_create_spapr_tce *args); +extern long kvm_vm_ioctl_allocate_rma(struct kvm *kvm, + struct kvm_allocate_rma *rma); +extern struct kvmppc_rma_info *kvm_alloc_rma(void); +extern void kvm_release_rma(struct kvmppc_rma_info *ri); +extern int kvmppc_core_init_vm(struct kvm *kvm); +extern void kvmppc_core_destroy_vm(struct kvm *kvm); +extern int kvmppc_core_prepare_memory_region(struct kvm *kvm, + struct kvm_userspace_memory_region *mem); +extern void kvmppc_core_commit_memory_region(struct kvm *kvm, + struct kvm_userspace_memory_region *mem); /* * Cuts out inst bits with ordering according to spec. @@ -151,4 +176,20 @@ int kvmppc_set_sregs_ivor(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs); void kvmppc_set_pid(struct kvm_vcpu *vcpu, u32 pid); +#ifdef CONFIG_KVM_BOOK3S_64_HV +static inline void kvmppc_set_xics_phys(int cpu, unsigned long addr) +{ + paca[cpu].kvm_hstate.xics_phys = addr; +} + +extern void kvm_rma_init(void); + +#else +static inline void kvmppc_set_xics_phys(int cpu, unsigned long addr) +{} + +static inline void kvm_rma_init(void) +{} +#endif + #endif /* __POWERPC_KVM_PPC_H__ */ diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h index d865bd909c7..b445e0af4c2 100644 --- a/arch/powerpc/include/asm/mmu-hash64.h +++ b/arch/powerpc/include/asm/mmu-hash64.h @@ -90,13 +90,19 @@ extern char initial_stab[]; #define HPTE_R_PP0 ASM_CONST(0x8000000000000000) #define HPTE_R_TS ASM_CONST(0x4000000000000000) +#define HPTE_R_KEY_HI ASM_CONST(0x3000000000000000) #define HPTE_R_RPN_SHIFT 12 -#define HPTE_R_RPN ASM_CONST(0x3ffffffffffff000) -#define HPTE_R_FLAGS ASM_CONST(0x00000000000003ff) +#define HPTE_R_RPN ASM_CONST(0x0ffffffffffff000) #define HPTE_R_PP ASM_CONST(0x0000000000000003) #define HPTE_R_N ASM_CONST(0x0000000000000004) +#define HPTE_R_G ASM_CONST(0x0000000000000008) +#define HPTE_R_M ASM_CONST(0x0000000000000010) +#define HPTE_R_I ASM_CONST(0x0000000000000020) +#define HPTE_R_W ASM_CONST(0x0000000000000040) +#define HPTE_R_WIMG ASM_CONST(0x0000000000000078) #define HPTE_R_C ASM_CONST(0x0000000000000080) #define HPTE_R_R ASM_CONST(0x0000000000000100) +#define HPTE_R_KEY_LO ASM_CONST(0x0000000000000e00) #define HPTE_V_1TB_SEG ASM_CONST(0x4000000000000000) #define HPTE_V_VRMA_MASK ASM_CONST(0x4001ffffff000000) diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index 74126765106..a6da1285995 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -147,9 +147,12 @@ struct paca_struct { struct dtl_entry *dtl_curr; /* pointer corresponding to dtl_ridx */ #ifdef CONFIG_KVM_BOOK3S_HANDLER +#ifdef CONFIG_KVM_BOOK3S_PR /* We use this to store guest state in */ struct kvmppc_book3s_shadow_vcpu shadow_vcpu; #endif + struct kvmppc_host_state kvm_hstate; +#endif }; extern struct paca_struct *paca; diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h index b90dbf8e5cd..90bd3ed4816 100644 --- a/arch/powerpc/include/asm/pci-bridge.h +++ b/arch/powerpc/include/asm/pci-bridge.h @@ -171,15 +171,9 @@ static inline struct pci_controller *pci_bus_to_host(const struct pci_bus *bus) #ifndef CONFIG_PPC64 -static inline struct device_node *pci_bus_to_OF_node(struct pci_bus *bus) -{ - struct pci_controller *host; - - if (bus->self) - return pci_device_to_OF_node(bus->self); - host = pci_bus_to_host(bus); - return host ? host->dn : NULL; -} +extern int pci_device_from_OF_node(struct device_node *node, + u8 *bus, u8 *devfn); +extern void pci_create_OF_bus_map(void); static inline int isa_vaddr_is_ioport(void __iomem *address) { @@ -223,17 +217,8 @@ struct pci_dn { /* Get the pointer to a device_node's pci_dn */ #define PCI_DN(dn) ((struct pci_dn *) (dn)->data) -extern struct device_node *fetch_dev_dn(struct pci_dev *dev); extern void * update_dn_pci_info(struct device_node *dn, void *data); -/* Get a device_node from a pci_dev. This code must be fast except - * in the case where the sysdata is incorrect and needs to be fixed - * up (this will only happen once). */ -static inline struct device_node *pci_device_to_OF_node(struct pci_dev *dev) -{ - return dev->dev.of_node ? dev->dev.of_node : fetch_dev_dn(dev); -} - static inline int pci_device_from_OF_node(struct device_node *np, u8 *bus, u8 *devfn) { @@ -244,14 +229,6 @@ static inline int pci_device_from_OF_node(struct device_node *np, return 0; } -static inline struct device_node *pci_bus_to_OF_node(struct pci_bus *bus) -{ - if (bus->self) - return pci_device_to_OF_node(bus->self); - else - return bus->dev.of_node; /* Must be root bus (PHB) */ -} - /** Find the bus corresponding to the indicated device node */ extern struct pci_bus *pcibios_find_pci_bus(struct device_node *dn); diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h index 7d7790954e0..1f522680ea1 100644 --- a/arch/powerpc/include/asm/pci.h +++ b/arch/powerpc/include/asm/pci.h @@ -179,8 +179,7 @@ extern int remove_phb_dynamic(struct pci_controller *phb); extern struct pci_dev *of_create_pci_dev(struct device_node *node, struct pci_bus *bus, int devfn); -extern void of_scan_pci_bridge(struct device_node *node, - struct pci_dev *dev); +extern void of_scan_pci_bridge(struct pci_dev *dev); extern void of_scan_bus(struct device_node *node, struct pci_bus *bus); extern void of_rescan_bus(struct device_node *node, struct pci_bus *bus); diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index e472659d906..e980faae422 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -71,6 +71,42 @@ #define PPC_INST_ERATSX 0x7c000126 #define PPC_INST_ERATSX_DOT 0x7c000127 +/* Misc instructions for BPF compiler */ +#define PPC_INST_LD 0xe8000000 +#define PPC_INST_LHZ 0xa0000000 +#define PPC_INST_LWZ 0x80000000 +#define PPC_INST_STD 0xf8000000 +#define PPC_INST_STDU 0xf8000001 +#define PPC_INST_MFLR 0x7c0802a6 +#define PPC_INST_MTLR 0x7c0803a6 +#define PPC_INST_CMPWI 0x2c000000 +#define PPC_INST_CMPDI 0x2c200000 +#define PPC_INST_CMPLW 0x7c000040 +#define PPC_INST_CMPLWI 0x28000000 +#define PPC_INST_ADDI 0x38000000 +#define PPC_INST_ADDIS 0x3c000000 +#define PPC_INST_ADD 0x7c000214 +#define PPC_INST_SUB 0x7c000050 +#define PPC_INST_BLR 0x4e800020 +#define PPC_INST_BLRL 0x4e800021 +#define PPC_INST_MULLW 0x7c0001d6 +#define PPC_INST_MULHWU 0x7c000016 +#define PPC_INST_MULLI 0x1c000000 +#define PPC_INST_DIVWU 0x7c0003d6 +#define PPC_INST_RLWINM 0x54000000 +#define PPC_INST_RLDICR 0x78000004 +#define PPC_INST_SLW 0x7c000030 +#define PPC_INST_SRW 0x7c000430 +#define PPC_INST_AND 0x7c000038 +#define PPC_INST_ANDDOT 0x7c000039 +#define PPC_INST_OR 0x7c000378 +#define PPC_INST_ANDI 0x70000000 +#define PPC_INST_ORI 0x60000000 +#define PPC_INST_ORIS 0x64000000 +#define PPC_INST_NEG 0x7c0000d0 +#define PPC_INST_BRANCH 0x48000000 +#define PPC_INST_BRANCH_COND 0x40800000 + /* macros to insert fields into opcodes */ #define __PPC_RA(a) (((a) & 0x1f) << 16) #define __PPC_RB(b) (((b) & 0x1f) << 11) @@ -83,6 +119,10 @@ #define __PPC_T_TLB(t) (((t) & 0x3) << 21) #define __PPC_WC(w) (((w) & 0x3) << 21) #define __PPC_WS(w) (((w) & 0x1f) << 11) +#define __PPC_SH(s) __PPC_WS(s) +#define __PPC_MB(s) (((s) & 0x1f) << 6) +#define __PPC_ME(s) (((s) & 0x1f) << 1) +#define __PPC_BI(s) (((s) & 0x1f) << 16) /* * Only use the larx hint bit on 64bit CPUs. e500v1/v2 based CPUs will treat a diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h index 1b422381fc1..368f72f7980 100644 --- a/arch/powerpc/include/asm/ppc_asm.h +++ b/arch/powerpc/include/asm/ppc_asm.h @@ -150,18 +150,22 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR) #define REST_16VSRSU(n,b,base) REST_8VSRSU(n,b,base); REST_8VSRSU(n+8,b,base) #define REST_32VSRSU(n,b,base) REST_16VSRSU(n,b,base); REST_16VSRSU(n+16,b,base) -#define SAVE_EVR(n,s,base) evmergehi s,s,n; stw s,THREAD_EVR0+4*(n)(base) -#define SAVE_2EVRS(n,s,base) SAVE_EVR(n,s,base); SAVE_EVR(n+1,s,base) -#define SAVE_4EVRS(n,s,base) SAVE_2EVRS(n,s,base); SAVE_2EVRS(n+2,s,base) -#define SAVE_8EVRS(n,s,base) SAVE_4EVRS(n,s,base); SAVE_4EVRS(n+4,s,base) -#define SAVE_16EVRS(n,s,base) SAVE_8EVRS(n,s,base); SAVE_8EVRS(n+8,s,base) -#define SAVE_32EVRS(n,s,base) SAVE_16EVRS(n,s,base); SAVE_16EVRS(n+16,s,base) -#define REST_EVR(n,s,base) lwz s,THREAD_EVR0+4*(n)(base); evmergelo n,s,n -#define REST_2EVRS(n,s,base) REST_EVR(n,s,base); REST_EVR(n+1,s,base) -#define REST_4EVRS(n,s,base) REST_2EVRS(n,s,base); REST_2EVRS(n+2,s,base) -#define REST_8EVRS(n,s,base) REST_4EVRS(n,s,base); REST_4EVRS(n+4,s,base) -#define REST_16EVRS(n,s,base) REST_8EVRS(n,s,base); REST_8EVRS(n+8,s,base) -#define REST_32EVRS(n,s,base) REST_16EVRS(n,s,base); REST_16EVRS(n+16,s,base) +/* + * b = base register for addressing, o = base offset from register of 1st EVR + * n = first EVR, s = scratch + */ +#define SAVE_EVR(n,s,b,o) evmergehi s,s,n; stw s,o+4*(n)(b) +#define SAVE_2EVRS(n,s,b,o) SAVE_EVR(n,s,b,o); SAVE_EVR(n+1,s,b,o) +#define SAVE_4EVRS(n,s,b,o) SAVE_2EVRS(n,s,b,o); SAVE_2EVRS(n+2,s,b,o) +#define SAVE_8EVRS(n,s,b,o) SAVE_4EVRS(n,s,b,o); SAVE_4EVRS(n+4,s,b,o) +#define SAVE_16EVRS(n,s,b,o) SAVE_8EVRS(n,s,b,o); SAVE_8EVRS(n+8,s,b,o) +#define SAVE_32EVRS(n,s,b,o) SAVE_16EVRS(n,s,b,o); SAVE_16EVRS(n+16,s,b,o) +#define REST_EVR(n,s,b,o) lwz s,o+4*(n)(b); evmergelo n,s,n +#define REST_2EVRS(n,s,b,o) REST_EVR(n,s,b,o); REST_EVR(n+1,s,b,o) +#define REST_4EVRS(n,s,b,o) REST_2EVRS(n,s,b,o); REST_2EVRS(n+2,s,b,o) +#define REST_8EVRS(n,s,b,o) REST_4EVRS(n,s,b,o); REST_4EVRS(n+4,s,b,o) +#define REST_16EVRS(n,s,b,o) REST_8EVRS(n,s,b,o); REST_8EVRS(n+8,s,b,o) +#define REST_32EVRS(n,s,b,o) REST_16EVRS(n,s,b,o); REST_16EVRS(n+16,s,b,o) /* Macros to adjust thread priority for hardware multithreading */ #define HMT_VERY_LOW or 31,31,31 # very low priority diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h index c189aa5fe1f..b823536375d 100644 --- a/arch/powerpc/include/asm/prom.h +++ b/arch/powerpc/include/asm/prom.h @@ -22,20 +22,6 @@ #define HAVE_ARCH_DEVTREE_FIXUPS -#ifdef CONFIG_PPC32 -/* - * PCI <-> OF matching functions - * (XXX should these be here?) - */ -struct pci_bus; -struct pci_dev; -extern int pci_device_from_OF_node(struct device_node *node, - u8* bus, u8* devfn); -extern struct device_node* pci_busdev_to_OF_node(struct pci_bus *, int); -extern struct device_node* pci_device_to_OF_node(struct pci_dev *); -extern void pci_create_OF_bus_map(void); -#endif - /* * OF address retreival & translation */ diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index c5cae0dd176..ddbe57ae858 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -189,6 +189,9 @@ #define SPRN_CTR 0x009 /* Count Register */ #define SPRN_DSCR 0x11 #define SPRN_CFAR 0x1c /* Come From Address Register */ +#define SPRN_AMR 0x1d /* Authority Mask Register */ +#define SPRN_UAMOR 0x9d /* User Authority Mask Override Register */ +#define SPRN_AMOR 0x15d /* Authority Mask Override Register */ #define SPRN_ACOP 0x1F /* Available Coprocessor Register */ #define SPRN_CTRLF 0x088 #define SPRN_CTRLT 0x098 @@ -232,22 +235,28 @@ #define LPCR_VPM0 (1ul << (63-0)) #define LPCR_VPM1 (1ul << (63-1)) #define LPCR_ISL (1ul << (63-2)) +#define LPCR_VC_SH (63-2) #define LPCR_DPFD_SH (63-11) #define LPCR_VRMA_L (1ul << (63-12)) #define LPCR_VRMA_LP0 (1ul << (63-15)) #define LPCR_VRMA_LP1 (1ul << (63-16)) +#define LPCR_VRMASD_SH (63-16) #define LPCR_RMLS 0x1C000000 /* impl dependent rmo limit sel */ +#define LPCR_RMLS_SH (63-37) #define LPCR_ILE 0x02000000 /* !HV irqs set MSR:LE */ #define LPCR_PECE 0x00007000 /* powersave exit cause enable */ #define LPCR_PECE0 0x00004000 /* ext. exceptions can cause exit */ #define LPCR_PECE1 0x00002000 /* decrementer can cause exit */ #define LPCR_PECE2 0x00001000 /* machine check etc can cause exit */ #define LPCR_MER 0x00000800 /* Mediated External Exception */ +#define LPCR_LPES 0x0000000c #define LPCR_LPES0 0x00000008 /* LPAR Env selector 0 */ #define LPCR_LPES1 0x00000004 /* LPAR Env selector 1 */ +#define LPCR_LPES_SH 2 #define LPCR_RMI 0x00000002 /* real mode is cache inhibit */ #define LPCR_HDICE 0x00000001 /* Hyp Decr enable (HV,PR,EE) */ #define SPRN_LPID 0x13F /* Logical Partition Identifier */ +#define LPID_RSVD 0x3ff /* Reserved LPID for partn switching */ #define SPRN_HMER 0x150 /* Hardware m? error recovery */ #define SPRN_HMEER 0x151 /* Hardware m? enable error recovery */ #define SPRN_HEIR 0x153 /* Hypervisor Emulated Instruction Register */ @@ -298,6 +307,7 @@ #define SPRN_HASH1 0x3D2 /* Primary Hash Address Register */ #define SPRN_HASH2 0x3D3 /* Secondary Hash Address Resgister */ #define SPRN_HID0 0x3F0 /* Hardware Implementation Register 0 */ +#define HID0_HDICE_SH (63 - 23) /* 970 HDEC interrupt enable */ #define HID0_EMCP (1<<31) /* Enable Machine Check pin */ #define HID0_EBA (1<<29) /* Enable Bus Address Parity */ #define HID0_EBD (1<<28) /* Enable Bus Data Parity */ @@ -353,6 +363,13 @@ #define SPRN_IABR2 0x3FA /* 83xx */ #define SPRN_IBCR 0x135 /* 83xx Insn Breakpoint Control Reg */ #define SPRN_HID4 0x3F4 /* 970 HID4 */ +#define HID4_LPES0 (1ul << (63-0)) /* LPAR env. sel. bit 0 */ +#define HID4_RMLS2_SH (63 - 2) /* Real mode limit bottom 2 bits */ +#define HID4_LPID5_SH (63 - 6) /* partition ID bottom 4 bits */ +#define HID4_RMOR_SH (63 - 22) /* real mode offset (16 bits) */ +#define HID4_LPES1 (1 << (63-57)) /* LPAR env. sel. bit 1 */ +#define HID4_RMLS0_SH (63 - 58) /* Real mode limit top bit */ +#define HID4_LPID1_SH 0 /* partition ID top 2 bits */ #define SPRN_HID4_GEKKO 0x3F3 /* Gekko HID4 */ #define SPRN_HID5 0x3F6 /* 970 HID5 */ #define SPRN_HID6 0x3F9 /* BE HID 6 */ @@ -802,28 +819,28 @@ mfspr rX,SPRN_SPRG_PACA; \ FTR_SECTION_ELSE_NESTED(66); \ mfspr rX,SPRN_SPRG_HPACA; \ - ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_HVMODE_206, 66) + ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_HVMODE, 66) #define SET_PACA(rX) \ BEGIN_FTR_SECTION_NESTED(66); \ mtspr SPRN_SPRG_PACA,rX; \ FTR_SECTION_ELSE_NESTED(66); \ mtspr SPRN_SPRG_HPACA,rX; \ - ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_HVMODE_206, 66) + ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_HVMODE, 66) #define GET_SCRATCH0(rX) \ BEGIN_FTR_SECTION_NESTED(66); \ mfspr rX,SPRN_SPRG_SCRATCH0; \ FTR_SECTION_ELSE_NESTED(66); \ mfspr rX,SPRN_SPRG_HSCRATCH0; \ - ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_HVMODE_206, 66) + ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_HVMODE, 66) #define SET_SCRATCH0(rX) \ BEGIN_FTR_SECTION_NESTED(66); \ mtspr SPRN_SPRG_SCRATCH0,rX; \ FTR_SECTION_ELSE_NESTED(66); \ mtspr SPRN_SPRG_HSCRATCH0,rX; \ - ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_HVMODE_206, 66) + ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_HVMODE, 66) #else /* CONFIG_PPC_BOOK3S_64 */ #define GET_SCRATCH0(rX) mfspr rX,SPRN_SPRG_SCRATCH0 diff --git a/arch/powerpc/include/asm/reg_booke.h b/arch/powerpc/include/asm/reg_booke.h index 0f0ad9fa01c..9ec0b39f9dd 100644 --- a/arch/powerpc/include/asm/reg_booke.h +++ b/arch/powerpc/include/asm/reg_booke.h @@ -318,6 +318,7 @@ #define ESR_ILK 0x00100000 /* Instr. Cache Locking */ #define ESR_PUO 0x00040000 /* Unimplemented Operation exception */ #define ESR_BO 0x00020000 /* Byte Ordering */ +#define ESR_SPV 0x00000080 /* Signal Processing operation */ /* Bit definitions related to the DBCR0. */ #if defined(CONFIG_40x) diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 36e1c8a29be..54b935f2f5d 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -128,6 +128,7 @@ int main(void) DEFINE(ICACHEL1LINESPERPAGE, offsetof(struct ppc64_caches, ilines_per_page)); /* paca */ DEFINE(PACA_SIZE, sizeof(struct paca_struct)); + DEFINE(PACA_LOCK_TOKEN, offsetof(struct paca_struct, lock_token)); DEFINE(PACAPACAINDEX, offsetof(struct paca_struct, paca_index)); DEFINE(PACAPROCSTART, offsetof(struct paca_struct, cpu_start)); DEFINE(PACAKSAVE, offsetof(struct paca_struct, kstack)); @@ -187,7 +188,9 @@ int main(void) DEFINE(LPPACASRR1, offsetof(struct lppaca, saved_srr1)); DEFINE(LPPACAANYINT, offsetof(struct lppaca, int_dword.any_int)); DEFINE(LPPACADECRINT, offsetof(struct lppaca, int_dword.fields.decr_int)); + DEFINE(LPPACA_PMCINUSE, offsetof(struct lppaca, pmcregs_in_use)); DEFINE(LPPACA_DTLIDX, offsetof(struct lppaca, dtl_idx)); + DEFINE(LPPACA_YIELDCOUNT, offsetof(struct lppaca, yield_count)); DEFINE(PACA_DTL_RIDX, offsetof(struct paca_struct, dtl_ridx)); #endif /* CONFIG_PPC_STD_MMU_64 */ DEFINE(PACAEMERGSP, offsetof(struct paca_struct, emergency_sp)); @@ -198,11 +201,6 @@ int main(void) DEFINE(PACA_USER_TIME, offsetof(struct paca_struct, user_time)); DEFINE(PACA_SYSTEM_TIME, offsetof(struct paca_struct, system_time)); DEFINE(PACA_TRAP_SAVE, offsetof(struct paca_struct, trap_save)); -#ifdef CONFIG_KVM_BOOK3S_64_HANDLER - DEFINE(PACA_KVM_SVCPU, offsetof(struct paca_struct, shadow_vcpu)); - DEFINE(SVCPU_SLB, offsetof(struct kvmppc_book3s_shadow_vcpu, slb)); - DEFINE(SVCPU_SLB_MAX, offsetof(struct kvmppc_book3s_shadow_vcpu, slb_max)); -#endif #endif /* CONFIG_PPC64 */ /* RTAS */ @@ -397,67 +395,160 @@ 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_VRSAVE, offsetof(struct kvm_vcpu, arch.vrsave)); + DEFINE(VCPU_FPRS, offsetof(struct kvm_vcpu, arch.fpr)); + DEFINE(VCPU_FPSCR, offsetof(struct kvm_vcpu, arch.fpscr)); +#ifdef CONFIG_ALTIVEC + DEFINE(VCPU_VRS, offsetof(struct kvm_vcpu, arch.vr)); + DEFINE(VCPU_VSCR, offsetof(struct kvm_vcpu, arch.vscr)); +#endif +#ifdef CONFIG_VSX + DEFINE(VCPU_VSRS, offsetof(struct kvm_vcpu, arch.vsr)); +#endif + DEFINE(VCPU_XER, offsetof(struct kvm_vcpu, arch.xer)); + DEFINE(VCPU_CTR, offsetof(struct kvm_vcpu, arch.ctr)); + DEFINE(VCPU_LR, offsetof(struct kvm_vcpu, arch.lr)); + DEFINE(VCPU_CR, offsetof(struct kvm_vcpu, arch.cr)); + DEFINE(VCPU_PC, offsetof(struct kvm_vcpu, arch.pc)); +#ifdef CONFIG_KVM_BOOK3S_64_HV + DEFINE(VCPU_MSR, offsetof(struct kvm_vcpu, arch.shregs.msr)); + DEFINE(VCPU_SRR0, offsetof(struct kvm_vcpu, arch.shregs.srr0)); + DEFINE(VCPU_SRR1, offsetof(struct kvm_vcpu, arch.shregs.srr1)); + DEFINE(VCPU_SPRG0, offsetof(struct kvm_vcpu, arch.shregs.sprg0)); + DEFINE(VCPU_SPRG1, offsetof(struct kvm_vcpu, arch.shregs.sprg1)); + DEFINE(VCPU_SPRG2, offsetof(struct kvm_vcpu, arch.shregs.sprg2)); + DEFINE(VCPU_SPRG3, offsetof(struct kvm_vcpu, arch.shregs.sprg3)); +#endif DEFINE(VCPU_SPRG4, offsetof(struct kvm_vcpu, arch.sprg4)); DEFINE(VCPU_SPRG5, offsetof(struct kvm_vcpu, arch.sprg5)); DEFINE(VCPU_SPRG6, offsetof(struct kvm_vcpu, arch.sprg6)); DEFINE(VCPU_SPRG7, offsetof(struct kvm_vcpu, arch.sprg7)); DEFINE(VCPU_SHADOW_PID, offsetof(struct kvm_vcpu, arch.shadow_pid)); + DEFINE(VCPU_SHADOW_PID1, offsetof(struct kvm_vcpu, arch.shadow_pid1)); DEFINE(VCPU_SHARED, offsetof(struct kvm_vcpu, arch.shared)); DEFINE(VCPU_SHARED_MSR, offsetof(struct kvm_vcpu_arch_shared, msr)); + DEFINE(VCPU_SHADOW_MSR, offsetof(struct kvm_vcpu, arch.shadow_msr)); /* book3s */ +#ifdef CONFIG_KVM_BOOK3S_64_HV + DEFINE(KVM_LPID, offsetof(struct kvm, arch.lpid)); + DEFINE(KVM_SDR1, offsetof(struct kvm, arch.sdr1)); + DEFINE(KVM_HOST_LPID, offsetof(struct kvm, arch.host_lpid)); + DEFINE(KVM_HOST_LPCR, offsetof(struct kvm, arch.host_lpcr)); + DEFINE(KVM_HOST_SDR1, offsetof(struct kvm, arch.host_sdr1)); + DEFINE(KVM_TLBIE_LOCK, offsetof(struct kvm, arch.tlbie_lock)); + DEFINE(KVM_ONLINE_CPUS, offsetof(struct kvm, online_vcpus.counter)); + DEFINE(KVM_LAST_VCPU, offsetof(struct kvm, arch.last_vcpu)); + DEFINE(KVM_LPCR, offsetof(struct kvm, arch.lpcr)); + DEFINE(KVM_RMOR, offsetof(struct kvm, arch.rmor)); + DEFINE(VCPU_DSISR, offsetof(struct kvm_vcpu, arch.shregs.dsisr)); + DEFINE(VCPU_DAR, offsetof(struct kvm_vcpu, arch.shregs.dar)); +#endif #ifdef CONFIG_PPC_BOOK3S + DEFINE(VCPU_KVM, offsetof(struct kvm_vcpu, kvm)); + DEFINE(VCPU_VCPUID, offsetof(struct kvm_vcpu, vcpu_id)); DEFINE(VCPU_HOST_RETIP, offsetof(struct kvm_vcpu, arch.host_retip)); DEFINE(VCPU_HOST_MSR, offsetof(struct kvm_vcpu, arch.host_msr)); - DEFINE(VCPU_SHADOW_MSR, offsetof(struct kvm_vcpu, arch.shadow_msr)); + DEFINE(VCPU_PURR, offsetof(struct kvm_vcpu, arch.purr)); + DEFINE(VCPU_SPURR, offsetof(struct kvm_vcpu, arch.spurr)); + DEFINE(VCPU_DSCR, offsetof(struct kvm_vcpu, arch.dscr)); + DEFINE(VCPU_AMR, offsetof(struct kvm_vcpu, arch.amr)); + DEFINE(VCPU_UAMOR, offsetof(struct kvm_vcpu, arch.uamor)); + DEFINE(VCPU_CTRL, offsetof(struct kvm_vcpu, arch.ctrl)); + DEFINE(VCPU_DABR, offsetof(struct kvm_vcpu, arch.dabr)); 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)); + DEFINE(VCPU_DEC, offsetof(struct kvm_vcpu, arch.dec)); + DEFINE(VCPU_DEC_EXPIRES, offsetof(struct kvm_vcpu, arch.dec_expires)); + DEFINE(VCPU_PENDING_EXC, offsetof(struct kvm_vcpu, arch.pending_exceptions)); + DEFINE(VCPU_VPA, offsetof(struct kvm_vcpu, arch.vpa)); + DEFINE(VCPU_MMCR, offsetof(struct kvm_vcpu, arch.mmcr)); + DEFINE(VCPU_PMC, offsetof(struct kvm_vcpu, arch.pmc)); + DEFINE(VCPU_SLB, offsetof(struct kvm_vcpu, arch.slb)); + DEFINE(VCPU_SLB_MAX, offsetof(struct kvm_vcpu, arch.slb_max)); + DEFINE(VCPU_SLB_NR, offsetof(struct kvm_vcpu, arch.slb_nr)); + DEFINE(VCPU_LAST_CPU, offsetof(struct kvm_vcpu, arch.last_cpu)); + DEFINE(VCPU_FAULT_DSISR, offsetof(struct kvm_vcpu, arch.fault_dsisr)); + DEFINE(VCPU_FAULT_DAR, offsetof(struct kvm_vcpu, arch.fault_dar)); + DEFINE(VCPU_LAST_INST, offsetof(struct kvm_vcpu, arch.last_inst)); + DEFINE(VCPU_TRAP, offsetof(struct kvm_vcpu, arch.trap)); + DEFINE(VCPU_PTID, offsetof(struct kvm_vcpu, arch.ptid)); + DEFINE(VCORE_ENTRY_EXIT, offsetof(struct kvmppc_vcore, entry_exit_count)); + DEFINE(VCORE_NAP_COUNT, offsetof(struct kvmppc_vcore, nap_count)); + DEFINE(VCORE_IN_GUEST, offsetof(struct kvmppc_vcore, in_guest)); DEFINE(VCPU_SVCPU, offsetof(struct kvmppc_vcpu_book3s, shadow_vcpu) - offsetof(struct kvmppc_vcpu_book3s, vcpu)); - DEFINE(SVCPU_CR, offsetof(struct kvmppc_book3s_shadow_vcpu, cr)); - DEFINE(SVCPU_XER, offsetof(struct kvmppc_book3s_shadow_vcpu, xer)); - DEFINE(SVCPU_CTR, offsetof(struct kvmppc_book3s_shadow_vcpu, ctr)); - DEFINE(SVCPU_LR, offsetof(struct kvmppc_book3s_shadow_vcpu, lr)); - DEFINE(SVCPU_PC, offsetof(struct kvmppc_book3s_shadow_vcpu, pc)); - DEFINE(SVCPU_R0, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[0])); - DEFINE(SVCPU_R1, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[1])); - DEFINE(SVCPU_R2, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[2])); - DEFINE(SVCPU_R3, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[3])); - DEFINE(SVCPU_R4, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[4])); - DEFINE(SVCPU_R5, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[5])); - DEFINE(SVCPU_R6, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[6])); - DEFINE(SVCPU_R7, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[7])); - DEFINE(SVCPU_R8, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[8])); - DEFINE(SVCPU_R9, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[9])); - DEFINE(SVCPU_R10, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[10])); - DEFINE(SVCPU_R11, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[11])); - DEFINE(SVCPU_R12, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[12])); - DEFINE(SVCPU_R13, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[13])); - DEFINE(SVCPU_HOST_R1, offsetof(struct kvmppc_book3s_shadow_vcpu, host_r1)); - DEFINE(SVCPU_HOST_R2, offsetof(struct kvmppc_book3s_shadow_vcpu, host_r2)); - DEFINE(SVCPU_VMHANDLER, offsetof(struct kvmppc_book3s_shadow_vcpu, - vmhandler)); - DEFINE(SVCPU_SCRATCH0, offsetof(struct kvmppc_book3s_shadow_vcpu, - scratch0)); - DEFINE(SVCPU_SCRATCH1, offsetof(struct kvmppc_book3s_shadow_vcpu, - scratch1)); - DEFINE(SVCPU_IN_GUEST, offsetof(struct kvmppc_book3s_shadow_vcpu, - in_guest)); - DEFINE(SVCPU_FAULT_DSISR, offsetof(struct kvmppc_book3s_shadow_vcpu, - fault_dsisr)); - DEFINE(SVCPU_FAULT_DAR, offsetof(struct kvmppc_book3s_shadow_vcpu, - fault_dar)); - DEFINE(SVCPU_LAST_INST, offsetof(struct kvmppc_book3s_shadow_vcpu, - last_inst)); - DEFINE(SVCPU_SHADOW_SRR1, offsetof(struct kvmppc_book3s_shadow_vcpu, - shadow_srr1)); + DEFINE(VCPU_SLB_E, offsetof(struct kvmppc_slb, orige)); + DEFINE(VCPU_SLB_V, offsetof(struct kvmppc_slb, origv)); + DEFINE(VCPU_SLB_SIZE, sizeof(struct kvmppc_slb)); + +#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_KVM_BOOK3S_PR +# define SVCPU_FIELD(x, f) DEFINE(x, offsetof(struct paca_struct, shadow_vcpu.f)) +#else +# define SVCPU_FIELD(x, f) +#endif +# define HSTATE_FIELD(x, f) DEFINE(x, offsetof(struct paca_struct, kvm_hstate.f)) +#else /* 32-bit */ +# define SVCPU_FIELD(x, f) DEFINE(x, offsetof(struct kvmppc_book3s_shadow_vcpu, f)) +# define HSTATE_FIELD(x, f) DEFINE(x, offsetof(struct kvmppc_book3s_shadow_vcpu, hstate.f)) +#endif + + SVCPU_FIELD(SVCPU_CR, cr); + SVCPU_FIELD(SVCPU_XER, xer); + SVCPU_FIELD(SVCPU_CTR, ctr); + SVCPU_FIELD(SVCPU_LR, lr); + SVCPU_FIELD(SVCPU_PC, pc); + SVCPU_FIELD(SVCPU_R0, gpr[0]); + SVCPU_FIELD(SVCPU_R1, gpr[1]); + SVCPU_FIELD(SVCPU_R2, gpr[2]); + SVCPU_FIELD(SVCPU_R3, gpr[3]); + SVCPU_FIELD(SVCPU_R4, gpr[4]); + SVCPU_FIELD(SVCPU_R5, gpr[5]); + SVCPU_FIELD(SVCPU_R6, gpr[6]); + SVCPU_FIELD(SVCPU_R7, gpr[7]); + SVCPU_FIELD(SVCPU_R8, gpr[8]); + SVCPU_FIELD(SVCPU_R9, gpr[9]); + SVCPU_FIELD(SVCPU_R10, gpr[10]); + SVCPU_FIELD(SVCPU_R11, gpr[11]); + SVCPU_FIELD(SVCPU_R12, gpr[12]); + SVCPU_FIELD(SVCPU_R13, gpr[13]); + SVCPU_FIELD(SVCPU_FAULT_DSISR, fault_dsisr); + SVCPU_FIELD(SVCPU_FAULT_DAR, fault_dar); + SVCPU_FIELD(SVCPU_LAST_INST, last_inst); + SVCPU_FIELD(SVCPU_SHADOW_SRR1, shadow_srr1); #ifdef CONFIG_PPC_BOOK3S_32 - DEFINE(SVCPU_SR, offsetof(struct kvmppc_book3s_shadow_vcpu, sr)); + SVCPU_FIELD(SVCPU_SR, sr); #endif -#else +#ifdef CONFIG_PPC64 + SVCPU_FIELD(SVCPU_SLB, slb); + SVCPU_FIELD(SVCPU_SLB_MAX, slb_max); +#endif + + HSTATE_FIELD(HSTATE_HOST_R1, host_r1); + HSTATE_FIELD(HSTATE_HOST_R2, host_r2); + HSTATE_FIELD(HSTATE_HOST_MSR, host_msr); + HSTATE_FIELD(HSTATE_VMHANDLER, vmhandler); + HSTATE_FIELD(HSTATE_SCRATCH0, scratch0); + HSTATE_FIELD(HSTATE_SCRATCH1, scratch1); + HSTATE_FIELD(HSTATE_IN_GUEST, in_guest); + +#ifdef CONFIG_KVM_BOOK3S_64_HV + HSTATE_FIELD(HSTATE_KVM_VCPU, kvm_vcpu); + HSTATE_FIELD(HSTATE_KVM_VCORE, kvm_vcore); + HSTATE_FIELD(HSTATE_XICS_PHYS, xics_phys); + HSTATE_FIELD(HSTATE_MMCR, host_mmcr); + HSTATE_FIELD(HSTATE_PMC, host_pmc); + HSTATE_FIELD(HSTATE_PURR, host_purr); + HSTATE_FIELD(HSTATE_SPURR, host_spurr); + HSTATE_FIELD(HSTATE_DSCR, host_dscr); + HSTATE_FIELD(HSTATE_DABR, dabr); + HSTATE_FIELD(HSTATE_DECEXP, dec_expires); +#endif /* CONFIG_KVM_BOOK3S_64_HV */ + +#else /* CONFIG_PPC_BOOK3S */ DEFINE(VCPU_CR, offsetof(struct kvm_vcpu, arch.cr)); DEFINE(VCPU_XER, offsetof(struct kvm_vcpu, arch.xer)); DEFINE(VCPU_LR, offsetof(struct kvm_vcpu, arch.lr)); @@ -467,7 +558,7 @@ int main(void) DEFINE(VCPU_FAULT_DEAR, offsetof(struct kvm_vcpu, arch.fault_dear)); DEFINE(VCPU_FAULT_ESR, offsetof(struct kvm_vcpu, arch.fault_esr)); #endif /* CONFIG_PPC_BOOK3S */ -#endif +#endif /* CONFIG_KVM */ #ifdef CONFIG_KVM_GUEST DEFINE(KVM_MAGIC_SCRATCH1, offsetof(struct kvm_vcpu_arch_shared, @@ -497,6 +588,13 @@ int main(void) DEFINE(TLBCAM_MAS7, offsetof(struct tlbcam, MAS7)); #endif +#if defined(CONFIG_KVM) && defined(CONFIG_SPE) + DEFINE(VCPU_EVR, offsetof(struct kvm_vcpu, arch.evr[0])); + DEFINE(VCPU_ACC, offsetof(struct kvm_vcpu, arch.acc)); + DEFINE(VCPU_SPEFSCR, offsetof(struct kvm_vcpu, arch.spefscr)); + DEFINE(VCPU_HOST_SPEFSCR, offsetof(struct kvm_vcpu, arch.host_spefscr)); +#endif + #ifdef CONFIG_KVM_EXIT_TIMING DEFINE(VCPU_TIMING_EXIT_TBU, offsetof(struct kvm_vcpu, arch.timing_exit.tv32.tbu)); diff --git a/arch/powerpc/kernel/cpu_setup_power7.S b/arch/powerpc/kernel/cpu_setup_power7.S index 4f9a93fcfe0..76797c5105d 100644 --- a/arch/powerpc/kernel/cpu_setup_power7.S +++ b/arch/powerpc/kernel/cpu_setup_power7.S @@ -45,12 +45,12 @@ _GLOBAL(__restore_cpu_power7) blr __init_hvmode_206: - /* Disable CPU_FTR_HVMODE_206 and exit if MSR:HV is not set */ + /* Disable CPU_FTR_HVMODE and exit if MSR:HV is not set */ mfmsr r3 rldicl. r0,r3,4,63 bnelr ld r5,CPU_SPEC_FEATURES(r4) - LOAD_REG_IMMEDIATE(r6,CPU_FTR_HVMODE_206) + LOAD_REG_IMMEDIATE(r6,CPU_FTR_HVMODE) xor r5,r5,r6 std r5,CPU_SPEC_FEATURES(r4) blr @@ -61,19 +61,23 @@ __init_LPCR: * LPES = 0b01 (HSRR0/1 used for 0x500) * PECE = 0b111 * DPFD = 4 + * HDICE = 0 + * VC = 0b100 (VPM0=1, VPM1=0, ISL=0) + * VRMASD = 0b10000 (L=1, LP=00) * * Other bits untouched for now */ mfspr r3,SPRN_LPCR - ori r3,r3,(LPCR_LPES0|LPCR_LPES1) - xori r3,r3, LPCR_LPES0 + li r5,1 + rldimi r3,r5, LPCR_LPES_SH, 64-LPCR_LPES_SH-2 ori r3,r3,(LPCR_PECE0|LPCR_PECE1|LPCR_PECE2) - li r5,7 - sldi r5,r5,LPCR_DPFD_SH - andc r3,r3,r5 li r5,4 - sldi r5,r5,LPCR_DPFD_SH - or r3,r3,r5 + rldimi r3,r5, LPCR_DPFD_SH, 64-LPCR_DPFD_SH-3 + clrrdi r3,r3,1 /* clear HDICE */ + li r5,4 + rldimi r3,r5, LPCR_VC_SH, 0 + li r5,0x10 + rldimi r3,r5, LPCR_VRMASD_SH, 64-LPCR_VRMASD_SH-5 mtspr SPRN_LPCR,r3 isync blr diff --git a/arch/powerpc/kernel/cpu_setup_ppc970.S b/arch/powerpc/kernel/cpu_setup_ppc970.S index 27f2507279d..12fac8df01c 100644 --- a/arch/powerpc/kernel/cpu_setup_ppc970.S +++ b/arch/powerpc/kernel/cpu_setup_ppc970.S @@ -76,7 +76,7 @@ _GLOBAL(__setup_cpu_ppc970) /* Do nothing if not running in HV mode */ mfmsr r0 rldicl. r0,r0,4,63 - beqlr + beq no_hv_mode mfspr r0,SPRN_HID0 li r11,5 /* clear DOZE and SLEEP */ @@ -90,7 +90,7 @@ _GLOBAL(__setup_cpu_ppc970MP) /* Do nothing if not running in HV mode */ mfmsr r0 rldicl. r0,r0,4,63 - beqlr + beq no_hv_mode mfspr r0,SPRN_HID0 li r11,0x15 /* clear DOZE and SLEEP */ @@ -109,6 +109,14 @@ load_hids: sync isync + /* Try to set LPES = 01 in HID4 */ + mfspr r0,SPRN_HID4 + clrldi r0,r0,1 /* clear LPES0 */ + ori r0,r0,HID4_LPES1 /* set LPES1 */ + sync + mtspr SPRN_HID4,r0 + isync + /* Save away cpu state */ LOAD_REG_ADDR(r5,cpu_state_storage) @@ -117,11 +125,21 @@ load_hids: std r3,CS_HID0(r5) mfspr r3,SPRN_HID1 std r3,CS_HID1(r5) - mfspr r3,SPRN_HID4 - std r3,CS_HID4(r5) + mfspr r4,SPRN_HID4 + std r4,CS_HID4(r5) mfspr r3,SPRN_HID5 std r3,CS_HID5(r5) + /* See if we successfully set LPES1 to 1; if not we are in Apple mode */ + andi. r4,r4,HID4_LPES1 + bnelr + +no_hv_mode: + /* Disable CPU_FTR_HVMODE and exit, since we don't have HV mode */ + ld r5,CPU_SPEC_FEATURES(r4) + LOAD_REG_IMMEDIATE(r6,CPU_FTR_HVMODE) + andc r5,r5,r6 + std r5,CPU_SPEC_FEATURES(r4) blr /* Called with no MMU context (typically MSR:IR/DR off) to diff --git a/arch/powerpc/kernel/e500-pmu.c b/arch/powerpc/kernel/e500-pmu.c index b150b510510..cb2e2949c8d 100644 --- a/arch/powerpc/kernel/e500-pmu.c +++ b/arch/powerpc/kernel/e500-pmu.c @@ -75,6 +75,11 @@ static int e500_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { [C(OP_WRITE)] = { -1, -1 }, [C(OP_PREFETCH)] = { -1, -1 }, }, + [C(NODE)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { -1, -1 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, }; static int num_events = 128; diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index a85f4874cba..41b02c792aa 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -40,7 +40,6 @@ __start_interrupts: .globl system_reset_pSeries; system_reset_pSeries: HMT_MEDIUM; - DO_KVM 0x100; SET_SCRATCH0(r13) #ifdef CONFIG_PPC_P7_NAP BEGIN_FTR_SECTION @@ -50,82 +49,73 @@ BEGIN_FTR_SECTION * state loss at this time. */ mfspr r13,SPRN_SRR1 - rlwinm r13,r13,47-31,30,31 - cmpwi cr0,r13,1 - bne 1f - b .power7_wakeup_noloss -1: cmpwi cr0,r13,2 - bne 1f - b .power7_wakeup_loss + rlwinm. r13,r13,47-31,30,31 + beq 9f + + /* waking up from powersave (nap) state */ + cmpwi cr1,r13,2 /* Total loss of HV state is fatal, we could try to use the * PIR to locate a PACA, then use an emergency stack etc... * but for now, let's just stay stuck here */ -1: cmpwi cr0,r13,3 - beq . -END_FTR_SECTION_IFSET(CPU_FTR_HVMODE_206) + bgt cr1,. + GET_PACA(r13) + +#ifdef CONFIG_KVM_BOOK3S_64_HV + lbz r0,PACAPROCSTART(r13) + cmpwi r0,0x80 + bne 1f + li r0,0 + stb r0,PACAPROCSTART(r13) + b kvm_start_guest +1: +#endif + + beq cr1,2f + b .power7_wakeup_noloss +2: b .power7_wakeup_loss +9: +END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) #endif /* CONFIG_PPC_P7_NAP */ - EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD) + EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD, + NOTEST, 0x100) . = 0x200 -_machine_check_pSeries: - HMT_MEDIUM - DO_KVM 0x200 - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common, EXC_STD) +machine_check_pSeries_1: + /* This is moved out of line as it can be patched by FW, but + * some code path might still want to branch into the original + * vector + */ + b machine_check_pSeries . = 0x300 .globl data_access_pSeries data_access_pSeries: HMT_MEDIUM - DO_KVM 0x300 SET_SCRATCH0(r13) +#ifndef CONFIG_POWER4_ONLY BEGIN_FTR_SECTION - GET_PACA(r13) - std r9,PACA_EXSLB+EX_R9(r13) - std r10,PACA_EXSLB+EX_R10(r13) - mfspr r10,SPRN_DAR - mfspr r9,SPRN_DSISR - srdi r10,r10,60 - rlwimi r10,r9,16,0x20 - mfcr r9 - cmpwi r10,0x2c - beq do_stab_bolted_pSeries - ld r10,PACA_EXSLB+EX_R10(r13) - std r11,PACA_EXGEN+EX_R11(r13) - ld r11,PACA_EXSLB+EX_R9(r13) - std r12,PACA_EXGEN+EX_R12(r13) - GET_SCRATCH0(r12) - std r10,PACA_EXGEN+EX_R10(r13) - std r11,PACA_EXGEN+EX_R9(r13) - std r12,PACA_EXGEN+EX_R13(r13) - EXCEPTION_PROLOG_PSERIES_1(data_access_common, EXC_STD) -FTR_SECTION_ELSE - EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, data_access_common, EXC_STD) -ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_SLB) + b data_access_check_stab +data_access_not_stab: +END_MMU_FTR_SECTION_IFCLR(MMU_FTR_SLB) +#endif + EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, data_access_common, EXC_STD, + KVMTEST_PR, 0x300) . = 0x380 .globl data_access_slb_pSeries data_access_slb_pSeries: HMT_MEDIUM - DO_KVM 0x380 SET_SCRATCH0(r13) - GET_PACA(r13) + EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST_PR, 0x380) std r3,PACA_EXSLB+EX_R3(r13) mfspr r3,SPRN_DAR - std r9,PACA_EXSLB+EX_R9(r13) /* save r9 - r12 */ - mfcr r9 #ifdef __DISABLED__ /* Keep that around for when we re-implement dynamic VSIDs */ cmpdi r3,0 bge slb_miss_user_pseries #endif /* __DISABLED__ */ - std r10,PACA_EXSLB+EX_R10(r13) - std r11,PACA_EXSLB+EX_R11(r13) - std r12,PACA_EXSLB+EX_R12(r13) - GET_SCRATCH0(r10) - std r10,PACA_EXSLB+EX_R13(r13) - mfspr r12,SPRN_SRR1 /* and SRR1 */ + mfspr r12,SPRN_SRR1 #ifndef CONFIG_RELOCATABLE b .slb_miss_realmode #else @@ -147,24 +137,16 @@ data_access_slb_pSeries: .globl instruction_access_slb_pSeries instruction_access_slb_pSeries: HMT_MEDIUM - DO_KVM 0x480 SET_SCRATCH0(r13) - GET_PACA(r13) + EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST_PR, 0x480) std r3,PACA_EXSLB+EX_R3(r13) mfspr r3,SPRN_SRR0 /* SRR0 is faulting address */ - std r9,PACA_EXSLB+EX_R9(r13) /* save r9 - r12 */ - mfcr r9 #ifdef __DISABLED__ /* Keep that around for when we re-implement dynamic VSIDs */ cmpdi r3,0 bge slb_miss_user_pseries #endif /* __DISABLED__ */ - std r10,PACA_EXSLB+EX_R10(r13) - std r11,PACA_EXSLB+EX_R11(r13) - std r12,PACA_EXSLB+EX_R12(r13) - GET_SCRATCH0(r10) - std r10,PACA_EXSLB+EX_R13(r13) - mfspr r12,SPRN_SRR1 /* and SRR1 */ + mfspr r12,SPRN_SRR1 #ifndef CONFIG_RELOCATABLE b .slb_miss_realmode #else @@ -184,26 +166,46 @@ instruction_access_slb_pSeries: hardware_interrupt_pSeries: hardware_interrupt_hv: BEGIN_FTR_SECTION - _MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt, EXC_STD) + _MASKABLE_EXCEPTION_PSERIES(0x502, hardware_interrupt, + EXC_HV, SOFTEN_TEST_HV) + KVM_HANDLER(PACA_EXGEN, EXC_HV, 0x502) FTR_SECTION_ELSE - _MASKABLE_EXCEPTION_PSERIES(0x502, hardware_interrupt, EXC_HV) - ALT_FTR_SECTION_END_IFCLR(CPU_FTR_HVMODE_206) + _MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt, + EXC_STD, SOFTEN_TEST_HV_201) + KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x500) + ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) STD_EXCEPTION_PSERIES(0x600, 0x600, alignment) + KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x600) + STD_EXCEPTION_PSERIES(0x700, 0x700, program_check) + KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x700) + STD_EXCEPTION_PSERIES(0x800, 0x800, fp_unavailable) + KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x800) MASKABLE_EXCEPTION_PSERIES(0x900, 0x900, decrementer) - MASKABLE_EXCEPTION_HV(0x980, 0x980, decrementer) + MASKABLE_EXCEPTION_HV(0x980, 0x982, decrementer) STD_EXCEPTION_PSERIES(0xa00, 0xa00, trap_0a) + KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xa00) + STD_EXCEPTION_PSERIES(0xb00, 0xb00, trap_0b) + KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xb00) . = 0xc00 .globl system_call_pSeries system_call_pSeries: HMT_MEDIUM - DO_KVM 0xc00 +#ifdef CONFIG_KVM_BOOK3S_64_HANDLER + SET_SCRATCH0(r13) + GET_PACA(r13) + std r9,PACA_EXGEN+EX_R9(r13) + std r10,PACA_EXGEN+EX_R10(r13) + mfcr r9 + KVMTEST(0xc00) + GET_SCRATCH0(r13) +#endif BEGIN_FTR_SECTION cmpdi r0,0x1ebe beq- 1f @@ -220,6 +222,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE) rfid b . /* prevent speculative execution */ + KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xc00) + /* Fast LE/BE switch system call */ 1: mfspr r12,SPRN_SRR1 xori r12,r12,MSR_LE @@ -228,6 +232,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE) b . STD_EXCEPTION_PSERIES(0xd00, 0xd00, single_step) + KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xd00) /* At 0xe??? we have a bunch of hypervisor exceptions, we branch * out of line to handle them @@ -262,30 +267,93 @@ vsx_unavailable_pSeries_1: #ifdef CONFIG_CBE_RAS STD_EXCEPTION_HV(0x1200, 0x1202, cbe_system_error) + KVM_HANDLER_PR_SKIP(PACA_EXGEN, EXC_HV, 0x1202) #endif /* CONFIG_CBE_RAS */ + STD_EXCEPTION_PSERIES(0x1300, 0x1300, instruction_breakpoint) + KVM_HANDLER_PR_SKIP(PACA_EXGEN, EXC_STD, 0x1300) + #ifdef CONFIG_CBE_RAS STD_EXCEPTION_HV(0x1600, 0x1602, cbe_maintenance) + KVM_HANDLER_PR_SKIP(PACA_EXGEN, EXC_HV, 0x1602) #endif /* CONFIG_CBE_RAS */ + STD_EXCEPTION_PSERIES(0x1700, 0x1700, altivec_assist) + KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x1700) + #ifdef CONFIG_CBE_RAS STD_EXCEPTION_HV(0x1800, 0x1802, cbe_thermal) + KVM_HANDLER_PR_SKIP(PACA_EXGEN, EXC_HV, 0x1802) #endif /* CONFIG_CBE_RAS */ . = 0x3000 /*** Out of line interrupts support ***/ + /* moved from 0x200 */ +machine_check_pSeries: + .globl machine_check_fwnmi +machine_check_fwnmi: + HMT_MEDIUM + SET_SCRATCH0(r13) /* save r13 */ + EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common, + EXC_STD, KVMTEST, 0x200) + KVM_HANDLER_SKIP(PACA_EXMC, EXC_STD, 0x200) + +#ifndef CONFIG_POWER4_ONLY + /* moved from 0x300 */ +data_access_check_stab: + GET_PACA(r13) + std r9,PACA_EXSLB+EX_R9(r13) + std r10,PACA_EXSLB+EX_R10(r13) + mfspr r10,SPRN_DAR + mfspr r9,SPRN_DSISR + srdi r10,r10,60 + rlwimi r10,r9,16,0x20 +#ifdef CONFIG_KVM_BOOK3S_PR + lbz r9,HSTATE_IN_GUEST(r13) + rlwimi r10,r9,8,0x300 +#endif + mfcr r9 + cmpwi r10,0x2c + beq do_stab_bolted_pSeries + mtcrf 0x80,r9 + ld r9,PACA_EXSLB+EX_R9(r13) + ld r10,PACA_EXSLB+EX_R10(r13) + b data_access_not_stab +do_stab_bolted_pSeries: + std r11,PACA_EXSLB+EX_R11(r13) + std r12,PACA_EXSLB+EX_R12(r13) + GET_SCRATCH0(r10) + std r10,PACA_EXSLB+EX_R13(r13) + EXCEPTION_PROLOG_PSERIES_1(.do_stab_bolted, EXC_STD) +#endif /* CONFIG_POWER4_ONLY */ + + KVM_HANDLER_PR_SKIP(PACA_EXGEN, EXC_STD, 0x300) + KVM_HANDLER_PR_SKIP(PACA_EXSLB, EXC_STD, 0x380) + KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x400) + KVM_HANDLER_PR(PACA_EXSLB, EXC_STD, 0x480) + KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x900) + KVM_HANDLER(PACA_EXGEN, EXC_HV, 0x982) + + .align 7 /* moved from 0xe00 */ - STD_EXCEPTION_HV(., 0xe00, h_data_storage) - STD_EXCEPTION_HV(., 0xe20, h_instr_storage) - STD_EXCEPTION_HV(., 0xe40, emulation_assist) - STD_EXCEPTION_HV(., 0xe60, hmi_exception) /* need to flush cache ? */ + STD_EXCEPTION_HV(., 0xe02, h_data_storage) + KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0xe02) + STD_EXCEPTION_HV(., 0xe22, h_instr_storage) + KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe22) + STD_EXCEPTION_HV(., 0xe42, emulation_assist) + KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe42) + STD_EXCEPTION_HV(., 0xe62, hmi_exception) /* need to flush cache ? */ + KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe62) /* moved from 0xf00 */ STD_EXCEPTION_PSERIES(., 0xf00, performance_monitor) + KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf00) STD_EXCEPTION_PSERIES(., 0xf20, altivec_unavailable) + KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf20) STD_EXCEPTION_PSERIES(., 0xf40, vsx_unavailable) + KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf40) /* * An interrupt came in while soft-disabled; clear EE in SRR1, @@ -317,14 +385,6 @@ masked_Hinterrupt: hrfid b . - .align 7 -do_stab_bolted_pSeries: - std r11,PACA_EXSLB+EX_R11(r13) - std r12,PACA_EXSLB+EX_R12(r13) - GET_SCRATCH0(r10) - std r10,PACA_EXSLB+EX_R13(r13) - EXCEPTION_PROLOG_PSERIES_1(.do_stab_bolted, EXC_STD) - #ifdef CONFIG_PPC_PSERIES /* * Vectors for the FWNMI option. Share common code. @@ -334,14 +394,8 @@ do_stab_bolted_pSeries: system_reset_fwnmi: HMT_MEDIUM SET_SCRATCH0(r13) /* save r13 */ - EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD) - - .globl machine_check_fwnmi - .align 7 -machine_check_fwnmi: - HMT_MEDIUM - SET_SCRATCH0(r13) /* save r13 */ - EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common, EXC_STD) + EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD, + NOTEST, 0x100) #endif /* CONFIG_PPC_PSERIES */ @@ -376,7 +430,11 @@ slb_miss_user_pseries: /* KVM's trampoline code needs to be close to the interrupt handlers */ #ifdef CONFIG_KVM_BOOK3S_64_HANDLER +#ifdef CONFIG_KVM_BOOK3S_PR #include "../kvm/book3s_rmhandlers.S" +#else +#include "../kvm/book3s_hv_rmhandlers.S" +#endif #endif .align 7 diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S index 5ecf54cfa7d..fe37dd0dfd1 100644 --- a/arch/powerpc/kernel/head_fsl_booke.S +++ b/arch/powerpc/kernel/head_fsl_booke.S @@ -656,7 +656,7 @@ load_up_spe: cmpi 0,r4,0 beq 1f addi r4,r4,THREAD /* want THREAD of last_task_used_spe */ - SAVE_32EVRS(0,r10,r4) + SAVE_32EVRS(0,r10,r4,THREAD_EVR0) evxor evr10, evr10, evr10 /* clear out evr10 */ evmwumiaa evr10, evr10, evr10 /* evr10 <- ACC = 0 * 0 + ACC */ li r5,THREAD_ACC @@ -676,7 +676,7 @@ load_up_spe: stw r4,THREAD_USED_SPE(r5) evlddx evr4,r10,r5 evmra evr4,evr4 - REST_32EVRS(0,r10,r5) + REST_32EVRS(0,r10,r5,THREAD_EVR0) #ifndef