diff options
Diffstat (limited to 'arch/powerpc/kernel')
30 files changed, 751 insertions, 504 deletions
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index f5808a35688c..83afacd3ba7b 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -28,7 +28,7 @@ endif obj-y := cputable.o ptrace.o syscalls.o \ irq.o align.o signal_32.o pmc.o vdso.o \ - init_task.o process.o systbl.o idle.o \ + process.o systbl.o idle.o \ signal.o sysfs.o cacheinfo.o time.o \ prom.o traps.o setup-common.o \ udbg.o misc.o io.o dma.o \ diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 34b8afe94a50..52c7ad78242e 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -116,6 +116,9 @@ int main(void) #ifdef CONFIG_KVM_BOOK3S_32_HANDLER DEFINE(THREAD_KVM_SVCPU, offsetof(struct thread_struct, kvm_shadow_vcpu)); #endif +#ifdef CONFIG_KVM_BOOKE_HV + DEFINE(THREAD_KVM_VCPU, offsetof(struct thread_struct, kvm_vcpu)); +#endif DEFINE(TI_FLAGS, offsetof(struct thread_info, flags)); DEFINE(TI_LOCAL_FLAGS, offsetof(struct thread_info, local_flags)); @@ -188,10 +191,6 @@ int main(void) DEFINE(SLBSHADOW_STACKESID, offsetof(struct slb_shadow, save_area[SLB_NUM_BOLTED - 1].esid)); DEFINE(SLBSHADOW_SAVEAREA, offsetof(struct slb_shadow, save_area)); - DEFINE(LPPACASRR0, offsetof(struct lppaca, saved_srr0)); - 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)); @@ -387,6 +386,7 @@ int main(void) #ifdef CONFIG_KVM DEFINE(VCPU_HOST_STACK, offsetof(struct kvm_vcpu, arch.host_stack)); DEFINE(VCPU_HOST_PID, offsetof(struct kvm_vcpu, arch.host_pid)); + DEFINE(VCPU_GUEST_PID, offsetof(struct kvm_vcpu, arch.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)); @@ -429,9 +429,11 @@ int main(void) DEFINE(VCPU_SHARED_MAS4, offsetof(struct kvm_vcpu_arch_shared, mas4)); DEFINE(VCPU_SHARED_MAS6, offsetof(struct kvm_vcpu_arch_shared, mas6)); + DEFINE(VCPU_KVM, offsetof(struct kvm_vcpu, kvm)); + DEFINE(KVM_LPID, offsetof(struct kvm, arch.lpid)); + /* 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)); @@ -444,9 +446,9 @@ int main(void) DEFINE(KVM_VRMA_SLB_V, offsetof(struct kvm, arch.vrma_slb_v)); DEFINE(VCPU_DSISR, offsetof(struct kvm_vcpu, arch.shregs.dsisr)); DEFINE(VCPU_DAR, offsetof(struct kvm_vcpu, arch.shregs.dar)); + DEFINE(VCPU_VPA, offsetof(struct kvm_vcpu, arch.vpa.pinned_addr)); #endif #ifdef CONFIG_PPC_BOOK3S - DEFINE(VCPU_KVM, offsetof(struct kvm_vcpu, kvm)); DEFINE(VCPU_VCPUID, offsetof(struct kvm_vcpu, vcpu_id)); DEFINE(VCPU_PURR, offsetof(struct kvm_vcpu, arch.purr)); DEFINE(VCPU_SPURR, offsetof(struct kvm_vcpu, arch.spurr)); @@ -461,7 +463,6 @@ int main(void) DEFINE(VCPU_PENDING_EXC, offsetof(struct kvm_vcpu, arch.pending_exceptions)); DEFINE(VCPU_CEDED, offsetof(struct kvm_vcpu, arch.ceded)); DEFINE(VCPU_PRODDED, offsetof(struct kvm_vcpu, arch.prodded)); - 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)); @@ -537,6 +538,8 @@ int main(void) HSTATE_FIELD(HSTATE_NAPPING, napping); #ifdef CONFIG_KVM_BOOK3S_64_HV + HSTATE_FIELD(HSTATE_HWTHREAD_REQ, hwthread_req); + HSTATE_FIELD(HSTATE_HWTHREAD_STATE, hwthread_state); HSTATE_FIELD(HSTATE_KVM_VCPU, kvm_vcpu); HSTATE_FIELD(HSTATE_KVM_VCORE, kvm_vcore); HSTATE_FIELD(HSTATE_XICS_PHYS, xics_phys); @@ -597,6 +600,12 @@ int main(void) DEFINE(VCPU_HOST_SPEFSCR, offsetof(struct kvm_vcpu, arch.host_spefscr)); #endif +#ifdef CONFIG_KVM_BOOKE_HV + DEFINE(VCPU_HOST_MAS4, offsetof(struct kvm_vcpu, arch.host_mas4)); + DEFINE(VCPU_HOST_MAS6, offsetof(struct kvm_vcpu, arch.host_mas6)); + DEFINE(VCPU_EPLC, offsetof(struct kvm_vcpu, arch.eplc)); +#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_fsl_booke.S b/arch/powerpc/kernel/cpu_setup_fsl_booke.S index 8053db02b85e..69fdd2322a66 100644 --- a/arch/powerpc/kernel/cpu_setup_fsl_booke.S +++ b/arch/powerpc/kernel/cpu_setup_fsl_booke.S @@ -73,6 +73,7 @@ _GLOBAL(__setup_cpu_e500v2) mtlr r4 blr _GLOBAL(__setup_cpu_e500mc) + mr r5, r4 mflr r4 bl __e500_icache_setup bl __e500_dcache_setup diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index f8a7a1a1a9f4..ed1718feb9d9 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -63,15 +63,9 @@ system_call_common: std r0,GPR0(r1) std r10,GPR1(r1) ACCOUNT_CPU_USER_ENTRY(r10, r11) - /* - * This "crclr so" clears CR0.SO, which is the error indication on - * return from this system call. There must be no cmp instruction - * between it and the "mfcr r9" below, otherwise if XER.SO is set, - * CR0.SO will get set, causing all system calls to appear to fail. - */ - crclr so std r2,GPR2(r1) std r3,GPR3(r1) + mfcr r2 std r4,GPR4(r1) std r5,GPR5(r1) std r6,GPR6(r1) @@ -82,18 +76,20 @@ system_call_common: std r11,GPR10(r1) std r11,GPR11(r1) std r11,GPR12(r1) + std r11,_XER(r1) + std r11,_CTR(r1) std r9,GPR13(r1) - mfcr r9 mflr r10 + /* + * This clears CR0.SO (bit 28), which is the error indication on + * return from this system call. + */ + rldimi r2,r11,28,(63-28) li r11,0xc01 - std r9,_CCR(r1) std r10,_LINK(r1) std r11,_TRAP(r1) - mfxer r9 - mfctr r10 - std r9,_XER(r1) - std r10,_CTR(r1) std r3,ORIG_GPR3(r1) + std r2,_CCR(r1) ld r2,PACATOC(r13) addi r9,r1,STACK_FRAME_OVERHEAD ld r11,exception_marker@toc(r2) @@ -154,7 +150,7 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR) ld r10,TI_FLAGS(r11) andi. r11,r10,_TIF_SYSCALL_T_OR_A bne- syscall_dotrace -syscall_dotrace_cont: +.Lsyscall_dotrace_cont: cmpldi 0,r0,NR_syscalls bge- syscall_enosys @@ -211,7 +207,7 @@ syscall_exit: cmpld r3,r11 ld r5,_CCR(r1) bge- syscall_error -syscall_error_cont: +.Lsyscall_error_cont: ld r7,_NIP(r1) BEGIN_FTR_SECTION stdcx. r0,0,r1 /* to clear the reservation */ @@ -246,7 +242,7 @@ syscall_error: oris r5,r5,0x1000 /* Set SO bit in CR */ neg r3,r3 std r5,_CCR(r1) - b syscall_error_cont + b .Lsyscall_error_cont /* Traced system call support */ syscall_dotrace: @@ -268,7 +264,7 @@ syscall_dotrace: addi r9,r1,STACK_FRAME_OVERHEAD clrrdi r10,r1,THREAD_SHIFT ld r10,TI_FLAGS(r10) - b syscall_dotrace_cont + b .Lsyscall_dotrace_cont syscall_enosys: li r3,-ENOSYS @@ -588,23 +584,19 @@ _GLOBAL(ret_from_except_lite) fast_exc_return_irq: restore: /* - * This is the main kernel exit path, we first check if we - * have to change our interrupt state. + * This is the main kernel exit path. First we check if we + * are about to re-enable interrupts */ ld r5,SOFTE(r1) lbz r6,PACASOFTIRQEN(r13) - cmpwi cr1,r5,0 - cmpw cr0,r5,r6 - beq cr0,4f + cmpwi cr0,r5,0 + beq restore_irq_off - /* We do, handle disable first, which is easy */ - bne cr1,3f; - li r0,0 - stb r0,PACASOFTIRQEN(r13); - TRACE_DISABLE_INTS - b 4f + /* We are enabling, were we already enabled ? Yes, just return */ + cmpwi cr0,r6,1 + beq cr0,do_restore -3: /* + /* * We are about to soft-enable interrupts (we are hard disabled * at this point). We check if there's anything that needs to * be replayed first. @@ -626,7 +618,7 @@ restore_no_replay: /* * Final return path. BookE is handled in a different file */ -4: +do_restore: #ifdef CONFIG_PPC_BOOK3E b .exception_return_book3e #else @@ -700,6 +692,25 @@ fast_exception_return: #endif /* CONFIG_PPC_BOOK3E */ /* + * We are returning to a context with interrupts soft disabled. + * + * However, we may also about to hard enable, so we need to + * make sure that in this case, we also clear PACA_IRQ_HARD_DIS + * or that bit can get out of sync and bad things will happen + */ +restore_irq_off: + ld r3,_MSR(r1) + lbz r7,PACAIRQHAPPENED(r13) + andi. r0,r3,MSR_EE + beq 1f + rlwinm r7,r7,0,~PACA_IRQ_HARD_DIS + stb r7,PACAIRQHAPPENED(r13) +1: li r0,0 + stb r0,PACASOFTIRQEN(r13); + TRACE_DISABLE_INTS + b do_restore + + /* * Something did happen, check if a re-emit is needed * (this also clears paca->irq_happened) */ @@ -748,6 +759,9 @@ restore_check_irq_replay: #endif /* CONFIG_PPC_BOOK3E */ 1: b .ret_from_except /* What else to do here ? */ + + +3: do_work: #ifdef CONFIG_PREEMPT andi. r0,r3,MSR_PR /* Returning to user mode? */ @@ -767,16 +781,6 @@ do_work: SOFT_DISABLE_INTS(r3,r4) 1: bl .preempt_schedule_irq - /* Hard-disable interrupts again (and update PACA) */ -#ifdef CONFIG_PPC_BOOK3E - wrteei 0 -#else - ld r10,PACAKMSR(r13) /* Get kernel MSR without EE */ - mtmsrd r10,1 -#endif /* CONFIG_PPC_BOOK3E */ - li r0,PACA_IRQ_HARD_DIS - stb r0,PACAIRQHAPPENED(r13) - /* Re-test flags and eventually loop */ clrrdi r9,r1,THREAD_SHIFT ld r4,TI_FLAGS(r9) @@ -787,14 +791,6 @@ do_work: user_work: #endif /* CONFIG_PREEMPT */ - /* Enable interrupts */ -#ifdef CONFIG_PPC_BOOK3E - wrteei 1 -#else - ori r10,r10,MSR_EE - mtmsrd r10,1 -#endif /* CONFIG_PPC_BOOK3E */ - andi. r0,r4,_TIF_NEED_RESCHED beq 1f bl .restore_interrupts diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index cb705fdbb458..1c06d2971545 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -63,11 +63,13 @@ BEGIN_FTR_SECTION GET_PACA(r13) #ifdef CONFIG_KVM_BOOK3S_64_HV - lbz r0,PACAPROCSTART(r13) - cmpwi r0,0x80 - bne 1f - li r0,1 - stb r0,PACAPROCSTART(r13) + li r0,KVM_HWTHREAD_IN_KERNEL + stb r0,HSTATE_HWTHREAD_STATE(r13) + /* Order setting hwthread_state vs. testing hwthread_req */ + sync + lbz r0,HSTATE_HWTHREAD_REQ(r13) + cmpwi r0,0 + beq 1f b kvm_start_guest 1: #endif @@ -94,12 +96,10 @@ machine_check_pSeries_1: data_access_pSeries: HMT_MEDIUM SET_SCRATCH0(r13) -#ifndef CONFIG_POWER4_ONLY BEGIN_FTR_SECTION 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, 0x300) @@ -301,7 +301,6 @@ machine_check_fwnmi: 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) @@ -328,7 +327,6 @@ do_stab_bolted_pSeries: 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_SKIP(PACA_EXGEN, EXC_STD, 0x300) KVM_HANDLER_SKIP(PACA_EXSLB, EXC_STD, 0x380) @@ -768,8 +766,8 @@ alignment_common: std r3,_DAR(r1) std r4,_DSISR(r1) bl .save_nvgprs + DISABLE_INTS addi r3,r1,STACK_FRAME_OVERHEAD - ENABLE_INTS bl .alignment_exception b .ret_from_except diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S index 7dd2981bcc50..7a2e5e421abf 100644 --- a/arch/powerpc/kernel/head_44x.S +++ b/arch/powerpc/kernel/head_44x.S @@ -248,10 +248,11 @@ _ENTRY(_start); interrupt_base: /* Critical Input Interrupt */ - CRITICAL_EXCEPTION(0x0100, CriticalInput, unknown_exception) + CRITICAL_EXCEPTION(0x0100, CRITICAL, CriticalInput, unknown_exception) /* Machine Check Interrupt */ - CRITICAL_EXCEPTION(0x0200, MachineCheck, machine_check_exception) + CRITICAL_EXCEPTION(0x0200, MACHINE_CHECK, MachineCheck, \ + machine_check_exception) MCHECK_EXCEPTION(0x0210, MachineCheckA, machine_check_exception) /* Data Storage Interrupt */ @@ -261,7 +262,8 @@ interrupt_base: INSTRUCTION_STORAGE_EXCEPTION /* External Input Interrupt */ - EXCEPTION(0x0500, ExternalInput, do_IRQ, EXC_XFER_LITE) + EXCEPTION(0x0500, BOOKE_INTERRUPT_EXTERNAL, ExternalInput, \ + do_IRQ, EXC_XFER_LITE) /* Alignment Interrupt */ ALIGNMENT_EXCEPTION @@ -273,29 +275,32 @@ interrupt_base: #ifdef CONFIG_PPC_FPU FP_UNAVAILABLE_EXCEPTION #else - EXCEPTION(0x2010, FloatingPointUnavailable, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x2010, BOOKE_INTERRUPT_FP_UNAVAIL, \ + FloatingPointUnavailable, unknown_exception, EXC_XFER_EE) #endif /* System Call Interrupt */ START_EXCEPTION(SystemCall) - NORMAL_EXCEPTION_PROLOG + NORMAL_EXCEPTION_PROLOG(BOOKE_INTERRUPT_SYSCALL) EXC_XFER_EE_LITE(0x0c00, DoSyscall) /* Auxiliary Processor Unavailable Interrupt */ - EXCEPTION(0x2020, AuxillaryProcessorUnavailable, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x2020, BOOKE_INTERRUPT_AP_UNAVAIL, \ + AuxillaryProcessorUnavailable, unknown_exception, EXC_XFER_EE) /* Decrementer Interrupt */ DECREMENTER_EXCEPTION /* Fixed Internal Timer Interrupt */ /* TODO: Add FIT support */ - EXCEPTION(0x1010, FixedIntervalTimer, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x1010, BOOKE_INTERRUPT_FIT, FixedIntervalTimer, \ + unknown_exception, EXC_XFER_EE) /* Watchdog Timer Interrupt */ /* TODO: Add watchdog support */ #ifdef CONFIG_BOOKE_WDT - CRITICAL_EXCEPTION(0x1020, WatchdogTimer, WatchdogException) + CRITICAL_EXCEPTION(0x1020, WATCHDOG, WatchdogTimer, WatchdogException) #else - CRITICAL_EXCEPTION(0x1020, WatchdogTimer, unknown_exception) + CRITICAL_EXCEPTION(0x1020, WATCHDOG, WatchdogTimer, unknown_exception) #endif /* Data TLB Error Interrupt */ @@ -778,14 +783,6 @@ _GLOBAL(__fixup_440A_mcheck) blr /* - * extern void giveup_altivec(struct task_struct *prev) - * - * The 44x core does not have an AltiVec unit. - */ -_GLOBAL(giveup_altivec) - blr - -/* * extern void giveup_fpu(struct task_struct *prev) * * The 44x core does not have an FPU. diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h index 0e4175388f47..5f051eeb93a2 100644 --- a/arch/powerpc/kernel/head_booke.h +++ b/arch/powerpc/kernel/head_booke.h @@ -2,6 +2,9 @@ #define __HEAD_BOOKE_H__ #include <asm/ptrace.h> /* for STACK_FRAME_REGS_MARKER */ +#include <asm/kvm_asm.h> +#include <asm/kvm_booke_hv_asm.h> + /* * Macros used for common Book-e exception handling */ @@ -28,14 +31,15 @@ */ #define THREAD_NORMSAVE(offset) (THREAD_NORMSAVES + (offset * 4)) -#define NORMAL_EXCEPTION_PROLOG \ +#define NORMAL_EXCEPTION_PROLOG(intno) \ mtspr SPRN_SPRG_WSCRATCH0, r10; /* save one register */ \ mfspr r10, SPRN_SPRG_THREAD; \ stw r11, THREAD_NORMSAVE(0)(r10); \ stw r13, THREAD_NORMSAVE(2)(r10); \ mfcr r13; /* save CR in r13 for now */\ - mfspr r11,SPRN_SRR1; /* check whether user or kernel */\ - andi. r11,r11,MSR_PR; \ + mfspr r11, SPRN_SRR1; \ + DO_KVM BOOKE_INTERRUPT_##intno SPRN_SRR1; \ + andi. r11, r11, MSR_PR; /* check whether user or kernel */\ mr r11, r1; \ beq 1f; \ /* if from user, start at top of this thread's kernel stack */ \ @@ -113,7 +117,7 @@ * registers as the normal prolog above. Instead we use a portion of the * critical/machine check exception stack at low physical addresses. */ -#define EXC_LEVEL_EXCEPTION_PROLOG(exc_level, exc_level_srr0, exc_level_srr1) \ +#define EXC_LEVEL_EXCEPTION_PROLOG(exc_level, intno, exc_level_srr0, exc_level_srr1) \ mtspr SPRN_SPRG_WSCRATCH_##exc_level,r8; \ BOOKE_LOAD_EXC_LEVEL_STACK(exc_level);/* r8 points to the exc_level stack*/ \ stw r9,GPR9(r8); /* save various registers */\ @@ -121,8 +125,9 @@ stw r10,GPR10(r8); \ stw r11,GPR11(r8); \ stw r9,_CCR(r8); /* save CR on stack */\ - mfspr r10,exc_level_srr1; /* check whether user or kernel */\ - andi. r10,r10,MSR_PR; \ + mfspr r11,exc_level_srr1; /* check whether user or kernel */\ + DO_KVM BOOKE_INTERRUPT_##intno exc_level_srr1; \ + andi. r11,r11,MSR_PR; \ mfspr r11,SPRN_SPRG_THREAD; /* if from user, start at top of */\ lwz r11,THREAD_INFO-THREAD(r11); /* this thread's kernel stack */\ addi r11,r11,EXC_LVL_FRAME_OVERHEAD; /* allocate stack frame */\ @@ -162,12 +167,30 @@ SAVE_4GPRS(3, r11); \ SAVE_2GPRS(7, r11) -#define CRITICAL_EXCEPTION_PROLOG \ - EXC_LEVEL_EXCEPTION_PROLOG(CRIT, SPRN_CSRR0, SPRN_CSRR1) +#define CRITICAL_EXCEPTION_PROLOG(intno) \ + EXC_LEVEL_EXCEPTION_PROLOG(CRIT, intno, SPRN_CSRR0, SPRN_CSRR1) #define DEBUG_EXCEPTION_PROLOG \ - EXC_LEVEL_EXCEPTION_PROLOG(DBG, SPRN_DSRR0, SPRN_DSRR1) + EXC_LEVEL_EXCEPTION_PROLOG(DBG, DEBUG, SPRN_DSRR0, SPRN_DSRR1) #define MCHECK_EXCEPTION_PROLOG \ - EXC_LEVEL_EXCEPTION_PROLOG(MC, SPRN_MCSRR0, SPRN_MCSRR1) + EXC_LEVEL_EXCEPTION_PROLOG(MC, MACHINE_CHECK, \ + SPRN_MCSRR0, SPRN_MCSRR1) + +/* + * Guest Doorbell -- this is a bit odd in that uses GSRR0/1 despite + * being delivered to the host. This exception can only happen + * inside a KVM guest -- so we just handle up to the DO_KVM rather + * than try to fit this into one of the existing prolog macros. + */ +#define GUEST_DOORBELL_EXCEPTION \ + START_EXCEPTION(GuestDoorbell); \ + mtspr SPRN_SPRG_WSCRATCH0, r10; /* save one register */ \ + mfspr r10, SPRN_SPRG_THREAD; \ + stw r11, THREAD_NORMSAVE(0)(r10); \ + mfspr r11, SPRN_SRR1; \ + stw r13, THREAD_NORMSAVE(2)(r10); \ + mfcr r13; /* save CR in r13 for now */\ + DO_KVM BOOKE_INTERRUPT_GUEST_DBELL SPRN_GSRR1; \ + trap /* * Exception vectors. @@ -181,16 +204,16 @@ label: .long func; \ .long ret_from_except_full -#define EXCEPTION(n, label, hdlr, xfer) \ +#define EXCEPTION(n, intno, label, hdlr, xfer) \ START_EXCEPTION(label); \ - NORMAL_EXCEPTION_PROLOG; \ + NORMAL_EXCEPTION_PROLOG(intno); \ addi r3,r1,STACK_FRAME_OVERHEAD; \ xfer(n, hdlr) -#define CRITICAL_EXCEPTION(n, label, hdlr) \ - START_EXCEPTION(label); \ - CRITICAL_EXCEPTION_PROLOG; \ - addi r3,r1,STACK_FRAME_OVERHEAD; \ +#define CRITICAL_EXCEPTION(n, intno, label, hdlr) \ + START_EXCEPTION(label); \ + CRITICAL_EXCEPTION_PROLOG(intno); \ + addi r3,r1,STACK_FRAME_OVERHEAD; \ EXC_XFER_TEMPLATE(hdlr, n+2, (MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)), \ NOCOPY, crit_transfer_to_handler, \ ret_from_crit_exc) @@ -302,7 +325,7 @@ label: #define DEBUG_CRIT_EXCEPTION \ START_EXCEPTION(DebugCrit); \ - CRITICAL_EXCEPTION_PROLOG; \ + CRITICAL_EXCEPTION_PROLOG(DEBUG); \ \ /* \ * If there is a single