diff options
| author | André Fabian Silva Delgado <emulatorman@parabola.nu> | 2016-10-20 00:10:27 -0300 |
|---|---|---|
| committer | André Fabian Silva Delgado <emulatorman@parabola.nu> | 2016-10-20 00:10:27 -0300 |
| commit | d0b2f91bede3bd5e3d24dd6803e56eee959c1797 (patch) | |
| tree | 7fee4ab0509879c373c4f2cbd5b8a5be5b4041ee /arch/powerpc/kernel | |
| parent | e914f8eb445e8f74b00303c19c2ffceaedd16a05 (diff) | |
Linux-libre 4.8.2-gnupck-4.8.2-gnu
Diffstat (limited to 'arch/powerpc/kernel')
60 files changed, 3461 insertions, 868 deletions
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 2da380fcc..fe4c075bc 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -42,12 +42,11 @@ obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_ppc970.o cpu_setup_pa6t.o obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_power.o obj-$(CONFIG_PPC_BOOK3S_64) += mce.o mce_power.o -obj64-$(CONFIG_RELOCATABLE) += reloc_64.o obj-$(CONFIG_PPC_BOOK3E_64) += exceptions-64e.o idle_book3e.o obj-$(CONFIG_PPC64) += vdso64/ obj-$(CONFIG_ALTIVEC) += vecemu.o obj-$(CONFIG_PPC_970_NAP) += idle_power4.o -obj-$(CONFIG_PPC_P7_NAP) += idle_power7.o +obj-$(CONFIG_PPC_P7_NAP) += idle_book3s.o procfs-y := proc_powerpc.o obj-$(CONFIG_PROC_FS) += $(procfs-y) rtaspci-$(CONFIG_PPC64)-$(CONFIG_PCI) := rtas_pci.o @@ -87,7 +86,7 @@ extra-$(CONFIG_FSL_BOOKE) := head_fsl_booke.o extra-$(CONFIG_8xx) := head_8xx.o extra-y += vmlinux.lds -obj-$(CONFIG_RELOCATABLE_PPC32) += reloc_32.o +obj-$(CONFIG_RELOCATABLE) += reloc_$(CONFIG_WORD_SIZE).o obj-$(CONFIG_PPC32) += entry_32.o setup_32.o obj-$(CONFIG_PPC64) += dma-iommu.o iommu.o diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c index 8e7cb8e2b..033f3385f 100644 --- a/arch/powerpc/kernel/align.c +++ b/arch/powerpc/kernel/align.c @@ -26,6 +26,7 @@ #include <asm/emulated_ops.h> #include <asm/switch_to.h> #include <asm/disassemble.h> +#include <asm/cpu_has_feature.h> struct aligninfo { unsigned char len; @@ -228,9 +229,7 @@ static int emulate_dcbz(struct pt_regs *regs, unsigned char __user *addr) #else #define REG_BYTE(rp, i) *((u8 *)(rp) + (i)) #endif -#endif - -#ifdef __LITTLE_ENDIAN__ +#else #define REG_BYTE(rp, i) (*(((u8 *)((rp) + ((i)>>2)) + ((i)&3)))) #endif @@ -875,6 +874,20 @@ int fix_alignment(struct pt_regs *regs) return emulate_vsx(addr, reg, areg, regs, flags, nb, elsize); } #endif + + /* + * ISA 3.0 (such as P9) copy, copy_first, paste and paste_last alignment + * check. + * + * Send a SIGBUS to the process that caused the fault. + * + * We do not emulate these because paste may contain additional metadata + * when pasting to a co-processor. Furthermore, paste_last is the + * synchronisation point for preceding copy/paste sequences. + */ + if ((instruction & 0xfc0006fe) == PPC_INST_COPY) + return -EIO; + /* A size of 0 indicates an instruction we don't support, with * the exception of DCBZ which is handled as a special case here */ diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 9ea09551a..b89d14c03 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -68,17 +68,18 @@ #include "../mm/mmu_decl.h" #endif +#ifdef CONFIG_PPC_8xx +#include <asm/fixmap.h> +#endif + int main(void) { DEFINE(THREAD, offsetof(struct task_struct, thread)); DEFINE(MM, offsetof(struct task_struct, mm)); DEFINE(MMCONTEXTID, offsetof(struct mm_struct, context.id)); #ifdef CONFIG_PPC64 - DEFINE(AUDITCONTEXT, offsetof(struct task_struct, audit_context)); DEFINE(SIGSEGV, SIGSEGV); DEFINE(NMI_MASK, NMI_MASK); - DEFINE(THREAD_DSCR, offsetof(struct thread_struct, dscr)); - DEFINE(THREAD_DSCR_INHERIT, offsetof(struct thread_struct, dscr_inherit)); DEFINE(TASKTHREADPPR, offsetof(struct task_struct, thread.ppr)); #else DEFINE(THREAD_INFO, offsetof(struct task_struct, stack)); @@ -132,17 +133,6 @@ int main(void) DEFINE(THREAD_KVM_VCPU, offsetof(struct thread_struct, kvm_vcpu)); #endif -#ifdef CONFIG_PPC_BOOK3S_64 - DEFINE(THREAD_TAR, offsetof(struct thread_struct, tar)); - DEFINE(THREAD_BESCR, offsetof(struct thread_struct, bescr)); - DEFINE(THREAD_EBBHR, offsetof(struct thread_struct, ebbhr)); - DEFINE(THREAD_EBBRR, offsetof(struct thread_struct, ebbrr)); - DEFINE(THREAD_SIAR, offsetof(struct thread_struct, siar)); - DEFINE(THREAD_SDAR, offsetof(struct thread_struct, sdar)); - DEFINE(THREAD_SIER, offsetof(struct thread_struct, sier)); - DEFINE(THREAD_MMCR0, offsetof(struct thread_struct, mmcr0)); - DEFINE(THREAD_MMCR2, offsetof(struct thread_struct, mmcr2)); -#endif #ifdef CONFIG_PPC_TRANSACTIONAL_MEM DEFINE(PACATMSCRATCH, offsetof(struct paca_struct, tm_scratch)); DEFINE(THREAD_TM_TFHAR, offsetof(struct thread_struct, tm_tfhar)); @@ -178,7 +168,6 @@ 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)); @@ -255,13 +244,28 @@ int main(void) DEFINE(PACAHWCPUID, offsetof(struct paca_struct, hw_cpu_id)); DEFINE(PACAKEXECSTATE, offsetof(struct paca_struct, kexec_state)); DEFINE(PACA_DSCR_DEFAULT, offsetof(struct paca_struct, dscr_default)); - DEFINE(PACA_STARTTIME, offsetof(struct paca_struct, starttime)); - DEFINE(PACA_STARTTIME_USER, offsetof(struct paca_struct, starttime_user)); - DEFINE(PACA_USER_TIME, offsetof(struct paca_struct, user_time)); - DEFINE(PACA_SYSTEM_TIME, offsetof(struct paca_struct, system_time)); + DEFINE(ACCOUNT_STARTTIME, + offsetof(struct paca_struct, accounting.starttime)); + DEFINE(ACCOUNT_STARTTIME_USER, + offsetof(struct paca_struct, accounting.starttime_user)); + DEFINE(ACCOUNT_USER_TIME, + offsetof(struct paca_struct, accounting.user_time)); + DEFINE(ACCOUNT_SYSTEM_TIME, + offsetof(struct paca_struct, accounting.system_time)); DEFINE(PACA_TRAP_SAVE, offsetof(struct paca_struct, trap_save)); DEFINE(PACA_NAPSTATELOST, offsetof(struct paca_struct, nap_state_lost)); DEFINE(PACA_SPRG_VDSO, offsetof(struct paca_struct, sprg_vdso)); +#else /* CONFIG_PPC64 */ +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE + DEFINE(ACCOUNT_STARTTIME, + offsetof(struct thread_info, accounting.starttime)); + DEFINE(ACCOUNT_STARTTIME_USER, + offsetof(struct thread_info, accounting.starttime_user)); + DEFINE(ACCOUNT_USER_TIME, + offsetof(struct thread_info, accounting.user_time)); + DEFINE(ACCOUNT_SYSTEM_TIME, + offsetof(struct thread_info, accounting.system_time)); +#endif #endif /* CONFIG_PPC64 */ /* RTAS */ @@ -275,12 +279,6 @@ int main(void) /* Create extra stack space for SRR0 and SRR1 when calling prom/rtas. */ DEFINE(PROM_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs) + 16); DEFINE(RTAS_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs) + 16); - - /* hcall statistics */ - DEFINE(HCALL_STAT_SIZE, sizeof(struct hcall_stats)); - DEFINE(HCALL_STAT_CALLS, offsetof(struct hcall_stats, num_calls)); - DEFINE(HCALL_STAT_TB, offsetof(struct hcall_stats, tb_total)); - DEFINE(HCALL_STAT_PURR, offsetof(struct hcall_stats, purr_total)); #endif /* CONFIG_PPC64 */ DEFINE(GPR0, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[0])); DEFINE(GPR1, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[1])); @@ -298,23 +296,6 @@ int main(void) DEFINE(GPR13, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[13])); #ifndef CONFIG_PPC64 DEFINE(GPR14, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[14])); - DEFINE(GPR15, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[15])); - DEFINE(GPR16, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[16])); - DEFINE(GPR17, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[17])); - DEFINE(GPR18, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[18])); - DEFINE(GPR19, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[19])); - DEFINE(GPR20, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[20])); - DEFINE(GPR21, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[21])); - DEFINE(GPR22, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[22])); - DEFINE(GPR23, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[23])); - DEFINE(GPR24, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[24])); - DEFINE(GPR25, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[25])); - DEFINE(GPR26, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[26])); - DEFINE(GPR27, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[27])); - DEFINE(GPR28, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[28])); - DEFINE(GPR29, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[29])); - DEFINE(GPR30, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[30])); - DEFINE(GPR31, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[31])); #endif /* CONFIG_PPC64 */ /* * Note: these symbols include _ because they overlap with special @@ -332,7 +313,6 @@ int main(void) DEFINE(RESULT, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, result)); DEFINE(_TRAP, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, trap)); #ifndef CONFIG_PPC64 - DEFINE(_MQ, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, mq)); /* * The PowerPC 400-class & Book-E processors have neither the DAR * nor the DSISR SPRs. Hence, we overload them to hold the similar @@ -369,8 +349,6 @@ int main(void) DEFINE(SAVED_KSP_LIMIT, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, saved_ksp_limit)); #endif #endif - DEFINE(CLONE_VM, CLONE_VM); - DEFINE(CLONE_UNTRACED, CLONE_UNTRACED); #ifndef CONFIG_PPC64 DEFINE(MM_PGD, offsetof(struct mm_struct, pgd)); @@ -380,7 +358,6 @@ int main(void) DEFINE(CPU_SPEC_FEATURES, offsetof(struct cpu_spec, cpu_features)); DEFINE(CPU_SPEC_SETUP, offsetof(struct cpu_spec, cpu_setup)); DEFINE(CPU_SPEC_RESTORE, offsetof(struct cpu_spec, cpu_restore)); - DEFINE(CPU_DOWN_FLUSH, offsetof(struct cpu_spec, cpu_down_flush)); DEFINE(pbe_address, offsetof(struct pbe, address)); DEFINE(pbe_orig_address, offsetof(struct pbe, orig_address)); @@ -395,7 +372,6 @@ int main(void) DEFINE(CFG_TB_ORIG_STAMP, offsetof(struct vdso_data, tb_orig_stamp)); DEFINE(CFG_TB_TICKS_PER_SEC, offsetof(struct vdso_data, tb_ticks_per_sec)); DEFINE(CFG_TB_TO_XS, offsetof(struct vdso_data, tb_to_xs)); - DEFINE(CFG_STAMP_XSEC, offsetof(struct vdso_data, stamp_xsec)); DEFINE(CFG_TB_UPDATE_COUNT, offsetof(struct vdso_data, tb_update_count)); DEFINE(CFG_TZ_MINUTEWEST, offsetof(struct vdso_data, tz_minuteswest)); DEFINE(CFG_TZ_DSTTIME, offsetof(struct vdso_data, tz_dsttime)); @@ -517,7 +493,6 @@ int main(void) DEFINE(KVM_HOST_SDR1, offsetof(struct kvm, arch.host_sdr1)); DEFINE(KVM_NEED_FLUSH, offsetof(struct kvm, arch.need_tlb_flush.bits)); DEFINE(KVM_ENABLED_HCALLS, offsetof(struct kvm, arch.enabled_hcalls)); - DEFINE(KVM_LPCR, offsetof(struct kvm, arch.lpcr)); 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)); @@ -528,7 +503,6 @@ int main(void) DEFINE(VCPU_THREAD_CPU, offsetof(struct kvm_vcpu, arch.thread_cpu)); #endif #ifdef CONFIG_PPC_BOOK3S - 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)); DEFINE(VCPU_IC, offsetof(struct kvm_vcpu, arch.ic)); @@ -566,7 +540,6 @@ int main(void) DEFINE(VCPU_CFAR, offsetof(struct kvm_vcpu, arch.cfar)); DEFINE(VCPU_PPR, offsetof(struct kvm_vcpu, arch.ppr)); DEFINE(VCPU_FSCR, offsetof(struct kvm_vcpu, arch.fscr)); - DEFINE(VCPU_SHADOW_FSCR, offsetof(struct kvm_vcpu, arch.shadow_fscr)); DEFINE(VCPU_PSPB, offsetof(struct kvm_vcpu, arch.pspb)); DEFINE(VCPU_EBBHR, offsetof(struct kvm_vcpu, arch.ebbhr)); DEFINE(VCPU_EBBRR, offsetof(struct kvm_vcpu, arch.ebbrr)); @@ -576,7 +549,6 @@ int main(void) DEFINE(VCPU_TCSCR, offsetof(struct kvm_vcpu, arch.tcscr)); DEFINE(VCPU_ACOP, offsetof(struct kvm_vcpu, arch.acop)); DEFINE(VCPU_WORT, offsetof(struct kvm_vcpu, arch.wort)); - DEFINE(VCPU_SHADOW_SRR1, offsetof(struct kvm_vcpu, arch.shadow_srr1)); DEFINE(VCORE_ENTRY_EXIT, offsetof(struct kvmppc_vcore, entry_exit_map)); DEFINE(VCORE_IN_GUEST, offsetof(struct kvmppc_vcore, in_guest)); DEFINE(VCORE_NAPPING_THREADS, offsetof(struct kvmppc_vcore, napping_threads)); @@ -693,7 +665,6 @@ int main(void) DEFINE(KVM_SPLIT_RPR, offsetof(struct kvm_split_mode, rpr)); DEFINE(KVM_SPLIT_PMMAR, offsetof(struct kvm_split_mode, pmmar)); DEFINE(KVM_SPLIT_LDBAR, offsetof(struct kvm_split_mode, ldbar)); - DEFINE(KVM_SPLIT_SIZE, offsetof(struct kvm_split_mode, subcore_size)); DEFINE(KVM_SPLIT_DO_NAP, offsetof(struct kvm_split_mode, do_nap)); DEFINE(KVM_SPLIT_NAPPED, offsetof(struct kvm_split_mode, napped)); #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */ @@ -756,7 +727,6 @@ int main(void) #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 @@ -783,5 +753,9 @@ int main(void) DEFINE(PPC_DBELL_SERVER, PPC_DBELL_SERVER); +#ifdef CONFIG_PPC_8xx + DEFINE(VIRT_IMMR_BASE, (u64)__fix_to_virt(FIX_IMMR_BASE)); +#endif + return 0; } diff --git a/arch/powerpc/kernel/cpu_setup_6xx.S b/arch/powerpc/kernel/cpu_setup_6xx.S index f8cd9fba4..c5e5a94d9 100644 --- a/arch/powerpc/kernel/cpu_setup_6xx.S +++ b/arch/powerpc/kernel/cpu_setup_6xx.S @@ -156,7 +156,7 @@ setup_7410_workarounds: blr /* 740/750/7400/7410 - * Enable Store Gathering (SGE), Address Brodcast (ABE), + * Enable Store Gathering (SGE), Address Broadcast (ABE), * Branch History Table (BHTE), Branch Target ICache (BTIC) * Dynamic Power Management (DPM), Speculative (SPD) * Clear Instruction cache throttling (ICTC) diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S index 584e119fa..52ff3f025 100644 --- a/arch/powerpc/kernel/cpu_setup_power.S +++ b/arch/powerpc/kernel/cpu_setup_power.S @@ -51,6 +51,7 @@ _GLOBAL(__setup_cpu_power8) mflr r11 bl __init_FSCR bl __init_PMU + bl __init_PMU_ISA207 bl __init_hvmode_206 mtlr r11 beqlr @@ -62,6 +63,7 @@ _GLOBAL(__setup_cpu_power8) bl __init_HFSCR bl __init_tlb_power8 bl __init_PMU_HV + bl __init_PMU_HV_ISA207 mtlr r11 blr @@ -69,6 +71,7 @@ _GLOBAL(__restore_cpu_power8) mflr r11 bl __init_FSCR bl __init_PMU + bl __init_PMU_ISA207 mfmsr r3 rldicl. r0,r3,4,63 mtlr r11 @@ -81,12 +84,14 @@ _GLOBAL(__restore_cpu_power8) bl __init_HFSCR bl __init_tlb_power8 bl __init_PMU_HV + bl __init_PMU_HV_ISA207 mtlr r11 blr _GLOBAL(__setup_cpu_power9) mflr r11 bl __init_FSCR + bl __init_PMU bl __init_hvmode_206 mtlr r11 beqlr @@ -94,15 +99,18 @@ _GLOBAL(__setup_cpu_power9) mtspr SPRN_LPID,r0 mfspr r3,SPRN_LPCR ori r3, r3, LPCR_PECEDH + ori r3, r3, LPCR_HVICE bl __init_LPCR bl __init_HFSCR bl __init_tlb_power9 + bl __init_PMU_HV mtlr r11 blr _GLOBAL(__restore_cpu_power9) mflr r11 bl __init_FSCR + bl __init_PMU mfmsr r3 rldicl. r0,r3,4,63 mtlr r11 @@ -111,9 +119,11 @@ _GLOBAL(__restore_cpu_power9) mtspr SPRN_LPID,r0 mfspr r3,SPRN_LPCR ori r3, r3, LPCR_PECEDH + ori r3, r3, LPCR_HVICE bl __init_LPCR bl __init_HFSCR bl __init_tlb_power9 + bl __init_PMU_HV mtlr r11 blr @@ -208,14 +218,22 @@ __init_tlb_power9: __init_PMU_HV: li r5,0 mtspr SPRN_MMCRC,r5 + blr + +__init_PMU_HV_ISA207: + li r5,0 mtspr SPRN_MMCRH,r5 blr __init_PMU: li r5,0 - mtspr SPRN_MMCRS,r5 mtspr SPRN_MMCRA,r5 mtspr SPRN_MMCR0,r5 mtspr SPRN_MMCR1,r5 mtspr SPRN_MMCR2,r5 blr + +__init_PMU_ISA207: + li r5,0 + mtspr SPRN_MMCRS,r5 + blr diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index eeeacf623..74248ab18 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -15,6 +15,7 @@ #include <linux/threads.h> #include <linux/init.h> #include <linux/export.h> +#include <linux/jump_label.h> #include <asm/oprofile_impl.h> #include <asm/cputable.h> @@ -137,7 +138,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "POWER4 (gp)", .cpu_features = CPU_FTRS_POWER4, .cpu_user_features = COMMON_USER_POWER4, - .mmu_features = MMU_FTRS_POWER4, + .mmu_features = MMU_FTRS_POWER4 | MMU_FTR_TLBIE_CROP_VA, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, @@ -152,7 +153,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "POWER4+ (gq)", .cpu_features = CPU_FTRS_POWER4, .cpu_user_features = COMMON_USER_POWER4, - .mmu_features = MMU_FTRS_POWER4, + .mmu_features = MMU_FTRS_POWER4 | MMU_FTR_TLBIE_CROP_VA, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, @@ -2224,3 +2225,39 @@ struct cpu_spec * __init identify_cpu(unsigned long offset, unsigned int pvr) return NULL; } + +#ifdef CONFIG_JUMP_LABEL_FEATURE_CHECKS +struct static_key_true cpu_feature_keys[NUM_CPU_FTR_KEYS] = { + [0 ... NUM_CPU_FTR_KEYS - 1] = STATIC_KEY_TRUE_INIT +}; +EXPORT_SYMBOL_GPL(cpu_feature_keys); + +void __init cpu_feature_keys_init(void) +{ + int i; + + for (i = 0; i < NUM_CPU_FTR_KEYS; i++) { + unsigned long f = 1ul << i; + + if (!(cur_cpu_spec->cpu_features & f)) + static_branch_disable(&cpu_feature_keys[i]); + } +} + +struct static_key_true mmu_feature_keys[NUM_MMU_FTR_KEYS] = { + [0 ... NUM_MMU_FTR_KEYS - 1] = STATIC_KEY_TRUE_INIT +}; +EXPORT_SYMBOL_GPL(mmu_feature_keys); + +void __init mmu_feature_keys_init(void) +{ + int i; + + for (i = 0; i < NUM_MMU_FTR_KEYS; i++) { + unsigned long f = 1ul << i; + + if (!