CONFIG_SMP subi r4,r5,THREAD stw r4,last_task_used_spe@l(r3) @@ -787,13 +787,11 @@ _GLOBAL(giveup_spe) addi r3,r3,THREAD /* want THREAD of task */ lwz r5,PT_REGS(r3) cmpi 0,r5,0 - SAVE_32EVRS(0, r4, r3) + SAVE_32EVRS(0, r4, r3, THREAD_EVR0) evxor evr6, evr6, evr6 /* clear out evr6 */ evmwumiaa evr6, evr6, evr6 /* evr6 <- ACC = 0 * 0 + ACC */ li r4,THREAD_ACC evstddx evr6, r4, r3 /* save off accumulator */ - mfspr r6,SPRN_SPEFSCR - stw r6,THREAD_SPEFSCR(r3) /* save spefscr register value */ beq 1f lwz r4,_MSR-STACK_FRAME_OVERHEAD(r5) lis r3,MSR_SPE@h diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S index f8f0bc7f1d4..3a70845a51c 100644 --- a/arch/powerpc/kernel/idle_power7.S +++ b/arch/powerpc/kernel/idle_power7.S @@ -73,7 +73,6 @@ _GLOBAL(power7_idle) b . _GLOBAL(power7_wakeup_loss) - GET_PACA(r13) ld r1,PACAR1(r13) REST_NVGPRS(r1) REST_GPR(2, r1) @@ -87,7 +86,6 @@ _GLOBAL(power7_wakeup_loss) rfid _GLOBAL(power7_wakeup_noloss) - GET_PACA(r13) ld r1,PACAR1(r13) ld r4,_MSR(r1) ld r5,_NIP(r1) diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c index 49cee9df225..a1cd701b575 100644 --- a/arch/powerpc/kernel/module.c +++ b/arch/powerpc/kernel/module.c @@ -31,20 +31,6 @@ LIST_HEAD(module_bug_list); -void *module_alloc(unsigned long size) -{ - if (size == 0) - return NULL; - - return vmalloc_exec(size); -} - -/* Free memory returned from module_alloc */ -void module_free(struct module *mod, void *module_region) -{ - vfree(module_region); -} - static const Elf_Shdr *find_section(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, const char *name) @@ -93,7 +79,3 @@ int module_finalize(const Elf_Ehdr *hdr, return 0; } - -void module_arch_cleanup(struct module *mod) -{ -} diff --git a/arch/powerpc/kernel/module_32.c b/arch/powerpc/kernel/module_32.c index f832773fc28..0b6d79617d7 100644 --- a/arch/powerpc/kernel/module_32.c +++ b/arch/powerpc/kernel/module_32.c @@ -174,17 +174,6 @@ int module_frob_arch_sections(Elf32_Ehdr *hdr, return 0; } -int apply_relocate(Elf32_Shdr *sechdrs, - const char *strtab, - unsigned int symindex, - unsigned int relsec, - struct module *module) -{ - printk(KERN_ERR "%s: Non-ADD RELOCATION unsupported\n", - module->name); - return -ENOEXEC; -} - static inline int entry_matches(struct ppc_plt_entry *entry, Elf32_Addr val) { if (entry->jump[0] == 0x3d600000 + ((val + 0x8000) >> 16) diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 8fbb12508bf..9f44a775a10 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -243,16 +243,6 @@ int module_frob_arch_sections(Elf64_Ehdr *hdr, return 0; } -int apply_relocate(Elf64_Shdr *sechdrs, - const char *strtab, - unsigned int symindex, - unsigned int relsec, - struct module *me) -{ - printk(KERN_ERR "%s: Non-ADD RELOCATION unsupported\n", me->name); - return -ENOEXEC; -} - /* r2 is the TOC pointer: it actually points 0x8000 into the TOC (this gives the value maximum span in an instruction which uses a signed offset) */ diff --git a/arch/powerpc/kernel/mpc7450-pmu.c b/arch/powerpc/kernel/mpc7450-pmu.c index 2cc5e0301d0..845a5847889 100644 --- a/arch/powerpc/kernel/mpc7450-pmu.c +++ b/arch/powerpc/kernel/mpc7450-pmu.c @@ -388,6 +388,11 @@ static int mpc7450_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { [C(OP_WRITE)] = { -1, -1 }, [C(OP_PREFETCH)] = { -1, -1 }, }, + [C(NODE)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { -1, -1 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, }; struct power_pmu mpc7450_pmu = { diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index efeb8818418..0a5a899846b 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -167,7 +167,7 @@ void setup_paca(struct paca_struct *new_paca) * if we do a GET_PACA() before the feature fixups have been * applied */ - if (cpu_has_feature(CPU_FTR_HVMODE_206)) + if (cpu_has_feature(CPU_FTR_HVMODE)) mtspr(SPRN_SPRG_HPACA, local_paca); #endif mtspr(SPRN_SPRG_PACA, local_paca); diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 893af2a9cd0..a3c92770e42 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -1097,9 +1097,6 @@ void __devinit pcibios_setup_bus_devices(struct pci_bus *bus) if (dev->is_added) continue; - /* Setup OF node pointer in the device */ - dev->dev.of_node = pci_device_to_OF_node(dev); - /* Fixup NUMA node as it may not be setup yet by the generic * code and is needed by the DMA init */ @@ -1685,6 +1682,13 @@ int early_find_capability(struct pci_controller *hose, int bus, int devfn, return pci_bus_find_capability(fake_pci_bus(hose, bus), devfn, cap); } +struct device_node *pcibios_get_phb_of_node(struct pci_bus *bus) +{ + struct pci_controller *hose = bus->sysdata; + + return of_node_get(hose->dn); +} + /** * pci_scan_phb - Given a pci_controller, setup and scan the PCI bus * @hose: Pointer to the PCI host controller instance structure @@ -1705,7 +1709,6 @@ void __devinit pcibios_scan_phb(struct pci_controller *hose) hose->global_number); return; } - bus->dev.of_node = of_node_get(node); bus->secondary = hose->first_busno; hose->bus = bus; diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c index bedb370459f..86585508e9c 100644 --- a/arch/powerpc/kernel/pci_32.c +++ b/arch/powerpc/kernel/pci_32.c @@ -167,150 +167,26 @@ pcibios_make_OF_bus_map(void) #endif } -typedef int (*pci_OF_scan_iterator)(struct device_node* node, void* data); - -static struct device_node* -scan_OF_pci_childs(struct device_node *parent, pci_OF_scan_iterator filter, void* data) -{ - struct device_node *node; - struct device_node* sub_node; - - for_each_child_of_node(parent, node) { - const unsigned int *class_code; - - if (filter(node, data)) { - of_node_put(node); - return node; - } - - /* For PCI<->PCI bridges or CardBus bridges, we go down - * Note: some OFs create a parent node "multifunc-device" as - * a fake root for all functions of a multi-function device, - * we go down them as well. - */ - class_code = of_get_property(node, "class-code", NULL); - if ((!class_code || ((*class_code >> 8) != PCI_CLASS_BRIDGE_PCI && - (*class_code >> 8) != PCI_CLASS_BRIDGE_CARDBUS)) && - strcmp(node->name, "multifunc-device")) - continue; - sub_node = scan_OF_pci_childs(node, filter, data); - if (sub_node) { - of_node_put(node); - return sub_node; - } - } - return NULL; -} - -static struct device_node *scan_OF_for_pci_dev(struct device_node *parent, - unsigned int devfn) -{ - struct device_node *np, *cnp; - const u32 *reg; - unsigned int psize; - - for_each_child_of_node(parent, np) { - reg = of_get_property(np, "reg", &psize); - if (reg && psize >= 4 && ((reg[0] >> 8) & 0xff) == devfn) - return np; - - /* Note: some OFs create a parent node "multifunc-device" as - * a fake root for all functions of a multi-function device, - * we go down them as well. */ - if (!strcmp(np->name, "multifunc-device")) { - cnp = scan_OF_for_pci_dev(np, devfn); - if (cnp) - return cnp; - } - } - return NULL; -} - - -static struct device_node *scan_OF_for_pci_bus(struct pci_bus *bus) -{ - struct device_node *parent, *np; - - /* Are we a root bus ? */ - if (bus->self == NULL || bus->parent == NULL) { - struct pci_controller *hose = pci_bus_to_host(bus); - if (hose == NULL) - return NULL; - return of_node_get(hose->dn); - } - - /* not a root bus, we need to get our parent */ - parent = scan_OF_for_pci_bus(bus->parent); - if (parent == NULL) - return NULL; - - /* now iterate for children for a match */ - np = scan_OF_for_pci_dev(parent, bus->self->devfn); - of_node_put(parent); - - return np; -} - -/* - * Scans the OF tree for a device node matching a PCI device - */ -struct device_node * -pci_busdev_to_OF_node(struct pci_bus *bus, int devfn) -{ - struct device_node *parent, *np; - - pr_debug("pci_busdev_to_OF_node(%d,0x%x)\n", bus->number, devfn); - parent = scan_OF_for_pci_bus(bus); - if (parent == NULL) - return NULL; - pr_debug(" parent is %s\n", parent ? parent->full_name : "<NULL>"); - np = scan_OF_for_pci_dev(parent, devfn); - of_node_put(parent); - pr_debug(" result is %s\n", np ? np->full_name : "<NULL>"); - - /* XXX most callers don't release the returned node - * mostly because ppc64 doesn't increase the refcount, - * we need to fix that. - */ - return np; -} -EXPORT_SYMBOL(pci_busdev_to_OF_node); - -struct device_node* -pci_device_to_OF_node(struct pci_dev *dev) -{ - return pci_busdev_to_OF_node(dev->bus, dev->devfn); -} -EXPORT_SYMBOL(pci_device_to_OF_node); - -static int -find_OF_pci_device_filter(struct device_node* node, void* data) -{ - return ((void *)node == data); -} /* * Returns the PCI device matching a given OF node */ -int -pci_device_from_OF_node(struct device_node* node, u8* bus, u8* devfn) +int pci_device_from_OF_node(struct device_node *node, u8 *bus, u8 *devfn) { - const unsigned int *reg; - struct pci_controller* hose; - struct pci_dev* dev = NULL; - - /* Make sure it's really a PCI device */ - hose = pci_find_hose_for_OF_device(node); - if (!hose || !hose->dn) - return -ENODEV; - if (!scan_OF_pci_childs(hose->dn, - find_OF_pci_device_filter, (void *)node)) + struct pci_dev *dev = NULL; + const __be32 *reg; + int size; + + /* Check if it might have a chance to be a PCI device */ + if (!pci_find_hose_for_OF_device(node)) return -ENODEV; - reg = of_get_property(node, "reg", NULL); - if (!reg) + + reg = of_get_property(node, "reg", &size); + if (!reg || size < 5 * sizeof(u32)) return -ENODEV; - *bus = (reg[0] >> 16) & 0xff; - *devfn = ((reg[0] >> 8) & 0xff); + + *bus = (be32_to_cpup(®[0]) >> 16) & 0xff; + *devfn = (be32_to_cpup(®[0]) >> 8) & 0xff; /* Ok, here we need some tweak. If we have already renumbered * all busses, we can't rely on the OF bus number any more. diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c index 6baabc13306..478f8d78716 100644 --- a/arch/powerpc/kernel/pci_dn.c +++ b/arch/powerpc/kernel/pci_dn.c @@ -142,53 +142,6 @@ void __devinit pci_devs_phb_init_dynamic(struct pci_controller *phb) traverse_pci_devices(dn, update_dn_pci_info, phb); } -/* - * Traversal func that looks for a <busno,devfcn> value. - * If found, the pci_dn is returned (thus terminating the traversal). - */ -static void *is_devfn_node(struct device_node *dn, void *data) -{ - int busno = ((unsigned long)data >> 8) & 0xff; - int devfn = ((unsigned long)data) & 0xff; - struct pci_dn *pci = dn->data; - - if (pci && (devfn == pci->devfn) && (busno == pci->busno)) - return dn; - return NULL; -} - -/* - * This is the "slow" path for looking up a device_node from a - * pci_dev. It will hunt for the device under its parent's - * phb and then update of_node pointer. - * - * It may also do fixups on the actual device since this happens - * on the first read/write. - * - * Note that it also must deal with devices that don't exist. - * In this case it may probe for real hardware ("just in case") - * and add a device_node to the device tree if necessary. - * - * Is this function necessary anymore now that dev->dev.of_node is - * used to store the node pointer? - * - */ -struct device_node *fetch_dev_dn(struct pci_dev *dev) -{ - struct pci_controller *phb = dev->sysdata; - struct device_node *dn; - unsigned long searchval = (dev->bus->number << 8) | dev->devfn; - - if (WARN_ON(!phb)) - return NULL; - - dn = traverse_pci_devices(phb->dn, is_devfn_node, (void *)searchval); - if (dn) - dev->dev.of_node = dn; - return dn; -} -EXPORT_SYMBOL(fetch_dev_dn); - /** * pci_devs_phb_init - Initialize phbs and pci devs under them. * diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c index 1e89a72fd03..fe0a5ad6f73 100644 --- a/arch/powerpc/kernel/pci_of_scan.c +++ b/arch/powerpc/kernel/pci_of_scan.c @@ -202,9 +202,9 @@ EXPORT_SYMBOL(of_create_pci_dev); * this routine in turn call of_scan_bus() recusively to scan for more child * devices. */ -void __devinit of_scan_pci_bridge(struct device_node *node, - struct pci_dev *dev) +void __devinit of_scan_pci_bridge(struct pci_dev *dev) { + struct device_node *node = dev->dev.of_node; struct pci_bus *bus; const u32 *busrange, *ranges; int len, i, mode; @@ -238,7 +238,6 @@ void __devinit of_scan_pci_bridge(struct device_node *node, bus->primary = dev->bus->number; bus->subordinate = busrange[1]; bus->bridge_ctl = 0; - bus->dev.of_node = of_node_get(node); /* parse ranges property */ /* PCI #address-cells == 3 and #size-cells == 2 always */ @@ -335,9 +334,7 @@ static void __devinit __of_scan_bus(struct device_node *node, list_for_each_entry(dev, &bus->devices, bus_list) { if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE || dev->hdr_type == PCI_HEADER_TYPE_CARDBUS) { - struct device_node *child = pci_device_to_OF_node(dev); - if (child) - of_scan_pci_bridge(child, dev); + of_scan_pci_bridge(dev); } } } diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c index 822f63008ae..14967de9887 100644 --- a/arch/powerpc/kernel/perf_event.c +++ b/arch/powerpc/kernel/perf_event.c @@ -1207,7 +1207,7 @@ struct pmu power_pmu = { * 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) + struct pt_regs *regs) { u64 period = event->hw.sample_period; s64 prev, delta, left; @@ -1258,7 +1258,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val, if (event->attr.sample_type & PERF_SAMPLE_ADDR) perf_get_data_addr(regs, &data.addr); - if (perf_event_overflow(event, nmi, &data, regs)) + if (perf_event_overflow(event, &data, regs)) power_pmu_stop(event, 0); } } @@ -1346,7 +1346,7 @@ static void perf_event_interrupt(struct pt_regs *regs) if ((int)val < 0) { /* event has overflowed */ found = 1; - record_and_restart(event, val, regs, nmi); + record_and_restart(event, val, regs); } } diff --git a/arch/powerpc/kernel/perf_event_fsl_emb.c b/arch/powerpc/kernel/perf_event_fsl_emb.c index b0dc8f7069c..0a6d2a9d569 100644 --- a/arch/powerpc/kernel/perf_event_fsl_emb.c +++ b/arch/powerpc/kernel/perf_event_fsl_emb.c @@ -568,7 +568,7 @@ static struct pmu fsl_emb_pmu = { * 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) + struct pt_regs *regs) { u64 period = event->hw.sample_period; s64 prev, delta, left; @@ -616,7 +616,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val, perf_sample_data_init(&data, 0); data.period = event->hw.last_period; - if (perf_event_overflow(event, nmi, &data, regs)) + if (perf_event_overflow(event, &data, regs)) fsl_emb_pmu_stop(event, 0); } } @@ -644,7 +644,7 @@ static void perf_event_interrupt(struct pt_regs *regs) if (event) { /* event has overflowed */ found = 1; - record_and_restart(event, val, regs, nmi); + record_and_restart(event, val, regs); } else { /* * Disabled counter is negative, diff --git a/arch/powerpc/kernel/power4-pmu.c b/arch/powerpc/kernel/power4-pmu.c index ead8b3c2649..e9dbc2d35c9 100644 --- a/arch/powerpc/kernel/power4-pmu.c +++ b/arch/powerpc/kernel/power4-pmu.c @@ -587,6 +587,11 @@ static int power4_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { [C(OP_WRITE)] = { -1, -1 }, [C(OP_PREFETCH)] = { -1, -1 }, }, + [C(NODE)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { -1, -1 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, }; static struct power_pmu power4_pmu = { diff --git a/arch/powerpc/kernel/power5+-pmu.c b/arch/powerpc/kernel/power5+-pmu.c index eca0ac595cb..f58a2bd41b5 100644 --- a/arch/powerpc/kernel/power5+-pmu.c +++ b/arch/powerpc/kernel/power5+-pmu.c @@ -653,6 +653,11 @@ static int power5p_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { [C(OP_WRITE)] = { -1, -1 }, [C(OP_PREFETCH)] = { -1, -1 }, }, + [C(NODE)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { -1, -1 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, }; static struct power_pmu power5p_pmu = { diff --git a/arch/powerpc/kernel/power5-pmu.c b/arch/powerpc/kernel/power5-pmu.c index d5ff0f64a5e..b1acab68414 100644 --- a/arch/powerpc/kernel/power5-pmu.c +++ b/arch/powerpc/kernel/power5-pmu.c @@ -595,6 +595,11 @@ static int power5_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { [C(OP_WRITE)] = { -1, -1 }, [C(OP_PREFETCH)] = { -1, -1 }, }, + [C(NODE)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { -1, -1 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, }; static struct power_pmu power5_pmu = { diff --git a/arch/powerpc/kernel/power6-pmu.c b/arch/powerpc/kernel/power6-pmu.c index 31603927e37..b24a3a23d07 100644 --- a/arch/powerpc/kernel/power6-pmu.c +++ b/arch/powerpc/kernel/power6-pmu.c @@ -516,6 +516,11 @@ static int power6_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { [C(OP_WRITE)] = { -1, -1 }, [C(OP_PREFETCH)] = { -1, -1 }, }, + [C(NODE)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { -1, -1 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, }; static struct power_pmu power6_pmu = { diff --git a/arch/powerpc/kernel/power7-pmu.c b/arch/powerpc/kernel/power7-pmu.c index 593740fcb79..6d9dccb2ea5 100644 --- a/arch/powerpc/kernel/power7-pmu.c +++ b/arch/powerpc/kernel/power7-pmu.c @@ -342,6 +342,11 @@ static int power7_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { [C(OP_WRITE)] = { -1, -1 }, [C(OP_PREFETCH)] = { -1, -1 }, }, + [C(NODE)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { -1, -1 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, }; static struct power_pmu power7_pmu = { diff --git a/arch/powerpc/kernel/ppc970-pmu.c b/arch/powerpc/kernel/ppc970-pmu.c index 9a6e093858f..b121de9658e 100644 --- a/arch/powerpc/kernel/ppc970-pmu.c +++ b/arch/powerpc/kernel/ppc970-pmu.c @@ -467,6 +467,11 @@ static int ppc970_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { [C(OP_WRITE)] = { -1, -1 }, [C(OP_PREFETCH)] = { -1, -1 }, }, + [C(NODE)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { -1, -1 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, }; static struct power_pmu ppc970_pmu = { diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 91e52df3d81..ec2d0edeb13 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -96,6 +96,7 @@ void flush_fp_to_thread(struct task_struct *tsk) preempt_enable(); } } +EXPORT_SYMBOL_GPL(flush_fp_to_thread); void enable_kernel_fp(void) { @@ -145,6 +146,7 @@ void flush_altivec_to_thread(struct task_struct *tsk) preempt_enable(); } } +EXPORT_SYMBOL_GPL(flush_altivec_to_thread); #endif /* CONFIG_ALTIVEC */ #ifdef CONFIG_VSX @@ -186,6 +188,7 @@ void flush_vsx_to_thread(struct task_struct *tsk) preempt_enable(); } } +EXPORT_SYMBOL_GPL(flush_vsx_to_thread); #endif /* CONFIG_VSX */ #ifdef CONFIG_SPE @@ -213,6 +216,7 @@ void flush_spe_to_thread(struct task_struct *tsk) #ifdef CONFIG_SMP BUG_ON(tsk != current); #endif + tsk->thread.spefscr = mfspr(SPRN_SPEFSCR); giveup_spe(tsk); } preempt_enable(); diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index cb22024f2b4..05b7dd217f6 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -882,7 +882,7 @@ void user_disable_single_step(struct task_struct *task) } #ifdef CONFIG_HAVE_HW_BREAKPOINT -void ptrace_triggered(struct perf_event *bp, int nmi, +void ptrace_triggered(struct perf_event *bp, struct perf_sample_data *data, struct pt_regs *regs) { struct perf_event_attr attr; @@ -973,7 +973,7 @@ int ptrace_set_debugreg(struct task_struct *task, unsigned long addr, &attr.bp_type); thread->ptrace_bps[0] = bp = register_user_hw_breakpoint(&attr, - ptrace_triggered, task); + ptrace_triggered, NULL, task); if (IS_ERR(bp)) { thread->ptrace_bps[0] = NULL; ptrace_put_breakpoints(task); diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 79fca2651b6..22051ef04bd 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -375,6 +375,9 @@ void __init check_for_initrd(void) int threads_per_core, threads_shift; cpumask_t threads_core_mask; +EXPORT_SYMBOL_GPL(threads_per_core); +EXPORT_SYMBOL_GPL(threads_shift); +EXPORT_SYMBOL_GPL(threads_core_mask); static void __init cpu_init_thread_core_maps(int tpc) { diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index a88bf2713d4..532054f24ec 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -63,6 +63,7 @@ #include <asm/kexec.h> #include <asm/mmu_context.h> #include <asm/code-patching.h> +#include <asm/kvm_ppc.h> #include "setup.h" @@ -580,6 +581,8 @@ void __init setup_arch(char **cmdline_p) /* Initialize the MMU context management stuff */ mmu_context_init(); + kvm_rma_init(); + ppc64_boot_msg(0x15, "Setup Done"); } diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 8ebc6700b98..09a85a9045d 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -243,6 +243,7 @@ void smp_send_reschedule(int cpu) if (likely(smp_ops)) smp_ops->message_pass(cpu, PPC_MSG_RESCHEDULE); } +EXPORT_SYMBOL_GPL(smp_send_reschedule); void arch_send_call_function_single_ipi(int cpu) { diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index f33acfd872a..03b29a6759a 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -544,7 +544,7 @@ DEFINE_PER_CPU(u8, irq_work_pending); #endif /* 32 vs 64 bit */ -void set_irq_work_pending(void) +void arch_irq_work_raise(void) { preempt_disable(); set_irq_work_pending_flag(); diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 1a0141426cd..f19d9777d3c 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -1387,10 +1387,7 @@ void SPEFloatingPointException(struct pt_regs *regs) int code = 0; int err; - preempt_disable(); - if (regs->msr & MSR_SPE) - giveup_spe(current); - preempt_enable(); + flush_spe_to_thread(current); spefscr = current->thread.spefscr; fpexc_mode = current->thread.fpexc_mode; diff --git a/arch/powerpc/kvm/44x_tlb.c b/arch/powerpc/kvm/44x_tlb.c index 5f3cff83e08..33aa715dab2 100644 --- a/arch/powerpc/kvm/44x_tlb.c +++ b/arch/powerpc/kvm/44x_tlb.c @@ -387,8 +387,10 @@ static void kvmppc_44x_invalidate(struct kvm_vcpu *vcpu, } } -void kvmppc_mmu_priv_switch(struct kvm_vcpu *vcpu, int usermode) +void kvmppc_mmu_msr_notify(struct kvm_vcpu *vcpu, u32 old_msr) { + int usermode = vcpu->arch.shared->msr & MSR_PR; + vcpu->arch.shadow_pid = !usermode; } diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index b7baff78f90..78133deb4b6 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -20,7 +20,6 @@ config KVM bool select PREEMPT_NOTIFIERS select ANON_INODES - select KVM_MMIO config KVM_BOOK3S_HANDLER bool @@ -28,16 +27,22 @@ config KVM_BOOK3S_HANDLER config KVM_BOOK3S_32_HANDLER bool select KVM_BOOK3S_HANDLER + select KVM_MMIO config KVM_BOOK3S_64_HANDLER bool select KVM_BOOK3S_HANDLER +config KVM_BOOK3S_PR + bool + select KVM_MMIO + config KVM_BOOK3S_32 tristate "KVM support for PowerPC book3s_32 processors" depends on EXPERIMENTAL && PPC_BOOK3S_32 && !SMP && !PTE_64BIT select KVM select KVM_BOOK3S_32_HANDLER + select KVM_BOOK3S_PR ---help--- Support running unmodified book3s_32 guest kernels in virtual machines on book3s_32 host processors. @@ -50,8 +55,8 @@ config KVM_BOOK3S_32 config KVM_BOOK3S_64 tristate "KVM support for PowerPC book3s_64 processors" depends on EXPERIMENTAL && PPC_BOOK3S_64 - select KVM select KVM_BOOK3S_64_HANDLER + select KVM ---help--- Support running unmodified book3s_64 and book3s_32 guest kernels in virtual machines on book3s_64 host processors. @@ -61,10 +66,34 @@ config KVM_BOOK3S_64 If unsure, say N. +config KVM_BOOK3S_64_HV + bool "KVM support for POWER7 and PPC970 using hypervisor mode in host" + depends on KVM_BOOK3S_64 + ---help--- + Support running unmodified book3s_64 guest kernels in + virtual machines on POWER7 and PPC970 processors that have + hypervisor mode available to the host. + + If you say Y here, KVM will use the hardware virtualization + facilities of POWER7 (and later) processors, meaning that + guest operating systems will run at full hardware speed + using supervisor and user modes. However, this also means + that KVM is not usable under PowerVM (pHyp), is only usable + on POWER7 (or later) processors and PPC970-family processors, + and cannot emulate a different processor from the host processor. + + If unsure, say N. + +config KVM_BOOK3S_64_PR + def_bool y + depends on KVM_BOOK3S_64 && !KVM_BOOK3S_64_HV + select KVM_BOOK3S_PR + config KVM_440 bool "KVM support for PowerPC 440 processors" depends on EXPERIMENTAL && 44x select KVM + select KVM_MMIO ---help--- Support running unmodified 440 guest kernels in virtual machines on 440 host processors. @@ -89,6 +118,7 @@ config KVM_E500 bool "KVM support for PowerPC E500 processors" depends on EXPERIMENTAL && E500 select KVM + select KVM_MMIO ---help--- Support running unmodified E500 guest kernels in virtual machines on E500 host processors. @@ -99,6 +129,5 @@ config KVM_E500 If unsure, say N. source drivers/vhost/Kconfig -source drivers/virtio/Kconfig endif # VIRTUALIZATION diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile index 4d6863823f6..08428e2c188 100644 --- a/arch/powerpc/kvm/Makefile +++ b/arch/powerpc/kvm/Makefile @@ -38,24 +38,42 @@ kvm-e500-objs := \ e500_emulate.o kvm-objs-$(CONFIG_KVM_E500) := $(kvm-e500-objs) -kvm-book3s_64-objs := \ - $(common-objs-y) \ +kvm-book3s_64-objs-$(CONFIG_KVM_BOOK3S_64_PR) := \ + ../../../virt/kvm/coalesced_mmio.o \ fpu.o \ book3s_paired_singles.o \ - book3s.o \ + book3s_pr.o \ book3s_emulate.o \ book3s_interrupts.o \ book3s_mmu_hpte.o \ book3s_64_mmu_host.o \ book3s_64_mmu.o \ book3s_32_mmu.o -kvm-objs-$(CONFIG_KVM_BOOK3S_64) := $(kvm-book3s_64-objs) + +kvm-book3s_64-objs-$(CONFIG_KVM_BOOK3S_64_HV) := \ + book3s_hv.o \ + book3s_hv_interrupts.o \ + book3s_64_mmu_hv.o +kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HV) := \ + book3s_hv_rm_mmu.o \ + book3s_64_vio_hv.o \ + book3s_hv_builtin.o + +kvm-book3s_64-module-objs := \ + ../../../virt/kvm/kvm_main.o \ + powerpc.o \ + emulate.o \ + book3s.o \ + $(kvm-book3s_64-objs-y) + +kvm-objs-$(CONFIG_KVM_BOOK3S_64) := $(kvm-book3s_64-module-objs) kvm-book3s_32-objs := \ $(common-objs-y) \ fpu.o \ book3s_paired_singles.o \ book3s.o \ + book3s_pr.o \ book3s_emulate.o \ book3s_interrupts.o \ book3s_mmu_hpte.o \ @@ -70,3 +88,4 @@ obj-$(CONFIG_KVM_E500) += kvm.o obj-$(CONFIG_KVM_BOOK3S_64) += kvm.o obj-$(CONFIG_KVM_BOOK3S_32) += kvm.o +obj-y += $(kvm-book3s_64-builtin-objs-y) diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index 0f95b5cce03..f68a34d1603 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -17,7 +17,6 @@ #include <linux/kvm_host.h> #include <linux/err.h> #include <linux/slab.h> -#include "trace.h" #include <asm/reg.h> #include <asm/cputable.h> @@ -28,25 +27,17 @@ #include <asm/kvm_ppc.h> #include <asm/kvm_book3s.h> #include <asm/mmu_context.h> +#include <asm/page.h> #include <linux/gfp.h> #include <linux/sched.h> #include <linux/vmalloc.h> #include <linux/highmem.h> +#include "trace.h" + #define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU /* #define EXIT_DEBUG */ -/* #define DEBUG_EXT */ - -static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr, - ulong msr); - -/* Some compatibility defines */ -#ifdef CONFIG_PPC_BOOK3S_32 -#define MSR_USER32 MSR_USER -#define MSR_USER64 MSR_USER -#define HW_PAGE_SIZE PAGE_SIZE -#endif struct kvm_stats_debugfs_item debugfs_entries[] = { { "exits", VCPU_STAT(sum_exits) }, @@ -77,100 +68,11 @@ void kvmppc_core_load_guest_debugstate(struct kvm_vcpu *vcpu) { } -void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu) -{ -#ifdef CONFIG_PPC_BOOK3S_64 - memcpy(to_svcpu(vcpu)->slb, to_book3s(vcpu)->slb_shadow, sizeof(to_svcpu(vcpu)->slb)); - memcpy(&get_paca()->shadow_vcpu, to_book3s(vcpu)->shadow_vcpu, - sizeof(get_paca()->shadow_vcpu)); - to_svcpu(vcpu)->slb_max = to_book3s(vcpu)->slb_shadow_max; -#endif - -#ifdef CONFIG_PPC_BOOK3S_32 - current->thread.kvm_shadow_vcpu = to_book3s(vcpu)->shadow_vcpu; -#endif -} - -void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu) -{ -#ifdef CONFIG_PPC_BOOK3S_64 - memcpy(to_book3s(vcpu)->slb_shadow, to_svcpu(vcpu)->slb, sizeof(to_svcpu(vcpu)->slb)); - memcpy(to_book3s(vcpu)->shadow_vcpu, &get_paca()->shadow_vcpu, - sizeof(get_paca()->shadow_vcpu)); - to_book3s(vcpu)->slb_shadow_max = to_svcpu(vcpu)->slb_max; -#endif - - kvmppc_giveup_ext(vcpu, MSR_FP); - kvmppc_giveup_ext(vcpu, MSR_VEC); - kvmppc_giveup_ext(vcpu, MSR_VSX); -} - -static void kvmppc_recalc_shadow_msr(struct kvm_vcpu *vcpu) -{ - ulong smsr = vcpu->arch.shared->msr; - - /* Guest MSR values */ - smsr &= MSR_FE0 | MSR_FE1 | MSR_SF | MSR_SE | MSR_BE | MSR_DE; - /* Process MSR values */ - smsr |= MSR_ME | MSR_RI | MSR_IR | MSR_DR | MSR_PR | MSR_EE; - /* External providers the guest reserved */ - smsr |= (vcpu->arch.shared->msr & vcpu->arch.guest_owned_ext); - /* 64-bit Process MSR values */ -#ifdef CONFIG_PPC_BOOK3S_64 - smsr |= MSR_ISF | MSR_HV; -#endif - vcpu->arch.shadow_msr = smsr; -} - -void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr) -{ - ulong old_msr = vcpu->arch.shared->msr; - -#ifdef EXIT_DEBUG - printk(KERN_INFO "KVM: Set MSR to 0x%llx\n", msr); -#endif - - msr &= to_book3s(vcpu)->msr_mask; - vcpu->arch.shared->msr = msr; - kvmppc_recalc_shadow_msr(vcpu); - - if (msr & MSR_POW) { - if (!vcpu->arch.pending_exceptions) { - kvm_vcpu_block(vcpu); - vcpu->stat.halt_wakeup++; - - /* Unset POW bit after we woke up */ - msr &= ~MSR_POW; - vcpu->arch.shared->msr = msr; - } - } - - if ((vcpu->arch.shared->msr & (MSR_PR|MSR_IR|MSR_DR)) != - (old_msr & (MSR_PR|MSR_IR|MSR_DR))) { - kvmppc_mmu_flush_segments(vcpu); - kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu)); - - /* Preload magic page segment when in kernel mode */ - if (!(msr & MSR_PR) && vcpu->arch.magic_page_pa) { - struct kvm_vcpu_arch *a = &vcpu->arch; - - if (msr & MSR_DR) - kvmppc_mmu_map_segment(vcpu, a->magic_page_ea); - else - kvmppc_mmu_map_segment(vcpu, a->magic_page_pa); - } - } - - /* Preload FPU if it's enabled */ - if (vcpu->arch.shared->msr & MSR_FP) - kvmppc_handle_ext(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL, MSR_FP); -} - void kvmppc_inject_interrupt(struct kvm_vcpu *vcpu, int vec, u64 flags) { vcpu->arch.shared->srr0 = kvmppc_get_pc(vcpu); vcpu->arch.shared->srr1 = vcpu->arch.shared->msr | flags; - kvmppc_set_pc(vcpu, to_book3s(vcpu)->hior + vec); + kvmppc_set_pc(vcpu, kvmppc_interrupt_offset(vcpu) + vec); vcpu->arch.mmu.reset_msr(vcpu); } @@ -204,11 +106,13 @@ static int kvmppc_book3s_vec2irqprio(unsigned int vec) static void kvmppc_book3s_dequeue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec) { + unsigned long old_pending = vcpu->arch.pending_exceptions; + clear_bit(kvmppc_book3s_vec2irqprio(vec), &vcpu->arch.pending_exceptions); - if (!vcpu->arch.pending_exceptions) - vcpu->arch.shared->int_pending = 0; + kvmppc_update_int_pending(vcpu, vcpu->arch.pending_exceptions, + old_pending); } void kvmppc_book3s_queue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec) @@ -225,8 +129,8 @@ void kvmppc_book3s_queue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec) 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); + /* might as well deliver this straight away */ + kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_PROGRAM, flags); } void kvmppc_core_queue_dec(struct kvm_vcpu *vcpu) @@ -266,21 +170,7 @@ int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu, unsigned int priority) { int deliver = 1; int vec = 0; - ulong flags = 0ULL; - ulong crit_raw = vcpu->arch.shared->critical; - ulong crit_r1 = kvmppc_get_gpr(vcpu, 1); - bool crit; - - /* Truncate crit indicators in 32 bit mode */ - if (!(vcpu->arch.shared->msr & MSR_SF)) { - crit_raw &= 0xffffffff; - crit_r1 &= 0xffffffff; - } - - /* Critical section when crit == r1 */ - crit = (crit_raw == crit_r1); - /* ... and we're in supervisor mode */ - crit = crit && !(vcpu->arch.shared->msr & MSR_PR); + bool crit = kvmppc_critical_section(vcpu); switch (priority) { case BOOK3S_IRQPRIO_DECREMENTER: @@ -315,7 +205,6 @@ 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; @@ -346,7 +235,7 @@ int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu, unsigned int priority) #endif if (deliver) - kvmppc_inject_interrupt(vcpu, vec, flags); + kvmppc_inject_interrupt(vcpu, vec, 0); return deliver; } @@ -392,64 +281,7 @@ void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu) } /* Tell the guest about our interrupt status */ - if (*pending) - vcpu->arch.shared->int_pending = 1; - else if (old_pending) - vcpu->arch.shared->int_pending = 0; -} - -void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr) -{ - u32 host_pvr; - - vcpu->arch.hflags &= ~BOOK3S_HFLAG_SLB; - vcpu->arch.pvr = pvr; -#ifdef CONFIG_PPC_BOOK3S_64 - if ((pvr >= 0x330000) && (pvr < 0x70330000)) { - kvmppc_mmu_book3s_64_init(vcpu); - to_book3s(vcpu)->hior = 0xfff00000; - to_book3s(vcpu)->msr_mask = 0xffffffffffffffffULL; - } else -#endif - { - kvmppc_mmu_book3s_32_init(vcpu); - to_book3s(vcpu)->hior = 0; - to_book3s(vcpu)->msr_mask = 0xffffffffULL; - } - - /* If we are in hypervisor level on 970, we can tell the CPU to - * treat DCBZ as 32 bytes store */ - vcpu->arch.hflags &= ~BOOK3S_HFLAG_DCBZ32; - if (vcpu->arch.mmu.is_dcbz32(vcpu) && (mfmsr() & MSR_HV) && - !strcmp(cur_cpu_spec->platform, "ppc970")) - vcpu->arch.hflags |= BOOK3S_HFLAG_DCBZ32; - - /* Cell performs badly if MSR_FEx are set. So let's hope nobody - really needs them in a VM on Cell and force disable them. */ - if (!strcmp(cur_cpu_spec->platform, "ppc-cell-be")) - to_book3s(vcpu)->msr_mask &= ~(MSR_FE0 | MSR_FE1); - -#ifdef CONFIG_PPC_BOOK3S_32 - /* 32 bit Book3S always has 32 byte dcbz */ - vcpu->arch.hflags |= BOOK3S_HFLAG_DCBZ32; -#endif - - /* On some CPUs we can execute paired single operations natively */ - asm ( "mfpvr %0" : "=r"(host_pvr)); - switch (host_pvr) { - case 0x00080200: /* lonestar 2.0 */ - case 0x00088202: /* lonestar 2.2 */ - case 0x70000100: /* gekko 1.0 */ - case 0x00080100: /* gekko 2.0 */ - case 0x00083203: /* gekko 2.3a */ - case 0x00083213: /* gekko 2.3b */ - case 0x00083204: /* gekko 2.4 */ - case 0x00083214: /* gekko 2.4e (8SE) - retail HW2 */ - case 0x00087200: /* broadway */ - vcpu->arch.hflags |= BOOK3S_HFLAG_NATIVE_PS; - /* Enable HID2.PSE - in case we need it later */ - mtspr(SPRN_HID2_GEKKO, mfspr(SPRN_HID2_GEKKO) | (1 << 29)); - } + kvmppc_update_int_pending(vcpu, *pending, old_pending); } pfn_t kvmppc_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn) @@ -471,44 +303,6 @@ pfn_t kvmppc_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn) return gfn_to_pfn(vcpu->kvm, gfn); } -/* Book3s_32 CPUs always have 32 bytes cache line size, which Linux assumes. To - * make Book3s_32 Linux work on Book3s_64, we have to make sure we trap dcbz to - * emulate 32 bytes dcbz length. - * - * The Book3s_64 inventors also realized this case and implemented a special bit - * in the HID5 register, which is a hypervisor ressource. Thus we can't use it. - * - * My approach here is to patch the dcbz instruction on executing pages. - */ -static void kvmppc_patch_dcbz(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte) -{ - struct page *hpage; - u64 hpage_offset; - u32 *page; - int i; - - hpage = gfn_to_page(vcpu->kvm, pte->raddr >> PAGE_SHIFT); - if (is_error_page(hpage)) { - kvm_release_page_clean(hpage); - return; - } - - hpage_offset = pte->raddr & ~PAGE_MASK; - hpage_offset &= ~0xFFFULL; - hpage_offset /= 4; - - get_page(hpage); - page = kmap_atomic(hpage, KM_USER0); - - /* patch dcbz into reserved instruction, so we trap */ - for (i=hpage_offset; i < hpage_offset + (HW_PAGE_SIZE / 4); i++) - if ((page[i] & 0xff0007ff) == INS_DCBZ) - page[i] &= 0xfffffff7; - - kunmap_atomic(page, KM_USER0); - put_page(hpage); -} - static int kvmppc_xlate(struct kvm_vcpu *vcpu, ulong eaddr, bool data, struct kvmppc_pte *pte) { @@ -606,519 +400,6 @@ mmio: return EMULATE_DO_MMIO; } -static int kvmppc_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn) -{ - ulong mp_pa = vcpu->arch.magic_page_pa; - - if (unlikely(mp_pa) && - unlikely((mp_pa & KVM_PAM) >> PAGE_SHIFT == gfn)) { - return 1; - } - - return kvm_is_visible_gfn(vcpu->kvm, gfn); -} - -int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu, - ulong eaddr, int vec) -{ - bool data = (vec == BOOK3S_INTERRUPT_DATA_STORAGE); - int r = RESUME_GUEST; - int relocated; - int page_found = 0; - struct kvmppc_pte pte; - bool is_mmio = false; - bool dr = (vcpu->arch.shared->msr & MSR_DR) ? true : false; - bool ir = (vcpu->arch.shared->msr & MSR_IR) ? true : false; - u64 vsid; - - relocated = data ? dr : ir; - - /* Resolve real address if translation turned on */ - if (relocated) { - page_found = vcpu->arch.mmu.xlate(vcpu, eaddr, &pte, data); - } else { - pte.may_execute = true; - pte.may_read = true; - pte.may_write = true; - pte.raddr = eaddr & KVM_PAM; - pte.eaddr = eaddr; - pte.vpage = eaddr >> 12; - } - - switch (vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) { - case 0: - pte.vpage |= ((u64)VSID_REAL << (SID_SHIFT - 12)); - break; - case MSR_DR: - case MSR_IR: - vcpu->arch.mmu.esid_to_vsid(vcpu, eaddr >> SID_SHIFT, &vsid); - - if ((vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) == MSR_DR) - pte.vpage |= ((u64)VSID_REAL_DR << (SID_SHIFT - 12)); - else - pte.vpage |= ((u64)VSID_REAL_IR << (SID_SHIFT - 12)); - pte.vpage |= vsid; - - if (vsid == -1) - page_found = -EINVAL; - break; - } - - if (vcpu->arch.mmu.is_dcbz32(vcpu) && - (!(vcpu->arch.hflags & BOOK3S_HFLAG_DCBZ32))) { - /* - * If we do the dcbz hack, we have to NX on every execution, - * so we can patch the executing code. This renders our guest - * NX-less. - */ - pte.may_execute = !data; - } - - if (page_found == -ENOENT) { - /* Page not found in guest PTE entries */ - vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu); - vcpu->arch.shared->dsisr = to_svcpu(vcpu)->fault_dsisr; - vcpu->arch.shared->msr |= - (to_svcpu(vcpu)->shadow_srr1 & 0x00000000f8000000ULL); - kvmppc_book3s_queue_irqprio(vcpu, vec); - } else if (page_found == -EPERM) { - /* Storage protection */ - vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu); - vcpu->arch.shared->dsisr = - to_svcpu(vcpu)->fault_dsisr & ~DSISR_NOHPTE; - vcpu->arch.shared->dsisr |= DSISR_PROTFAULT; - vcpu->arch.shared->msr |= - (to_svcpu(vcpu)->shadow_srr1 & 0x00000000f8000000ULL); - kvmppc_book3s_queue_irqprio(vcpu, vec); - } else if (page_found == -EINVAL) { - /* Page not found in guest SLB */ - vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu); - kvmppc_book3s_queue_irqprio(vcpu, vec + 0x80); - } else if (!is_mmio && - kvmppc_visible_gfn(vcpu, pte.raddr >> PAGE_SHIFT)) { - /* The guest's PTE is not mapped yet. Map on the host */ - kvmppc_mmu_map_page(vcpu, &pte); - if (data) - vcpu->stat.sp_storage++; - else if (vcpu->arch.mmu.is_dcbz32(vcpu) && - (!(vcpu->arch.hflags & BOOK3S_HFLAG_DCBZ32))) - kvmppc_patch_dcbz(vcpu, &pte); - } else { - /* MMIO */ - vcpu->stat.mmio_exits++; - vcpu->arch.paddr_accessed = pte.raddr; - r = kvmppc_emulate_mmio(run, vcpu); - if ( r == RESUME_HOST_NV ) - r = RESUME_HOST; - } - - 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) */ -void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr) -{ - struct thread_struct *t = ¤t->thread; - u64 *vcpu_fpr = vcpu->arch.fpr; -#ifdef CONFIG_VSX - u64 *vcpu_vsx = vcpu->arch.vsr; -#endif - 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); -} - -static int kvmppc_read_inst(struct kvm_vcpu *vcpu) -{ - ulong srr0 = kvmppc_get_pc(vcpu); - u32 last_inst = kvmppc_get_last_inst(vcpu); - int ret; - - ret = kvmppc_ld(vcpu, &srr0, sizeof(u32), &last_inst, false); - if (ret == -ENOENT) { - ulong msr = vcpu->arch.shared->msr; - - msr = kvmppc_set_field(msr, 33, 33, 1); - msr = kvmppc_set_field(msr, 34, 36, 0); - vcpu->arch.shared->msr = kvmppc_set_field(msr, 42, 47, 0); - kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_INST_STORAGE); - return EMULATE_AGAIN; - } - - return EMULATE_DONE; -} - -static int kvmppc_check_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr) -{ - - /* Need to do paired single emulation? */ - if (!(vcpu->arch.hflags & BOOK3S_HFLAG_PAIRED_SINGLE)) - return EMULATE_DONE; - - /* Read out the instruction */ - if (kvmppc_read_inst(vcpu) == EMULATE_DONE) - /* Need to emulate */ - return EMULATE_FAIL; - - return EMULATE_AGAIN; -} - -/* 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; -#ifdef CONFIG_VSX - u64 *vcpu_vsx = vcpu->arch.vsr; -#endif - u64 *thread_fpr = (u64*)t->fpr; - int i; - - /* When we have paired singles, we emulate in software */ - if (vcpu->arch.hflags & BOOK3S_HFLAG_PAIRED_SINGLE) - return RESUME_GUEST; - - if (!(vcpu->arch.shared->msr & msr)) { - kvmppc_book3s_queue_irqprio(vcpu, exit_nr); - return RESUME_GUEST; - } - - /* We already own the ext */ - if (vcpu->arch.guest_owned_ext & msr) { - 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) -{ - int r = RESUME_HOST; - - vcpu->stat.sum_exits++; - - run->exit_reason = KVM_EXIT_UNKNOWN; - run->ready_for_interrupt_injection = 1; - - trace_kvm_book3s_exit(exit_nr, vcpu); - kvm_resched(vcpu); - switch (exit_nr) { - case BOOK3S_INTERRUPT_INST_STORAGE: - vcpu->stat.pf_instruc++; - -#ifdef CONFIG_PPC_BOOK3S_32 - /* We set segments as unused segments when invalidating them. So - * treat the respective fault as segment fault. */ - if (to_svcpu(vcpu)->sr[kvmppc_get_pc(vcpu) >> SID_SHIFT] - == SR_INVALID) { - kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu)); - r = RESUME_GUEST; - break; - } -#endif - - /* only care about PTEG not found errors, but leave NX alone */ - if (to_svcpu(vcpu)->shadow_srr1 & 0x40000000) { - r = kvmppc_handle_pagefault(run, vcpu, kvmppc_get_pc(vcpu), exit_nr); - vcpu->stat.sp_instruc++; - } else if (vcpu->arch.mmu.is_dcbz32(vcpu) && - (!