step or branch-taken exception in an \ @@ -355,7 +378,7 @@ label: #define DATA_STORAGE_EXCEPTION \ START_EXCEPTION(DataStorage) \ - NORMAL_EXCEPTION_PROLOG; \ + NORMAL_EXCEPTION_PROLOG(DATA_STORAGE); \ mfspr r5,SPRN_ESR; /* Grab the ESR and save it */ \ stw r5,_ESR(r11); \ mfspr r4,SPRN_DEAR; /* Grab the DEAR */ \ @@ -363,7 +386,7 @@ label: #define INSTRUCTION_STORAGE_EXCEPTION \ START_EXCEPTION(InstructionStorage) \ - NORMAL_EXCEPTION_PROLOG; \ + NORMAL_EXCEPTION_PROLOG(INST_STORAGE); \ mfspr r5,SPRN_ESR; /* Grab the ESR and save it */ \ stw r5,_ESR(r11); \ mr r4,r12; /* Pass SRR0 as arg2 */ \ @@ -372,7 +395,7 @@ label: #define ALIGNMENT_EXCEPTION \ START_EXCEPTION(Alignment) \ - NORMAL_EXCEPTION_PROLOG; \ + NORMAL_EXCEPTION_PROLOG(ALIGNMENT); \ mfspr r4,SPRN_DEAR; /* Grab the DEAR and save it */ \ stw r4,_DEAR(r11); \ addi r3,r1,STACK_FRAME_OVERHEAD; \ @@ -380,7 +403,7 @@ label: #define PROGRAM_EXCEPTION \ START_EXCEPTION(Program) \ - NORMAL_EXCEPTION_PROLOG; \ + NORMAL_EXCEPTION_PROLOG(PROGRAM); \ mfspr r4,SPRN_ESR; /* Grab the ESR and save it */ \ stw r4,_ESR(r11); \ addi r3,r1,STACK_FRAME_OVERHEAD; \ @@ -388,7 +411,7 @@ label: #define DECREMENTER_EXCEPTION \ START_EXCEPTION(Decrementer) \ - NORMAL_EXCEPTION_PROLOG; \ + NORMAL_EXCEPTION_PROLOG(DECREMENTER); \ lis r0,TSR_DIS@h; /* Setup the DEC interrupt mask */ \ mtspr SPRN_TSR,r0; /* Clear the DEC interrupt */ \ addi r3,r1,STACK_FRAME_OVERHEAD; \ @@ -396,7 +419,7 @@ label: #define FP_UNAVAILABLE_EXCEPTION \ START_EXCEPTION(FloatingPointUnavailable) \ - NORMAL_EXCEPTION_PROLOG; \ + NORMAL_EXCEPTION_PROLOG(FP_UNAVAIL); \ beq 1f; \ bl load_up_fpu; /* if from user, just load it up */ \ b fast_exception_return; \ diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S index 28e62598d0e8..1f4434a38608 100644 --- a/arch/powerpc/kernel/head_fsl_booke.S +++ b/arch/powerpc/kernel/head_fsl_booke.S @@ -301,19 +301,20 @@ _ENTRY(__early_start) interrupt_base: /* Critical Input Interrupt */ - CRITICAL_EXCEPTION(0x0100, CriticalInput, unknown_exception) + CRITICAL_EXCEPTION(0x0100, CRITICAL, CriticalInput, unknown_exception) /* Machine Check Interrupt */ #ifdef CONFIG_E200 /* no RFMCI, MCSRRs on E200 */ - CRITICAL_EXCEPTION(0x0200, MachineCheck, machine_check_exception) + CRITICAL_EXCEPTION(0x0200, MACHINE_CHECK, MachineCheck, \ + machine_check_exception) #else MCHECK_EXCEPTION(0x0200, MachineCheck, machine_check_exception) #endif /* Data Storage Interrupt */ START_EXCEPTION(DataStorage) - NORMAL_EXCEPTION_PROLOG + NORMAL_EXCEPTION_PROLOG(DATA_STORAGE) mfspr r5,SPRN_ESR /* Grab the ESR, save it, pass arg3 */ stw r5,_ESR(r11) mfspr r4,SPRN_DEAR /* Grab the DEAR, save it, pass arg2 */ @@ -328,7 +329,7 @@ interrupt_base: INSTRUCTION_STORAGE_EXCEPTION /* External Input Interrupt */ - EXCEPTION(0x0500, ExternalInput, do_IRQ, EXC_XFER_LITE) + EXCEPTION(0x0500, EXTERNAL, ExternalInput, do_IRQ, EXC_XFER_LITE) /* Alignment Interrupt */ ALIGNMENT_EXCEPTION @@ -342,32 +343,36 @@ interrupt_base: #else #ifdef CONFIG_E200 /* E200 treats 'normal' floating point instructions as FP Unavail exception */ - EXCEPTION(0x0800, FloatingPointUnavailable, program_check_exception, EXC_XFER_EE) + EXCEPTION(0x0800, FP_UNAVAIL, FloatingPointUnavailable, \ + program_check_exception, EXC_XFER_EE) #else - EXCEPTION(0x0800, FloatingPointUnavailable, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x0800, FP_UNAVAIL, FloatingPointUnavailable, \ + unknown_exception, EXC_XFER_EE) #endif #endif /* System Call Interrupt */ START_EXCEPTION(SystemCall) - NORMAL_EXCEPTION_PROLOG + NORMAL_EXCEPTION_PROLOG(SYSCALL) EXC_XFER_EE_LITE(0x0c00, DoSyscall) /* Auxiliary Processor Unavailable Interrupt */ - EXCEPTION(0x2900, AuxillaryProcessorUnavailable, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x2900, AP_UNAVAIL, AuxillaryProcessorUnavailable, \ + unknown_exception, EXC_XFER_EE) /* Decrementer Interrupt */ DECREMENTER_EXCEPTION /* Fixed Internal Timer Interrupt */ /* TODO: Add FIT support */ - EXCEPTION(0x3100, FixedIntervalTimer, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x3100, FIT, FixedIntervalTimer, \ + unknown_exception, EXC_XFER_EE) /* Watchdog Timer Interrupt */ #ifdef CONFIG_BOOKE_WDT - CRITICAL_EXCEPTION(0x3200, WatchdogTimer, WatchdogException) + CRITICAL_EXCEPTION(0x3200, WATCHDOG, WatchdogTimer, WatchdogException) #else - CRITICAL_EXCEPTION(0x3200, WatchdogTimer, unknown_exception) + CRITICAL_EXCEPTION(0x3200, WATCHDOG, WatchdogTimer, unknown_exception) #endif /* Data TLB Error Interrupt */ @@ -375,10 +380,16 @@ interrupt_base: mtspr SPRN_SPRG_WSCRATCH0, r10 /* Save some working registers */ mfspr r10, SPRN_SPRG_THREAD stw r11, THREAD_NORMSAVE(0)(r10) +#ifdef CONFIG_KVM_BOOKE_HV +BEGIN_FTR_SECTION + mfspr r11, SPRN_SRR1 +END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV) +#endif stw r12, THREAD_NORMSAVE(1)(r10) stw r13, THREAD_NORMSAVE(2)(r10) mfcr r13 stw r13, THREAD_NORMSAVE(3)(r10) + DO_KVM BOOKE_INTERRUPT_DTLB_MISS SPRN_SRR1 mfspr r10, SPRN_DEAR /* Get faulting address */ /* If we are faulting a kernel address, we have to use the @@ -463,10 +474,16 @@ interrupt_base: mtspr SPRN_SPRG_WSCRATCH0, r10 /* Save some working registers */ mfspr r10, SPRN_SPRG_THREAD stw r11, THREAD_NORMSAVE(0)(r10) +#ifdef CONFIG_KVM_BOOKE_HV +BEGIN_FTR_SECTION + mfspr r11, SPRN_SRR1 +END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV) +#endif stw r12, THREAD_NORMSAVE(1)(r10) stw r13, THREAD_NORMSAVE(2)(r10) mfcr r13 stw r13, THREAD_NORMSAVE(3)(r10) + DO_KVM BOOKE_INTERRUPT_ITLB_MISS SPRN_SRR1 mfspr r10, SPRN_SRR0 /* Get faulting address */ /* If we are faulting a kernel address, we have to use the @@ -538,36 +555,54 @@ interrupt_base: #ifdef CONFIG_SPE /* SPE Unavailable */ START_EXCEPTION(SPEUnavailable) - NORMAL_EXCEPTION_PROLOG + NORMAL_EXCEPTION_PROLOG(SPE_UNAVAIL) bne load_up_spe addi r3,r1,STACK_FRAME_OVERHEAD EXC_XFER_EE_LITE(0x2010, KernelSPE) #else - EXCEPTION(0x2020, SPEUnavailable, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x2020, SPE_UNAVAIL, SPEUnavailable, \ + unknown_exception, EXC_XFER_EE) #endif /* CONFIG_SPE */ /* SPE Floating Point Data */ #ifdef CONFIG_SPE - EXCEPTION(0x2030, SPEFloatingPointData, SPEFloatingPointException, EXC_XFER_EE); + EXCEPTION(0x2030, SPE_FP_DATA, SPEFloatingPointData, \ + SPEFloatingPointException, EXC_XFER_EE); /* SPE Floating Point Round */ - EXCEPTION(0x2050, SPEFloatingPointRound, SPEFloatingPointRoundException, EXC_XFER_EE) + EXCEPTION(0x2050, SPE_FP_ROUND, SPEFloatingPointRound, \ + SPEFloatingPointRoundException, EXC_XFER_EE) #else - EXCEPTION(0x2040, SPEFloatingPointData, unknown_exception, EXC_XFER_EE) - EXCEPTION(0x2050, SPEFloatingPointRound, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x2040, SPE_FP_DATA, SPEFloatingPointData, \ + unknown_exception, EXC_XFER_EE) + EXCEPTION(0x2050, SPE_FP_ROUND, SPEFloatingPointRound, \ + unknown_exception, EXC_XFER_EE) #endif /* CONFIG_SPE */ /* Performance Monitor */ - EXCEPTION(0x2060, PerformanceMonitor, performance_monitor_exception, EXC_XFER_STD) + EXCEPTION(0x2060, PERFORMANCE_MONITOR, PerformanceMonitor, \ + performance_monitor_exception, EXC_XFER_STD) - EXCEPTION(0x2070, Doorbell, doorbell_exception, EXC_XFER_STD) + EXCEPTION(0x2070, DOORBELL, Doorbell, doorbell_exception, EXC_XFER_STD) - CRITICAL_EXCEPTION(0x2080, CriticalDoorbell, unknown_exception) + CRITICAL_EXCEPTION(0x2080, DOORBELL_CRITICAL, \ + CriticalDoorbell, unknown_exception) /* Debug Interrupt */ DEBUG_DEBUG_EXCEPTION DEBUG_CRIT_EXCEPTION + GUEST_DOORBELL_EXCEPTION + + CRITICAL_EXCEPTION(0, GUEST_DBELL_CRIT, CriticalGuestDoorbell, \ + unknown_exception) + + /* Hypercall */ + EXCEPTION(0, HV_SYSCALL, Hypercall, unknown_exception, EXC_XFER_EE) + + /* Embedded Hypervisor Privilege */ + EXCEPTION(0, HV_PRIV, Ehvpriv, unknown_exception, EXC_XFER_EE) + /* * Local functions */ @@ -871,16 +906,31 @@ _GLOBAL(__setup_e500mc_ivors) mtspr SPRN_IVOR36,r3 li r3,CriticalDoorbell@l mtspr SPRN_IVOR37,r3 - sync - blr -/* - * extern void giveup_altivec(struct task_struct *prev) - * - * The e500 core does not have an AltiVec unit. - */ -_GLOBAL(giveup_altivec) + /* + * We only want to touch IVOR38-41 if we're running on hardware + * that supports category E.HV. The architectural way to determine + * this is MMUCFG[LPIDSIZE]. + */ + mfspr r3, SPRN_MMUCFG + andis. r3, r3, MMUCFG_LPIDSIZE@h + beq no_hv + li