(cur_cpu_spec->mmu_features & f)) + static_branch_disable(&mmu_feature_keys[i]); + } +} +#endif diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c index 2bb252c01..47b63de81 100644 --- a/arch/powerpc/kernel/crash.c +++ b/arch/powerpc/kernel/crash.c @@ -48,8 +48,8 @@ int crashing_cpu = -1; static int time_to_dump; #define CRASH_HANDLER_MAX 3 -/* NULL terminated list of shutdown handles */ -static crash_shutdown_t crash_shutdown_handles[CRASH_HANDLER_MAX+1]; +/* List of shutdown handles */ +static crash_shutdown_t crash_shutdown_handles[CRASH_HANDLER_MAX]; static DEFINE_SPINLOCK(crash_handlers_lock); static unsigned long crash_shutdown_buf[JMP_BUF_LEN]; @@ -65,7 +65,7 @@ static int handle_fault(struct pt_regs *regs) #ifdef CONFIG_SMP static atomic_t cpus_in_crash; -void crash_ipi_callback(struct pt_regs *regs) +static void crash_ipi_callback(struct pt_regs *regs) { static cpumask_t cpus_state_saved = CPU_MASK_NONE; @@ -288,9 +288,14 @@ int crash_shutdown_unregister(crash_shutdown_t handler) rc = 1; } else { /* Shift handles down */ - for (; crash_shutdown_handles[i]; i++) + for (; i < (CRASH_HANDLER_MAX - 1); i++) crash_shutdown_handles[i] = crash_shutdown_handles[i+1]; + /* + * Reset last entry to NULL now that it has been shifted down, + * this will allow new handles to be added here. + */ + crash_shutdown_handles[i] = NULL; rc = 0; } @@ -346,7 +351,7 @@ void default_machine_crash_shutdown(struct pt_regs *regs) old_handler = __debugger_fault_handler; __debugger_fault_handler = handle_fault; crash_shutdown_cpu = smp_processor_id(); - for (i = 0; crash_shutdown_handles[i]; i++) { + for (i = 0; i < CRASH_HANDLER_MAX && crash_shutdown_handles[i]; i++) { if (setjmp(crash_shutdown_buf) == 0) { /* * Insert syncs and delay to ensure diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c index 41a7d9d49..fb7cbaa37 100644 --- a/arch/powerpc/kernel/dma-iommu.c +++ b/arch/powerpc/kernel/dma-iommu.c @@ -18,7 +18,7 @@ */ static void *dma_iommu_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag, - struct dma_attrs *attrs) + unsigned long attrs) { return iommu_alloc_coherent(dev, get_iommu_table_base(dev), size, dma_handle, dev->coherent_dma_mask, flag, @@ -27,7 +27,7 @@ static void *dma_iommu_alloc_coherent(struct device *dev, size_t size, static void dma_iommu_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle, - struct dma_attrs *attrs) + unsigned long attrs) { iommu_free_coherent(get_iommu_table_base(dev), size, vaddr, dma_handle); } @@ -40,7 +40,7 @@ static void dma_iommu_free_coherent(struct device *dev, size_t size, static dma_addr_t dma_iommu_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { return iommu_map_page(dev, get_iommu_table_base(dev), page, offset, size, device_to_mask(dev), direction, attrs); @@ -49,7 +49,7 @@ static dma_addr_t dma_iommu_map_page(struct device *dev, struct page *page, static void dma_iommu_unmap_page(struct device *dev, dma_addr_t dma_handle, size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { iommu_unmap_page(get_iommu_table_base(dev), dma_handle, size, direction, attrs); @@ -58,7 +58,7 @@ static void dma_iommu_unmap_page(struct device *dev, dma_addr_t dma_handle, static int dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist, int nelems, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { return ppc_iommu_map_sg(dev, get_iommu_table_base(dev), sglist, nelems, device_to_mask(dev), direction, attrs); @@ -66,7 +66,7 @@ static int dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist, static void dma_iommu_unmap_sg(struct device *dev, struct scatterlist *sglist, int nelems, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { ppc_iommu_unmap_sg(get_iommu_table_base(dev), sglist, nelems, direction, attrs); diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c index 3f1472a78..e64a6016f 100644 --- a/arch/powerpc/kernel/dma.c +++ b/arch/powerpc/kernel/dma.c @@ -64,7 +64,7 @@ static int dma_direct_dma_supported(struct device *dev, u64 mask) void *__dma_direct_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag, - struct dma_attrs *attrs) + unsigned long attrs) { void *ret; #ifdef CONFIG_NOT_COHERENT_CACHE @@ -121,7 +121,7 @@ void *__dma_direct_alloc_coherent(struct device *dev, size_t size, void __dma_direct_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle, - struct dma_attrs *attrs) + unsigned long attrs) { #ifdef CONFIG_NOT_COHERENT_CACHE __dma_free_coherent(size, vaddr); @@ -132,7 +132,7 @@ void __dma_direct_free_coherent(struct device *dev, size_t size, static void *dma_direct_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag, - struct dma_attrs *attrs) + unsigned long attrs) { struct iommu_table *iommu; @@ -156,7 +156,7 @@ static void *dma_direct_alloc_coherent(struct device *dev, size_t size, static void dma_direct_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle, - struct dma_attrs *attrs) + unsigned long attrs) { struct iommu_table *iommu; @@ -177,7 +177,7 @@ static void dma_direct_free_coherent(struct device *dev, size_t size, int dma_direct_mmap_coherent(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t handle, size_t size, - struct dma_attrs *attrs) + unsigned long attrs) { unsigned long pfn; @@ -195,7 +195,7 @@ int dma_direct_mmap_coherent(struct device *dev, struct vm_area_struct *vma, static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { struct scatterlist *sg; int i; @@ -211,7 +211,7 @@ static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, static void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { } @@ -232,7 +232,7 @@ static inline dma_addr_t dma_direct_map_page(struct device *dev, unsigned long offset, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { BUG_ON(dir == DMA_NONE); __dma_sync_page(page, offset, size, dir); @@ -243,7 +243,7 @@ static inline void dma_direct_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { } diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index c9bc78e9c..7429556eb 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -168,10 +168,10 @@ static size_t eeh_dump_dev_log(struct eeh_dev *edev, char *buf, size_t len) int n = 0, l = 0; char buffer[128]; - n += scnprintf(buf+n, len-n, "%04x:%02x:%02x:%01x\n", + n += scnprintf(buf+n, len-n, "%04x:%02x:%02x.%01x\n", edev->phb->global_number, pdn->busno, PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn)); - pr_warn("EEH: of node=%04x:%02x:%02x:%01x\n", + pr_warn("EEH: of node=%04x:%02x:%02x.%01x\n", edev->phb->global_number, pdn->busno, PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn)); diff --git a/arch/powerpc/kernel/eeh_cache.c b/arch/powerpc/kernel/eeh_cache.c index ddbcfab7e..d4cc26618 100644 --- a/arch/powerpc/kernel/eeh_cache.c +++ b/arch/powerpc/kernel/eeh_cache.c @@ -114,9 +114,9 @@ static void eeh_addr_cache_print(struct pci_io_addr_cache *cache) while (n) { struct pci_io_addr_range *piar; piar = rb_entry(n, struct pci_io_addr_range, rb_node); - pr_debug("PCI: %s addr range %d [%lx-%lx]: %s\n", + pr_debug("PCI: %s addr range %d [%pap-%pap]: %s\n", (piar->flags & IORESOURCE_IO) ? "i/o" : "mem", cnt, - piar->addr_lo, piar->addr_hi, pci_name(piar->pcidev)); + &piar->addr_lo, &piar->addr_hi, pci_name(piar->pcidev)); cnt++; n = rb_next(n); } @@ -159,8 +159,8 @@ eeh_addr_cache_insert(struct pci_dev *dev, resource_size_t alo, piar->flags = flags; #ifdef DEBUG - pr_debug("PIAR: insert range=[%lx:%lx] dev=%s\n", - alo, ahi, pci_name(dev)); + pr_debug("PIAR: insert range=[%pap:%pap] dev=%s\n", + &alo, &ahi, pci_name(dev)); #endif rb_link_node(&piar->rb_node, parent, p); diff --git a/arch/powerpc/kernel/eeh_dev.c b/arch/powerpc/kernel/eeh_dev.c index 7815095fe..d6b2ca70d 100644 --- a/arch/powerpc/kernel/eeh_dev.c +++ b/arch/powerpc/kernel/eeh_dev.c @@ -44,14 +44,13 @@ /** * eeh_dev_init - Create EEH device according to OF node * @pdn: PCI device node - * @data: PHB * * It will create EEH device according to the given OF node. The function * might be called by PCI emunation, DR, PHB hotplug. */ -void *eeh_dev_init(struct pci_dn *pdn, void *data) +struct eeh_dev *eeh_dev_init(struct pci_dn *pdn) { - struct pci_controller *phb = data; + struct pci_controller *phb = pdn->phb; struct eeh_dev *edev; /* Allocate EEH device */ @@ -69,7 +68,7 @@ void *eeh_dev_init(struct pci_dn *pdn, void *data) INIT_LIST_HEAD(&edev->list); INIT_LIST_HEAD(&edev->rmv_list); - return NULL; + return edev; } /** @@ -81,16 +80,8 @@ void *eeh_dev_init(struct pci_dn *pdn, void *data) */ void eeh_dev_phb_init_dynamic(struct pci_controller *phb) { - struct pci_dn *root = phb->pci_data; - /* EEH PE for PHB */ eeh_phb_pe_create(phb); - - /* EEH device for PHB */ - eeh_dev_init(root, phb); - - /* EEH devices for children OF nodes */ - traverse_pci_dn(root, eeh_dev_init, phb); } /** @@ -106,8 +97,6 @@ static int __init eeh_dev_phb_init(void) list_for_each_entry_safe(phb, tmp, &hose_list, list_node) eeh_dev_phb_init_dynamic(phb); - pr_info("EEH: devices created\n"); - return 0; } diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index d70101e1e..5f36e8a70 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -139,7 +139,7 @@ static void eeh_enable_irq(struct pci_dev *dev) * into it. * * That's just wrong.The warning in the core code is - * there to tell people to fix their assymetries in + * there to tell people to fix their asymmetries in * their own code, not by abusing the core information * to avoid it. * diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 2405631e9..989903223 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -175,6 +175,12 @@ transfer_to_handler: addi r12,r12,-1 stw r12,4(r11) #endif +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE + CURRENT_THREAD_INFO(r9, r1) + tophys(r9, r9) + ACCOUNT_CPU_USER_ENTRY(r9, r11, r12) +#endif + b 3f 2: /* if from kernel, check interrupted DOZE/NAP mode and @@ -398,6 +404,13 @@ BEGIN_FTR_SECTION lwarx r7,0,r1 END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX) stwcx. r0,0,r1 /* to clear the reservation */ +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE + andi. r4,r8,MSR_PR + beq 3f + CURRENT_THREAD_INFO(r4, r1) + ACCOUNT_CPU_USER_EXIT(r4, r5, r7) +3: +#endif lwz r4,_LINK(r1) lwz r5,_CCR(r1) mtlr r4 @@ -769,6 +782,10 @@ restore_user: andis. r10,r0,DBCR0_IDM@h bnel- load_dbcr0 #endif +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE + CURRENT_THREAD_INFO(r9, r1) + ACCOUNT_CPU_USER_EXIT(r9, r10, r11) +#endif b restore diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 96fd031a3..5afd03e5e 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -72,7 +72,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_TM) std r0,GPR0(r1) std r10,GPR1(r1) beq 2f /* if from kernel mode */ - ACCOUNT_CPU_USER_ENTRY(r10, r11) + ACCOUNT_CPU_USER_ENTRY(r13, r10, r11) 2: std r2,GPR2(r1) std r3,GPR3(r1) mfcr r2 @@ -246,7 +246,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS) ld r4,_LINK(r1) beq- 1f - ACCOUNT_CPU_USER_EXIT(r11, r12) + ACCOUNT_CPU_USER_EXIT(r13, r11, r12) BEGIN_FTR_SECTION HMT_MEDIUM_LOW @@ -453,7 +453,7 @@ _GLOBAL(ret_from_kernel_thread) REST_NVGPRS(r1) mtlr r14 mr r3,r15 -#if defined(_CALL_ELF) && _CALL_ELF == 2 +#ifdef PPC64_ELF_ABI_v2 mr r12,r14 #endif blrl @@ -532,7 +532,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) #ifdef CONFIG_PPC_STD_MMU_64 BEGIN_MMU_FTR_SECTION b 2f -END_MMU_FTR_SECTION_IFSET(MMU_FTR_RADIX) +END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX) BEGIN_FTR_SECTION clrrdi r6,r8,28 /* get its ESID */ clrrdi r9,r1,28 /* get current sp ESID */ @@ -859,7 +859,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) BEGIN_FTR_SECTION mtspr SPRN_PPR,r2 /* Restore PPR */ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) - ACCOUNT_CPU_USER_EXIT(r2, r4) + ACCOUNT_CPU_USER_EXIT(r13, r2, r4) REST_GPR(13, r1) 1: mtspr SPRN_SRR1,r3 diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index 488e6314f..38a1f9643 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -386,7 +386,7 @@ exc_##n##_common: \ std r10,_NIP(r1); /* save SRR0 to stackframe */ \ std r11,_MSR(r1); /* save SRR1 to stackframe */ \ beq 2f; /* if from kernel mode */ \ - ACCOUNT_CPU_USER_ENTRY(r10,r11);/* accounting (uses cr0+eq) */ \ + ACCOUNT_CPU_USER_ENTRY(r13,r10,r11);/* accounting (uses cr0+eq) */ \ 2: ld r3,excf+EX_R10(r13); /* get back r10 */ \ ld r4,excf+EX_R11(r13); /* get back r11 */ \ mfspr r5,scratch; /* get back r13 */ \ @@ -453,7 +453,7 @@ exc_##n##_bad_stack: \ sth r1,PACA_TRAP_SAVE(r13); /* store trap */ \ b bad_stack_book3e; /* bad stack error */ -/* WARNING: If you change the layout of this stub, make sure you chcek +/* WARNING: If you change the layout of this stub, make sure you check * the debug exception handler which handles single stepping * into exceptions from userspace, and the MM code in * arch/powerpc/mm/tlb_nohash.c which patches the branch here @@ -1059,7 +1059,7 @@ fast_exception_return: andi. r6,r10,MSR_PR REST_2GPRS(6, r1) beq 1f - ACCOUNT_CPU_USER_EXIT(r10, r11) + ACCOUNT_CPU_USER_EXIT(r13, r10, r11) ld r0,GPR13(r1) 1: stdcx. r0,0,r1 /* to clear the reservation */ diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 8bcc1b457..bffec73db 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -107,25 +107,9 @@ BEGIN_FTR_SECTION beq 9f cmpwi cr3,r13,2 - - /* - * Check if last bit of HSPGR0 is set. This indicates whether we are - * waking up from winkle. - */ GET_PACA(r13) - clrldi r5,r13,63 - clrrdi r13,r13,1 - cmpwi cr4,r5,1 - mtspr SPRN_HSPRG0,r13 - - lbz r0,PACA_THREAD_IDLE_STATE(r13) - cmpwi cr2,r0,PNV_THREAD_NAP - bgt cr2,8f /* Either sleep or Winkle */ + bl pnv_restore_hyp_resource - /* Waking up from nap should not cause hypervisor state loss */ - bgt cr3,. - - /* Waking up from nap */ li r0,PNV_THREAD_RUNNING stb r0,PACA_THREAD_IDLE_STATE(r13) /* Clear thread state */ @@ -143,13 +127,9 @@ BEGIN_FTR_SECTION /* Return SRR1 from power7_nap() */ mfspr r3,SPRN_SRR1 - beq cr3,2f - b power7_wakeup_noloss -2: b power7_wakeup_loss - - /* Fast Sleep wakeup on PowerNV */ -8: GET_PACA(r13) - b power7_wakeup_tb_loss + blt cr3,2f + b pnv_wakeup_loss +2: b pnv_wakeup_noloss 9: END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) @@ -164,29 +144,14 @@ machine_check_pSeries_1: * vector */ SET_SCRATCH0(r13) /* save r13 */ -#ifdef CONFIG_PPC_P7_NAP -BEGIN_FTR_SECTION - /* Running native on arch 2.06 or later, check if we are - * waking up from nap. We only handle no state loss and - * supervisor state loss. We do -not- handle hypervisor - * state loss at this time. + /* + * Running native on arch 2.06 or later, we may wakeup from winkle + * inside machine check. If yes, then last bit of HSPGR0 would be set + * to 1. Hence clear it unconditionally. */ - mfspr r13,SPRN_SRR1 - rlwinm. r13,r13,47-31,30,31 - OPT_GET_SPR(r13, SPRN_CFAR, CPU_FTR_CFAR) - beq 9f - - mfspr r13,SPRN_SRR1 - rlwinm. r13,r13,47-31,30,31 - /* waking up from powersave (nap) state */ - cmpwi cr1,r13,2 - /* Total loss of HV state is fatal. let's just stay stuck here */ - OPT_GET_SPR(r13, SPRN_CFAR, CPU_FTR_CFAR) - bgt cr1,. -9: - OPT_SET_SPR(r13, SPRN_CFAR, CPU_FTR_CFAR) -END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) -#endif /* CONFIG_PPC_P7_NAP */ + GET_PACA(r13) + clrrdi r13,r13,1 + SET_PACA(r13) EXCEPTION_PROLOG_0(PACA_EXMC) BEGIN_FTR_SECTION b machine_check_powernv_early @@ -351,6 +316,12 @@ hv_doorbell_trampoline: EXCEPTION_PROLOG_0(PACA_EXGEN) b h_doorbell_hv + . = 0xea0 +hv_virt_irq_trampoline: + SET_SCRATCH0(r13) + EXCEPTION_PROLOG_0(PACA_EXGEN) + b h_virt_irq_hv + /* We need to deal with the Altivec unavailable exception * here which is at 0xf20, thus in the middle of the * prolog code of the PerformanceMonitor one. A little @@ -514,7 +485,23 @@ machine_check_fwnmi: EXCEPTION_PROLOG_0(PACA_EXMC) machine_check_pSeries_0: EXCEPTION_PROLOG_1(PACA_EXMC, KVMTEST, 0x200) - EXCEPTION_PROLOG_PSERIES_1(machine_check_common, EXC_STD) + /* + * The following is essentially EXCEPTION_PROLOG_PSERIES_1 with the + * difference that MSR_RI is not enabled, because PACA_EXMC is being + * used, so nested machine check corrupts it. machine_check_common + * enables MSR_RI. + */ + ld r12,PACAKBASE(r13) + ld r10,PACAKMSR(r13) + xori r10,r10,MSR_RI + mfspr r11,SPRN_SRR0 + LOAD_HANDLER(r12, machine_check_common) + mtspr SPRN_SRR0,r12 + mfspr r12,SPRN_SRR1 + mtspr SPRN_SRR1,r10 + rfid + b . /* prevent speculative execution */ + KVM_HANDLER_SKIP(PACA_EXMC, EXC_STD, 0x200) KVM_HANDLER_SKIP(PACA_EXGEN, EXC_STD, 0x300) KVM_HANDLER_SKIP(PACA_EXSLB, EXC_STD, 0x380) @@ -601,6 +588,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR) MASKABLE_EXCEPTION_HV_OOL(0xe82, h_doorbell) KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe82) + MASKABLE_EXCEPTION_HV_OOL(0xea2, h_virt_irq) + KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xea2) + /* moved from 0xf00 */ STD_EXCEPTION_PSERIES_OOL(0xf00, performance_monitor) KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xf00) @@ -680,6 +670,10 @@ _GLOBAL(__replay_interrupt) BEGIN_FTR_SECTION cmpwi r3,0xe80 beq h_doorbell_common + cmpwi r3,0xea0 + beq h_virt_irq_common + cmpwi r3,0xe60 + beq hmi_exception_common FTR_SECTION_ELSE cmpwi r3,0xa00 beq doorbell_super_common @@ -754,6 +748,7 @@ kvmppc_skip_Hinterrupt: #else STD_EXCEPTION_COMMON_ASYNC(0xe80, h_doorbell, unknown_exception) #endif + STD_EXCEPTION_COMMON_ASYNC(0xea0, h_virt_irq, do_IRQ) STD_EXCEPTION_COMMON_ASYNC(0xf00, performance_monitor, performance_monitor_exception) STD_EXCEPTION_COMMON(0x1300, instruction_breakpoint, instruction_breakpoint_exception) STD_EXCEPTION_COMMON(0x1502, denorm, unknown_exception) @@ -762,11 +757,6 @@ kvmppc_skip_Hinterrupt: #else STD_EXCEPTION_COMMON(0x1700, altivec_assist, unknown_exception) #endif -#ifdef CONFIG_CBE_RAS - STD_EXCEPTION_COMMON(0x1200, cbe_system_error, cbe_system_error_exception) - STD_EXCEPTION_COMMON(0x1600, cbe_maintenance, cbe_maintenance_exception) - STD_EXCEPTION_COMMON(0x1800, cbe_thermal, cbe_thermal_exception) -#endif /* CONFIG_CBE_RAS */ /* * Relocation-on interrupts: A subset of the interrupts can be delivered @@ -877,6 +867,12 @@ h_doorbell_relon_trampoline: EXCEPTION_PROLOG_0(PACA_EXGEN) b h_doorbell_relon_hv + . = 0x4ea0 +h_virt_irq_relon_trampoline: + SET_SCRATCH0(r13) + EXCEPTION_PROLOG_0(PACA_EXGEN) + b h_virt_irq_relon_hv + . = 0x4f00 performance_monitor_relon_pseries_trampoline: SET_SCRATCH0(r13) @@ -945,7 +941,7 @@ BEGIN_MMU_FTR_SECTION b do_hash_page /* Try to handle as hpte fault */ MMU_FTR_SECTION_ELSE b handle_page_fault -ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_RADIX) +ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) .align 7 .globl h_data_storage_common @@ -976,7 +972,7 @@ BEGIN_MMU_FTR_SECTION b do_hash_page /* Try to handle as hpte fault */ MMU_FTR_SECTION_ELSE b handle_page_fault -ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_RADIX) +ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) STD_EXCEPTION_COMMON(0xe20, h_instr_storage, unknown_exception) @@ -989,14 +985,17 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_RADIX) machine_check_common: mfspr r10,SPRN_DAR - std r10,PACA_EXGEN+EX_DAR(r13) + std r10,PACA_EXMC+EX_DAR(r13) mfspr r10,SPRN_DSISR - stw r10,PACA_EXGEN+EX_DSISR(r13) + stw r10,PACA_EXMC+EX_DSISR(r13) EXCEPTION_PROLOG_COMMON(0x200, PACA_EXMC) FINISH_NAP RECONCILE_IRQ_STATE(r10, r11) - ld r3,PACA_EXGEN+EX_DAR(r13) - lwz r4,PACA_EXGEN+EX_DSISR(r13) + ld r3,PACA_EXMC+EX_DAR(r13) + lwz r4,PACA_EXMC+EX_DSISR(r13) + /* Enable MSR_RI when finished with PACA_EXMC */ + li r10,MSR_RI + mtmsrd r10,1 std r3,_DAR(r1) std r4,_DSISR(r1) bl save_nvgprs @@ -1131,12 +1130,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX) bl vsx_unavailable_exception b ret_from_except - STD_EXCEPTION_COMMON(0xf60, facility_unavailable, facility_unavailable_exception) - STD_EXCEPTION_COMMON(0xf80, hv_facility_unavailable, facility_unavailable_exception) - /* Equivalents to the above handlers for relocation-on interrupt vectors */ STD_RELON_EXCEPTION_HV_OOL(0xe40, emulation_assist) MASKABLE_RELON_EXCEPTION_HV_OOL(0xe80, h_doorbell) + MASKABLE_RELON_EXCEPTION_HV_OOL(0xea0, h_virt_irq) STD_RELON_EXCEPTION_PSERIES_OOL(0xf00, performance_monitor) STD_RELON_EXCEPTION_PSERIES_OOL(0xf20, altivec_unavailable) @@ -1170,9 +1167,18 @@ fwnmi_data_area: . = 0x8000 #endif /* defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) */ + STD_EXCEPTION_COMMON(0xf60, facility_unavailable, facility_unavailable_exception) + STD_EXCEPTION_COMMON(0xf80, hv_facility_unavailable, facility_unavailable_exception) + +#ifdef CONFIG_CBE_RAS + STD_EXCEPTION_COMMON(0x1200, cbe_system_error, cbe_system_error_exception) + STD_EXCEPTION_COMMON(0x1600, cbe_maintenance, cbe_maintenance_exception) + STD_EXCEPTION_COMMON(0x1800, cbe_thermal, cbe_thermal_exception) +#endif /* CONFIG_CBE_RAS */ + .globl hmi_exception_early hmi_exception_early: - EXCEPTION_PROLOG_1(PACA_EXGEN, NOTEST, 0xe60) + EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST, 0xe62) mr r10,r1 /* Save r1 */ ld r1,PACAEMERGSP(r13) /* Use emergency stack */ subi r1,r1,INT_FRAME_SIZE /* alloc stack frame */ @@ -1271,25 +1277,51 @@ machine_check_handle_early: * Check if thread was in power saving mode. We come here when any * of the following is true: * a. thread wasn't in power saving mode - * b. thread was in power saving mode with no state loss or - * supervisor state loss + * b. thread was in power saving mode with no state loss, + * supervisor state loss or hypervisor state loss. * - * Go back to nap again if (b) is true. + * Go back to nap/sleep/winkle mode again if (b) is true. */ rlwinm. r11,r12,47-31,30,31 /* Was it in power saving mode? */ beq 4f /* No, it wasn;t */ /* Thread was in power saving mode. Go back to nap again. */ cmpwi r11,2 - bne 3f - /* Supervisor state loss */ + blt 3f + /* Supervisor/Hypervisor state loss */ li r0,1 stb r0,PACA_NAPSTATELOST(r13) 3: bl machine_check_queue_event MACHINE_CHECK_HANDLER_WINDUP GET_PACA(r13) ld r1,PACAR1(r13) - li r3,PNV_THREAD_NAP - b power7_enter_nap_mode + /* + * Check what idle state this CPU was in and go back to same mode + * again. + */ + lbz r3,PACA_THREAD_IDLE_STATE(r13) + cmpwi r3,PNV_THREAD_NAP + bgt 10f + IDLE_STATE_ENTER_SEQ(PPC_NAP) + /* No return */ +10: + cmpwi r3,PNV_THREAD_SLEEP + bgt 2f + IDLE_STATE_ENTER_SEQ(PPC_SLEEP) + /* No return */ + +2: + /* + * Go back to winkle. Please note that this thread was woken up in + * machine check from winkle and have not restored the per-subcore + * state. Hence before going back to winkle, set last bit of HSPGR0 + * to 1. This will make sure that if this thread gets woken up + * again at reset vector 0x100 then it will get chance to restore + * the subcore state. + */ + ori r13,r13,1 + SET_PACA(r13) + IDLE_STATE_ENTER_SEQ(PPC_WINKLE) + /* No return */ 4: #endif /* @@ -1390,7 +1422,7 @@ slb_miss_realmode: #ifdef CONFIG_PPC_STD_MMU_64 BEGIN_MMU_FTR_SECTION bl slb_allocate_realmode -END_MMU_FTR_SECTION_IFCLR(MMU_FTR_RADIX) +END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX) #endif /* All done -- return from exception. */ @@ -1404,7 +1436,7 @@ BEGIN_MMU_FTR_SECTION beq- 2f FTR_SECTION_ELSE b 2f -ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_RADIX) +ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) .machine push .machine "power4" diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index 3cb3b02a1..b3a663333 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -1009,8 +1009,7 @@ static int fadump_invalidate_dump(struct fadump_mem_struct *fdm) } while (wait_time); if (rc) { - printk(KERN_ERR "Failed to invalidate firmware-assisted dump " - "rgistration. unexpected error(%d).