(vcpu->arch.hflags & BOOK3S_HFLAG_DCBZ32))) { - /* - * XXX If we do the dcbz hack we use the NX bit to flush&patch the page, - * so we can't use the NX bit inside the guest. Let's cross our fingers, - * that no guest that needs the dcbz hack does NX. - */ - kvmppc_mmu_pte_flush(vcpu, kvmppc_get_pc(vcpu), ~0xFFFUL); - r = RESUME_GUEST; - } else { - vcpu->arch.shared->msr |= - to_svcpu(vcpu)->shadow_srr1 & 0x58000000; - kvmppc_book3s_queue_irqprio(vcpu, exit_nr); - r = RESUME_GUEST; - } - break; - case BOOK3S_INTERRUPT_DATA_STORAGE: - { - ulong dar = kvmppc_get_fault_dar(vcpu); - vcpu->stat.pf_storage++; - -#ifdef CONFIG_PPC_BOOK3S_32 - /* We set segments as unused segments when invalidating them. So - * treat the respective fault as segment fault. */ - if ((to_svcpu(vcpu)->sr[dar >> SID_SHIFT]) == SR_INVALID) { - kvmppc_mmu_map_segment(vcpu, dar); - r = RESUME_GUEST; - break; - } -#endif - - /* The only case we need to handle is missing shadow PTEs */ - if (to_svcpu(vcpu)->fault_dsisr & DSISR_NOHPTE) { - r = kvmppc_handle_pagefault(run, vcpu, dar, exit_nr); - } else { - vcpu->arch.shared->dar = dar; - vcpu->arch.shared->dsisr = to_svcpu(vcpu)->fault_dsisr; - kvmppc_book3s_queue_irqprio(vcpu, exit_nr); - r = RESUME_GUEST; - } - break; - } - case BOOK3S_INTERRUPT_DATA_SEGMENT: - if (kvmppc_mmu_map_segment(vcpu, kvmppc_get_fault_dar(vcpu)) < 0) { - vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu); - kvmppc_book3s_queue_irqprio(vcpu, - BOOK3S_INTERRUPT_DATA_SEGMENT); - } - r = RESUME_GUEST; - break; - case BOOK3S_INTERRUPT_INST_SEGMENT: - if (kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu)) < 0) { - kvmppc_book3s_queue_irqprio(vcpu, - BOOK3S_INTERRUPT_INST_SEGMENT); - } - r = RESUME_GUEST; - break; - /* We're good on these - the host merely wanted to get our attention */ - case BOOK3S_INTERRUPT_DECREMENTER: - vcpu->stat.dec_exits++; - r = RESUME_GUEST; - break; - case BOOK3S_INTERRUPT_EXTERNAL: - vcpu->stat.ext_intr_exits++; - r = RESUME_GUEST; - break; - case BOOK3S_INTERRUPT_PERFMON: - r = RESUME_GUEST; - break; - case BOOK3S_INTERRUPT_PROGRAM: - { - enum emulation_result er; - ulong flags; - -program_interrupt: - flags = to_svcpu(vcpu)->shadow_srr1 & 0x1f0000ull; - - if (vcpu->arch.shared->msr & MSR_PR) { -#ifdef EXIT_DEBUG - printk(KERN_INFO "Userspace triggered 0x700 exception at 0x%lx (0x%x)\n", kvmppc_get_pc(vcpu), kvmppc_get_last_inst(vcpu)); -#endif - if ((kvmppc_get_last_inst(vcpu) & 0xff0007ff) != - (INS_DCBZ & 0xfffffff7)) { - kvmppc_core_queue_program(vcpu, flags); - r = RESUME_GUEST; - break; - } - } - - vcpu->stat.emulated_inst_exits++; - er = kvmppc_emulate_instruction(run, vcpu); - switch (er) { - case EMULATE_DONE: - r = RESUME_GUEST_NV; - break; - case EMULATE_AGAIN: - r = RESUME_GUEST; - break; - case EMULATE_FAIL: - printk(KERN_CRIT "%s: emulation at %lx failed (%08x)\n", - __func__, kvmppc_get_pc(vcpu), kvmppc_get_last_inst(vcpu)); - kvmppc_core_queue_program(vcpu, flags); - r = RESUME_GUEST; - break; - case EMULATE_DO_MMIO: - run->exit_reason = KVM_EXIT_MMIO; - r = RESUME_HOST_NV; - break; - default: - BUG(); - } - break; - } - case BOOK3S_INTERRUPT_SYSCALL: - if (vcpu->arch.osi_enabled && - (((u32)kvmppc_get_gpr(vcpu, 3)) == OSI_SC_MAGIC_R3) && - (((u32)kvmppc_get_gpr(vcpu, 4)) == OSI_SC_MAGIC_R4)) { - /* MOL hypercalls */ - u64 *gprs = run->osi.gprs; - int i; - - run->exit_reason = KVM_EXIT_OSI; - for (i = 0; i < 32; i++) - gprs[i] = kvmppc_get_gpr(vcpu, i); - vcpu->arch.osi_needed = 1; - r = RESUME_HOST_NV; - } else if (!(vcpu->arch.shared->msr & MSR_PR) && - (((u32)kvmppc_get_gpr(vcpu, 0)) == KVM_SC_MAGIC_R0)) { - /* KVM PV hypercalls */ - kvmppc_set_gpr(vcpu, 3, kvmppc_kvm_pv(vcpu)); - r = RESUME_GUEST; - } else { - /* Guest syscalls */ - vcpu->stat.syscall_exits++; - kvmppc_book3s_queue_irqprio(vcpu, exit_nr); - r = RESUME_GUEST; - } - break; - case BOOK3S_INTERRUPT_FP_UNAVAIL: - case BOOK3S_INTERRUPT_ALTIVEC: - case BOOK3S_INTERRUPT_VSX: - { - int ext_msr = 0; - - switch (exit_nr) { - case BOOK3S_INTERRUPT_FP_UNAVAIL: ext_msr = MSR_FP; break; - case BOOK3S_INTERRUPT_ALTIVEC: ext_msr = MSR_VEC; break; - case BOOK3S_INTERRUPT_VSX: ext_msr = MSR_VSX; break; - } - - switch (kvmppc_check_ext(vcpu, exit_nr)) { - case EMULATE_DONE: - /* everything ok - let's enable the ext */ - r = kvmppc_handle_ext(vcpu, exit_nr, ext_msr); - break; - case EMULATE_FAIL: - /* we need to emulate this instruction */ - goto program_interrupt; - break; - default: - /* nothing to worry about - go again */ - break; - } - break; - } - case BOOK3S_INTERRUPT_ALIGNMENT: - if (kvmppc_read_inst(vcpu) == EMULATE_DONE) { - vcpu->arch.shared->dsisr = kvmppc_alignment_dsisr(vcpu, - kvmppc_get_last_inst(vcpu)); - vcpu->arch.shared->dar = kvmppc_alignment_dar(vcpu, - kvmppc_get_last_inst(vcpu)); - kvmppc_book3s_queue_irqprio(vcpu, exit_nr); - } - r = RESUME_GUEST; - 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, kvmppc_get_pc(vcpu), to_svcpu(vcpu)->shadow_srr1); - r = RESUME_HOST; - BUG(); - break; - } - - - if (!(r & RESUME_HOST)) { - /* To avoid clobbering exit_reason, only check for signals if - * we aren't already exiting to userspace for some other - * reason. */ - if (signal_pending(current)) { -#ifdef EXIT_DEBUG - printk(KERN_EMERG "KVM: Going back to host\n"); -#endif - vcpu->stat.signal_exits++; - run->exit_reason = KVM_EXIT_INTR; - r = -EINTR; - } else { - /* In case an interrupt came in that was triggered - * from userspace (like DEC), we need to check what - * to inject now! */ - kvmppc_core_deliver_interrupts(vcpu); - } - } - - trace_kvm_book3s_reenter(r, vcpu); - - return r; -} - int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) { return 0; @@ -1179,69 +460,6 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) return 0; } -int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, - struct kvm_sregs *sregs) -{ - struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu); - int i; - - sregs->pvr = vcpu->arch.pvr; - - sregs->u.s.sdr1 = to_book3s(vcpu)->sdr1; - if (vcpu->arch.hflags & BOOK3S_HFLAG_SLB) { - for (i = 0; i < 64; i++) { - sregs->u.s.ppc64.slb[i].slbe = vcpu3s->slb[i].orige | i; - sregs->u.s.ppc64.slb[i].slbv = vcpu3s->slb[i].origv; - } - } else { - for (i = 0; i < 16; i++) - sregs->u.s.ppc32.sr[i] = vcpu->arch.shared->sr[i]; - - for (i = 0; i < 8; i++) { - sregs->u.s.ppc32.ibat[i] = vcpu3s->ibat[i].raw; - sregs->u.s.ppc32.dbat[i] = vcpu3s->dbat[i].raw; - } - } - - return 0; -} - -int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, - struct kvm_sregs *sregs) -{ - struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu); - int i; - - kvmppc_set_pvr(vcpu, sregs->pvr); - - vcpu3s->sdr1 = sregs->u.s.sdr1; - if (vcpu->arch.hflags & BOOK3S_HFLAG_SLB) { - for (i = 0; i < 64; i++) { - vcpu->arch.mmu.slbmte(vcpu, sregs->u.s.ppc64.slb[i].slbv, - sregs->u.s.ppc64.slb[i].slbe); - } - } else { - for (i = 0; i < 16; i++) { - vcpu->arch.mmu.mtsrin(vcpu, i, sregs->u.s.ppc32.sr[i]); - } - for (i = 0; i < 8; i++) { - kvmppc_set_bat(vcpu, &(vcpu3s->ibat[i]), false, - (u32)sregs->u.s.ppc32.ibat[i]); - kvmppc_set_bat(vcpu, &(vcpu3s->ibat[i]), true, - (u32)(sregs->u.s.ppc32.ibat[i] >> 32)); - kvmppc_set_bat(vcpu, &(vcpu3s->dbat[i]), false, - (u32)sregs->u.s.ppc32.dbat[i]); - kvmppc_set_bat(vcpu, &(vcpu3s->dbat[i]), true, - (u32)(sregs->u.s.ppc32.dbat[i] >> 32)); - } - } - - /* Flush the MMU after messing with the segments */ - kvmppc_mmu_pte_flush(vcpu, 0, 0); - - return 0; -} - int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { return -ENOTSUPP; @@ -1296,202 +514,3 @@ out: mutex_unlock(&kvm->slots_lock); return r; } - -int kvmppc_core_check_processor_compat(void) -{ - return 0; -} - -struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id) -{ - struct kvmppc_vcpu_book3s *vcpu_book3s; - struct kvm_vcpu *vcpu; - int err = -ENOMEM; - unsigned long p; - - vcpu_book3s = vzalloc(sizeof(struct kvmppc_vcpu_book3s)); - if (!vcpu_book3s) - goto out; - - vcpu_book3s->shadow_vcpu = (struct kvmppc_book3s_shadow_vcpu *) - kzalloc(sizeof(*vcpu_book3s->shadow_vcpu), GFP_KERNEL); - if (!vcpu_book3s->shadow_vcpu) - goto free_vcpu; - - vcpu = &vcpu_book3s->vcpu; - err = kvm_vcpu_init(vcpu, kvm, id); - if (err) - goto free_shadow_vcpu; - - p = __get_free_page(GFP_KERNEL|__GFP_ZERO); - /* the real shared page fills the last 4k of our page */ - vcpu->arch.shared = (void*)(p + PAGE_SIZE - 4096); - if (!p) - goto uninit_vcpu; - - vcpu->arch.host_retip = kvm_return_point; - vcpu->arch.host_msr = mfmsr(); -#ifdef CONFIG_PPC_BOOK3S_64 - /* default to book3s_64 (970fx) */ - vcpu->arch.pvr = 0x3C0301; -#else - /* default to book3s_32 (750) */ - vcpu->arch.pvr = 0x84202; -#endif - kvmppc_set_pvr(vcpu, vcpu->arch.pvr); - vcpu_book3s->slb_nr = 64; - - /* remember where some real-mode handlers are */ - vcpu->arch.trampoline_lowmem = kvmppc_trampoline_lowmem; - vcpu->arch.trampoline_enter = kvmppc_trampoline_enter; - vcpu->arch.highmem_handler = (ulong)kvmppc_handler_highmem; -#ifdef CONFIG_PPC_BOOK3S_64 - vcpu->arch.rmcall = *(ulong*)kvmppc_rmcall; -#else - vcpu->arch.rmcall = (ulong)kvmppc_rmcall; -#endif - - vcpu->arch.shadow_msr = MSR_USER64; - - err = kvmppc_mmu_init(vcpu); - if (err < 0) - goto uninit_vcpu; - - return vcpu; - -uninit_vcpu: - kvm_vcpu_uninit(vcpu); -free_shadow_vcpu: - kfree(vcpu_book3s->shadow_vcpu); -free_vcpu: - vfree(vcpu_book3s); -out: - return ERR_PTR(err); -} - -void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu) -{ - struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu); - - free_page((unsigned long)vcpu->arch.shared & PAGE_MASK); - kvm_vcpu_uninit(vcpu); - kfree(vcpu_book3s->shadow_vcpu); - vfree(vcpu_book3s); -} - -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; - double fpr[32][TS_FPRWIDTH]; - unsigned int fpscr; - int fpexc_mode; -#ifdef CONFIG_ALTIVEC - vector128 vr[32]; - vector128 vscr; - unsigned long uninitialized_var(vrsave); - int used_vr; -#endif -#ifdef CONFIG_VSX - int used_vsr; -#endif - ulong ext_msr; - - /* No need to go into the guest when all we do is going out */ - if (signal_pending(current)) { - kvm_run->exit_reason = KVM_EXIT_INTR; - return -EINTR; - } - - /* Save FPU state in stack */ - if (current->thread.regs->msr & MSR_FP) - giveup_fpu(current); - memcpy(fpr, current->thread.fpr, sizeof(current->thread.fpr)); - fpscr = current->thread.fpscr.val; - fpexc_mode = current->thread.fpexc_mode; - -#ifdef CONFIG_ALTIVEC - /* Save Altivec state in stack */ - used_vr = current->thread.used_vr; - if (used_vr) { - if (current->thread.regs->msr & MSR_VEC) - giveup_altivec(current); - memcpy(vr, current->thread.vr, sizeof(current->thread.vr)); - vscr = current->thread.vscr; - vrsave = current->thread.vrsave; - } -#endif - -#ifdef CONFIG_VSX - /* Save VSX state in stack */ - used_vsr = current->thread.used_vsr; - if (used_vsr && (current->thread.regs->msr & MSR_VSX)) - __giveup_vsx(current); -#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(); - - /* Preload FPU if it's enabled */ - if (vcpu->arch.shared->msr & MSR_FP) - kvmppc_handle_ext(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL, MSR_FP); - - ret = __kvmppc_vcpu_entry(kvm_run, 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, fpr, sizeof(current->thread.fpr)); - current->thread.fpscr.val = fpscr; - current->thread.fpexc_mode = fpexc_mode; - -#ifdef CONFIG_ALTIVEC - /* Restore Altivec state from stack */ - if (used_vr && current->thread.used_vr) { - memcpy(current->thread.vr, vr, sizeof(current->thread.vr)); - current->thread.vscr = vscr; - current->thread.vrsave = vrsave; - } - current->thread.used_vr = used_vr; -#endif - -#ifdef CONFIG_VSX - current->thread.used_vsr = used_vsr; -#endif - - return ret; -} - -static int kvmppc_book3s_init(void) -{ - int r; - - r = kvm_init(NULL, sizeof(struct kvmppc_vcpu_book3s), 0, - THIS_MODULE); - - if (r) - return r; - - r = kvmppc_mmu_hpte_sysinit(); - - return r; -} - -static void kvmppc_book3s_exit(void) -{ - kvmppc_mmu_hpte_sysexit(); - kvm_exit(); -} - -module_init(kvmppc_book3s_init); -module_exit(kvmppc_book3s_exit); diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c index d7889ef3211..c6d3e194b6b 100644 --- a/arch/powerpc/kvm/book3s_64_mmu.c +++ b/arch/powerpc/kvm/book3s_64_mmu.c @@ -41,36 +41,36 @@ static void kvmppc_mmu_book3s_64_reset_msr(struct kvm_vcpu *vcpu) } static struct kvmppc_slb *kvmppc_mmu_book3s_64_find_slbe( - struct kvmppc_vcpu_book3s *vcpu_book3s, + struct kvm_vcpu *vcpu, gva_t eaddr) { int i; u64 esid = GET_ESID(eaddr); u64 esid_1t = GET_ESID_1T(eaddr); - for (i = 0; i < vcpu_book3s->slb_nr; i++) { + for (i = 0; i < vcpu->arch.slb_nr; i++) { u64 cmp_esid = esid; - if (!vcpu_book3s->slb[i].valid) + if (!vcpu->arch.slb[i].valid) continue; - if (vcpu_book3s->slb[i].tb) + if (vcpu->arch.slb[i].tb) cmp_esid = esid_1t; - if (vcpu_book3s->slb[i].esid == cmp_esid) - return &vcpu_book3s->slb[i]; + if (vcpu->arch.slb[i].esid == cmp_esid) + return &vcpu->arch.slb[i]; } dprintk("KVM: No SLB entry found for 0x%lx [%llx | %llx]\n", eaddr, esid, esid_1t); - for (i = 0; i < vcpu_book3s->slb_nr; i++) { - if (vcpu_book3s->slb[i].vsid) + for (i = 0; i < vcpu->arch.slb_nr; i++) { + if (vcpu->arch.slb[i].vsid) 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); + vcpu->arch.slb[i].valid ? 'v' : ' ', + vcpu->arch.slb[i].large ? 'l' : ' ', + vcpu->arch.slb[i].tb ? 't' : ' ', + vcpu->arch.slb[i].esid, + vcpu->arch.slb[i].vsid); } return NULL; @@ -81,7 +81,7 @@ static u64 kvmppc_mmu_book3s_64_ea_to_vp(struct kvm_vcpu *vcpu, gva_t eaddr, { struct kvmppc_slb *slb; - slb = kvmppc_mmu_book3s_64_find_slbe(to_book3s(vcpu), eaddr); + slb = kvmppc_mmu_book3s_64_find_slbe(vcpu, eaddr); if (!slb) return 0; @@ -180,7 +180,7 @@ static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, return 0; } - slbe = kvmppc_mmu_book3s_64_find_slbe(vcpu_book3s, eaddr); + slbe = kvmppc_mmu_book3s_64_find_slbe(vcpu, eaddr); if (!slbe) goto no_seg_found; @@ -320,10 +320,10 @@ static void kvmppc_mmu_book3s_64_slbmte(struct kvm_vcpu *vcpu, u64 rs, u64 rb) esid_1t = GET_ESID_1T(rb); slb_nr = rb & 0xfff; - if (slb_nr > vcpu_book3s->slb_nr) + if (slb_nr > vcpu->arch.slb_nr) return; - slbe = &vcpu_book3s->slb[slb_nr]; + slbe = &vcpu->arch.slb[slb_nr]; slbe->large = (rs & SLB_VSID_L) ? 1 : 0; slbe->tb = (rs & SLB_VSID_B_1T) ? 1 : 0; @@ -344,38 +344,35 @@ static void kvmppc_mmu_book3s_64_slbmte(struct kvm_vcpu *vcpu, u64 rs, u64 rb) static u64 kvmppc_mmu_book3s_64_slbmfee(struct kvm_vcpu *vcpu, u64 slb_nr) { - struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu); struct kvmppc_slb *slbe; - if (slb_nr > vcpu_book3s->slb_nr) + if (slb_nr > vcpu->arch.slb_nr) return 0; - slbe = &vcpu_book3s->slb[slb_nr]; + slbe = &vcpu->arch.slb[slb_nr]; return slbe->orige; } static u64 kvmppc_mmu_book3s_64_slbmfev(struct kvm_vcpu *vcpu, u64 slb_nr) { - struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu); struct kvmppc_slb *slbe; - if (slb_nr > vcpu_book3s->slb_nr) + if (slb_nr > vcpu->arch.slb_nr) return 0; - slbe = &vcpu_book3s->slb[slb_nr]; + slbe = &vcpu->arch.slb[slb_nr]; return slbe->origv; } static void kvmppc_mmu_book3s_64_slbie(struct kvm_vcpu *vcpu, u64 ea) { - struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu); struct kvmppc_slb *slbe; dprintk("KVM MMU: slbie(0x%llx)\n", ea); - slbe = kvmppc_mmu_book3s_64_find_slbe(vcpu_book3s, ea); + slbe = kvmppc_mmu_book3s_64_find_slbe(vcpu, ea); if (!slbe) return; @@ -389,13 +386,12 @@ static void kvmppc_mmu_book3s_64_slbie(struct kvm_vcpu *vcpu, u64 ea) static void kvmppc_mmu_book3s_64_slbia(struct kvm_vcpu *vcpu) { - struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu); int i; dprintk("KVM MMU: slbia()\n"); - for (i = 1; i < vcpu_book3s->slb_nr; i++) - vcpu_book3s->slb[i].valid = false; + for (i = 1; i < vcpu->arch.slb_nr; i++) + vcpu->arch.slb[i].valid = false; if (vcpu->arch.shared->msr & MSR_IR) { kvmppc_mmu_flush_segments(vcpu); @@ -464,7 +460,7 @@ static int kvmppc_mmu_book3s_64_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid, ulong mp_ea = vcpu->arch.magic_page_ea; if (vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) { - slb = kvmppc_mmu_book3s_64_find_slbe(to_book3s(vcpu), ea); + slb = kvmppc_mmu_book3s_64_find_slbe(vcpu, ea); if (slb) gvsid = slb->vsid; } diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c new file mode 100644 index 00000000000..bc3a2ea9421 --- /dev/null +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -0,0 +1,180 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + * + * Copyright 2010 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com> + */ + +#include <linux/types.h> +#include <linux/string.h> +#include <linux/kvm.h> +#include <linux/kvm_host.h> +#include <linux/highmem.h> +#include <linux/gfp.h> +#include <linux/slab.h> +#include <linux/hugetlb.h> + +#include <asm/tlbflush.h> +#include <asm/kvm_ppc.h> +#include <asm/kvm_book3s.h> +#include <asm/mmu-hash64.h> +#include <asm/hvcall.h> +#include <asm/synch.h> +#include <asm/ppc-opcode.h> +#include <asm/cputable.h> + +/* For now use fixed-size 16MB page table */ +#define HPT_ORDER 24 +#define HPT_NPTEG (1ul << (HPT_ORDER - 7)) /* 128B per pteg */ +#define HPT_HASH_MASK (HPT_NPTEG - 1) + +/* Pages in the VRMA are 16MB pages */ +#define VRMA_PAGE_ORDER 24 +#define VRMA_VSID 0x1ffffffUL /* 1TB VSID reserved for VRMA */ + +/* POWER7 has 10-bit LPIDs, PPC970 has 6-bit LPIDs */ +#define MAX_LPID_970 63 +#define NR_LPIDS (LPID_RSVD + 1) +unsigned long lpid_inuse[BITS_TO_LONGS(NR_LPIDS)]; + +long kvmppc_alloc_hpt(struct kvm *kvm) +{ + unsigned long hpt; + unsigned long lpid; + + hpt = __get_free_pages(GFP_KERNEL|__GFP_ZERO|__GFP_REPEAT|__GFP_NOWARN, + HPT_ORDER - PAGE_SHIFT); + if (!hpt) { + pr_err("kvm_alloc_hpt: Couldn't alloc HPT\n"); + return -ENOMEM; + } + kvm->arch.hpt_virt = hpt; + + do { + lpid = find_first_zero_bit(lpid_inuse, NR_LPIDS); + if (lpid >= NR_LPIDS) { + pr_err("kvm_alloc_hpt: No LPIDs free\n"); + free_pages(hpt, HPT_ORDER - PAGE_SHIFT); + return -ENOMEM; + } + } while (test_and_set_bit(lpid, lpid_inuse)); + + kvm->arch.sdr1 = __pa(hpt) | (HPT_ORDER - 18); + kvm->arch.lpid = lpid; + + pr_info("KVM guest htab at %lx, LPID %lx\n", hpt, lpid); + return 0; +} + +void kvmppc_free_hpt(struct kvm *kvm) +{ + clear_bit(kvm->arch.lpid, lpid_inuse); + free_pages(kvm->arch.hpt_virt, HPT_ORDER - PAGE_SHIFT); +} + +void kvmppc_map_vrma(struct kvm *kvm, struct kvm_userspace_memory_region *mem) +{ + unsigned long i; + unsigned long npages = kvm->arch.ram_npages; + unsigned long pfn; + unsigned long *hpte; + unsigned long hash; + struct kvmppc_pginfo *pginfo = kvm->arch.ram_pginfo; + + if (!pginfo) + return; + + /* VRMA can't be > 1TB */ + if (npages > 1ul << (40 - kvm->arch.ram_porder)) + npages = 1ul << (40 - kvm->arch.ram_porder); + /* Can't use more than 1 HPTE per HPTEG */ + if (npages > HPT_NPTEG) + npages = HPT_NPTEG; + + for (i = 0; i < npages; ++i) { + pfn = pginfo[i].pfn; + if (!pfn) + break; + /* can't use hpt_hash since va > 64 bits */ + hash = (i ^ (VRMA_VSID ^ (VRMA_VSID << 25))) & HPT_HASH_MASK; + /* + * We assume that the hash table is empty and no + * vcpus are using it at this stage. Since we create + * at most one HPTE per HPTEG, we just assume entry 7 + * is available and use it. + */ + hpte = (unsigned long *) (kvm->arch.hpt_virt + (hash << 7)); + hpte += 7 * 2; + /* HPTE low word - RPN, protection, etc. */ + hpte[1] = (pfn << PAGE_SHIFT) | HPTE_R_R | HPTE_R_C | + HPTE_R_M | PP_RWXX; + wmb(); + hpte[0] = HPTE_V_1TB_SEG | (VRMA_VSID << (40 - 16)) | + (i << (VRMA_PAGE_ORDER - 16)) | HPTE_V_BOLTED | + HPTE_V_LARGE | HPTE_V_VALID; + } +} + +int kvmppc_mmu_hv_init(void) +{ + unsigned long host_lpid, rsvd_lpid; + + if (!cpu_has_feature(CPU_FTR_HVMODE)) + return -EINVAL; + + memset(lpid_inuse, 0, sizeof(lpid_inuse)); + + if (cpu_has_feature(CPU_FTR_ARCH_206)) { + host_lpid = mfspr(SPRN_LPID); /* POWER7 */ + rsvd_lpid = LPID_RSVD; + } else { + host_lpid = 0; /* PPC970 */ + rsvd_lpid = MAX_LPID_970; + } + + set_bit(host_lpid, lpid_inuse); + /* rsvd_lpid is reserved for use in partition switching */ + set_bit(rsvd_lpid, lpid_inuse); + + return 0; +} + +void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu) +{ +} + +static void kvmppc_mmu_book3s_64_hv_reset_msr(struct kvm_vcpu *vcpu) +{ + kvmppc_set_msr(vcpu, MSR_SF | MSR_ME); +} + +static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, + struct kvmppc_pte *gpte, bool data) +{ + return -ENOENT; +} + +void kvmppc_mmu_book3s_hv_init(struct kvm_vcpu *vcpu) +{ + struct kvmppc_mmu *mmu = &vcpu->arch.mmu; + + if (cpu_has_feature(CPU_FTR_ARCH_206)) + vcpu->arch.slb_nr = 32; /* POWER7 */ + else + vcpu->arch.slb_nr = 64; + + mmu->xlate = kvmppc_mmu_book3s_64_hv_xlate; + mmu->reset_msr = kvmppc_mmu_book3s_64_hv_reset_msr; + + vcpu->arch.hflags |= BOOK3S_HFLAG_SLB; +} diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c new file mode 100644 index 00000000000..ea0f8c537c2 --- /dev/null +++ b/arch/powerpc/kvm/book3s_64_vio_hv.c @@ -0,0 +1,73 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + * + * Copyright 2010 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com> + * Copyright 2011 David Gibson, IBM Corporation <dwg@au1.ibm.com> + */ + +#include <linux/types.h> +#include <linux/string.h> +#include <linux/kvm.h> +#include <linux/kvm_host.h> +#include <linux/highmem.h> +#include <linux/gfp.h> +#include <linux/slab.h> +#include <linux/hugetlb.h> +#include <linux/list.h> + +#include <asm/tlbflush.h> +#include <asm/kvm_ppc.h> +#include <asm/kvm_book3s.h> +#include <asm/mmu-hash64.h> +#include <asm/hvcall.h> +#include <asm/synch.h> +#include <asm/ppc-opcode.h> +#include <asm/kvm_host.h> +#include <asm/udbg.h> + +#define TCES_PER_PAGE (PAGE_SIZE / sizeof(u64)) + +long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, + unsigned long ioba, unsigned long tce) +{ + struct kvm *kvm = vcpu->kvm; + struct kvmppc_spapr_tce_table *stt; + + /* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */ + /* liobn, ioba, tce); */ + + list_for_each_entry(stt, &kvm->arch.spapr_tce_tables, list) { + if (stt->liobn == liobn) { + unsigned long idx = ioba >> SPAPR_TCE_SHIFT; + struct page *page; + u64 *tbl; + + /* udbg_printf("H_PUT_TCE: liobn 0x%lx => stt=%p window_size=0x%x\n", */ + /* liobn, stt, stt->window_size); */ + if (ioba >= stt->window_size) + return H_PARAMETER; + + page = stt->pages[idx / TCES_PER_PAGE]; + tbl = (u64 *)page_address(page); + + /* FIXME: Need to validate the TCE itself */ + /* udbg_printf("tce @ %p\n", &tbl[idx % TCES_PER_PAGE]); */ + tbl[idx % TCES_PER_PAGE] = tce; + return H_SUCCESS; + } + } + + /* Didn't find the liobn, punt it to userspace */ + return H_TOO_HARD; +} diff --git a/arch/powerpc/kvm/book3s_exports.c b/arch/powerpc/kvm/book3s_exports.c index 1dd5a1ddfd0..88c8f26add0 100644 --- a/arch/powerpc/kvm/book3s_exports.c +++ b/arch/powerpc/kvm/book3s_exports.c @@ -20,8 +20,11 @@ #include <linux/module.h> #include <asm/kvm_book3s.h> -EXPORT_SYMBOL_GPL(kvmppc_trampoline_enter); -EXPORT_SYMBOL_GPL(kvmppc_trampoline_lowmem); +#ifdef CONFIG_KVM_BOOK3S_64_HV +EXPORT_SYMBOL_GPL(kvmppc_hv_entry_trampoline); +#else +EXPORT_SYMBOL_GPL(kvmppc_handler_trampoline_enter); +EXPORT_SYMBOL_GPL(kvmppc_handler_lowmem_trampoline); EXPORT_SYMBOL_GPL(kvmppc_rmcall); EXPORT_SYMBOL_GPL(kvmppc_load_up_fpu); #ifdef CONFIG_ALTIVEC @@ -30,3 +33,5 @@ EXPORT_SYMBOL_GPL(kvmppc_load_up_altivec); #ifdef CONFIG_VSX EXPORT_SYMBOL_GPL(kvmppc_load_up_vsx); #endif +#endif + diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c new file mode 100644 index 00000000000..cc0d7f1b19a --- /dev/null +++ b/arch/powerpc/kvm/book3s_hv.c @@ -0,0 +1,1269 @@ +/* + * Copyright 2011 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com> + * Copyright (C) 2009. SUSE Linux Products GmbH. All rights reserved. + * + * Authors: + * Paul Mackerras <paulus@au1.ibm.com> + * Alexander Graf <agraf@suse.de> + * Kevin Wolf <mail@kevin-wolf.de> + * + * Description: KVM functions specific to running on Book 3S + * processors in hypervisor mode (specifically POWER7 and later). + * + * This file is derived from arch/powerpc/kvm/book3s.c, + * by Alexander Graf <agraf@suse.de>. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + */ + +#include <linux/kvm_host.h> +#include <linux/err.h> +#include <linux/slab.h> +#include <linux/preempt.h> +#include <linux/sched.h> +#include <linux/delay.h> +#include <linux/fs.h> +#include <linux/anon_inodes.h> +#include <linux/cpumask.h> +#include <linux/spinlock.h> +#include <linux/page-flags.h> + +#include <asm/reg.h> +#include <asm/cputable.h> +#include <asm/cacheflush.h> +#include <asm/tlbflush.h> +#include <asm/uaccess.h> +#include <asm/io.h> +#include <asm/kvm_ppc.h> +#include <asm/kvm_book3s.h> +#include <asm/mmu_context.h> +#include <asm/lppaca.h> +#include <asm/processor.h> +#include <asm/cputhreads.h> +#include <asm/page.h> +#include <linux/gfp.h> +#include <linux/sched.h> +#include <linux/vmalloc.h> +#include <linux/highmem.h> + +/* + * For now, limit memory to 64GB and require it to be large pages. + * This value is chosen because it makes the ram_pginfo array be + * 64kB in size, which is about as large as we want to be trying + * to allocate with kmalloc. + */ +#define MAX_MEM_ORDER 36 + +#define LARGE_PAGE_ORDER 24 /* 16MB pages */ + +/* #define EXIT_DEBUG */ +/* #define EXIT_DEBUG_SIMPLE */ +/* #define EXIT_DEBUG_INT */ + +void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu) +{ + local_paca->kvm_hstate.kvm_vcpu = vcpu; + local_paca->kvm_hstate.kvm_vcore = vcpu->arch.vcore; +} + +void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu) +{ +} + +static void kvmppc_vcpu_blocked(struct kvm_vcpu *vcpu); +static void kvmppc_vcpu_unblocked(struct kvm_vcpu *vcpu); + +void kvmppc_vcpu_block(struct kvm_vcpu *vcpu) +{ + u64 now; + unsigned long dec_nsec; + + now = get_tb(); + if (now >= vcpu->arch.dec_expires && !kvmppc_core_pending_dec(vcpu)) + kvmppc_core_queue_dec(vcpu); + if (vcpu->arch.pending_exceptions) + return; + if (vcpu->arch.dec_expires != ~(u64)0) { + dec_nsec = (vcpu->arch.dec_expires - now) * NSEC_PER_SEC / + tb_ticks_per_sec; + hrtimer_start(&vcpu->arch.dec_timer, ktime_set(0, dec_nsec), + HRTIMER_MODE_REL); + } + + kvmppc_vcpu_blocked(vcpu); + + kvm_vcpu_block(vcpu); + vcpu->stat.halt_wakeup++; + + if (vcpu->arch.dec_expires != ~(u64)0) + hrtimer_try_to_cancel(&vcpu->arch.dec_timer); + + kvmppc_vcpu_unblocked(vcpu); +} + +void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr) +{ + vcpu->arch.shregs.msr = msr; +} + +void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr) +{ + vcpu->arch.pvr = pvr; +} + +void kvmppc_dump_regs(struct kvm_vcpu *vcpu) +{ + int r; + + pr_err("vcpu %p (%d):\n", vcpu, vcpu->vcpu_id); + pr_err("pc = %.16lx msr = %.16llx trap = %x\n", + vcpu->arch.pc, vcpu->arch.shregs.msr, vcpu->arch.trap); + for (r = 0; r < 16; ++r) + pr_err("r%2d = %.16lx r%d = %.16lx\n", + r, kvmppc_get_gpr(vcpu, r), + r+16, kvmppc_get_gpr(vcpu, r+16)); + pr_err("ctr = %.16lx lr = %.16lx\n", + vcpu->arch.ctr, vcpu->arch.lr); + pr_err("srr0 = %.16llx srr1 = %.16llx\n", + vcpu->arch.shregs.srr0, vcpu->arch.shregs.srr1); + pr_err("sprg0 = %.16llx sprg1 = %.16llx\n", + vcpu->arch.shregs.sprg0, vcpu->arch.shregs.sprg1); + pr_err("sprg2 = %.16llx sprg3 = %.16llx\n", + vcpu->arch.shregs.sprg2, vcpu->arch.shregs.sprg3); + pr_err("cr = %.8x xer = %.16lx dsisr = %.8x\n", + vcpu->arch.cr, vcpu->arch.xer, vcpu->arch.shregs.dsisr); + pr_err("dar = %.16llx\n", vcpu->arch.shregs.dar); + pr_err("fault dar = %.16lx dsisr = %.8x\n", + vcpu->arch.fault_dar, vcpu->arch.fault_dsisr); + pr_err("SLB (%d entries):\n", vcpu->arch.slb_max); + for (r = 0; r < vcpu->arch.slb_max; ++r) + pr_err(" ESID = %.16llx VSID = %.16llx\n", + vcpu->arch.slb[r].orige, vcpu->arch.slb[r].origv); + pr_err("lpcr = %.16lx sdr1 = %.16lx last_inst = %.8x\n", + vcpu->kvm->arch.lpcr, vcpu->kvm->arch.sdr1, + vcpu->arch.last_inst); +} + +struct kvm_vcpu *kvmppc_find_vcpu(struct kvm *kvm, int id) +{ + int r; + struct kvm_vcpu *v, *ret = NULL; + + mutex_lock(&kvm->lock); + kvm_for_each_vcpu(r, v, kvm) { + if (v->vcpu_id == id) { + ret = v; + break; + } + } + mutex_unlock(&kvm->lock); + return ret; +} + +static void init_vpa(struct kvm_vcpu *vcpu, struct lppaca *vpa) +{ + vpa->shared_proc = 1; + vpa->yield_count = 1; +} + +static unsigned long do_h_register_vpa(struct kvm_vcpu *vcpu, + unsigned long flags, + unsigned long vcpuid, unsigned long vpa) +{ + struct kvm *kvm = vcpu->kvm; + unsigned long pg_index, ra, len; + unsigned long pg_offset; + void *va; + struct kvm_vcpu *tvcpu; + + tvcpu = kvmppc_find_vcpu(kvm, vcpuid); + if (!tvcpu) + return H_PARAMETER; + + flags >>= 63 - 18; + flags &= 7; + if (flags == 0 || flags == 4) + return H_PARAMETER; + if (flags < 4) { + if (vpa & 0x7f) + return H_PARAMETER; + /* registering new area; convert logical addr to real */ + pg_index = vpa >> kvm->arch.ram_porder; + pg_offset = vpa & (kvm->arch.ram_psize - 1); + if (pg_index >= kvm->arch.ram_npages) + return H_PARAMETER; + if (kvm->arch.ram_pginfo[pg_index].pfn == 0) + return H_PARAMETER; + ra = kvm->arch.ram_pginfo[pg_index].pfn << PAGE_SHIFT; + ra |= pg_offset; + va = __va(ra); + if (flags <= 1) + len = *(unsigned short *)(va + 4); + else + len = *(unsigned int *)(va + 4); + if (pg_offset + len > kvm->arch.ram_psize) + return H_PARAMETER; + switch (flags) { + case 1: /* register VPA */ + if (len < 640) + return H_PARAMETER; + tvcpu->arch.vpa = va; + init_vpa(vcpu, va); + break; + case 2: /* register DTL */ + if (len < 48) + return H_PARAMETER; + if (!tvcpu->arch.vpa) + return H_RESOURCE; + len -= len % 48; + tvcpu->arch.dtl = va; + tvcpu->arch.dtl_end = va + len; + break; + case 3: /* register SLB shadow buffer */ + if (len < 8) + return H_PARAMETER; + if (!tvcpu->arch.vpa) + return H_RESOURCE; + tvcpu->arch.slb_shadow = va; + len = (len - 16) / 16; + tvcpu->arch.slb_shadow = va; + break; + } + } else { + switch (flags) { + case 5: /* unregister VPA */ + if (tvcpu->arch.slb_shadow || tvcpu->arch.dtl) + return H_RESOURCE; + tvcpu->arch.vpa = NULL; + break; + case 6: /* unregister DTL */ + tvcpu->arch.dtl = NULL; + break; + case 7: /* unregister SLB shadow buffer */ + tvcpu->arch.slb_shadow = NULL; + break; + } + } + return H_SUCCESS; +} + +int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) +{ + unsigned long req = kvmppc_get_gpr(vcpu, 3); + unsigned long target, ret = H_SUCCESS; + struct kvm_vcpu *tvcpu; + + switch (req) { + case H_CEDE: + vcpu->arch.shregs.msr |= MSR_EE; + vcpu->arch.ceded = 1; + smp_mb(); + if (!vcpu->arch.prodded) + kvmppc_vcpu_block(vcpu); + else + vcpu->arch.prodded = 0; + smp_mb(); + vcpu->arch.ceded = 0; + break; + case H_PROD: + target = kvmppc_get_gpr(vcpu, 4); + tvcpu = kvmppc_find_vcpu(vcpu->kvm, target); + if (!tvcpu) { + ret = H_PARAMETER; + break; + } + tvcpu->arch.prodded = 1; + smp_mb(); + if (vcpu->arch.ceded) { + if (waitqueue_active(&vcpu->wq)) { + wake_up_interruptible(&vcpu->wq); + vcpu->stat.halt_wakeup++; + } + } + break; + case H_CONFER: + break; + case H_REGISTER_VPA: + ret = do_h_register_vpa(vcpu, kvmppc_get_gpr(vcpu, 4), + kvmppc_get_gpr(vcpu, 5), + kvmppc_get_gpr(vcpu, 6)); + break; + default: + return RESUME_HOST; + } + kvmppc_set_gpr(vcpu, 3, ret); + vcpu->arch.hcall_needed = 0; + return RESUME_GUEST; +} + +static int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, + struct task_struct *tsk) +{ + int r = RESUME_HOST; + + vcpu->stat.sum_exits++; + + run->exit_reason = KVM_EXIT_UNKNOWN; + run->ready_for_interrupt_injection = 1; + switch (vcpu->arch.trap) { + /* We're good on these - the host merely wanted to get our attention */ + case BOOK3S_INTERRUPT_HV_DECREMENTER: + vcpu->stat.dec_exits++; + r = RESUME_GUEST; + break; + case BOOK3S_INTERRUPT_EXTERNAL: + vcpu->stat.ext_intr_exits++; + r = RESUME_GUEST; + break; + case BOOK3S_INTERRUPT_PERFMON: + r = RESUME_GUEST; + break; + case BOOK3S_INTERRUPT_PROGRAM: + { + ulong flags; + /* + * Normally program interrupts are delivered directly + * to the guest by the hardware, but we can get here + * as a result of a hypervisor emulation interrupt + * (e40) getting turned into a 700 by BML RTAS. + */ + flags = vcpu->arch.shregs.msr & 0x1f0000ull; + kvmppc_core_queue_program(vcpu, flags); + r = RESUME_GUEST; + break; + } + case BOOK3S_INTERRUPT_SYSCALL: + { + /* hcall - punt to userspace */ + int i; + + if (vcpu->arch.shregs.msr & MSR_PR) { + /* sc 1 from userspace - reflect to guest syscall */ + kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_SYSCALL); + r = RESUME_GUEST; + break; + } + run->papr_hcall.nr = kvmppc_get_gpr(vcpu, 3); + for (i = 0; i < 9; ++i) + run->papr_hcall.args[i] = kvmppc_get_gpr(vcpu, 4 + i); + run->exit_reason = KVM_EXIT_PAPR_HCALL; + vcpu->arch.hcall_needed = 1; + r = RESUME_HOST; + break; + } + /* + * We get these next two if the guest does a bad real-mode access, + * as we have enabled VRMA (virtualized real mode area) mode in the + * LPCR. We just generate an appropriate DSI/ISI to the guest. + */ + case BOOK3S_INTERRUPT_H_DATA_STORAGE: + vcpu->arch.shregs.dsisr = vcpu->arch.fault_dsisr; + vcpu->arch.shregs.dar = vcpu->arch.fault_dar; + kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_DATA_STORAGE, 0); + r = RESUME_GUEST; + break; + case BOOK3S_INTERRUPT_H_INST_STORAGE: + kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_INST_STORAGE, + 0x08000000); + r = RESUME_GUEST; + break; + /* + * This occurs if the guest executes an illegal instruction. + * We just generate a program interrupt to the guest, since + * we don't emulate any guest instructions at this stage. + */ + case BOOK3S_INTERRUPT_H_EMUL_ASSIST: + kvmppc_core_queue_program(vcpu, 0x80000); + r = RESUME_GUEST; + break; + default: + kvmppc_dump_regs(vcpu); + printk(KERN_EMERG "trap=0x%x | pc=0x%lx | msr=0x%llx\n", + vcpu->arch.trap, kvmppc_get_pc(vcpu), + vcpu->arch.shregs.msr); + r = RESUME_HOST; + BUG(); + break; + } + + + if (!(r & RESUME_HOST)) { + /* To avoid clobbering exit_reason, only check for signals if + * we aren't already exiting to userspace for some other + * reason. */ + if (signal_pending(tsk)) { + vcpu->stat.signal_exits++; + run->exit_reason = KVM_EXIT_INTR; + r = -EINTR; + } else { + kvmppc_core_deliver_interrupts(vcpu); + } + } + + return r; +} + +int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, + struct kvm_sregs *sregs) +{ + int i; + + sregs->pvr = vcpu->arch.pvr; + + memset(sregs, 0, sizeof(struct kvm_sregs)); + for (i = 0; i < vcpu->arch.slb_max; i++) { + sregs->u.s.ppc64.slb[i].slbe = vcpu->arch.slb[i].orige; + sregs->u.s.ppc64.slb[i].slbv = vcpu->arch.slb[i].origv; + } + + return 0; +} + +int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, + struct kvm_sregs *sregs) +{ + int i, j; + + kvmppc_set_pvr(vcpu, sregs->pvr); + + j = 0; + for (i = 0; i < vcpu->arch.slb_nr; i++) { + if (sregs->u.s.ppc64.slb[i].slbe & SLB_ESID_V) { + vcpu->arch.slb[j].orige = sregs->u.s.ppc64.slb[i].slbe; + vcpu->arch.slb[j].origv = sregs->u.s.ppc64.slb[i].slbv; + ++j; + } + } + vcpu->arch.slb_max = j; + + return 0; +} + +int kvmppc_core_check_processor_compat(void) +{ + if (cpu_has_feature(CPU_FTR_HVMODE)) + return 0; + return -EIO; +} + +struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id) +{ + struct kvm_vcpu *vcpu; + int err = -EINVAL; + int core; + struct kvmppc_vcore *vcore; + + core = id / threads_per_core; + if (core >= KVM_MAX_VCORES) + goto out; + + err = -ENOMEM; + vcpu = kzalloc(sizeof(struct kvm_vcpu), GFP_KERNEL); + if (!vcpu) + goto out; + + err = kvm_vcpu_init(vcpu, kvm, id); + if (err) + goto free_vcpu; + + vcpu->arch.shared = &vcpu->arch.shregs; + vcpu->arch.last_cpu = -1; + vcpu->arch.mmcr[0] = MMCR0_FC; + vcpu->arch.ctrl = CTRL_RUNLATCH; + /* default to host PVR, since we can't spoof it */ + vcpu->arch.pvr = mfspr(SPRN_PVR); + kvmppc_set_pvr(vcpu, vcpu->arch.pvr); + + kvmppc_mmu_book3s_hv_init(vcpu); + + /* + * Some vcpus may start out in stopped state. If we initialize + * them to busy-in-host state they will stop other vcpus in the + * vcore from running. Instead we initialize them to blocked + * state, effectively considering them to be stopped until we + * see the first run ioctl for them. + */ + vcpu->arch.state = KVMPPC_VCPU_BLOCKED; + + init_waitqueue_head(&vcpu->arch.cpu_run); + + mutex_lock(&kvm->lock); + vcore = kvm->arch.vcores[core]; + if (!vcore) { + vcore = kzalloc(sizeof(struct kvmppc_vcore), GFP_KERNEL); + if (vcore) { + INIT_LIST_HEAD(&vcore->runnable_threads); + spin_lock_init(&vcore->lock); + } + kvm->arch.vcores[core] = vcore; + } + mutex_unlock(&kvm->lock); + + if (!vcore) + goto free_vcpu; + + spin_lock(&vcore->lock); + ++vcore->num_threads; + ++vcore->n_blocked; + spin_unlock(&vcore->lock); + vcpu->arch.vcore = vcore; + + return vcpu; + +free_vcpu: + kfree(vcpu); +out: + return ERR_PTR(err); +} + +void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu) +{ + kvm_vcpu_uninit(vcpu); + kfree(vcpu); +} + +static void kvmppc_vcpu_blocked(struct kvm_vcpu *vcpu) +{ + struct kvmppc_vcore *vc = vcpu->arch.vcore; + + spin_lock(&vc->lock); + vcpu->arch.state = KVMPPC_VCPU_BLOCKED; + ++vc->n_blocked; + if (vc->n_runnable > 0 && + vc->n_runnable + vc->n_blocked == vc->num_threads) { + vcpu = list_first_entry(&vc->runnable_threads, struct kvm_vcpu, + arch.run_list); + wake_up(&vcpu->arch.cpu_run); + } + spin_unlock(&vc->lock); +} + +static void kvmppc_vcpu_unblocked(struct kvm_vcpu *vcpu) +{ + struct kvmppc_vcore *vc = vcpu->arch.vcore; + + spin_lock(&vc->lock); + vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST; + --vc->n_blocked; + spin_unlock(&vc->lock); +} + +extern int __kvmppc_vcore_entry(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu); +extern void xics_wake_cpu(int cpu); + +static void kvmppc_remove_runnable(struct kvmppc_vcore *vc, + struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu *v; + + if (vcpu->arch.state != KVMPPC_VCPU_RUNNABLE) + return; + vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST; + --vc->n_runnable; + /* decrement the physical thread id of each following vcpu */ + v = vcpu; + list_for_each_entry_continue(v, &vc->runnable_threads, arch.run_list) + --v->arch.ptid; + list_del(&vcpu->arch.run_list); +} + +static void kvmppc_start_thread(struct kvm_vcpu *vcpu) +{ + int cpu; + struct paca_struct *tpaca; + struct kvmppc_vcore *vc = vcpu->arch.vcore; + + cpu = vc->pcpu + vcpu->arch.ptid; + tpaca = &paca[cpu]; + tpaca->kvm_hstate.kvm_vcpu = vcpu; + tpaca->kvm_hstate.kvm_vcore = vc; + smp_wmb(); +#ifdef CONFIG_PPC_ICP_NATIVE + if (vcpu->arch.ptid) { + tpaca->cpu_start = 0x80; + tpaca->kvm_hstate.in_guest = KVM_GUEST_MODE_GUEST; + wmb(); + xics_wake_cpu(cpu); + ++vc->n_woken; + } +#endif +} + +static void kvmppc_wait_for_nap(struct kvmppc_vcore *vc) +{ + int i; + + HMT_low(); + i = 0; + while (vc->nap_count < vc->n_woken) { + if (++i >= 1000000) { + pr_err("kvmppc_wait_for_nap timeout %d %d\n", + vc->nap_count, vc->n_woken); + break; + } + cpu_relax(); + } + HMT_medium(); +} + +/* + * Check that we are on thread 0 and that any other threads in + * this core are off-line. + */ +static int on_primary_thread(void) +{ + int cpu = smp_processor_id(); + int thr = cpu_thread_in_core(cpu); + + if (thr) + return 0; + while (++thr < threads_per_core) + if (cpu_online(cpu + thr)) + return 0; + return 1; +} + +/* + * Run a set of guest threads on a physical core. + * Called with vc->lock held. + */ +static int kvmppc_run_core(struct kvmppc_vcore *vc) +{ + struct kvm_vcpu *vcpu, *vnext; + long ret; + u64 now; + + /* don't start if any threads have a signal pending */ + list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) + if (signal_pending(vcpu->arch.run_task)) + return 0; + + /* + * Make sure we are running on thread 0, and that + * secondary threads are offline. + * XXX we should also block attempts to bring any + * secondary threads online. + */ + if (threads_per_core > 1 && !on_primary_thread()) { + list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) + vcpu->arch.ret = -EBUSY; + goto out; + } + + vc->n_woken = 0; + vc->nap_count = 0; + vc->entry_exit_count = 0; + vc->vcore_running = 1; + vc->in_guest = 0; + vc->pcpu = smp_processor_id(); + list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) + kvmppc_start_thread(vcpu); + vcpu = list_first_entry(&vc->runnable_threads, struct kvm_vcpu, + arch.run_list); + + spin_unlock(&vc->lock); + + preempt_disable(); + kvm_guest_enter(); + __kvmppc_vcore_entry(NULL, vcpu); + + /* wait for secondary threads to finish writing their state to memory */ + spin_lock(&vc->lock); + if (vc->nap_count < vc->n_woken) + kvmppc_wait_for_nap(vc); + /* prevent other vcpu threads from doing kvmppc_start_thread() now */ + vc->vcore_running = 2; + spin_unlock(&vc->lock); + + /* make sure updates to secondary vcpu structs are visible now */ + smp_mb(); + kvm_guest_exit(); + + preempt_enable(); + kvm_resched(vcpu); + + now = get_tb(); + list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) { + /* cancel pending dec exception if dec is positive */ + if (now < vcpu->arch.dec_expires && + kvmppc_core_pending_dec(vcpu)) + kvmppc_core_dequeue_dec(vcpu); + if (!vcpu->arch.trap) { + if (signal_pending(vcpu->arch.run_task)) { + vcpu->arch.kvm_run->exit_reason = KVM_EXIT_INTR; + vcpu->arch.ret = -EINTR; + } + continue; /* didn't get to run */ + } + ret = kvmppc_handle_exit(vcpu->arch.kvm_run, vcpu, + vcpu->arch.run_task); + vcpu->arch.ret = ret; + vcpu->arch.trap = 0; + } + + spin_lock(&vc->lock); + out: + vc->vcore_running = 0; + list_for_each_entry_safe(vcpu, vnext, &vc->runnable_threads, + arch.run_list) { + if (vcpu->arch.ret != RESUME_GUEST) { + kvmppc_remove_runnable(vc, vcpu); + wake_up(&vcpu->arch.cpu_run); + } + } + + return 1; +} + +static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) +{ + int ptid; + int wait_state; + struct kvmppc_vcore *vc; + DEFINE_WAIT(wait); + + /* No need to go into the guest when all we do is going out */ + if (signal_pending(current)) { + kvm_run->exit_reason = KVM_EXIT_INTR; + return -EINTR; + } + + /* On PPC970, check that we have an RMA region */ + if (!vcpu->kvm->arch.rma && cpu_has_feature(CPU_FTR_ARCH_201)) + return -EPERM; + + kvm_run->exit_reason = 0; + vcpu->arch.ret = RESUME_GUEST; + vcpu->arch.trap = 0; + + flush_fp_to_thread(current); + flush_altivec_to_thread(current); + flush_vsx_to_thread(current); + + /* + * Synchronize with other threads in this virtual core + */ + vc = vcpu->arch.vcore; + spin_lock(&vc->lock); + /* This happens the first time this is called for a vcpu */ + if (vcpu->arch.state == KVMPPC_VCPU_BLOCKED) + --vc->n_blocked; + vcpu->arch.state = KVMPPC_VCPU_RUNNABLE; + ptid = vc->n_runnable; + vcpu->arch.run_task = current; + vcpu->arch.kvm_run = kvm_run; + vcpu->arch.ptid = ptid; + list_add_tail(&vcpu->arch.run_list, &vc->runnable_threads); + ++vc->n_runnable; + + wait_state = TASK_INTERRUPTIBLE; + while (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE) { + if (signal_pending(current)) { + if (!vc->vcore_running) { + kvm_run->exit_reason = KVM_EXIT_INTR; + vcpu->arch.ret = -EINTR; + break; + } + /* have to wait for vcore to stop executing guest */ + wait_state = TASK_UNINTERRUPTIBLE; + smp_send_reschedule(vc->pcpu); + } + + if (!vc->vcore_running && + vc->n_runnable + vc->n_blocked == vc->num_threads) { + /* we can run now */ + if (kvmppc_run_core(vc)) + continue; + } + + if (vc->vcore_running == 1 && VCORE_EXIT_COUNT(vc) == 0) + kvmppc_start_thread(vcpu); + + /* wait for other threads to come in, or wait for vcore */ + prepare_to_wait(&vcpu->arch.cpu_run, &wait, wait_state); + spin_unlock(&vc->lock); + schedule(); + finish_wait(&vcpu->arch.cpu_run, &wait); + spin_lock(&vc->lock); + } + + if (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE) + kvmppc_remove_runnable(vc, vcpu); + spin_unlock(&vc->lock); + + return vcpu->arch.ret; +} + +int kvmppc_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu) +{ + int r; + + do { + r = kvmppc_run_vcpu(run, vcpu); + + if (run->exit_reason == KVM_EXIT_PAPR_HCALL && + !