r3,GuestDoorbell@l + mtspr SPRN_IVOR38,r3 + li r3,CriticalGuestDoorbell@l + mtspr SPRN_IVOR39,r3 + li r3,Hypercall@l + mtspr SPRN_IVOR40,r3 + li r3,Ehvpriv@l + mtspr SPRN_IVOR41,r3 +skip_hv_ivors: + sync blr +no_hv: + lwz r3, CPU_SPEC_FEATURES(r5) + rlwinm r3, r3, 0, ~CPU_FTR_EMB_HV + stw r3, CPU_SPEC_FEATURES(r5) + b skip_hv_ivors #ifdef CONFIG_SPE /* diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c index 6d2209ac0c44..2099d9a879e8 100644 --- a/arch/powerpc/kernel/idle.c +++ b/arch/powerpc/kernel/idle.c @@ -113,29 +113,6 @@ void cpu_idle(void) } } - -/* - * cpu_idle_wait - Used to ensure that all the CPUs come out of the old - * idle loop and start using the new idle loop. - * Required while changing idle handler on SMP systems. - * Caller must have changed idle handler to the new value before the call. - * This window may be larger on shared systems. - */ -void cpu_idle_wait(void) -{ - int cpu; - smp_mb(); - - /* kick all the CPUs so that they exit out of old idle routine */ - get_online_cpus(); - for_each_online_cpu(cpu) { - if (cpu != smp_processor_id()) - smp_send_reschedule(cpu); - } - put_online_cpus(); -} -EXPORT_SYMBOL_GPL(cpu_idle_wait); - int powersave_nap; #ifdef CONFIG_SYSCTL diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S index 0cdc9a392839..7140d838339e 100644 --- a/arch/powerpc/kernel/idle_power7.S +++ b/arch/powerpc/kernel/idle_power7.S @@ -16,6 +16,7 @@ #include <asm/asm-offsets.h> #include <asm/ppc-opcode.h> #include <asm/hw_irq.h> +#include <asm/kvm_book3s_asm.h> #undef DEBUG @@ -81,6 +82,12 @@ _GLOBAL(power7_idle) std r9,_MSR(r1) std r1,PACAR1(r13) +#ifdef CONFIG_KVM_BOOK3S_64_HV + /* Tell KVM we're napping */ + li r4,KVM_HWTHREAD_IN_NAP + stb r4,HSTATE_HWTHREAD_STATE(r13) +#endif + /* Magic NAP mode enter sequence */ std r0,0(r1) ptesync diff --git a/arch/powerpc/kernel/init_task.c b/arch/powerpc/kernel/init_task.c deleted file mode 100644 index d076d465dbd1..000000000000 --- a/arch/powerpc/kernel/init_task.c +++ /dev/null @@ -1,29 +0,0 @@ -#include <linux/mm.h> -#include <linux/export.h> -#include <linux/sched.h> -#include <linux/init.h> -#include <linux/init_task.h> -#include <linux/fs.h> -#include <linux/mqueue.h> -#include <asm/uaccess.h> - -static struct signal_struct init_signals = INIT_SIGNALS(init_signals); -static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand); -/* - * Initial thread structure. - * - * We need to make sure that this is 16384-byte aligned due to the - * way process stacks are handled. This is done by having a special - * "init_task" linker map entry.. - */ -union thread_union init_thread_union __init_task_data = - { INIT_THREAD_INFO(init_task) }; - -/* - * Initial task structure. - * - * All other task structs will be allocated on slabs in fork.c - */ -struct task_struct init_task = INIT_TASK(init_task); - -EXPORT_SYMBOL(init_task); diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 5ec1b2354ca6..7835a5e1ea5f 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -229,6 +229,19 @@ notrace void arch_local_irq_restore(unsigned long en) */ if (unlikely(irq_happened != PACA_IRQ_HARD_DIS)) __hard_irq_disable(); +#ifdef CONFIG_TRACE_IRQFLAG + else { + /* + * We should already be hard disabled here. We had bugs + * where that wasn't the case so let's dbl check it and + * warn if we are wrong. Only do that when IRQ tracing + * is enabled as mfmsr() can be costly. + */ + if (WARN_ON(mfmsr() & MSR_EE)) + __hard_irq_disable(); + } +#endif /* CONFIG_TRACE_IRQFLAG */ + set_soft_enabled(0); /* @@ -260,11 +273,17 @@ EXPORT_SYMBOL(arch_local_irq_restore); * if they are currently disabled. This is typically called before * schedule() or do_signal() when returning to userspace. We do it * in C to avoid the burden of dealing with lockdep etc... + * + * NOTE: This is called with interrupts hard disabled but not marked + * as such in paca->irq_happened, so we need to resync this. */ void restore_interrupts(void) { - if (irqs_disabled()) + if (irqs_disabled()) { + local_paca->irq_happened |= PACA_IRQ_HARD_DIS; local_irq_enable(); + } else + __hard_irq_enable(); } #endif /* CONFIG_PPC64 */ @@ -330,14 +349,10 @@ void migrate_irqs(void) alloc_cpumask_var(&mask, GFP_KERNEL); - for_each_irq(irq) { + for_each_irq_desc(irq, desc) { struct irq_data *data; struct irq_chip *chip; - desc = irq_to_desc(irq); - if (!desc) - continue; - data = irq_desc_get_irq_data(desc); if (irqd_is_per_cpu(data)) continue; @@ -572,7 +587,7 @@ int irq_choose_cpu(const struct cpumask *mask) { int cpuid; - if (cpumask_equal(mask, cpu_all_mask)) { + if (cpumask_equal(mask, cpu_online_mask)) { static int irq_rover; static DEFINE_RAW_SPINLOCK(irq_rover_lock); unsigned long flags; diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c index c957b1202bdc..5df777794403 100644 --- a/arch/powerpc/kernel/machine_kexec.c +++ b/arch/powerpc/kernel/machine_kexec.c @@ -23,14 +23,11 @@ void machine_kexec_mask_interrupts(void) { unsigned int i; + struct irq_desc *desc; - for_each_irq(i) { - struct irq_desc *desc = irq_to_desc(i); + for_each_irq_desc(i, desc) { struct irq_chip *chip; - if (!desc) - continue; - chip = irq_desc_get_chip(desc); if (!chip) continue; diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index 7cd07b42ca1a..386d57f66f28 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -738,8 +738,23 @@ relocate_new_kernel: mr r5, r31 li r0, 0 -#elif defined(CONFIG_44x) && !defined(CONFIG_PPC_47x) +#elif defined(CONFIG_44x) + /* Save our parameters */ + mr r29, r3 + mr r30, r4 + mr r31, r5 + +#ifdef CONFIG_PPC_47x + /* Check for 47x cores */ + mfspr r3,SPRN_PVR + srwi r3,r3,16 + cmplwi cr0,r3,PVR_476@h + beq setup_map_47x + cmplwi cr0,r3,PVR_476_ISS@h + beq setup_map_47x +#endif /* CONFIG_PPC_47x */ + /* * Code for setting up 1:1 mapping for PPC440x for KEXEC * @@ -753,16 +768,15 @@ relocate_new_kernel: * 5) Invalidate the tmp mapping. * * - Based on the kexec support code for FSL BookE - * - Doesn't support 47x yet. * */ - /* Save our parameters */ - mr r29, r3 - mr r30, r4 - mr r31, r5 - /* Load our MSR_IS and TID to MMUCR for TLB search */ - mfspr r3,SPRN_PID + /* + * Load the PID with kernel PID (0). + * Also load our MSR_IS and TID to MMUCR for TLB search. + */ + li r3, 0 + mtspr SPRN_PID, r3 mfmsr r4 andi. r4,r4,MSR_IS@l beq wmmucr @@ -900,6 +914,179 @@ next_tlb: li r3, 0 tlbwe r3, r24, PPC44x_TLB_PAGEID sync + b ppc44x_map_done + +#ifdef CONFIG_PPC_47x + + /* 1:1 mapping for 47x */ + +setup_map_47x: + + /* + * Load the kernel pid (0) to PID and also to MMUCR[TID]. + * Also set the MSR IS->MMUCR STS + */ + li r3, 0 + mtspr SPRN_PID, r3 /* Set PID */ + mfmsr r4 /* Get MSR */ + andi. r4, r4, MSR_IS@l /* TS=1? */ + beq 1f /* If not, leave STS=0 */ + oris r3, r3, PPC47x_MMUCR_STS@h /* Set STS=1 */ +1: mtspr SPRN_MMUCR, r3 /* Put MMUCR */ + sync + + /* Find the entry we are running from */ + bl 2f +2: mflr r23 + tlbsx r23, 0, r23 + tlbre r24, r23, 0 /* TLB Word 0 */ + tlbre r25, r23, 1 /* TLB Word 1 */ + tlbre r26, r23, 2 /* TLB Word 2 */ + + + /* + * Invalidates all the tlb entries by writing to 256 RPNs(r4) + * of 4k page size in all 4 ways (0-3 in r3). + * This would invalidate the entire UTLB including the one we are + * running from. However the shadow TLB entries would help us + * to continue the execution, until we flush them (rfi/isync). + */ + addis r3, 0, 0x8000 /* specify the way */ + addi r4, 0, 0 /* TLB Word0 = (EPN=0, VALID = 0) */ + addi r5, 0, 0 + b clear_utlb_entry + + /* Align the loop to speed things up. from head_44x.S */ + .align 6 + +clear_utlb_entry: + + tlbwe r4, r3, 0 + tlbwe r5, r3, 1 + tlbwe r5, r3, 2 + addis r3, r3, 0x2000 /* Increment the way */ + cmpwi r3, 0 + bne clear_utlb_entry + addis r3, 0, 0x8000 + addis r4, r4, 0x100 /* Increment the EPN */ + cmpwi r4, 0 + bne clear_utlb_entry + + /* Create the entries in the other address space */ + mfmsr r5 + rlwinm r7, r5, 27, 31, 31 /* Get the TS (Bit 26) from MSR */ + xori r7, r7, 1 /* r7 = !TS */ + + insrwi r24, r7, 1, 21 /* Change the TS in the saved TLB word 0 */ + + /* + * write out the TLB entries for the tmp mapping + * Use way '0' so that we could easily invalidate it later. + */ + lis r3, 0x8000 /* Way '0' */ + + tlbwe r24, r3, 0 + tlbwe r25, r3, 1 + tlbwe r26, r3, 2 + + /* Update the msr to the new TS */ + insrwi r5, r7, 1, 26 + + bl 1f +1: mflr r6 + addi r6, r6, (2f-1b) + + mtspr