\n", rc); + pr_err("Failed to invalidate firmware-assisted dump registration. Unexpected error (%d).\n", rc); return rc; } fw_dump.dump_active = 0; diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c index 1123a4d8d..cc52d9795 100644 --- a/arch/powerpc/kernel/ftrace.c +++ b/arch/powerpc/kernel/ftrace.c @@ -144,6 +144,21 @@ __ftrace_make_nop(struct module *mod, return -EINVAL; } +#ifdef CC_USING_MPROFILE_KERNEL + /* When using -mkernel_profile there is no load to jump over */ + pop = PPC_INST_NOP; + + if (probe_kernel_read(&op, (void *)(ip - 4), 4)) { + pr_err("Fetching instruction at %lx failed.\n", ip - 4); + return -EFAULT; + } + + /* We expect either a mflr r0, or a std r0, LRSAVE(r1) */ + if (op != PPC_INST_MFLR && op != PPC_INST_STD_LR) { + pr_err("Unexpected instruction %08x around bl _mcount\n", op); + return -EINVAL; + } +#else /* * Our original call site looks like: * @@ -170,24 +185,10 @@ __ftrace_make_nop(struct module *mod, } if (op != PPC_INST_LD_TOC) { - unsigned int inst; - - if (probe_kernel_read(&inst, (void *)(ip - 4), 4)) { - pr_err("Fetching instruction at %lx failed.\n", ip - 4); - return -EFAULT; - } - - /* We expect either a mlfr r0, or a std r0, LRSAVE(r1) */ - if (inst != PPC_INST_MFLR && inst != PPC_INST_STD_LR) { - pr_err("Unexpected instructions around bl _mcount\n" - "when enabling dynamic ftrace!\t" - "(%08x,bl,%08x)\n", inst, op); - return -EINVAL; - } - - /* When using -mkernel_profile there is no load to jump over */ - pop = PPC_INST_NOP; + pr_err("Expected %08x found %08x\n", PPC_INST_LD_TOC, op); + return -EINVAL; } +#endif /* CC_USING_MPROFILE_KERNEL */ if (patch_instruction((unsigned int *)ip, pop)) { pr_err("Patching NOP failed.\n"); @@ -608,7 +609,7 @@ unsigned long __init arch_syscall_addr(int nr) } #endif /* CONFIG_FTRACE_SYSCALLS && CONFIG_PPC64 */ -#if defined(CONFIG_PPC64) && (!defined(_CALL_ELF) || _CALL_ELF != 2) +#ifdef PPC64_ELF_ABI_v1 char *arch_ftrace_match_adjust(char *str, const char *search) { if (str[0] == '.' && search[0] != '.') @@ -616,4 +617,4 @@ char *arch_ftrace_match_adjust(char *str, const char *search) else return str; } -#endif /* defined(CONFIG_PPC64) && (!defined(_CALL_ELF) || _CALL_ELF != 2) */ +#endif /* PPC64_ELF_ABI_v1 */ diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 2d14774af..f765b0434 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -401,7 +401,7 @@ generic_secondary_common_init: ld r12,CPU_SPEC_RESTORE(r23) cmpdi 0,r12,0 beq 3f -#if !defined(_CALL_ELF) || _CALL_ELF != 2 +#ifdef PPC64_ELF_ABI_v1 ld r12,0(r12) #endif mtctr r12 @@ -941,7 +941,7 @@ start_here_multiplatform: mtspr SPRN_SRR1,r4 RFI b . /* prevent speculative execution */ - + /* This is where all platforms converge execution */ start_here_common: @@ -951,9 +951,6 @@ start_here_common: /* Load the TOC (virtual address) */ ld r2,PACATOC(r13) - /* Do more system initializations in virtual mode */ - bl setup_system - /* Mark interrupts soft and hard disabled (they might be enabled * in the PACA when doing hotplug) */ diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index 80c694723..43ddaae42 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -30,6 +30,7 @@ #include <asm/ppc_asm.h> #include <asm/asm-offsets.h> #include <asm/ptrace.h> +#include <asm/fixmap.h> /* Macro to make the code more readable. */ #ifdef CONFIG_8xx_CPU6 @@ -383,28 +384,57 @@ InstructionTLBMiss: EXCEPTION_EPILOG_0 rfi +/* + * Bottom part of DataStoreTLBMiss handler for IMMR area + * not enough space in the DataStoreTLBMiss area + */ +DTLBMissIMMR: + mtcr r10 + /* Set 512k byte guarded page and mark it valid */ + li r10, MD_PS512K | MD_GUARDED | MD_SVALID + MTSPR_CPU6(SPRN_MD_TWC, r10, r11) + mfspr r10, SPRN_IMMR /* Get current IMMR */ + rlwinm r10, r10, 0, 0xfff80000 /* Get 512 kbytes boundary */ + ori r10, r10, 0xf0 | MD_SPS16K | _PAGE_SHARED | _PAGE_DIRTY | \ + _PAGE_PRESENT | _PAGE_NO_CACHE + MTSPR_CPU6(SPRN_MD_RPN, r10, r11) /* Update TLB entry */ + + li r11, RPN_PATTERN + mtspr SPRN_DAR, r11 /* Tag DAR */ + EXCEPTION_EPILOG_0 + rfi + . = 0x1200 DataStoreTLBMiss: - mtspr SPRN_SPRG_SCRATCH2, r3 EXCEPTION_PROLOG_0 - mfcr r3 + mfcr r10 /* If we are faulting a kernel address, we have to use the * kernel page tables. */ - mfspr r10, SPRN_MD_EPN - IS_KERNEL(r11, r10) + mfspr r11, SPRN_MD_EPN + rlwinm r11, r11, 16, 0xfff8 +#ifndef CONFIG_PIN_TLB_IMMR + cmpli cr0, r11, VIRT_IMMR_BASE@h +#endif + cmpli cr7, r11, PAGE_OFFSET@h +#ifndef CONFIG_PIN_TLB_IMMR +_ENTRY(DTLBMiss_jmp) + beq- DTLBMissIMMR +#endif + bge- cr7, 4f + mfspr r11, SPRN_M_TW /* Get level 1 table */ - BRANCH_UNLESS_KERNEL(3f) - lis r11, (swapper_pg_dir-PAGE_OFFSET)@ha 3: + mtcr r10 +#ifdef CONFIG_8xx_CPU6 + mtspr SPRN_SPRG_SCRATCH2, r3 +#endif + mfspr r10, SPRN_MD_EPN /* Insert level 1 index */ rlwimi r11, r10, 32 - ((PAGE_SHIFT - 2) << 1), (PAGE_SHIFT - 2) << 1, 29 lwz r11, (swapper_pg_dir-PAGE_OFFSET)@l(r11) /* Get the level 1 entry */ - mtcr r11 - bt- 28,DTLBMiss8M /* bit 28 = Large page (8M) */ - mtcr r3 /* We have a pte table, so load fetch the pte from the table. */ @@ -452,29 +482,30 @@ DataStoreTLBMiss: MTSPR_CPU6(SPRN_MD_RPN, r10, r3) /* Update TLB entry */ /* Restore registers */ +#ifdef CONFIG_8xx_CPU6 mfspr r3, SPRN_SPRG_SCRATCH2 +#endif mtspr SPRN_DAR, r11 /* Tag DAR */ EXCEPTION_EPILOG_0 rfi -DTLBMiss8M: - mtcr r3 - ori r11, r11, MD_SVALID - MTSPR_CPU6(SPRN_MD_TWC, r11, r3) -#ifdef CONFIG_PPC_16K_PAGES - /* - * In 16k pages mode, each PGD entry defines a 64M block. - * Here we select the 8M page within the block. - */ - rlwimi r11, r10, 0, 0x03800000 -#endif - rlwinm r10, r11, 0, 0xff800000 +4: +_ENTRY(DTLBMiss_cmp) + cmpli cr0, r11, (PAGE_OFFSET + 0x1800000)@h + lis r11, (swapper_pg_dir-PAGE_OFFSET)@ha + bge- 3b + + mtcr r10 + /* Set 8M byte page and mark it valid */ + li r10, MD_PS8MEG | MD_SVALID + MTSPR_CPU6(SPRN_MD_TWC, r10, r11) + mfspr r10, SPRN_MD_EPN + rlwinm r10, r10, 0, 0x0f800000 /* 8xx supports max 256Mb RAM */ ori r10, r10, 0xf0 | MD_SPS16K | _PAGE_SHARED | _PAGE_DIRTY | \ _PAGE_PRESENT - MTSPR_CPU6(SPRN_MD_RPN, r10, r3) /* Update TLB entry */ + MTSPR_CPU6(SPRN_MD_RPN, r10, r11) /* Update TLB entry */ li r11, RPN_PATTERN - mfspr r3, SPRN_SPRG_SCRATCH2 mtspr SPRN_DAR, r11 /* Tag DAR */ EXCEPTION_EPILOG_0 rfi @@ -553,12 +584,14 @@ FixupDAR:/* Entry point for dcbx workaround. */ IS_KERNEL(r11, r10) mfspr r11, SPRN_M_TW /* Get level 1 table */ BRANCH_UNLESS_KERNEL(3f) + rlwinm r11, r10, 16, 0xfff8 +_ENTRY(FixupDAR_cmp) + cmpli cr7, r11, (PAGE_OFFSET + 0x1800000)@h + blt- cr7, 200f lis r11, (swapper_pg_dir-PAGE_OFFSET)@ha /* Insert level 1 index */ 3: rlwimi r11, r10, 32 - ((PAGE_SHIFT - 2) << 1), (PAGE_SHIFT - 2) << 1, 29 lwz r11, (swapper_pg_dir-PAGE_OFFSET)@l(r11) /* Get the level 1 entry */ - mtcr r11 - bt 28,200f /* bit 28 = Large page (8M) */ rlwinm r11, r11,0,0,19 /* Extract page descriptor page address */ /* Insert level 2 index */ rlwimi r11, r10, 32 - (PAGE_SHIFT - 2), 32 - PAGE_SHIFT, 29 @@ -584,8 +617,8 @@ FixupDAR:/* Entry point for dcbx workaround. */ 141: mfspr r10,SPRN_SPRG_SCRATCH2 b DARFixed /* Nope, go back to normal TLB processing */ - /* concat physical page address(r11) and page offset(r10) */ -200: rlwimi r11, r10, 0, 32 - (PAGE_SHIFT << 1), 31 + /* create physical page address from effective address */ +200: tophys(r11, r10) b 201b 144: mfspr r10, SPRN_DSISR @@ -763,10 +796,18 @@ start_here: * virtual to physical. Also, set the cache mode since that is defined * by TLB entries and perform any additional mapping (like of the IMMR). * If configured to pin some TLBs, we pin the first 8 Mbytes of kernel, - * 24 Mbytes of data, and the 8M IMMR space. Anything not covered by + * 24 Mbytes of data, and the 512k IMMR space. Anything not covered by * these mappings is mapped by page tables. */ initial_mmu: + li r8, 0 + mtspr SPRN_MI_CTR, r8 /* remove PINNED ITLB entries */ + lis r10, MD_RESETVAL@h +#ifndef CONFIG_8xx_COPYBACK + oris r10, r10, MD_WTDEF@h +#endif + mtspr SPRN_MD_CTR, r10 /* remove PINNED DTLB entries */ + tlbia /* Invalidate all TLB entries */ /* Always pin the first 8 MB ITLB to prevent ITLB misses while mucking around with SRR0/SRR1 in asm @@ -777,34 +818,20 @@ initial_mmu: mtspr SPRN_MI_CTR, r8 /* Set instruction MMU control */ #ifdef CONFIG_PIN_TLB - lis r10, (MD_RSV4I | MD_RESETVAL)@h - ori r10, r10, 0x1c00 - mr r8, r10 -#else - lis r10, MD_RESETVAL@h -#endif -#ifndef CONFIG_8xx_COPYBACK - oris r10, r10, MD_WTDEF@h -#endif + oris r10, r10, MD_RSV4I@h mtspr SPRN_MD_CTR, r10 /* Set data TLB control */ +#endif - /* Now map the lower 8 Meg into the TLBs. For this quick hack, - * we can load the instruction and data TLB registers with the - * same values. - */ + /* Now map the lower 8 Meg into the ITLB. */ lis r8, KERNELBASE@h /* Create vaddr for TLB */ ori r8, r8, MI_EVALID /* Mark it valid */ mtspr SPRN_MI_EPN, r8 - mtspr SPRN_MD_EPN, r8 li r8, MI_PS8MEG | (2 << 5) /* Set 8M byte page, APG 2 */ ori r8, r8, MI_SVALID /* Make it valid */ mtspr SPRN_MI_TWC, r8 - li r8, MI_PS8MEG /* Set 8M byte page, APG 0 */ - ori r8, r8, MI_SVALID /* Make it valid */ - mtspr SPRN_MD_TWC, r8 li r8, MI_BOOTINIT /* Create RPN for address 0 */ mtspr SPRN_MI_RPN, r8 /* Store TLB entry */ - mtspr SPRN_MD_RPN, r8 + lis r8, MI_APG_INIT@h /* Set protection modes */ ori r8, r8, MI_APG_INIT@l mtspr SPRN_MI_AP, r8 @@ -812,51 +839,25 @@ initial_mmu: ori r8, r8, MD_APG_INIT@l mtspr SPRN_MD_AP, r8 - /* Map another 8 MByte at the IMMR to get the processor + /* Map a 512k page for the IMMR to get the processor * internal registers (among other things). */ -#ifdef CONFIG_PIN_TLB - addi r10, r10, 0x0100 +#ifdef CONFIG_PIN_TLB_IMMR + ori r10, r10, 0x1c00 mtspr SPRN_MD_CTR, r10 -#endif + mfspr r9, 638 /* Get current IMMR */ - andis. r9, r9, 0xff80 /* Get 8Mbyte boundary */ + andis. r9, r9, 0xfff8 /* Get 512 kbytes boundary */ - mr r8, r9 /* Create vaddr for TLB */ + lis r8, VIRT_IMMR_BASE@h /* Create vaddr for TLB */ ori r8, r8, MD_EVALID /* Mark it valid */ mtspr SPRN_MD_EPN, r8 - li r8, MD_PS8MEG /* Set 8M byte page */ + li r8, MD_PS512K | MD_GUARDED /* Set 512k byte page */ ori r8, r8, MD_SVALID /* Make it valid */ mtspr SPRN_MD_TWC, r8 mr r8, r9 /* Create paddr for TLB */ ori r8, r8, MI_BOOTINIT|0x2 /* Inhibit cache -- Cort */ mtspr SPRN_MD_RPN, r8 - -#ifdef CONFIG_PIN_TLB - /* Map two more 8M kernel data pages. - */ - addi r10, r10, 0x0100 - mtspr SPRN_MD_CTR, r10 - - lis r8, KERNELBASE@h /* Create vaddr for TLB */ - addis r8, r8, 0x0080 /* Add 8M */ - ori r8, r8, MI_EVALID /* Mark it valid */ - mtspr SPRN_MD_EPN, r8 - li r9, MI_PS8MEG /* Set 8M byte page */ - ori r9, r9, MI_SVALID /* Make it valid */ - mtspr SPRN_MD_TWC, r9 - li r11, MI_BOOTINIT /* Create RPN for address 0 */ - addis r11, r11, 0x0080 /* Add 8M */ - mtspr SPRN_MD_RPN, r11 - - addi r10, r10, 0x0100 - mtspr SPRN_MD_CTR, r10 - - addis r8, r8, 0x0080 /* Add 8M */ - mtspr SPRN_MD_EPN, r8 - mtspr SPRN_MD_TWC, r9 - addis r11, r11, 0x0080 /* Add 8M */ - mtspr SPRN_MD_RPN, r11 #endif /* Since the cache is enabled according to the information we diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c index a89f4f7a6..c1ca9282f 100644 --- a/arch/powerpc/kernel/ibmebus.c +++ b/arch/powerpc/kernel/ibmebus.c @@ -65,7 +65,7 @@ static void *ibmebus_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag, - struct dma_attrs *attrs) + unsigned long attrs) { void *mem; @@ -78,7 +78,7 @@ static void *ibmebus_alloc_coherent(struct device *dev, static void ibmebus_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle, - struct dma_attrs *attrs) + unsigned long attrs) { kfree(vaddr); } @@ -88,7 +88,7 @@ static dma_addr_t ibmebus_map_page(struct device *dev, unsigned long offset, size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { return (dma_addr_t)(page_address(page) + offset); } @@ -97,7 +97,7 @@ static void ibmebus_unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { return; } @@ -105,7 +105,7 @@ static void ibmebus_unmap_page(struct device *dev, static int ibmebus_map_sg(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { struct scatterlist *sg; int i; @@ -121,7 +121,7 @@ static int ibmebus_map_sg(struct device *dev, static void ibmebus_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { return; } diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S new file mode 100644 index 000000000..bd739fed2 --- /dev/null +++ b/arch/powerpc/kernel/idle_book3s.S @@ -0,0 +1,655 @@ +/* + * This file contains idle entry/exit functions for POWER7, + * POWER8 and POWER9 CPUs. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/threads.h> +#include <asm/processor.h> +#include <asm/page.h> +#include <asm/cputable.h> +#include <asm/thread_info.h> +#include <asm/ppc_asm.h> +#include <asm/asm-offsets.h> +#include <asm/ppc-opcode.h> +#include <asm/hw_irq.h> +#include <asm/kvm_book3s_asm.h> +#include <asm/opal.h> +#include <asm/cpuidle.h> +#include <asm/book3s/64/mmu-hash.h> +#include <asm/mmu.h> + +#undef DEBUG + +/* + * Use unused space in the interrupt stack to save and restore + * registers for winkle support. + */ +#define _SDR1 GPR3 +#define _RPR GPR4 +#define _SPURR GPR5 +#define _PURR GPR6 +#define _TSCR GPR7 +#define _DSCR GPR8 +#define _AMOR GPR9 +#define _WORT GPR10 +#define _WORC GPR11 +#define _PTCR GPR12 + +#define PSSCR_HV_TEMPLATE PSSCR_ESL | PSSCR_EC | \ + PSSCR_PSLL_MASK | PSSCR_TR_MASK | \ + PSSCR_MTL_MASK + + .text + +/* + * Used by threads before entering deep idle states. Saves SPRs + * in interrupt stack frame + */ +save_sprs_to_stack: + /* + * Note all register i.e per-core, per-subcore or per-thread is saved + * here since any thread in the core might wake up first + */ +BEGIN_FTR_SECTION + mfspr r3,SPRN_PTCR + std r3,_PTCR(r1) + /* + * Note - SDR1 is dropped in Power ISA v3. Hence not restoring + * SDR1 here + */ +FTR_SECTION_ELSE + mfspr r3,SPRN_SDR1 + std r3,_SDR1(r1) +ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300) + mfspr r3,SPRN_RPR + std r3,_RPR(r1) + mfspr r3,SPRN_SPURR + std r3,_SPURR(r1) + mfspr r3,SPRN_PURR + std r3,_PURR(r1) + mfspr r3,SPRN_TSCR + std r3,_TSCR(r1) + mfspr r3,SPRN_DSCR + std r3,_DSCR(r1) + mfspr r3,SPRN_AMOR + std r3,_AMOR(r1) + mfspr r3,SPRN_WORT + std r3,_WORT(r1) + mfspr r3,SPRN_WORC + std r3,_WORC(r1) + + blr + +/* + * Used by threads when the lock bit of core_idle_state is set. + * Threads will spin in HMT_LOW until the lock bit is cleared. + * r14 - pointer to core_idle_state + * r15 - used to load contents of core_idle_state + */ + +core_idle_lock_held: + HMT_LOW +3: lwz r15,0(r14) + andi. r15,r15,PNV_CORE_IDLE_LOCK_BIT + bne 3b + HMT_MEDIUM + lwarx r15,0,r14 + blr + +/* + * Pass requested state in r3: + * r3 - PNV_THREAD_NAP/SLEEP/WINKLE in POWER8 + * - Requested STOP state in POWER9 + * + * To check IRQ_HAPPENED in r4 + * 0 - don't check + * 1 - check + * + * Address to 'rfid' to in r5 + */ +_GLOBAL(pnv_powersave_common) + /* Use r3 to pass state nap/sleep/winkle */ + /* NAP is a state loss, we create a regs frame on the + * stack, fill it up with the state we care about and + * stick a pointer to it in PACAR1. We really only + * need to save PC, some CR bits and the NV GPRs, + * but for now an interrupt frame will do. + */ + mflr r0 + std r0,16(r1) + stdu r1,-INT_FRAME_SIZE(r1) + std r0,_LINK(r1) + std r0,_NIP(r1) + + /* Hard disable interrupts */ + mfmsr r9 + rldicl r9,r9,48,1 + rotldi r9,r9,16 + mtmsrd r9,1 /* hard-disable interrupts */ + + /* Check if something happened while soft-disabled */ + lbz r0,PACAIRQHAPPENED(r13) + andi. r0,r0,~PACA_IRQ_HARD_DIS@l + beq 1f + cmpwi cr0,r4,0 + beq 1f + addi r1,r1,INT_FRAME_SIZE + ld r0,16(r1) + li r3,0 /* Return 0 (no nap) */ + mtlr r0 + blr + +1: /* We mark irqs hard disabled as this is the state we'll + * be in when returning and we need to tell arch_local_irq_restore() + * about it + */ + li r0,PACA_IRQ_HARD_DIS + stb r0,PACAIRQHAPPENED(r13) + + /* We haven't lost state ... yet */ + li r0,0 + stb r0,PACA_NAPSTATELOST(r13) + + /* Continue saving state */ + SAVE_GPR(2, r1) + SAVE_NVGPRS(r1) + mfcr r4 + std r4,_CCR(r1) + std r9,_MSR(r1) + std r1,PACAR1(r13) + +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + /* Tell KVM we're entering idle */ + li r4,KVM_HWTHREAD_IN_IDLE + stb r4,HSTATE_HWTHREAD_STATE(r13) +#endif + + /* + * Go to real mode to do the nap, as required by the architecture. + * Also, we need to be in real mode before setting hwthread_state, + * because as soon as we do that, another thread can switch + * the MMU context to the guest. + */ + LOAD_REG_IMMEDIATE(r7, MSR_IDLE) + li r6, MSR_RI + andc r6, r9, r6 + mtmsrd r6, 1 /* clear RI before setting SRR0/1 */ + mtspr SPRN_SRR0, r5 + mtspr SPRN_SRR1, r7 + rfid + + .globl pnv_enter_arch207_idle_mode +pnv_enter_arch207_idle_mode: + stb r3,PACA_THREAD_IDLE_STATE(r13) + cmpwi cr3,r3,PNV_THREAD_SLEEP + bge cr3,2f + IDLE_STATE_ENTER_SEQ(PPC_NAP) + /* No return */ +2: + /* Sleep or winkle */ + lbz r7,PACA_THREAD_MASK(r13) + ld r14,PACA_CORE_IDLE_STATE_PTR(r13) +lwarx_loop1: + lwarx r15,0,r14 + + andi. r9,r15,PNV_CORE_IDLE_LOCK_BIT + bnel core_idle_lock_held + + andc r15,r15,r7 /* Clear thread bit */ + + andi. r15,r15,PNV_CORE_IDLE_THREAD_BITS + +/* + * If cr0 = 0, then current thread is the last thread of the core entering + * sleep. Last thread needs to execute the hardware bug workaround code if + * required by the platform. + * Make the workaround call unconditionally here. The below branch call is + * patched out when the idle states are discovered if the platform does not + * require it. + */ +.global pnv_fastsleep_workaround_at_entry +pnv_fastsleep_workaround_at_entry: + beq fastsleep_workaround_at_entry + + stwcx. r15,0,r14 + bne- lwarx_loop1 + isync + +common_enter: /* common code for all the threads entering sleep or winkle */ + bgt cr3,enter_winkle + IDLE_STATE_ENTER_SEQ(PPC_SLEEP) + +fastsleep_workaround_at_entry: + ori r15,r15,PNV_CORE_IDLE_LOCK_BIT + stwcx. r15,0,r14 + bne- lwarx_loop1 + isync + + /* Fast sleep