(vcpu->arch.shregs.msr & MSR_PR)) { + r = kvmppc_pseries_do_hcall(vcpu); + kvmppc_core_deliver_interrupts(vcpu); + } + } while (r == RESUME_GUEST); + return r; +} + +static long kvmppc_stt_npages(unsigned long window_size) +{ + return ALIGN((window_size >> SPAPR_TCE_SHIFT) + * sizeof(u64), PAGE_SIZE) / PAGE_SIZE; +} + +static void release_spapr_tce_table(struct kvmppc_spapr_tce_table *stt) +{ + struct kvm *kvm = stt->kvm; + int i; + + mutex_lock(&kvm->lock); + list_del(&stt->list); + for (i = 0; i < kvmppc_stt_npages(stt->window_size); i++) + __free_page(stt->pages[i]); + kfree(stt); + mutex_unlock(&kvm->lock); + + kvm_put_kvm(kvm); +} + +static int kvm_spapr_tce_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +{ + struct kvmppc_spapr_tce_table *stt = vma->vm_file->private_data; + struct page *page; + + if (vmf->pgoff >= kvmppc_stt_npages(stt->window_size)) + return VM_FAULT_SIGBUS; + + page = stt->pages[vmf->pgoff]; + get_page(page); + vmf->page = page; + return 0; +} + +static const struct vm_operations_struct kvm_spapr_tce_vm_ops = { + .fault = kvm_spapr_tce_fault, +}; + +static int kvm_spapr_tce_mmap(struct file *file, struct vm_area_struct *vma) +{ + vma->vm_ops = &kvm_spapr_tce_vm_ops; + return 0; +} + +static int kvm_spapr_tce_release(struct inode *inode, struct file *filp) +{ + struct kvmppc_spapr_tce_table *stt = filp->private_data; + + release_spapr_tce_table(stt); + return 0; +} + +static struct file_operations kvm_spapr_tce_fops = { + .mmap = kvm_spapr_tce_mmap, + .release = kvm_spapr_tce_release, +}; + +long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm, + struct kvm_create_spapr_tce *args) +{ + struct kvmppc_spapr_tce_table *stt = NULL; + long npages; + int ret = -ENOMEM; + int i; + + /* Check this LIOBN hasn't been previously allocated */ + list_for_each_entry(stt, &kvm->arch.spapr_tce_tables, list) { + if (stt->liobn == args->liobn) + return -EBUSY; + } + + npages = kvmppc_stt_npages(args->window_size); + + stt = kzalloc(sizeof(*stt) + npages* sizeof(struct page *), + GFP_KERNEL); + if (!stt) + goto fail; + + stt->liobn = args->liobn; + stt->window_size = args->window_size; + stt->kvm = kvm; + + for (i = 0; i < npages; i++) { + stt->pages[i] = alloc_page(GFP_KERNEL | __GFP_ZERO); + if (!stt->pages[i]) + goto fail; + } + + kvm_get_kvm(kvm); + + mutex_lock(&kvm->lock); + list_add(&stt->list, &kvm->arch.spapr_tce_tables); + + mutex_unlock(&kvm->lock); + + return anon_inode_getfd("kvm-spapr-tce", &kvm_spapr_tce_fops, + stt, O_RDWR); + +fail: + if (stt) { + for (i = 0; i < npages; i++) + if (stt->pages[i]) + __free_page(stt->pages[i]); + + kfree(stt); + } + return ret; +} + +/* Work out RMLS (real mode limit selector) field value for a given RMA size. + Assumes POWER7 or PPC970. */ +static inline int lpcr_rmls(unsigned long rma_size) +{ + switch (rma_size) { + case 32ul << 20: /* 32 MB */ + if (cpu_has_feature(CPU_FTR_ARCH_206)) + return 8; /* only supported on POWER7 */ + return -1; + case 64ul << 20: /* 64 MB */ + return 3; + case 128ul << 20: /* 128 MB */ + return 7; + case 256ul << 20: /* 256 MB */ + return 4; + case 1ul << 30: /* 1 GB */ + return 2; + case 16ul << 30: /* 16 GB */ + return 1; + case 256ul << 30: /* 256 GB */ + return 0; + default: + return -1; + } +} + +static int kvm_rma_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +{ + struct kvmppc_rma_info *ri = vma->vm_file->private_data; + struct page *page; + + if (vmf->pgoff >= ri->npages) + return VM_FAULT_SIGBUS; + + page = pfn_to_page(ri->base_pfn + vmf->pgoff); + get_page(page); + vmf->page = page; + return 0; +} + +static const struct vm_operations_struct kvm_rma_vm_ops = { + .fault = kvm_rma_fault, +}; + +static int kvm_rma_mmap(struct file *file, struct vm_area_struct *vma) +{ + vma->vm_flags |= VM_RESERVED; + vma->vm_ops = &kvm_rma_vm_ops; + return 0; +} + +static int kvm_rma_release(struct inode *inode, struct file *filp) +{ + struct kvmppc_rma_info *ri = filp->private_data; + + kvm_release_rma(ri); + return 0; +} + +static struct file_operations kvm_rma_fops = { + .mmap = kvm_rma_mmap, + .release = kvm_rma_release, +}; + +long kvm_vm_ioctl_allocate_rma(struct kvm *kvm, struct kvm_allocate_rma *ret) +{ + struct kvmppc_rma_info *ri; + long fd; + + ri = kvm_alloc_rma(); + if (!ri) + return -ENOMEM; + + fd = anon_inode_getfd("kvm-rma", &kvm_rma_fops, ri, O_RDWR); + if (fd < 0) + kvm_release_rma(ri); + + ret->rma_size = ri->npages << PAGE_SHIFT; + return fd; +} + +static struct page *hva_to_page(unsigned long addr) +{ + struct page *page[1]; + int npages; + + might_sleep(); + + npages = get_user_pages_fast(addr, 1, 1, page); + + if (unlikely(npages != 1)) + return 0; + + return page[0]; +} + +int kvmppc_core_prepare_memory_region(struct kvm *kvm, + struct kvm_userspace_memory_region *mem) +{ + unsigned long psize, porder; + unsigned long i, npages, totalpages; + unsigned long pg_ix; + struct kvmppc_pginfo *pginfo; + unsigned long hva; + struct kvmppc_rma_info *ri = NULL; + struct page *page; + + /* For now, only allow 16MB pages */ + porder = LARGE_PAGE_ORDER; + psize = 1ul << porder; + if ((mem->memory_size & (psize - 1)) || + (mem->guest_phys_addr & (psize - 1))) { + pr_err("bad memory_size=%llx @ %llx\n", + mem->memory_size, mem->guest_phys_addr); + return -EINVAL; + } + + npages = mem->memory_size >> porder; + totalpages = (mem->guest_phys_addr + mem->memory_size) >> porder; + + /* More memory than we have space to track? */ + if (totalpages > (1ul << (MAX_MEM_ORDER - LARGE_PAGE_ORDER))) + return -EINVAL; + + /* Do we already have an RMA registered? */ + if (mem->guest_phys_addr == 0 && kvm->arch.rma) + return -EINVAL; + + if (totalpages > kvm->arch.ram_npages) + kvm->arch.ram_npages = totalpages; + + /* Is this one of our preallocated RMAs? */ + if (mem->guest_phys_addr == 0) { + struct vm_area_struct *vma; + + down_read(¤t->mm->mmap_sem); + vma = find_vma(current->mm, mem->userspace_addr); + if (vma && vma->vm_file && + vma->vm_file->f_op == &kvm_rma_fops && + mem->userspace_addr == vma->vm_start) + ri = vma->vm_file->private_data; + up_read(¤t->mm->mmap_sem); + if (!ri && cpu_has_feature(CPU_FTR_ARCH_201)) { + pr_err("CPU requires an RMO\n"); + return -EINVAL; + } + } + + if (ri) { + unsigned long rma_size; + unsigned long lpcr; + long rmls; + + rma_size = ri->npages << PAGE_SHIFT; + if (rma_size > mem->memory_size) + rma_size = mem->memory_size; + rmls = lpcr_rmls(rma_size); + if (rmls < 0) { + pr_err("Can't use RMA of 0x%lx bytes\n", rma_size); + return -EINVAL; + } + atomic_inc(&ri->use_count); + kvm->arch.rma = ri; + kvm->arch.n_rma_pages = rma_size >> porder; + + /* Update LPCR and RMOR */ + lpcr = kvm->arch.lpcr; + if (cpu_has_feature(CPU_FTR_ARCH_201)) { + /* PPC970; insert RMLS value (split field) in HID4 */ + lpcr &= ~((1ul << HID4_RMLS0_SH) | + (3ul << HID4_RMLS2_SH)); + lpcr |= ((rmls >> 2) << HID4_RMLS0_SH) | + ((rmls & 3) << HID4_RMLS2_SH); + /* RMOR is also in HID4 */ + lpcr |= ((ri->base_pfn >> (26 - PAGE_SHIFT)) & 0xffff) + << HID4_RMOR_SH; + } else { + /* POWER7 */ + lpcr &= ~(LPCR_VPM0 | LPCR_VRMA_L); + lpcr |= rmls << LPCR_RMLS_SH; + kvm->arch.rmor = kvm->arch.rma->base_pfn << PAGE_SHIFT; + } + kvm->arch.lpcr = lpcr; + pr_info("Using RMO at %lx size %lx (LPCR = %lx)\n", + ri->base_pfn << PAGE_SHIFT, rma_size, lpcr); + } + + pg_ix = mem->guest_phys_addr >> porder; + pginfo = kvm->arch.ram_pginfo + pg_ix; + for (i = 0; i < npages; ++i, ++pg_ix) { + if (ri && pg_ix < kvm->arch.n_rma_pages) { + pginfo[i].pfn = ri->base_pfn + + (pg_ix << (porder - PAGE_SHIFT)); + continue; + } + hva = mem->userspace_addr + (i << porder); + page = hva_to_page(hva); + if (!page) { + pr_err("oops, no pfn for hva %lx\n", hva); + goto err; + } + /* Check it's a 16MB page */ + if (!PageHead(page) || + compound_order(page) != (LARGE_PAGE_ORDER - PAGE_SHIFT)) { + pr_err("page at %lx isn't 16MB (o=%d)\n", + hva, compound_order(page)); + goto err; + } + pginfo[i].pfn = page_to_pfn(page); + } + + return 0; + + err: + return -EINVAL; +} + +void kvmppc_core_commit_memory_region(struct kvm *kvm, + struct kvm_userspace_memory_region *mem) +{ + if (mem->guest_phys_addr == 0 && mem->memory_size != 0 && + !kvm->arch.rma) + kvmppc_map_vrma(kvm, mem); +} + +int kvmppc_core_init_vm(struct kvm *kvm) +{ + long r; + unsigned long npages = 1ul << (MAX_MEM_ORDER - LARGE_PAGE_ORDER); + long err = -ENOMEM; + unsigned long lpcr; + + /* Allocate hashed page table */ + r = kvmppc_alloc_hpt(kvm); + if (r) + return r; + + INIT_LIST_HEAD(&kvm->arch.spapr_tce_tables); + + kvm->arch.ram_pginfo = kzalloc(npages * sizeof(struct kvmppc_pginfo), + GFP_KERNEL); + if (!kvm->arch.ram_pginfo) { + pr_err("kvmppc_core_init_vm: couldn't alloc %lu bytes\n", + npages * sizeof(struct kvmppc_pginfo)); + goto out_free; + } + + kvm->arch.ram_npages = 0; + kvm->arch.ram_psize = 1ul << LARGE_PAGE_ORDER; + kvm->arch.ram_porder = LARGE_PAGE_ORDER; + kvm->arch.rma = NULL; + kvm->arch.n_rma_pages = 0; + + kvm->arch.host_sdr1 = mfspr(SPRN_SDR1); + + if (cpu_has_feature(CPU_FTR_ARCH_201)) { + /* PPC970; HID4 is effectively the LPCR */ + unsigned long lpid = kvm->arch.lpid; + kvm->arch.host_lpid = 0; + kvm->arch.host_lpcr = lpcr = mfspr(SPRN_HID4); + lpcr &= ~((3 << HID4_LPID1_SH) | (0xful << HID4_LPID5_SH)); + lpcr |= ((lpid >> 4) << HID4_LPID1_SH) | + ((lpid & 0xf) << HID4_LPID5_SH); + } else { + /* POWER7; init LPCR for virtual RMA mode */ + kvm->arch.host_lpid = mfspr(SPRN_LPID); + kvm->arch.host_lpcr = lpcr = mfspr(SPRN_LPCR); + lpcr &= LPCR_PECE | LPCR_LPES; + lpcr |= (4UL << LPCR_DPFD_SH) | LPCR_HDICE | + LPCR_VPM0 | LPCR_VRMA_L; + } + kvm->arch.lpcr = lpcr; + + return 0; + + out_free: + kvmppc_free_hpt(kvm); + return err; +} + +void kvmppc_core_destroy_vm(struct kvm *kvm) +{ + struct kvmppc_pginfo *pginfo; + unsigned long i; + + if (kvm->arch.ram_pginfo) { + pginfo = kvm->arch.ram_pginfo; + kvm->arch.ram_pginfo = NULL; + for (i = kvm->arch.n_rma_pages; i < kvm->arch.ram_npages; ++i) + if (pginfo[i].pfn) + put_page(pfn_to_page(pginfo[i].pfn)); + kfree(pginfo); + } + if (kvm->arch.rma) { + kvm_release_rma(kvm->arch.rma); + kvm->arch.rma = NULL; + } + + kvmppc_free_hpt(kvm); + WARN_ON(!list_empty(&kvm->arch.spapr_tce_tables)); +} + +/* These are stubs for now */ +void kvmppc_mmu_pte_pflush(struct kvm_vcpu *vcpu, ulong pa_start, ulong pa_end) +{ +} + +/* We don't need to emulate any privileged instructions or dcbz */ +int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, + unsigned int inst, int *advance) +{ + return EMULATE_FAIL; +} + +int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs) +{ + return EMULATE_FAIL; +} + +int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt) +{ + return EMULATE_FAIL; +} + +static int kvmppc_book3s_hv_init(void) +{ + int r; + + r = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE); + + if (r) + return r; + + r = kvmppc_mmu_hv_init(); + + return r; +} + +static void kvmppc_book3s_hv_exit(void) +{ + kvm_exit(); +} + +module_init(kvmppc_book3s_hv_init); +module_exit(kvmppc_book3s_hv_exit); diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c new file mode 100644 index 00000000000..d43120355ee --- /dev/null +++ b/arch/powerpc/kvm/book3s_hv_builtin.c @@ -0,0 +1,155 @@ +/* + * Copyright 2011 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + */ + +#include <linux/kvm_host.h> +#include <linux/preempt.h> +#include <linux/sched.h> +#include <linux/spinlock.h> +#include <linux/bootmem.h> +#include <linux/init.h> + +#include <asm/cputable.h> +#include <asm/kvm_ppc.h> +#include <asm/kvm_book3s.h> + +/* + * This maintains a list of RMAs (real mode areas) for KVM guests to use. + * Each RMA has to be physically contiguous and of a size that the + * hardware supports. PPC970 and POWER7 support 64MB, 128MB and 256MB, + * and other larger sizes. Since we are unlikely to be allocate that + * much physically contiguous memory after the system is up and running, + * we preallocate a set of RMAs in early boot for KVM to use. + */ +static unsigned long kvm_rma_size = 64 << 20; /* 64MB */ +static unsigned long kvm_rma_count; + +static int __init early_parse_rma_size(char *p) +{ + if (!p) + return 1; + + kvm_rma_size = memparse(p, &p); + + return 0; +} +early_param("kvm_rma_size", early_parse_rma_size); + +static int __init early_parse_rma_count(char *p) +{ + if (!p) + return 1; + + kvm_rma_count = simple_strtoul(p, NULL, 0); + + return 0; +} +early_param("kvm_rma_count", early_parse_rma_count); + +static struct kvmppc_rma_info *rma_info; +static LIST_HEAD(free_rmas); +static DEFINE_SPINLOCK(rma_lock); + +/* Work out RMLS (real mode limit selector) field value for a given RMA size. + Assumes POWER7 or PPC970. */ +static inline int lpcr_rmls(unsigned long rma_size) +{ + switch (rma_size) { + case 32ul << 20: /* 32 MB */ + if (cpu_has_feature(CPU_FTR_ARCH_206)) + return 8; /* only supported on POWER7 */ + return -1; + case 64ul << 20: /* 64 MB */ + return 3; + case 128ul << 20: /* 128 MB */ + return 7; + case 256ul << 20: /* 256 MB */ + return 4; + case 1ul << 30: /* 1 GB */ + return 2; + case 16ul << 30: /* 16 GB */ + return 1; + case 256ul << 30: /* 256 GB */ + return 0; + default: + return -1; + } +} + +/* + * Called at boot time while the bootmem allocator is active, + * to allocate contiguous physical memory for the real memory + * areas for guests. + */ +void kvm_rma_init(void) +{ + unsigned long i; + unsigned long j, npages; + void *rma; + struct page *pg; + + /* Only do this on PPC970 in HV mode */ + if (!cpu_has_feature(CPU_FTR_HVMODE) || + !cpu_has_feature(CPU_FTR_ARCH_201)) + return; + + if (!kvm_rma_size || !kvm_rma_count) + return; + + /* Check that the requested size is one supported in hardware */ + if (lpcr_rmls(kvm_rma_size) < 0) { + pr_err("RMA size of 0x%lx not supported\n", kvm_rma_size); + return; + } + + npages = kvm_rma_size >> PAGE_SHIFT; + rma_info = alloc_bootmem(kvm_rma_count * sizeof(struct kvmppc_rma_info)); + for (i = 0; i < kvm_rma_count; ++i) { + rma = alloc_bootmem_align(kvm_rma_size, kvm_rma_size); + pr_info("Allocated KVM RMA at %p (%ld MB)\n", rma, + kvm_rma_size >> 20); + rma_info[i].base_virt = rma; + rma_info[i].base_pfn = __pa(rma) >> PAGE_SHIFT; + rma_info[i].npages = npages; + list_add_tail(&rma_info[i].list, &free_rmas); + atomic_set(&rma_info[i].use_count, 0); + + pg = pfn_to_page(rma_info[i].base_pfn); + for (j = 0; j < npages; ++j) { + atomic_inc(&pg->_count); + ++pg; + } + } +} + +struct kvmppc_rma_info *kvm_alloc_rma(void) +{ + struct kvmppc_rma_info *ri; + + ri = NULL; + spin_lock(&rma_lock); + if (!list_empty(&free_rmas)) { + ri = list_first_entry(&free_rmas, struct kvmppc_rma_info, list); + list_del(&ri->list); + atomic_inc(&ri->use_count); + } + spin_unlock(&rma_lock); + return ri; +} +EXPORT_SYMBOL_GPL(kvm_alloc_rma); + +void kvm_release_rma(struct kvmppc_rma_info *ri) +{ + if (atomic_dec_and_test(&ri->use_count)) { + spin_lock(&rma_lock); + list_add_tail(&ri->list, &free_rmas); + spin_unlock(&rma_lock); + + } +} +EXPORT_SYMBOL_GPL(kvm_release_rma); + diff --git a/arch/powerpc/kvm/book3s_hv_interrupts.S b/arch/powerpc/kvm/book3s_hv_interrupts.S new file mode 100644 index 00000000000..3f7b674dd4b --- /dev/null +++ b/arch/powerpc/kvm/book3s_hv_interrupts.S @@ -0,0 +1,166 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + * + * Copyright 2011 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com> + * + * Derived from book3s_interrupts.S, which is: + * Copyright SUSE Linux Products GmbH 2009 + * + * Authors: Alexander Graf <agraf@suse.de> + */ + +#include <asm/ppc_asm.h> +#include <asm/kvm_asm.h> +#include <asm/reg.h> +#include <asm/page.h> +#include <asm/asm-offsets.h> +#include <asm/exception-64s.h> +#include <asm/ppc-opcode.h> + +/***************************************************************************** + * * + * Guest entry / exit code that is in kernel module memory (vmalloc) * + * * + ****************************************************************************/ + +/* Registers: + * r4: vcpu pointer + */ +_GLOBAL(__kvmppc_vcore_entry) + + /* Write correct stack frame */ + mflr r0 + std r0,PPC_LR_STKOFF(r1) + + /* Save host state to the stack */ + stdu r1, -SWITCH_FRAME_SIZE(r1) + + /* Save non-volatile registers (r14 - r31) */ + SAVE_NVGPRS(r1) + + /* Save host DSCR */ +BEGIN_FTR_SECTION + mfspr r3, SPRN_DSCR + std r3, HSTATE_DSCR(r13) +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) + + /* Save host DABR */ + mfspr r3, SPRN_DABR + std r3, HSTATE_DABR(r13) + + /* Hard-disable interrupts */ + mfmsr r10 + std r10, HSTATE_HOST_MSR(r13) + rldicl r10,r10,48,1 + rotldi r10,r10,16 + mtmsrd r10,1 + + /* Save host PMU registers and load guest PMU registers */ + /* R4 is live here (vcpu pointer) but not r3 or r5 */ + li r3, 1 + sldi r3, r3, 31 /* MMCR0_FC (freeze counters) bit */ + mfspr r7, SPRN_MMCR0 /* save MMCR0 */ + mtspr SPRN_MMCR0, r3 /* freeze all counters, disable interrupts */ + isync + ld r3, PACALPPACAPTR(r13) /* is the host using the PMU? */ + lbz r5, LPPACA_PMCINUSE(r3) + cmpwi r5, 0 + beq 31f /* skip if not */ + mfspr r5, SPRN_MMCR1 + mfspr r6, SPRN_MMCRA + std r7, HSTATE_MMCR(r13) + std r5, HSTATE_MMCR + 8(r13) + std r6, HSTATE_MMCR + 16(r13) + mfspr r3, SPRN_PMC1 + mfspr r5, SPRN_PMC2 + mfspr r6, SPRN_PMC3 + mfspr r7, SPRN_PMC4 + mfspr r8, SPRN_PMC5 + mfspr r9, SPRN_PMC6 +BEGIN_FTR_SECTION + mfspr r10, SPRN_PMC7 + mfspr r11, SPRN_PMC8 +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) + stw r3, HSTATE_PMC(r13) + stw r5, HSTATE_PMC + 4(r13) + stw r6, HSTATE_PMC + 8(r13) + stw r7, HSTATE_PMC + 12(r13) + stw r8, HSTATE_PMC + 16(r13) + stw r9, HSTATE_PMC + 20(r13) +BEGIN_FTR_SECTION + stw r10, HSTATE_PMC + 24(r13) + stw r11, HSTATE_PMC + 28(r13) +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) +31: + + /* + * Put whatever is in the decrementer into the + * hypervisor decrementer. + */ + mfspr r8,SPRN_DEC + mftb r7 + mtspr SPRN_HDEC,r8 + extsw r8,r8 + add r8,r8,r7 + std r8,HSTATE_DECEXP(r13) + + /* + * On PPC970, if the guest vcpu has an external interrupt pending, + * send ourselves an IPI so as to interrupt the guest once it + * enables interrupts. (It must have interrupts disabled, + * otherwise we would already have delivered the interrupt.) + */ +BEGIN_FTR_SECTION + ld r0, VCPU_PENDING_EXC(r4) + li r7, (1 << BOOK3S_IRQPRIO_EXTERNAL) + oris r7, r7, (1 << BOOK3S_IRQPRIO_EXTERNAL_LEVEL)@h + and. r0, r0, r7 + beq 32f + mr r31, r4 + lhz r3, PACAPACAINDEX(r13) + bl smp_send_reschedule + nop + mr r4, r31 +32: +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) + + /* Jump to partition switch code */ + bl .kvmppc_hv_entry_trampoline + nop + +/* + * We return here in virtual mode after the guest exits + * with something that we can't handle in real mode. + * Interrupts are enabled again at this point. + */ + +.global kvmppc_handler_highmem +kvmppc_handler_highmem: + + /* + * Register usage at this point: + * + * R1 = host R1 + * R2 = host R2 + * R12 = exit handler id + * R13 = PACA + */ + + /* Restore non-volatile host registers (r14 - r31) */ + REST_NVGPRS(r1) + + addi r1, r1, SWITCH_FRAME_SIZE + ld r0, PPC_LR_STKOFF(r1) + mtlr r0 + blr diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c new file mode 100644 index 00000000000..fcfe6b05555 --- /dev/null +++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c @@ -0,0 +1,370 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * Copyright 2010-2011 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com> + */ + +#include <linux/types.h> +#include <linux/string.h> +#include <linux/kvm.h> +#include <linux/kvm_host.h> +#include <linux/hugetlb.h> + +#include <asm/tlbflush.h> +#include <asm/kvm_ppc.h> +#include <asm/kvm_book3s.h> +#include <asm/mmu-hash64.h> +#include <asm/hvcall.h> +#include <asm/synch.h> +#include <asm/ppc-opcode.h> + +/* For now use fixed-size 16MB page table */ +#define HPT_ORDER 24 +#define HPT_NPTEG (1ul << (HPT_ORDER - 7)) /* 128B per pteg */ +#define HPT_HASH_MASK (HPT_NPTEG - 1) + +#define HPTE_V_HVLOCK 0x40UL + +static inline long lock_hpte(unsigned long *hpte, unsigned long bits) +{ + unsigned long tmp, old; + + asm volatile(" ldarx %0,0,%2\n" + " and. %1,%0,%3\n" + " bne 2f\n" + " ori %0,%0,%4\n" + " stdcx. %0,0,%2\n" + " beq+ 2f\n" + " li %1,%3\n" + "2: isync" + : "=&r" (tmp), "=&r" (old) + : "r" (hpte), "r" (bits), "i" (HPTE_V_HVLOCK) + : "cc", "memory"); + return old == 0; +} + +long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags, + long pte_index, unsigned long pteh, unsigned long ptel) +{ + unsigned long porder; + struct kvm *kvm = vcpu->kvm; + unsigned long i, lpn, pa; + unsigned long *hpte; + + /* only handle 4k, 64k and 16M pages for now */ + porder = 12; + if (pteh & HPTE_V_LARGE) { + if (cpu_has_feature(CPU_FTR_ARCH_206) && + (ptel & 0xf000) == 0x1000) { + /* 64k page */ + porder = 16; + } else if ((ptel & 0xff000) == 0) { + /* 16M page */ + porder = 24; + /* lowest AVA bit must be 0 for 16M pages */ + if (pteh & 0x80) + return H_PARAMETER; + } else + return H_PARAMETER; + } + lpn = (ptel & HPTE_R_RPN) >> kvm->arch.ram_porder; + if (lpn >= kvm->arch.ram_npages || porder > kvm->arch.ram_porder) + return H_PARAMETER; + pa = kvm->arch.ram_pginfo[lpn].pfn << PAGE_SHIFT; + if (!pa) + return H_PARAMETER; + /* Check WIMG */ + if ((ptel & HPTE_R_WIMG) != HPTE_R_M && + (ptel & HPTE_R_WIMG) != (HPTE_R_W | HPTE_R_I | HPTE_R_M)) + return H_PARAMETER; + pteh &= ~0x60UL; + ptel &= ~(HPTE_R_PP0 - kvm->arch.ram_psize); + ptel |= pa; + if (pte_index >= (HPT_NPTEG << 3)) + return H_PARAMETER; + if (likely((flags & H_EXACT) == 0)) { + pte_index &= ~7UL; + hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4)); + for (i = 0; ; ++i) { + if (i == 8) + return H_PTEG_FULL; + if ((*hpte & HPTE_V_VALID) == 0 && + lock_hpte(hpte, HPTE_V_HVLOCK | HPTE_V_VALID)) + break; + hpte += 2; + } + } else { + i = 0; + hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4)); + if (!lock_hpte(hpte, HPTE_V_HVLOCK | HPTE_V_VALID)) + return H_PTEG_FULL; + } + hpte[1] = ptel; + eieio(); + hpte[0] = pteh; + asm volatile("ptesync" : : : "memory"); + atomic_inc(&kvm->arch.ram_pginfo[lpn].refcnt); + vcpu->arch.gpr[4] = pte_index + i; + return H_SUCCESS; +} + +static unsigned long compute_tlbie_rb(unsigned long v, unsigned long r, + unsigned long pte_index) +{ + unsigned long rb, va_low; + + rb = (v & ~0x7fUL) << 16; /* AVA field */ + va_low = pte_index >> 3; + if (v & HPTE_V_SECONDARY) + va_low = ~va_low; + /* xor vsid from AVA */ + if (!(v & HPTE_V_1TB_SEG)) + va_low ^= v >> 12; + else + va_low ^= v >> 24; + va_low &= 0x7ff; + if (v & HPTE_V_LARGE) { + rb |= 1; /* L field */ + if (cpu_has_feature(CPU_FTR_ARCH_206) && + (r & 0xff000)) { + /* non-16MB large page, must be 64k */ + /* (masks depend on page size) */ + rb |= 0x1000; /* page encoding in LP field */ + rb |= (va_low & 0x7f) << 16; /* 7b of VA in AVA/LP field */ + rb |= (va_low & 0xfe); /* AVAL field (P7 doesn't seem to care) */ + } + } else { + /* 4kB page */ + rb |= (va_low & 0x7ff) << 12; /* remaining 11b of VA */ + } + rb |= (v >> 54) & 0x300; /* B field */ + return rb; +} + +#define LOCK_TOKEN (*(u32 *)(&get_paca()->lock_token)) + +static inline int try_lock_tlbie(unsigned int *lock) +{ + unsigned int tmp, old; + unsigned int token = LOCK_TOKEN; + + asm volatile("1:lwarx %1,0,%2\n" + " cmpwi cr0,%1,0\n" + " bne 2f\n" + " stwcx. %3,0,%2\n" + " bne- 1b\n" + " isync\n" + "2:" + : "=&r" (tmp), "=&r" (old) + : "r" (lock), "r" (token) + : "cc", "memory"); + return old == 0; +} + +long kvmppc_h_remove(struct kvm_vcpu *vcpu, unsigned long flags, + unsigned long pte_index, unsigned long avpn, + unsigned long va) +{ + struct kvm *kvm = vcpu->kvm; + unsigned long *hpte; + unsigned long v, r, rb; + + if (pte_index >= (HPT_NPTEG << 3)) + return H_PARAMETER; + hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4)); + while (!lock_hpte(hpte, HPTE_V_HVLOCK)) + cpu_relax(); + if ((hpte[0] & HPTE_V_VALID) == 0 || + ((flags & H_AVPN) && (hpte[0] & ~0x7fUL) != avpn) || + ((flags & H_ANDCOND) && (hpte[0] & avpn) != 0)) { + hpte[0] &= ~HPTE_V_HVLOCK; + return H_NOT_FOUND; + } + if (atomic_read(&kvm->online_vcpus) == 1) + flags |= H_LOCAL; + vcpu->arch.gpr[4] = v = hpte[0] & ~HPTE_V_HVLOCK; + vcpu->arch.gpr[5] = r = hpte[1]; + rb = compute_tlbie_rb(v, r, pte_index); + hpte[0] = 0; + if (!(flags & H_LOCAL)) { + while(!try_lock_tlbie(&kvm->arch.tlbie_lock)) + cpu_relax(); + asm volatile("ptesync" : : : "memory"); + asm volatile(PPC_TLBIE(%1,%0)"; eieio; tlbsync" + : : "r" (rb), "r" (kvm->arch.lpid)); + asm volatile("ptesync" : : : "memory"); + kvm->arch.tlbie_lock = 0; + } else { + asm volatile("ptesync" : : : "memory"); + asm volatile("tlbiel %0" : : "r" (rb)); + asm volatile("ptesync" : : : "memory"); + } + return H_SUCCESS; +} + +long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + unsigned long *args = &vcpu->arch.gpr[4]; + unsigned long *hp, tlbrb[4]; + long int i, found; + long int n_inval = 0; + unsigned long flags, req, pte_index; + long int local = 0; + long int ret = H_SUCCESS; + + if (atomic_read(&kvm->online_vcpus) == 1) + local = 1; + for (i = 0; i < 4; ++i) { + pte_index = args[i * 2]; + flags = pte_index >> 56; + pte_index &= ((1ul << 56) - 1); + req = flags >> 6; + flags &= 3; + if (req == 3) + break; + if (req != 1 || flags == 3 || + pte_index >= (HPT_NPTEG << 3)) { + /* parameter error */ + args[i * 2] = ((0xa0 | flags) << 56) + pte_index; + ret = H_PARAMETER; + break; + } + hp = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4)); + while (!lock_hpte(hp, HPTE_V_HVLOCK)) + cpu_relax(); + found = 0; + if (hp[0] & HPTE_V_VALID) { + switch (flags & 3) { + case 0: /* absolute */ + found = 1; + break; + case 1: /* andcond */ + if (!(hp[0] & args[i * 2 + 1])) + found = 1; + break; + case 2: /* AVPN */ + if ((hp[0] & ~0x7fUL) == args[i * 2 + 1]) + found = 1; + break; + } + } + if (!found) { + hp[0] &= ~HPTE_V_HVLOCK; + args[i * 2] = ((0x90 | flags) << 56) + pte_index; + continue; + } + /* insert R and C bits from PTE */ + flags |= (hp[1] >> 5) & 0x0c; + args[i * 2] = ((0x80 | flags) << 56) + pte_index; + tlbrb[n_inval++] = compute_tlbie_rb(hp[0], hp[1], pte_index); + hp[0] = 0; + } + if (n_inval == 0) + return ret; + + if (!local) { + while(!try_lock_tlbie(&kvm->arch.tlbie_lock)) + cpu_relax(); + asm volatile("ptesync" : : : "memory"); + for (i = 0; i < n_inval; ++i) + asm volatile(PPC_TLBIE(%1,%0) + : : "r" (tlbrb[i]), "r" (kvm->arch.lpid)); + asm volatile("eieio; tlbsync; ptesync" : : : "memory"); + kvm->arch.tlbie_lock = 0; + } else { + asm volatile("ptesync" : : : "memory"); + for (i = 0; i < n_inval; ++i) + asm volatile("tlbiel %0" : : "r" (tlbrb[i])); + asm volatile("ptesync" : : : "memory"); + } + return ret; +} + +long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags, + unsigned long pte_index, unsigned long avpn, + unsigned long va) +{ + struct kvm *kvm = vcpu->kvm; + unsigned long *hpte; + unsigned long v, r, rb; + + if (pte_index >= (HPT_NPTEG << 3)) + return H_PARAMETER; + hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4)); + while (!lock_hpte(hpte, HPTE_V_HVLOCK)) + cpu_relax(); + if ((hpte[0] & HPTE_V_VALID) == 0 || + ((flags & H_AVPN) && (hpte[0] & ~0x7fUL) != avpn)) { + hpte[0] &= ~HPTE_V_HVLOCK; + return H_NOT_FOUND; + } + if (atomic_read(&kvm->online_vcpus) == 1) + flags |= H_LOCAL; + v = hpte[0]; + r = hpte[1] & ~(HPTE_R_PP0 | HPTE_R_PP | HPTE_R_N | + HPTE_R_KEY_HI | HPTE_R_KEY_LO); + r |= (flags << 55) & HPTE_R_PP0; + r |= (flags << 48) & HPTE_R_KEY_HI; + r |= flags & (HPTE_R_PP | HPTE_R_N | HPTE_R_KEY_LO); + rb = compute_tlbie_rb(v, r, pte_index); + hpte[0] = v & ~HPTE_V_VALID; + if (!(flags & H_LOCAL)) { + while(!try_lock_tlbie(&kvm->arch.tlbie_lock)) + cpu_relax(); + asm volatile("ptesync" : : : "memory"); + asm volatile(PPC_TLBIE(%1,%0)"; eieio; tlbsync" + : : "r" (rb), "r" (kvm->arch.lpid)); + asm volatile("ptesync" : : : "memory"); + kvm->arch.tlbie_lock = 0; + } else { + asm volatile("ptesync" : : : "memory"); + asm volatile("tlbiel %0" : : "r" (rb)); + asm volatile("ptesync" : : : "memory"); + } + hpte[1] = r; + eieio(); + hpte[0] = v & ~HPTE_V_HVLOCK; + asm volatile("ptesync" : : : "memory"); + return H_SUCCESS; +} + +static unsigned long reverse_xlate(struct kvm *kvm, unsigned long realaddr) +{ + long int i; + unsigned long offset, rpn; + + offset = realaddr & (kvm->arch.ram_psize - 1); + rpn = (realaddr - offset) >> PAGE_SHIFT; + for (i = 0; i < kvm->arch.ram_npages; ++i) + if (rpn == kvm->arch.ram_pginfo[i].pfn) + return (i << PAGE_SHIFT) + offset; + return HPTE_R_RPN; /* all 1s in the RPN field */ +} + +long kvmppc_h_read(struct kvm_vcpu *vcpu, unsigned long flags, + unsigned long pte_index) +{ + struct kvm *kvm = vcpu->kvm; + unsigned long *hpte, r; + int i, n = 1; + + if (pte_index >= (HPT_NPTEG << 3)) + return H_PARAMETER; + if (flags & H_READ_4) { + pte_index &= ~3; + n = 4; + } + for (i = 0; i < n; ++i, ++pte_index) { + hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4)); + r = hpte[1]; + if ((flags & H_R_XLATE) && (hpte[0] & HPTE_V_VALID)) + r = reverse_xlate(kvm, r & HPTE_R_RPN) | + (r & ~HPTE_R_RPN); + vcpu->arch.gpr[4 + i * 2] = hpte[0]; + vcpu->arch.gpr[5 + i * 2] = r; + } + return H_SUCCESS; +} diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S new file mode 100644 index 00000000000..6dd33581a22 --- /dev/null +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -0,0 +1,1345 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * Copyright 2011 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com> + * + * Derived from book3s_rmhandlers.S and other files, which are: + * + * Copyright SUSE Linux Products GmbH 2009 + * + * Authors: Alexander Graf <agraf@suse.de> + */ + +#include <asm/ppc_asm.h> +#include <asm/kvm_asm.h> +#include <asm/reg.h> +#include <asm/page.h> +#include <asm/asm-offsets.h> +#include <asm/exception-64s.h> + +/***************************************************************************** + * * + * Real Mode handlers that need to be in the linear mapping * + * * + ****************************************************************************/ + + .globl kvmppc_skip_interrupt +kvmppc_skip_interrupt: + mfspr r13,SPRN_SRR0 + addi r13,r13,4 + mtspr SPRN_SRR0,r13 + GET_SCRATCH0(r13) + rfid + b . + + .globl kvmppc_skip_Hinterrupt +kvmppc_skip_Hinterrupt: + mfspr r13,SPRN_HSRR0 + addi r13,r13,4 + mtspr SPRN_HSRR0,r13 + GET_SCRATCH0(r13) + hrfid + b . + +/* + * Call kvmppc_handler_trampoline_enter in real mode. + * Must be called with interrupts hard-disabled. + * + * Input Registers: + * + * LR = return address to continue at after eventually re-enabling MMU + */ +_GLOBAL(kvmppc_hv_entry_trampoline) + mfmsr r10 + LOAD_REG_ADDR(r5, kvmppc_hv_entry) + li r0,MSR_RI + andc r0,r10,r0 + li r6,MSR_IR | MSR_DR + andc r6,r10,r6 + mtmsrd r0,1 /* clear RI in MSR */ + mtsrr0 r5 + mtsrr1 r6 + RFI + +#define ULONG_SIZE 8 +#define VCPU_GPR(n) (VCPU_GPRS + (n * ULONG_SIZE)) + +/****************************************************************************** + * * + * Entry code * + * * + *****************************************************************************/ + +#define XICS_XIRR 4 +#define XICS_QIRR 0xc + +/* + * We come in here when wakened from nap mode on a secondary hw thread. + * Relocation is off and most register values are lost. + * r13 points to the PACA. + */ + .globl kvm_start_guest +kvm_start_guest: + ld r1,PACAEMERGSP(r13) + subi r1,r1,STACK_FRAME_OVERHEAD + + /* get vcpu pointer */ + ld r4, HSTATE_KVM_VCPU(r13) + + /* We got here with an IPI; clear it */ + ld r5, HSTATE_XICS_PHYS(r13) + li r0, 0xff + li r6, XICS_QIRR + li r7, XICS_XIRR + lwzcix r8, r5, r7 /* ack the interrupt */ + sync + stbcix r0, r5, r6 /* clear it */ + stwcix r8, r5, r7 /* EOI it */ + +.global kvmppc_hv_entry +kvmppc_hv_entry: + + /* Required state: + * + * R4 = vcpu pointer + * MSR = ~IR|DR + * R13 = PACA + * R1 = host R1 + * all other volatile GPRS = free + */ + mflr r0 + std r0, HSTATE_VMHANDLER(r13) + + 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) + + /* Load guest PMU registers */ + /* R4 is live here (vcpu pointer) */ + li r3, 1 + sldi r3, r3, 31 /* MMCR0_FC (freeze counters) bit */ + mtspr SPRN_MMCR0, r3 /* freeze all counters, disable ints */ + isync + lwz r3, VCPU_PMC(r4) /* always load up guest PMU registers */ + lwz r5, VCPU_PMC + 4(r4) /* to prevent information leak */ + lwz r6, VCPU_PMC + 8(r4) + lwz r7, VCPU_PMC + 12(r4) + lwz r8, VCPU_PMC + 16(r4) + lwz r9, VCPU_PMC + 20(r4) +BEGIN_FTR_SECTION + lwz r10, VCPU_PMC + 24(r4) + lwz r11, VCPU_PMC + 28(r4) +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) + mtspr SPRN_PMC1, r3 + mtspr SPRN_PMC2, r5 + mtspr SPRN_PMC3, r6 + mtspr SPRN_PMC4, r7 + mtspr SPRN_PMC5, r8 + mtspr SPRN_PMC6, r9 +BEGIN_FTR_SECTION + mtspr SPRN_PMC7, r10 + mtspr SPRN_PMC8, r11 +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) + ld r3, VCPU_MMCR(r4) + ld r5, VCPU_MMCR + 8(r4) + ld r6, VCPU_MMCR + 16(r4) + mtspr SPRN_MMCR1, r5 + mtspr SPRN_MMCRA, r6 + mtspr SPRN_MMCR0, r3 + isync + + /* Load up FP, VMX and VSX registers */ + bl kvmppc_load_fp + +BEGIN_FTR_SECTION + /* Switch DSCR to guest value */ + ld r5, VCPU_DSCR(r4) + mtspr SPRN_DSCR, r5 +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) + + /* + * Set the decrementer to the guest decrementer. + */ + ld r8,VCPU_DEC_EXPIRES(r4) + mftb r7 + subf r3,r7,r8 + mtspr SPRN_DEC,r3 + stw r3,VCPU_DEC(r4) + + ld r5, VCPU_SPRG0(r4) + ld r6, VCPU_SPRG1(r4) + ld r7, VCPU_SPRG2(r4) + ld r8, VCPU_SPRG3(r4) + mtspr SPRN_SPRG0, r5 + mtspr SPRN_SPRG1, r6 + mtspr SPRN_SPRG2, r7 + mtspr SPRN_SPRG3, r8 + + /* Save R1 in the PACA */ + std r1, HSTATE_HOST_R1(r13) + + /* Increment yield count if they have a VPA */ + ld r3, VCPU_VPA(r4) + cmpdi r3, 0 + beq 25f + lwz r5, LPPACA_YIELDCOUNT(r3) + addi r5, r5, 1 + stw r5, LPPACA_YIELDCOUNT(r3) +25: + /* Load up DAR and DSISR */ + ld r5, VCPU_DAR(r4) + lwz r6, VCPU_DSISR(r4) + mtspr SPRN_DAR, r5 + mtspr SPRN_DSISR, r6 + + /* Set partition DABR */ + li r5,3 + ld r6,VCPU_DABR(r4) + mtspr SPRN_DABRX,r5 + mtspr SPRN_DABR,r6 + +BEGIN_FTR_SECTION + /* Restore AMR and UAMOR, set AMOR to all 1s */ + ld r5,VCPU_AMR(r4) + ld r6,VCPU_UAMOR(r4) + li r7,-1 + mtspr SPRN_AMR,r5 + mtspr SPRN_UAMOR,r6 + mtspr SPRN_AMOR,r7 +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) + + /* Clear out SLB */ + li r6,0 + slbmte r6,r6 + slbia + ptesync + +BEGIN_FTR_SECTION + b 30f +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) + /* + * POWER7 host -> guest partition switch code. + * We don't have to lock against concurrent tlbies, + * but we do have to coordinate across hardware threads. + */ + /* Increment entry count iff exit count is zero. */ + ld r5,HSTATE_KVM_VCORE(r13) + addi r9,r5,VCORE_ENTRY_EXIT +21: lwarx r3,0,r9 + cmpwi r3,0x100 /* any threads starting to exit? */ + bge secondary_too_late /* if so we're too late to the party */ + addi r3,r3,1 + stwcx. r3,0,r9 + bne 21b + + /* Primary thread switches to guest partition. */ + ld r9,VCPU_KVM(r4) /* pointer to struct kvm */ + lwz r6,VCPU_PTID(r4) + cmpwi r6,0 + bne 20f + ld r6,KVM_SDR1(r9) + lwz r7,KVM_LPID(r9) + li r0,LPID_RSVD /* switch to reserved LPID */ + mtspr SPRN_LPID,r0 + ptesync + mtspr SPRN_SDR1,r6 /* switch to partition page table */ + mtspr SPRN_LPID,r7 + isync + li r0,1 + stb r0,VCORE_IN_GUEST(r5) /* signal secondaries to continue */ + b 10f + + /* Secondary threads wait for primary to have done partition switch */ +20: lbz r0,VCORE_IN_GUEST(r5) + cmpwi r0,0 + beq 20b + + /* Set LPCR. Set the MER bit if there is a pending external irq. */ +10: ld r8,KVM_LPCR(r9) + ld r0,VCPU_PENDING_EXC(r4) + li r7,(1 << BOOK3S_IRQPRIO_EXTERNAL) + oris r7,r7,(1 << BOOK3S_IRQPRIO_EXTERNAL_LEVEL)@h + and. r0,r0,r7 + beq 11f + ori r8,r8,LPCR_MER +11: mtspr SPRN_LPCR,r8 + ld r8,KVM_RMOR(r9) + mtspr SPRN_RMOR,r8 + isync + + /* Check if HDEC expires soon */ + mfspr r3,SPRN_HDEC + cmpwi r3,10 + li r12,BOOK3S_INTERRUPT_HV_DECREMENTER + mr r9,r4 + blt hdec_soon + + /* + * Invalidate the TLB if we could possibly have stale TLB + * entries for this partition on this core due to the use + * of tlbiel. + * XXX maybe only need this on primary thread? + */ + ld r9,VCPU_KVM(r4) /* pointer to struct kvm */ + lwz r5,VCPU_VCPUID(r4) + lhz r6,PACAPACAINDEX(r13) + rldimi r6,r5,0,62 /* XXX map as if threads 1:1 p:v */ + lhz r8,VCPU_LAST_CPU(r4) + sldi r7,r6,1 /* see if this is the same vcpu */ + add r7,r7,r9 /* as last ran on this pcpu */ + lhz r0,KVM_LAST_VCPU(r7) + cmpw r6,r8 /* on the same cpu core as last time? */ + bne 3f + cmpw r0,r5 /* same vcpu as this core last ran? */ + beq 1f +3: sth r6,VCPU_LAST_CPU(r4) /* if not, invalidate partition TLB */ + sth r5,KVM_LAST_VCPU(r7) + li r6,128 + mtctr r6 + li r7,0x800 /* IS field = 0b10 */ + ptesync +2: tlbiel r7 + addi r7,r7,0x1000 + bdnz 2b + ptesync +1: + + /* Save purr/spurr */ + mfspr r5,SPRN_PURR + mfspr r6,SPRN_SPURR + std r5,HSTATE_PURR(r13) + std r6,HSTATE_SPURR(r13) + ld r7,VCPU_PURR(r4) + ld r8,VCPU_SPURR(r4) + mtspr SPRN_PURR,r7 + mtspr SPRN_SPURR,r8 + b 31f + + /* + * PPC970 host -> guest partition switch code. + * We have to lock against concurrent tlbies, + * using native_tlbie_lock to lock against host tlbies + * and kvm->arch.tlbie_lock to lock against guest tlbies. + * We also have to invalidate the TLB since its + * entries aren't tagged with the LPID. + */ +30: ld r9,VCPU_KVM(r4) /* pointer to struct kvm */ + + /* first take native_tlbie_lock */ + .section ".toc","aw" +toc_tlbie_lock: + .tc native_tlbie_lock[TC],native_tlbie_lock + .previous + ld r3,toc_tlbie_lock@toc(2) + lwz r8,PACA_LOCK_TOKEN(r13) +24: lwarx r0,0,r3 + cmpwi r0,0 + bne 24b + stwcx. r8,0,r3 + bne 24b + isync + + ld r7,KVM_LPCR(r9) /* use kvm->arch.lpcr to store HID4 */ + li r0,0x18f + rotldi r0,r0,HID4_LPID5_SH /* all lpid bits in HID4 = 1 */ + or r0,r7,r0 + ptesync + sync + mtspr SPRN_HID4,r0 /* switch to reserved LPID */ + isync + li r0,0 + stw r0,0(r3) /* drop native_tlbie_lock */ + + /* invalidate the whole TLB */ + li r0,256 + mtctr r0 + li r6,0 +25: tlbiel r6 + addi r6,r6,0x1000 + bdnz 25b + ptesync + + /* Take the guest's tlbie_lock */ + addi r3,r9,KVM_TLBIE_LOCK +24: lwarx r0,0,r3 + cmpwi r0,0 + bne 24b + stwcx. r8,0,r3 + bne 24b + isync + ld r6,KVM_SDR1(r9) + mtspr SPRN_SDR1,r6 /* switch to partition page table */ + + /* Set up HID4 with the guest's LPID etc. */ + sync + mtspr SPRN_HID4,r7 + isync + + /* drop the guest's tlbie_lock */ + li r0,0 + stw r0,0(r3) + + /* Check if HDEC expires soon */ + mfspr r3,SPRN_HDEC + cmpwi r3,10 + li r12,BOOK3S_INTERRUPT_HV_DECREMENTER + mr r9,r4 + blt hdec_soon + + /* Enable HDEC interrupts */ + mfspr r0,SPRN_HID0 + li r3,1 + rldimi r0,r3, HID0_HDICE_SH, 64-HID0_HDICE_SH-1 + sync + mtspr SPRN_HID0,r0 + mfspr r0,SPRN_HID0 + mfspr r0,SPRN_HID0 + mfspr r0,SPRN_HID0 + mfspr r0,SPRN_HID0 + mfspr r0,SPRN_HID0 + mfspr r0,SPRN_HID0 + + /* Load up guest SLB entries */ +31: lwz r5,VCPU_SLB_MAX(r4) + cmpwi r5,0 + beq 9f + mtctr r5 + addi r6,r4,VCPU_SLB +1: ld r8,VCPU_SLB_E(r6) + ld r9,VCPU_SLB_V(r6) + slbmte r9,r8 + addi r6,r6,VCPU_SLB_SIZE + bdnz 1b +9: + + /* Restore state of CTRL run bit; assume 1 on entry */ + lwz r5,VCPU_CTRL(r4) + andi. r5,r5,1 + bne 4f + mfspr r6,SPRN_CTRLF + clrrdi r6,r6,1 + mtspr SPRN_CTRLT,r6 +4: + ld r6, VCPU_CTR(r4) + lwz r7, VCPU_XER(r4) + + mtctr r6 + mtxer r7 + + /* Move SRR0 and SRR1 into the respective regs */ + ld r6, VCPU_SRR0(r4) + ld r7, VCPU_SRR1(r4) + mtspr SPRN_SRR0, r6 + mtspr SPRN_SRR1, r7 + + ld r10, VCPU_PC(r4) + + ld r11, VCPU_MSR(r4) /* r10 = vcpu->arch.msr & ~MSR_HV */ + rldicl r11, r11, 63 - MSR_HV_LG, 1 + rotldi r11, r11, 1 + MSR_HV_LG + ori r11, r11, MSR_ME + +fast_guest_return: + mtspr SPRN_HSRR0,r10 + mtspr SPRN_HSRR1,r11 + + /* Activate guest mode, so faults get handled by KVM */ + li r9, KVM_GUEST_MODE_GUEST + stb r9, HSTATE_IN_GUEST(r13) + + /* Enter guest */ + + ld r5, VCPU_LR(r4) + lwz r6, VCPU_CR(r4) + mtlr r5 + mtcr r6 + + 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 r9, VCPU_GPR(r9)(r4) + ld r10, VCPU_GPR(r10)(r4) + ld r11, VCPU_GPR(r11)(r4) + ld r12, VCPU_GPR(r12)(r4) + ld r13, VCPU_GPR(r13)(r4) + + ld r4, VCPU_GPR(r4)(r4) + + hrfid + b . + +/****************************************************************************** + * * + * Exit code * + * * + *****************************************************************************/ + +/* + * We come here from the first-level interrupt handlers. + */ + .globl kvmppc_interrupt +kvmppc_interrupt: + /* + * Register contents: + * R12 = interrupt vector + * R13 = PACA + * guest CR, R12 saved in shadow VCPU SCRATCH1/0 + * guest R13 saved in SPRN_SCRATCH0 + */ + /* abuse host_r2 as third scratch area; we get r2 from PACATOC(r13) */ + std r9, HSTATE_HOST_R2(r13) + ld r9, HSTATE_KVM_VCPU(r13) + + /* Save registers */ + + std r0, VCPU_GPR(r0)(r9) + std r1, VCPU_GPR(r1)(r9) + std r2, VCPU_GPR(r2)(r9) + std r3, VCPU_GPR(r3)(r9) + std r4, VCPU_GPR(r4)(r9) + std r5, VCPU_GPR(r5)(r9) + std r6, VCPU_GPR(r6)(r9) + std r7, VCPU_GPR(r7)(r9) + std r8, VCPU_GPR(r8)(r9) + ld r0, HSTATE_HOST_R2(r13) + std r0, VCPU_GPR(r9)(r9) + std r10, VCPU_GPR(r10)(r9) + std r11, VCPU_GPR(r11)(r9) + ld r3, HSTATE_SCRATCH0(r13) + lwz r4, HSTATE_SCRATCH1(r13) + std r3, VCPU_GPR(r12)(r9) + stw r4, VCPU_CR(r9) + + /* Restore R1/R2 so we can handle faults */ + ld