SPRN_SRR0, r6 + mtspr SPRN_SRR1, r5 + rfi + + /* + * Now we are in the tmp address space. + * Create a 1:1 mapping for 0-2GiB in the original TS. + */ +2: + li r3, 0 + li r4, 0 /* TLB Word 0 */ + li r5, 0 /* TLB Word 1 */ + li r6, 0 + ori r6, r6, PPC47x_TLB2_S_RWX /* TLB word 2 */ + + li r8, 0 /* PageIndex */ + + xori r7, r7, 1 /* revert back to original TS */ + +write_utlb: + rotlwi r5, r8, 28 /* RPN = PageIndex * 256M */ + /* ERPN = 0 as we don't use memory above 2G */ + + mr r4, r5 /* EPN = RPN */ + ori r4, r4, (PPC47x_TLB0_VALID | PPC47x_TLB0_256M) + insrwi r4, r7, 1, 21 /* Insert the TS to Word 0 */ + + tlbwe r4, r3, 0 /* Write out the entries */ + tlbwe r5, r3, 1 + tlbwe r6, r3, 2 + addi r8, r8, 1 + cmpwi r8, 8 /* Have we completed ? */ + bne write_utlb + + /* make sure we complete the TLB write up */ + isync + + /* + * Prepare to jump to the 1:1 mapping. + * 1) Extract page size of the tmp mapping + * DSIZ = TLB_Word0[22:27] + * 2) Calculate the physical address of the address + * to jump to. + */ + rlwinm r10, r24, 0, 22, 27 + + cmpwi r10, PPC47x_TLB0_4K + bne 0f + li r10, 0x1000 /* r10 = 4k */ + bl 1f + +0: + /* Defaults to 256M */ + lis r10, 0x1000 + + bl 1f +1: mflr r4 + addi r4, r4, (2f-1b) /* virtual address of 2f */ + + subi r11, r10, 1 /* offsetmask = Pagesize - 1 */ + not r10, r11 /* Pagemask = ~(offsetmask) */ + + and r5, r25, r10 /* Physical page */ + and r6, r4, r11 /* offset within the current page */ + + or r5, r5, r6 /* Physical address for 2f */ + + /* Switch the TS in MSR to the original one */ + mfmsr r8 + insrwi r8, r7, 1, 26 + + mtspr SPRN_SRR1, r8 + mtspr SPRN_SRR0, r5 + rfi + +2: + /* Invalidate the tmp mapping */ + lis r3, 0x8000 /* Way '0' */ + + clrrwi r24, r24, 12 /* Clear the valid bit */ + tlbwe r24, r3, 0 + tlbwe r25, r3, 1 + tlbwe r26, r3, 2 + + /* Make sure we complete the TLB write and flush the shadow TLB */ + isync + +#endif + +ppc44x_map_done: + /* Restore the parameters */ mr r3, r29 diff --git a/arch/powerpc/kernel/module_32.c b/arch/powerpc/kernel/module_32.c index 0b6d79617d7b..2e3200ca485f 100644 --- a/arch/powerpc/kernel/module_32.c +++ b/arch/powerpc/kernel/module_32.c @@ -176,8 +176,8 @@ int module_frob_arch_sections(Elf32_Ehdr *hdr, static inline int entry_matches(struct ppc_plt_entry *entry, Elf32_Addr val) { - if (entry->jump[0] == 0x3d600000 + ((val + 0x8000) >> 16) - && entry->jump[1] == 0x396b0000 + (val & 0xffff)) + if (entry->jump[0] == 0x3d800000 + ((val + 0x8000) >> 16) + && entry->jump[1] == 0x398c0000 + (val & 0xffff)) return 1; return 0; } @@ -204,10 +204,9 @@ static uint32_t do_plt_call(void *location, entry++; } - /* Stolen from Paul Mackerras as well... */ - entry->jump[0] = 0x3d600000+((val+0x8000)>>16); /* lis r11,sym@ha */ - entry->jump[1] = 0x396b0000 + (val&0xffff); /* addi r11,r11,sym@l*/ - entry->jump[2] = 0x7d6903a6; /* mtctr r11 */ + entry->jump[0] = 0x3d800000+((val+0x8000)>>16); /* lis r12,sym@ha */ + entry->jump[1] = 0x398c0000 + (val&0xffff); /* addi r12,r12,sym@l*/ + entry->jump[2] = 0x7d8903a6; /* mtctr r12 */ entry->jump[3] = 0x4e800420; /* bctr */ DEBUGP("Initialized plt for 0x%x at %p\n", val, entry); diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index 0bb1f98613ba..fbe1a12dc7f1 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -36,10 +36,7 @@ struct lppaca lppaca[] = { [0 ... (NR_LPPACAS-1)] = { .desc = 0xd397d781, /* "LpPa" */ .size = sizeof(struct lppaca), - .dyn_proc_status = 2, - .decr_val = 0x00ff0000, .fpregs_in_use = 1, - .end_of_quantum = 0xfffffffffffffffful, .slb_count = 64, .vmxregs_in_use = 0, .page_ins = 0, diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c index 786a2700ec2d..3e4031581c65 100644 --- a/arch/powerpc/kernel/ppc_ksyms.c +++ b/arch/powerpc/kernel/ppc_ksyms.c @@ -85,8 +85,6 @@ EXPORT_SYMBOL(csum_tcpudp_magic); EXPORT_SYMBOL(__copy_tofrom_user); EXPORT_SYMBOL(__clear_user); -EXPORT_SYMBOL(__strncpy_from_user); -EXPORT_SYMBOL(__strnlen_user); EXPORT_SYMBOL(copy_page); #if defined(CONFIG_PCI) && defined(CONFIG_PPC32) @@ -190,3 +188,7 @@ EXPORT_SYMBOL(__arch_hweight16); EXPORT_SYMBOL(__arch_hweight32); EXPORT_SYMBOL(__arch_hweight64); #endif + +#ifdef CONFIG_PPC_BOOK3S_64 +EXPORT_SYMBOL_GPL(mmu_psize_defs); +#endif diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 4937c9690090..710f400476de 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -124,7 +124,7 @@ void enable_kernel_altivec(void) if (current->thread.regs && (current->thread.regs->msr & MSR_VEC)) giveup_altivec(current); else - giveup_altivec(NULL); /* just enable AltiVec for kernel - force */ + giveup_altivec_notask(); #else giveup_altivec(last_task_used_altivec); #endif /* CONFIG_SMP */ @@ -711,18 +711,21 @@ release_thread(struct task_struct *t) } /* - * This gets called before we allocate a new thread and copy - * the current task into it. + * this gets called so that we can store coprocessor state into memory and + * copy the current task into the new thread. */ -void prepare_to_copy(struct task_struct *tsk) +int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { - flush_fp_to_thread(current); - flush_altivec_to_thread(current); - flush_vsx_to_thread(current); - flush_spe_to_thread(current); + flush_fp_to_thread(src); + flush_altivec_to_thread(src); + flush_vsx_to_thread(src); + flush_spe_to_thread(src); #ifdef CONFIG_HAVE_HW_BREAKPOINT - flush_ptrace_hw_breakpoint(tsk); + flush_ptrace_hw_breakpoint(src); #endif /* CONFIG_HAVE_HW_BREAKPOINT */ + + *dst = *src; + return 0; } /* @@ -1252,37 +1255,6 @@ void __ppc64_runlatch_off(void) } #endif /* CONFIG_PPC64 */ -#if THREAD_SHIFT < PAGE_SHIFT - -static struct kmem_cache *thread_info_cache; - -struct thread_info *alloc_thread_info_node(struct task_struct *tsk, int node) -{ - struct thread_info *ti; - - ti = kmem_cache_alloc_node(thread_info_cache, GFP_KERNEL, node); - if (unlikely(ti == NULL)) - return NULL; -#ifdef CONFIG_DEBUG_STACK_USAGE - memset(ti, 0, THREAD_SIZE); -#endif - return ti; -} - -void free_thread_info(struct thread_info *ti) -{ - kmem_cache_free(thread_info_cache, ti); -} - -void thread_info_cache_init(void) -{ - thread_info_cache = kmem_cache_create("thread_info", THREAD_SIZE, - THREAD_SIZE, 0, NULL); - BUG_ON(thread_info_cache == NULL); -} - -#endif /* THREAD_SHIFT < PAGE_SHIFT */ - unsigned long arch_align_stack(unsigned long sp) { if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space) diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 99860273211b..1b488e5305c5 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -680,6 +680,9 @@ static void __init early_cmdline_parse(void) #define OV3_VMX 0x40 /* VMX/Altivec */ #define OV3_DFP 0x20 /* decimal FP */ +/* Option vector 4: IBM PAPR implementation */ +#define OV4_MIN_ENT_CAP 0x01 /* minimum VP entitled capacity */ + /* Option vector 5: PAPR/OF options supported */ #define OV5_LPAR 0x80 /* logical partitioning supported */ #define OV5_SPLPAR 0x40 /* shared-processor LPAR supported */ @@ -701,6 +704,8 @@ static void __init early_cmdline_parse(void) #define OV5_XCMO 0x00 #endif #define OV5_TYPE1_AFFINITY 0x80 /* Type 1 NUMA affinity */ +#define OV5_PFO_HW_RNG 0x80 /* PFO Random Number Generator */ +#define OV5_PFO_HW_ENCR 0x20 /* PFO Encryption Accelerator */ /* Option Vector 6: IBM PAPR hints */ #define OV6_LINUX 0x02 /* Linux is our OS */ @@ -744,11 +749,12 @@ static unsigned char ibm_architecture_vec[] = { OV3_FP | OV3_VMX | OV3_DFP, /* option vector 4: IBM PAPR implementation */ - 2 - 2, /* length */ + 3 - 2, /* length */ 0, /* don't halt */ + OV4_MIN_ENT_CAP, /* minimum VP entitled capacity */ /* option vector 5: PAPR/OF options */ - 13 - 2, /* length */ + 18 - 2, /* length */ 0, /* don't ignore, don't halt */ OV5_LPAR | OV5_SPLPAR | OV5_LARGE_PAGES | OV5_DRCONF_MEMORY | OV5_DONATE_DEDICATE_CPU | OV5_MSI, @@ -762,8 +768,13 @@ static unsigned char ibm_architecture_vec[] = { * must match by the macro below. Update the definition if * the structure layout changes. */ -#define IBM_ARCH_VEC_NRCORES_OFFSET 100 +#define IBM_ARCH_VEC_NRCORES_OFFSET 101 W(NR_CPUS), /* number of cores supported */ + 0, + 0, + 0, + 0, + OV5_PFO_HW_RNG | OV5_PFO_HW_ENCR, /* option vector 6: IBM PAPR hints */ 4 - 2, /* length */ diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index dd5e214cdf21..c10fc28b9092 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -1432,40 +1432,6 @@ static long ppc_del_hwdebug(struct task_struct *child, long addr, long data) #endif } -/* - * Here are the old "legacy" powerpc specific getregs/setregs ptrace calls, - * we mark them as obsolete now, they will be removed in a future version - */ -static long arch_ptrace_old(struct task_struct *child, long request, - unsigned long addr, unsigned long data) -{ - void __user *datavp = (void __user *) data; - - switch (request) { - case PPC_PTRACE_GETREGS: /* Get GPRs 0 - 31. */ - return copy_regset_to_user(child, &user_ppc_native_view, - REGSET_GPR, 0, 32 * sizeof(long), - datavp); - - case PPC_PTRACE_SETREGS: /* Set GPRs 0 - 31. */ - return copy_regset_from_user(child, &user_ppc_native_view, - REGSET_GPR, 0, 32 * sizeof(long), - datavp); - - case PPC_PTRACE_GETFPREGS: /* Get FPRs 0 - 31. */ - return copy_regset_to_user(child, &user_ppc_native_view, - REGSET_FPR, 0, 32 * sizeof(double), - datavp); - - case PPC_PTRACE_SETFPREGS: /* Set FPRs 0 - 31. */ - return copy_regset_from_user(child, &user_ppc_native_view, - REGSET_FPR, 0, 32 * sizeof(double), - datavp); - } - - return -EPERM; -} - long arch_ptrace(struct task_struct *child, long request, unsigned long addr, unsigned long data) { @@ -1687,14 +1653,6 @@ long arch_ptrace(struct task_struct *child, long request, datavp); #endif - /* Old reverse args ptrace callss */ - case PPC_PTRACE_GETREGS: /* Get GPRs 0 - 31. */ - case PPC_PTRACE_SETREGS: /* Set GPRs 0 - 31. */ - case PPC_PTRACE_GETFPREGS: /* Get FPRs 0 - 31. */ - case PPC_PTRACE_SETFPREGS: /* Get FPRs 0 - 31. */ - ret = arch_ptrace_old(child, request, addr, data); - break; - default: ret = ptrace_request(child, request, addr, data); break; diff --git a/arch/powerpc/kernel/ptrace32.c b/arch/powerpc/kernel/ptrace32.c index 469349d14a97..8c21658719d9 100644 --- a/arch/powerpc/kernel/ptrace32.c +++ b/arch/powerpc/kernel/ptrace32.c @@ -39,30 +39,6 @@ * in exit.c or in signal.c. */ -/* - * Here are the old "legacy" powerpc specific getregs/setregs ptrace calls, - * we mark them as obsolete now, they will be removed in a future version - */ -static long compat_ptrace_old(struct task_struct *child, long request, - long addr, long data) -{ - switch (request) { - case PPC_PTRACE_GETREGS: /* Get GPRs 0 - 31. */ - return copy_regset_to_user(child, - task_user_regset_view(current), 0, - 0, 32 * sizeof(compat_long_t), - compat_ptr(data)); - - case PPC_PTRACE_SETREGS: /* Set GPRs 0 - 31. */ - return copy_regset_from_user(child, - task_user_regset_view(current), 0, - 0, 32 * sizeof(compat_long_t), - compat_ptr(data)); - } - - return -EPERM; -} - /* Macros to workout the correct index for the FPR in the thread struct */ #define FPRNUMBER(i) (((i) - PT_FPR0) >> 1) #define FPRHALF(i) (((i) - PT_FPR0) & 1) @@ -308,8 +284,6 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, case PTRACE_SETVSRREGS: case PTRACE_GETREGS64: case PTRACE_SETREGS64: - case PPC_PTRACE_GETFPREGS: - case PPC_PTRACE_SETFPREGS: case PTRACE_KILL: case PTRACE_SINGLESTEP: case PTRACE_DETACH: @@ -322,12 +296,6 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, ret = arch_ptrace(child, request, addr, data); break; - /* Old reverse args ptrace callss */ - case PPC_PTRACE_GETREGS: /* Get GPRs 0 - 31. */ - case PPC_PTRACE_SETREGS: /* Set GPRs 0 - 31. */ - ret = compat_ptrace_old(child, request, addr, data); - break; - default: ret = compat_ptrace_request(child, request, addr, data); break; diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index 651c5963662b..5c023c9cf16e 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -51,16 +51,6 @@ void __user * get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, return (void __user *)newsp; } - -/* - * Restore the user process's signal mask - */ -void restore_sigmask(sigset_t *set) -{ - sigdelsetmask(set, ~_BLOCKABLE); - set_current_blocked(set); -} - static void check_syscall_restart(struct pt_regs *regs, struct k_sigaction *ka, int has_handler) { @@ -114,30 +104,21 @@ static void check_syscall_restart(struct pt_regs *regs, struct k_sigaction *ka, static int do_signal(struct pt_regs *regs) { - sigset_t *oldset; + sigset_t *oldset = sigmask_to_save(); siginfo_t info; int signr; struct k_sigaction ka; int ret; int is32 = is_32bit_task(); - if (current_thread_info()->local_flags & _TLF_RESTORE_SIGMASK) - oldset = ¤t->saved_sigmask; - else - oldset = ¤t->blocked; - signr = get_signal_to_deliver(&info, &ka, regs, NULL); /* Is there any syscall restart business here ? */ check_syscall_restart(regs, &ka, signr > 0); if (signr <= 0) { - struct thread_info *ti = current_thread_info(); /* No signal to deliver -- put the saved sigmask back */ - if (ti->local_flags & _TLF_RESTORE_SIGMASK) { - ti->local_flags &= ~_TLF_RESTORE_SIGMASK; - sigprocmask(SIG_SETMASK, ¤t->saved_sigmask, NULL); - } + restore_saved_sigmask(); regs->trap = 0; return 0; /* no signals delivered */ } @@ -167,18 +148,7 @@ static int do_signal(struct pt_regs *regs) regs->trap = 0; if (ret) { - block_sigmask(&ka, signr); - - /* - * A signal was successfully delivered; the saved sigmask is in - * its frame, and we can clear the TLF_RESTORE_SIGMASK flag. - */ - current_thread_info()->local_flags &= ~_TLF_RESTORE_SIGMASK; - - /* - * Let tracing know that we've done the handler setup. - */ - tracehook_signal_handler(signr, &info, &ka, regs, + signal_delivered(signr, &info, &ka, regs, test_thread_flag(TIF_SINGLESTEP)); } @@ -193,8 +163,6 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags) if (thread_info_flags & _TIF_NOTIFY_RESUME) { clear_thread_flag(TIF_NOTIFY_RESUME); tracehook_notify_resume(regs); - if (current->replacement_session_keyring) - key_replace_session_keyring(); } } diff --git a/arch/powerpc/kernel/signal.h b/arch/powerpc/kernel/signal.h index 8dde973aaaf5..e00acb413934 100644 --- a/arch/powerpc/kernel/signal.h +++ b/arch/powerpc/kernel/signal.h @@ -10,13 +10,10 @@ #ifndef _POWERPC_ARCH_SIGNAL_H #define _POWERPC_ARCH_SIGNAL_H -#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) - extern void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags); extern void __user * get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, int is_32); -extern void restore_sigmask(sigset_t *set); extern int handle_signal32(unsigned long sig, struct k_sigaction *ka, siginfo_t *info, sigset_t *oldset, diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 45eb998557f8..8b4c049aee20 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -204,10 +204,10 @@ static inline int get_old_sigaction(struct k_sigaction *new_ka, if (!access_ok(VERIFY_READ, act, sizeof(*act)) || __get_user(new_ka->sa.sa_handler, &act->sa_handler) || - __get_user(new_ka->sa.sa_restorer, &act->sa_restorer)) + __get_user(new_ka->sa.sa_restorer, &act->sa_restorer) || + __get_user(new_ka->sa.sa_flags, &act->sa_flags) || + __get_user(mask, &act->sa_mask)) return -EFAULT; - __get_user(new_ka->sa.sa_flags, &act->sa_flags); - __get_user(mask, &act->sa_mask); siginitset(&new_ka->sa.sa_mask, mask); return 0; } @@ -244,17 +244,8 @@ static inline int restore_general_regs(struct pt_regs *regs, long sys_sigsuspend(old_sigset_t mask) { sigset_t blocked; - - current->saved_sigmask = current->blocked; - - mask &= _BLOCKABLE; siginitset(&blocked, mask); - set_current_blocked(&blocked); - - current->state = TASK_INTERRUPTIBLE; - schedule(); - set_restore_sigmask(); - return -ERESTARTNOHAND; + return sigsuspend(&blocked); } long sys_sigaction(int sig, struct old_sigaction __user *act, @@ -928,7 +919,7 @@ static int do_setcontext(struct ucontext __user *ucp, struct pt_regs *regs, int if (!access_ok(VERIFY_READ, mcp, sizeof(*mcp))) return -EFAULT; #endif - restore_sigmask(&set); + set_current_blocked(&set); if (restore_user_regs(regs, mcp, sig)) return -EFAULT; @@ -1282,7 +1273,7 @@ long sys_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8, set.sig[0] = sigctx.oldmask; set.sig[1] = sigctx._unused[3]; #endif - restore_sigmask(&set); + set_current_blocked(&set); sr = (struct mcontext __user *)from_user_ptr(sigctx.regs); addr = sr; diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 2692efdb154e..d183f8719a50 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -335,7 +335,7 @@ int sys_swapcontext(struct ucontext __user *old_ctx, if (__copy_from_user(&set, &new_ctx->uc_sigmask, sizeof(set))) do_exit(SIGSEGV); - restore_sigmask(&set); + set_current_blocked(&set); if (restore_sigcontext(regs, NULL, 0, &new_ctx->uc_mcontext)) do_exit(SIGSEGV); @@ -364,7 +364,7 @@ int sys_rt_sigreturn(unsigned long r3, unsigned long r4, unsigned long r5, if (__copy_from_user(&set, &uc->uc_sigmask, sizeof(set))) goto badframe; - restore_sigmask(&set); + set_current_blocked(&set); if (restore_sigcontext(regs, NULL, 1, &uc->uc_mcontext)) goto badframe; diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index d9f94410fd7f..e4cb34322de4 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -57,27 +57,9 @@ #define DBG(fmt...) #endif - -/* Store all idle threads, this can be reused instead of creating -* a new thread. Also avoids complicated thread destroy functionality -* for idle threads. -*/ #ifdef CONFIG_HOTPLUG_CPU -/* - * Needed only for CONFIG_HOTPLUG_CPU because __cpuinitdata is - * removed after init for !CONFIG_HOTPLUG_CPU. - */ -static DEFINE_PER_CPU(struct task_struct *, idle_thread_array); -#define get_idle_for_cpu(x) (per_cpu(idle_thread_array, x)) -#define set_idle_for_cpu(x, p) (per_cpu(idle_thread_array, x) = (p)) - /* State of each CPU during hotplug phases */ static DEFINE_PER_CPU(int, cpu_state) = { 0 }; - -#else -static struct task_struct *idle_thread_array[NR_CPUS] __cpuinitdata ; -#define get_idle_for_cpu(x) (idle_thread_array[(x)]) -#define set_idle_for_cpu(x, p) (idle_thread_array[(x)] = (p)) #endif struct thread_info *secondary_ti; @@ -429,60 +411,19 @@ int generic_check_cpu_restart(unsigned int cpu) } #endif -struct create_idle { - struct work_struct work; - struct task_struct *idle; - struct completion done; - int cpu; -}; - -static void __cpuinit do_fork_idle(struct work_struct *work) +static void cpu_idle_thread_init(unsigned int cpu, struct task_struct *idle) { - struct create_idle *c_idle = - container_of(work, struct create_idle, work); - - c_idle->idle = fork_idle(c_idle->cpu); - complete(&c_idle->done); -} - -static int __cpuinit create_idle(unsigned int cpu) -{ - struct thread_info *ti; - struct create_idle c_idle = { - .cpu = cpu, - .done = COMPLETION_INITIALIZER_ONSTACK(c_idle.done), - }; - INIT_WORK_ONSTACK(&c_idle.work, do_fork_idle); - - c_idle.idle = get_idle_for_cpu(cpu); - - /* We can't use kernel_thread since we must avoid to - * reschedule the child. We use a workqueue because - * we want to fork from a kernel thread, not whatever - * userspace process happens to be trying to online us. - */ - if (!c_idle.idle) { - schedule_work(&c_idle.work); - wait_for_completion(&c_idle.done); - } else - init_idle(c_idle.idle, cpu); - if (IS_ERR(c_idle.idle)) { - pr_err("Failed fork for CPU %u: %li", cpu, PTR_ERR(c_idle.idle)); - return PTR_ERR(c_idle.idle); - } - ti = task_thread_info(c_idle.idle); + struct thread_info *ti = task_thread_info(idle); #ifdef CONFIG_PPC64 - paca[cpu].__current = c_idle.idle; + paca[cpu].__current = idle; paca[cpu].kstack = (unsigned long)ti + THREAD_SIZE - STACK_FRAME_OVERHEAD; #endif ti->cpu = cpu; - current_set[cpu] = ti; - - return 0; + secondary_ti = current_set[cpu] = ti; } -int __cpuinit __cpu_up(unsigned int cpu) +int __cpuinit __cpu_up(unsigned int cpu, struct task_struct *tidle) { int rc, c; @@ -490,12 +431,7 @@ int __cpuinit __cpu_up(unsigned int cpu) (smp_ops->cpu_bootable && !smp_ops->cpu_bootable(cpu))) return -EINVAL; - /* Make sure we have an idle thread */ - rc = create_idle(cpu); - if (rc) - return rc; - - secondary_ti = current_set[cpu]; + cpu_idle_thread_init(cpu, tidle); /* Make sure callin-map entry is 0 (can be leftover a CPU * hotplug diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 2c42cd72d0f5..be171ee73bf8 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -100,7 +100,7 @@ static int decrementer_set_next_event(unsigned long evt, static void decrementer_set_mode(enum clock_event_mode mode, struct clock_event_device *dev); -static struct clock_event_device decrementer_clockevent = { +struct clock_event_device decrementer_clockevent = { .name = "decrementer", .rating = 200, .irq = 0, @@ -108,6 +108,7 @@ static struct clock_event_device decrementer_clockevent = { .set_mode = decrementer_set_mode, .features = CLOCK_EVT_FEAT_ONESHOT, }; +EXPORT_SYMBOL(decrementer_clockevent); DEFINE_PER_CPU(u64, decrementers_next_tb); static DEFINE_PER_CPU(struct clock_event_device, decrementers); @@ -474,6 +475,7 @@ void timer_interrupt(struct pt_regs * regs) struct pt_regs *old_regs; u64 *next_tb = &__get_cpu_var(decrementers_next_tb); struct clock_event_device *evt = &__get_cpu_var(decrementers); + u64 now; /* Ensure a positive value is written to the decrementer, or else * some CPUs will continue to take decrementer exceptions. @@ -508,9 +510,16 @@ void timer_interrupt(struct pt_regs * regs) irq_work_run(); } - *next_tb = ~(u64)0; - if (evt->event_handler) - evt->event_handler(evt); + now = get_tb_or_rtc(); + if (now >= *next_tb) { + *next_tb = ~(u64)0; + if (evt->event_handler) + evt->event_handler(evt); + } else { + now = *next_tb - now; + if (now <= DECREMENTER_MAX) + set_dec((int)now); + } #ifdef CONFIG_PPC64 /* collect purr register values often, for accurate calculations */ diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 6aa0c663e247..158972341a2d 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -248,7 +248,7 @@ void _exception(int signr, struct pt_regs *regs, int code, unsigned long addr) addr, regs->nip, regs->link, code); } - if (!arch_irq_disabled_regs(regs)) + if (arch_irqs_disabled() && !arch_irq_disabled_regs(regs)) local_irq_enable(); memset(&info, 0, sizeof(info)); @@ -1019,7 +1019,9 @@ void __kprobes program_check_exception(struct pt_regs *regs) return; } - local_irq_enable(); + /* We restore the interrupt state now */ + if (!arch_irq_disabled_regs(regs)) + local_irq_enable(); #ifdef CONFIG_MATH_EMULATION /* (reason & REASON_ILLEGAL) would be the obvious thing here, @@ -1069,6 +1071,10 @@ void alignment_exception(struct pt_regs *regs) { int sig, code, fixed = 0; + /* We restore the interrupt state now */ + if (!arch_irq_disabled_regs(regs)) + local_irq_enable(); + /* we don't implement logging of alignment exceptions */ if (!(current->thread.align_ctl & PR_UNALIGN_SIGBUS)) fixed = fix_alignment(regs); diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S index 4d5a3edff49e..e830289d2e48 100644 --- a/arch/powerpc/kernel/vector.S +++ b/arch/powerpc/kernel/vector.S @@ -89,6 +89,16 @@ _GLOBAL(load_up_altivec) /* restore registers and return */ blr +_GLOBAL(giveup_altivec_notask) + mfmsr r3 + andis. r4,r3,MSR_VEC@h + bnelr /* Already enabled? */ + oris r3,r3,MSR_VEC@h + SYNC + MTMSRD(r3) /* enable use of VMX now */ + isync + blr + /* * giveup_altivec(tsk) * Disable VMX for the task given as the argument, diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c index a3a99901c8ec..cb87301ccd55 100644 --- a/arch/powerpc/kernel/vio.c +++ b/arch/powerpc/kernel/vio.c @@ -14,7 +14,9 @@ * 2 of the License, or (at your option) any later version. */ +#include <linux/cpu.h> #include <linux/types.h> +#include <linux/delay.h> #include <linux/stat.h> #include <linux/device.h> #include <linux/init.h> @@ -709,13 +711,26 @@ static int vio_cmo_bus_probe(struct vio_dev *viodev) struct vio_driver *viodrv = to_vio_driver(dev->driver); unsigned long flags; size_t size; + bool dma_capable = false; + + /* A device requires entitlement if it has a DMA window property */ + switch (viodev->family) { + case VDEVICE: + if (of_get_property(viodev->dev.of_node, + "ibm,my-dma-window", NULL)) + dma_capable = true; + break; + case PFO: + dma_capable = false; + break; + default: + dev_warn(dev, "unknown device family: %d\n", viodev->family); + BUG(); + break; + } - /* - * Check to see that device has a DMA window and configure - * entitlement for the device. - */ - if (of_get_property(viodev->dev.of_node, - "ibm,my-dma-window", NULL)) { + /* Configure entitlement for the device. */ + if (dma_capable) { /* Check that the driver is CMO enabled and get desired DMA */ if (!viodrv->get_desired_dma) { dev_err(dev, "%s: device driver does not support CMO\n", @@ -1050,6 +1065,94 @@ static void vio_cmo_sysfs_init(void) { } EXPORT_SYMBOL(vio_cmo_entitlement_update); EXPORT_SYMBOL(vio_cmo_set_dev_desired); + +/* + * Platform Facilities Option (PFO) support + */ + +/** + * vio_h_cop_sync - Perform a synchronous PFO co-processor operation + * + * @vdev - Pointer to a struct vio_dev for device + * @op - Pointer to