workaround */ + li r3,1 + li r4,1 + bl opal_rm_config_cpu_idle_state + + /* Clear Lock bit */ + li r0,0 + lwsync + stw r0,0(r14) + b common_enter + +enter_winkle: + bl save_sprs_to_stack + + IDLE_STATE_ENTER_SEQ(PPC_WINKLE) + +/* + * r3 - requested stop state + */ +power_enter_stop: +/* + * Check if the requested state is a deep idle state. + */ + LOAD_REG_ADDRBASE(r5,pnv_first_deep_stop_state) + ld r4,ADDROFF(pnv_first_deep_stop_state)(r5) + cmpd r3,r4 + bge 2f + IDLE_STATE_ENTER_SEQ(PPC_STOP) +2: +/* + * Entering deep idle state. + * Clear thread bit in PACA_CORE_IDLE_STATE, save SPRs to + * stack and enter stop + */ + lbz r7,PACA_THREAD_MASK(r13) + ld r14,PACA_CORE_IDLE_STATE_PTR(r13) + +lwarx_loop_stop: + lwarx r15,0,r14 + andi. r9,r15,PNV_CORE_IDLE_LOCK_BIT + bnel core_idle_lock_held + andc r15,r15,r7 /* Clear thread bit */ + + stwcx. r15,0,r14 + bne- lwarx_loop_stop + isync + + bl save_sprs_to_stack + + IDLE_STATE_ENTER_SEQ(PPC_STOP) + +_GLOBAL(power7_idle) + /* Now check if user or arch enabled NAP mode */ + LOAD_REG_ADDRBASE(r3,powersave_nap) + lwz r4,ADDROFF(powersave_nap)(r3) + cmpwi 0,r4,0 + beqlr + li r3, 1 + /* fall through */ + +_GLOBAL(power7_nap) + mr r4,r3 + li r3,PNV_THREAD_NAP + LOAD_REG_ADDR(r5, pnv_enter_arch207_idle_mode) + b pnv_powersave_common + /* No return */ + +_GLOBAL(power7_sleep) + li r3,PNV_THREAD_SLEEP + li r4,1 + LOAD_REG_ADDR(r5, pnv_enter_arch207_idle_mode) + b pnv_powersave_common + /* No return */ + +_GLOBAL(power7_winkle) + li r3,PNV_THREAD_WINKLE + li r4,1 + LOAD_REG_ADDR(r5, pnv_enter_arch207_idle_mode) + b pnv_powersave_common + /* No return */ + +#define CHECK_HMI_INTERRUPT \ + mfspr r0,SPRN_SRR1; \ +BEGIN_FTR_SECTION_NESTED(66); \ + rlwinm r0,r0,45-31,0xf; /* extract wake reason field (P8) */ \ +FTR_SECTION_ELSE_NESTED(66); \ + rlwinm r0,r0,45-31,0xe; /* P7 wake reason field is 3 bits */ \ +ALT_FTR_SECTION_END_NESTED_IFSET(CPU_FTR_ARCH_207S, 66); \ + cmpwi r0,0xa; /* Hypervisor maintenance ? */ \ + bne 20f; \ + /* Invoke opal call to handle hmi */ \ + ld r2,PACATOC(r13); \ + ld r1,PACAR1(r13); \ + std r3,ORIG_GPR3(r1); /* Save original r3 */ \ + li r3,0; /* NULL argument */ \ + bl hmi_exception_realmode; \ + nop; \ + ld r3,ORIG_GPR3(r1); /* Restore original r3 */ \ +20: nop; + + +/* + * r3 - requested stop state + */ +_GLOBAL(power9_idle_stop) + LOAD_REG_IMMEDIATE(r4, PSSCR_HV_TEMPLATE) + or r4,r4,r3 + mtspr SPRN_PSSCR, r4 + li r4, 1 + LOAD_REG_ADDR(r5,power_enter_stop) + b pnv_powersave_common + /* No return */ +/* + * Called from reset vector. Check whether we have woken up with + * hypervisor state loss. If yes, restore hypervisor state and return + * back to reset vector. + * + * r13 - Contents of HSPRG0 + * cr3 - set to gt if waking up with partial/complete hypervisor state loss + */ +_GLOBAL(pnv_restore_hyp_resource) +BEGIN_FTR_SECTION + ld r2,PACATOC(r13); + /* + * POWER ISA 3. Use PSSCR to determine if we + * are waking up from deep idle state + */ + LOAD_REG_ADDRBASE(r5,pnv_first_deep_stop_state) + ld r4,ADDROFF(pnv_first_deep_stop_state)(r5) + + mfspr r5,SPRN_PSSCR + /* + * 0-3 bits correspond to Power-Saving Level Status + * which indicates the idle state we are waking up from + */ + rldicl r5,r5,4,60 + cmpd cr4,r5,r4 + bge cr4,pnv_wakeup_tb_loss + /* + * Waking up without hypervisor state loss. Return to + * reset vector + */ + blr + +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) + + /* + * POWER ISA 2.07 or less. + * Check if last bit of HSPGR0 is set. This indicates whether we are + * waking up from winkle. + */ + clrldi r5,r13,63 + clrrdi r13,r13,1 + + /* Now that we are sure r13 is corrected, load TOC */ + ld r2,PACATOC(r13); + cmpwi cr4,r5,1 + mtspr SPRN_HSPRG0,r13 + + lbz r0,PACA_THREAD_IDLE_STATE(r13) + cmpwi cr2,r0,PNV_THREAD_NAP + bgt cr2,pnv_wakeup_tb_loss /* Either sleep or Winkle */ + + /* + * We fall through here if PACA_THREAD_IDLE_STATE shows we are waking + * up from nap. At this stage CR3 shouldn't contains 'gt' since that + * indicates we are waking with hypervisor state loss from nap. + */ + bgt cr3,. + + blr /* Return back to System Reset vector from where + pnv_restore_hyp_resource was invoked */ + +/* + * Called if waking up from idle state which can cause either partial or + * complete hyp state loss. + * In POWER8, called if waking up from fastsleep or winkle + * In POWER9, called if waking up from stop state >= pnv_first_deep_stop_state + * + * r13 - PACA + * cr3 - gt if waking up with partial/complete hypervisor state loss + * cr4 - gt or eq if waking up from complete hypervisor state loss. + */ +_GLOBAL(pnv_wakeup_tb_loss) + ld r1,PACAR1(r13) + /* + * Before entering any idle state, the NVGPRs are saved in the stack + * and they are restored before switching to the process context. Hence + * until they are restored, they are free to be used. + * + * Save SRR1 and LR in NVGPRs as they might be clobbered in + * opal_call() (called in CHECK_HMI_INTERRUPT). SRR1 is required + * to determine the wakeup reason if we branch to kvm_start_guest. LR + * is required to return back to reset vector after hypervisor state + * restore is complete. + */ + mflr r17 + mfspr r16,SPRN_SRR1 +BEGIN_FTR_SECTION + CHECK_HMI_INTERRUPT +END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) + + lbz r7,PACA_THREAD_MASK(r13) + ld r14,PACA_CORE_IDLE_STATE_PTR(r13) +lwarx_loop2: + lwarx r15,0,r14 + andi. r9,r15,PNV_CORE_IDLE_LOCK_BIT + /* + * Lock bit is set in one of the 2 cases- + * a. In the sleep/winkle enter path, the last thread is executing + * fastsleep workaround code. + * b. In the wake up path, another thread is executing fastsleep + * workaround undo code or resyncing timebase or restoring context + * In either case loop until the lock bit is cleared. + */ + bnel core_idle_lock_held + + cmpwi cr2,r15,0 + + /* + * At this stage + * cr2 - eq if first thread to wakeup in core + * cr3- gt if waking up with partial/complete hypervisor state loss + * cr4 - gt or eq if waking up from complete hypervisor state loss. + */ + + ori r15,r15,PNV_CORE_IDLE_LOCK_BIT + stwcx. r15,0,r14 + bne- lwarx_loop2 + isync + +BEGIN_FTR_SECTION + lbz r4,PACA_SUBCORE_SIBLING_MASK(r13) + and r4,r4,r15 + cmpwi r4,0 /* Check if first in subcore */ + + or r15,r15,r7 /* Set thread bit */ + beq first_thread_in_subcore +END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300) + + or r15,r15,r7 /* Set thread bit */ + beq cr2,first_thread_in_core + + /* Not first thread in core or subcore to wake up */ + b clear_lock + +first_thread_in_subcore: + /* + * If waking up from sleep, subcore state is not lost. Hence + * skip subcore state restore + */ + blt cr4,subcore_state_restored + + /* Restore per-subcore state */ + ld r4,_SDR1(r1) + mtspr SPRN_SDR1,r4 + + ld r4,_RPR(r1) + mtspr SPRN_RPR,r4 + ld r4,_AMOR(r1) + mtspr SPRN_AMOR,r4 + +subcore_state_restored: + /* + * Check if the thread is also the first thread in the core. If not, + * skip to clear_lock. + */ + bne cr2,clear_lock + +first_thread_in_core: + + /* + * First thread in the core waking up from any state which can cause + * partial or complete hypervisor state loss. It needs to + * call the fastsleep workaround code if the platform requires it. + * Call it unconditionally here. The below branch instruction will + * be patched out if the platform does not have fastsleep or does not + * require the workaround. Patching will be performed during the + * discovery of idle-states. + */ +.global pnv_fastsleep_workaround_at_exit +pnv_fastsleep_workaround_at_exit: + b fastsleep_workaround_at_exit + +timebase_resync: + /* + * Use cr3 which indicates that we are waking up with atleast partial + * hypervisor state loss to determine if TIMEBASE RESYNC is needed. + */ + ble cr3,clear_lock + /* Time base re-sync */ + bl opal_rm_resync_timebase; + /* + * If waking up from sleep, per core state is not lost, skip to + * clear_lock. + */ + blt cr4,clear_lock + + /* + * First thread in the core to wake up and its waking up with + * complete hypervisor state loss. Restore per core hypervisor + * state. + */ +BEGIN_FTR_SECTION + ld r4,_PTCR(r1) + mtspr SPRN_PTCR,r4 + ld r4,_RPR(r1) + mtspr SPRN_RPR,r4 +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) + + ld r4,_TSCR(r1) + mtspr SPRN_TSCR,r4 + ld r4,_WORC(r1) + mtspr SPRN_WORC,r4 + +clear_lock: + andi. r15,r15,PNV_CORE_IDLE_THREAD_BITS + lwsync + stw r15,0(r14) + +common_exit: + /* + * Common to all threads. + * + * If waking up from sleep, hypervisor state is not lost. Hence + * skip hypervisor state restore. + */ + blt cr4,hypervisor_state_restored + + /* Waking up from winkle */ + +BEGIN_MMU_FTR_SECTION + b no_segments +END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX) + /* Restore SLB from PACA */ + ld r8,PACA_SLBSHADOWPTR(r13) + + .rept SLB_NUM_BOLTED + li r3, SLBSHADOW_SAVEAREA + LDX_BE r5, r8, r3 + addi r3, r3, 8 + LDX_BE r6, r8, r3 + andis. r7,r5,SLB_ESID_V@h + beq 1f + slbmte r6,r5 +1: addi r8,r8,16 + .endr +no_segments: + + /* Restore per thread state */ + + ld r4,_SPURR(r1) + mtspr SPRN_SPURR,r4 + ld r4,_PURR(r1) + mtspr SPRN_PURR,r4 + ld r4,_DSCR(r1) + mtspr SPRN_DSCR,r4 + ld r4,_WORT(r1) + mtspr SPRN_WORT,r4 + + /* Call cur_cpu_spec->cpu_restore() */ + LOAD_REG_ADDR(r4, cur_cpu_spec) + ld r4,0(r4) + ld r12,CPU_SPEC_RESTORE(r4) +#ifdef PPC64_ELF_ABI_v1 + ld r12,0(r12) +#endif + mtctr r12 + bctrl + +hypervisor_state_restored: + + mtspr SPRN_SRR1,r16 + mtlr r17 + blr /* Return back to System Reset vector from where + pnv_restore_hyp_resource was invoked */ + +fastsleep_workaround_at_exit: + li r3,1 + li r4,0 + bl opal_rm_config_cpu_idle_state + b timebase_resync + +/* + * R3 here contains the value that will be returned to the caller + * of power7_nap. + */ +_GLOBAL(pnv_wakeup_loss) + ld r1,PACAR1(r13) +BEGIN_FTR_SECTION + CHECK_HMI_INTERRUPT +END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) + REST_NVGPRS(r1) + REST_GPR(2, r1) + ld r6,_CCR(r1) + ld r4,_MSR(r1) + ld r5,_NIP(r1) + addi r1,r1,INT_FRAME_SIZE + mtcr r6 + mtspr SPRN_SRR1,r4 + mtspr SPRN_SRR0,r5 + rfid + +/* + * R3 here contains the value that will be returned to the caller + * of power7_nap. + */ +_GLOBAL(pnv_wakeup_noloss) + lbz r0,PACA_NAPSTATELOST(r13) + cmpwi r0,0 + bne pnv_wakeup_loss +BEGIN_FTR_SECTION + CHECK_HMI_INTERRUPT +END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) + ld r1,PACAR1(r13) + ld r6,_CCR(r1) + ld r4,_MSR(r1) + ld r5,_NIP(r1) + addi r1,r1,INT_FRAME_SIZE + mtcr r6 + mtspr SPRN_SRR1,r4 + mtspr SPRN_SRR0,r5 + rfid diff --git a/arch/powerpc/kernel/iomap.c b/arch/powerpc/kernel/iomap.c index 12e48d56f..3963f0b68 100644 --- a/arch/powerpc/kernel/iomap.c +++ b/arch/powerpc/kernel/iomap.c @@ -38,6 +38,18 @@ EXPORT_SYMBOL(ioread16); EXPORT_SYMBOL(ioread16be); EXPORT_SYMBOL(ioread32); EXPORT_SYMBOL(ioread32be); +#ifdef __powerpc64__ +u64 ioread64(void __iomem *addr) +{ + return readq(addr); +} +u64 ioread64be(void __iomem *addr) +{ + return readq_be(addr); +} +EXPORT_SYMBOL(ioread64); +EXPORT_SYMBOL(ioread64be); +#endif /* __powerpc64__ */ void iowrite8(u8 val, void __iomem *addr) { @@ -64,6 +76,18 @@ EXPORT_SYMBOL(iowrite16); EXPORT_SYMBOL(iowrite16be); EXPORT_SYMBOL(iowrite32); EXPORT_SYMBOL(iowrite32be); +#ifdef __powerpc64__ +void iowrite64(u64 val, void __iomem *addr) +{ + writeq(val, addr); +} +void iowrite64be(u64 val, void __iomem *addr) +{ + writeq_be(val, addr); +} +EXPORT_SYMBOL(iowrite64); +EXPORT_SYMBOL(iowrite64be); +#endif /* __powerpc64__ */ /* * These are the "repeat read/write" functions. Note the diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index a8e3490b5..37d6e741b 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -307,7 +307,7 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl, void *page, unsigned int npages, enum dma_data_direction direction, unsigned long mask, unsigned int align_order, - struct dma_attrs *attrs) + unsigned long attrs) { unsigned long entry; dma_addr_t ret = DMA_ERROR_CODE; @@ -431,7 +431,7 @@ static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr, int ppc_iommu_map_sg(struct device *dev, struct iommu_table *tbl, struct scatterlist *sglist, int nelems, unsigned long mask, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { dma_addr_t dma_next = 0, dma_addr; struct scatterlist *s, *outs, *segstart; @@ -574,7 +574,7 @@ int ppc_iommu_map_sg(struct device *dev, struct iommu_table *tbl, void ppc_iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist, int nelems, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { struct scatterlist *sg; @@ -753,7 +753,7 @@ void iommu_free_table(struct iommu_table *tbl, const char *node_name) dma_addr_t iommu_map_page(struct device *dev, struct iommu_table *tbl, struct page *page, unsigned long offset, size_t size, unsigned long mask, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { dma_addr_t dma_handle = DMA_ERROR_CODE; void *vaddr; @@ -790,7 +790,7 @@ dma_addr_t iommu_map_page(struct device *dev, struct iommu_table *tbl, void iommu_unmap_page(struct iommu_table *tbl, dma_addr_t dma_handle, size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { unsigned int npages; @@ -845,7 +845,7 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl, nio_pages = size >> tbl->it_page_shift; io_order = get_iommu_order(size, tbl); mapping = iommu_alloc(dev, tbl, ret, nio_pages, DMA_BIDIRECTIONAL, - mask >> tbl->it_page_shift, io_order, NULL); + mask >> tbl->it_page_shift, io_order, 0); if (mapping == DMA_ERROR_CODE) { free_pages((unsigned long)ret, order); return NULL; diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 3cb46a3b1..08887cf2b 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -75,6 +75,7 @@ #endif #define CREATE_TRACE_POINTS #include <asm/trace.h> +#include <asm/cpu_has_feature.h> DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat); EXPORT_PER_CPU_SYMBOL(irq_stat); @@ -250,7 +251,7 @@ notrace void arch_local_irq_restore(unsigned long en) if (WARN_ON(mfmsr() & MSR_EE)) __hard_irq_disable(); } -#endif /* CONFIG_TRACE_IRQFLAG */ +#endif /* CONFIG_TRACE_IRQFLAGS */ set_soft_enabled(0); @@ -342,6 +343,21 @@ bool prep_irq_for_idle(void) return true; } +/* + * Force a replay of the external interrupt handler on this CPU. + */ +void force_external_irq_replay(void) +{ + /* + * This must only be called with interrupts soft-disabled, + * the replay will happen when re-enabling. + */ + WARN_ON(!arch_irqs_disabled()); + + /* Indicate in the PACA that we have an interrupt to replay */ + local_paca->irq_happened |= PACA_IRQ_EE; +} + #endif /* CONFIG_PPC64 */ int arch_show_interrupts(struct seq_file *p, int prec) diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index 7c053f281..e785cc9e1 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -29,7 +29,7 @@ #include <linux/kprobes.h> #include <linux/ptrace.h> #include <linux/preempt.h> -#include <linux/module.h> +#include <linux/extable.h> #include <linux/kdebug.h> #include <linux/slab.h> #include <asm/code-patching.h> @@ -278,12 +278,11 @@ no_kprobe: * - When the probed function returns, this probe * causes the handlers to fire */ -static void __used kretprobe_trampoline_holder(void) -{ - asm volatile(".global kretprobe_trampoline\n" - "kretprobe_trampoline:\n" - "nop\n"); -} +asm(".global kretprobe_trampoline\n" + ".type kretprobe_trampoline, @function\n" + "kretprobe_trampoline:\n" + "nop\n" + ".size kretprobe_trampoline, .-kretprobe_trampoline\n"); /* * Called when the probe at kretprobe trampoline is hit @@ -506,13 +505,11 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) /* setup return addr to the jprobe handler routine */ regs->nip = arch_deref_entry_point(jp->entry); -#ifdef CONFIG_PPC64 -#if defined(_CALL_ELF) && _CALL_ELF == 2 +#ifdef PPC64_ELF_ABI_v2 regs->gpr[12] = (unsigned long)jp->entry; -#else +#elif defined(PPC64_ELF_ABI_v1) regs->gpr[2] = (unsigned long)(((func_descr_t *)jp->entry)->toc); #endif -#endif return 1; } diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c index b8c202d63..4c780a342 100644 --- a/arch/powerpc/kernel/machine_kexec_64.c +++ b/arch/powerpc/kernel/machine_kexec_64.c @@ -29,6 +29,7 @@ #include <asm/prom.h> #include <asm/smp.h> #include <asm/hw_breakpoint.h> +#include <asm/asm-prototypes.h> #ifdef CONFIG_PPC_BOOK3E int default_machine_kexec_prepare(struct kimage *image) @@ -54,7 +55,7 @@ int default_machine_kexec_prepare(struct kimage *image) const unsigned long *basep; const unsigned int *sizep; - if (!ppc_md.hpte_clear_all) + if (!mmu_hash_ops.hpte_clear_all) return -ENOENT; /* @@ -379,7 +380,12 @@ void default_machine_kexec(struct kimage *image) */ kexec_sequence(&kexec_stack, image->start, image, page_address(image->control_code_page), - ppc_md.hpte_clear_all); +#ifdef CONFIG_PPC_STD_MMU + mmu_hash_ops.hpte_clear_all +#else + NULL +#endif + ); /* NOTREACHED */ } diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c index ef267fd9d..5e7ece0fd 100644 --- a/arch/powerpc/kernel/mce.c +++ b/arch/powerpc/kernel/mce.c @@ -92,7 +92,8 @@ void save_mce_event(struct pt_regs *regs, long handled, mce->in_use = 1; mce->initiator = MCE_INITIATOR_CPU; - if (handled) + /* Mark it recovered if we have handled it and MSR(RI=1). */ + if (handled && (regs->msr & MSR_RI)) mce->disposition = MCE_DISPOSITION_RECOVERED; else mce->disposition = MCE_DISPOSITION_NOT_RECOVERED; diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index 285ca8c6c..d9c912b6e 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -104,20 +104,6 @@ _GLOBAL(mulhdu) blr /* - * sub_reloc_offset(x) returns x - reloc_offset(). - */ -_GLOBAL(sub_reloc_offset) - mflr r0 - bl 1f -1: mflr r5 - lis r4,1b@ha - addi r4,r4,1b@l - subf r5,r4,r5 - subf r3,r5,r3 - mtlr r0 - blr - -/* * reloc_got2 runs through the .got2 section adding an offset * to each entry. */ diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index f28754c49..cb195157b 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -661,13 +661,13 @@ _GLOBAL(kexec_sequence) #ifndef CONFIG_PPC_BOOK3E /* clear out hardware hash page table and tlb */ -#if !defined(_CALL_ELF) || _CALL_ELF != 2 +#ifdef PPC64_ELF_ABI_v1 ld r12,0(r27) /* deref function descriptor */ #else mr r12,r27 #endif mtctr r12 - bctrl /* ppc_md.hpte_clear_all(void); */ + bctrl /* mmu_hash_ops.hpte_clear_all(void); */ #endif /* !CONFIG_PPC_BOOK3E */ /* diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 9ce9a25f5..183368e00 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -41,7 +41,7 @@ this, and makes other things simpler. Anton? --RR. */ -#if defined(_CALL_ELF) && _CALL_ELF == 2 +#ifdef PPC64_ELF_ABI_v2 /* An address is simply the address of the function. */ typedef unsigned long func_desc_t; @@ -132,7 +132,7 @@ static u32 ppc64_stub_insns[] = { /* Save current r2 value in magic place on the stack. */ 0xf8410000|R2_STACK_OFFSET, /* std r2,R2_STACK_OFFSET(r1) */ 0xe98b0020, /* ld r12,32(r11) */ -#if !defined(_CALL_ELF) || _CALL_ELF != 2 +#ifdef PPC64_ELF_ABI_v1 /* Set up new r2 from function descriptor */ 0xe84b0028, /* ld r2,40(r11) */ #endif @@ -494,9 +494,10 @@ static bool is_early_mcount_callsite(u32 *instruction) restore r2. */ static int restore_r2(u32 *instruction, struct module *me) { + if (is_early_mcount_callsite(instruction - 1)) + return 1; + if (*instruction != PPC_INST_NOP) { - if (is_early_mcount_callsite(instruction - 1)) - return 1; pr_err("%s: Expect noop after relocate, got %08x\n", me->name, *instruction); return 0; diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c index 856f9a794..64174bf95 100644 --- a/arch/powerpc/kernel/nvram_64.c +++ b/arch/powerpc/kernel/nvram_64.c @@ -444,7 +444,8 @@ static int nvram_pstore_write(enum pstore_type_id type, */ static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type, int *count, struct timespec *time, char **buf, - bool *compressed, struct pstore_info *psi) + bool *compressed, ssize_t *ecc_notice_size, + struct pstore_info *psi) { struct oops_log_info *oops_hdr; unsigned int err_type, id_no, size = 0; @@ -545,6 +546,7 @@ static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type, return -ENOMEM; kfree(buff); + *ecc_notice_size = 0; if (err_type == ERR_TYPE_KERNEL_PANIC_GZ) *compressed = true; else diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index 93dae296b..fa20060ff 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -184,7 +184,7 @@ 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)) + if (early_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 0f7a60f1e..e58908066 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -41,11 +41,18 @@ #include <asm/ppc-pci.h> #include <asm/eeh.h> +/* hose_spinlock protects accesses to the the phb_bitmap. */ static DEFINE_SPINLOCK(hose_spinlock); LIST_HEAD(hose_list); -/* XXX kill that some day ... */ -static int global_phb_number; /* Global phb counter */ +/* For dynamic PHB numbering on get_phb_number(): max number of PHBs. */ +#define MAX_PHBS 0x10000 + +/* + * For dynamic PHB numbering: used/free PHBs tracking bitmap. + * Accesses to this bitmap should be protected by hose_spinlock. + */ +static DECLARE_BITMAP(phb_bitmap, MAX_PHBS); /* ISA Memory physical address */ resource_size_t isa_mem_base; @@ -64,6 +71,45 @@ struct dma_map_ops *get_pci_dma_ops(void) } EXPORT_SYMBOL(get_pci_dma_ops); +/* + * This function should run under locking protection, specifically + * hose_spinlock. + */ +static int get_phb_number(struct device_node *dn) +{ + int ret, phb_id = -1; + u32 prop_32; + u64 prop; + + /* + * Try fixed PHB numbering first, by checking archs and reading + * the respective device-tree properties. Firstly, try powernv by + * reading "ibm,opal-phbid", only present in OPAL environment. + */ + ret = of_property_read_u64(dn, "ibm,opal-phbid", &prop); + if (ret) { + ret = of_property_read_u32_index(dn, "reg", 1, &prop_32); + prop = prop_32; + } + + if (!ret) + phb_id = (int)(prop & (MAX_PHBS - 1)); + + /* We need to be sure to not use the same PHB number twice. */ + if ((phb_id >= 0) && !test_and_set_bit(phb_id, phb_bitmap)) + return phb_id; + + /* + * If not pseries nor powernv, or if fixed PHB numbering tried to add + * the same PHB number twice, then fallback to dynamic PHB numbering. + */ + phb_id = find_first_zero_bit(phb_bitmap, MAX_PHBS); + BUG_ON(phb_id >= MAX_PHBS); + set_bit(phb_id, phb_bitmap); + + return phb_id; +} + struct pci_controller *pcibios_alloc_controller(struct device_node *dev) { struct pci_controller *phb; @@ -72,7 +118,7 @@ struct pci_controller *pcibios_alloc_controller(struct device_node *dev) if (phb == NULL) return NULL; spin_lock(&hose_spinlock); - phb->global_number = global_phb_number++; + phb->global_number = get_phb_number(dev); list_add_tail(&phb->list_node, &hose_list); spin_unlock(&hose_spinlock); phb->dn = dev; @@ -94,6 +140,11 @@ EXPORT_SYMBOL_GPL(pcibios_alloc_controller); void pcibios_free_controller(struct pci_controller *phb) { spin_lock(&hose_spinlock); + + /* Clear bit of phb_bitmap to allow reuse of this PHB number. */ + if (phb->global_number < MAX_PHBS) + clear_bit(phb->global_number, phb_bitmap); + list_del(&phb->list_node); spin_unlock(&hose_spinlock); @@ -103,6 +154,42 @@ void pcibios_free_controller(struct pci_controller *phb) EXPORT_SYMBOL_GPL(pcibios_free_controller); /* + * This function is used to call pcibios_free_controller() + * in a deferred manner: a callback from the PCI subsystem. + * + * _*DO NOT*_ call pcibios_free_controller() explicitly if + * this is used (or it may access an invalid *phb pointer). + * + * The callback occurs when all references to the root bus + * are dropped (e.g., child buses/devices and their users). + * + * It's called as .release_fn() of 'struct pci_host_bridge' + * which is associated with the 'struct pci_controller.bus' + * (root bus) - it expects .release_data to hold a pointer + * to 'struct pci_controller'. + * + * In order to use it, register .release_fn()/release_data + * like this: + * + * pci_set_host_bridge_release(bridge, + * pcibios_free_controller_deferred + * (void *) phb); + * + * e.g. in the pcibios_root_bridge_prepare() callback from + * pci_create_root_bus(). + */ +void pcibios_free_controller_deferred(struct pci_host_bridge *bridge) +{ + struct pci_controller *phb = (struct pci_controller *) + bridge->release_data; + + pr_debug("domain %d, dynamic %d\n", phb->global_number, phb->is_dynamic); + + pcibios_free_controller(phb); +} +EXPORT_SYMBOL_GPL(pcibios_free_controller_deferred); + +/* * The function is used to return the minimal alignment * for memory or I/O windows of the associated P2P bridge. * By default, 4KiB alignment for I/O windows and 1MiB for @@ -124,6 +211,14 @@ resource_size_t pcibios_window_alignment(struct pci_bus *bus, return 1; } +void pcibios_setup_bridge(struct pci_bus *bus, unsigned long type) +{ + struct pci_controller *hose = pci_bus_to_host(bus); + + if (hose->controller_ops.setup_bridge) + hose->controller_ops.setup_bridge(bus, type); +} + void pcibios_reset_secondary_bus(struct pci_dev *dev) { struct pci_controller *phb = pci_bus_to_host(dev->bus); @@ -356,36 +451,6 @@ static struct resource *__pci_mmap_make_offset(struct pci_dev *dev, } /* - * Set vm_page_prot of VMA, as appropriate for this architecture, for a pci - * device mapping. - */ -static pgprot_t __pci_mmap_set_pgprot(struct pci_dev *dev, struct resource *rp, - pgprot_t protection, - enum pci_mmap_state mmap_state, - int write_combine) -{ - - /* Write combine is always 0 on non-memory space mappings. On - * memory space, if the user didn't pass 1, we check for a - * "prefetchable" resource. This is a bit hackish, but we use - * this to workaround the inability of /sysfs to provide a write - * combine bit - */ - if (mmap_state != pci_mmap_mem) - write_combine = 0; - else if (write_combine == 0) { - if (rp->flags & IORESOURCE_PREFETCH) - write_combine = 1; - } - - /* XXX would be nice to have a way to ask for write-through */ - if (write_combine) - return pgprot_noncached_wc(protection); - else - return pgprot_noncached(protection); -} - -/* * This one is used by /dev/mem and fbdev who have no clue about the * PCI device, it tries to find the PCI device first and calls the * above routine @@ -458,9 +523,10 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, return -EINVAL; vma->vm_pgoff = offset >> PAGE_SHIFT; - vma->vm_page_prot = __pci_mmap_set_pgprot(dev, rp, - vma->vm_page_prot, - mmap_state, write_combine); + if (write_combine) + vma->vm_page_prot = pgprot_noncached_wc(vma->vm_page_prot); + else + vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); ret = remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff, vma->vm_end - vma->vm_start, vma->vm_page_prot); @@ -610,39 +676,25 @@ void pci_resource_to_user(const struct pci_dev *dev, int bar, const struct resource *rsrc, resource_size_t *start, resource_size_t *end) { - struct pci_controller *hose = pci_bus_to_host(dev->bus); - resource_size_t offset = 0; + struct pci_bus_region region; - if (hose == NULL) + if (rsrc->flags & IORESOURCE_IO) { + pcibios_resource_to_bus(dev->bus, ®ion, + (struct resource *) rsrc); + *start = region.start; + *end = region.end; return; + } - if (rsrc->flags & IORESOURCE_IO) - offset = (unsigned long)hose->io_base_virt - _IO_BASE; - - /* We pass a fully fixed up address to userland for MMIO instead of - * a BAR value because X is lame and expects to be able to use that - * to pass to /dev/mem ! - * - * That means that we'll have potentially 64 bits values where some - * userland apps only expect 32 (like X itself since it thinks only - * Sparc has 64 bits MMIO) but if we don't do that, we break it on - * 32 bits CHRPs :-( + /* We pass a CPU physical address to userland for MMIO instead of a + * BAR value because X is lame and expects to be able to use that + * to pass to /dev/mem! * - * Hopefully, the sysfs insterface is immune to that gunk. Once X - * has been fixed (and the fix spread enough), we can re-enable the - * 2 lines below and pass down a BAR value to userland. In that case - * we'll also have to re-enable the matching code in - * __pci_mmap_make_offset(). - * - * BenH. + * That means we may have 64-bit values where some apps only expect + * 32 (like X itself since it thinks only Sparc has 64-bit MMIO). */ -#if 0 - else if (rsrc->flags & IORESOURCE_MEM) - offset = hose->pci_mem_offset; -#endif - - *start = rsrc->start - offset; - *end = rsrc->end - offset; + *start = rsrc->start; + *end = rsrc->end; } /** @@ -1362,8 +1414,10 @@ void __init pcibios_resource_survey(void) /* Allocate and assign resources */ list_for_each_entry(b, &pci_root_buses, node) pcibios_allocate_bus_resources(b); - pcibios_allocate_resources(0); - pcibios_allocate_resources(1); + if (!pci_has_flag(PCI_REASSIGN_ALL_RSRC)) { + pcibios_allocate_resources(0); + pcibios_allocate_resources(1); + } /* Before we start assigning unassigned resource, we try to reserve * the low IO area and the VGA memory area if they intersect the @@ -1436,8 +1490,12 @@ void pcibios_finish_adding_to_bus(struct pci_bus *bus) /* Allocate bus and devices resources */ pcibios_allocate_bus_resources(bus); pcibios_claim_one_bus(bus); - if (!pci_has_flag(PCI_PROBE_ONLY)) - pci_assign_unassigned_bus_resources(bus); + if (!pci_has_flag(PCI_PROBE_ONLY)) { + if (bus->self) + pci_assign_unassigned_bridge_resources(bus->self); + else + pci_assign_unassigned_bus_resources(bus); + } /* Fixup EEH */ eeh_add_device_tree_late(bus); @@ -1485,9 +1543,9 @@ static void pcibios_setup_phb_resources(struct pci_controller *hose, res = &hose->io_resource; if (!res->flags) { - pr_info("PCI: I/O resource not set for host" - " bridge %s (domain %d)\n", - hose->dn->full_name, hose->global_number); + pr_debug("PCI: I/O resource not set for host" + " bridge %s (domain %d)\n", + hose->dn->full_name, hose->global_number); } else { offset = pcibios_io_space_offset(hose); diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index a5ae49a2d..ed5e9ff61 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -81,7 +81,7 @@ int pcibios_unmap_io_space(struct pci_bus *bus) /* If this is not a PHB, we only flush the hash table over * the area mapped by this bridge. We don't play with the PTE - * mappings since we might have to deal with sub-page alignemnts + * mappings since we might have to deal with sub-page alignments * so flushing the hash table is the only sane way to make sure * that no hash entries are covering that removed bridge area * while still allowing other busses overlapping those pages diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c index ecdccce78..592693437 100644 --- a/arch/powerpc/kernel/pci_dn.c +++ b/arch/powerpc/kernel/pci_dn.c @@ -31,6 +31,7 @@ #include <asm/pci-bridge.h> #include <asm/ppc-pci.h> #include <asm/firmware.h> +#include <asm/eeh.h> /* * The function is used to find the firmware data of one @@ -181,7 +182,6 @@ struct pci_dn *add_dev_pci_data(struct pci_dev *pdev) { #ifdef CONFIG_PCI_IOV struct pci_dn *parent, *pdn; - struct eeh_dev *edev; int i; /* Only support IOV for now */ @@ -199,6 +199,8 @@ struct pci_dn *add_dev_pci_data(struct pci_dev *pdev) return NULL; for (i = 0; i < pci_sriov_get_totalvfs(pdev); i++) { + struct eeh_dev *edev __maybe_unused; + pdn = add_one_dev_pci_data(parent, NULL, i, pci_iov_virtfn_bus(pdev, i), pci_iov_virtfn_devfn(pdev, i)); @@ -208,11 +210,12 @@ struct pci_dn *add_dev_pci_data(struct pci_dev *pdev) return NULL; } +#ifdef CONFIG_EEH /* Create the EEH device for the VF */ - eeh_dev_init(pdn, pci_bus_to_host(pdev->bus)); - edev = pdn_to_eeh_dev(pdn); + edev = eeh_dev_init(pdn); BUG_ON(!edev); edev->physfn = pdev; +#endif /* CONFIG_EEH */ } #endif /* CONFIG_PCI_IOV */ @@ -224,7 +227,6 @@ void remove_dev_pci_data(struct pci_dev *pdev) #ifdef CONFIG_PCI_IOV struct pci_dn *parent; struct pci_dn *pdn, *tmp; - struct eeh_dev *edev; int i; /* @@ -260,18 +262,22 @@ void remove_dev_pci_data(struct pci_dev *pdev) * a batch mode. */ for (i = 0; i < pci_sriov_get_totalvfs(pdev); i++) { + struct eeh_dev *edev __maybe_unused; + list_for_each_entry_safe(pdn, tmp, &parent->child_list, list) { if (pdn->busno != pci_iov_virtfn_bus(pdev, i) || pdn->devfn != pci_iov_virtfn_devfn(pdev, i)) continue; +#ifdef CONFIG_EEH /* Release EEH device for the VF */ edev = pdn_to_eeh_dev(pdn); if (edev) { pdn->edev = NULL; kfree(edev); } +#endif /* CONFIG_EEH */ if (!list_empty(&pdn->list)) list_del(&pdn->list); @@ -289,8 +295,11 @@ struct pci_dn *pci_add_device_node_info(struct pci_controller *hose, const __be32 *regs; struct device_node *parent; struct pci_dn *pdn; +#ifdef CONFIG_EEH + struct eeh_dev *edev; +#endif - pdn = zalloc_maybe_bootmem(sizeof(*pdn), GFP_KERNEL); + pdn = kzalloc(sizeof(*pdn), GFP_KERNEL); if (pdn == NULL) return NULL; dn->data = pdn; @@ -319,6 +328,15 @@ struct pci_dn *pci_add_device_node_info(struct pci_controller *hose, /* Extended config space */ pdn->pci_ext_config_space = (type && of_read_number(type, 1) == 1); + /* Create EEH device */ +#ifdef CONFIG_EEH + edev = eeh_dev_init(pdn); + if (!edev) { + kfree(pdn); + return NULL; + } +#endif + /* Attach to parent node */ INIT_LIST_HEAD(&pdn->child_list); INIT_LIST_HEAD(&pdn->list); @@ -504,15 +522,19 @@ void pci_devs_phb_init_dynamic(struct pci_controller *phb) * pci device found underneath. This routine runs once, * early in the boot sequence. */ -void __init pci_devs_phb_init(void) +static int __init pci_devs_phb_init(void) { struct pci_controller *phb, *tmp; /* This must be done first so the device nodes have valid pci info! */ list_for_each_entry_safe(phb, tmp, &hose_list, list_node) pci_devs_phb_init_dynamic(phb); + + return 0; } +core_initcall(pci_devs_phb_init); + static void pci_dev_pdn_setup(struct pci_dev *pdev) { struct pci_dn *pdn; diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 0b9389342..9ee2623e0 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -58,6 +58,7 @@ #include <asm/code-patching.h> #include <asm/exec.h> #include <asm/livepatch.h> +#include <asm/cpu_has_feature.h> #include <linux/kprobes.h> #include <linux/kdebug.h> @@ -139,12 +140,16 @@ EXPORT_SYMBOL(__msr_check_and_clear); #ifdef CONFIG_PPC_FPU void __giveup_fpu(struct task_struct *tsk) { + unsigned long msr; + save_fpu(tsk); - tsk->thread.regs->msr &= ~MSR_FP; + msr = tsk->thread.regs->msr; + msr &= ~MSR_FP; #ifdef CONFIG_VSX if (cpu_has_feature(CPU_FTR_VSX)) - tsk->thread.regs->msr &= ~MSR_VSX; + msr &= ~MSR_VSX; #endif + tsk->thread.regs->msr = msr; } void giveup_fpu(struct task_struct *tsk) @@ -219,12 +224,16 @@ static int restore_fp(struct task_struct *tsk) { return 0; } static void __giveup_altivec(struct task_struct *tsk) { + unsigned long msr; + save_altivec(tsk); - tsk->thread.regs->msr &= ~MSR_VEC; + msr = tsk->thread.regs->msr; + msr &= ~MSR_VEC; #ifdef CONFIG_VSX if (cpu_has_feature(CPU_FTR_VSX)) - tsk->thread.regs->msr &= ~MSR_VSX; + msr &= ~MSR_VSX; #endif + tsk->thread.regs->msr = msr; } void giveup_altivec(struct task_struct *tsk) @@ -794,7 +803,7 @@ static void tm_reclaim_thread(struct thread_struct *thr, * this state. * We do this using the current MSR, rather tracking it in * some specific thread_struct bit, as it has the additional - * benifit of checking for a potential TM bad thing exception. + * benefit of checking for a potential TM bad thing exception. */ if (!MSR_TM_SUSPENDED(mfmsr())) return; @@ -1009,6 +1018,14 @@ static inline void save_sprs(struct thread_struct *t) */ t->tar = mfspr(SPRN_TAR); } + + if (cpu_has_feature(CPU_FTR_ARCH_300)) { + /* Conditionally save Load Monitor registers, if enabled */ + if (t->fscr & FSCR_LM) { + t->lmrr = mfspr(SPRN_LMRR); + t->lmser = mfspr(SPRN_LMSER); + } + } #endif } @@ -1023,18 +1040,11 @@ static inline void restore_sprs(struct thread_struct *old_thread, #ifdef CONFIG_PPC_BOOK3S_64 if (cpu_has_feature(CPU_FTR_DSCR)) { u64 dscr = get_paca()->dscr_default; - u64 fscr = old_thread->fscr & ~FSCR_DSCR; - - if (new_thread->dscr_inherit) { + if (new_thread->dscr_inherit) dscr = new_thread->dscr; - fscr |= FSCR_DSCR; - } if (old_thread->dscr != dscr) mtspr(SPRN_DSCR, dscr); - - if (old_thread->fscr != fscr) - mtspr(SPRN_FSCR, fscr); } if (cpu_has_feature(CPU_FTR_ARCH_207S)) { @@ -1045,9 +1055,22 @@ static inline void restore_sprs(struct thread_struct *old_thread, if (old_thread->ebbrr != new_thread->ebbrr) mtspr(SPRN_EBBRR, new_thread->ebbrr); + if (old_thread->fscr != new_thread->fscr) + mtspr(SPRN_FSCR, new_thread->fscr); + if (old_thread->tar != new_thread->tar) mtspr(SPRN_TAR, new_thread->tar); } + + if (cpu_has_feature(CPU_FTR_ARCH_300)) { + /* Conditionally restore Load Monitor registers, if enabled */ + if (new_thread->fscr & FSCR_LM) { + if (old_thread->lmrr != new_thread->lmrr) + mtspr(SPRN_LMRR, new_thread->lmrr); + if (old_thread->lmser != new_thread->lmser) + mtspr(SPRN_LMSER, new_thread->lmser); + } + } #endif } diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 946e34ffe..b0245bed6 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -56,6 +56,8 @@ #include <asm/opal.h> #include <asm/fadump.h> #include <asm/debug.h> +#include <asm/epapr_hcalls.h> +#include <asm/firmware.h> #include <mm/mmu_decl.h> @@ -168,7 +170,7 @@ static struct ibm_pa_feature { */ {CPU_FTR_TM_COMP, 0, 0, PPC_FEATURE2_HTM_COMP|PPC_FEATURE2_HTM_NOSC_COMP, 22, 0, 0}, - {0, MMU_FTR_RADIX, 0, 0, 40, 0, 0}, + {0, MMU_FTR_TYPE_RADIX, 0, 0, 40, 0, 0}, }; static void __init scan_features(unsigned long node, const unsigned char *ftrs, @@ -735,10 +737,22 @@ void __init early_init_devtree(void *params) spinning_secondaries = boot_cpu_count - 1; #endif + mmu_early_init_devtree(); + #ifdef CONFIG_PPC_POWERNV /* Scan and build the list of machine check recoverable ranges */ of_scan_flat_dt(early_init_dt_scan_recoverable_ranges, NULL); #endif + epapr_paravirt_early_init(); + + /* Now try to figure out if we are running on LPAR and so on */ + pseries_probe_fw_features(); + +#ifdef CONFIG_PPC_PS3 + /* Identify PS3 firmware */ + if (of_flat_dt_is_compatible(of_get_flat_dt_root(), "sony,ps3")) + powerpc_firmware_features |= FW_FEATURE_PS3_POSSIBLE; +#endif DBG(" <- early_init_devtree()\n"); } diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 6ee4b72cd..d3eff99e9 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -695,7 +695,7 @@ unsigned char ibm_architecture_vec[] = { OV4_MIN_ENT_CAP, /* minimum VP entitled capacity */ /* option vector 5: PAPR/OF options */ - VECTOR_LENGTH(18), /* length */ + VECTOR_LENGTH(21), /* length */ 0, /* don't ignore, don't halt */ OV5_FEAT(OV5_LPAR) | OV5_FEAT(OV5_SPLPAR) | OV5_FEAT(OV5_LARGE_PAGES) | OV5_FEAT(OV5_DRCONF_MEMORY) | OV5_FEAT(OV5_DONATE_DEDICATE_CPU) | @@ -726,8 +726,11 @@ unsigned char ibm_architecture_vec[] = { 0, 0, OV5_FEAT(OV5_PFO_HW_RNG) | OV5_FEAT(OV5_PFO_HW_ENCR) | - OV5_FEAT(OV5_PFO_HW_842), - OV5_FEAT(OV5_SUB_PROCESSORS), + OV5_FEAT(OV5_PFO_HW_842), /* Byte 17 */ + 0, /* Byte 18 */ + 0, /* Byte 19 */ + 0, /* Byte 20 */ + OV5_FEAT(OV5_SUB_PROCESSORS), /* Byte 21 */ /* option vector 6: IBM PAPR hints */ VECTOR_LENGTH(3), /* length */ @@ -2940,7 +2943,7 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4, /* Don't print anything after quiesce under OPAL, it crashes OFW */ if (of_platform != PLATFORM_OPAL) { - prom_printf("Booting Linux via __start() ...