r1, HSTATE_HOST_R1(r13) + ld r2, PACATOC(r13) + + mfspr r10, SPRN_SRR0 + mfspr r11, SPRN_SRR1 + std r10, VCPU_SRR0(r9) + std r11, VCPU_SRR1(r9) + andi. r0, r12, 2 /* need to read HSRR0/1? */ + beq 1f + mfspr r10, SPRN_HSRR0 + mfspr r11, SPRN_HSRR1 + clrrdi r12, r12, 2 +1: std r10, VCPU_PC(r9) + std r11, VCPU_MSR(r9) + + GET_SCRATCH0(r3) + mflr r4 + std r3, VCPU_GPR(r13)(r9) + std r4, VCPU_LR(r9) + + /* Unset guest mode */ + li r0, KVM_GUEST_MODE_NONE + stb r0, HSTATE_IN_GUEST(r13) + + stw r12,VCPU_TRAP(r9) + + /* See if this is a leftover HDEC interrupt */ + cmpwi r12,BOOK3S_INTERRUPT_HV_DECREMENTER + bne 2f + mfspr r3,SPRN_HDEC + cmpwi r3,0 + bge ignore_hdec +2: + /* See if this is something we can handle in real mode */ + cmpwi r12,BOOK3S_INTERRUPT_SYSCALL + beq hcall_try_real_mode +hcall_real_cont: + + /* Check for mediated interrupts (could be done earlier really ...) */ +BEGIN_FTR_SECTION + cmpwi r12,BOOK3S_INTERRUPT_EXTERNAL + bne+ 1f + ld r5,VCPU_KVM(r9) + ld r5,KVM_LPCR(r5) + andi. r0,r11,MSR_EE + beq 1f + andi. r0,r5,LPCR_MER + bne bounce_ext_interrupt +1: +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) + + /* Save DEC */ + mfspr r5,SPRN_DEC + mftb r6 + extsw r5,r5 + add r5,r5,r6 + std r5,VCPU_DEC_EXPIRES(r9) + + /* Save HEIR (HV emulation assist reg) in last_inst + if this is an HEI (HV emulation interrupt, e40) */ + li r3,-1 +BEGIN_FTR_SECTION + cmpwi r12,BOOK3S_INTERRUPT_H_EMUL_ASSIST + bne 11f + mfspr r3,SPRN_HEIR +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) +11: stw r3,VCPU_LAST_INST(r9) + + /* Save more register state */ + mfxer r5 + mfdar r6 + mfdsisr r7 + mfctr r8 + + stw r5, VCPU_XER(r9) + std r6, VCPU_DAR(r9) + stw r7, VCPU_DSISR(r9) + std r8, VCPU_CTR(r9) + /* grab HDAR & HDSISR if HV data storage interrupt (HDSI) */ +BEGIN_FTR_SECTION + cmpwi r12,BOOK3S_INTERRUPT_H_DATA_STORAGE + beq 6f +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) +7: std r6, VCPU_FAULT_DAR(r9) + stw r7, VCPU_FAULT_DSISR(r9) + + /* Save guest CTRL register, set runlatch to 1 */ + mfspr r6,SPRN_CTRLF + stw r6,VCPU_CTRL(r9) + andi. r0,r6,1 + bne 4f + ori r6,r6,1 + mtspr SPRN_CTRLT,r6 +4: + /* Read the guest SLB and save it away */ + lwz r0,VCPU_SLB_NR(r9) /* number of entries in SLB */ + mtctr r0 + li r6,0 + addi r7,r9,VCPU_SLB + li r5,0 +1: slbmfee r8,r6 + andis. r0,r8,SLB_ESID_V@h + beq 2f + add r8,r8,r6 /* put index in */ + slbmfev r3,r6 + std r8,VCPU_SLB_E(r7) + std r3,VCPU_SLB_V(r7) + addi r7,r7,VCPU_SLB_SIZE + addi r5,r5,1 +2: addi r6,r6,1 + bdnz 1b + stw r5,VCPU_SLB_MAX(r9) + + /* + * Save the guest PURR/SPURR + */ +BEGIN_FTR_SECTION + mfspr r5,SPRN_PURR + mfspr r6,SPRN_SPURR + ld r7,VCPU_PURR(r9) + ld r8,VCPU_SPURR(r9) + std r5,VCPU_PURR(r9) + std r6,VCPU_SPURR(r9) + subf r5,r7,r5 + subf r6,r8,r6 + + /* + * Restore host PURR/SPURR and add guest times + * so that the time in the guest gets accounted. + */ + ld r3,HSTATE_PURR(r13) + ld r4,HSTATE_SPURR(r13) + add r3,r3,r5 + add r4,r4,r6 + mtspr SPRN_PURR,r3 + mtspr SPRN_SPURR,r4 +END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_201) + + /* Clear out SLB */ + li r5,0 + slbmte r5,r5 + slbia + ptesync + +hdec_soon: +BEGIN_FTR_SECTION + b 32f +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) + /* + * POWER7 guest -> host partition switch code. + * We don't have to lock against tlbies but we do + * have to coordinate the hardware threads. + */ + /* Increment the threads-exiting-guest count in the 0xff00 + bits of vcore->entry_exit_count */ + lwsync + ld r5,HSTATE_KVM_VCORE(r13) + addi r6,r5,VCORE_ENTRY_EXIT +41: lwarx r3,0,r6 + addi r0,r3,0x100 + stwcx. r0,0,r6 + bne 41b + + /* + * At this point we have an interrupt that we have to pass + * up to the kernel or qemu; we can't handle it in real mode. + * Thus we have to do a partition switch, so we have to + * collect the other threads, if we are the first thread + * to take an interrupt. To do this, we set the HDEC to 0, + * which causes an HDEC interrupt in all threads within 2ns + * because the HDEC register is shared between all 4 threads. + * However, we don't need to bother if this is an HDEC + * interrupt, since the other threads will already be on their + * way here in that case. + */ + cmpwi r12,BOOK3S_INTERRUPT_HV_DECREMENTER + beq 40f + cmpwi r3,0x100 /* Are we the first here? */ + bge 40f + cmpwi r3,1 + ble 40f + li r0,0 + mtspr SPRN_HDEC,r0 +40: + + /* Secondary threads wait for primary to do partition switch */ + ld r4,VCPU_KVM(r9) /* pointer to struct kvm */ + ld r5,HSTATE_KVM_VCORE(r13) + lwz r3,VCPU_PTID(r9) + cmpwi r3,0 + beq 15f + HMT_LOW +13: lbz r3,VCORE_IN_GUEST(r5) + cmpwi r3,0 + bne 13b + HMT_MEDIUM + b 16f + + /* Primary thread waits for all the secondaries to exit guest */ +15: lwz r3,VCORE_ENTRY_EXIT(r5) + srwi r0,r3,8 + clrldi r3,r3,56 + cmpw r3,r0 + bne 15b + isync + + /* Primary thread switches back to host partition */ + ld r6,KVM_HOST_SDR1(r4) + lwz r7,KVM_HOST_LPID(r4) + li r8,LPID_RSVD /* switch to reserved LPID */ + mtspr SPRN_LPID,r8 + ptesync + mtspr SPRN_SDR1,r6 /* switch to partition page table */ + mtspr SPRN_LPID,r7 + isync + li r0,0 + stb r0,VCORE_IN_GUEST(r5) + lis r8,0x7fff /* MAX_INT@h */ + mtspr SPRN_HDEC,r8 + +16: ld r8,KVM_HOST_LPCR(r4) + mtspr SPRN_LPCR,r8 + isync + b 33f + + /* + * PPC970 guest -> host partition switch code. + * We have to lock against concurrent tlbies, and + * we have to flush the whole TLB. + */ +32: ld r4,VCPU_KVM(r9) /* pointer to struct kvm */ + + /* Take the guest's tlbie_lock */ + lwz r8,PACA_LOCK_TOKEN(r13) + addi r3,r4,KVM_TLBIE_LOCK +24: lwarx r0,0,r3 + cmpwi r0,0 + bne 24b + stwcx. r8,0,r3 + bne 24b + isync + + ld r7,KVM_HOST_LPCR(r4) /* use kvm->arch.host_lpcr for HID4 */ + li r0,0x18f + rotldi r0,r0,HID4_LPID5_SH /* all lpid bits in HID4 = 1 */ + or r0,r7,r0 + ptesync + sync + mtspr SPRN_HID4,r0 /* switch to reserved LPID */ + isync + li r0,0 + stw r0,0(r3) /* drop guest tlbie_lock */ + + /* invalidate the whole TLB */ + li r0,256 + mtctr r0 + li r6,0 +25: tlbiel r6 + addi r6,r6,0x1000 + bdnz 25b + ptesync + + /* take native_tlbie_lock */ + ld r3,toc_tlbie_lock@toc(2) +24: lwarx r0,0,r3 + cmpwi r0,0 + bne 24b + stwcx. r8,0,r3 + bne 24b + isync + + ld r6,KVM_HOST_SDR1(r4) + mtspr SPRN_SDR1,r6 /* switch to host page table */ + + /* Set up host HID4 value */ + sync + mtspr SPRN_HID4,r7 + isync + li r0,0 + stw r0,0(r3) /* drop native_tlbie_lock */ + + lis r8,0x7fff /* MAX_INT@h */ + mtspr SPRN_HDEC,r8 + + /* Disable HDEC interrupts */ + mfspr r0,SPRN_HID0 + li r3,0 + rldimi r0,r3, HID0_HDICE_SH, 64-HID0_HDICE_SH-1 + sync + mtspr SPRN_HID0,r0 + mfspr r0,SPRN_HID0 + mfspr r0,SPRN_HID0 + mfspr r0,SPRN_HID0 + mfspr r0,SPRN_HID0 + mfspr r0,SPRN_HID0 + mfspr r0,SPRN_HID0 + + /* load host SLB entries */ +33: ld r8,PACA_SLBSHADOWPTR(r13) + + .rept SLB_NUM_BOLTED + ld r5,SLBSHADOW_SAVEAREA(r8) + ld r6,SLBSHADOW_SAVEAREA+8(r8) + andis. r7,r5,SLB_ESID_V@h + beq 1f + slbmte r6,r5 +1: addi r8,r8,16 + .endr + + /* Save and reset AMR and UAMOR before turning on the MMU */ +BEGIN_FTR_SECTION + mfspr r5,SPRN_AMR + mfspr r6,SPRN_UAMOR + std r5,VCPU_AMR(r9) + std r6,VCPU_UAMOR(r9) + li r6,0 + mtspr SPRN_AMR,r6 +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) + + /* Restore host DABR and DABRX */ + ld r5,HSTATE_DABR(r13) + li r6,7 + mtspr SPRN_DABR,r5 + mtspr SPRN_DABRX,r6 + + /* Switch DSCR back to host value */ +BEGIN_FTR_SECTION + mfspr r8, SPRN_DSCR + ld r7, HSTATE_DSCR(r13) + std r8, VCPU_DSCR(r7) + mtspr SPRN_DSCR, r7 +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) + + /* Save non-volatile GPRs */ + std r14, VCPU_GPR(r14)(r9) + std r15, VCPU_GPR(r15)(r9) + std r16, VCPU_GPR(r16)(r9) + std r17, VCPU_GPR(r17)(r9) + std r18, VCPU_GPR(r18)(r9) + std r19, VCPU_GPR(r19)(r9) + std r20, VCPU_GPR(r20)(r9) + std r21, VCPU_GPR(r21)(r9) + std r22, VCPU_GPR(r22)(r9) + std r23, VCPU_GPR(r23)(r9) + std r24, VCPU_GPR(r24)(r9) + std r25, VCPU_GPR(r25)(r9) + std r26, VCPU_GPR(r26)(r9) + std r27, VCPU_GPR(r27)(r9) + std r28, VCPU_GPR(r28)(r9) + std r29, VCPU_GPR(r29)(r9) + std r30, VCPU_GPR(r30)(r9) + std r31, VCPU_GPR(r31)(r9) + + /* Save SPRGs */ + mfspr r3, SPRN_SPRG0 + mfspr r4, SPRN_SPRG1 + mfspr r5, SPRN_SPRG2 + mfspr r6, SPRN_SPRG3 + std r3, VCPU_SPRG0(r9) + std r4, VCPU_SPRG1(r9) + std r5, VCPU_SPRG2(r9) + std r6, VCPU_SPRG3(r9) + + /* Increment yield count if they have a VPA */ + ld r8, VCPU_VPA(r9) /* do they have a VPA? */ + cmpdi r8, 0 + beq 25f + lwz r3, LPPACA_YIELDCOUNT(r8) + addi r3, r3, 1 + stw r3, LPPACA_YIELDCOUNT(r8) +25: + /* Save PMU registers if requested */ + /* r8 and cr0.eq are live here */ + li r3, 1 + sldi r3, r3, 31 /* MMCR0_FC (freeze counters) bit */ + mfspr r4, SPRN_MMCR0 /* save MMCR0 */ + mtspr SPRN_MMCR0, r3 /* freeze all counters, disable ints */ + isync + beq 21f /* if no VPA, save PMU stuff anyway */ + lbz r7, LPPACA_PMCINUSE(r8) + cmpwi r7, 0 /* did they ask for PMU stuff to be saved? */ + bne 21f + std r3, VCPU_MMCR(r9) /* if not, set saved MMCR0 to FC */ + b 22f +21: mfspr r5, SPRN_MMCR1 + mfspr r6, SPRN_MMCRA + std r4, VCPU_MMCR(r9) + std r5, VCPU_MMCR + 8(r9) + std r6, VCPU_MMCR + 16(r9) + mfspr r3, SPRN_PMC1 + mfspr r4, SPRN_PMC2 + mfspr r5, SPRN_PMC3 + mfspr r6, SPRN_PMC4 + mfspr r7, SPRN_PMC5 + mfspr r8, SPRN_PMC6 +BEGIN_FTR_SECTION + mfspr r10, SPRN_PMC7 + mfspr r11, SPRN_PMC8 +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) + stw r3, VCPU_PMC(r9) + stw r4, VCPU_PMC + 4(r9) + stw r5, VCPU_PMC + 8(r9) + stw r6, VCPU_PMC + 12(r9) + stw r7, VCPU_PMC + 16(r9) + stw r8, VCPU_PMC + 20(r9) +BEGIN_FTR_SECTION + stw r10, VCPU_PMC + 24(r9) + stw r11, VCPU_PMC + 28(r9) +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) +22: + /* save FP state */ + mr r3, r9 + bl .kvmppc_save_fp + + /* Secondary threads go off to take a nap on POWER7 */ +BEGIN_FTR_SECTION + lwz r0,VCPU_PTID(r3) + cmpwi r0,0 + bne secondary_nap +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) + + /* + * Reload DEC. HDEC interrupts were disabled when + * we reloaded the host's LPCR value. + */ + ld r3, HSTATE_DECEXP(r13) + mftb r4 + subf r4, r4, r3 + mtspr SPRN_DEC, r4 + + /* Reload the host's PMU registers */ + ld r3, PACALPPACAPTR(r13) /* is the host using the PMU? */ + lbz r4, LPPACA_PMCINUSE(r3) + cmpwi r4, 0 + beq 23f /* skip if not */ + lwz r3, HSTATE_PMC(r13) + lwz r4, HSTATE_PMC + 4(r13) + lwz r5, HSTATE_PMC + 8(r13) + lwz r6, HSTATE_PMC + 12(r13) + lwz r8, HSTATE_PMC + 16(r13) + lwz r9, HSTATE_PMC + 20(r13) +BEGIN_FTR_SECTION + lwz r10, HSTATE_PMC + 24(r13) + lwz r11, HSTATE_PMC + 28(r13) +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) + mtspr SPRN_PMC1, r3 + mtspr SPRN_PMC2, r4 + mtspr SPRN_PMC3, r5 + mtspr SPRN_PMC4, r6 + mtspr SPRN_PMC5, r8 + mtspr SPRN_PMC6, r9 +BEGIN_FTR_SECTION + mtspr SPRN_PMC7, r10 + mtspr SPRN_PMC8, r11 +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) + ld r3, HSTATE_MMCR(r13) + ld r4, HSTATE_MMCR + 8(r13) + ld r5, HSTATE_MMCR + 16(r13) + mtspr SPRN_MMCR1, r4 + mtspr SPRN_MMCRA, r5 + mtspr SPRN_MMCR0, r3 + isync +23: + /* + * For external and machine check interrupts, we need + * to call the Linux handler to process the interrupt. + * We do that by jumping to the interrupt vector address + * which we have in r12. The [h]rfid at the end of the + * handler will return to the book3s_hv_interrupts.S code. + * For other interrupts we do the rfid to get back + * to the book3s_interrupts.S code here. + */ + ld r8, HSTATE_VMHANDLER(r13) + ld r7, HSTATE_HOST_MSR(r13) + + cmpwi r12, BOOK3S_INTERRUPT_EXTERNAL + beq 11f + cmpwi r12, BOOK3S_INTERRUPT_MACHINE_CHECK + + /* RFI into the highmem handler, or branch to interrupt handler */ +12: mfmsr r6 + mtctr r12 + li r0, MSR_RI + andc r6, r6, r0 + mtmsrd r6, 1 /* Clear RI in MSR */ + mtsrr0 r8 + mtsrr1 r7 + beqctr + RFI + +11: +BEGIN_FTR_SECTION + b 12b +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) + mtspr SPRN_HSRR0, r8 + mtspr SPRN_HSRR1, r7 + ba 0x500 + +6: mfspr r6,SPRN_HDAR + mfspr r7,SPRN_HDSISR + b 7b + +/* + * Try to handle an hcall in real mode. + * Returns to the guest if we handle it, or continues on up to + * the kernel if we can't (i.e. if we don't have a handler for + * it, or if the handler returns H_TOO_HARD). + */ + .globl hcall_try_real_mode +hcall_try_real_mode: + ld r3,VCPU_GPR(r3)(r9) + andi. r0,r11,MSR_PR + bne hcall_real_cont + clrrdi r3,r3,2 + cmpldi r3,hcall_real_table_end - hcall_real_table + bge hcall_real_cont + LOAD_REG_ADDR(r4, hcall_real_table) + lwzx r3,r3,r4 + cmpwi r3,0 + beq hcall_real_cont + add r3,r3,r4 + mtctr r3 + mr r3,r9 /* get vcpu pointer */ + ld r4,VCPU_GPR(r4)(r9) + bctrl + cmpdi r3,H_TOO_HARD + beq hcall_real_fallback + ld r4,HSTATE_KVM_VCPU(r13) + std r3,VCPU_GPR(r3)(r4) + ld r10,VCPU_PC(r4) + ld r11,VCPU_MSR(r4) + b fast_guest_return + + /* We've attempted a real mode hcall, but it's punted it back + * to userspace. We need to restore some clobbered volatiles + * before resuming the pass-it-to-qemu path */ +hcall_real_fallback: + li r12,BOOK3S_INTERRUPT_SYSCALL + ld r9, HSTATE_KVM_VCPU(r13) + ld r11, VCPU_MSR(r9) + + b hcall_real_cont + + .globl hcall_real_table +hcall_real_table: + .long 0 /* 0 - unused */ + .long .kvmppc_h_remove - hcall_real_table + .long .kvmppc_h_enter - hcall_real_table + .long .kvmppc_h_read - hcall_real_table + .long 0 /* 0x10 - H_CLEAR_MOD */ + .long 0 /* 0x14 - H_CLEAR_REF */ + .long .kvmppc_h_protect - hcall_real_table + .long 0 /* 0x1c - H_GET_TCE */ + .long .kvmppc_h_put_tce - hcall_real_table + .long 0 /* 0x24 - H_SET_SPRG0 */ + .long .kvmppc_h_set_dabr - hcall_real_table + .long 0 /* 0x2c */ + .long 0 /* 0x30 */ + .long 0 /* 0x34 */ + .long 0 /* 0x38 */ + .long 0 /* 0x3c */ + .long 0 /* 0x40 */ + .long 0 /* 0x44 */ + .long 0 /* 0x48 */ + .long 0 /* 0x4c */ + .long 0 /* 0x50 */ + .long 0 /* 0x54 */ + .long 0 /* 0x58 */ + .long 0 /* 0x5c */ + .long 0 /* 0x60 */ + .long 0 /* 0x64 */ + .long 0 /* 0x68 */ + .long 0 /* 0x6c */ + .long 0 /* 0x70 */ + .long 0 /* 0x74 */ + .long 0 /* 0x78 */ + .long 0 /* 0x7c */ + .long 0 /* 0x80 */ + .long 0 /* 0x84 */ + .long 0 /* 0x88 */ + .long 0 /* 0x8c */ + .long 0 /* 0x90 */ + .long 0 /* 0x94 */ + .long 0 /* 0x98 */ + .long 0 /* 0x9c */ + .long 0 /* 0xa0 */ + .long 0 /* 0xa4 */ + .long 0 /* 0xa8 */ + .long 0 /* 0xac */ + .long 0 /* 0xb0 */ + .long 0 /* 0xb4 */ + .long 0 /* 0xb8 */ + .long 0 /* 0xbc */ + .long 0 /* 0xc0 */ + .long 0 /* 0xc4 */ + .long 0 /* 0xc8 */ + .long 0 /* 0xcc */ + .long 0 /* 0xd0 */ + .long 0 /* 0xd4 */ + .long 0 /* 0xd8 */ + .long 0 /* 0xdc */ + .long 0 /* 0xe0 */ + .long 0 /* 0xe4 */ + .long 0 /* 0xe8 */ + .long 0 /* 0xec */ + .long 0 /* 0xf0 */ + .long 0 /* 0xf4 */ + .long 0 /* 0xf8 */ + .long 0 /* 0xfc */ + .long 0 /* 0x100 */ + .long 0 /* 0x104 */ + .long 0 /* 0x108 */ + .long 0 /* 0x10c */ + .long 0 /* 0x110 */ + .long 0 /* 0x114 */ + .long 0 /* 0x118 */ + .long 0 /* 0x11c */ + .long 0 /* 0x120 */ + .long .kvmppc_h_bulk_remove - hcall_real_table +hcall_real_table_end: + +ignore_hdec: + mr r4,r9 + b fast_guest_return + +bounce_ext_interrupt: + mr r4,r9 + mtspr SPRN_SRR0,r10 + mtspr SPRN_SRR1,r11 + li r10,BOOK3S_INTERRUPT_EXTERNAL + LOAD_REG_IMMEDIATE(r11,MSR_SF | MSR_ME); + b fast_guest_return + +_GLOBAL(kvmppc_h_set_dabr) + std r4,VCPU_DABR(r3) + mtspr SPRN_DABR,r4 + li r3,0 + blr + +secondary_too_late: + ld r5,HSTATE_KVM_VCORE(r13) + HMT_LOW +13: lbz r3,VCORE_IN_GUEST(r5) + cmpwi r3,0 + bne 13b + HMT_MEDIUM + ld r11,PACA_SLBSHADOWPTR(r13) + + .rept SLB_NUM_BOLTED + ld r5,SLBSHADOW_SAVEAREA(r11) + ld r6,SLBSHADOW_SAVEAREA+8(r11) + andis. r7,r5,SLB_ESID_V@h + beq 1f + slbmte r6,r5 +1: addi r11,r11,16 + .endr + b 50f + +secondary_nap: + /* Clear any pending IPI */ +50: ld r5, HSTATE_XICS_PHYS(r13) + li r0, 0xff + li r6, XICS_QIRR + stbcix r0, r5, r6 + + /* increment the nap count and then go to nap mode */ + ld r4, HSTATE_KVM_VCORE(r13) + addi r4, r4, VCORE_NAP_COUNT + lwsync /* make previous updates visible */ +51: lwarx r3, 0, r4 + addi r3, r3, 1 + stwcx. r3, 0, r4 + bne 51b + isync + + mfspr r4, SPRN_LPCR + li r0, LPCR_PECE + andc r4, r4, r0 + ori r4, r4, LPCR_PECE0 /* exit nap on interrupt */ + mtspr SPRN_LPCR, r4 + li r0, 0 + std r0, HSTATE_SCRATCH0(r13) + ptesync + ld r0, HSTATE_SCRATCH0(r13) +1: cmpd r0, r0 + bne 1b + nap + b . + +/* + * Save away FP, VMX and VSX registers. + * r3 = vcpu pointer + */ +_GLOBAL(kvmppc_save_fp) + mfmsr r9 + ori r8,r9,MSR_FP +#ifdef CONFIG_ALTIVEC +BEGIN_FTR_SECTION + oris r8,r8,MSR_VEC@h +END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) +#endif +#ifdef CONFIG_VSX +BEGIN_FTR_SECTION + oris r8,r8,MSR_VSX@h +END_FTR_SECTION_IFSET(CPU_FTR_VSX) +#endif + mtmsrd r8 + isync +#ifdef CONFIG_VSX +BEGIN_FTR_SECTION + reg = 0 + .rept 32 + li r6,reg*16+VCPU_VSRS + stxvd2x reg,r6,r3 + reg = reg + 1 + .endr +FTR_SECTION_ELSE +#endif + reg = 0 + .rept 32 + stfd reg,reg*8+VCPU_FPRS(r3) + reg = reg + 1 + .endr +#ifdef CONFIG_VSX +ALT_FTR_SECTION_END_IFSET(CPU_FTR_VSX) +#endif + mffs fr0 + stfd fr0,VCPU_FPSCR(r3) + +#ifdef CONFIG_ALTIVEC +BEGIN_FTR_SECTION + reg = 0 + .rept 32 + li r6,reg*16+VCPU_VRS + stvx reg,r6,r3 + reg = reg + 1 + .endr + mfvscr vr0 + li r6,VCPU_VSCR + stvx vr0,r6,r3 +END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) +#endif + mfspr r6,SPRN_VRSAVE + stw r6,VCPU_VRSAVE(r3) + mtmsrd r9 + isync + blr + +/* + * Load up FP, VMX and VSX registers + * r4 = vcpu pointer + */ + .globl kvmppc_load_fp +kvmppc_load_fp: + mfmsr r9 + ori r8,r9,MSR_FP +#ifdef CONFIG_ALTIVEC +BEGIN_FTR_SECTION + oris r8,r8,MSR_VEC@h +END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) +#endif +#ifdef CONFIG_VSX +BEGIN_FTR_SECTION + oris r8,r8,MSR_VSX@h +END_FTR_SECTION_IFSET(CPU_FTR_VSX) +#endif + mtmsrd r8 + isync + lfd fr0,VCPU_FPSCR(r4) + MTFSF_L(fr0) +#ifdef CONFIG_VSX +BEGIN_FTR_SECTION + reg = 0 + .rept 32 + li r7,reg*16+VCPU_VSRS + lxvd2x reg,r7,r4 + reg = reg + 1 + .endr +FTR_SECTION_ELSE +#endif + reg = 0 + .rept 32 + lfd reg,reg*8+VCPU_FPRS(r4) + reg = reg + 1 + .endr +#ifdef CONFIG_VSX +ALT_FTR_SECTION_END_IFSET(CPU_FTR_VSX) +#endif + +#ifdef CONFIG_ALTIVEC +BEGIN_FTR_SECTION + li r7,VCPU_VSCR + lvx vr0,r7,r4 + mtvscr vr0 + reg = 0 + .rept 32 + li r7,reg*16+VCPU_VRS + lvx reg,r7,r4 + reg = reg + 1 + .endr +END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) +#endif + lwz r7,VCPU_VRSAVE(r4) + mtspr SPRN_VRSAVE,r7 + blr diff --git a/arch/powerpc/kvm/book3s_interrupts.S b/arch/powerpc/kvm/book3s_interrupts.S index 2f0bc928b08..c54b0e30cf3 100644 --- a/arch/powerpc/kvm/book3s_interrupts.S +++ b/arch/powerpc/kvm/book3s_interrupts.S @@ -29,8 +29,7 @@ #define ULONG_SIZE 8 #define FUNC(name) GLUE(.,name) -#define GET_SHADOW_VCPU(reg) \ - addi reg, r13, PACA_KVM_SVCPU +#define GET_SHADOW_VCPU_R13 #define DISABLE_INTERRUPTS \ mfmsr r0; \ @@ -43,8 +42,8 @@ #define ULONG_SIZE 4 #define FUNC(name) name -#define GET_SHADOW_VCPU(reg) \ - lwz reg, (THREAD + THREAD_KVM_SVCPU)(r2) +#define GET_SHADOW_VCPU_R13 \ + lwz r13, (THREAD + THREAD_KVM_SVCPU)(r2) #define DISABLE_INTERRUPTS \ mfmsr r0; \ @@ -85,7 +84,7 @@ * r3: kvm_run pointer * r4: vcpu pointer */ -_GLOBAL(__kvmppc_vcpu_entry) +_GLOBAL(__kvmppc_vcpu_run) kvm_start_entry: /* Write correct stack frame */ @@ -107,17 +106,11 @@ kvm_start_entry: /* Load non-volatile guest state from the vcpu */ VCPU_LOAD_NVGPRS(r4) - GET_SHADOW_VCPU(r5) - - /* Save R1/R2 in the PACA */ - PPC_STL r1, SVCPU_HOST_R1(r5) - PPC_STL r2, SVCPU_HOST_R2(r5) +kvm_start_lightweight: - /* XXX swap in/out on load? */ + GET_SHADOW_VCPU_R13 PPC_LL r3, VCPU_HIGHMEM_HANDLER(r4) - PPC_STL r3, SVCPU_VMHANDLER(r5) - -kvm_start_lightweight: + PPC_STL r3, HSTATE_VMHANDLER(r13) PPC_LL r10, VCPU_SHADOW_MSR(r4) /* r10 = vcpu->arch.shadow_msr */ diff --git a/arch/powerpc/kvm/book3s_mmu_hpte.c b/arch/powerpc/kvm/book3s_mmu_hpte.c index 79751d8dd13..41cb0017e75 100644 --- a/arch/powerpc/kvm/book3s_mmu_hpte.c +++ b/arch/powerpc/kvm/book3s_mmu_hpte.c @@ -21,7 +21,6 @@ #include <linux/kvm_host.h> #include <linux/hash.h> #include <linux/slab.h> -#include "trace.h" #include <asm/kvm_ppc.h> #include <asm/kvm_book3s.h> @@ -29,6 +28,8 @@ #include <asm/mmu_context.h> #include <asm/hw_irq.h> +#include "trace.h" + #define PTE_SIZE 12 static struct kmem_cache *hpte_cache; @@ -58,30 +59,31 @@ static inline u64 kvmppc_mmu_hash_vpte_long(u64 vpage) void kvmppc_mmu_hpte_cache_map(struct kvm_vcpu *vcpu, struct hpte_cache *pte) { u64 index; + struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu); trace_kvm_book3s_mmu_map(pte); - spin_lock(&vcpu->arch.mmu_lock); + spin_lock(&vcpu3s->mmu_lock); /* Add to ePTE list */ index = kvmppc_mmu_hash_pte(pte->pte.eaddr); - hlist_add_head_rcu(&pte->list_pte, &vcpu->arch.hpte_hash_pte[index]); + hlist_add_head_rcu(&pte->list_pte, &vcpu3s->hpte_hash_pte[index]); /* Add to ePTE_long list */ index = kvmppc_mmu_hash_pte_long(pte->pte.eaddr); hlist_add_head_rcu(&pte->list_pte_long, - &vcpu->arch.hpte_hash_pte_long[index]); + &vcpu3s->hpte_hash_pte_long[index]); /* Add to vPTE list */ index = kvmppc_mmu_hash_vpte(pte->pte.vpage); - hlist_add_head_rcu(&pte->list_vpte, &vcpu->arch.hpte_hash_vpte[index]); + hlist_add_head_rcu(&pte->list_vpte, &vcpu3s->hpte_hash_vpte[index]); /* Add to vPTE_long list */ index = kvmppc_mmu_hash_vpte_long(pte->pte.vpage); hlist_add_head_rcu(&pte->list_vpte_long, - &vcpu->arch.hpte_hash_vpte_long[index]); + &vcpu3s->hpte_hash_vpte_long[index]); - spin_unlock(&vcpu->arch.mmu_lock); + spin_unlock(&vcpu3s->mmu_lock); } static void free_pte_rcu(struct rcu_head *head) @@ -92,16 +94,18 @@ static void free_pte_rcu(struct rcu_head *head) static void invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte) { + struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu); + trace_kvm_book3s_mmu_invalidate(pte); /* Different for 32 and 64 bit */ kvmppc_mmu_invalidate_pte(vcpu, pte); - spin_lock(&vcpu->arch.mmu_lock); + spin_lock(&vcpu3s->mmu_lock); /* pte already invalidated in between? */ if (hlist_unhashed(&pte->list_pte)) { - spin_unlock(&vcpu->arch.mmu_lock); + spin_unlock(&vcpu3s->mmu_lock); return; } @@ -115,14 +119,15 @@ static void invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte) else kvm_release_pfn_clean(pte->pfn); - spin_unlock(&vcpu->arch.mmu_lock); + spin_unlock(&vcpu3s->mmu_lock); - vcpu->arch.hpte_cache_count--; + vcpu3s->hpte_cache_count--; call_rcu(&pte->rcu_head, free_pte_rcu); } static void kvmppc_mmu_pte_flush_all(struct kvm_vcpu *vcpu) { + struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu); struct hpte_cache *pte; struct hlist_node *node; int i; @@ -130,7 +135,7 @@ static void kvmppc_mmu_pte_flush_all(struct kvm_vcpu *vcpu) rcu_read_lock(); for (i = 0; i < HPTEG_HASH_NUM_VPTE_LONG; i++) { - struct hlist_head *list = &vcpu->arch.hpte_hash_vpte_long[i]; + struct hlist_head *list = &vcpu3s->hpte_hash_vpte_long[i]; hlist_for_each_entry_rcu(pte, node, list, list_vpte_long) invalidate_pte(vcpu, pte); @@ -141,12 +146,13 @@ static void kvmppc_mmu_pte_flush_all(struct kvm_vcpu *vcpu) static void kvmppc_mmu_pte_flush_page(struct kvm_vcpu *vcpu, ulong guest_ea) { + struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu); struct hlist_head *list; struct hlist_node *node; struct hpte_cache *pte; /* Find the list of entries in the map */ - list = &vcpu->arch.hpte_hash_pte[kvmppc_mmu_hash_pte(guest_ea)]; + list = &vcpu3s->hpte_hash_pte[kvmppc_mmu_hash_pte(guest_ea)]; rcu_read_lock(); @@ -160,12 +166,13 @@ static void kvmppc_mmu_pte_flush_page(struct kvm_vcpu *vcpu, ulong guest_ea) static void kvmppc_mmu_pte_flush_long(struct kvm_vcpu *vcpu, ulong guest_ea) { + struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu); struct hlist_head *list; struct hlist_node *node; struct hpte_cache *pte; /* Find the list of entries in the map */ - list = &vcpu->arch.hpte_hash_pte_long[ + list = &vcpu3s->hpte_hash_pte_long[ kvmppc_mmu_hash_pte_long(guest_ea)]; rcu_read_lock(); @@ -203,12 +210,13 @@ void kvmppc_mmu_pte_flush(struct kvm_vcpu *vcpu, ulong guest_ea, ulong ea_mask) /* Flush with mask 0xfffffffff */ static void kvmppc_mmu_pte_vflush_short(struct kvm_vcpu *vcpu, u64 guest_vp) { + struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu); struct hlist_head *list; struct hlist_node *node; struct hpte_cache *pte; u64 vp_mask = 0xfffffffffULL; - list = &vcpu->arch.hpte_hash_vpte[kvmppc_mmu_hash_vpte(guest_vp)]; + list = &vcpu3s->hpte_hash_vpte[kvmppc_mmu_hash_vpte(guest_vp)]; rcu_read_lock(); @@ -223,12 +231,13 @@ static void kvmppc_mmu_pte_vflush_short(struct kvm_vcpu *vcpu, u64 guest_vp) /* Flush with mask 0xffffff000 */ static void kvmppc_mmu_pte_vflush_long(struct kvm_vcpu *vcpu, u64 guest_vp) { + struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu); struct hlist_head *list; struct hlist_node *node; struct hpte_cache *pte; u64 vp_mask = 0xffffff000ULL; - list = &vcpu->arch.hpte_hash_vpte_long[ + list = &vcpu3s->hpte_hash_vpte_long[ kvmppc_mmu_hash_vpte_long(guest_vp)]; rcu_read_lock(); @@ -261,6 +270,7 @@ void kvmppc_mmu_pte_vflush(struct kvm_vcpu *vcpu, u64 guest_vp, u64 vp_mask) void kvmppc_mmu_pte_pflush(struct kvm_vcpu *vcpu, ulong pa_start, ulong pa_end) { + struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu); struct hlist_node *node; struct hpte_cache *pte; int i; @@ -270,7 +280,7 @@ void kvmppc_mmu_pte_pflush(struct kvm_vcpu *vcpu, ulong pa_start, ulong pa_end) rcu_read_lock(); for (i = 0; i < HPTEG_HASH_NUM_VPTE_LONG; i++) { - struct hlist_head *list = &vcpu->arch.hpte_hash_vpte_long[i]; + struct hlist_head *list = &vcpu3s->hpte_hash_vpte_long[i]; hlist_for_each_entry_rcu(pte, node, list, list_vpte_long) if ((pte->pte.raddr >= pa_start) && @@ -283,12 +293,13 @@ void kvmppc_mmu_pte_pflush(struct kvm_vcpu *vcpu, ulong pa_start, ulong pa_end) struct hpte_cache *kvmppc_mmu_hpte_cache_next(struct kvm_vcpu *vcpu) { + struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu); struct hpte_cache *pte; pte = kmem_cache_zalloc(hpte_cache, GFP_KERNEL); - vcpu->arch.hpte_cache_count++; + vcpu3s->hpte_cache_count++; - if (vcpu->arch.hpte_cache_count == HPTEG_CACHE_NUM) + if (vcpu3s->hpte_cache_count == HPTEG_CACHE_NUM) kvmppc_mmu_pte_flush_all(vcpu); return pte; @@ -309,17 +320,19 @@ static void kvmppc_mmu_hpte_init_hash(struct hlist_head *hash_list, int len) int kvmppc_mmu_hpte_init(struct kvm_vcpu *vcpu) { + struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu); + /* init hpte lookup hashes */ - kvmppc_mmu_hpte_init_hash(vcpu->arch.hpte_hash_pte, - ARRAY_SIZE(vcpu->arch.hpte_hash_pte)); - kvmppc_mmu_hpte_init_hash(vcpu->arch.hpte_hash_pte_long, - ARRAY_SIZE(vcpu->arch.hpte_hash_pte_long)); - kvmppc_mmu_hpte_init_hash(vcpu->arch.hpte_hash_vpte, - ARRAY_SIZE(vcpu->arch.hpte_hash_vpte)); - kvmppc_mmu_hpte_init_hash(vcpu->arch.hpte_hash_vpte_long, - ARRAY_SIZE(vcpu->arch.hpte_hash_vpte_long)); - - spin_lock_init(&vcpu->arch.mmu_lock); + kvmppc_mmu_hpte_init_hash(vcpu3s->hpte_hash_pte, + ARRAY_SIZE(vcpu3s->hpte_hash_pte)); + kvmppc_mmu_hpte_init_hash(vcpu3s->hpte_hash_pte_long, + ARRAY_SIZE(vcpu3s->hpte_hash_pte_long)); + kvmppc_mmu_hpte_init_hash(vcpu3s->hpte_hash_vpte, + ARRAY_SIZE(vcpu3s->hpte_hash_vpte)); + kvmppc_mmu_hpte_init_hash(vcpu3s->hpte_hash_vpte_long, + ARRAY_SIZE(vcpu3s->hpte_hash_vpte_long)); + + spin_lock_init(&vcpu3s->mmu_lock); return 0; } diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c new file mode 100644 index 00000000000..0c0d3f27443 --- /dev/null +++ b/arch/powerpc/kvm/book3s_pr.c @@ -0,0 +1,1029 @@ +/* + * Copyright (C) 2009. SUSE Linux Products GmbH. All rights reserved. + * + * Authors: + * Alexander Graf <agraf@suse.de> + * Kevin Wolf <mail@kevin-wolf.de> + * Paul Mackerras <paulus@samba.org> + * + * Description: + * Functions relating to running KVM on Book 3S processors where + * we don't have access to hypervisor mode, and we run the guest + * in problem state (user mode). + * + * This file is derived from arch/powerpc/kvm/44x.c, + * by Hollis Blanchard <hollisb@us.ibm.com>. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + */ + +#include <linux/kvm_host.h> +#include <linux/err.h> +#include <linux/slab.h> + +#include <asm/reg.h> +#include <asm/cputable.h> +#include <asm/cacheflush.h> +#include <asm/tlbflush.h> +#include <asm/uaccess.h> +#include <asm/io.h> +#include <asm/kvm_ppc.h> +#include <asm/kvm_book3s.h> +#include <asm/mmu_context.h> +#include <linux/gfp.h> +#include <linux/sched.h> +#include <linux/vmalloc.h> +#include <linux/highmem.h> + +#include "trace.h" + +/* #define EXIT_DEBUG */ +/* #define DEBUG_EXT */ + +static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr, + ulong msr); + +/* Some compatibility defines */ +#ifdef CONFIG_PPC_BOOK3S_32 +#define MSR_USER32 MSR_USER +#define MSR_USER64 MSR_USER +#define HW_PAGE_SIZE PAGE_SIZE +#endif + +void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu) +{ +#ifdef CONFIG_PPC_BOOK3S_64 + memcpy(to_svcpu(vcpu)->slb, to_book3s(vcpu)->slb_shadow, sizeof(to_svcpu(vcpu)->slb)); + memcpy(&get_paca()->shadow_vcpu, to_book3s(vcpu)->shadow_vcpu, + sizeof(get_paca()->shadow_vcpu)); + to_svcpu(vcpu)->slb_max = to_book3s(vcpu)->slb_shadow_max; +#endif + +#ifdef CONFIG_PPC_BOOK3S_32 + current->thread.kvm_shadow_vcpu = to_book3s(vcpu)->shadow_vcpu; +#endif +} + +void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu) +{ +#ifdef CONFIG_PPC_BOOK3S_64 + memcpy(to_book3s(vcpu)->slb_shadow, to_svcpu(vcpu)->slb, sizeof(to_svcpu(vcpu)->slb)); + memcpy(to_book3s(vcpu)->shadow_vcpu, &get_paca()->shadow_vcpu, + sizeof(get_paca()->shadow_vcpu)); + to_book3s(vcpu)->slb_shadow_max = to_svcpu(vcpu)->slb_max; +#endif + + kvmppc_giveup_ext(vcpu, MSR_FP); + kvmppc_giveup_ext(vcpu, MSR_VEC); + kvmppc_giveup_ext(vcpu, MSR_VSX); +} + +static void kvmppc_recalc_shadow_msr(struct kvm_vcpu *vcpu) +{ + ulong smsr = vcpu->arch.shared->msr; + + /* Guest MSR values */ + smsr &= MSR_FE0 | MSR_FE1 | MSR_SF | MSR_SE | MSR_BE | MSR_DE; + /* Process MSR values */ + smsr |= MSR_ME | MSR_RI | MSR_IR | MSR_DR | MSR_PR | MSR_EE; + /* External providers the guest reserved */ + smsr |= (vcpu->arch.shared->msr & vcpu->arch.guest_owned_ext); + /* 64-bit Process MSR values */ +#ifdef CONFIG_PPC_BOOK3S_64 + smsr |= MSR_ISF | MSR_HV; +#endif + vcpu->arch.shadow_msr = smsr; +} + +void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr) +{ + ulong old_msr = vcpu->arch.shared->msr; + +#ifdef EXIT_DEBUG + printk(KERN_INFO "KVM: Set MSR to 0x%llx\n", msr); +#endif + + msr &= to_book3s(vcpu)->msr_mask; + vcpu->arch.shared->msr = msr; + kvmppc_recalc_shadow_msr(vcpu); + + if (msr & MSR_POW) { + if (!vcpu->arch.pending_exceptions) { + kvm_vcpu_block(vcpu); + vcpu->stat.halt_wakeup++; + + /* Unset POW bit after we woke up */ + msr &= ~MSR_POW; + vcpu->arch.shared->msr = msr; + } + } + + if ((vcpu->arch.shared->msr & (MSR_PR|MSR_IR|MSR_DR)) != + (old_msr & (MSR_PR|MSR_IR|MSR_DR))) { + kvmppc_mmu_flush_segments(vcpu); + kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu)); + + /* Preload magic page segment when in kernel mode */ + if (!(msr & MSR_PR) && vcpu->arch.magic_page_pa) { + struct kvm_vcpu_arch *a = &vcpu->arch; + + if (msr & MSR_DR) + kvmppc_mmu_map_segment(vcpu, a->magic_page_ea); + else + kvmppc_mmu_map_segment(vcpu, a->magic_page_pa); + } + } + + /* Preload FPU if it's enabled */ + if (vcpu->arch.shared->msr & MSR_FP) + kvmppc_handle_ext(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL, MSR_FP); +} + +void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr) +{ + u32 host_pvr; + + vcpu->arch.hflags &= ~BOOK3S_HFLAG_SLB; + vcpu->arch.pvr = pvr; +#ifdef CONFIG_PPC_BOOK3S_64 + if ((pvr >= 0x330000) && (pvr < 0x70330000)) { + kvmppc_mmu_book3s_64_init(vcpu); + to_book3s(vcpu)->hior = 0xfff00000; + to_book3s(vcpu)->msr_mask = 0xffffffffffffffffULL; + } else +#endif + { + kvmppc_mmu_book3s_32_init(vcpu); + to_book3s(vcpu)->hior = 0; + to_book3s(vcpu)->msr_mask = 0xffffffffULL; + } + + /* If we are in hypervisor level on 970, we can tell the CPU to + * treat DCBZ as 32 bytes store */ + vcpu->arch.hflags &= ~BOOK3S_HFLAG_DCBZ32; + if (vcpu->arch.mmu.is_dcbz32(vcpu) && (mfmsr() & MSR_HV) && + !strcmp(cur_cpu_spec->platform, "ppc970")) + vcpu->arch.hflags |= BOOK3S_HFLAG_DCBZ32; + + /* Cell performs badly if MSR_FEx are set. So let's hope nobody + really needs them in a VM on Cell and force disable them. */ + if (!strcmp(cur_cpu_spec->platform, "ppc-cell-be")) + to_book3s(vcpu)->msr_mask &= ~(MSR_FE0 | MSR_FE1); + +#ifdef CONFIG_PPC_BOOK3S_32 + /* 32 bit Book3S always has 32 byte dcbz */ + vcpu->arch.hflags |= BOOK3S_HFLAG_DCBZ32; +#endif + + /* On some CPUs we can execute paired single operations natively */ + asm ( "mfpvr %0" : "=r"(host_pvr)); + switch (host_pvr) { + case 0x00080200: /* lonestar 2.0 */ + case 0x00088202: /* lonestar 2.2 */ + case 0x70000100: /* gekko 1.0 */ + case 0x00080100: /* gekko 2.0 */ + case 0x00083203: /* gekko 2.3a */ + case 0x00083213: /* gekko 2.3b */ + case 0x00083204: /* gekko 2.4 */ + case 0x00083214: /* gekko 2.4e (8SE) - retail HW2 */ + case 0x00087200: /* broadway */ + vcpu->arch.hflags |= BOOK3S_HFLAG_NATIVE_PS; + /* Enable HID2.PSE - in case we need it later */ + mtspr(SPRN_HID2_GEKKO, mfspr(SPRN_HID2_GEKKO) | (1 << 29)); + } +} + +/* Book3s_32 CPUs always have 32 bytes cache line size, which Linux assumes. To + * make Book3s_32 Linux work on Book3s_64, we have to make sure we trap dcbz to + * emulate 32 bytes dcbz length. + * + * The Book3s_64 inventors also realized this case and implemented a special bit + * in the HID5 register, which is a hypervisor ressource. Thus we can't use it. + * + * My approach here is to patch the dcbz instruction on executing pages. + */ +static void kvmppc_patch_dcbz(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte) +{ + struct page *hpage; + u64 hpage_offset; + u32 *page; + int i; + + hpage = gfn_to_page(vcpu->kvm, pte->raddr >> PAGE_SHIFT); + if (is_error_page(hpage)) { + kvm_release_page_clean(hpage); + return; + } + + hpage_offset = pte->raddr & ~PAGE_MASK; + hpage_offset &= ~0xFFFULL; + hpage_offset /= 4; + + get_page(hpage); + page = kmap_atomic(hpage, KM_USER0); + + /* patch dcbz into reserved instruction, so we trap */ + for (i=hpage_offset; i < hpage_offset + (HW_PAGE_SIZE / 4); i++) + if ((page[i] & 0xff0007ff) == INS_DCBZ) + page[i] &= 0xfffffff7; + + kunmap_atomic(page, KM_USER0); + put_page(hpage); +} + +static int kvmppc_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn) +{ + ulong mp_pa = vcpu->arch.magic_page_pa; + + if (unlikely(mp_pa) && + unlikely((mp_pa & KVM_PAM) >> PAGE_SHIFT == gfn)) { + return 1; + } + + return kvm_is_visible_gfn(vcpu->kvm, gfn); +} + +int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu, + ulong eaddr, int vec) +{ + bool data = (vec == BOOK3S_INTERRUPT_DATA_STORAGE); + int r = RESUME_GUEST; + int relocated; + int page_found = 0; + struct kvmppc_pte pte; + bool is_mmio = false; + bool dr = (vcpu->arch.shared->msr & MSR_DR) ? true : false; + bool ir = (vcpu->arch.shared->msr & MSR_IR) ? true : false; + u64 vsid; + + relocated = data ? dr : ir; + + /* Resolve real address if translation turned on */ + if (relocated) { + page_found = vcpu->arch.mmu.xlate(vcpu, eaddr, &pte, data); + } else { + pte.may_execute = true; + pte.may_read = true; + pte.may_write = true; + pte.raddr = eaddr & KVM_PAM; + pte.eaddr = eaddr; + pte.vpage = eaddr >> 12; + } + + switch (vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) { + case 0: + pte.vpage |= ((u64)VSID_REAL << (SID_SHIFT - 12)); + break; + case MSR_DR: + case MSR_IR: + vcpu->arch.mmu.esid_to_vsid(vcpu, eaddr >> SID_SHIFT, &vsid); + + if ((vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) == MSR_DR) + pte.vpage |= ((u64)VSID_REAL_DR << (SID_SHIFT - 12)); + else + pte.vpage |= ((u64)VSID_REAL_IR << (SID_SHIFT - 12)); + pte.vpage |= vsid; + + if (vsid == -1) + page_found = -EINVAL; + break; + } + + if (vcpu->arch.mmu.is_dcbz32(vcpu) && + (!(vcpu->arch.hflags & BOOK3S_HFLAG_DCBZ32))) { + /* + * If we do the dcbz hack, we have to NX on every execution, + * so we can patch the executing code. This renders our guest + * NX-less. + */ + pte.may_execute = !data; + } + + if (page_found == -ENOENT) { + /* Page not found in guest PTE entries */ + vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu); + vcpu->arch.shared->dsisr = to_svcpu(vcpu)->fault_dsisr; + vcpu->arch.shared->msr |= + (to_svcpu(vcpu)->shadow_srr1 & 0x00000000f8000000ULL); + kvmppc_book3s_queue_irqprio(vcpu, vec); + } else if (page_found == -EPERM) { + /* Storage protection */ + vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu); + vcpu->arch.shared->dsisr = + to_svcpu(vcpu)->fault_dsisr & ~DSISR_NOHPTE; + vcpu->arch.shared->dsisr |= DSISR_PROTFAULT; + vcpu->arch.shared->msr |= + (to_svcpu(vcpu)->shadow_srr1 & 0x00000000f8000000ULL); + kvmppc_book3s_queue_irqprio(vcpu, vec); + } else if (page_found == -EINVAL) { + /* Page not found in guest SLB */ + vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu); + kvmppc_book3s_queue_irqprio(vcpu, vec + 0x80); + } else if (!is_mmio && + kvmppc_visible_gfn(vcpu, pte.raddr >> PAGE_SHIFT)) { + /* The guest's PTE is not mapped yet. Map on the host */ + kvmppc_mmu_map_page(vcpu, &pte); + if (data) + vcpu->stat.sp_storage++; + else if (vcpu->arch.mmu.is_dcbz32(vcpu) && + (!(vcpu->arch.hflags & BOOK3S_HFLAG_DCBZ32))) + kvmppc_patch_dcbz(vcpu, &pte); + } else { + /* MMIO */ + vcpu->stat.mmio_exits++; + vcpu->arch.paddr_accessed = pte.raddr; + r = kvmppc_emulate_mmio(run, vcpu); + if ( r == RESUME_HOST_NV ) + r = RESUME_HOST; + } + + 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) */ +void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr) +{ + struct thread_struct *t = ¤t->thread; + u64 *vcpu_fpr = vcpu->arch.fpr; +#ifdef CONFIG_VSX + u64 *vcpu_vsx = vcpu->arch.vsr; +#endif + 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); +} + +static int kvmppc_read_inst(struct kvm_vcpu *vcpu) +{ + ulong srr0 = kvmppc_get_pc(vcpu); + u32 last_inst = kvmppc_get_last_inst(vcpu); + int ret; + + ret = kvmppc_ld(vcpu, &srr0, sizeof(u32), &last_inst, false); + if (ret == -ENOENT) { + ulong msr = vcpu->arch.shared->msr; + + msr = kvmppc_set_field(msr, 33, 33, 1); + msr = kvmppc_set_field(msr, 34, 36, 0); + vcpu->arch.shared->msr = kvmppc_set_field(msr, 42, 47, 0); + kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_INST_STORAGE); + return EMULATE_AGAIN; + } + + return EMULATE_DONE; +} + +static int kvmppc_check_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr) +{ + + /* Need to do paired single emulation? */ + if (!(vcpu->arch.hflags & BOOK3S_HFLAG_PAIRED_SINGLE)) + return EMULATE_DONE; + + /* Read out the instruction */ + if (kvmppc_read_inst(vcpu) == EMULATE_DONE) + /* Need to emulate */ + return EMULATE_FAIL; + + return EMULATE_AGAIN; +} + +/* 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; +#ifdef CONFIG_VSX + u64 *vcpu_vsx = vcpu->arch.vsr; +#endif + u64 *thread_fpr = (u64*)t->fpr; + int i; + + /* When we have paired singles, we emulate in software */ + if (vcpu->arch.hflags & BOOK3S_HFLAG_PAIRED_SINGLE) + return RESUME_GUEST; + + if (!(vcpu->arch.shared->msr & msr)) { + kvmppc_book3s_queue_irqprio(vcpu, exit_nr); + return RESUME_GUEST; + } + + /* We already own the ext */ + if (vcpu->arch.guest_owned_ext & msr) { + 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) +{ + int r = RESUME_HOST; + + vcpu->stat.sum_exits++; + + run->exit_reason = KVM_EXIT_UNKNOWN; + run->ready_for_interrupt_injection = 1; + + trace_kvm_book3s_exit(exit_nr, vcpu); + kvm_resched(vcpu); + switch (exit_nr) { + case BOOK3S_INTERRUPT_INST_STORAGE: + vcpu->stat.pf_instruc++; + +#ifdef CONFIG_PPC_BOOK3S_32 + /* We set segments as unused segments when invalidating them. So + * treat the respective fault as segment fault. */ + if (to_svcpu(vcpu)->sr[kvmppc_get_pc(vcpu) >> SID_SHIFT] + == SR_INVALID) { + kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu)); + r = RESUME_GUEST; + break; + } +#endif + + /* only care about PTEG not found errors, but leave NX alone */ + if (to_svcpu(vcpu)->shadow_srr1 & 0x40000000) { + r = kvmppc_handle_pagefault(run, vcpu, kvmppc_get_pc(vcpu), exit_nr); + vcpu->stat.sp_instruc++; + } else if (vcpu->arch.mmu.is_dcbz32(vcpu) && + (!(vcpu->arch.hflags & BOOK3S_HFLAG_DCBZ32))) { + /* + * XXX If we do the dcbz hack we use the NX bit to flush&patch the page, + * so we can't use the NX bit inside the guest. Let's cross our fingers, + * that no guest that needs the dcbz hack does NX. + */ + kvmppc_mmu_pte_flush(vcpu, kvmppc_get_pc(vcpu), ~0xFFFUL); + r = RESUME_GUEST; + } else { + vcpu->arch.shared->msr |= + to_svcpu(vcpu)->shadow_srr1 & 0x58000000; + kvmppc_book3s_queue_irqprio(vcpu, exit_nr); + r = RESUME_GUEST; + } + break; + case BOOK3S_INTERRUPT_DATA_STORAGE: + { + ulong dar = kvmppc_get_fault_dar(vcpu); + vcpu->stat.pf_storage++; + +#ifdef CONFIG_PPC_BOOK3S_32 + /* We set segments as unused segments when invalidating them. So + * treat the respective fault as segment fault. */ + if ((to_svcpu(vcpu)->sr[dar >> SID_SHIFT]) == SR_INVALID) { + kvmppc_mmu_map_segment(vcpu, dar); + r = RESUME_GUEST; + break; + } +#endif + + /* The only case we need to handle is missing shadow PTEs */ + if (to_svcpu(vcpu)->fault_dsisr & DSISR_NOHPTE) { + r = kvmppc_handle_pagefault(run, vcpu, dar, exit_nr); + } else { + vcpu->arch.shared->dar = dar; + vcpu->arch.shared->dsisr = to_svcpu(vcpu)->fault_dsisr; + kvmppc_book3s_queue_irqprio(vcpu, exit_nr); + r = RESUME_GUEST; + } + break; + } + case BOOK3S_INTERRUPT_DATA_SEGMENT: + if (kvmppc_mmu_map_segment(vcpu, kvmppc_get_fault_dar(vcpu)) < 0) { + vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu); + kvmppc_book3s_queue_irqprio(vcpu, + BOOK3S_INTERRUPT_DATA_SEGMENT); + } + r = RESUME_GUEST; + break; + case BOOK3S_INTERRUPT_INST_SEGMENT: + if (kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu)) < 0) { + kvmppc_book3s_queue_irqprio(vcpu, + BOOK3S_INTERRUPT_INST_SEGMENT); + } + r = RESUME_GUEST; + break; + /* We're good on these - the host merely wanted to get our attention */ + case BOOK3S_INTERRUPT_DECREMENTER: + vcpu->stat.dec_exits++; + r = RESUME_GUEST; + break; + case BOOK3S_INTERRUPT_EXTERNAL: + vcpu->stat.ext_intr_exits++; + r = RESUME_GUEST; + break; + case BOOK3S_INTERRUPT_PERFMON: + r = RESUME_GUEST; + break; + case BOOK3S_INTERRUPT_PROGRAM: + { + enum emulation_result er; + ulong flags; + +program_interrupt: + flags = to_svcpu(vcpu)->shadow_srr1 & 0x1f0000ull; + + if (vcpu->arch.shared->msr & MSR_PR) { +#ifdef EXIT_DEBUG + printk(KERN_INFO "Userspace triggered 0x700 exception at 0x%lx (0x%x)\n", kvmppc_get_pc(vcpu), kvmppc_get_last_inst(vcpu)); +#endif + if ((kvmppc_get_last_inst(vcpu) & 0xff0007ff) != + (INS_DCBZ & 0xfffffff7)) { + kvmppc_core_queue_program(vcpu, flags); + r = RESUME_GUEST; + break; + } + } + + vcpu->stat.emulated_inst_exits++; + er = kvmppc_emulate_instruction(run, vcpu); + switch (er) { + case EMULATE_DONE: + r = RESUME_GUEST_NV; + break; + case EMULATE_AGAIN: + r = RESUME_GUEST; + break; + case EMULATE_FAIL: + printk(KERN_CRIT "%s: emulation at %lx failed (%08x)\n", + __func__, kvmppc_get_pc(vcpu), kvmppc_get_last_inst(vcpu)); + kvmppc_core_queue_program(vcpu, flags); + r = RESUME_GUEST; + break; + case EMULATE_DO_MMIO: + run->exit_reason = KVM_EXIT_MMIO; + r = RESUME_HOST_NV; + break; + default: + BUG(); + } + break; + } + case BOOK3S_INTERRUPT_SYSCALL: + if (vcpu->arch.osi_enabled && + (((u32)kvmppc_get_gpr(vcpu, 3)) == OSI_SC_MAGIC_R3) && + (((u32)kvmppc_get_gpr(vcpu, 4)) == OSI_SC_MAGIC_R4)) { + /* MOL hypercalls */ + u64 *gprs = run->osi.gprs; + int i; + + run->exit_reason = KVM_EXIT_OSI; + for (i = 0; i < 32; i++) + gprs[i] = kvmppc_get_gpr(vcpu, i); + vcpu->arch.osi_needed = 1; + r = RESUME_HOST_NV; + } else if (!