a struct vio_pfo_op for the operation parameters + * + * Calls the hypervisor to synchronously perform the PFO operation + * described in @op. In the case of a busy response from the hypervisor, + * the operation will be re-submitted indefinitely unless a non-zero timeout + * is specified or an error occurs. The timeout places a limit on when to + * stop re-submitting a operation, the total time can be exceeded if an + * operation is in progress. + * + * If op->hcall_ret is not NULL, this will be set to the return from the + * last h_cop_op call or it will be 0 if an error not involving the h_call + * was encountered. + * + * Returns: + * 0 on success, + * -EINVAL if the h_call fails due to an invalid parameter, + * -E2BIG if the h_call can not be performed synchronously, + * -EBUSY if a timeout is specified and has elapsed, + * -EACCES if the memory area for data/status has been rescinded, or + * -EPERM if a hardware fault has been indicated + */ +int vio_h_cop_sync(struct vio_dev *vdev, struct vio_pfo_op *op) +{ + struct device *dev = &vdev->dev; + unsigned long deadline = 0; + long hret = 0; + int ret = 0; + + if (op->timeout) + deadline = jiffies + msecs_to_jiffies(op->timeout); + + while (true) { + hret = plpar_hcall_norets(H_COP, op->flags, + vdev->resource_id, + op->in, op->inlen, op->out, + op->outlen, op->csbcpb); + + if (hret == H_SUCCESS || + (hret != H_NOT_ENOUGH_RESOURCES && + hret != H_BUSY && hret != H_RESOURCE) || + (op->timeout && time_after(deadline, jiffies))) + break; + + dev_dbg(dev, "%s: hcall ret(%ld), retrying.\n", __func__, hret); + } + + switch (hret) { + case H_SUCCESS: + ret = 0; + break; + case H_OP_MODE: + case H_TOO_BIG: + ret = -E2BIG; + break; + case H_RESCINDED: + ret = -EACCES; + break; + case H_HARDWARE: + ret = -EPERM; + break; + case H_NOT_ENOUGH_RESOURCES: + case H_RESOURCE: + case H_BUSY: + ret = -EBUSY; + break; + default: + ret = -EINVAL; + break; + } + + if (ret) + dev_dbg(dev, "%s: Sync h_cop_op failure (ret:%d) (hret:%ld)\n", + __func__, ret, hret); + + op->hcall_err = hret; + return ret; +} +EXPORT_SYMBOL(vio_h_cop_sync); + static struct iommu_table *vio_build_iommu_table(struct vio_dev *dev) { const unsigned char *dma_window; @@ -1211,35 +1314,87 @@ static void __devinit vio_dev_release(struct device *dev) struct vio_dev *vio_register_device_node(struct device_node *of_node) { struct vio_dev *viodev; + struct device_node *parent_node; const unsigned int *unit_address; + const unsigned int *pfo_resid = NULL; + enum vio_dev_family family; + const char *of_node_name = of_node->name ? of_node->name : "<unknown>"; - /* we need the 'device_type' property, in order to match with drivers */ - if (of_node->type == NULL) { - printk(KERN_WARNING "%s: node %s missing 'device_type'\n", - __func__, - of_node->name ? of_node->name : "<unknown>"); + /* + * Determine if this node is a under the /vdevice node or under the + * /ibm,platform-facilities node. This decides the device's family. + */ + parent_node = of_get_parent(of_node); + if (parent_node) { + if (!strcmp(parent_node->full_name, "/ibm,platform-facilities")) + family = PFO; + else if (!strcmp(parent_node->full_name, "/vdevice")) + family = VDEVICE; + else { + pr_warn("%s: parent(%s) of %s not recognized.\n", + __func__, + parent_node->full_name, + of_node_name); + of_node_put(parent_node); + return NULL; + } + of_node_put(parent_node); + } else { + pr_warn("%s: could not determine the parent of node %s.\n", + __func__, of_node_name); return NULL; } - unit_address = of_get_property(of_node, "reg", NULL); - if (unit_address == NULL) { - printk(KERN_WARNING "%s: node %s missing 'reg'\n", - __func__, - of_node->name ? of_node->name : "<unknown>"); - return NULL; + if (family == PFO) { + if (of_get_property(of_node, "interrupt-controller", NULL)) { + pr_debug("%s: Skipping the interrupt controller %s.\n", + __func__, of_node_name); + return NULL; + } } /* allocate a vio_dev for this node */ viodev = kzalloc(sizeof(struct vio_dev), GFP_KERNEL); - if (viodev == NULL) + if (viodev == NULL) { + pr_warn("%s: allocation failure for VIO device.\n", __func__); return NULL; + } - viodev->irq = irq_of_parse_and_map(of_node, 0); + /* we need the 'device_type' property, in order to match with drivers */ + viodev->family = family; + if (viodev->family == VDEVICE) { + if (of_node->type != NULL) + viodev->type = of_node->type; + else { + pr_warn("%s: node %s is missing the 'device_type' " + "property.\n", __func__, of_node_name); + goto out; + } + + unit_address = of_get_property(of_node, "reg", NULL); + if (unit_address == NULL) { + pr_warn("%s: node %s missing 'reg'\n", + __func__, of_node_name); + goto out; + } + dev_set_name(&viodev->dev, "%x", *unit_address); + viodev->irq = irq_of_parse_and_map(of_node, 0); + viodev->unit_address = *unit_address; + } else { + /* PFO devices need their resource_id for submitting COP_OPs + * This is an optional field for devices, but is required when + * performing synchronous ops */ + pfo_resid = of_get_property(of_node, "ibm,resource-id", NULL); + if (pfo_resid != NULL) + viodev->resource_id = *pfo_resid; + + unit_address = NULL; + dev_set_name(&viodev->dev, "%s", of_node_name); + viodev->type = of_node_name; + viodev->irq = 0; + } - dev_set_name(&viodev->dev, "%x", *unit_address); viodev->name = of_node->name; - viodev->type = of_node->type; - viodev->unit_address = *unit_address; viodev->dev.of_node = of_node_get(of_node); if (firmware_has_feature(FW_FEATURE_CMO)) @@ -1267,16 +1422,51 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node) } return viodev; + +out: /* Use this exit point for any return prior to device_register */ + kfree(viodev); + + return NULL; } EXPORT_SYMBOL(vio_register_device_node); +/* + * vio_bus_scan_for_devices - Scan OF and register each child device + * @root_name - OF node name for the root of the subtree to search. + * This must be non-NULL + * + * Starting from the root node provide, register the device node for + * each child beneath the root. + */ +static void vio_bus_scan_register_devices(char *root_name) +{ + struct device_node *node_root, *node_child; + + if (!root_name) + return; + + node_root = of_find_node_by_name(NULL, root_name); + if (node_root) { + + /* + * Create struct vio_devices for each virtual device in + * the device tree. Drivers will associate with them later. + */ + node_child = of_get_next_child(node_root, NULL); + while (node_child) { + vio_register_device_node(node_child); + node_child = of_get_next_child(node_root, node_child); + } + of_node_put(node_root); + } +} + /** * vio_bus_init: - Initialize the virtual IO bus */ static int __init vio_bus_init(void) { int err; - struct device_node *node_vroot; if (firmware_has_feature(FW_FEATURE_CMO)) vio_cmo_sysfs_init(); @@ -1301,19 +1491,8 @@ static int __init vio_bus_init(void) if (firmware_has_feature(FW_FEATURE_CMO)) vio_cmo_bus_init(); - node_vroot = of_find_node_by_name(NULL, "vdevice"); - if (node_vroot) { - struct device_node *of_node; - - /* - * Create struct vio_devices for each virtual device in - * the device tree. Drivers will associate with them later. - */ - for (of_node = node_vroot->child; of_node != NULL; - of_node = of_node->sibling) - vio_register_device_node(of_node); - of_node_put(node_vroot); - } + vio_bus_scan_register_devices("vdevice"); + vio_bus_scan_register_devices("ibm,platform-facilities"); return 0; } @@ -1436,12 +1615,28 @@ struct vio_dev *vio_find_node(struct device_node *vnode) { const uint32_t *unit_address; char kobj_name[20]; + struct device_node *vnode_parent; + const char *dev_type; + + vnode_parent = of_get_parent(vnode); + if (!vnode_parent) + return NULL; + + dev_type = of_get_property(vnode_parent, "device_type", NULL); + of_node_put(vnode_parent); + if (!dev_type) + return NULL; /* construct the kobject name from the device node */ - unit_address = of_get_property(vnode, "reg", NULL); - if (!unit_address) + if (!strcmp(dev_type, "vdevice")) { + unit_address = of_get_property(vnode, "reg", NULL); + if (!unit_address) + return NULL; + snprintf(kobj_name, sizeof(kobj_name), "%x", *unit_address); + } else if (!strcmp(dev_type, "ibm,platform-facilities")) + snprintf(kobj_name, sizeof(kobj_name), "%s", vnode->name); + else return NULL; - snprintf(kobj_name, sizeof(kobj_name), "%x", *unit_address); return vio_find_name(kobj_name); } |