(vcpu->arch.shared->msr & MSR_PR) && + (((u32)kvmppc_get_gpr(vcpu, 0)) == KVM_SC_MAGIC_R0)) { + /* KVM PV hypercalls */ + kvmppc_set_gpr(vcpu, 3, kvmppc_kvm_pv(vcpu)); + r = RESUME_GUEST; + } else { + /* Guest syscalls */ + vcpu->stat.syscall_exits++; + kvmppc_book3s_queue_irqprio(vcpu, exit_nr); + r = RESUME_GUEST; + } + break; + case BOOK3S_INTERRUPT_FP_UNAVAIL: + case BOOK3S_INTERRUPT_ALTIVEC: + case BOOK3S_INTERRUPT_VSX: + { + int ext_msr = 0; + + switch (exit_nr) { + case BOOK3S_INTERRUPT_FP_UNAVAIL: ext_msr = MSR_FP; break; + case BOOK3S_INTERRUPT_ALTIVEC: ext_msr = MSR_VEC; break; + case BOOK3S_INTERRUPT_VSX: ext_msr = MSR_VSX; break; + } + + switch (kvmppc_check_ext(vcpu, exit_nr)) { + case EMULATE_DONE: + /* everything ok - let's enable the ext */ + r = kvmppc_handle_ext(vcpu, exit_nr, ext_msr); + break; + case EMULATE_FAIL: + /* we need to emulate this instruction */ + goto program_interrupt; + break; + default: + /* nothing to worry about - go again */ + break; + } + break; + } + case BOOK3S_INTERRUPT_ALIGNMENT: + if (kvmppc_read_inst(vcpu) == EMULATE_DONE) { + vcpu->arch.shared->dsisr = kvmppc_alignment_dsisr(vcpu, + kvmppc_get_last_inst(vcpu)); + vcpu->arch.shared->dar = kvmppc_alignment_dar(vcpu, + kvmppc_get_last_inst(vcpu)); + kvmppc_book3s_queue_irqprio(vcpu, exit_nr); + } + r = RESUME_GUEST; + 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, kvmppc_get_pc(vcpu), to_svcpu(vcpu)->shadow_srr1); + r = RESUME_HOST; + BUG(); + break; + } + + + if (!(r & RESUME_HOST)) { + /* To avoid clobbering exit_reason, only check for signals if + * we aren't already exiting to userspace for some other + * reason. */ + if (signal_pending(current)) { +#ifdef EXIT_DEBUG + printk(KERN_EMERG "KVM: Going back to host\n"); +#endif + vcpu->stat.signal_exits++; + run->exit_reason = KVM_EXIT_INTR; + r = -EINTR; + } else { + /* In case an interrupt came in that was triggered + * from userspace (like DEC), we need to check what + * to inject now! */ + kvmppc_core_deliver_interrupts(vcpu); + } + } + + trace_kvm_book3s_reenter(r, vcpu); + + return r; +} + +int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, + struct kvm_sregs *sregs) +{ + struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu); + int i; + + sregs->pvr = vcpu->arch.pvr; + + sregs->u.s.sdr1 = to_book3s(vcpu)->sdr1; + if (vcpu->arch.hflags & BOOK3S_HFLAG_SLB) { + for (i = 0; i < 64; i++) { + sregs->u.s.ppc64.slb[i].slbe = vcpu->arch.slb[i].orige | i; + sregs->u.s.ppc64.slb[i].slbv = vcpu->arch.slb[i].origv; + } + } else { + for (i = 0; i < 16; i++) + sregs->u.s.ppc32.sr[i] = vcpu->arch.shared->sr[i]; + + for (i = 0; i < 8; i++) { + sregs->u.s.ppc32.ibat[i] = vcpu3s->ibat[i].raw; + sregs->u.s.ppc32.dbat[i] = vcpu3s->dbat[i].raw; + } + } + + return 0; +} + +int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, + struct kvm_sregs *sregs) +{ + struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu); + int i; + + kvmppc_set_pvr(vcpu, sregs->pvr); + + vcpu3s->sdr1 = sregs->u.s.sdr1; + if (vcpu->arch.hflags & BOOK3S_HFLAG_SLB) { + for (i = 0; i < 64; i++) { + vcpu->arch.mmu.slbmte(vcpu, sregs->u.s.ppc64.slb[i].slbv, + sregs->u.s.ppc64.slb[i].slbe); + } + } else { + for (i = 0; i < 16; i++) { + vcpu->arch.mmu.mtsrin(vcpu, i, sregs->u.s.ppc32.sr[i]); + } + for (i = 0; i < 8; i++) { + kvmppc_set_bat(vcpu, &(vcpu3s->ibat[i]), false, + (u32)sregs->u.s.ppc32.ibat[i]); + kvmppc_set_bat(vcpu, &(vcpu3s->ibat[i]), true, + (u32)(sregs->u.s.ppc32.ibat[i] >> 32)); + kvmppc_set_bat(vcpu, &(vcpu3s->dbat[i]), false, + (u32)sregs->u.s.ppc32.dbat[i]); + kvmppc_set_bat(vcpu, &(vcpu3s->dbat[i]), true, + (u32)(sregs->u.s.ppc32.dbat[i] >> 32)); + } + } + + /* Flush the MMU after messing with the segments */ + kvmppc_mmu_pte_flush(vcpu, 0, 0); + + return 0; +} + +int kvmppc_core_check_processor_compat(void) +{ + return 0; +} + +struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id) +{ + struct kvmppc_vcpu_book3s *vcpu_book3s; + struct kvm_vcpu *vcpu; + int err = -ENOMEM; + unsigned long p; + + vcpu_book3s = vzalloc(sizeof(struct kvmppc_vcpu_book3s)); + if (!vcpu_book3s) + goto out; + + vcpu_book3s->shadow_vcpu = (struct kvmppc_book3s_shadow_vcpu *) + kzalloc(sizeof(*vcpu_book3s->shadow_vcpu), GFP_KERNEL); + if (!vcpu_book3s->shadow_vcpu) + goto free_vcpu; + + vcpu = &vcpu_book3s->vcpu; + err = kvm_vcpu_init(vcpu, kvm, id); + if (err) + goto free_shadow_vcpu; + + p = __get_free_page(GFP_KERNEL|__GFP_ZERO); + /* the real shared page fills the last 4k of our page */ + vcpu->arch.shared = (void*)(p + PAGE_SIZE - 4096); + if (!p) + goto uninit_vcpu; + + vcpu->arch.host_retip = kvm_return_point; + vcpu->arch.host_msr = mfmsr(); +#ifdef CONFIG_PPC_BOOK3S_64 + /* default to book3s_64 (970fx) */ + vcpu->arch.pvr = 0x3C0301; +#else + /* default to book3s_32 (750) */ + vcpu->arch.pvr = 0x84202; +#endif + kvmppc_set_pvr(vcpu, vcpu->arch.pvr); + vcpu->arch.slb_nr = 64; + + /* remember where some real-mode handlers are */ + vcpu->arch.trampoline_lowmem = __pa(kvmppc_handler_lowmem_trampoline); + vcpu->arch.trampoline_enter = __pa(kvmppc_handler_trampoline_enter); + vcpu->arch.highmem_handler = (ulong)kvmppc_handler_highmem; +#ifdef CONFIG_PPC_BOOK3S_64 + vcpu->arch.rmcall = *(ulong*)kvmppc_rmcall; +#else + vcpu->arch.rmcall = (ulong)kvmppc_rmcall; +#endif + + vcpu->arch.shadow_msr = MSR_USER64; + + err = kvmppc_mmu_init(vcpu); + if (err < 0) + goto uninit_vcpu; + + return vcpu; + +uninit_vcpu: + kvm_vcpu_uninit(vcpu); +free_shadow_vcpu: + kfree(vcpu_book3s->shadow_vcpu); +free_vcpu: + vfree(vcpu_book3s); +out: + return ERR_PTR(err); +} + +void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu) +{ + struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu); + + free_page((unsigned long)vcpu->arch.shared & PAGE_MASK); + kvm_vcpu_uninit(vcpu); + kfree(vcpu_book3s->shadow_vcpu); + vfree(vcpu_book3s); +} + +int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) +{ + int ret; + double fpr[32][TS_FPRWIDTH]; + unsigned int fpscr; + int fpexc_mode; +#ifdef CONFIG_ALTIVEC + vector128 vr[32]; + vector128 vscr; + unsigned long uninitialized_var(vrsave); + int used_vr; +#endif +#ifdef CONFIG_VSX + int used_vsr; +#endif + ulong ext_msr; + + /* No need to go into the guest when all we do is going out */ + if (signal_pending(current)) { + kvm_run->exit_reason = KVM_EXIT_INTR; + return -EINTR; + } + + /* Save FPU state in stack */ + if (current->thread.regs->msr & MSR_FP) + giveup_fpu(current); + memcpy(fpr, current->thread.fpr, sizeof(current->thread.fpr)); + fpscr = current->thread.fpscr.val; + fpexc_mode = current->thread.fpexc_mode; + +#ifdef CONFIG_ALTIVEC + /* Save Altivec state in stack */ + used_vr = current->thread.used_vr; + if (used_vr) { + if (current->thread.regs->msr & MSR_VEC) + giveup_altivec(current); + memcpy(vr, current->thread.vr, sizeof(current->thread.vr)); + vscr = current->thread.vscr; + vrsave = current->thread.vrsave; + } +#endif + +#ifdef CONFIG_VSX + /* Save VSX state in stack */ + used_vsr = current->thread.used_vsr; + if (used_vsr && (current->thread.regs->msr & MSR_VSX)) + __giveup_vsx(current); +#endif + + /* Remember the MSR with disabled extensions */ + ext_msr = current->thread.regs->msr; + + /* Preload FPU if it's enabled */ + if (vcpu->arch.shared->msr & MSR_FP) + kvmppc_handle_ext(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL, MSR_FP); + + kvm_guest_enter(); + + ret = __kvmppc_vcpu_run(kvm_run, vcpu); + + kvm_guest_exit(); + + 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, fpr, sizeof(current->thread.fpr)); + current->thread.fpscr.val = fpscr; + current->thread.fpexc_mode = fpexc_mode; + +#ifdef CONFIG_ALTIVEC + /* Restore Altivec state from stack */ + if (used_vr && current->thread.used_vr) { + memcpy(current->thread.vr, vr, sizeof(current->thread.vr)); + current->thread.vscr = vscr; + current->thread.vrsave = vrsave; + } + current->thread.used_vr = used_vr; +#endif + +#ifdef CONFIG_VSX + current->thread.used_vsr = used_vsr; +#endif + + return ret; +} + +int kvmppc_core_prepare_memory_region(struct kvm *kvm, + struct kvm_userspace_memory_region *mem) +{ + return 0; +} + +void kvmppc_core_commit_memory_region(struct kvm *kvm, + struct kvm_userspace_memory_region *mem) +{ +} + +int kvmppc_core_init_vm(struct kvm *kvm) +{ + return 0; +} + +void kvmppc_core_destroy_vm(struct kvm *kvm) +{ +} + +static int kvmppc_book3s_init(void) +{ + int r; + + r = kvm_init(NULL, sizeof(struct kvmppc_vcpu_book3s), 0, + THIS_MODULE); + + if (r) + return r; + + r = kvmppc_mmu_hpte_sysinit(); + + return r; +} + +static void kvmppc_book3s_exit(void) +{ + kvmppc_mmu_hpte_sysexit(); + kvm_exit(); +} + +module_init(kvmppc_book3s_init); +module_exit(kvmppc_book3s_exit); diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S index 1a1b34487e7..c1f877c4a88 100644 --- a/arch/powerpc/kvm/book3s_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_rmhandlers.S @@ -36,41 +36,44 @@ #if defined(CONFIG_PPC_BOOK3S_64) #define LOAD_SHADOW_VCPU(reg) GET_PACA(reg) -#define SHADOW_VCPU_OFF PACA_KVM_SVCPU #define MSR_NOIRQ MSR_KERNEL & ~(MSR_IR | MSR_DR) #define FUNC(name) GLUE(.,name) +kvmppc_skip_interrupt: + /* + * Here all GPRs are unchanged from when the interrupt happened + * except for r13, which is saved in SPRG_SCRATCH0. + */ + mfspr r13, SPRN_SRR0 + addi r13, r13, 4 + mtspr SPRN_SRR0, r13 + GET_SCRATCH0(r13) + rfid + b . + +kvmppc_skip_Hinterrupt: + /* + * Here all GPRs are unchanged from when the interrupt happened + * except for r13, which is saved in SPRG_SCRATCH0. + */ + mfspr r13, SPRN_HSRR0 + addi r13, r13, 4 + mtspr SPRN_HSRR0, r13 + GET_SCRATCH0(r13) + hrfid + b . + #elif defined(CONFIG_PPC_BOOK3S_32) -#define LOAD_SHADOW_VCPU(reg) \ - mfspr reg, SPRN_SPRG_THREAD; \ - lwz reg, THREAD_KVM_SVCPU(reg); \ - /* PPC32 can have a NULL pointer - let's check for that */ \ - mtspr SPRN_SPRG_SCRATCH1, r12; /* Save r12 */ \ - mfcr r12; \ - cmpwi reg, 0; \ - bne 1f; \ - mfspr reg, SPRN_SPRG_SCRATCH0; \ - mtcr r12; \ - mfspr r12, SPRN_SPRG_SCRATCH1; \ - b kvmppc_resume_\intno; \ -1:; \ - mtcr r12; \ - mfspr r12, SPRN_SPRG_SCRATCH1; \ - tophys(reg, reg) - -#define SHADOW_VCPU_OFF 0 #define MSR_NOIRQ MSR_KERNEL #define FUNC(name) name -#endif - .macro INTERRUPT_TRAMPOLINE intno .global kvmppc_trampoline_\intno kvmppc_trampoline_\intno: - SET_SCRATCH0(r13) /* Save r13 */ + mtspr SPRN_SPRG_SCRATCH0, r13 /* Save r13 */ /* * First thing to do is to find out if we're coming @@ -78,19 +81,28 @@ kvmppc_trampoline_\intno: * * To distinguish, we check a magic byte in the PACA/current */ - LOAD_SHADOW_VCPU(r13) - PPC_STL r12, (SHADOW_VCPU_OFF + SVCPU_SCRATCH0)(r13) + mfspr r13, SPRN_SPRG_THREAD + lwz r13, THREAD_KVM_SVCPU(r13) + /* PPC32 can have a NULL pointer - let's check for that */ + mtspr SPRN_SPRG_SCRATCH1, r12 /* Save r12 */ mfcr r12 - stw r12, (SHADOW_VCPU_OFF + SVCPU_SCRATCH1)(r13) - lbz r12, (SHADOW_VCPU_OFF + SVCPU_IN_GUEST)(r13) + cmpwi r13, 0 + bne 1f +2: mtcr r12 + mfspr r12, SPRN_SPRG_SCRATCH1 + mfspr r13, SPRN_SPRG_SCRATCH0 /* r13 = original r13 */ + b kvmppc_resume_\intno /* Get back original handler */ + +1: tophys(r13, r13) + stw r12, HSTATE_SCRATCH1(r13) + mfspr r12, SPRN_SPRG_SCRATCH1 + stw r12, HSTATE_SCRATCH0(r13) + lbz r12, HSTATE_IN_GUEST(r13) cmpwi r12, KVM_GUEST_MODE_NONE bne ..kvmppc_handler_hasmagic_\intno /* No KVM guest? Then jump back to the Linux handler! */ - lwz r12, (SHADOW_VCPU_OFF + SVCPU_SCRATCH1)(r13) - mtcr r12 - PPC_LL r12, (SHADOW_VCPU_OFF + SVCPU_SCRATCH0)(r13) - GET_SCRATCH0(r13) /* r13 = original r13 */ - b kvmppc_resume_\intno /* Get back original handler */ + lwz r12, HSTATE_SCRATCH1(r13) + b 2b /* Now we know we're handling a KVM guest */ ..kvmppc_handler_hasmagic_\intno: @@ -112,9 +124,6 @@ INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_MACHINE_CHECK INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_DATA_STORAGE INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_INST_STORAGE INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_EXTERNAL -#ifdef CONFIG_PPC_BOOK3S_64 -INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_EXTERNAL_HV -#endif INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_ALIGNMENT INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_PROGRAM INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_FP_UNAVAIL @@ -124,14 +133,6 @@ INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_TRACE INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_PERFMON INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_ALTIVEC -/* Those are only available on 64 bit machines */ - -#ifdef CONFIG_PPC_BOOK3S_64 -INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_DATA_SEGMENT -INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_INST_SEGMENT -INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_VSX -#endif - /* * Bring us back to the faulting code, but skip the * faulting instruction. @@ -143,8 +144,8 @@ INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_VSX * * R12 = free * R13 = Shadow VCPU (PACA) - * SVCPU.SCRATCH0 = guest R12 - * SVCPU.SCRATCH1 = guest CR + * HSTATE.SCRATCH0 = guest R12 + * HSTATE.SCRATCH1 = guest CR * SPRG_SCRATCH0 = guest R13 * */ @@ -156,13 +157,14 @@ kvmppc_handler_skip_ins: mtsrr0 r12 /* Clean up all state */ - lwz r12, (SHADOW_VCPU_OFF + SVCPU_SCRATCH1)(r13) + lwz r12, HSTATE_SCRATCH1(r13) mtcr r12 - PPC_LL r12, (SHADOW_VCPU_OFF + SVCPU_SCRATCH0)(r13) + PPC_LL r12, HSTATE_SCRATCH0(r13) GET_SCRATCH0(r13) /* And get back into the code */ RFI +#endif /* * This trampoline brings us back to a real mode handler @@ -251,12 +253,4 @@ define_load_up(altivec) define_load_up(vsx) #endif -.global kvmppc_trampoline_lowmem -kvmppc_trampoline_lowmem: - PPC_LONG kvmppc_handler_lowmem_trampoline - CONFIG_KERNEL_START - -.global kvmppc_trampoline_enter -kvmppc_trampoline_enter: - PPC_LONG kvmppc_handler_trampoline_enter - CONFIG_KERNEL_START - #include "book3s_segment.S" diff --git a/arch/powerpc/kvm/book3s_segment.S b/arch/powerpc/kvm/book3s_segment.S index 451264274b8..aed32e51721 100644 --- a/arch/powerpc/kvm/book3s_segment.S +++ b/arch/powerpc/kvm/book3s_segment.S @@ -22,7 +22,7 @@ #if defined(CONFIG_PPC_BOOK3S_64) #define GET_SHADOW_VCPU(reg) \ - addi reg, r13, PACA_KVM_SVCPU + mr reg, r13 #elif defined(CONFIG_PPC_BOOK3S_32) @@ -71,6 +71,10 @@ kvmppc_handler_trampoline_enter: /* r3 = shadow vcpu */ GET_SHADOW_VCPU(r3) + /* Save R1/R2 in the PACA (64-bit) or shadow_vcpu (32-bit) */ + PPC_STL r1, HSTATE_HOST_R1(r3) + PPC_STL r2, HSTATE_HOST_R2(r3) + /* Move SRR0 and SRR1 into the respective regs */ PPC_LL r9, SVCPU_PC(r3) mtsrr0 r9 @@ -78,36 +82,36 @@ kvmppc_handler_trampoline_enter: /* Activate guest mode, so faults get handled by KVM */ li r11, KVM_GUEST_MODE_GUEST - stb r11, SVCPU_IN_GUEST(r3) + stb r11, HSTATE_IN_GUEST(r3) /* Switch to guest segment. This is subarch specific. */ LOAD_GUEST_SEGMENTS /* Enter guest */ - PPC_LL r4, (SVCPU_CTR)(r3) - PPC_LL r5, (SVCPU_LR)(r3) - lwz r6, (SVCPU_CR)(r3) - lwz r7, (SVCPU_XER)(r3) + PPC_LL r4, SVCPU_CTR(r3) + PPC_LL r5, SVCPU_LR(r3) + lwz r6, SVCPU_CR(r3) + lwz r7, SVCPU_XER(r3) mtctr r4 mtlr r5 mtcr r6 mtxer r7 - PPC_LL r0, (SVCPU_R0)(r3) - PPC_LL r1, (SVCPU_R1)(r3) - PPC_LL r2, (SVCPU_R2)(r3) - PPC_LL r4, (SVCPU_R4)(r3) - PPC_LL r5, (SVCPU_R5)(r3) - PPC_LL r6, (SVCPU_R6)(r3) - PPC_LL r7, (SVCPU_R7)(r3) - PPC_LL r8, (SVCPU_R8)(r3) - PPC_LL r9, (SVCPU_R9)(r3) - PPC_LL r10, (SVCPU_R10)(r3) - PPC_LL r11, (SVCPU_R11)(r3) - PPC_LL r12, (SVCPU_R12)(r3) - PPC_LL r13, (SVCPU_R13)(r3) + PPC_LL r0, SVCPU_R0(r3) + PPC_LL r1, SVCPU_R1(r3) + PPC_LL r2, SVCPU_R2(r3) + PPC_LL r4, SVCPU_R4(r3) + PPC_LL r5, SVCPU_R5(r3) + PPC_LL r6, SVCPU_R6(r3) + PPC_LL r7, SVCPU_R7(r3) + PPC_LL r8, SVCPU_R8(r3) + PPC_LL r9, SVCPU_R9(r3) + PPC_LL r10, SVCPU_R10(r3) + PPC_LL r11, SVCPU_R11(r3) + PPC_LL r12, SVCPU_R12(r3) + PPC_LL r13, SVCPU_R13(r3) PPC_LL r3, (SVCPU_R3)(r3) @@ -125,56 +129,63 @@ kvmppc_handler_trampoline_enter_end: .global kvmppc_handler_trampoline_exit kvmppc_handler_trampoline_exit: +.global kvmppc_interrupt +kvmppc_interrupt: + /* Register usage at this point: * * SPRG_SCRATCH0 = guest R13 * R12 = exit handler id - * R13 = shadow vcpu - SHADOW_VCPU_OFF [=PACA on PPC64] - * SVCPU.SCRATCH0 = guest R12 - * SVCPU.SCRATCH1 = guest CR + * R13 = shadow vcpu (32-bit) or PACA (64-bit) + * HSTATE.SCRATCH0 = guest R12 + * HSTATE.SCRATCH1 = guest CR * */ /* Save registers */ - PPC_STL r0, (SHADOW_VCPU_OFF + SVCPU_R0)(r13) - PPC_STL r1, (SHADOW_VCPU_OFF + SVCPU_R1)(r13) - PPC_STL r2, (SHADOW_VCPU_OFF + SVCPU_R2)(r13) - PPC_STL r3, (SHADOW_VCPU_OFF + SVCPU_R3)(r13) - PPC_STL r4, (SHADOW_VCPU_OFF + SVCPU_R4)(r13) - PPC_STL r5, (SHADOW_VCPU_OFF + SVCPU_R5)(r13) - PPC_STL r6, (SHADOW_VCPU_OFF + SVCPU_R6)(r13) - PPC_STL r7, (SHADOW_VCPU_OFF + SVCPU_R7)(r13) - PPC_STL r8, (SHADOW_VCPU_OFF + SVCPU_R8)(r13) - PPC_STL r9, (SHADOW_VCPU_OFF + SVCPU_R9)(r13) - PPC_STL r10, (SHADOW_VCPU_OFF + SVCPU_R10)(r13) - PPC_STL r11, (SHADOW_VCPU_OFF + SVCPU_R11)(r13) + PPC_STL r0, SVCPU_R0(r13) + PPC_STL r1, SVCPU_R1(r13) + PPC_STL r2, SVCPU_R2(r13) + PPC_STL r3, SVCPU_R3(r13) + PPC_STL r4, SVCPU_R4(r13) + PPC_STL r5, SVCPU_R5(r13) + PPC_STL r6, SVCPU_R6(r13) + PPC_STL r7, SVCPU_R7(r13) + PPC_STL r8, SVCPU_R8(r13) + PPC_STL r9, SVCPU_R9(r13) + PPC_STL r10, SVCPU_R10(r13) + PPC_STL r11, SVCPU_R11(r13) /* Restore R1/R2 so we can handle faults */ - PPC_LL r1, (SHADOW_VCPU_OFF + SVCPU_HOST_R1)(r13) - PPC_LL r2, (SHADOW_VCPU_OFF + SVCPU_HOST_R2)(r13) + PPC_LL r1, HSTATE_HOST_R1(r13) + PPC_LL r2, HSTATE_HOST_R2(r13) /* Save guest PC and MSR */ +#ifdef CONFIG_PPC64 +BEGIN_FTR_SECTION andi. r0,r12,0x2 beq 1f mfspr r3,SPRN_HSRR0 mfspr r4,SPRN_HSRR1 andi. r12,r12,0x3ffd b 2f +END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) +#endif 1: mfsrr0 r3 mfsrr1 r4 2: - PPC_STL r3, (SHADOW_VCPU_OFF + SVCPU_PC)(r13) - PPC_STL r4, (SHADOW_VCPU_OFF + SVCPU_SHADOW_SRR1)(r13) + PPC_STL r3, SVCPU_PC(r13) + PPC_STL r4, SVCPU_SHADOW_SRR1(r13) /* Get scratch'ed off registers */ GET_SCRATCH0(r9) - PPC_LL r8, (SHADOW_VCPU_OFF + SVCPU_SCRATCH0)(r13) - lwz r7, (SHADOW_VCPU_OFF + SVCPU_SCRATCH1)(r13) + PPC_LL r8, HSTATE_SCRATCH0(r13) + lwz r7, HSTATE_SCRATCH1(r13) - PPC_STL r9, (SHADOW_VCPU_OFF + SVCPU_R13)(r13) - PPC_STL r8, (SHADOW_VCPU_OFF + SVCPU_R12)(r13) - stw r7, (SHADOW_VCPU_OFF + SVCPU_CR)(r13) + PPC_STL r9, SVCPU_R13(r13) + PPC_STL r8, SVCPU_R12(r13) + stw r7, SVCPU_CR(r13) /* Save more register state */ @@ -184,11 +195,11 @@ kvmppc_handler_trampoline_exit: mfctr r8 mflr r9 - stw r5, (SHADOW_VCPU_OFF + SVCPU_XER)(r13) - PPC_STL r6, (SHADOW_VCPU_OFF + SVCPU_FAULT_DAR)(r13) - stw r7, (SHADOW_VCPU_OFF + SVCPU_FAULT_DSISR)(r13) - PPC_STL r8, (SHADOW_VCPU_OFF + SVCPU_CTR)(r13) - PPC_STL r9, (SHADOW_VCPU_OFF + SVCPU_LR)(r13) + stw r5, SVCPU_XER(r13) + PPC_STL r6, SVCPU_FAULT_DAR(r13) + stw r7, SVCPU_FAULT_DSISR(r13) + PPC_STL r8, SVCPU_CTR(r13) + PPC_STL r9, SVCPU_LR(r13) /* * In order for us to easily get the last instruction, @@ -218,7 +229,7 @@ ld_last_inst: /* 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, (SHADOW_VCPU_OFF + SVCPU_IN_GUEST)(r13) + stb r9, HSTATE_IN_GUEST(r13) /* 1) enable paging for data */ mfmsr r9 @@ -232,13 +243,13 @@ ld_last_inst: sync #endif - stw r0, (SHADOW_VCPU_OFF + SVCPU_LAST_INST)(r13) + stw r0, SVCPU_LAST_INST(r13) no_ld_last_inst: /* Unset guest mode */ li r9, KVM_GUEST_MODE_NONE - stb r9, (SHADOW_VCPU_OFF + SVCPU_IN_GUEST)(r13) + stb r9, HSTATE_IN_GUEST(r13) /* Switch back to host MMU */ LOAD_HOST_SEGMENTS @@ -248,7 +259,7 @@ no_ld_last_inst: * R1 = host R1 * R2 = host R2 * R12 = exit handler id - * R13 = shadow vcpu - SHADOW_VCPU_OFF [=PACA on PPC64] + * R13 = shadow vcpu (32-bit) or PACA (64-bit) * SVCPU.* = guest * * */ @@ -258,7 +269,7 @@ no_ld_last_inst: ori r7, r7, MSR_IR|MSR_DR|MSR_RI|MSR_ME /* Enable paging */ mtsrr1 r7 /* Load highmem handler address */ - PPC_LL r8, (SHADOW_VCPU_OFF + SVCPU_VMHANDLER)(r13) + PPC_LL r8, HSTATE_VMHANDLER(r13) mtsrr0 r8 RFI diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 8462b3a1c1c..ee45fa01220 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -13,6 +13,7 @@ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. * * Copyright IBM Corp. 2007 + * Copyright 2010-2011 Freescale Semiconductor, Inc. * * Authors: Hollis Blanchard <hollisb@us.ibm.com> * Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com> @@ -78,6 +79,60 @@ void kvmppc_dump_vcpu(struct kvm_vcpu *vcpu) } } +#ifdef CONFIG_SPE +void kvmppc_vcpu_disable_spe(struct kvm_vcpu *vcpu) +{ + preempt_disable(); + enable_kernel_spe(); + kvmppc_save_guest_spe(vcpu); + vcpu->arch.shadow_msr &= ~MSR_SPE; + preempt_enable(); +} + +static void kvmppc_vcpu_enable_spe(struct kvm_vcpu *vcpu) +{ + preempt_disable(); + enable_kernel_spe(); + kvmppc_load_guest_spe(vcpu); + vcpu->arch.shadow_msr |= MSR_SPE; + preempt_enable(); +} + +static void kvmppc_vcpu_sync_spe(struct kvm_vcpu *vcpu) +{ + if (vcpu->arch.shared->msr & MSR_SPE) { + if (!(vcpu->arch.shadow_msr & MSR_SPE)) + kvmppc_vcpu_enable_spe(vcpu); + } else if (vcpu->arch.shadow_msr & MSR_SPE) { + kvmppc_vcpu_disable_spe(vcpu); + } +} +#else +static void kvmppc_vcpu_sync_spe(struct kvm_vcpu *vcpu) +{ +} +#endif + +/* + * Helper function for "full" MSR writes. No need to call this if only + * EE/CE/ME/DE/RI are changing. + */ +void kvmppc_set_msr(struct kvm_vcpu *vcpu, u32 new_msr) +{ + u32 old_msr = vcpu->arch.shared->msr; + + vcpu->arch.shared->msr = new_msr; + + kvmppc_mmu_msr_notify(vcpu, old_msr); + + if (vcpu->arch.shared->msr & MSR_WE) { + kvm_vcpu_block(vcpu); + kvmppc_set_exit_type(vcpu, EMULATED_MTMSRWE_EXITS); + }; + + kvmppc_vcpu_sync_spe(vcpu); +} + static void kvmppc_booke_queue_irqprio(struct kvm_vcpu *vcpu, unsigned int priority) { @@ -257,6 +312,19 @@ void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu) vcpu->arch.shared->int_pending = 0; } +int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) +{ + int ret; + + local_irq_disable(); + kvm_guest_enter(); + ret = __kvmppc_vcpu_run(kvm_run, vcpu); + kvm_guest_exit(); + local_irq_enable(); + + return ret; +} + /** * kvmppc_handle_exit * @@ -344,10 +412,16 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, r = RESUME_GUEST; break; - case BOOKE_INTERRUPT_SPE_UNAVAIL: - kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_SPE_UNAVAIL); +#ifdef CONFIG_SPE + case BOOKE_INTERRUPT_SPE_UNAVAIL: { + if (vcpu->arch.shared->msr & MSR_SPE) + kvmppc_vcpu_enable_spe(vcpu); + else + kvmppc_booke_queue_irqprio(vcpu, + BOOKE_IRQPRIO_SPE_UNAVAIL); r = RESUME_GUEST; break; + } case BOOKE_INTERRUPT_SPE_FP_DATA: kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_SPE_FP_DATA); @@ -358,6 +432,28 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_SPE_FP_ROUND); r = RESUME_GUEST; break; +#else + case BOOKE_INTERRUPT_SPE_UNAVAIL: + /* + * Guest wants SPE, but host kernel doesn't support it. Send + * an "unimplemented operation" program check to the guest. + */ + kvmppc_core_queue_program(vcpu, ESR_PUO | ESR_SPV); + r = RESUME_GUEST; + break; + + /* + * These really should never happen without CONFIG_SPE, + * as we should never enable the real MSR[SPE] in the guest. + */ + case BOOKE_INTERRUPT_SPE_FP_DATA: + case BOOKE_INTERRUPT_SPE_FP_ROUND: + printk(KERN_CRIT "%s: unexpected SPE interrupt %u at %08lx\n", + __func__, exit_nr, vcpu->arch.pc); + run->hw.hardware_exit_reason = exit_nr; + r = RESUME_HOST; + break; +#endif case BOOKE_INTERRUPT_DATA_STORAGE: kvmppc_core_queue_data_storage(vcpu, vcpu->arch.fault_dear, @@ -392,6 +488,17 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, gpa_t gpaddr; gfn_t gfn; +#ifdef CONFIG_KVM_E500 + if (!(vcpu->arch.shared->msr & MSR_PR) && + (eaddr & PAGE_MASK) == vcpu->arch.magic_page_ea) { + kvmppc_map_magic(vcpu); + kvmppc_account_exit(vcpu, DTLB_VIRT_MISS_EXITS); + r = RESUME_GUEST; + + break; + } +#endif + /* Check the guest TLB. */ gtlb_index = kvmppc_mmu_dtlb_index(vcpu, eaddr); if (gtlb_index < 0) { @@ -514,6 +621,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) vcpu->arch.pc = 0; vcpu->arch.shared->msr = 0; + vcpu->arch.shadow_msr = MSR_USER | MSR_DE | MSR_IS | MSR_DS; kvmppc_set_gpr(vcpu, 1, (16<<20) - 8); /* -8 for the callee-save LR slot */ vcpu->arch.shadow_pid = 1; @@ -770,6 +878,26 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) return -ENOTSUPP; } +int kvmppc_core_prepare_memory_region(struct kvm *kvm, + struct kvm_userspace_memory_region *mem) +{ + return 0; +} + +void kvmppc_core_commit_memory_region(struct kvm *kvm, + struct kvm_userspace_memory_region *mem) +{ +} + +int kvmppc_core_init_vm(struct kvm *kvm) +{ + return 0; +} + +void kvmppc_core_destroy_vm(struct kvm *kvm) +{ +} + int __init kvmppc_booke_init(void) { unsigned long ivor[16]; diff --git a/arch/powerpc/kvm/booke.h b/arch/powerpc/kvm/booke.h index 492bb703035..8e1fe33d64e 100644 --- a/arch/powerpc/kvm/booke.h +++ b/arch/powerpc/kvm/booke.h @@ -52,24 +52,19 @@ extern unsigned long kvmppc_booke_handlers; -/* Helper function for "full" MSR writes. No need to call this if only EE is - * changing. */ -static inline void kvmppc_set_msr(struct kvm_vcpu *vcpu, u32 new_msr) -{ - if ((new_msr & MSR_PR) != (vcpu->arch.shared->msr & MSR_PR)) - kvmppc_mmu_priv_switch(vcpu, new_msr & MSR_PR); - - vcpu->arch.shared->msr = new_msr; - - if (vcpu->arch.shared->msr & MSR_WE) { - kvm_vcpu_block(vcpu); - kvmppc_set_exit_type(vcpu, EMULATED_MTMSRWE_EXITS); - }; -} +void kvmppc_set_msr(struct kvm_vcpu *vcpu, u32 new_msr); +void kvmppc_mmu_msr_notify(struct kvm_vcpu *vcpu, u32 old_msr); int kvmppc_booke_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, unsigned int inst, int *advance); int kvmppc_booke_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt); int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs); +/* low-level asm code to transfer guest state */ +void kvmppc_load_guest_spe(struct kvm_vcpu *vcpu); +void kvmppc_save_guest_spe(struct kvm_vcpu *vcpu); + +/* high-level function, manages flags, host state */ +void kvmppc_vcpu_disable_spe(struct kvm_vcpu *vcpu); + #endif /* __KVM_BOOKE_H__ */ diff --git a/arch/powerpc/kvm/booke_interrupts.S b/arch/powerpc/kvm/booke_interrupts.S index b58ccae9590..42f2fb1f66e 100644 --- a/arch/powerpc/kvm/booke_interrupts.S +++ b/arch/powerpc/kvm/booke_interrupts.S @@ -13,6 +13,7 @@ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. * * Copyright IBM Corp. 2007 + * Copyright 2011 Freescale Semiconductor, Inc. * * Authors: Hollis Blanchard <hollisb@us.ibm.com> */ @@ -24,8 +25,6 @@ #include <asm/page.h> #include <asm/asm-offsets.h> -#define KVMPPC_MSR_MASK (MSR_CE|MSR_EE|MSR_PR|MSR_DE|MSR_ME|MSR_IS|MSR_DS) - #define VCPU_GPR(n) (VCPU_GPRS + (n * 4)) /* The host stack layout: */ @@ -192,6 +191,12 @@ _GLOBAL(kvmppc_resume_host) lwz r3, VCPU_HOST_PID(r4) mtspr SPRN_PID, r3 +#ifdef CONFIG_FSL_BOOKE + /* we cheat and know that Linux doesn't use PID1 which is always 0 */ + lis r3, 0 + mtspr SPRN_PID1, r3 +#endif + /* Restore host IVPR before re-enabling interrupts. We cheat and know * that Linux IVPR is always 0xc0000000. */ lis r3, 0xc000 @@ -241,6 +246,14 @@ _GLOBAL(kvmppc_resume_host) heavyweight_exit: /* Not returning to guest. */ +#ifdef CONFIG_SPE + /* save guest SPEFSCR and load host SPEFSCR */ + mfspr r9, SPRN_SPEFSCR + stw r9, VCPU_SPEFSCR(r4) + lwz r9, VCPU_HOST_SPEFSCR(r4) + mtspr SPRN_SPEFSCR, r9 +#endif + /* We already saved guest volatile register state; now save the * non-volatiles. */ stw r15, VCPU_GPR(r15)(r4) @@ -342,6 +355,14 @@ _GLOBAL(__kvmppc_vcpu_run) lwz r30, VCPU_GPR(r30)(r4) lwz r31, VCPU_GPR(r31)(r4) +#ifdef CONFIG_SPE + /* save host SPEFSCR and load guest SPEFSCR */ + mfspr r3, SPRN_SPEFSCR + stw r3, VCPU_HOST_SPEFSCR(r4) + lwz r3, VCPU_SPEFSCR(r4) + mtspr SPRN_SPEFSCR, r3 +#endif + lightweight_exit: stw r2, HOST_R2(r1) @@ -350,6 +371,11 @@ lightweight_exit: lwz r3, VCPU_SHADOW_PID(r4) mtspr SPRN_PID, r3 +#ifdef CONFIG_FSL_BOOKE + lwz r3, VCPU_SHADOW_PID1(r4) + mtspr SPRN_PID1, r3 +#endif + #ifdef CONFIG_44x iccci 0, 0 /* XXX hack */ #endif @@ -405,20 +431,17 @@ lightweight_exit: /* Finish loading guest volatiles and jump to guest. */ lwz r3, VCPU_CTR(r4) + lwz r5, VCPU_CR(r4) + lwz r6, VCPU_PC(r4) + lwz r7, VCPU_SHADOW_MSR(r4) mtctr r3 - lwz r3, VCPU_CR(r4) - mtcr r3 + mtcr r5 + mtsrr0 r6 + mtsrr1 r7 lwz r5, VCPU_GPR(r5)(r4) lwz r6, VCPU_GPR(r6)(r4) lwz r7, VCPU_GPR(r7)(r4) lwz r8, VCPU_GPR(r8)(r4) - lwz r3, VCPU_PC(r4) - mtsrr0 r3 - lwz r3, VCPU_SHARED(r4) - lwz r3, (VCPU_SHARED_MSR + 4)(r3) - oris r3, r3, KVMPPC_MSR_MASK@h - ori r3, r3, KVMPPC_MSR_MASK@l - mtsrr1 r3 /* Clear any debug events which occurred since we disabled MSR[DE]. * XXX This gives us a 3-instruction window in which a breakpoint @@ -430,3 +453,24 @@ lightweight_exit: lwz r3, VCPU_GPR(r3)(r4) lwz r4, VCPU_GPR(r4)(r4) rfi + +#ifdef CONFIG_SPE +_GLOBAL(kvmppc_save_guest_spe) + cmpi 0,r3,0 + beqlr- + SAVE_32EVRS(0, r4, r3, VCPU_EVR) + evxor evr6, evr6, evr6 + evmwumiaa evr6, evr6, evr6 + li r4,VCPU_ACC + evstddx evr6, r4, r3 /* save acc */ + blr + +_GLOBAL(kvmppc_load_guest_spe) + cmpi 0,r3,0 + beqlr- + li r4,VCPU_ACC + evlddx evr6,r4,r3 + evmra evr6,evr6 /* load acc */ + REST_32EVRS(0, r4, r3, VCPU_EVR) + blr +#endif diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c index 318dbc61ba4..797a7447c26 100644 --- a/arch/powerpc/kvm/e500.c +++ b/arch/powerpc/kvm/e500.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2008 Freescale Semiconductor, Inc. All rights reserved. + * Copyright (C) 2008-2011 Freescale Semiconductor, Inc. All rights reserved. * * Author: Yu Liu, <yu.liu@freescale.com> * @@ -41,6 +41,11 @@ void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu) void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu) { kvmppc_e500_tlb_put(vcpu); + +#ifdef CONFIG_SPE + if (vcpu->arch.shadow_msr & MSR_SPE) + kvmppc_vcpu_disable_spe(vcpu); +#endif } int kvmppc_core_check_processor_compat(void) diff --git a/arch/powerpc/kvm/e500_emulate.c b/arch/powerpc/kvm/e500_emulate.c index 69cd665a0ca..d48ae396f41 100644 --- a/arch/powerpc/kvm/e500_emulate.c +++ b/arch/powerpc/kvm/e500_emulate.c @@ -81,8 +81,12 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs) kvmppc_set_pid(vcpu, spr_val); break; case SPRN_PID1: + if (spr_val != 0) + return EMULATE_FAIL; vcpu_e500->pid[1] = spr_val; break; case SPRN_PID2: + if (spr_val != 0) + return EMULATE_FAIL; vcpu_e500->pid[2] = spr_val; break; case SPRN_MAS0: vcpu_e500->mas0 = spr_val; break; diff --git a/arch/powerpc/kvm/e500_tlb.c b/arch/powerpc/kvm/e500_tlb.c index b18fe353397..13c432ea2fa 100644 --- a/arch/powerpc/kvm/e500_tlb.c +++ b/arch/powerpc/kvm/e500_tlb.c @@ -28,8 +28,196 @@ #define to_htlb1_esel(esel) (tlb1_entry_num - (esel) - 1) +struct id { + unsigned long val; + struct id **pentry; +}; + +#define NUM_TIDS 256 + +/* + * This table provide mappings from: + * (guestAS,guestTID,guestPR) --> ID of physical cpu + * guestAS [0..1] + * guestTID [0..255] + * guestPR [0..1] + * ID [1..255] + * Each vcpu keeps one vcpu_id_table. + */ +struct vcpu_id_table { + struct id id[2][NUM_TIDS][2]; +}; + +/* + * This table provide reversed mappings of vcpu_id_table: + * ID --> address of vcpu_id_table item. + * Each physical core has one pcpu_id_table. + */ +struct pcpu_id_table { + struct id *entry[NUM_TIDS]; +}; + +static DEFINE_PER_CPU(struct pcpu_id_table, pcpu_sids); + +/* This variable keeps last used shadow ID on local core. + * The valid range of shadow ID is [1..255] */ +static DEFINE_PER_CPU(unsigned long, pcpu_last_used_sid); + static unsigned int tlb1_entry_num; +/* + * Allocate a free shadow id and setup a valid sid mapping in given entry. + * A mapping is only valid when vcpu_id_table and pcpu_id_table are match. + * + * The caller must have preemption disabled, and keep it that way until + * it has finished with the returned shadow id (either written into the + * TLB or arch.shadow_pid, or discarded). + */ +static inline int local_sid_setup_one(struct id *entry) +{ + unsigned long sid; + int ret = -1; + + sid = ++(__get_cpu_var(pcpu_last_used_sid)); + if (sid < NUM_TIDS) { + __get_cpu_var(pcpu_sids).entry[sid] = entry; + entry->val = sid; + entry->pentry = &__get_cpu_var(pcpu_sids).entry[sid]; + ret = sid; + } + + /* + * If sid == NUM_TIDS, we've run out of sids. We return -1, and + * the caller will invalidate everything and start over. + * + * sid > NUM_TIDS indicates a race, which we disable preemption to + * avoid. + */ + WARN_ON(sid > NUM_TIDS); + + return ret; +} + +/* + * Check if given entry contain a valid shadow id mapping. + * An ID mapping is considered valid only if + * both vcpu and pcpu know this mapping. + * + * The caller must have preemption disabled, and keep it that way until + * it has finished with the returned shadow id (either written into the + * TLB or arch.shadow_pid, or discarded). + */ +static inline int local_sid_lookup(struct id *entry) +{ + if (entry && entry->val != 0 && + __get_cpu_var(pcpu_sids).entry[entry->val] == entry && + entry->pentry == &__get_cpu_var(pcpu_sids).entry[entry->val]) + return entry->val; + return -1; +} + +/* Invalidate all id mappings on local core */ +static inline void local_sid_destroy_all(void) +{ + preempt_disable(); + __get_cpu_var(pcpu_last_used_sid) = 0; + memset(&__get_cpu_var(pcpu_sids), 0, sizeof(__get_cpu_var(pcpu_sids))); + preempt_enable(); +} + +static void *kvmppc_e500_id_table_alloc(struct kvmppc_vcpu_e500 *vcpu_e500) +{ + vcpu_e500->idt = kzalloc(sizeof(struct vcpu_id_table), GFP_KERNEL); + return vcpu_e500->idt; +} + +static void kvmppc_e500_id_table_free(struct kvmppc_vcpu_e500 *vcpu_e500) +{ + kfree(vcpu_e500->idt); +} + +/* Invalidate all mappings on vcpu */ +static void kvmppc_e500_id_table_reset_all(struct kvmppc_vcpu_e500 *vcpu_e500) +{ + memset(vcpu_e500->idt, 0, sizeof(struct vcpu_id_table)); + + /* Update shadow pid when mappings are changed */ + kvmppc_e500_recalc_shadow_pid(vcpu_e500); +} + +/* Invalidate one ID mapping on vcpu */ +static inline void kvmppc_e500_id_table_reset_one( + struct kvmppc_vcpu_e500 *vcpu_e500, + int as, int pid, int pr) +{ + struct vcpu_id_table *idt = vcpu_e500->idt; + + BUG_ON(as >= 2); + BUG_ON(pid >= NUM_TIDS); + BUG_ON(pr >= 2); + + idt->id[as][pid][pr].val = 0; + idt->id[as][pid][pr].pentry = NULL; + + /* Update shadow pid when mappings are changed */ + kvmppc_e500_recalc_shadow_pid(vcpu_e500); +} + +/* + * Map guest (vcpu,AS,ID,PR) to physical core shadow id. + * This function first lookup if a valid mapping exists, + * if not, then creates a new one. + * + * The caller must have preemption disabled, and keep it that way until + * it has finished with the returned shadow id (either written into the + * TLB or arch.shadow_pid, or discarded). + */ +static unsigned int kvmppc_e500_get_sid(struct kvmppc_vcpu_e500 *vcpu_e500, + unsigned int as, unsigned int gid, + unsigned int pr, int avoid_recursion) +{ + struct vcpu_id_table *idt = vcpu_e500->idt; + int sid; + + BUG_ON(as >= 2); + BUG_ON(gid >= NUM_TIDS); + BUG_ON(pr >= 2); + + sid = local_sid_lookup(&idt->id[as][gid][pr]); + + while (sid <= 0) { + /* No mapping yet */ + sid = local_sid_setup_one(&idt->id[as][gid][pr]); + if (sid <= 0) { + _tlbil_all(); + local_sid_destroy_all(); + } + + /* Update shadow pid when mappings are changed */ + if (!avoid_recursion) + kvmppc_e500_recalc_shadow_pid(vcpu_e500); + } + + return sid; +} + +/* Map guest pid to shadow. + * We use PID to keep shadow of current guest non-zero PID, + * and use PID1 to keep shadow of guest zero PID. + * So that guest tlbe with TID=0 can be accessed at any time */ +void kvmppc_e500_recalc_shadow_pid(struct kvmppc_vcpu_e500 *vcpu_e500) +{ + preempt_disable(); + vcpu_e500->vcpu.arch.shadow_pid = kvmppc_e500_get_sid(vcpu_e500, + get_cur_as(&vcpu_e500->vcpu), + get_cur_pid(&vcpu_e500->vcpu), + get_cur_pr(&vcpu_e500->vcpu), 1); + vcpu_e500->vcpu.arch.shadow_pid1 = kvmppc_e500_get_sid(vcpu_e500, + get_cur_as(&vcpu_e500->vcpu), 0, + get_cur_pr(&vcpu_e500->vcpu), 1); + preempt_enable(); +} + void kvmppc_dump_tlbs(struct kvm_vcpu *vcpu) { struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu); @@ -41,25 +229,14 @@ void kvmppc_dump_tlbs(struct kvm_vcpu *vcpu) for (tlbsel = 0; tlbsel < 2; tlbsel++) { printk("Guest TLB%d:\n", tlbsel); - for (i = 0; i < vcpu_e500->guest_tlb_size[tlbsel]; i++) { - tlbe = &vcpu_e500->guest_tlb[tlbsel][i]; + for (i = 0; i < vcpu_e500->gtlb_size[tlbsel]; i++) { + tlbe = &vcpu_e500->gtlb_arch[tlbsel][i]; if (tlbe->mas1 & MAS1_VALID) printk(" G[%d][%3d] | %08X | %08X | %08X | %08X |\n", tlbsel, i, tlbe->mas1, tlbe->mas2, tlbe->mas3, tlbe->mas7); } } - - for (tlbsel = 0; tlbsel < 2; tlbsel++) { - printk("Shadow TLB%d:\n", tlbsel); - for (i = 0; i < vcpu_e500->shadow_tlb_size[tlbsel]; i++) { - tlbe = &vcpu_e500->shadow_tlb[tlbsel][i]; - if (tlbe->mas1 & MAS1_VALID) - printk(" S[%d][%3d] | %08X | %08X | %08X | %08X |\n", - tlbsel, i, tlbe->mas1, tlbe->mas2, - tlbe->mas3, tlbe->mas7); - } - } } static inline unsigned int tlb0_get_next_victim( @@ -67,16 +244,17 @@ static inline unsigned int tlb0_get_next_victim( { unsigned int victim; - victim = vcpu_e500->guest_tlb_nv[0]++; - if (unlikely(vcpu_e500->guest_tlb_nv[0] >= KVM_E500_TLB0_WAY_NUM)) - vcpu_e500->guest_tlb_nv[0] = 0; + victim = vcpu_e500->gtlb_nv[0]++; + if (unlikely(vcpu_e500->gtlb_nv[0] >= KVM_E500_TLB0_WAY_NUM)) + vcpu_e500->gtlb_nv[0] = 0; return victim; } static inline unsigned int tlb1_max_shadow_size(void) { - return tlb1_entry_num - tlbcam_index; + /* reserve one entry for magic page */ + return tlb1_entry_num - tlbcam_index - 1; } static inline int tlbe_is_writable(struct tlbe *tlbe) @@ -112,72 +290,149 @@ static inline u32 e500_shadow_mas2_attrib(u32 mas2, int usermode) /* * writing shadow tlb entry to host TLB */ -static inline void __write_host_tlbe(struct tlbe *stlbe) +static inline void __write_host_tlbe(struct tlbe *stlbe, uint32_t mas0) { + unsigned long flags; + + local_irq_save(flags); + mtspr(SPRN_MAS0, mas0); mtspr(SPRN_MAS1, stlbe->mas1); mtspr(SPRN_MAS2, stlbe->mas2); mtspr(SPRN_MAS3, stlbe->mas3); mtspr(SPRN_MAS7, stlbe->mas7); - __asm__ __volatile__ ("tlbwe\n" : : ); + asm volatile("isync; tlbwe" : : : "memory"); + local_irq_restore(flags); } static inline void write_host_tlbe(struct kvmppc_vcpu_e500 *vcpu_e500, - int tlbsel, int esel) + int tlbsel, int esel, struct tlbe *stlbe) { - struct tlbe *stlbe = &vcpu_e500->shadow_tlb[tlbsel][esel]; - - local_irq_disable(); if (tlbsel == 0) { - __write_host_tlbe(stlbe); + __write_host_tlbe(stlbe, + MAS0_TLBSEL(0) | + MAS0_ESEL(esel & (KVM_E500_TLB0_WAY_NUM - 1))); } else { - unsigned register mas0; - - mas0 = mfspr(SPRN_MAS0); - - mtspr(SPRN_MAS0, MAS0_TLBSEL(1) | MAS0_ESEL(to_htlb1_esel(esel))); - __write_host_tlbe(stlbe); - - mtspr(SPRN_MAS0, mas0); + __write_host_tlbe(stlbe, + MAS0_TLBSEL(1) | + MAS0_ESEL(to_htlb1_esel(esel))); } - local_irq_enable(); + trace_kvm_stlb_write(index_of(tlbsel, esel), stlbe->mas1, stlbe->mas2, + stlbe->mas3, stlbe->mas7); +} + +void kvmppc_map_magic(struct kvm_vcpu *vcpu) +{ + struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu); + struct tlbe magic; + ulong shared_page = ((ulong)vcpu->arch.shared) & PAGE_MASK; + unsigned int stid; + pfn_t pfn; + + pfn = (pfn_t)virt_to_phys((void *)shared_page) >> PAGE_SHIFT; + get_page(pfn_to_page(pfn)); + + preempt_disable(); + stid = kvmppc_e500_get_sid(vcpu_e500, 0, 0, 0, 0); + + magic.mas1 = MAS1_VALID | MAS1_TS | MAS1_TID(stid) | + MAS1_TSIZE(BOOK3E_PAGESZ_4K); + magic.mas2 = vcpu->arch.magic_page_ea | MAS2_M; + magic.mas3 = (pfn << PAGE_SHIFT) | + MAS3_SW | MAS3_SR | MAS3_UW | MAS3_UR; + magic.mas7 = pfn >> (32 - PAGE_SHIFT); + + __write_host_tlbe(&magic, MAS0_TLBSEL(1) | MAS0_ESEL(tlbcam_index)); + preempt_enable(); } void kvmppc_e500_tlb_load(struct kvm_vcpu *vcpu, int cpu) { struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu); - int i; - unsigned register mas0; - - /* Load all valid TLB1 entries to reduce guest tlb miss fault */ - local_irq_disable(); - mas0 = mfspr(SPRN_MAS0); - for (i = 0; i < tlb1_max_shadow_size(); i++) { - struct tlbe *stlbe = &vcpu_e500->shadow_tlb[1][i]; - - if (get_tlb_v(stlbe)) { - mtspr(SPRN_MAS0, MAS0_TLBSEL(1) - | MAS0_ESEL(to_htlb1_esel(i))); - __write_host_tlbe(stlbe); - } - } - mtspr(SPRN_MAS0, mas0); - local_irq_enable(); + + /* Shadow PID may be expired on local core */ + kvmppc_e500_recalc_shadow_pid(vcpu_e500); } void kvmppc_e500_tlb_put(struct kvm_vcpu *vcpu) { - _tlbil_all(); +} + +static void kvmppc_e500_stlbe_invalidate(struct kvmppc_vcpu_e500 *vcpu_e500, + int tlbsel, int esel) +{ + struct tlbe *gtlbe = &vcpu_e500->gtlb_arch[tlbsel][esel]; + struct vcpu_id_table *idt = vcpu_e500->idt; + unsigned int pr, tid, ts, pid; + u32 val, eaddr; + unsigned long flags; + + ts = get_tlb_ts(gtlbe); + tid = get_tlb_tid(gtlbe); + + preempt_disable(); + + /* One guest ID may be mapped to two shadow IDs */ + for (pr = 0; pr < 2; pr++) { + /* + * The shadow PID can have a valid mapping on at most one + * host CPU. In the common case, it will be valid on this + * CPU, in which case (for TLB0) we do a local invalidation + * of the specific address. + * + * If the shadow PID is not valid on the current host CPU, or + * if we're invalidating a TLB1 entry, we invalidate the + * entire shadow PID. + */ + if (tlbsel == 1 || + (pid = local_sid_lookup(&idt->id[ts][tid][pr])) <= 0) { + kvmppc_e500_id_table_reset_one(vcpu_e500, ts, tid, pr); + continue; + } + + /* + * The guest is invalidating a TLB0 entry which is in a PID + * that has a valid shadow mapping on this host CPU. We + * search host TLB0 to invalidate it's shadow TLB entry, + * similar to __tlbil_va except that we need to look in AS1. + */ + val = (pid << MAS6_SPID_SHIFT) | MAS6_SAS; + eaddr = get_tlb_eaddr(gtlbe); + + local_irq_save(flags); + + mtspr(SPRN_MAS6, val); + asm volatile("tlbsx 0, %[eaddr]" : : [eaddr] "r" (eaddr)); + val = mfspr(SPRN_MAS1); + if (val & MAS1_VALID) { + mtspr(SPRN_MAS1, val & ~MAS1_VALID); + asm volatile("tlbwe"); + } + + local_irq_restore(flags); + } + + preempt_enable(); } /* Search the guest TLB for a matching entry. */ static int kvmppc_e500_tlb_index(struct kvmppc_vcpu_e500 *vcpu_e500, gva_t eaddr, int tlbsel, unsigned int pid, int as) { + int size = vcpu_e500->gtlb_size[tlbsel]; + int set_base; int i; - /* XXX Replace loop with fancy data structures. */ - for (i = 0; i < vcpu_e500->guest_tlb_size[tlbsel]; i++) { - struct tlbe *tlbe = &vcpu_e500->guest_tlb[tlbsel][i]; + if (tlbsel == 0) { + int mask = size / KVM_E500_TLB0_WAY_NUM - 1; + set_base = (eaddr >> PAGE_SHIFT) & mask; + set_base *= KVM_E500_TLB0_WAY_NUM; + size = KVM_E500_TLB0_WAY_NUM; + } else { + set_base = 0; + } + + for (i = 0; i < size; i++) { + struct tlbe *tlbe = &vcpu_e500->gtlb_arch[tlbsel][set_base + i]; unsigned int tid; if (eaddr < get_tlb_eaddr(tlbe)) @@ -196,66 +451,32 @@ static int kvmppc_e500_tlb_index(struct kvmppc_vcpu_e500 *vcpu_e500, if (get_tlb_ts(tlbe) != as && as != -1) continue; - return i; + return set_base + i; } return -1; } -static void kvmppc_e500_shadow_release(struct kvmppc_vcpu_e500 *vcpu_e500, - int tlbsel, int esel) -{ - struct tlbe *stlbe = &vcpu_e500->shadow_tlb[tlbsel][esel]; - struct page *page = vcpu_e500->shadow_pages[tlbsel][esel]; - - if (page) { - vcpu_e500->shadow_pages[tlbsel][esel] = NULL; - - if (get_tlb_v(stlbe)) { - if (tlbe_is_writable(stlbe)) - kvm_release_page_dirty(page); - else - kvm_release_page_clean(page); - } - } -} - -static void kvmppc_e500_stlbe_invalidate(struct kvmppc_vcpu_e500 *vcpu_e500, - int tlbsel, int esel) +static inline void kvmppc_e500_priv_setup(struct tlbe_priv *priv, + struct tlbe *gtlbe, + pfn_t pfn) { - struct tlbe *stlbe = &vcpu_e500->shadow_tlb[tlbsel][esel]; + priv->pfn = pfn; + priv->flags = E500_TLB_VALID; - kvmppc_e500_shadow_release(vcpu_e500, tlbsel, esel); - stlbe->mas1 = 0; - trace_kvm_stlb_inval(index_of(tlbsel, esel)); + if (tlbe_is_writable(gtlbe)) + priv->flags |= E500_TLB_DIRTY; } -static void kvmppc_e500_tlb1_invalidate(struct kvmppc_vcpu_e500 *vcpu_e500, - gva_t eaddr, gva_t eend, u32 tid) +static inline void kvmppc_e500_priv_release(struct tlbe_priv *priv) { - unsigned int pid = tid & 0xff; - unsigned int i; - - /* XXX Replace loop with fancy data structures. */ - for (i = 0; i < vcpu_e500->guest_tlb_size[1]; i++) { - struct tlbe *stlbe = &vcpu_e500->shadow_tlb[1][i]; - unsigned int tid; - - if (!get_tlb_v(stlbe)) - continue; - - if (eend < get_tlb_eaddr(stlbe)) - continue; + if (priv->flags & E500_TLB_VALID) { + if (priv->flags & E500_TLB_DIRTY) + kvm_release_pfn_dirty(priv->pfn); + else + kvm_release_pfn_clean(priv->pfn); - if (eaddr > get_tlb_end(stlbe)) - continue; - - tid = get_tlb_tid(stlbe); - if (tid && (tid != pid)) - continue; - - kvmppc_e500_stlbe_invalidate(vcpu_e500, 1, i); - write_host_tlbe(vcpu_e500, 1, i); + priv->flags = 0; } } @@ -273,7 +494,7 @@ static inline void kvmppc_e500_deliver_tlb_miss(struct kvm_vcpu *vcpu, tsized = (vcpu_e500->mas4 >> 7) & 0x1f; vcpu_e500->mas0 = MAS0_TLBSEL(tlbsel) | MAS0_ESEL(victim) - | MAS0_NV(vcpu_e500->guest_tlb_nv[tlbsel]); + | MAS0_NV(vcpu_e500->gtlb_nv[tlbsel]); vcpu_e500->mas1 = MAS1_VALID | (as ? MAS1_TS : 0) | MAS1_TID(vcpu_e500->pid[pidsel]) | MAS1_TSIZE(tsized); @@ -286,56 +507,154 @@ static inline void kvmppc_e500_deliver_tlb_miss(struct kvm_vcpu *vcpu, vcpu_e500->mas7 = 0; } -static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, - u64 gvaddr, gfn_t gfn, struct tlbe *gtlbe, int tlbsel, int esel) +static inline void kvmppc_e500_setup_stlbe(struct kvmppc_vcpu_e500 *vcpu_e500, + struct tlbe *gtlbe, int tsize, + struct tlbe_priv *priv, + u64 gvaddr, struct tlbe *stlbe) { - struct page *new_page; - struct tlbe *stlbe; - hpa_t hpaddr; - - stlbe = &vcpu_e500->shadow_tlb[tlbsel][esel]; - - /* Get reference to new page. */ - new_page = gfn_to_page(vcpu_e500->vcpu.kvm, gfn); - if (is_error_page(new_page)) { - printk(KERN_ERR "Couldn't get guest page for gfn %lx!\n", - (long)gfn); - kvm_release_page_clean(new_page); - return; - } - hpaddr = page_to_phys(new_page); - - /* Drop reference to old page. */ - kvmppc_e500_shadow_release(vcpu_e500, tlbsel, esel); + pfn_t pfn = priv->pfn; + unsigned int stid; - vcpu_e500->shadow_pages[tlbsel][esel] = new_page; + stid = kvmppc_e500_get_sid(vcpu_e500, get_tlb_ts(gtlbe), + get_tlb_tid(gtlbe), + get_cur_pr(&vcpu_e500->vcpu), 0); - /* Force TS=1 IPROT=0 TSIZE=4KB for all guest mappings. */ - stlbe->mas1 = MAS1_TSIZE(BOOK3E_PAGESZ_4K) - | MAS1_TID(get_tlb_tid(gtlbe)) | MAS1_TS | MAS1_VALID; + /* Force TS=1 IPROT=0 for all guest mappings. */ + stlbe->mas1 = MAS1_TSIZE(tsize) + | MAS1_TID(stid) | MAS1_TS | MAS1_VALID; stlbe->mas2 = (gvaddr & MAS2_EPN) | e500_shadow_mas2_attrib(gtlbe->mas2, vcpu_e500->vcpu.arch.shared->msr & MSR_PR); - stlbe->mas3 = (hpaddr & MAS3_RPN) + stlbe->mas3 = ((pfn << PAGE_SHIFT) & MAS3_RPN) | e500_shadow_mas3_attrib(gtlbe->mas3, vcpu_e500->vcpu.arch.shared->msr & MSR_PR); - stlbe->mas7 = (hpaddr >> 32) & MAS7_RPN; + stlbe->mas7 = (pfn >> (32 - PAGE_SHIFT)) & MAS7_RPN; +} - trace_kvm_stlb_write(index_of(tlbsel, esel), stlbe->mas1, stlbe->mas2, - stlbe->mas3, stlbe->mas7); + +static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, + u64 gvaddr, gfn_t gfn, struct tlbe *gtlbe, int tlbsel, int esel, + struct tlbe *stlbe) +{ + struct kvm_memory_slot *slot; + unsigned long pfn, hva; + int pfnmap = 0; + int tsize = BOOK3E_PAGESZ_4K; + struct tlbe_priv *priv; + + /* + * Translate guest physical to true physical, acquiring + * a page reference if it is normal, non-reserved memory. + * + * gfn_to_memslot() must succeed because otherwise we wouldn't + * have gotten this far. Eventually we should just pass the slot + * pointer through from the first lookup. + */ + slot = gfn_to_memslot(vcpu_e500->vcpu.kvm, gfn); + hva = gfn_to_hva_memslot(slot, gfn); + + if (tlbsel == 1) { + struct vm_area_struct *vma; + down_read(¤t->mm->mmap_sem); + + vma = find_vma(current->mm, hva); + if (vma && hva >= vma->vm_start && + (vma->vm_flags & VM_PFNMAP)) { + /* + * This VMA is a physically contiguous region (e.g. + * /dev/mem) that bypasses normal Linux page + * management. Find the overlap between the + * vma and the memslot. + */ + + unsigned long start, end; + unsigned long slot_start, slot_end; + + pfnmap = 1; + + start = vma->vm_pgoff; + end = start + + ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT); + + pfn = start + ((hva - vma->vm_start) >> PAGE_SHIFT); + + slot_start = pfn - (gfn - slot->base_gfn); + slot_end = slot_start + slot->npages; + + if (start < slot_start) + start = slot_start; + if (end > slot_end) + end = slot_end; + + tsize = (gtlbe->mas1 & MAS1_TSIZE_MASK) >> + MAS1_TSIZE_SHIFT; + + /* + * e500 doesn't implement the lowest tsize bit, + * or 1K pages. + */ + tsize = max(BOOK3E_PAGESZ_4K, tsize & ~1); + + /* + * Now find the largest tsize (up to what the guest + * requested) that will cover gfn, stay within the + * range, and for which gfn and pfn are mutually + * aligned. + */ + + for (; tsize > BOOK3E_PAGESZ_4K; tsize -= 2) { + unsigned long gfn_start, gfn_end, tsize_pages; + tsize_pages = 1 << (tsize - 2); + + gfn_start = gfn & ~(tsize_pages - 1); + gfn_end = gfn_start + tsize_pages; + + if (gfn_start + pfn - gfn < start) + continue; + if (gfn_end + pfn - gfn > end) + continue; + if ((gfn & (tsize_pages - 1)) != + (pfn & (tsize_pages - 1))) + continue; + + gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1); + pfn &= ~(tsize_pages - 1); + break; + } + } + + up_read(¤t->mm->mmap_sem); + } + + if (likely(!pfnmap)) { + pfn = gfn_to_pfn_memslot(vcpu_e500->vcpu.kvm, slot, gfn); + if (is_error_pfn(pfn)) { + printk(KERN_ERR "Couldn't get real page for gfn %lx!\n", + (long)gfn); + kvm_release_pfn_clean(pfn); + return; + } + } + + /* Drop old priv and setup new one. */ + priv = &vcpu_e500->gtlb_priv[tlbsel][esel]; + kvmppc_e500_priv_release(priv); + kvmppc_e500_priv_setup(priv, gtlbe, pfn); + + kvmppc_e500_setup_stlbe(vcpu_e500, gtlbe, tsize, priv, gvaddr, stlbe); } /* XXX only map the one-one case, for now use TLB0 */ -static int kvmppc_e500_stlbe_map(struct kvmppc_vcpu_e500 *vcpu_e500, - int tlbsel, int esel) +static int kvmppc_e500_tlb0_map(struct kvmppc_vcpu_e500 *vcpu_e500, + int esel, struct tlbe *stlbe) { struct tlbe *gtlbe; - gtlbe = &vcpu_e500->guest_tlb[tlbsel][esel]; + gtlbe = &vcpu_e500->gtlb_arch[0][esel]; kvmppc_e500_shadow_map(vcpu_e500, get_tlb_eaddr(gtlbe), get_tlb_raddr(gtlbe) >> PAGE_SHIFT, - gtlbe, tlbsel, esel); + gtlbe, 0, esel, stlbe); return esel; } @@ -344,53 +663,37 @@ static int kvmppc_e500_stlbe_map(struct kvmppc_vcpu_e500 *vcpu_e500, * the shadow TLB. */ /* XXX for both one-one and one-to-many , for now use TLB1 */ static int kvmppc_e500_tlb1_map(struct kvmppc_vcpu_e500 *vcpu_e500, - u64 gvaddr, gfn_t gfn, struct tlbe *gtlbe) + u64 gvaddr, gfn_t gfn, struct tlbe *gtlbe, struct tlbe *stlbe) { unsigned int victim; - victim = vcpu_e500->guest_tlb_nv[1]++; + victim = vcpu_e500->gtlb_nv[1]++; - if (unlikely(vcpu_e500->guest_tlb_nv[1] >= tlb1_max_shadow_size())) - vcpu_e500->guest_tlb_nv[1] = 0; + if (unlikely(vcpu_e500->gtlb_nv[1] >= tlb1_max_shadow_size())) + vcpu_e500->gtlb_nv[1] = 0; - kvmppc_e500_shadow_map(vcpu_e500, gvaddr, gfn, gtlbe, 1, victim); + kvmppc_e500_shadow_map(vcpu_e500, gvaddr, gfn, gtlbe, 1, victim, stlbe); return victim; } -/* Invalidate all guest kernel mappings when enter usermode, - * so that when they fault back in they will get the - * proper permission bits. */ -void kvmppc_mmu_priv_switch(struct kvm_vcpu *vcpu, int usermode) +void kvmppc_mmu_msr_notify(struct kvm_vcpu *vcpu, u32 old_msr) { - if (usermode) { - struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu); - int i; - - /* XXX Replace loop with fancy data structures. */ - for (i = 0; i < tlb1_max_shadow_size(); i++) - kvmppc_e500_stlbe_invalidate(vcpu_e500, 1, i); + struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu); - _tlbil_all(); - } + /* Recalc shadow pid since MSR changes */ + kvmppc_e500_recalc_shadow_pid(vcpu_e500); } -static int kvmppc_e500_gtlbe_invalidate(struct kvmppc_vcpu_e500 *vcpu_e500, - int tlbsel, int esel) +static inline int kvmppc_e500_gtlbe_invalidate( + struct kvmppc_vcpu_e500 *vcpu_e500, + int tlbsel, int esel) { - struct tlbe *gtlbe = &vcpu_e500->guest_tlb[tlbsel][esel]; + struct tlbe *gtlbe = &vcpu_e500->gtlb_arch[tlbsel][esel]; if (unlikely(get_tlb_iprot(gtlbe))) return -1; - if (tlbsel == 1) { - kvmppc_e500_tlb1_invalidate(vcpu_e500, get_tlb_eaddr(gtlbe), - get_tlb_end(gtlbe), - get_tlb_tid(gtlbe)); - } else { - kvmppc_e500_stlbe_invalidate(vcpu_e500, tlbsel, esel); - } - gtlbe->mas1 = 0; return 0; @@ -401,13 +704,14 @@ int kvmppc_e500_emul_mt_mmucsr0(struct kvmppc_vcpu_e500 *vcpu_e500, ulong value) int esel; if (value & MMUCSR0_TLB0FI) - for (esel = 0; esel < vcpu_e500->guest_tlb_size[0]; esel++) + for (esel = 0; esel < vcpu_e500->gtlb_size[0]; esel++) kvmppc_e500_gtlbe_invalidate(vcpu_e500, 0, esel); if (value & MMUCSR0_TLB1FI) - for (esel = 0; esel < vcpu_e500->guest_tlb_size[1]; esel++) + for (esel = 0; esel < vcpu_e500->gtlb_size[1]; esel++) kvmppc_e500_gtlbe_invalidate(vcpu_e500, 1, esel); - _tlbil_all(); + /* Invalidate all vcpu id mappings */ + kvmppc_e500_id_table_reset_all(vcpu_e500); return EMULATE_DONE; } @@ -428,7 +732,7 @@ int kvmppc_e500_emul_tlbivax(struct kvm_vcpu *vcpu, int ra, int rb) if (ia) { /* invalidate all entries */ - for (esel = 0; esel < vcpu_e500->guest_tlb_size[tlbsel]; esel++) + for (esel = 0; esel < vcpu_e500->gtlb_size[tlbsel]; esel++) kvmppc_e500_gtlbe_invalidate(vcpu_e500, tlbsel, esel); } else { ea &= 0xfffff000; @@ -438,7 +742,8 @@ int kvmppc_e500_emul_tlbivax(struct kvm_vcpu *vcpu, int ra, int rb) kvmppc_e500_gtlbe_invalidate(vcpu_e500, tlbsel, esel); } - _tlbil_all(); + /* Invalidate all vcpu id mappings */ + kvmppc_e500_id_table_reset_all(vcpu_e500); return EMULATE_DONE; } @@ -452,9 +757,9 @@ int kvmppc_e500_emul_tlbre(struct kvm_vcpu *vcpu) tlbsel = get_tlb_tlbsel(vcpu_e500); esel = get_tlb_esel(vcpu_e500, tlbsel); - gtlbe = &vcpu_e500->guest_tlb[tlbsel][esel]; + gtlbe = &vcpu_e500->gtlb_arch[tlbsel][esel]; vcpu_e500->mas0 &= ~MAS0_NV(~0); - vcpu_e500->mas0 |= MAS0_NV(vcpu_e500->guest_tlb_nv[tlbsel]); + vcpu_e500->mas0 |= MAS0_NV(vcpu_e500->gtlb_nv[tlbsel]); vcpu_e500->mas1 = gtlbe->mas1; vcpu_e500->mas2 = gtlbe->mas2; vcpu_e500->mas3 = gtlbe->mas3; @@ -477,14 +782,14 @@ int kvmppc_e500_emul_tlbsx(struct kvm_vcpu *vcpu, int rb) for (tlbsel = 0; tlbsel < 2; tlbsel++) { esel = kvmppc_e500_tlb_index(vcpu_e500, ea, tlbsel, pid, as); if (esel >= 0) { - gtlbe = &vcpu_e500->guest_tlb[tlbsel][esel]; + gtlbe = &vcpu_e500->gtlb_arch[tlbsel][esel]; break; } } if (gtlbe) { vcpu_e500->mas0 = MAS0_TLBSEL(tlbsel) | MAS0_ESEL(esel) - | MAS0_NV(vcpu_e500->guest_tlb_nv[tlbsel]); + | MAS0_NV(vcpu_e500->gtlb_nv[tlbsel]); vcpu_e500->mas1 = gtlbe->mas1; vcpu_e500->mas2 = gtlbe->mas2; vcpu_e500->mas3 = gtlbe->mas3; @@ -497,7 +802,7 @@ int kvmppc_e500_emul_tlbsx(struct kvm_vcpu *vcpu, int rb) victim = (tlbsel == 0) ? tlb0_get_next_victim(vcpu_e500) : 0; vcpu_e500->mas0 = MAS0_TLBSEL(tlbsel) | MAS0_ESEL(victim) - | MAS0_NV(vcpu_e500->guest_tlb_nv[tlbsel]); + | MAS0_NV(vcpu_e500->gtlb_nv[tlbsel]); vcpu_e500->mas1 = (vcpu_e500->mas6 & MAS6_SPID0) | (vcpu_e500->mas6 & (MAS6_SAS ? MAS1_TS : 0)) | (vcpu_e500->mas4 & MAS4_TSIZED(~0)); @@ -514,23 +819,16 @@ int kvmppc_e500_emul_tlbsx(struct kvm_vcpu *vcpu, int rb) int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu) { struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu); - u64 eaddr; - u64 raddr; - u32 tid; struct tlbe *gtlbe; - int tlbsel, esel, stlbsel, sesel; + int tlbsel, esel; tlbsel = get_tlb_tlbsel(vcpu_e500); esel = get_tlb_esel(vcpu_e500, tlbsel); - gtlbe = &vcpu_e500->guest_tlb[tlbsel][esel]; + gtlbe = &vcpu_e500->gtlb_arch[tlbsel][esel]; - if (get_tlb_v(gtlbe) && tlbsel == 1) { - eaddr = get_tlb_eaddr(gtlbe); - tid = get_tlb_tid(gtlbe); - kvmppc_e500_tlb1_invalidate(vcpu_e500, eaddr, - get_tlb_end(gtlbe), tid); - } + if (get_tlb_v(gtlbe)) + kvmppc_e500_stlbe_invalidate(vcpu_e500, tlbsel, esel); gtlbe->mas1 = vcpu_e500->mas1; gtlbe->mas2 = vcpu_e500->mas2; @@ -542,6 +840,12 @@ int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu) /* Invalidate shadow mappings for the about-to-be-clobbered TLBE. */ if (tlbe_is_host_safe(vcpu, gtlbe)) { + struct tlbe stlbe; + int stlbsel, sesel; + u64 eaddr; + u64 raddr; + + preempt_disable(); switch (tlbsel) { case 0: /* TLB0 */ @@ -549,7 +853,7 @@ int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu) gtlbe->mas1 |= MAS1_TSIZE(BOOK3E_PAGESZ_4K); stlbsel = 0; - sesel = kvmppc_e500_stlbe_map(vcpu_e500, 0, esel); + sesel = kvmppc_e500_tlb0_map(vcpu_e500, esel, &stlbe); break; @@ -564,13 +868,14 @@ int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu) * are mapped on the fly. */ stlbsel = 1; sesel = kvmppc_e500_tlb1_map(vcpu_e500, eaddr, - raddr >> PAGE_SHIFT, gtlbe); + raddr >> PAGE_SHIFT, gtlbe, &stlbe); break; default: BUG(); } - write_host_tlbe(vcpu_e500, stlbsel, sesel); + write_host_tlbe(vcpu_e500, stlbsel, sesel, &stlbe); + preempt_enable(); } kvmppc_set_exit_type(vcpu, EMULATED_TLBWE_EXITS); @@ -610,7 +915,7 @@ gpa_t kvmppc_mmu_xlate(struct kvm_vcpu *vcpu, unsigned int index, { struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu); struct tlbe *gtlbe = - &vcpu_e500->guest_tlb[tlbsel_of(index)][esel_of(index)]; + &vcpu_e500->gtlb_arch[tlbsel_of(index)][esel_of(index)]; u64 pgmask = get_tlb_bytes(gtlbe) - 1; return get_tlb_raddr(gtlbe) | (eaddr & pgmask); @@ -618,38 +923,37 @@ gpa_t kvmppc_mmu_xlate(struct kvm_vcpu *vcpu, unsigned int index, void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu) { - struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu); - int tlbsel, i; - - for (tlbsel = 0; tlbsel < 2; tlbsel++) - for (i = 0; i < vcpu_e500->guest_tlb_size[tlbsel]; i++) - kvmppc_e500_shadow_release(vcpu_e500, tlbsel, i); - - /* discard all guest mapping */ - _tlbil_all(); } void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr, unsigned int index) { struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu); + struct tlbe_priv *priv; + struct tlbe *gtlbe, stlbe; int tlbsel = tlbsel_of(index); int esel = esel_of(index); int stlbsel, sesel; + gtlbe = &vcpu_e500->gtlb_arch[tlbsel][esel]; + + preempt_disable(); switch (tlbsel) { case 0: stlbsel = 0; sesel = esel; + priv = &vcpu_e500->gtlb_priv[stlbsel][sesel]; + + kvmppc_e500_setup_stlbe(vcpu_e500, gtlbe, BOOK3E_PAGESZ_4K, + priv, eaddr, &stlbe); break; case 1: { gfn_t gfn = gpaddr >> PAGE_SHIFT; - struct tlbe *gtlbe - = &vcpu_e500->guest_tlb[tlbsel][esel]; stlbsel = 1; - sesel = kvmppc_e500_tlb1_map(vcpu_e500, eaddr, gfn, gtlbe); + sesel = kvmppc_e500_tlb1_map(vcpu_e500, eaddr, gfn, + gtlbe, &stlbe); break; } @@ -657,7 +961,9 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr, BUG(); break; } - write_host_tlbe(vcpu_e500, stlbsel, sesel); + + write_host_tlbe(vcpu_e500, stlbsel, sesel, &stlbe); + preempt_enable(); } int kvmppc_e500_tlb_search(struct kvm_vcpu *vcpu, @@ -679,8 +985,10 @@ void kvmppc_set_pid(struct kvm_vcpu *vcpu, u32 pid) { struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu); - vcpu_e500->pid[0] = vcpu->arch.shadow_pid = - vcpu->arch.pid = pid; + if (vcpu->arch.pid != pid) { + vcpu_e500->pid[0] = vcpu->arch.pid = pid; + kvmppc_e500_recalc_shadow_pid(vcpu_e500); + } } void kvmppc_e500_tlb_setup(struct kvmppc_vcpu_e500 *vcpu_e500) @@ -688,14 +996,14 @@ void kvmppc_e500_tlb_setup(struct kvmppc_vcpu_e500 *vcpu_e500) struct tlbe *tlbe; /* Insert large initial mapping for guest. */ - tlbe = &vcpu_e500->guest_tlb[1][0]; + tlbe = &vcpu_e500->gtlb_arch[1][0]; tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOK3E_PAGESZ_256M); tlbe->mas2 = 0; tlbe->mas3 = E500_TLB_SUPER_PERM_MASK; tlbe->mas7 = 0; /* 4K map for serial output. Used by kernel wrapper. */ - tlbe = &vcpu_e500->guest_tlb[1][1]; + tlbe = &vcpu_e500->gtlb_arch[1][1]; tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOK3E_PAGESZ_4K); tlbe->mas2 = (0xe0004500 & 0xFFFFF000) | MAS2_I | MAS2_G; tlbe->mas3 = (0xe0004500 & 0xFFFFF000) | E500_TLB_SUPER_PERM_MASK; @@ -706,68 +1014,64 @@ int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500) { tlb1_entry_num = mfspr(SPRN_TLB1CFG) & 0xFFF; - vcpu_e500->guest_tlb_size[0] = KVM_E500_TLB0_SIZE; - vcpu_e500->guest_tlb[0] = + vcpu_e500->gtlb_size[0] = KVM_E500_TLB0_SIZE; + vcpu_e500->gtlb_arch[0] = kzalloc(sizeof(struct tlbe) * KVM_E500_TLB0_SIZE, GFP_KERNEL); - if (vcpu_e500->guest_tlb[0] == NULL) + if (vcpu_e500->gtlb_arch[0] == NULL) goto err_out; - vcpu_e500->shadow_tlb_size[0] = KVM_E500_TLB0_SIZE; - vcpu_e500->shadow_tlb[0] = - kzalloc(sizeof(struct tlbe) * KVM_E500_TLB0_SIZE, GFP_KERNEL); - if (vcpu_e500->shadow_tlb[0] == NULL) - goto err_out_guest0; - - vcpu_e500->guest_tlb_size[1] = KVM_E500_TLB1_SIZE; - vcpu_e500->guest_tlb[1] = + vcpu_e500->gtlb_size[1] = KVM_E500_TLB1_SIZE; + vcpu_e500->gtlb_arch[1] = kzalloc(sizeof(struct tlbe) * KVM_E500_TLB1_SIZE, GFP_KERNEL); - if (vcpu_e500->guest_tlb[1] == NULL) - goto err_out_shadow0; + if (vcpu_e500->gtlb_arch[1] == NULL) + goto err_out_guest0; - vcpu_e500->shadow_tlb_size[1] = tlb1_entry_num; - vcpu_e500->shadow_tlb[1] = - kzalloc(sizeof(struct tlbe) * tlb1_entry_num, GFP_KERNEL); - if (vcpu_e500->shadow_tlb[1] == NULL) + vcpu_e500->gtlb_priv[0] = (struct tlbe_priv *) + kzalloc(sizeof(struct tlbe_priv) * KVM_E500_TLB0_SIZE, GFP_KERNEL); + if (vcpu_e500->gtlb_priv[0] == NULL) goto err_out_guest1; + vcpu_e500->gtlb_priv[1] = (struct tlbe_priv *) + kzalloc(sizeof(struct tlbe_priv) * KVM_E500_TLB1_SIZE, GFP_KERNEL); - vcpu_e500->shadow_pages[0] = (struct page **) - kzalloc(sizeof(struct page *) * KVM_E500_TLB0_SIZE, GFP_KERNEL); - if (vcpu_e500->shadow_pages[0] == NULL) - goto err_out_shadow1; + if (vcpu_e500->gtlb_priv[1] == NULL) + goto err_out_priv0; - vcpu_e500->shadow_pages[1] = (struct page **) - kzalloc(sizeof(struct page *) * tlb1_entry_num, GFP_KERNEL); - if (vcpu_e500->shadow_pages[1] == NULL) - goto err_out_page0; + if (kvmppc_e500_id_table_alloc(vcpu_e500) == NULL) + goto err_out_priv1; /* Init TLB configuration register */ vcpu_e500->tlb0cfg = mfspr(SPRN_TLB0CFG) & ~0xfffUL; - vcpu_e500->tlb0cfg |= vcpu_e500->guest_tlb_size[0]; + vcpu_e500->tlb0cfg |= vcpu_e500->gtlb_size[0]; vcpu_e500->tlb1cfg = mfspr(SPRN_TLB1CFG) & ~0xfffUL; - vcpu_e500->tlb1cfg |= vcpu_e500->guest_tlb_size[1]; + vcpu_e500->tlb1cfg |= vcpu_e500->gtlb_size[1]; return 0; -err_out_page0: - kfree(vcpu_e500->shadow_pages[0]); -err_out_shadow1: - kfree(vcpu_e500->shadow_tlb[1]); +err_out_priv1: + kfree(vcpu_e500->gtlb_priv[1]); +err_out_priv0: + kfree(vcpu_e500->gtlb_priv[0]); err_out_guest1: - kfree(vcpu_e500->guest_tlb[1]); -err_out_shadow0: - kfree(vcpu_e500->shadow_tlb[0]); + kfree(vcpu_e500->gtlb_arch[1]); err_out_guest0: - kfree(vcpu_e500->guest_tlb[0]); + kfree(vcpu_e500->gtlb_arch[0]); err_out: return -1; } void kvmppc_e500_tlb_uninit(struct kvmppc_vcpu_e500 *vcpu_e500) { - kfree(vcpu_e500->shadow_pages[1]); - kfree(vcpu_e500->shadow_pages[0]); - kfree(vcpu_e500->shadow_tlb[1]); - kfree(vcpu_e500->guest_tlb[1]); - kfree(vcpu_e500->shadow_tlb[0]); - kfree(vcpu_e500->guest_tlb[0]); + int stlbsel, i; + + /* release all privs */ + for (stlbsel = 0; stlbsel < 2; stlbsel++) + for (i = 0; i < vcpu_e500->gtlb_size[stlbsel]; i++) { + struct tlbe_priv *priv = + &vcpu_e500->gtlb_priv[stlbsel][i]; + kvmppc_e500_priv_release(priv); + } + + kvmppc_e500_id_table_free(vcpu_e500); + kfree(vcpu_e500->gtlb_arch[1]); + kfree(vcpu_e500->gtlb_arch[0]); } diff --git a/arch/powerpc/kvm/e500_tlb.h b/arch/powerpc/kvm/e500_tlb.h index 458946b4775..59b88e99a23 100644 --- a/arch/powerpc/kvm/e500_tlb.h +++ b/arch/powerpc/kvm/e500_tlb.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2008 Freescale Semiconductor, Inc. All rights reserved. + * Copyright (C) 2008-2011 Freescale Semiconductor, Inc. All rights reserved. * * Author: Yu Liu, yu.liu@freescale.com * @@ -55,6 +55,7 @@ extern void kvmppc_e500_tlb_load(struct kvm_vcpu *, int); extern int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *); extern void kvmppc_e500_tlb_uninit(struct kvmppc_vcpu_e500 *); extern void kvmppc_e500_tlb_setup(struct kvmppc_vcpu_e500 *); +extern void kvmppc_e500_recalc_shadow_pid(struct kvmppc_vcpu_e500 *); /* TLB helper functions */ static inline unsigned int get_tlb_size(const struct tlbe *tlbe) @@ -110,6 +111,16 @@ static inline unsigned int get_cur_pid(struct kvm_vcpu *vcpu) return vcpu->arch.pid & 0xff; } +static inline unsigned int get_cur_as(struct kvm_vcpu *vcpu) +{ + return !!(vcpu->arch.shared->msr & (MSR_IS | MSR_DS)); +} + +static inline unsigned int get_cur_pr(struct kvm_vcpu *vcpu) +{ + return !!(vcpu->arch.shared->msr & MSR_PR); +} + static inline unsigned int get_cur_spid( const struct kvmppc_vcpu_e500 *vcpu_e500) { diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 616dd516ca1..a107c9be0fb 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -30,6 +30,7 @@ #include <asm/uaccess.h> #include <asm/kvm_ppc.h> #include <asm/tlbflush.h> +#include <asm/cputhreads.h> #include "timing.h" #include "../mm/mmu_decl.h" @@ -38,8 +39,12 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *v) { +#ifndef CONFIG_KVM_BOOK3S_64_HV return !(v->arch.shared->msr & MSR_WE) || !!(v->arch.pending_exceptions); +#else + return !(v->arch.ceded) || !!(v->arch.pending_exceptions); +#endif } int kvmppc_kvm_pv(struct kvm_vcpu *vcpu) @@ -73,7 +78,8 @@ int kvmppc_kvm_pv(struct kvm_vcpu *vcpu) } case HC_VENDOR_KVM | KVM_HC_FEATURES: r = HC_EV_SUCCESS; -#if defined(CONFIG_PPC_BOOK3S) /* XXX Missing magic page on BookE */ +#if defined(CONFIG_PPC_BOOK3S) || defined(CONFIG_KVM_E500) + /* XXX Missing magic page on 44x */ r2 |= (1 << KVM_FEATURE_MAGIC_PAGE); #endif @@ -147,7 +153,7 @@ void kvm_arch_check_processor_compat(void *rtn) int kvm_arch_init_vm(struct kvm *kvm) { - return 0; + return kvmppc_core_init_vm(kvm); } void kvm_arch_destroy_vm(struct kvm *kvm) @@ -163,6 +169,9 @@ void kvm_arch_destroy_vm(struct kvm *kvm) kvm->vcpus[i] = NULL; atomic_set(&kvm->online_vcpus, 0); + + kvmppc_core_destroy_vm(kvm); + mutex_unlock(&kvm->lock); } @@ -180,10 +189,13 @@ int kvm_dev_ioctl_check_extension(long ext) #else case KVM_CAP_PPC_SEGSTATE: #endif - case KVM_CAP_PPC_PAIRED_SINGLES: case KVM_CAP_PPC_UNSET_IRQ: case KVM_CAP_PPC_IRQ_LEVEL: case KVM_CAP_ENABLE_CAP: + r = 1; + break; +#ifndef CONFIG_KVM_BOOK3S_64_HV + case KVM_CAP_PPC_PAIRED_SINGLES: case KVM_CAP_PPC_OSI: case KVM_CAP_PPC_GET_PVINFO: r = 1; @@ -191,6 +203,21 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_COALESCED_MMIO: r = KVM_COALESCED_MMIO_PAGE_OFFSET; break; +#endif +#ifdef CONFIG_KVM_BOOK3S_64_HV + case KVM_CAP_SPAPR_TCE: + r = 1; + break; + case KVM_CAP_PPC_SMT: + r = threads_per_core; + break; + case KVM_CAP_PPC_RMA: + r = 1; + /* PPC970 requires an RMA */ + if (cpu_has_feature(CPU_FTR_ARCH_201)) + r = 2; + break; +#endif default: r = 0; break; @@ -211,7 +238,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem, int user_alloc) { - return 0; + return kvmppc_core_prepare_memory_region(kvm, mem); } void kvm_arch_commit_memory_region(struct kvm *kvm, @@ -219,7 +246,7 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, struct kvm_memory_slot old, int user_alloc) { - return; + kvmppc_core_commit_memory_region(kvm, mem); } @@ -287,6 +314,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) hrtimer_init(&vcpu->arch.dec_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS); tasklet_init(&vcpu->arch.tasklet, kvmppc_decrementer_func, (ulong)vcpu); vcpu->arch.dec_timer.function = kvmppc_decrementer_wakeup; + vcpu->arch.dec_expires = ~(u64)0; #ifdef CONFIG_KVM_EXIT_TIMING mutex_init(&vcpu->arch.exit_timing_lock); @@ -313,6 +341,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) mtspr(SPRN_VRSAVE, vcpu->arch.vrsave); #endif kvmppc_core_vcpu_load(vcpu, cpu); + vcpu->cpu = smp_processor_id(); } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) @@ -321,6 +350,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) #ifdef CONFIG_BOOKE vcpu->arch.vrsave = mfspr(SPRN_VRSAVE); #endif + vcpu->cpu = -1; } int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, @@ -492,15 +522,18 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) for (i = 0; i < 32; i++) kvmppc_set_gpr(vcpu, i, gprs[i]); vcpu->arch.osi_needed = 0; + } else if (vcpu->arch.hcall_needed) { + int i; + + kvmppc_set_gpr(vcpu, 3, run->papr_hcall.ret); + for (i = 0; i < 9; ++i) + kvmppc_set_gpr(vcpu, 4 + i, run->papr_hcall.args[i]); + vcpu->arch.hcall_needed = 0; } kvmppc_core_deliver_interrupts(vcpu); - local_irq_disable(); - kvm_guest_enter(); - r = __kvmppc_vcpu_run(run, vcpu); - kvm_guest_exit(); - local_irq_enable(); + r = kvmppc_vcpu_run(run, vcpu); if (vcpu->sigset_active) sigprocmask(SIG_SETMASK, &sigsaved, NULL); @@ -518,6 +551,8 @@ int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq) if (waitqueue_active(&vcpu->wq)) { wake_up_interruptible(&vcpu->wq); vcpu->stat.halt_wakeup++; + } else if (vcpu->cpu != -1) { + smp_send_reschedule(vcpu->cpu); } return 0; @@ -633,6 +668,29 @@ long kvm_arch_vm_ioctl(struct file *filp, break; } +#ifdef CONFIG_KVM_BOOK3S_64_HV + case KVM_CREATE_SPAPR_TCE: { + struct kvm_create_spapr_tce create_tce; + struct kvm *kvm = filp->private_data; + + r = -EFAULT; + if (copy_from_user(&create_tce, argp, sizeof(create_tce))) + goto out; + r = kvm_vm_ioctl_create_spapr_tce(kvm, &create_tce); + goto out; + } + + case KVM_ALLOCATE_RMA: { + struct kvm *kvm = filp->private_data; + struct kvm_allocate_rma rma; + + r = kvm_vm_ioctl_allocate_rma(kvm, &rma); + if (r >= 0 && copy_to_user(argp, &rma, sizeof(rma))) + r = -EFAULT; + break; + } +#endif /* CONFIG_KVM_BOOK3S_64_HV */ + default: r = -ENOTTY; } diff --git a/arch/powerpc/kvm/timing.c b/arch/powerpc/kvm/timing.c index 319177df958..07b6110a4bb 100644 --- a/arch/powerpc/kvm/timing.c +++ b/arch/powerpc/kvm/timing.c @@ -56,15 +56,6 @@ static void add_exit_timing(struct kvm_vcpu *vcpu, u64 duration, int type) { u64 old; - do_div(duration, tb_ticks_per_usec); - if (unlikely(duration > 0xFFFFFFFF)) { - printk(KERN_ERR"%s - duration too big -> overflow" - " duration %lld type %d exit #%d\n", - __func__, duration, type, - vcpu->arch.timing_count_type[type]); - return; - } - mutex_lock(&vcpu->arch.exit_timing_lock); vcpu->arch.timing_count_type[type]++; diff --git a/arch/powerpc/kvm/trace.h b/arch/powerpc/kvm/trace.h index 3aca1b042b8..b135d3d397d 100644 --- a/arch/powerpc/kvm/trace.h +++ b/arch/powerpc/kvm/trace.h @@ -103,7 +103,7 @@ TRACE_EVENT(kvm_gtlb_write, * Book3S trace points * *************************************************************************/ -#ifdef CONFIG_PPC_BOOK3S +#ifdef CONFIG_KVM_BOOK3S_PR TRACE_EVENT(kvm_book3s_exit, TP_PROTO(unsigned int exit_nr, struct kvm_vcpu *vcpu), @@ -252,7 +252,7 @@ TRACE_EVENT(kvm_book3s_mmu_flush, ), TP_fast_assign( - __entry->count = vcpu->arch.hpte_cache_count; + __entry->count = to_book3s(vcpu)->hpte_cache_count; __entry->p1 = p1; __entry->p2 = p2; __entry->type = type; diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index ad35f66c69e..5efe8c96d37 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -174,7 +174,7 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address, die("Weird page fault", regs, SIGSEGV); } - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, 0, regs, address); + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); /* When running in the kernel we expect faults to occur only to * addresses in user space. All other faults represent errors in the @@ -320,7 +320,7 @@ good_area: } if (ret & VM_FAULT_MAJOR) { current->maj_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0, + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address); #ifdef CONFIG_PPC_SMLPAR if (firmware_has_feature(FW_FEATURE_CMO)) { @@ -331,7 +331,7 @@ good_area: #endif } else { current->min_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0, + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address); } up_read(&mm->mmap_sem); diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c index dfd764896db..90039bc6411 100644 --- a/arch/powerpc/mm/hash_native_64.c +++ b/arch/powerpc/mm/hash_native_64.c @@ -37,7 +37,7 @@ #define HPTE_LOCK_BIT 3 -static DEFINE_RAW_SPINLOCK(native_tlbie_lock); +DEFINE_RAW_SPINLOCK(native_tlbie_lock); static inline void __tlbie(unsigned long va, int psize, int ssize) { @@ -51,7 +51,7 @@ static inline void __tlbie(unsigned long va, int psize, int ssize) va &= ~0xffful; va |= ssize << 8; asm volatile(ASM_FTR_IFCLR("tlbie %0,0", PPC_TLBIE(%1,%0), %2) - : : "r" (va), "r"(0), "i" (CPU_FTR_HVMODE_206) + : : "r" (va), "r"(0), "i" (CPU_FTR_ARCH_206) : "memory"); break; default: @@ -61,7 +61,7 @@ static inline void __tlbie(unsigned long va, int psize, int ssize) va |= ssize << 8; va |= 1; /* L */ asm volatile(ASM_FTR_IFCLR("tlbie %0,1", PPC_TLBIE(%1,%0), %2) - : : "r" (va), "r"(0), "i" (CPU_FTR_HVMODE_206) + : : "r" (va), "r"(0), "i" (CPU_FTR_ARCH_206) : "memory"); break; } diff --git a/arch/powerpc/net/Makefile b/arch/powerpc/net/Makefile new file mode 100644 index 00000000000..266b3950c3a --- /dev/null +++ b/arch/powerpc/net/Makefile @@ -0,0 +1,4 @@ +# +# Arch-specific network modules +# +obj-$(CONFIG_BPF_JIT) += bpf_jit_64.o bpf_jit_comp.o diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h new file mode 100644 index 00000000000..af1ab5e9a69 --- /dev/null +++ b/arch/powerpc/net/bpf_jit.h @@ -0,0 +1,227 @@ +/* bpf_jit.h: BPF JIT compiler for PPC64 + * + * Copyright 2011 Matt Evans <matt@ozlabs.org>, 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; version 2 + * of the License. + */ +#ifndef _BPF_JIT_H +#define _BPF_JIT_H + +#define BPF_PPC_STACK_LOCALS 32 +#define BPF_PPC_STACK_BASIC (48+64) +#define BPF_PPC_STACK_SAVE (18*8) +#define BPF_PPC_STACKFRAME (BPF_PPC_STACK_BASIC+BPF_PPC_STACK_LOCALS+ \ + BPF_PPC_STACK_SAVE) +#define BPF_PPC_SLOWPATH_FRAME (48+64) + +/* + * Generated code register usage: + * + * As normal PPC C ABI (e.g. r1=sp, r2=TOC), with: + * + * skb r3 (Entry parameter) + * A register r4 + * X register r5 + * addr param r6 + * r7-r10 scratch + * skb->data r14 + * skb headlen r15 (skb->len - skb->data_len) + * m[0] r16 + * m[...] ... + * m[15] r31 + */ +#define r_skb 3 +#define r_ret 3 +#define r_A 4 +#define r_X 5 +#define r_addr 6 +#define r_scratch1 7 +#define r_D 14 +#define r_HL 15 +#define r_M 16 + +#ifndef __ASSEMBLY__ + +/* + * Assembly helpers from arch/powerpc/net/bpf_jit.S: + */ +extern u8 sk_load_word[], sk_load_half[], sk_load_byte[], sk_load_byte_msh[]; + +#define FUNCTION_DESCR_SIZE 24 + +/* + * 16-bit immediate helper macros: HA() is for use with sign-extending instrs + * (e.g. LD, ADDI). If the bottom 16 bits is "-ve", add another bit into the + * top half to negate the effect (i.e. 0xffff + 1 = 0x(1)0000). + */ +#define IMM_H(i) ((uintptr_t)(i)>>16) +#define IMM_HA(i) (((uintptr_t)(i)>>16) + \ + (((uintptr_t)(i) & 0x8000) >> 15)) +#define IMM_L(i) ((uintptr_t)(i) & 0xffff) + +#define PLANT_INSTR(d, idx, instr) \ + do { if (d) { (d)[idx] = instr; } idx++; } while (0) +#define EMIT(instr) PLANT_INSTR(image, ctx->idx, instr) + +#define PPC_NOP() EMIT(PPC_INST_NOP) +#define PPC_BLR() EMIT(PPC_INST_BLR) +#define PPC_BLRL() EMIT(PPC_INST_BLRL) +#define PPC_MTLR(r) EMIT(PPC_INST_MTLR | __PPC_RT(r)) +#define PPC_ADDI(d, a, i) EMIT(PPC_INST_ADDI | __PPC_RT(d) | \ + __PPC_RA(a) | IMM_L(i)) +#define PPC_MR(d, a) PPC_OR(d, a, a) +#define PPC_LI(r, i) PPC_ADDI(r, 0, i) +#define PPC_ADDIS(d, a, i) EMIT(PPC_INST_ADDIS | \ + __PPC_RS(d) | __PPC_RA(a) | IMM_L(i)) +#define PPC_LIS(r, i) PPC_ADDIS(r, 0, i) +#define PPC_STD(r, base, i) EMIT(PPC_INST_STD | __PPC_RS(r) | \ + __PPC_RA(base) | ((i) & 0xfffc)) + +#define PPC_LD(r, base, i) EMIT(PPC_INST_LD | __PPC_RT(r) | \ + __PPC_RA(base) | IMM_L(i)) +#define PPC_LWZ(r, base, i) EMIT(PPC_INST_LWZ | __PPC_RT(r) | \ + __PPC_RA(base) | IMM_L(i)) +#define PPC_LHZ(r, base, i) EMIT(PPC_INST_LHZ | __PPC_RT(r) | \ + __PPC_RA(base) | IMM_L(i)) +/* Convenience helpers for the above with 'far' offsets: */ +#define PPC_LD_OFFS(r, base, i) do { if ((i) < 32768) PPC_LD(r, base, i); \ + else { PPC_ADDIS(r, base, IMM_HA(i)); \ + PPC_LD(r, r, IMM_L(i)); } } while(0) + +#define PPC_LWZ_OFFS(r, base, i) do { if ((i) < 32768) PPC_LWZ(r, base, i); \ + else { PPC_ADDIS(r, base, IMM_HA(i)); \ + PPC_LWZ(r, r, IMM_L(i)); } } while(0) + +#define PPC_LHZ_OFFS(r, base, i) do { if ((i) < 32768) PPC_LHZ(r, base, i); \ + else { PPC_ADDIS(r, base, IMM_HA(i)); \ + PPC_LHZ(r, r, IMM_L(i)); } } while(0) + +#define PPC_CMPWI(a, i) EMIT(PPC_INST_CMPWI | __PPC_RA(a) | IMM_L(i)) +#define PPC_CMPDI(a, i) EMIT(PPC_INST_CMPDI | __PPC_RA(a) | IMM_L(i)) +#define PPC_CMPLWI(a, i) EMIT(PPC_INST_CMPLWI | __PPC_RA(a) | IMM_L(i)) +#define PPC_CMPLW(a, b) EMIT(PPC_INST_CMPLW | __PPC_RA(a) | __PPC_RB(b)) + +#define PPC_SUB(d, a, b) EMIT(PPC_INST_SUB | __PPC_RT(d) | \ + __PPC_RB(a) | __PPC_RA(b)) +#define PPC_ADD(d, a, b) EMIT(PPC_INST_ADD | __PPC_RT(d) | \ + __PPC_RA(a) | __PPC_RB(b)) +#define PPC_MUL(d, a, b) EMIT(PPC_INST_MULLW | __PPC_RT(d) | \ + __PPC_RA(a) | __PPC_RB(b)) +#define PPC_MULHWU(d, a, b) EMIT(PPC_INST_MULHWU | __PPC_RT(d) | \ + __PPC_RA(a) | __PPC_RB(b)) +#define PPC_MULI(d, a, i) EMIT(PPC_INST_MULLI | __PPC_RT(d) | \ + __PPC_RA(a) | IMM_L(i)) +#define PPC_DIVWU(d, a, b) EMIT(PPC_INST_DIVWU | __PPC_RT(d) | \ + __PPC_RA(a) | __PPC_RB(b)) +#define PPC_AND(d, a, b) EMIT(PPC_INST_AND | __PPC_RA(d) | \ + __PPC_RS(a) | __PPC_RB(b)) +#define PPC_ANDI(d, a, i) EMIT(PPC_INST_ANDI | __PPC_RA(d) | \ + __PPC_RS(a) | IMM_L(i)) +#define PPC_AND_DOT(d, a, b) EMIT(PPC_INST_ANDDOT | __PPC_RA(d) | \ + __PPC_RS(a) | __PPC_RB(b)) +#define PPC_OR(d, a, b) EMIT(PPC_INST_OR | __PPC_RA(d) | \ + __PPC_RS(a) | __PPC_RB(b)) +#define PPC_ORI(d, a, i) EMIT(PPC_INST_ORI | __PPC_RA(d) | \ + __PPC_RS(a) | IMM_L(i)) +#define PPC_ORIS(d, a, i) EMIT(PPC_INST_ORIS | __PPC_RA(d) | \ + __PPC_RS(a) | IMM_L(i)) +#define PPC_SLW(d, a, s) EMIT(PPC_INST_SLW | __PPC_RA(d) | \ + __PPC_RS(a) | __PPC_RB(s)) +#define PPC_SRW(d, a, s) EMIT(PPC_INST_SRW | __PPC_RA(d) | \ + __PPC_RS(a) | __PPC_RB(s)) +/* slwi = rlwinm Rx, Ry, n, 0, 31-n */ +#define PPC_SLWI(d, a, i) EMIT(PPC_INST_RLWINM | __PPC_RA(d) | \ + __PPC_RS(a) | __PPC_SH(i) | \ + __PPC_MB(0) | __PPC_ME(31-(i))) +/* srwi = rlwinm Rx, Ry, 32-n, n, 31 */ +#define PPC_SRWI(d, a, i) EMIT(PPC_INST_RLWINM | __PPC_RA(d) | \ + __PPC_RS(a) | __PPC_SH(32-(i)) | \ + __PPC_MB(i) | __PPC_ME(31)) +/* sldi = rldicr Rx, Ry, n, 63-n */ +#define PPC_SLDI(d, a, i) EMIT(PPC_INST_RLDICR | __PPC_RA(d) | \ + __PPC_RS(a) | __PPC_SH(i) | \ + __PPC_MB(63-(i)) | (((i) & 0x20) >> 4)) +#define PPC_NEG(d, a) EMIT(PPC_INST_NEG | __PPC_RT(d) | __PPC_RA(a)) + +/* Long jump; (unconditional 'branch') */ +#define PPC_JMP(dest) EMIT(PPC_INST_BRANCH | \ + (((dest) - (ctx->idx * 4)) & 0x03fffffc)) +/* "cond" here covers BO:BI fields. */ +#define PPC_BCC_SHORT(cond, dest) EMIT(PPC_INST_BRANCH_COND | \ + (((cond) & 0x3ff) << 16) | \ + (((dest) - (ctx->idx * 4)) & \ + 0xfffc)) +#define PPC_LI32(d, i) do { PPC_LI(d, IMM_L(i)); \ + if ((u32)(uintptr_t)(i) >= 32768) { \ + PPC_ADDIS(d, d, IMM_HA(i)); \ + } } while(0) +#define PPC_LI64(d, i) do { \ + if (!((uintptr_t)(i) & 0xffffffff00000000ULL)) \ + PPC_LI32(d, i); \ + else { \ + PPC_LIS(d, ((uintptr_t)(i) >> 48)); \ + if ((uintptr_t)(i) & 0x0000ffff00000000ULL) \ + PPC_ORI(d, d, \ + ((uintptr_t)(i) >> 32) & 0xffff); \ + PPC_SLDI(d, d, 32); \ + if ((uintptr_t)(i) & 0x00000000ffff0000ULL) \ + PPC_ORIS(d, d, \ + ((uintptr_t)(i) >> 16) & 0xffff); \ + if ((uintptr_t)(i) & 0x000000000000ffffULL) \ + PPC_ORI(d, d, (uintptr_t)(i) & 0xffff); \ + } } while (0); + +static inline bool is_nearbranch(int offset) +{ + return (offset < 32768) && (offset >= -32768); +} + +/* + * The fly in the ointment of code size changing from pass to pass is + * avoided by padding the short branch case with a NOP. If code size differs + * with different branch reaches we will have the issue of code moving from + * one pass to the next and will need a few passes to converge on a stable + * state. + */ +#define PPC_BCC(cond, dest) do { \ + if (is_nearbranch((dest) - (ctx->idx * 4))) { \ + PPC_BCC_SHORT(cond, dest); \ + PPC_NOP(); \ + } else { \ + /* Flip the 'T or F' bit to invert comparison */ \ + PPC_BCC_SHORT(cond ^ COND_CMP_TRUE, (ctx->idx+2)*4); \ + PPC_JMP(dest); \ + } } while(0) + +/* To create a branch condition, select a bit of cr0... */ +#define CR0_LT 0 +#define CR0_GT 1 +#define CR0_EQ 2 +/* ...and modify BO[3] */ +#define COND_CMP_TRUE 0x100 +#define COND_CMP_FALSE 0x000 +/* Together, they make all required comparisons: */ +#define COND_GT (CR0_GT | COND_CMP_TRUE) +#define COND_GE (CR0_LT | COND_CMP_FALSE) +#define COND_EQ (CR0_EQ | COND_CMP_TRUE) +#define COND_NE (CR0_EQ | COND_CMP_FALSE) +#define COND_LT (CR0_LT | COND_CMP_TRUE) + +#define SEEN_DATAREF 0x10000 /* might call external helpers */ +#define SEEN_XREG 0x20000 /* X reg is used */ +#define SEEN_MEM 0x40000 /* SEEN_MEM+(1<<n) = use mem[n] for temporary + * storage */ +#define SEEN_MEM_MSK 0x0ffff + +struct codegen_context { + unsigned int seen; + unsigned int idx; + int pc_ret0; /* bpf index of first RET #0 instruction (if any) */ +}; + +#endif + +#endif diff --git a/arch/powerpc/net/bpf_jit_64.S b/arch/powerpc/net/bpf_jit_64.S new file mode 100644 index 00000000000..ff4506e85cc --- /dev/null +++ b/arch/powerpc/net/bpf_jit_64.S @@ -0,0 +1,138 @@ +/* bpf_jit.S: Packet/header access helper functions + * for PPC64 BPF compiler. + * + * Copyright 2011 Matt Evans <matt@ozlabs.org>, 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; version 2 + * of the License. + */ + +#include <asm/ppc_asm.h> +#include "bpf_jit.h" + +/* + * All of these routines are called directly from generated code, + * whose register usage is: + * + * r3 skb + * r4,r5 A,X + * r6 *** address parameter to helper *** + * r7-r10 scratch + * r14 skb->data + * r15 skb headlen + * r16-31 M[] + */ + +/* + * To consider: These helpers are so small it could be better to just + * generate them inline. Inline code can do the simple headlen check + * then branch directly to slow_path_XXX if required. (In fact, could + * load a spare GPR with the address of slow_path_generic and pass size + * as an argument, making the call site a mtlr, li and bllr.) + * + * Technically, the "is addr < 0" check is unnecessary & slowing down + * the ABS path, as it's statically checked on generation. + */ + .globl sk_load_word +sk_load_word: + cmpdi r_addr, 0 + blt bpf_error + /* Are we accessing past headlen? */ + subi r_scratch1, r_HL, 4 + cmpd r_scratch1, r_addr + blt bpf_slow_path_word + /* Nope, just hitting the header. cr0 here is eq or gt! */ + lwzx r_A, r_D, r_addr + /* When big endian we don't need to byteswap. */ + blr /* Return success, cr0 != LT */ + + .globl sk_load_half +sk_load_half: + cmpdi r_addr, 0 + blt bpf_error + subi r_scratch1, r_HL, 2 + cmpd r_scratch1, r_addr + blt bpf_slow_path_half + lhzx r_A, r_D, r_addr + blr + + .globl sk_load_byte +sk_load_byte: + cmpdi r_addr, 0 + blt bpf_error + cmpd r_HL, r_addr + ble bpf_slow_path_byte + lbzx r_A, r_D, r_addr + blr + +/* + * BPF_S_LDX_B_MSH: ldxb 4*([offset]&0xf) + * r_addr is the offset value, already known positive + */ + .globl sk_load_byte_msh +sk_load_byte_msh: + cmpd r_HL, r_addr + ble bpf_slow_path_byte_msh + lbzx r_X, r_D, r_addr + rlwinm r_X, r_X, 2, 32-4-2, 31-2 + blr + +bpf_error: + /* Entered with cr0 = lt */ + li r3, 0 + /* Generated code will 'blt epilogue', returning 0. */ + blr + +/* Call out to skb_copy_bits: + * We'll need to back up our volatile regs first; we have + * local variable space at r1+(BPF_PPC_STACK_BASIC). + * Allocate a new stack frame here to remain ABI-compliant in + * stashing LR. + */ +#define bpf_slow_path_common(SIZE) \ + mflr r0; \ + std r0, 16(r1); \ + /* R3 goes in parameter space of caller's frame */ \ + std r_skb, (BPF_PPC_STACKFRAME+48)(r1); \ + std r_A, (BPF_PPC_STACK_BASIC+(0*8))(r1); \ + std r_X, (BPF_PPC_STACK_BASIC+(1*8))(r1); \ + addi r5, r1, BPF_PPC_STACK_BASIC+(2*8); \ + stdu r1, -BPF_PPC_SLOWPATH_FRAME(r1); \ + /* R3 = r_skb, as passed */ \ + mr r4, r_addr; \ + li r6, SIZE; \ + bl skb_copy_bits; \ + /* R3 = 0 on success */ \ + addi r1, r1, BPF_PPC_SLOWPATH_FRAME; \ + ld r0, 16(r1); \ + ld r_A, (BPF_PPC_STACK_BASIC+(0*8))(r1); \ + ld r_X, (BPF_PPC_STACK_BASIC+(1*8))(r1); \ + mtlr r0; \ + cmpdi r3, 0; \ + blt bpf_error; /* cr0 = LT */ \ + ld r_skb, (BPF_PPC_STACKFRAME+48)(r1); \ + /* Great success! */ + +bpf_slow_path_word: + bpf_slow_path_common(4) + /* Data value is on stack, and cr0 != LT */ + lwz r_A, BPF_PPC_STACK_BASIC+(2*8)(r1) + blr + +bpf_slow_path_half: + bpf_slow_path_common(2) + lhz r_A, BPF_PPC_STACK_BASIC+(2*8)(r1) + blr + +bpf_slow_path_byte: + bpf_slow_path_common(1) + lbz r_A, BPF_PPC_STACK_BASIC+(2*8)(r1) + blr + +bpf_slow_path_byte_msh: + bpf_slow_path_common(1) + lbz r_X, BPF_PPC_STACK_BASIC+(2*8)(r1) + rlwinm r_X, r_X, 2, 32-4-2, 31-2 + blr diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c new file mode 100644 index 00000000000..73619d3aeb6 --- /dev/null +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -0,0 +1,694 @@ +/* bpf_jit_comp.c: BPF JIT compiler for PPC64 + * + * Copyright 2011 Matt Evans <matt@ozlabs.org>, IBM Corporation + * + * Based on the x86 BPF compiler, by Eric Dumazet (eric.dumazet@gmail.com) + * + * 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; version 2 + * of the License. + */ +#include <linux/moduleloader.h> +#include <asm/cacheflush.h> +#include <linux/netdevice.h> +#include <linux/filter.h> +#include "bpf_jit.h" + +#ifndef __BIG_ENDIAN +/* There are endianness assumptions herein. */ +#error "Little-endian PPC not supported in BPF compiler" +#endif + +int bpf_jit_enable __read_mostly; + + +static inline void bpf_flush_icache(void *start, void *end) +{ + smp_wmb(); + flush_icache_range((unsigned long)start, (unsigned long)end); +} + +static void bpf_jit_build_prologue(struct sk_filter *fp, u32 *image, + struct codegen_context *ctx) +{ + int i; + const struct sock_filter *filter = fp->insns; + + if (ctx->seen & (SEEN_MEM | SEEN_DATAREF)) { + /* Make stackframe */ + if (ctx->seen & SEEN_DATAREF) { + /* If we call any helpers (for loads), save LR */ + EMIT(PPC_INST_MFLR | __PPC_RT(0)); + PPC_STD(0, 1, 16); + + /* Back up non-volatile regs. */ + PPC_STD(r_D, 1, -(8*(32-r_D))); + PPC_STD(r_HL, 1, -(8*(32-r_HL))); + } + if (ctx->seen & SEEN_MEM) { + /* + * Conditionally save regs r15-r31 as some will be used + * for M[] data. + */ + for (i = r_M; i < (r_M+16); i++) { + if (ctx->seen & (1 << (i-r_M))) + PPC_STD(i, 1, -(8*(32-i))); + } + } + EMIT(PPC_INST_STDU | __PPC_RS(1) | __PPC_RA(1) | + (-BPF_PPC_STACKFRAME & 0xfffc)); + } + + if (ctx->seen & SEEN_DATAREF) { + /* + * If this filter needs to access skb data, + * prepare r_D and r_HL: + * r_HL = skb->len - skb->data_len + * r_D = skb->data + */ + PPC_LWZ_OFFS(r_scratch1, r_skb, offsetof(struct sk_buff, + data_len)); + PPC_LWZ_OFFS(r_HL, r_skb, offsetof(struct sk_buff, len)); + PPC_SUB(r_HL, r_HL, r_scratch1); + PPC_LD_OFFS(r_D, r_skb, offsetof(struct sk_buff, data)); + } + + if (ctx->seen & SEEN_XREG) { + /* + * TODO: Could also detect whether first instr. sets X and + * avoid this (as below, with A). + */ + PPC_LI(r_X, 0); + } + + switch (filter[0].code) { + case BPF_S_RET_K: + case BPF_S_LD_W_LEN: + case BPF_S_ANC_PROTOCOL: + case BPF_S_ANC_IFINDEX: + case BPF_S_ANC_MARK: + case BPF_S_ANC_RXHASH: + case BPF_S_ANC_CPU: + case BPF_S_ANC_QUEUE: + case BPF_S_LD_W_ABS: + case BPF_S_LD_H_ABS: + case BPF_S_LD_B_ABS: + /* first instruction sets A register (or is RET 'constant') */ + break; + default: + /* make sure we dont leak kernel information to user */ + PPC_LI(r_A, 0); + } +} + +static void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx) +{ + int i; + + if (ctx->seen & (SEEN_MEM | SEEN_DATAREF)) { + PPC_ADDI(1, 1, BPF_PPC_STACKFRAME); + if (ctx->seen & SEEN_DATAREF) { + PPC_LD(0, 1, 16); + PPC_MTLR(0); + PPC_LD(r_D, 1, -(8*(32-r_D))); + PPC_LD(r_HL, 1, -(8*(32-r_HL))); + } + if (ctx->seen & SEEN_MEM) { + /* Restore any saved non-vol registers */ + for (i = r_M; i < (r_M+16); i++) { + if (ctx->seen & (1 << (i-r_M))) + PPC_LD(i, 1, -(8*(32-i))); + } + } + } + /* The RETs have left a return value in R3. */ + + PPC_BLR(); +} + +/* Assemble the body code between the prologue & epilogue. */ +static int bpf_jit_build_body(struct sk_filter *fp, u32 *image, + struct codegen_context *ctx, + unsigned int *addrs) +{ + const struct sock_filter *filter = fp->insns; + int flen = fp->len; + u8 *func; + unsigned int true_cond; + int i; + + /* Start of epilogue code */ + unsigned int exit_addr = addrs[flen]; + + for (i = 0; i < flen; i++) { + unsigned int K = filter[i].k; + + /* + * addrs[] maps a BPF bytecode address into a real offset from + * the start of the body code. + */ + addrs[i] = ctx->idx * 4; + + switch (filter[i].code) { + /*** ALU ops ***/ + case BPF_S_ALU_ADD_X: /* A += X; */ + ctx->seen |= SEEN_XREG; + PPC_ADD(r_A, r_A, r_X); + break; + case BPF_S_ALU_ADD_K: /* A += K; */ + if (!K) + break; + PPC_ADDI(r_A, r_A, IMM_L(K)); + if (K >= 32768) + PPC_ADDIS(r_A, r_A, IMM_HA(K)); + break; + case BPF_S_ALU_SUB_X: /* A -= X; */ + ctx->seen |= SEEN_XREG; + PPC_SUB(r_A, r_A, r_X); + break; + case BPF_S_ALU_SUB_K: /* A -= K */ + if (!K) + break; + PPC_ADDI(r_A, r_A, IMM_L(-K)); + if (K >= 32768) + PPC_ADDIS(r_A, r_A, IMM_HA(-K)); + break; + case BPF_S_ALU_MUL_X: /* A *= X; */ + ctx->seen |= SEEN_XREG; + PPC_MUL(r_A, r_A, r_X); + break; + case BPF_S_ALU_MUL_K: /* A *= K */ + if (K < 32768) + PPC_MULI(r_A, r_A, K); + else { + PPC_LI32(r_scratch1, K); + PPC_MUL(r_A, r_A, r_scratch1); + } + break; + case BPF_S_ALU_DIV_X: /* A /= X; */ + ctx->seen |= SEEN_XREG; + PPC_CMPWI(r_X, 0); + if (ctx->pc_ret0 != -1) { + PPC_BCC(COND_EQ, addrs[ctx->pc_ret0]); + } else { + /* + * Exit, returning 0; first pass hits here + * (longer worst-case code size). + */ + PPC_BCC_SHORT(COND_NE, (ctx->idx*4)+12); + PPC_LI(r_ret, 0); + PPC_JMP(exit_addr); + } + PPC_DIVWU(r_A, r_A, r_X); + break; + case BPF_S_ALU_DIV_K: /* A = reciprocal_divide(A, K); */ + PPC_LI32(r_scratch1, K); + /* Top 32 bits of 64bit result -> A */ + PPC_MULHWU(r_A, r_A, r_scratch1); + break; + case BPF_S_ALU_AND_X: + ctx->seen |= SEEN_XREG; + PPC_AND(r_A, r_A, r_X); + break; + case BPF_S_ALU_AND_K: + if (!IMM_H(K)) + PPC_ANDI(r_A, r_A, K); + else { + PPC_LI32(r_scratch1, K); + PPC_AND(r_A, r_A, r_scratch1); + } + break; + case BPF_S_ALU_OR_X: + ctx->seen |= SEEN_XREG; + PPC_OR(r_A, r_A, r_X); + break; + case BPF_S_ALU_OR_K: + if (IMM_L(K)) + PPC_ORI(r_A, r_A, IMM_L(K)); + if (K >= 65536) + PPC_ORIS(r_A, r_A, IMM_H(K)); + break; + case BPF_S_ALU_LSH_X: /* A <<= X; */ + ctx->seen |= SEEN_XREG; + PPC_SLW(r_A, r_A, r_X); + break; + case BPF_S_ALU_LSH_K: + if (K == 0) + break; + else + PPC_SLWI(r_A, r_A, K); + break; + case BPF_S_ALU_RSH_X: /* A >>= X; */ + ctx->seen |= SEEN_XREG; + PPC_SRW(r_A, r_A, r_X); + break; + case BPF_S_ALU_RSH_K: /* A >>= K; */ + if (K == 0) + break; + else + PPC_SRWI(r_A, r_A, K); + break; + case BPF_S_ALU_NEG: + PPC_NEG(r_A, r_A); + break; + case BPF_S_RET_K: + PPC_LI32(r_ret, K); + if (!K) { + if (ctx->pc_ret0 == -1) + ctx->pc_ret0 = i; + } + /* + * If this isn't the very last instruction, branch to + * the epilogue if we've stuff to clean up. Otherwise, + * if there's nothing to tidy, just return. If we /are/ + * the last instruction, we're about to fall through to + * the epilogue to return. + */ + if (i != flen - 1) { + /* + * Note: 'seen' is properly valid only on pass + * #2. Both parts of this conditional are the + * same instruction size though, meaning the + * first pass will still correctly determine the + * code size/addresses. + */ + if (ctx->seen) + PPC_JMP(exit_addr); + else + PPC_BLR(); + } + break; + case BPF_S_RET_A: + PPC_MR(r_ret, r_A); + if (i != flen - 1) { + if (ctx->seen) + PPC_JMP(exit_addr); + else + PPC_BLR(); + } + break; + case BPF_S_MISC_TAX: /* X = A */ + PPC_MR(r_X, r_A); + break; + case BPF_S_MISC_TXA: /* A = X */ + ctx->seen |= SEEN_XREG; + PPC_MR(r_A, r_X); + break; + + /*** Constant loads/M[] access ***/ + case BPF_S_LD_IMM: /* A = K */ + PPC_LI32(r_A, K); + break; + case BPF_S_LDX_IMM: /* X = K */ + PPC_LI32(r_X, K); + break; + case BPF_S_LD_MEM: /* A = mem[K] */ + PPC_MR(r_A, r_M + (K & 0xf)); + ctx->seen |= SEEN_MEM | (1<<(K & 0xf)); + break; + case BPF_S_LDX_MEM: /* X = mem[K] */ + PPC_MR(r_X, r_M + (K & 0xf)); + ctx->seen |= SEEN_MEM | (1<<(K & 0xf)); + break; + case BPF_S_ST: /* mem[K] = A */ + PPC_MR(r_M + (K & 0xf), r_A); + ctx->seen |= SEEN_MEM | (1<<(K & 0xf)); + break; + case BPF_S_STX: /* mem[K] = X */ + PPC_MR(r_M + (K & 0xf), r_X); + ctx->seen |= SEEN_XREG | SEEN_MEM | (1<<(K & 0xf)); + break; + case BPF_S_LD_W_LEN: /* A = skb->len; */ + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4); + PPC_LWZ_OFFS(r_A, r_skb, offsetof(struct sk_buff, len)); + break; + case BPF_S_LDX_W_LEN: /* X = skb->len; */ + PPC_LWZ_OFFS(r_X, r_skb, offsetof(struct sk_buff, len)); + break; + + /*** Ancillary info loads ***/ + + /* None of the BPF_S_ANC* codes appear to be passed by + * sk_chk_filter(). The interpreter and the x86 BPF + * compiler implement them so we do too -- they may be + * planted in future. + */ + case BPF_S_ANC_PROTOCOL: /* A = ntohs(skb->protocol); */ + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, + protocol) != 2); + PPC_LHZ_OFFS(r_A, r_skb, offsetof(struct sk_buff, + protocol)); + /* ntohs is a NOP with BE loads. */ + break; + case BPF_S_ANC_IFINDEX: + PPC_LD_OFFS(r_scratch1, r_skb, offsetof(struct sk_buff, + dev)); + PPC_CMPDI(r_scratch1, 0); + if (ctx->pc_ret0 != -1) { + PPC_BCC(COND_EQ, addrs[ctx->pc_ret0]); + } else { + /* Exit, returning 0; first pass hits here. */ + PPC_BCC_SHORT(COND_NE, (ctx->idx*4)+12); + PPC_LI(r_ret, 0); + PPC_JMP(exit_addr); + } + BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, + ifindex) != 4); + PPC_LWZ_OFFS(r_A, r_scratch1, + offsetof(struct net_device, ifindex)); + break; + case BPF_S_ANC_MARK: + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4); + PPC_LWZ_OFFS(r_A, r_skb, offsetof(struct sk_buff, + mark)); + break; + case BPF_S_ANC_RXHASH: + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, rxhash) != 4); + PPC_LWZ_OFFS(r_A, r_skb, offsetof(struct sk_buff, + rxhash)); + break; + case BPF_S_ANC_QUEUE: + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, + queue_mapping) != 2); + PPC_LHZ_OFFS(r_A, r_skb, offsetof(struct sk_buff, + queue_mapping)); + break; + case BPF_S_ANC_CPU: +#ifdef CONFIG_SMP + /* + * PACA ptr is r13: + * raw_smp_processor_id() = local_paca->paca_index + */ + BUILD_BUG_ON(FIELD_SIZEOF(struct paca_struct, + paca_index) != 2); + PPC_LHZ_OFFS(r_A, 13, + offsetof(struct paca_struct, paca_index)); +#else + PPC_LI(r_A, 0); +#endif + break; + + /*** Absolute loads from packet header/data ***/ + case BPF_S_LD_W_ABS: + func = sk_load_word; + goto common_load; + case BPF_S_LD_H_ABS: + func = sk_load_half; + goto common_load; + case BPF_S_LD_B_ABS: + func = sk_load_byte; + common_load: + /* + * Load from [K]. Reference with the (negative) + * SKF_NET_OFF/SKF_LL_OFF offsets is unsupported. + */ + ctx->seen |= SEEN_DATAREF; + if ((int)K < 0) + return -ENOTSUPP; + PPC_LI64(r_scratch1, func); + PPC_MTLR(r_scratch1); + PPC_LI32(r_addr, K); + PPC_BLRL(); + /* + * Helper returns 'lt' condition on error, and an + * appropriate return value in r3 + */ + PPC_BCC(COND_LT, exit_addr); + break; + + /*** Indirect loads from packet header/data ***/ + case BPF_S_LD_W_IND: + func = sk_load_word; + goto common_load_ind; + case BPF_S_LD_H_IND: + func = sk_load_half; + goto common_load_ind; + case BPF_S_LD_B_IND: + func = sk_load_byte; + common_load_ind: + /* + * Load from [X + K]. Negative offsets are tested for + * in the helper functions, and result in a 'ret 0'. + */ + ctx->seen |= SEEN_DATAREF | SEEN_XREG; + PPC_LI64(r_scratch1, func); + PPC_MTLR(r_scratch1); + PPC_ADDI(r_addr, r_X, IMM_L(K)); + if (K >= 32768) + PPC_ADDIS(r_addr, r_addr, IMM_HA(K)); + PPC_BLRL(); + /* If error, cr0.LT set */ + PPC_BCC(COND_LT, exit_addr); + break; + + case BPF_S_LDX_B_MSH: + /* + * x86 version drops packet (RET 0) when K<0, whereas + * interpreter does allow K<0 (__load_pointer, special + * ancillary data). common_load returns ENOTSUPP if K<0, + * so we fall back to interpreter & filter works. + */ + func = sk_load_byte_msh; + goto common_load; + break; + + /*** Jump and branches ***/ + case BPF_S_JMP_JA: + if (K != 0) + PPC_JMP(addrs[i + 1 + K]); + break; + + case BPF_S_JMP_JGT_K: + case BPF_S_JMP_JGT_X: + true_cond = COND_GT; + goto cond_branch; + case BPF_S_JMP_JGE_K: + case BPF_S_JMP_JGE_X: + true_cond = COND_GE; + goto cond_branch; + case BPF_S_JMP_JEQ_K: + case BPF_S_JMP_JEQ_X: + true_cond = COND_EQ; + goto cond_branch; + case BPF_S_JMP_JSET_K: + case BPF_S_JMP_JSET_X: + true_cond = COND_NE; + /* Fall through */ + cond_branch: + /* same targets, can avoid doing the test :) */ + if (filter[i].jt == filter[i].jf) { + if (filter[i].jt > 0) + PPC_JMP(addrs[i + 1 + filter[i].jt]); + break; + } + + switch (filter[i].code) { + case BPF_S_JMP_JGT_X: + case BPF_S_JMP_JGE_X: + case BPF_S_JMP_JEQ_X: + ctx->seen |= SEEN_XREG; + PPC_CMPLW(r_A, r_X); + break; + case BPF_S_JMP_JSET_X: + ctx->seen |= SEEN_XREG; + PPC_AND_DOT(r_scratch1, r_A, r_X); + break; + case BPF_S_JMP_JEQ_K: + case BPF_S_JMP_JGT_K: + case BPF_S_JMP_JGE_K: + if (K < 32768) + PPC_CMPLWI(r_A, K); + else { + PPC_LI32(r_scratch1, K); + PPC_CMPLW(r_A, r_scratch1); + } + break; + case BPF_S_JMP_JSET_K: + if (K < 32768) + /* PPC_ANDI is /only/ dot-form */ + PPC_ANDI(r_scratch1, r_A, K); + else { + PPC_LI32(r_scratch1, K); + PPC_AND_DOT(r_scratch1, r_A, + r_scratch1); + } + break; + } + /* Sometimes branches are constructed "backward", with + * the false path being the branch and true path being + * a fallthrough to the next instruction. + */ + if (filter[i].jt == 0) + /* Swap the sense of the branch */ + PPC_BCC(true_cond ^ COND_CMP_TRUE, + addrs[i + 1 + filter[i].jf]); + else { + PPC_BCC(true_cond, addrs[i + 1 + filter[i].jt]); + if (filter[i].jf != 0) + PPC_JMP(addrs[i + 1 + filter[i].jf]); + } + break; + default: + /* The filter contains something cruel & unusual. + * We don't handle it, but also there shouldn't be + * anything missing from our list. + */ + if (printk_ratelimit()) + pr_err("BPF filter opcode %04x (@%d) unsupported\n", + filter[i].code, i); + return -ENOTSUPP; + } + + } + /* Set end-of-body-code address for exit. */ + addrs[i] = ctx->idx * 4; + + return 0; +} + +void bpf_jit_compile(struct sk_filter *fp) +{ + unsigned int proglen; + unsigned int alloclen; + u32 *image = NULL; + u32 *code_base; + unsigned int *addrs; + struct codegen_context cgctx; + int pass; + int flen = fp->len; + + if (!bpf_jit_enable) + return; + + addrs = kzalloc((flen+1) * sizeof(*addrs), GFP_KERNEL); + if (addrs == NULL) + return; + + /* + * There are multiple assembly passes as the generated code will change + * size as it settles down, figuring out the max branch offsets/exit + * paths required. + * + * The range of standard conditional branches is +/- 32Kbytes. Since + * BPF_MAXINSNS = 4096, we can only jump from (worst case) start to + * finish with 8 bytes/instruction. Not feasible, so long jumps are + * used, distinct from short branches. + * + * Current: + * + * For now, both branch types assemble to 2 words (short branches padded + * with a NOP); this is less efficient, but assembly will always complete + * after exactly 3 passes: + * + * First pass: No code buffer; Program is "faux-generated" -- no code + * emitted but maximum size of output determined (and addrs[] filled + * in). Also, we note whether we use M[], whether we use skb data, etc. + * All generation choices assumed to be 'worst-case', e.g. branches all + * far (2 instructions), return path code reduction not available, etc. + * + * Second pass: Code buffer allocated with size determined previously. + * Prologue generated to support features we have seen used. Exit paths + * determined and addrs[] is filled in again, as code may be slightly + * smaller as a result. + * + * Third pass: Code generated 'for real', and branch destinations + * determined from now-accurate addrs[] map. + * + * Ideal: + * + * If we optimise this, near branches will be shorter. On the + * first assembly pass, we should err on the side of caution and + * generate the biggest code. On subsequent passes, branches will be + * generated short or long and code size will reduce. With smaller + * code, more branches may fall into the short category, and code will + * reduce more. + * + * Finally, if we see one pass generate code the same size as the + * previous pass we have converged and should now generate code for + * real. Allocating at the end will also save the memory that would + * otherwise be wasted by the (small) current code shrinkage. + * Preferably, we should do a small number of passes (e.g. 5) and if we + * haven't converged by then, get impatient and force code to generate + * as-is, even if the odd branch would be left long. The chances of a + * long jump are tiny with all but the most enormous of BPF filter + * inputs, so we should usually converge on the third pass. + */ + + cgctx.idx = 0; + cgctx.seen = 0; + cgctx.pc_ret0 = -1; + /* Scouting faux-generate pass 0 */ + if (bpf_jit_build_body(fp, 0, &cgctx, addrs)) + /* We hit something illegal or unsupported. */ + goto out; + + /* + * Pretend to build prologue, given the features we've seen. This will + * update ctgtx.idx as it pretends to output instructions, then we can + * calculate total size from idx. + */ + bpf_jit_build_prologue(fp, 0, &cgctx); + bpf_jit_build_epilogue(0, &cgctx); + + proglen = cgctx.idx * 4; + alloclen = proglen + FUNCTION_DESCR_SIZE; + image = module_alloc(max_t(unsigned int, alloclen, + sizeof(struct work_struct))); + if (!image) + goto out; + + code_base = image + (FUNCTION_DESCR_SIZE/4); + + /* Code generation passes 1-2 */ + for (pass = 1; pass < 3; pass++) { + /* Now build the prologue, body code & epilogue for real. */ + cgctx.idx = 0; + bpf_jit_build_prologue(fp, code_base, &cgctx); + bpf_jit_build_body(fp, code_base, &cgctx, addrs); + bpf_jit_build_epilogue(code_base, &cgctx); + + if (bpf_jit_enable > 1) + pr_info("Pass %d: shrink = %d, seen = 0x%x\n", pass, + proglen - (cgctx.idx * 4), cgctx.seen); + } + + if (bpf_jit_enable > 1) + pr_info("flen=%d proglen=%u pass=%d image=%p\n", + flen, proglen, pass, image); + + if (image) { + if (bpf_jit_enable > 1) + print_hex_dump(KERN_ERR, "JIT code: ", + DUMP_PREFIX_ADDRESS, + 16, 1, code_base, + proglen, false); + + bpf_flush_icache(code_base, code_base + (proglen/4)); + /* Function descriptor nastiness: Address + TOC */ + ((u64 *)image)[0] = (u64)code_base; + ((u64 *)image)[1] = local_paca->kernel_toc; + fp->bpf_func = (void *)image; + } +out: + kfree(addrs); + return; +} + +static void jit_free_defer(struct work_struct *arg) +{ + module_free(NULL, arg); +} + +/* run from softirq, we must use a work_struct to call + * module_free() from process context + */ +void bpf_jit_free(struct sk_filter *fp) +{ + if (fp->bpf_func != sk_run_filter) { + struct work_struct *work = (struct work_struct *)fp->bpf_func; + + INIT_WORK(work, jit_free_defer); + schedule_work(work); + } +} diff --git a/arch/powerpc/platforms/52xx/Kconfig b/arch/powerpc/platforms/52xx/Kconfig index 47ea1be1481..90f4496017e 100644 --- a/arch/powerpc/platforms/52xx/Kconfig +++ b/arch/powerpc/platforms/52xx/Kconfig @@ -55,14 +55,6 @@ config PPC_MPC5200_BUGFIX It is safe to say 'Y' here -config PPC_MPC5200_GPIO - bool "MPC5200 GPIO support" - depends on PPC_MPC52xx - select ARCH_REQUIRE_GPIOLIB - select GENERIC_GPIO - help - Enable gpiolib support for mpc5200 based boards - config PPC_MPC5200_LPBFIFO tristate "MPC5200 LocalPlus bus FIFO driver" depends on PPC_MPC52xx diff --git a/arch/powerpc/platforms/52xx/Makefile b/arch/powerpc/platforms/52xx/Makefile index 2bc8cd0c5cf..4e62486791e 100644 --- a/arch/powerpc/platforms/52xx/Makefile +++ b/arch/powerpc/platforms/52xx/Makefile @@ -14,5 +14,4 @@ ifeq ($(CONFIG_PPC_LITE5200),y) obj-$(CONFIG_PM) += lite5200_sleep.o lite5200_pm.o endif -obj-$(CONFIG_PPC_MPC5200_GPIO) += mpc52xx_gpio.o obj-$(CONFIG_PPC_MPC5200_LPBFIFO) += mpc52xx_lpbfifo.o diff --git a/arch/powerpc/platforms/52xx/mpc52xx_gpio.c b/arch/powerpc/platforms/52xx/mpc52xx_gpio.c deleted file mode 100644 index 1757d1db4b5..00000000000 --- a/arch/powerpc/platforms/52xx/mpc52xx_gpio.c +++ /dev/null @@ -1,380 +0,0 @@ -/* - * MPC52xx gpio driver - * - * Copyright (c) 2008 Sascha Hauer <s.hauer@pengutronix.de>, Pengutronix - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 - * as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ - -#include <linux/of.h> -#include <linux/kernel.h> -#include <linux/slab.h> -#include <linux/of_gpio.h> -#include <linux/io.h> -#include <linux/of_platform.h> - -#include <asm/gpio.h> -#include <asm/mpc52xx.h> -#include <sysdev/fsl_soc.h> - -static DEFINE_SPINLOCK(gpio_lock); - -struct mpc52xx_gpiochip { - struct of_mm_gpio_chip mmchip; - unsigned int shadow_dvo; - unsigned int shadow_gpioe; - unsigned int shadow_ddr; -}; - -/* - * GPIO LIB API implementation for wakeup GPIOs. - * - * There's a maximum of 8 wakeup GPIOs. Which of these are available - * for use depends on your board setup. - * - * 0 -> GPIO_WKUP_7 - * 1 -> GPIO_WKUP_6 - * 2 -> PSC6_1 - * 3 -> PSC6_0 - * 4 -> ETH_17 - * 5 -> PSC3_9 - * 6 -> PSC2_4 - * 7 -> PSC1_4 - * - */ -static int mpc52xx_wkup_gpio_get(struct gpio_chip *gc, unsigned int gpio) -{ - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - struct mpc52xx_gpio_wkup __iomem *regs = mm_gc->regs; - unsigned int ret; - - ret = (in_8(®s->wkup_ival) >> (7 - gpio)) & 1; - - pr_debug("%s: gpio: %d ret: %d\n", __func__, gpio, ret); - - return ret; -} - -static inline void -__mpc52xx_wkup_gpio_set(struct gpio_chip *gc, unsigned int gpio, int val) -{ - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - struct mpc52xx_gpiochip *chip = container_of(mm_gc, - struct mpc52xx_gpiochip, mmchip); - struct mpc52xx_gpio_wkup __iomem *regs = mm_gc->regs; - - if (val) - chip->shadow_dvo |= 1 << (7 - gpio); - else - chip->shadow_dvo &= ~(1 << (7 - gpio)); - - out_8(®s->wkup_dvo, chip->shadow_dvo); -} - -static void -mpc52xx_wkup_gpio_set(struct gpio_chip *gc, unsigned int gpio, int val) -{ - unsigned long flags; - - spin_lock_irqsave(&gpio_lock, flags); - - __mpc52xx_wkup_gpio_set(gc, gpio, val); - - spin_unlock_irqrestore(&gpio_lock, flags); - - pr_debug("%s: gpio: %d val: %d\n", __func__, gpio, val); -} - -static int mpc52xx_wkup_gpio_dir_in(struct gpio_chip *gc, unsigned int gpio) -{ - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - struct mpc52xx_gpiochip *chip = container_of(mm_gc, - struct mpc52xx_gpiochip, mmchip); - struct mpc52xx_gpio_wkup __iomem *regs = mm_gc->regs; - unsigned long flags; - - spin_lock_irqsave(&gpio_lock, flags); - - /* set the direction */ - chip->shadow_ddr &= ~(1 << (7 - gpio)); - out_8(®s->wkup_ddr, chip->shadow_ddr); - - /* and enable the pin */ - chip->shadow_gpioe |= 1 << (7 - gpio); - out_8(®s->wkup_gpioe, chip->shadow_gpioe); - - spin_unlock_irqrestore(&gpio_lock, flags); - - return 0; -} - -static int -mpc52xx_wkup_gpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val) -{ - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - struct mpc52xx_gpio_wkup __iomem *regs = mm_gc->regs; - struct mpc52xx_gpiochip *chip = container_of(mm_gc, - struct mpc52xx_gpiochip, mmchip); - unsigned long flags; - - spin_lock_irqsave(&gpio_lock, flags); - - __mpc52xx_wkup_gpio_set(gc, gpio, val); - - /* Then set direction */ - chip->shadow_ddr |= 1 << (7 - gpio); - out_8(®s->wkup_ddr, chip->shadow_ddr); - - /* Finally enable the pin */ - chip->shadow_gpioe |= 1 << (7 - gpio); - out_8(®s->wkup_gpioe, chip->shadow_gpioe); - - spin_unlock_irqrestore(&gpio_lock, flags); - - pr_debug("%s: gpio: %d val: %d\n", __func__, gpio, val); - - return 0; -} - -static int __devinit mpc52xx_wkup_gpiochip_probe(struct platform_device *ofdev) -{ - struct mpc52xx_gpiochip *chip; - struct mpc52xx_gpio_wkup __iomem *regs; - struct gpio_chip *gc; - int ret; - - chip = kzalloc(sizeof(*chip), GFP_KERNEL); - if (!chip) - return -ENOMEM; - - gc = &chip->mmchip.gc; - - gc->ngpio = 8; - gc->direction_input = mpc52xx_wkup_gpio_dir_in; - gc->direction_output = mpc52xx_wkup_gpio_dir_out; - gc->get = mpc52xx_wkup_gpio_get; - gc->set = mpc52xx_wkup_gpio_set; - - ret = of_mm_gpiochip_add(ofdev->dev.of_node, &chip->mmchip); - if (ret) - return ret; - - regs = chip->mmchip.regs; - chip->shadow_gpioe = in_8(®s->wkup_gpioe); - chip->shadow_ddr = in_8(®s->wkup_ddr); - chip->shadow_dvo = in_8(®s->wkup_dvo); - - return 0; -} - -static int mpc52xx_gpiochip_remove(struct platform_device *ofdev) -{ - return -EBUSY; -} - -static const struct of_device_id mpc52xx_wkup_gpiochip_match[] = { - { - .compatible = "fsl,mpc5200-gpio-wkup", - }, - {} -}; - -static struct platform_driver mpc52xx_wkup_gpiochip_driver = { - .driver = { - .name = "gpio_wkup", - .owner = THIS_MODULE, - .of_match_table = mpc52xx_wkup_gpiochip_match, - }, - .probe = mpc52xx_wkup_gpiochip_probe, - .remove = mpc52xx_gpiochip_remove, -}; - -/* - * GPIO LIB API implementation for simple GPIOs - * - * There's a maximum of 32 simple GPIOs. Which of these are available - * for use depends on your board setup. - * The numbering reflects the bit numbering in the port registers: - * - * 0..1 > reserved - * 2..3 > IRDA - * 4..7 > ETHR - * 8..11 > reserved - * 12..15 > USB - * 16..17 > reserved - * 18..23 > PSC3 - * 24..27 > PSC2 - * 28..31 > PSC1 - */ -static int mpc52xx_simple_gpio_get(struct gpio_chip *gc, unsigned int gpio) -{ - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - struct mpc52xx_gpio __iomem *regs = mm_gc->regs; - unsigned int ret; - - ret = (in_be32(®s->simple_ival) >> (31 - gpio)) & 1; - - return ret; -} - -static inline void -__mpc52xx_simple_gpio_set(struct gpio_chip *gc, unsigned int gpio, int val) -{ - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - struct mpc52xx_gpiochip *chip = container_of(mm_gc, - struct mpc52xx_gpiochip, mmchip); - struct mpc52xx_gpio __iomem *regs = mm_gc->regs; - - if (val) - chip->shadow_dvo |= 1 << (31 - gpio); - else - chip->shadow_dvo &= ~(1 << (31 - gpio)); - out_be32(®s->simple_dvo, chip->shadow_dvo); -} - -static void -mpc52xx_simple_gpio_set(struct gpio_chip *gc, unsigned int gpio, int val) -{ - unsigned long flags; - - spin_lock_irqsave(&gpio_lock, flags); - - __mpc52xx_simple_gpio_set(gc, gpio, val); - - spin_unlock_irqrestore(&gpio_lock, flags); - - pr_debug("%s: gpio: %d val: %d\n", __func__, gpio, val); -} - -static int mpc52xx_simple_gpio_dir_in(struct gpio_chip *gc, unsigned int gpio) -{ - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - struct mpc52xx_gpiochip *chip = container_of(mm_gc, - struct mpc52xx_gpiochip, mmchip); - struct mpc52xx_gpio __iomem *regs = mm_gc->regs; - unsigned long flags; - - spin_lock_irqsave(&gpio_lock, flags); - - /* set the direction */ - chip->shadow_ddr &= ~(1 << (31 - gpio)); - out_be32(®s->simple_ddr, chip->shadow_ddr); - - /* and enable the pin */ - chip->shadow_gpioe |= 1 << (31 - gpio); - out_be32(®s->simple_gpioe, chip->shadow_gpioe); - - spin_unlock_irqrestore(&gpio_lock, flags); - - return 0; -} - -static int -mpc52xx_simple_gpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val) -{ - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - struct mpc52xx_gpiochip *chip = container_of(mm_gc, - struct mpc52xx_gpiochip, mmchip); - struct mpc52xx_gpio __iomem *regs = mm_gc->regs; - unsigned long flags; - - spin_lock_irqsave(&gpio_lock, flags); - - /* First set initial value */ - __mpc52xx_simple_gpio_set(gc, gpio, val); - - /* Then set direction */ - chip->shadow_ddr |= 1 << (31 - gpio); - out_be32(®s->simple_ddr, chip->shadow_ddr); - - /* Finally enable the pin */ - chip->shadow_gpioe |= 1 << (31 - gpio); - out_be32(®s->simple_gpioe, chip->shadow_gpioe); - - spin_unlock_irqrestore(&gpio_lock, flags); - - pr_debug("%s: gpio: %d val: %d\n", __func__, gpio, val); - - return 0; -} - -static int __devinit mpc52xx_simple_gpiochip_probe(struct platform_device *ofdev) -{ - struct mpc52xx_gpiochip *chip; - struct gpio_chip *gc; - struct mpc52xx_gpio __iomem *regs; - int ret; - - chip = kzalloc(sizeof(*chip), GFP_KERNEL); - if (!chip) - return -ENOMEM; - - gc = &chip->mmchip.gc; - - gc->ngpio = 32; - gc->direction_input = mpc52xx_simple_gpio_dir_in; - gc->direction_output = mpc52xx_simple_gpio_dir_out; - gc->get = mpc52xx_simple_gpio_get; - gc->set = mpc52xx_simple_gpio_set; - - ret = of_mm_gpiochip_add(ofdev->dev.of_node, &chip->mmchip); - if (ret) - return ret; - - regs = chip->mmchip.regs; - chip->shadow_gpioe = in_be32(®s->simple_gpioe); - chip->shadow_ddr = in_be32(®s->simple_ddr); - chip->shadow_dvo = in_be32(®s->simple_dvo); - - return 0; -} - -static const struct of_device_id mpc52xx_simple_gpiochip_match[] = { - { - .compatible = "fsl,mpc5200-gpio", - }, - {} -}; - -static struct platform_driver mpc52xx_simple_gpiochip_driver = { - .driver = { - .name = "gpio", - .owner = THIS_MODULE, - .of_match_table = mpc52xx_simple_gpiochip_match, - }, - .probe = mpc52xx_simple_gpiochip_probe, - .remove = mpc52xx_gpiochip_remove, -}; - -static int __init mpc52xx_gpio_init(void) -{ - if (platform_driver_register(&mpc52xx_wkup_gpiochip_driver)) - printk(KERN_ERR "Unable to register wakeup GPIO driver\n"); - - if (platform_driver_register(&mpc52xx_simple_gpiochip_driver)) - printk(KERN_ERR "Unable to register simple GPIO driver\n"); - - return 0; -} - - -/* Make sure we get initialised before anyone else tries to use us */ -subsys_initcall(mpc52xx_gpio_init); - -/* No exit call at the moment as we cannot unregister of gpio chips */ - -MODULE_DESCRIPTION("Freescale MPC52xx gpio driver"); -MODULE_AUTHOR("Sascha Hauer <s.hauer@pengutronix.de"); -MODULE_LICENSE("GPL v2"); - diff --git a/arch/powerpc/platforms/amigaone/Kconfig b/arch/powerpc/platforms/amigaone/Kconfig index 02247671771..128de25cc28 100644 --- a/arch/powerpc/platforms/amigaone/Kconfig +++ b/arch/powerpc/platforms/amigaone/Kconfig @@ -8,7 +8,7 @@ config AMIGAONE select NOT_COHERENT_CACHE select CHECK_CACHE_COHERENCY select DEFAULT_UIMAGE - select PCSPKR_PLATFORM + select HAVE_PCSPKR_PLATFORM help Select AmigaOne for the following machines: - AmigaOne SE/Teron CX (G3 only) diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c index 3c7c3f82d84..fb59c46e9e9 100644 --- a/arch/powerpc/platforms/cell/spufs/file.c +++ b/arch/powerpc/platforms/cell/spufs/file.c @@ -1850,9 +1850,16 @@ out: return ret; } -static int spufs_mfc_fsync(struct file *file, int datasync) +static int spufs_mfc_fsync(struct file *file, loff_t start, loff_t end, int datasync) { - return spufs_mfc_flush(file, NULL); + struct inode *inode = file->f_path.dentry->d_inode; + int err = filemap_write_and_wait_range(inode->i_mapping, start, end); + if (!err) { + mutex_lock(&inode->i_mutex); + err = spufs_mfc_flush(file, NULL); + mutex_unlock(&inode->i_mutex); + } + return err; } static int spufs_mfc_fasync(int fd, struct file *file, int on) diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index 856e9c39806..e481f6b9a78 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -611,15 +611,14 @@ out: static struct file_system_type spufs_type; -long spufs_create(struct nameidata *nd, unsigned int flags, mode_t mode, - struct file *filp) +long spufs_create(struct path *path, struct dentry *dentry, + unsigned int flags, mode_t mode, struct file *filp) { - struct dentry *dentry; int ret; ret = -EINVAL; /* check if we are on spufs */ - if (nd->path.dentry->d_sb->s_type != &spufs_type) + if (path->dentry->d_sb->s_type != &spufs_type) goto out; /* don't accept undefined flags */ @@ -627,33 +626,27 @@ long spufs_create(struct nameidata *nd, unsigned int flags, mode_t mode, goto out; /* only threads can be underneath a gang */ - if (nd->path.dentry != nd->path.dentry->d_sb->s_root) { + if (path->dentry != path->dentry->d_sb->s_root) { if ((flags & SPU_CREATE_GANG) || - !SPUFS_I(nd->path.dentry->d_inode)->i_gang) + !SPUFS_I(path->dentry->d_inode)->i_gang) goto out; } - dentry = lookup_create(nd, 1); - ret = PTR_ERR(dentry); - if (IS_ERR(dentry)) - goto out_dir; - mode &= ~current_umask(); if (flags & SPU_CREATE_GANG) - ret = spufs_create_gang(nd->path.dentry->d_inode, - dentry, nd->path.mnt, mode); + ret = spufs_create_gang(path->dentry->d_inode, + dentry, path->mnt, mode); else - ret = spufs_create_context(nd->path.dentry->d_inode, - dentry, nd->path.mnt, flags, mode, + ret = spufs_create_context(path->dentry->d_inode, + dentry, path->mnt, flags, mode, filp); if (ret >= 0) - fsnotify_mkdir(nd->path.dentry->d_inode, dentry); + fsnotify_mkdir(path->dentry->d_inode, dentry); return ret; -out_dir: - mutex_unlock(&nd->path.dentry->d_inode->i_mutex); out: + mutex_unlock(&path->dentry->d_inode->i_mutex); return ret; } diff --git a/arch/powerpc/platforms/cell/spufs/spufs.h b/arch/powerpc/platforms/cell/spufs/spufs.h index c448bac6551..099245f230b 100644 --- a/arch/powerpc/platforms/cell/spufs/spufs.h +++ b/arch/powerpc/platforms/cell/spufs/spufs.h @@ -248,7 +248,7 @@ extern const struct spufs_tree_descr spufs_dir_debug_contents[]; /* system call implementation */ extern struct spufs_calls spufs_calls; long spufs_run_spu(struct spu_context *ctx, u32 *npc, u32 *status); -long spufs_create(struct nameidata *nd, unsigned int flags, +long spufs_create(struct path *nd, struct dentry *dentry, unsigned int flags, mode_t mode, struct file *filp); /* ELF coredump callbacks for writing SPU ELF notes */ extern int spufs_coredump_extra_notes_size(void); diff --git a/arch/powerpc/platforms/cell/spufs/syscalls.c b/arch/powerpc/platforms/cell/spufs/syscalls.c index a3d2ce54ea2..609e016e92d 100644 --- a/arch/powerpc/platforms/cell/spufs/syscalls.c +++ b/arch/powerpc/platforms/cell/spufs/syscalls.c @@ -62,21 +62,17 @@ out: static long do_spu_create(const char __user *pathname, unsigned int flags, mode_t mode, struct file *neighbor) { - char *tmp; + struct path path; + struct dentry *dentry; int ret; - tmp = getname(pathname); - ret = PTR_ERR(tmp); - if (!IS_ERR(tmp)) { - struct nameidata nd; - - ret = kern_path_parent(tmp, &nd); - if (!ret) { - nd.flags |= LOOKUP_OPEN | LOOKUP_CREATE; - ret = spufs_create(&nd, flags, mode, neighbor); - path_put(&nd.path); - } - putname(tmp); + dentry = user_path_create(AT_FDCWD, pathname, &path, 1); + ret = PTR_ERR(dentry); + if (!IS_ERR(dentry)) { + ret = spufs_create(&path, dentry, flags, mode, neighbor); + mutex_unlock(&path.dentry->d_inode->i_mutex); + dput(dentry); + path_put(&path); } return ret; diff --git a/arch/powerpc/platforms/chrp/Kconfig b/arch/powerpc/platforms/chrp/Kconfig index bc0b0efdc5f..d3cdab582c5 100644 --- a/arch/powerpc/platforms/chrp/Kconfig +++ b/arch/powerpc/platforms/chrp/Kconfig @@ -1,6 +1,7 @@ config PPC_CHRP bool "Common Hardware Reference Platform (CHRP) based machines" depends on 6xx + select HAVE_PCSPKR_PLATFORM select MPIC select PPC_I8259 select PPC_INDIRECT_PCI diff --git a/arch/powerpc/platforms/iseries/exception.S b/arch/powerpc/platforms/iseries/exception.S index 29c02f36b32..f519ee17ff7 100644 --- a/arch/powerpc/platforms/iseries/exception.S +++ b/arch/powerpc/platforms/iseries/exception.S @@ -167,7 +167,7 @@ BEGIN_FTR_SECTION std r12,PACA_EXGEN+EX_R13(r13) EXCEPTION_PROLOG_ISERIES_1 FTR_SECTION_ELSE - EXCEPTION_PROLOG_1(PACA_EXGEN) + EXCEPTION_PROLOG_1(PACA_EXGEN, NOTEST, 0) EXCEPTION_PROLOG_ISERIES_1 ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_SLB) b data_access_common diff --git a/arch/powerpc/platforms/iseries/exception.h b/arch/powerpc/platforms/iseries/exception.h index bae3fba5ad8..50271b550a9 100644 --- a/arch/powerpc/platforms/iseries/exception.h +++ b/arch/powerpc/platforms/iseries/exception.h @@ -39,7 +39,7 @@ label##_iSeries: \ HMT_MEDIUM; \ mtspr SPRN_SPRG_SCRATCH0,r13; /* save r13 */ \ - EXCEPTION_PROLOG_1(area); \ + EXCEPTION_PROLOG_1(area, NOTEST, 0); \ EXCEPTION_PROLOG_ISERIES_1; \ b label##_common @@ -48,7 +48,7 @@ label##_iSeries: \ label##_iSeries: \ HMT_MEDIUM; \ mtspr SPRN_SPRG_SCRATCH0,r13; /* save r13 */ \ - EXCEPTION_PROLOG_1(PACA_EXGEN); \ + EXCEPTION_PROLOG_1(PACA_EXGEN, NOTEST, 0); \ lbz r10,PACASOFTIRQEN(r13); \ cmpwi 0,r10,0; \ beq- label##_iSeries_masked; \ diff --git a/arch/powerpc/platforms/powermac/pci.c b/arch/powerpc/platforms/powermac/pci.c index f33e08d573c..abe8d7e2ebe 100644 --- a/arch/powerpc/platforms/powermac/pci.c +++ b/arch/powerpc/platforms/powermac/pci.c @@ -17,6 +17,7 @@ #include <linux/init.h> #include <linux/bootmem.h> #include <linux/irq.h> +#include <linux/of_pci.h> #include <asm/sections.h> #include <asm/io.h> @@ -235,7 +236,7 @@ static int chaos_validate_dev(struct pci_bus *bus, int devfn, int offset) if (offset >= 0x100) return PCIBIOS_BAD_REGISTER_NUMBER; - np = pci_busdev_to_OF_node(bus, devfn); + np = of_pci_find_child_device(bus->dev.of_node, devfn); if (np == NULL) return PCIBIOS_DEVICE_NOT_FOUND; diff --git a/arch/powerpc/platforms/prep/Kconfig b/arch/powerpc/platforms/prep/Kconfig index bf8330ef2e7..f0536c7cda9 100644 --- a/arch/powerpc/platforms/prep/Kconfig +++ b/arch/powerpc/platforms/prep/Kconfig @@ -1,6 +1,7 @@ config PPC_PREP bool "PowerPC Reference Platform (PReP) based machines" depends on 6xx && BROKEN + select HAVE_PCSPKR_PLATFORM select MPIC select PPC_I8259 select PPC_INDIRECT_PCI diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig index 71af4c5d6c0..05cf4769b88 100644 --- a/arch/powerpc/platforms/pseries/Kconfig +++ b/arch/powerpc/platforms/pseries/Kconfig @@ -1,6 +1,7 @@ config PPC_PSERIES depends on PPC64 && PPC_BOOK3S bool "IBM pSeries & new (POWER5-based) iSeries" + select HAVE_PCSPKR_PLATFORM select MPIC select PCI_MSI select PPC_XICS diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 33867ec4a23..9d6a8effeda 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -12,6 +12,8 @@ #include <linux/of.h> #include <linux/memblock.h> #include <linux/vmalloc.h> +#include <linux/memory.h> + #include <asm/firmware.h> #include <asm/machdep.h> #include <asm/pSeries_reconfig.h> @@ -20,24 +22,25 @@ static unsigned long get_memblock_size(void) { struct device_node *np; - unsigned int memblock_size = 0; + unsigned int memblock_size = MIN_MEMORY_BLOCK_SIZE; + struct resource r; np = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory"); if (np) { - const unsigned long *size; + const __be64 *size; size = of_get_property(np, "ibm,lmb-size", NULL); - memblock_size = size ? *size : 0; - + if (size) + memblock_size = be64_to_cpup(size); of_node_put(np); - } else { + } else if (machine_is(pseries)) { + /* This fallback really only applies to pseries */ unsigned int memzero_size = 0; - const unsigned int *regs; np = of_find_node_by_path("/memory@0"); if (np) { - regs = of_get_property(np, "reg", NULL); - memzero_size = regs ? regs[3] : 0; + if (!of_address_to_resource(np, 0, &r)) + memzero_size = resource_size(&r); of_node_put(np); } @@ -50,16 +53,21 @@ static unsigned long get_memblock_size(void) sprintf(buf, "/memory@%x", memzero_size); np = of_find_node_by_path(buf); if (np) { - regs = of_get_property(np, "reg", NULL); - memblock_size = regs ? regs[3] : 0; + if (!of_address_to_resource(np, 0, &r)) + memblock_size = resource_size(&r); of_node_put(np); } } } - return memblock_size; } +/* WARNING: This is going to override the generic definition whenever + * pseries is built-in regardless of what platform is active at boot + * time. This is fine for now as this is the only "option" and it + * should work everywhere. If not, we'll have to turn this into a + * ppc_md. callback + */ unsigned long memory_block_size_bytes(void) { return get_memblock_size(); diff --git a/arch/powerpc/sysdev/xics/icp-native.c b/arch/powerpc/sysdev/xics/icp-native.c index 1f15ad43614..ba382b59b92 100644 --- a/arch/powerpc/sysdev/xics/icp-native.c +++ b/arch/powerpc/sysdev/xics/icp-native.c @@ -17,6 +17,7 @@ #include <linux/cpu.h> #include <linux/of.h> #include <linux/spinlock.h> +#include <linux/module.h> #include <asm/prom.h> #include <asm/io.h> @@ -24,6 +25,7 @@ #include <asm/irq.h> #include <asm/errno.h> #include <asm/xics.h> +#include <asm/kvm_ppc.h> struct icp_ipl { union { @@ -139,6 +141,12 @@ static void icp_native_cause_ipi(int cpu, unsigned long data) icp_native_set_qirr(cpu, IPI_PRIORITY); } +void xics_wake_cpu(int cpu) +{ + icp_native_set_qirr(cpu, IPI_PRIORITY); +} +EXPORT_SYMBOL_GPL(xics_wake_cpu); + static irqreturn_t icp_native_ipi_action(int irq, void *dev_id) { int cpu = smp_processor_id(); @@ -185,6 +193,7 @@ static int __init icp_native_map_one_cpu(int hw_id, unsigned long addr, } icp_native_regs[cpu] = ioremap(addr, size); + kvmppc_set_xics_phys(cpu, addr); if (!icp_native_regs[cpu]) { pr_warning("icp_native: Failed ioremap for CPU %d, " "interrupt server #0x%x, addr %#lx\n", |