\n"); + prom_printf("Booting Linux via __start() @ 0x%lx ...\n", kbase); prom_debug("->dt_header_start=0x%x\n", hdr); } diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index 060b140f0..bf91658a8 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -38,6 +38,7 @@ #include <asm/page.h> #include <asm/pgtable.h> #include <asm/switch_to.h> +#include <asm/tm.h> #define CREATE_TRACE_POINTS #include <trace/events/syscalls.h> @@ -64,6 +65,10 @@ struct pt_regs_offset { {.name = STR(gpr##num), .offset = offsetof(struct pt_regs, gpr[num])} #define REG_OFFSET_END {.name = NULL, .offset = 0} +#define TVSO(f) (offsetof(struct thread_vr_state, f)) +#define TFSO(f) (offsetof(struct thread_fp_state, f)) +#define TSO(f) (offsetof(struct thread_struct, f)) + static const struct pt_regs_offset regoffset_table[] = { GPR_OFFSET_NAME(0), GPR_OFFSET_NAME(1), @@ -114,6 +119,24 @@ static const struct pt_regs_offset regoffset_table[] = { REG_OFFSET_END, }; +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM +static void flush_tmregs_to_thread(struct task_struct *tsk) +{ + /* + * If task is not current, it will have been flushed already to + * it's thread_struct during __switch_to(). + * + * A reclaim flushes ALL the state. + */ + + if (tsk == current && MSR_TM_SUSPENDED(mfmsr())) + tm_reclaim_current(TM_CAUSE_SIGNAL); + +} +#else +static inline void flush_tmregs_to_thread(struct task_struct *tsk) { } +#endif + /** * regs_query_register_offset() - query register offset from its name * @name: the name of a register @@ -181,6 +204,26 @@ static int set_user_msr(struct task_struct *task, unsigned long msr) return 0; } +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM +static unsigned long get_user_ckpt_msr(struct task_struct *task) +{ + return task->thread.ckpt_regs.msr | task->thread.fpexc_mode; +} + +static int set_user_ckpt_msr(struct task_struct *task, unsigned long msr) +{ + task->thread.ckpt_regs.msr &= ~MSR_DEBUGCHANGE; + task->thread.ckpt_regs.msr |= msr & MSR_DEBUGCHANGE; + return 0; +} + +static int set_user_ckpt_trap(struct task_struct *task, unsigned long trap) +{ + task->thread.ckpt_regs.trap = trap & 0xfff0; + return 0; +} +#endif + #ifdef CONFIG_PPC64 static int get_user_dscr(struct task_struct *task, unsigned long *data) { @@ -358,6 +401,29 @@ static int gpr_set(struct task_struct *target, const struct user_regset *regset, return ret; } +/* + * When the transaction is active, 'transact_fp' holds the current running + * value of all FPR registers and 'fp_state' holds the last checkpointed + * value of all FPR registers for the current transaction. When transaction + * is not active 'fp_state' holds the current running state of all the FPR + * registers. So this function which returns the current running values of + * all the FPR registers, needs to know whether any transaction is active + * or not. + * + * Userspace interface buffer layout: + * + * struct data { + * u64 fpr[32]; + * u64 fpscr; + * }; + * + * There are two config options CONFIG_VSX and CONFIG_PPC_TRANSACTIONAL_MEM + * which determines the final code in this function. All the combinations of + * these two config options are possible except the one below as transactional + * memory config pulls in CONFIG_VSX automatically. + * + * !defined(CONFIG_VSX) && defined(CONFIG_PPC_TRANSACTIONAL_MEM) + */ static int fpr_get(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf) @@ -368,14 +434,31 @@ static int fpr_get(struct task_struct *target, const struct user_regset *regset, #endif flush_fp_to_thread(target); -#ifdef CONFIG_VSX +#if defined(CONFIG_VSX) && defined(CONFIG_PPC_TRANSACTIONAL_MEM) + /* copy to local buffer then write that out */ + if (MSR_TM_ACTIVE(target->thread.regs->msr)) { + flush_altivec_to_thread(target); + flush_tmregs_to_thread(target); + for (i = 0; i < 32 ; i++) + buf[i] = target->thread.TS_TRANS_FPR(i); + buf[32] = target->thread.transact_fp.fpscr; + } else { + for (i = 0; i < 32 ; i++) + buf[i] = target->thread.TS_FPR(i); + buf[32] = target->thread.fp_state.fpscr; + } + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, buf, 0, -1); +#endif + +#if defined(CONFIG_VSX) && !defined(CONFIG_PPC_TRANSACTIONAL_MEM) /* copy to local buffer then write that out */ for (i = 0; i < 32 ; i++) buf[i] = target->thread.TS_FPR(i); buf[32] = target->thread.fp_state.fpscr; return user_regset_copyout(&pos, &count, &kbuf, &ubuf, buf, 0, -1); +#endif -#else +#if !defined(CONFIG_VSX) && !defined(CONFIG_PPC_TRANSACTIONAL_MEM) BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) != offsetof(struct thread_fp_state, fpr[32])); @@ -384,6 +467,29 @@ static int fpr_get(struct task_struct *target, const struct user_regset *regset, #endif } +/* + * When the transaction is active, 'transact_fp' holds the current running + * value of all FPR registers and 'fp_state' holds the last checkpointed + * value of all FPR registers for the current transaction. When transaction + * is not active 'fp_state' holds the current running state of all the FPR + * registers. So this function which setss the current running values of + * all the FPR registers, needs to know whether any transaction is active + * or not. + * + * Userspace interface buffer layout: + * + * struct data { + * u64 fpr[32]; + * u64 fpscr; + * }; + * + * There are two config options CONFIG_VSX and CONFIG_PPC_TRANSACTIONAL_MEM + * which determines the final code in this function. All the combinations of + * these two config options are possible except the one below as transactional + * memory config pulls in CONFIG_VSX automatically. + * + * !defined(CONFIG_VSX) && defined(CONFIG_PPC_TRANSACTIONAL_MEM) + */ static int fpr_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) @@ -394,7 +500,27 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset, #endif flush_fp_to_thread(target); -#ifdef CONFIG_VSX +#if defined(CONFIG_VSX) && defined(CONFIG_PPC_TRANSACTIONAL_MEM) + /* copy to local buffer then write that out */ + i = user_regset_copyin(&pos, &count, &kbuf, &ubuf, buf, 0, -1); + if (i) + return i; + + if (MSR_TM_ACTIVE(target->thread.regs->msr)) { + flush_altivec_to_thread(target); + flush_tmregs_to_thread(target); + for (i = 0; i < 32 ; i++) + target->thread.TS_TRANS_FPR(i) = buf[i]; + target->thread.transact_fp.fpscr = buf[32]; + } else { + for (i = 0; i < 32 ; i++) + target->thread.TS_FPR(i) = buf[i]; + target->thread.fp_state.fpscr = buf[32]; + } + return 0; +#endif + +#if defined(CONFIG_VSX) && !defined(CONFIG_PPC_TRANSACTIONAL_MEM) /* copy to local buffer then write that out */ i = user_regset_copyin(&pos, &count, &kbuf, &ubuf, buf, 0, -1); if (i) @@ -403,7 +529,9 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset, target->thread.TS_FPR(i) = buf[i]; target->thread.fp_state.fpscr = buf[32]; return 0; -#else +#endif + +#if !defined(CONFIG_VSX) && !defined(CONFIG_PPC_TRANSACTIONAL_MEM) BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) != offsetof(struct thread_fp_state, fpr[32])); @@ -433,10 +561,28 @@ static int vr_active(struct task_struct *target, return target->thread.used_vr ? regset->n : 0; } +/* + * When the transaction is active, 'transact_vr' holds the current running + * value of all the VMX registers and 'vr_state' holds the last checkpointed + * value of all the VMX registers for the current transaction to fall back + * on in case it aborts. When transaction is not active 'vr_state' holds + * the current running state of all the VMX registers. So this function which + * gets the current running values of all the VMX registers, needs to know + * whether any transaction is active or not. + * + * Userspace interface buffer layout: + * + * struct data { + * vector128 vr[32]; + * vector128 vscr; + * vector128 vrsave; + * }; + */ static int vr_get(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf) { + struct thread_vr_state *addr; int ret; flush_altivec_to_thread(target); @@ -444,8 +590,19 @@ static int vr_get(struct task_struct *target, const struct user_regset *regset, BUILD_BUG_ON(offsetof(struct thread_vr_state, vscr) != offsetof(struct thread_vr_state, vr[32])); +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (MSR_TM_ACTIVE(target->thread.regs->msr)) { + flush_fp_to_thread(target); + flush_tmregs_to_thread(target); + addr = &target->thread.transact_vr; + } else { + addr = &target->thread.vr_state; + } +#else + addr = &target->thread.vr_state; +#endif ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, - &target->thread.vr_state, 0, + addr, 0, 33 * sizeof(vector128)); if (!ret) { /* @@ -456,7 +613,16 @@ static int vr_get(struct task_struct *target, const struct user_regset *regset, u32 word; } vrsave; memset(&vrsave, 0, sizeof(vrsave)); + +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (MSR_TM_ACTIVE(target->thread.regs->msr)) + vrsave.word = target->thread.transact_vrsave; + else + vrsave.word = target->thread.vrsave; +#else vrsave.word = target->thread.vrsave; +#endif + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &vrsave, 33 * sizeof(vector128), -1); } @@ -464,10 +630,28 @@ static int vr_get(struct task_struct *target, const struct user_regset *regset, return ret; } +/* + * When the transaction is active, 'transact_vr' holds the current running + * value of all the VMX registers and 'vr_state' holds the last checkpointed + * value of all the VMX registers for the current transaction to fall back + * on in case it aborts. When transaction is not active 'vr_state' holds + * the current running state of all the VMX registers. So this function which + * sets the current running values of all the VMX registers, needs to know + * whether any transaction is active or not. + * + * Userspace interface buffer layout: + * + * struct data { + * vector128 vr[32]; + * vector128 vscr; + * vector128 vrsave; + * }; + */ static int vr_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { + struct thread_vr_state *addr; int ret; flush_altivec_to_thread(target); @@ -475,8 +659,19 @@ static int vr_set(struct task_struct *target, const struct user_regset *regset, BUILD_BUG_ON(offsetof(struct thread_vr_state, vscr) != offsetof(struct thread_vr_state, vr[32])); +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (MSR_TM_ACTIVE(target->thread.regs->msr)) { + flush_fp_to_thread(target); + flush_tmregs_to_thread(target); + addr = &target->thread.transact_vr; + } else { + addr = &target->thread.vr_state; + } +#else + addr = &target->thread.vr_state; +#endif ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, - &target->thread.vr_state, 0, + addr, 0, 33 * sizeof(vector128)); if (!ret && count > 0) { /* @@ -487,11 +682,28 @@ static int vr_set(struct task_struct *target, const struct user_regset *regset, u32 word; } vrsave; memset(&vrsave, 0, sizeof(vrsave)); + +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (MSR_TM_ACTIVE(target->thread.regs->msr)) + vrsave.word = target->thread.transact_vrsave; + else + vrsave.word = target->thread.vrsave; +#else vrsave.word = target->thread.vrsave; +#endif ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &vrsave, 33 * sizeof(vector128), -1); - if (!ret) + if (!ret) { + +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (MSR_TM_ACTIVE(target->thread.regs->msr)) + target->thread.transact_vrsave = vrsave.word; + else + target->thread.vrsave = vrsave.word; +#else target->thread.vrsave = vrsave.word; +#endif + } } return ret; @@ -512,6 +724,21 @@ static int vsr_active(struct task_struct *target, return target->thread.used_vsr ? regset->n : 0; } +/* + * When the transaction is active, 'transact_fp' holds the current running + * value of all FPR registers and 'fp_state' holds the last checkpointed + * value of all FPR registers for the current transaction. When transaction + * is not active 'fp_state' holds the current running state of all the FPR + * registers. So this function which returns the current running values of + * all the FPR registers, needs to know whether any transaction is active + * or not. + * + * Userspace interface buffer layout: + * + * struct data { + * u64 vsx[32]; + * }; + */ static int vsr_get(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf) @@ -519,16 +746,47 @@ static int vsr_get(struct task_struct *target, const struct user_regset *regset, u64 buf[32]; int ret, i; +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + flush_fp_to_thread(target); + flush_altivec_to_thread(target); + flush_tmregs_to_thread(target); +#endif flush_vsx_to_thread(target); +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (MSR_TM_ACTIVE(target->thread.regs->msr)) { + for (i = 0; i < 32 ; i++) + buf[i] = target->thread. + transact_fp.fpr[i][TS_VSRLOWOFFSET]; + } else { + for (i = 0; i < 32 ; i++) + buf[i] = target->thread. + fp_state.fpr[i][TS_VSRLOWOFFSET]; + } +#else for (i = 0; i < 32 ; i++) buf[i] = target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET]; +#endif ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, buf, 0, 32 * sizeof(double)); return ret; } +/* + * When the transaction is active, 'transact_fp' holds the current running + * value of all FPR registers and 'fp_state' holds the last checkpointed + * value of all FPR registers for the current transaction. When transaction + * is not active 'fp_state' holds the current running state of all the FPR + * registers. So this function which sets the current running values of all + * the FPR registers, needs to know whether any transaction is active or not. + * + * Userspace interface buffer layout: + * + * struct data { + * u64 vsx[32]; + * }; + */ static int vsr_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) @@ -536,12 +794,30 @@ static int vsr_set(struct task_struct *target, const struct user_regset *regset, u64 buf[32]; int ret,i; +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + flush_fp_to_thread(target); + flush_altivec_to_thread(target); + flush_tmregs_to_thread(target); +#endif flush_vsx_to_thread(target); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, buf, 0, 32 * sizeof(double)); + +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (MSR_TM_ACTIVE(target->thread.regs->msr)) { + for (i = 0; i < 32 ; i++) + target->thread.transact_fp. + fpr[i][TS_VSRLOWOFFSET] = buf[i]; + } else { + for (i = 0; i < 32 ; i++) + target->thread.fp_state. + fpr[i][TS_VSRLOWOFFSET] = buf[i]; + } +#else for (i = 0; i < 32 ; i++) target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = buf[i]; +#endif return ret; @@ -614,8 +890,1030 @@ static int evr_set(struct task_struct *target, const struct user_regset *regset, } #endif /* CONFIG_SPE */ +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM +/** + * tm_cgpr_active - get active number of registers in CGPR + * @target: The target task. + * @regset: The user regset structure. + * + * This function checks for the active number of available + * regisers in transaction checkpointed GPR category. + */ +static int tm_cgpr_active(struct task_struct *target, + const struct user_regset *regset) +{ + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return 0; + + return regset->n; +} + +/** + * tm_cgpr_get - get CGPR registers + * @target: The target task. + * @regset: The user regset structure. + * @pos: The buffer position. + * @count: Number of bytes to copy. + * @kbuf: Kernel buffer to copy from. + * @ubuf: User buffer to copy into. + * + * This function gets transaction checkpointed GPR registers. + * + * When the transaction is active, 'ckpt_regs' holds all the checkpointed + * GPR register values for the current transaction to fall back on if it + * aborts in between. This function gets those checkpointed GPR registers. + * The userspace interface buffer layout is as follows. + * + * struct data { + * struct pt_regs ckpt_regs; + * }; + */ +static int tm_cgpr_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + int ret; + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return -ENODATA; + + flush_fp_to_thread(target); + flush_altivec_to_thread(target); + flush_tmregs_to_thread(target); + + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.ckpt_regs, + 0, offsetof(struct pt_regs, msr)); + if (!ret) { + unsigned long msr = get_user_ckpt_msr(target); + + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &msr, + offsetof(struct pt_regs, msr), + offsetof(struct pt_regs, msr) + + sizeof(msr)); + } + + BUILD_BUG_ON(offsetof(struct pt_regs, orig_gpr3) != + offsetof(struct pt_regs, msr) + sizeof(long)); + + if (!ret) + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.ckpt_regs.orig_gpr3, + offsetof(struct pt_regs, orig_gpr3), + sizeof(struct pt_regs)); + if (!ret) + ret = user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf, + sizeof(struct pt_regs), -1); + + return ret; +} /* + * tm_cgpr_set - set the CGPR registers + * @target: The target task. + * @regset: The user regset structure. + * @pos: The buffer position. + * @count: Number of bytes to copy. + * @kbuf: Kernel buffer to copy into. + * @ubuf: User buffer to copy from. + * + * This function sets in transaction checkpointed GPR registers. + * + * When the transaction is active, 'ckpt_regs' holds the checkpointed + * GPR register values for the current transaction to fall back on if it + * aborts in between. This function sets those checkpointed GPR registers. + * The userspace interface buffer layout is as follows. + * + * struct data { + * struct pt_regs ckpt_regs; + * }; + */ +static int tm_cgpr_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + unsigned long reg; + int ret; + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return -ENODATA; + + flush_fp_to_thread(target); + flush_altivec_to_thread(target); + flush_tmregs_to_thread(target); + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.ckpt_regs, + 0, PT_MSR * sizeof(reg)); + + if (!ret && count > 0) { + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, ®, + PT_MSR * sizeof(reg), + (PT_MSR + 1) * sizeof(reg)); + if (!ret) + ret = set_user_ckpt_msr(target, reg); + } + + BUILD_BUG_ON(offsetof(struct pt_regs, orig_gpr3) != + offsetof(struct pt_regs, msr) + sizeof(long)); + + if (!ret) + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.ckpt_regs.orig_gpr3, + PT_ORIG_R3 * sizeof(reg), + (PT_MAX_PUT_REG + 1) * sizeof(reg)); + + if (PT_MAX_PUT_REG + 1 < PT_TRAP && !ret) + ret = user_regset_copyin_ignore( + &pos, &count, &kbuf, &ubuf, + (PT_MAX_PUT_REG + 1) * sizeof(reg), + PT_TRAP * sizeof(reg)); + + if (!ret && count > 0) { + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, ®, + PT_TRAP * sizeof(reg), + (PT_TRAP + 1) * sizeof(reg)); + if (!ret) + ret = set_user_ckpt_trap(target, reg); + } + + if (!ret) + ret = user_regset_copyin_ignore( + &pos, &count, &kbuf, &ubuf, + (PT_TRAP + 1) * sizeof(reg), -1); + + return ret; +} + +/** + * tm_cfpr_active - get active number of registers in CFPR + * @target: The target task. + * @regset: The user regset structure. + * + * This function checks for the active number of available + * regisers in transaction checkpointed FPR category. + */ +static int tm_cfpr_active(struct task_struct *target, + const struct user_regset *regset) +{ + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return 0; + + return regset->n; +} + +/** + * tm_cfpr_get - get CFPR registers + * @target: The target task. + * @regset: The user regset structure. + * @pos: The buffer position. + * @count: Number of bytes to copy. + * @kbuf: Kernel buffer to copy from. + * @ubuf: User buffer to copy into. + * + * This function gets in transaction checkpointed FPR registers. + * + * When the transaction is active 'fp_state' holds the checkpointed + * values for the current transaction to fall back on if it aborts + * in between. This function gets those checkpointed FPR registers. + * The userspace interface buffer layout is as follows. + * + * struct data { + * u64 fpr[32]; + * u64 fpscr; + *}; + */ +static int tm_cfpr_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + u64 buf[33]; + int i; + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return -ENODATA; + + flush_fp_to_thread(target); + flush_altivec_to_thread(target); + flush_tmregs_to_thread(target); + + /* copy to local buffer then write that out */ + for (i = 0; i < 32 ; i++) + buf[i] = target->thread.TS_FPR(i); + buf[32] = target->thread.fp_state.fpscr; + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, buf, 0, -1); +} + +/** + * tm_cfpr_set - set CFPR registers + * @target: The target task. + * @regset: The user regset structure. + * @pos: The buffer position. + * @count: Number of bytes to copy. + * @kbuf: Kernel buffer to copy into. + * @ubuf: User buffer to copy from. + * + * This function sets in transaction checkpointed FPR registers. + * + * When the transaction is active 'fp_state' holds the checkpointed + * FPR register values for the current transaction to fall back on + * if it aborts in between. This function sets these checkpointed + * FPR registers. The userspace interface buffer layout is as follows. + * + * struct data { + * u64 fpr[32]; + * u64 fpscr; + *}; + */ +static int tm_cfpr_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + u64 buf[33]; + int i; + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return -ENODATA; + + flush_fp_to_thread(target); + flush_altivec_to_thread(target); + flush_tmregs_to_thread(target); + + /* copy to local buffer then write that out */ + i = user_regset_copyin(&pos, &count, &kbuf, &ubuf, buf, 0, -1); + if (i) + return i; + for (i = 0; i < 32 ; i++) + target->thread.TS_FPR(i) = buf[i]; + target->thread.fp_state.fpscr = buf[32]; + return 0; +} + +/** + * tm_cvmx_active - get active number of registers in CVMX + * @target: The target task. + * @regset: The user regset structure. + * + * This function checks for the active number of available + * regisers in checkpointed VMX category. + */ +static int tm_cvmx_active(struct task_struct *target, + const struct user_regset *regset) +{ + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return 0; + + return regset->n; +} + +/** + * tm_cvmx_get - get CMVX registers + * @target: The target task. + * @regset: The user regset structure. + * @pos: The buffer position. + * @count: Number of bytes to copy. + * @kbuf: Kernel buffer to copy from. + * @ubuf: User buffer to copy into. + * + * This function gets in transaction checkpointed VMX registers. + * + * When the transaction is active 'vr_state' and 'vr_save' hold + * the checkpointed values for the current transaction to fall + * back on if it aborts in between. The userspace interface buffer + * layout is as follows. + * + * struct data { + * vector128 vr[32]; + * vector128 vscr; + * vector128 vrsave; + *}; + */ +static int tm_cvmx_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + int ret; + + BUILD_BUG_ON(TVSO(vscr) != TVSO(vr[32])); + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return -ENODATA; + + /* Flush the state */ + flush_fp_to_thread(target); + flush_altivec_to_thread(target); + flush_tmregs_to_thread(target); + + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.vr_state, 0, + 33 * sizeof(vector128)); + if (!ret) { + /* + * Copy out only the low-order word of vrsave. + */ + union { + elf_vrreg_t reg; + u32 word; + } vrsave; + memset(&vrsave, 0, sizeof(vrsave)); + vrsave.word = target->thread.vrsave; + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &vrsave, + 33 * sizeof(vector128), -1); + } + + return ret; +} + +/** + * tm_cvmx_set - set CMVX registers + * @target: The target task. + * @regset: The user regset structure. + * @pos: The buffer position. + * @count: Number of bytes to copy. + * @kbuf: Kernel buffer to copy into. + * @ubuf: User buffer to copy from. + * + * This function sets in transaction checkpointed VMX registers. + * + * When the transaction is active 'vr_state' and 'vr_save' hold + * the checkpointed values for the current transaction to fall + * back on if it aborts in between. The userspace interface buffer + * layout is as follows. + * + * struct data { + * vector128 vr[32]; + * vector128 vscr; + * vector128 vrsave; + *}; + */ +static int tm_cvmx_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + + BUILD_BUG_ON(TVSO(vscr) != TVSO(vr[32])); + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return -ENODATA; + + flush_fp_to_thread(target); + flush_altivec_to_thread(target); + flush_tmregs_to_thread(target); + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.vr_state, 0, + 33 * sizeof(vector128)); + if (!ret && count > 0) { + /* + * We use only the low-order word of vrsave. + */ + union { + elf_vrreg_t reg; + u32 word; + } vrsave; + memset(&vrsave, 0, sizeof(vrsave)); + vrsave.word = target->thread.vrsave; + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &vrsave, + 33 * sizeof(vector128), -1); + if (!ret) + target->thread.vrsave = vrsave.word; + } + + return ret; +} + +/** + * tm_cvsx_active - get active number of registers in CVSX + * @target: The target task. + * @regset: The user regset structure. + * + * This function checks for the active number of available + * regisers in transaction checkpointed VSX category. + */ +static int tm_cvsx_active(struct task_struct *target, + const struct user_regset *regset) +{ + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return 0; + + flush_vsx_to_thread(target); + return target->thread.used_vsr ? regset->n : 0; +} + +/** + * tm_cvsx_get - get CVSX registers + * @target: The target task. + * @regset: The user regset structure. + * @pos: The buffer position. + * @count: Number of bytes to copy. + * @kbuf: Kernel buffer to copy from. + * @ubuf: User buffer to copy into. + * + * This function gets in transaction checkpointed VSX registers. + * + * When the transaction is active 'fp_state' holds the checkpointed + * values for the current transaction to fall back on if it aborts + * in between. This function gets those checkpointed VSX registers. + * The userspace interface buffer layout is as follows. + * + * struct data { + * u64 vsx[32]; + *}; + */ +static int tm_cvsx_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + u64 buf[32]; + int ret, i; + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return -ENODATA; + + /* Flush the state */ + flush_fp_to_thread(target); + flush_altivec_to_thread(target); + flush_tmregs_to_thread(target); + flush_vsx_to_thread(target); + + for (i = 0; i < 32 ; i++) + buf[i] = target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET]; + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + buf, 0, 32 * sizeof(double)); + + return ret; +} + +/** + * tm_cvsx_set - set CFPR registers + * @target: The target task. + * @regset: The user regset structure. + * @pos: The buffer position. + * @count: Number of bytes to copy. + * @kbuf: Kernel buffer to copy into. + * @ubuf: User buffer to copy from. + * + * This function sets in transaction checkpointed VSX registers. + * + * When the transaction is active 'fp_state' holds the checkpointed + * VSX register values for the current transaction to fall back on + * if it aborts in between. This function sets these checkpointed + * FPR registers. The userspace interface buffer layout is as follows. + * + * struct data { + * u64 vsx[32]; + *}; + */ +static int tm_cvsx_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + u64 buf[32]; + int ret, i; + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return -ENODATA; + + /* Flush the state */ + flush_fp_to_thread(target); + flush_altivec_to_thread(target); + flush_tmregs_to_thread(target); + flush_vsx_to_thread(target); + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + buf, 0, 32 * sizeof(double)); + for (i = 0; i < 32 ; i++) + target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = buf[i]; + + return ret; +} + +/** + * tm_spr_active - get active number of registers in TM SPR + * @target: The target task. + * @regset: The user regset structure. + * + * This function checks the active number of available + * regisers in the transactional memory SPR category. + */ +static int tm_spr_active(struct task_struct *target, + const struct user_regset *regset) +{ + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + return regset->n; +} + +/** + * tm_spr_get - get the TM related SPR registers + * @target: The target task. + * @regset: The user regset structure. + * @pos: The buffer position. + * @count: Number of bytes to copy. + * @kbuf: Kernel buffer to copy from. + * @ubuf: User buffer to copy into. + * + * This function gets transactional memory related SPR registers. + * The userspace interface buffer layout is as follows. + * + * struct { + * u64 tm_tfhar; + * u64 tm_texasr; + * u64 tm_tfiar; + * }; + */ +static int tm_spr_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + int ret; + + /* Build tests */ + BUILD_BUG_ON(TSO(tm_tfhar) + sizeof(u64) != TSO(tm_texasr)); + BUILD_BUG_ON(TSO(tm_texasr) + sizeof(u64) != TSO(tm_tfiar)); + BUILD_BUG_ON(TSO(tm_tfiar) + sizeof(u64) != TSO(ckpt_regs)); + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + /* Flush the states */ + flush_fp_to_thread(target); + flush_altivec_to_thread(target); + flush_tmregs_to_thread(target); + + /* TFHAR register */ + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.tm_tfhar, 0, sizeof(u64)); + + /* TEXASR register */ + if (!ret) + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.tm_texasr, sizeof(u64), + 2 * sizeof(u64)); + + /* TFIAR register */ + if (!ret) + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.tm_tfiar, + 2 * sizeof(u64), 3 * sizeof(u64)); + return ret; +} + +/** + * tm_spr_set - set the TM related SPR registers + * @target: The target task. + * @regset: The user regset structure. + * @pos: The buffer position. + * @count: Number of bytes to copy. + * @kbuf: Kernel buffer to copy into. + * @ubuf: User buffer to copy from. + * + * This function sets transactional memory related SPR registers. + * The userspace interface buffer layout is as follows. + * + * struct { + * u64 tm_tfhar; + * u64 tm_texasr; + * u64 tm_tfiar; + * }; + */ +static int tm_spr_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + + /* Build tests */ + BUILD_BUG_ON(TSO(tm_tfhar) + sizeof(u64) != TSO(tm_texasr)); + BUILD_BUG_ON(TSO(tm_texasr) + sizeof(u64) != TSO(tm_tfiar)); + BUILD_BUG_ON(TSO(tm_tfiar) + sizeof(u64) != TSO(ckpt_regs)); + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + /* Flush the states */ + flush_fp_to_thread(target); + flush_altivec_to_thread(target); + flush_tmregs_to_thread(target); + + /* TFHAR register */ + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.tm_tfhar, 0, sizeof(u64)); + + /* TEXASR register */ + if (!ret) + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.tm_texasr, sizeof(u64), + 2 * sizeof(u64)); + + /* TFIAR register */ + if (!ret) + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.tm_tfiar, + 2 * sizeof(u64), 3 * sizeof(u64)); + return ret; +} + +static int tm_tar_active(struct task_struct *target, + const struct user_regset *regset) +{ + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (MSR_TM_ACTIVE(target->thread.regs->msr)) + return regset->n; + + return 0; +} + +static int tm_tar_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + int ret; + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return -ENODATA; + + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.tm_tar, 0, sizeof(u64)); + return ret; +} + +static int tm_tar_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return -ENODATA; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.tm_tar, 0, sizeof(u64)); + return ret; +} + +static int tm_ppr_active(struct task_struct *target, + const struct user_regset *regset) +{ + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (MSR_TM_ACTIVE(target->thread.regs->msr)) + return regset->n; + + return 0; +} + + +static int tm_ppr_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + int ret; + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return -ENODATA; + + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.tm_ppr, 0, sizeof(u64)); + return ret; +} + +static int tm_ppr_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return -ENODATA; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.tm_ppr, 0, sizeof(u64)); + return ret; +} + +static int tm_dscr_active(struct task_struct *target, + const struct user_regset *regset) +{ + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (MSR_TM_ACTIVE(target->thread.regs->msr)) + return regset->n; + + return 0; +} + +static int tm_dscr_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + int ret; + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return -ENODATA; + + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.tm_dscr, 0, sizeof(u64)); + return ret; +} + +static int tm_dscr_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return -ENODATA; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.tm_dscr, 0, sizeof(u64)); + return ret; +} +#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ + +#ifdef CONFIG_PPC64 +static int ppr_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + int ret; + + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.ppr, 0, sizeof(u64)); + return ret; +} + +static int ppr_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.ppr, 0, sizeof(u64)); + return ret; +} + +static int dscr_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + int ret; + + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.dscr, 0, sizeof(u64)); + return ret; +} +static int dscr_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.dscr, 0, sizeof(u64)); + return ret; +} +#endif +#ifdef CONFIG_PPC_BOOK3S_64 +static int tar_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + int ret; + + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.tar, 0, sizeof(u64)); + return ret; +} +static int tar_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.tar, 0, sizeof(u64)); + return ret; +} + +static int ebb_active(struct task_struct *target, + const struct user_regset *regset) +{ + if (!cpu_has_feature(CPU_FTR_ARCH_207S)) + return -ENODEV; + + if (target->thread.used_ebb) + return regset->n; + + return 0; +} + +static int ebb_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + /* Build tests */ + BUILD_BUG_ON(TSO(ebbrr) + sizeof(unsigned long) != TSO(ebbhr)); + BUILD_BUG_ON(TSO(ebbhr) + sizeof(unsigned long) != TSO(bescr)); + + if (!cpu_has_feature(CPU_FTR_ARCH_207S)) + return -ENODEV; + + if (!target->thread.used_ebb) + return -ENODATA; + + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.ebbrr, 0, 3 * sizeof(unsigned long)); +} + +static int ebb_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret = 0; + + /* Build tests */ + BUILD_BUG_ON(TSO(ebbrr) + sizeof(unsigned long) != TSO(ebbhr)); + BUILD_BUG_ON(TSO(ebbhr) + sizeof(unsigned long) != TSO(bescr)); + + if (!cpu_has_feature(CPU_FTR_ARCH_207S)) + return -ENODEV; + + if (target->thread.used_ebb) + return -ENODATA; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.ebbrr, 0, sizeof(unsigned long)); + + if (!ret) + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.ebbhr, sizeof(unsigned long), + 2 * sizeof(unsigned long)); + + if (!ret) + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.bescr, + 2 * sizeof(unsigned long), 3 * sizeof(unsigned long)); + + return ret; +} +static int pmu_active(struct task_struct *target, + const struct user_regset *regset) +{ + if (!cpu_has_feature(CPU_FTR_ARCH_207S)) + return -ENODEV; + + return regset->n; +} + +static int pmu_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + /* Build tests */ + BUILD_BUG_ON(TSO(siar) + sizeof(unsigned long) != TSO(sdar)); + BUILD_BUG_ON(TSO(sdar) + sizeof(unsigned long) != TSO(sier)); + BUILD_BUG_ON(TSO(sier) + sizeof(unsigned long) != TSO(mmcr2)); + BUILD_BUG_ON(TSO(mmcr2) + sizeof(unsigned long) != TSO(mmcr0)); + + if (!cpu_has_feature(CPU_FTR_ARCH_207S)) + return -ENODEV; + + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.siar, 0, + 5 * sizeof(unsigned long)); +} + +static int pmu_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret = 0; + + /* Build tests */ + BUILD_BUG_ON(TSO(siar) + sizeof(unsigned long) != TSO(sdar)); + BUILD_BUG_ON(TSO(sdar) + sizeof(unsigned long) != TSO(sier)); + BUILD_BUG_ON(TSO(sier) + sizeof(unsigned long) != TSO(mmcr2)); + BUILD_BUG_ON(TSO(mmcr2) + sizeof(unsigned long) != TSO(mmcr0)); + + if (!cpu_has_feature(CPU_FTR_ARCH_207S)) + return -ENODEV; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.siar, 0, + sizeof(unsigned long)); + + if (!ret) + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.sdar, sizeof(unsigned long), + 2 * sizeof(unsigned long)); + + if (!ret) + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.sier, 2 * sizeof(unsigned long), + 3 * sizeof(unsigned long)); + + if (!ret) + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.mmcr2, 3 * sizeof(unsigned long), + 4 * sizeof(unsigned long)); + + if (!ret) + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.mmcr0, 4 * sizeof(unsigned long), + 5 * sizeof(unsigned long)); + return ret; +} +#endif +/* * These are our native regset flavors. */ enum powerpc_regset { @@ -630,6 +1928,25 @@ enum powerpc_regset { #ifdef CONFIG_SPE REGSET_SPE, #endif +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + REGSET_TM_CGPR, /* TM checkpointed GPR registers */ + REGSET_TM_CFPR, /* TM checkpointed FPR registers */ + REGSET_TM_CVMX, /* TM checkpointed VMX registers */ + REGSET_TM_CVSX, /* TM checkpointed VSX registers */ + REGSET_TM_SPR, /* TM specific SPR registers */ + REGSET_TM_CTAR, /* TM checkpointed TAR register */ + REGSET_TM_CPPR, /* TM checkpointed PPR register */ + REGSET_TM_CDSCR, /* TM checkpointed DSCR register */ +#endif +#ifdef CONFIG_PPC64 + REGSET_PPR, /* PPR register */ + REGSET_DSCR, /* DSCR register */ +#endif +#ifdef CONFIG_PPC_BOOK3S_64 + REGSET_TAR, /* TAR register */ + REGSET_EBB, /* EBB registers */ + REGSET_PMR, /* Performance Monitor Registers */ +#endif }; static const struct user_regset native_regsets[] = { @@ -664,6 +1981,77 @@ static const struct user_regset native_regsets[] = { .active = evr_active, .get = evr_get, .set = evr_set }, #endif +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + [REGSET_TM_CGPR] = { + .core_note_type = NT_PPC_TM_CGPR, .n = ELF_NGREG, + .size = sizeof(long), .align = sizeof(long), + .active = tm_cgpr_active, .get = tm_cgpr_get, .set = tm_cgpr_set + }, + [REGSET_TM_CFPR] = { + .core_note_type = NT_PPC_TM_CFPR, .n = ELF_NFPREG, + .size = sizeof(double), .align = sizeof(double), + .active = tm_cfpr_active, .get = tm_cfpr_get, .set = tm_cfpr_set + }, + [REGSET_TM_CVMX] = { + .core_note_type = NT_PPC_TM_CVMX, .n = ELF_NVMX, + .size = sizeof(vector128), .align = sizeof(vector128), + .active = tm_cvmx_active, .get = tm_cvmx_get, .set = tm_cvmx_set + }, + [REGSET_TM_CVSX] = { + .core_note_type = NT_PPC_TM_CVSX, .n = ELF_NVSX, + .size = sizeof(double), .align = sizeof(double), + .active = tm_cvsx_active, .get = tm_cvsx_get, .set = tm_cvsx_set + }, + [REGSET_TM_SPR] = { + .core_note_type = NT_PPC_TM_SPR, .n = ELF_NTMSPRREG, + .size = sizeof(u64), .align = sizeof(u64), + .active = tm_spr_active, .get = tm_spr_get, .set = tm_spr_set + }, + [REGSET_TM_CTAR] = { + .core_note_type = NT_PPC_TM_CTAR, .n = 1, + .size = sizeof(u64), .align = sizeof(u64), + .active = tm_tar_active, .get = tm_tar_get, .set = tm_tar_set + }, + [REGSET_TM_CPPR] = { + .core_note_type = NT_PPC_TM_CPPR, .n = 1, + .size = sizeof(u64), .align = sizeof(u64), + .active = tm_ppr_active, .get = tm_ppr_get, .set = tm_ppr_set + }, + [REGSET_TM_CDSCR] = { + .core_note_type = NT_PPC_TM_CDSCR, .n = 1, + .size = sizeof(u64), .align = sizeof(u64), + .active = tm_dscr_active, .get = tm_dscr_get, .set = tm_dscr_set + }, +#endif +#ifdef CONFIG_PPC64 + [REGSET_PPR] = { + .core_note_type = NT_PPC_PPR, .n = 1, + .size = sizeof(u64), .align = sizeof(u64), + .get = ppr_get, .set = ppr_set + }, + [REGSET_DSCR] = { + .core_note_type = NT_PPC_DSCR, .n = 1, + .size = sizeof(u64), .align = sizeof(u64), + .get = dscr_get, .set = dscr_set + }, +#endif +#ifdef CONFIG_PPC_BOOK3S_64 + [REGSET_TAR] = { + .core_note_type = NT_PPC_TAR, .n = 1, + .size = sizeof(u64), .align = sizeof(u64), + .get = tar_get, .set = tar_set + }, + [REGSET_EBB] = { + .core_note_type = NT_PPC_EBB, .n = ELF_NEBB, + .size = sizeof(u64), .align = sizeof(u64), + .active = ebb_active, .get = ebb_get, .set = ebb_set + }, + [REGSET_PMR] = { + .core_note_type = NT_PPC_PMU, .n = ELF_NPMU, + .size = sizeof(u64), .align = sizeof(u64), + .active = pmu_active, .get = pmu_get, .set = pmu_set + }, +#endif }; static const struct user_regset_view user_ppc_native_view = { @@ -674,24 +2062,35 @@ static const struct user_regset_view user_ppc_native_view = { #ifdef CONFIG_PPC64 #include <linux/compat.h> -static int gpr32_get(struct task_struct *target, +static int gpr32_get_common(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, - void *kbuf, void __user *ubuf) + void *kbuf, void __user *ubuf, bool tm_active) { const unsigned long *regs = &target->thread.regs->gpr[0]; + const unsigned long *ckpt_regs; compat_ulong_t *k = kbuf; compat_ulong_t __user *u = ubuf; compat_ulong_t reg; int i; - if (target->thread.regs == NULL) - return -EIO; +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + ckpt_regs = &target->thread.ckpt_regs.gpr[0]; +#endif + if (tm_active) { + regs = ckpt_regs; + } else { + if (target->thread.regs == NULL) + return -EIO; - if (!FULL_REGS(target->thread.regs)) { - /* We have a partial register set. Fill 14-31 with bogus values */ - for (i = 14; i < 32; i++) - target->thread.regs->gpr[i] = NV_REG_POISON; + if (!FULL_REGS(target->thread.regs)) { + /* + * We have a partial register set. + * Fill 14-31 with bogus values. + */ + for (i = 14; i < 32; i++) + target->thread.regs->gpr[i] = NV_REG_POISON; + } } pos /= sizeof(reg); @@ -731,20 +2130,31 @@ static int gpr32_get(struct task_struct *target, PT_REGS_COUNT * sizeof(reg), -1); } -static int gpr32_set(struct task_struct *target, +static int gpr32_set_common(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, - const void *kbuf, const void __user *ubuf) + const void *kbuf, const void __user *ubuf, bool tm_active) { unsigned long *regs = &target->thread.regs->gpr[0]; + unsigned long *ckpt_regs; const compat_ulong_t *k = kbuf; const compat_ulong_t __user *u = ubuf; compat_ulong_t reg; - if (target->thread.regs == NULL) - return -EIO; +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + ckpt_regs = &target->thread.ckpt_regs.gpr[0]; +#endif - CHECK_FULL_REGS(target->thread.regs); + if (tm_active) { + regs = ckpt_regs; + } else { + regs = &target->thread.regs->gpr[0]; + + if (target->thread.regs == NULL) + return -EIO; + + CHECK_FULL_REGS(target->thread.regs); + } pos /= sizeof(reg); count /= sizeof(reg); @@ -804,6 +2214,40 @@ static int gpr32_set(struct task_struct *target, (PT_TRAP + 1) * sizeof(reg), -1); } +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM +static int tm_cgpr32_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + return gpr32_get_common(target, regset, pos, count, kbuf, ubuf, 1); +} + +static int tm_cgpr32_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + return gpr32_set_common(target, regset, pos, count, kbuf, ubuf, 1); +} +#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ + +static int gpr32_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + return gpr32_get_common(target, regset, pos, count, kbuf, ubuf, 0); +} + +static int gpr32_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + return gpr32_set_common(target, regset, pos, count, kbuf, ubuf, 0); +} + /* * These are the regset flavors matching the CONFIG_PPC32 native set. */ @@ -832,6 +2276,73 @@ static const struct user_regset compat_regsets[] = { .active = evr_active, .get = evr_get, .set = evr_set }, #endif +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + [REGSET_TM_CGPR] = { + .core_note_type = NT_PPC_TM_CGPR, .n = ELF_NGREG, + .size = sizeof(long), .align = sizeof(long), + .active = tm_cgpr_active, + .get = tm_cgpr32_get, .set = tm_cgpr32_set + }, + [REGSET_TM_CFPR] = { + .core_note_type = NT_PPC_TM_CFPR, .n = ELF_NFPREG, + .size = sizeof(double), .align = sizeof(double), + .active = tm_cfpr_active, .get = tm_cfpr_get, .set = tm_cfpr_set + }, + [REGSET_TM_CVMX] = { + .core_note_type = NT_PPC_TM_CVMX, .n = ELF_NVMX, + .size = sizeof(vector128), .align = sizeof(vector128), + .active = tm_cvmx_active, .get = tm_cvmx_get, .set = tm_cvmx_set + }, + [REGSET_TM_CVSX] = { + .core_note_type = NT_PPC_TM_CVSX, .n = ELF_NVSX, + .size = sizeof(double), .align = sizeof(double), + .active = tm_cvsx_active, .get = tm_cvsx_get, .set = tm_cvsx_set + }, + [REGSET_TM_SPR] = { + .core_note_type = NT_PPC_TM_SPR, .n = ELF_NTMSPRREG, + .size = sizeof(u64), .align = sizeof(u64), + .active = tm_spr_active, .get = tm_spr_get, .set = tm_spr_set + }, + [REGSET_TM_CTAR] = { + .core_note_type = NT_PPC_TM_CTAR, .n = 1, + .size = sizeof(u64), .align = sizeof(u64), + .active = tm_tar_active, .get = tm_tar_get, .set = tm_tar_set + }, + [REGSET_TM_CPPR] = { + .core_note_type = NT_PPC_TM_CPPR, .n = 1, + .size = sizeof(u64), .align = sizeof(u64), + .active = tm_ppr_active, .get = tm_ppr_get, .set = tm_ppr_set + }, + [REGSET_TM_CDSCR] = { + .core_note_type = NT_PPC_TM_CDSCR, .n = 1, + .size = sizeof(u64), .align = sizeof(u64), + .active = tm_dscr_active, .get = tm_dscr_get, .set = tm_dscr_set + }, +#endif +#ifdef CONFIG_PPC64 + [REGSET_PPR] = { + .core_note_type = NT_PPC_PPR, .n = 1, + .size = sizeof(u64), .align = sizeof(u64), + .get = ppr_get, .set = ppr_set + }, + [REGSET_DSCR] = { + .core_note_type = NT_PPC_DSCR, .n = 1, + .size = sizeof(u64), .align = sizeof(u64), + .get = dscr_get, .set = dscr_set + }, +#endif +#ifdef CONFIG_PPC_BOOK3S_64 + [REGSET_TAR] = { + .core_note_type = NT_PPC_TAR, .n = 1, + .size = sizeof(u64), .align = sizeof(u64), + .get = tar_get, .set = tar_set + }, + [REGSET_EBB] = { + .core_note_type = NT_PPC_EBB, .n = ELF_NEBB, + .size = sizeof(u64), .align = sizeof(u64), + .active = ebb_active, .get = ebb_get, .set = ebb_set + }, +#endif }; static const struct user_regset_view user_ppc_compat_view = { @@ -1783,12 +3294,12 @@ static int do_seccomp(struct pt_regs *regs) * have already loaded -ENOSYS into r3, or seccomp has put * something else in r3 (via SECCOMP_RET_ERRNO/TRACE). */ - if (__secure_computing()) + if (__secure_computing(NULL)) return -1; /* * The syscall was allowed by seccomp, restore the register - * state to what ptrace and audit expect. + * state to what audit expects. * Note that we use orig_gpr3, which means a seccomp tracer can * modify the first syscall parameter (in orig_gpr3) and also * allow the syscall to proceed. @@ -1822,22 +3333,25 @@ static inline int do_seccomp(struct pt_regs *regs) { return 0; } */ long do_syscall_trace_enter(struct pt_regs *regs) { - bool abort = false; - user_exit(); + /* + * The tracer may decide to abort the syscall, if so tracehook + * will return !0. Note that the tracer may also just change + * regs->gpr[0] to an invalid syscall number, that is handled + * below on the exit path. + */ + if (test_thread_flag(TIF_SYSCALL_TRACE) && + tracehook_report_syscall_entry(regs)) + goto skip; + + /* Run seccomp after ptrace; allow it to set gpr[3]. */ if (do_seccomp(regs)) return -1; - if (test_thread_flag(TIF_SYSCALL_TRACE)) { - /* - * The tracer may decide to abort the syscall, if so tracehook - * will return !0. Note that the tracer may also just change - * regs->gpr[0] to an invalid syscall number, that is handled - * below on the exit path. - */ - abort = tracehook_report_syscall_entry(regs) != 0; - } + /* Avoid trace and audit when syscall is invalid. */ + if (regs->gpr[0] >= NR_syscalls) + goto skip; if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) trace_sys_enter(regs, regs->gpr[0]); @@ -1854,17 +3368,16 @@ long do_syscall_trace_enter(struct pt_regs *regs) regs->gpr[5] & 0xffffffff, regs->gpr[6] & 0xffffffff); - if (abort || regs->gpr[0] >= NR_syscalls) { - /* - * If we are aborting explicitly, or if the syscall number is - * now invalid, set the return value to -ENOSYS. - */ - regs->gpr[3] = -ENOSYS; - return -1; - } - /* Return the possibly modified but valid syscall number */ return regs->gpr[0]; + +skip: + /* + * If we are aborting explicitly, or if the syscall number is + * now invalid, set the return value to -ENOSYS. + */ + regs->gpr[3] = -ENOSYS; + return -1; } void do_syscall_trace_leave(struct pt_regs *regs) diff --git a/arch/powerpc/kernel/rtas-proc.c b/arch/powerpc/kernel/rtas-proc.c index fb2fb3ea8..c82eed97b 100644 --- a/arch/powerpc/kernel/rtas-proc.c +++ b/arch/powerpc/kernel/rtas-proc.c @@ -698,7 +698,7 @@ static void check_location(struct seq_file *m, const char *c) /* * Format: * ${LETTER}${NUMBER}[[-/]${LETTER}${NUMBER} [ ... ] ] - * the '.' may be an abbrevation + * the '.' may be an abbreviation */ static void check_location_string(struct seq_file *m, const char *c) { diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 28736ff27..6a3e5de54 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -685,7 +685,7 @@ int rtas_set_indicator_fast(int indicator, int index, int new_value) return rc; } -void rtas_restart(char *cmd) +void __noreturn rtas_restart(char *cmd) { if (rtas_flash_term_hook) rtas_flash_term_hook(SYS_RESTART); @@ -704,7 +704,7 @@ void rtas_power_off(void) for (;;); } -void rtas_halt(void) +void __noreturn rtas_halt(void) { if (rtas_flash_term_hook) rtas_flash_term_hook(SYS_HALT); @@ -1070,7 +1070,7 @@ asmlinkage int ppc_rtas(struct rtas_args __user *uargs) nret = be32_to_cpu(args.nret); token = be32_to_cpu(args.token); - if (nargs > ARRAY_SIZE(args.args) + if (nargs >= ARRAY_SIZE(args.args) || nret > ARRAY_SIZE(args.args) || nargs + nret > ARRAY_SIZE(args.args)) return -EINVAL; @@ -1174,7 +1174,7 @@ void __init rtas_initialize(void) * the stop-self token if any */ #ifdef CONFIG_PPC64 - if (machine_is(pseries) && firmware_has_feature(FW_FEATURE_LPAR)) { + if (firmware_has_feature(FW_FEATURE_LPAR)) { rtas_region = min(ppc64_rma_size, RTAS_INSTANTIATE_MAX); ibm_suspend_me_token = rtas_token("ibm,suspend-me"); } diff --git a/arch/powerpc/kernel/rtasd.c b/arch/powerpc/kernel/rtasd.c index c638e2487..a26a02006 100644 --- a/arch/powerpc/kernel/rtasd.c +++ b/arch/powerpc/kernel/rtasd.c @@ -483,7 +483,7 @@ static void rtas_event_scan(struct work_struct *w) } #ifdef CONFIG_PPC64 -static void retreive_nvram_error_log(void) +static void retrieve_nvram_error_log(void) { unsigned int err_type ; int rc ; @@ -501,7 +501,7 @@ static void retreive_nvram_error_log(void) } } #else /* CONFIG_PPC64 */ -static void retreive_nvram_error_log(void) +static void retrieve_nvram_error_log(void) { } #endif /* CONFIG_PPC64 */ @@ -513,7 +513,7 @@ static void start_event_scan(void) (30000 / rtas_event_scan_rate)); /* Retrieve errors from nvram if any */ - retreive_nvram_error_log(); + retrieve_nvram_error_log(); schedule_delayed_work_on(cpumask_first(cpu_online_mask), &event_scan_work, event_scan_delay); @@ -526,10 +526,8 @@ void rtas_cancel_event_scan(void) } EXPORT_SYMBOL_GPL(rtas_cancel_event_scan); -static int __init rtas_init(void) +static int __init rtas_event_scan_init(void) { - struct proc_dir_entry *entry; - if (!machine_is(pseries) && !machine_is(chrp)) return 0; @@ -562,13 +560,27 @@ static int __init rtas_init(void) return -ENOMEM; } + start_event_scan(); + + return 0; +} +arch_initcall(rtas_event_scan_init); + +static int __init rtas_init(void) +{ + struct proc_dir_entry *entry; + + if (!machine_is(pseries) && !machine_is(chrp)) + return 0; + + if (!rtas_log_buf) + return -ENODEV; + entry = proc_create("powerpc/rtas/error_log", S_IRUSR, NULL, &proc_rtas_log_operations); if (!entry) printk(KERN_ERR "Failed to create error_log proc entry\n"); - start_event_scan(); - return 0; } __initcall(rtas_init); diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 8ca79b750..dba265c58 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -35,6 +35,7 @@ #include <linux/percpu.h> #include <linux/memblock.h> #include <linux/of_platform.h> +#include <linux/hugetlb.h> #include <asm/io.h> #include <asm/paca.h> #include <asm/prom.h> @@ -61,6 +62,13 @@ #include <asm/cputhreads.h> #include <mm/mmu_decl.h> #include <asm/fadump.h> +#include <asm/udbg.h> +#include <asm/hugetlb.h> +#include <asm/livepatch.h> +#include <asm/mmu_context.h> +#include <asm/cpu_has_feature.h> + +#include "setup.h" #ifdef DEBUG #include <asm/udbg.h> @@ -494,7 +502,7 @@ void __init smp_setup_cpu_maps(void) * On pSeries LPAR, we need to know how many cpus * could possibly be added to this partition. */ - if (machine_is(pseries) && firmware_has_feature(FW_FEATURE_LPAR) && + if (firmware_has_feature(FW_FEATURE_LPAR) && (dn = of_find_node_by_path("/rtas"))) { int num_addr_cell, num_size_cell, maxcpus; const __be32 *ireg; @@ -575,6 +583,7 @@ void probe_machine(void) { extern struct machdep_calls __machine_desc_start; extern struct machdep_calls __machine_desc_end; + unsigned int i; /* * Iterate all ppc_md structures until we find the proper @@ -582,6 +591,17 @@ void probe_machine(void) */ DBG("Probing machine type ...\n"); + /* + * Check ppc_md is empty, if not we have a bug, ie, we setup an + * entry before probe_machine() which will be overwritten + */ + for (i = 0; i < (sizeof(ppc_md) / sizeof(void *)); i++) { + if (((void **)&ppc_md)[i]) { + printk(KERN_ERR "Entry %d in ppc_md non empty before" + " machine probe !\n", i); + } + } + for (machine_id = &__machine_desc_start; machine_id < &__machine_desc_end; machine_id++) { @@ -676,6 +696,8 @@ static struct notifier_block ppc_panic_block = { void __init setup_panic(void) { + if (!ppc_md.panic) + return; atomic_notifier_chain_register(&panic_notifier_list, &ppc_panic_block); } @@ -744,3 +766,169 @@ void arch_setup_pdev_archdata(struct platform_device *pdev) pdev->dev.dma_mask = &pdev->archdata.dma_mask; set_dma_ops(&pdev->dev, &dma_direct_ops); } + +static __init void print_system_info(void) +{ + pr_info("-----------------------------------------------------\n"); +#ifdef CONFIG_PPC_STD_MMU_64 + pr_info("ppc64_pft_size = 0x%llx\n", ppc64_pft_size); +#endif +#ifdef CONFIG_PPC_STD_MMU_32 + pr_info("Hash_size = 0x%lx\n", Hash_size); +#endif + pr_info("phys_mem_size = 0x%llx\n", + (unsigned long long)memblock_phys_mem_size()); + + pr_info("dcache_bsize = 0x%x\n", dcache_bsize); + pr_info("icache_bsize = 0x%x\n", icache_bsize); + if (ucache_bsize != 0) + pr_info("ucache_bsize = 0x%x\n", ucache_bsize); + + pr_info("cpu_features = 0x%016lx\n", cur_cpu_spec->cpu_features); + pr_info(" possible = 0x%016lx\n", + (unsigned long)CPU_FTRS_POSSIBLE); + pr_info(" always = 0x%016lx\n", + (unsigned long)CPU_FTRS_ALWAYS); + pr_info("cpu_user_features = 0x%08x 0x%08x\n", + cur_cpu_spec->cpu_user_features, + cur_cpu_spec->cpu_user_features2); + pr_info("mmu_features = 0x%08x\n", cur_cpu_spec->mmu_features); +#ifdef CONFIG_PPC64 + pr_info("firmware_features = 0x%016lx\n", powerpc_firmware_features); +#endif + +#ifdef CONFIG_PPC_STD_MMU_64 + if (htab_address) + pr_info("htab_address = 0x%p\n", htab_address); + if (htab_hash_mask) + pr_info("htab_hash_mask = 0x%lx\n", htab_hash_mask); +#endif +#ifdef CONFIG_PPC_STD_MMU_32 + if (Hash) + pr_info("Hash = 0x%p\n", Hash); + if (Hash_mask) + pr_info("Hash_mask = 0x%lx\n", Hash_mask); +#endif + + if (PHYSICAL_START > 0) + pr_info("physical_start = 0x%llx\n", + (unsigned long long)PHYSICAL_START); + pr_info("-----------------------------------------------------\n"); +} + +/* + * Called into from start_kernel this initializes memblock, which is used + * to manage page allocation until mem_init is called. + */ +void __init setup_arch(char **cmdline_p) +{ + *cmdline_p = boot_command_line; + + /* Set a half-reasonable default so udelay does something sensible */ + loops_per_jiffy = 500000000 / HZ; + + /* Unflatten the device-tree passed by prom_init or kexec */ + unflatten_device_tree(); + + /* + * Initialize cache line/block info from device-tree (on ppc64) or + * just cputable (on ppc32). + */ + initialize_cache_info(); + + /* Initialize RTAS if available. */ + rtas_initialize(); + + /* Check if we have an initrd provided via the device-tree. */ + check_for_initrd(); + + /* Probe the machine type, establish ppc_md. */ + probe_machine(); + + /* Setup panic notifier if requested by the platform. */ + setup_panic(); + + /* + * Configure ppc_md.power_save (ppc32 only, 64-bit machines do + * it from their respective probe() function. + */ + setup_power_save(); + + /* Discover standard serial ports. */ + find_legacy_serial_ports(); + + /* Register early console with the printk subsystem. */ + register_early_udbg_console(); + + /* Setup the various CPU maps based on the device-tree. */ + smp_setup_cpu_maps(); + + /* Initialize xmon. */ + xmon_setup(); + + /* Check the SMT related command line arguments (ppc64). */ + check_smt_enabled(); + + /* On BookE, setup per-core TLB data structures. */ + setup_tlb_core_data(); + + /* + * Release secondary cpus out of their spinloops at 0x60 now that + * we can map physical -> logical CPU ids. + * + * Freescale Book3e parts spin in a loop provided by firmware, + * so smp_release_cpus() does nothing for them. + */ +#ifdef CONFIG_SMP + smp_release_cpus(); +#endif + + /* Print various info about the machine that has been gathered so far. */ + print_system_info(); + + /* Reserve large chunks of memory for use by CMA for KVM. */ + kvm_cma_reserve(); + + /* + * Reserve any gigantic pages requested on the command line. + * memblock needs to have been initialized by the time this is + * called since this will reserve memory. + */ + reserve_hugetlb_gpages(); + + klp_init_thread_info(&init_thread_info); + + init_mm.start_code = (unsigned long)_stext; + init_mm.end_code = (unsigned long) _etext; + init_mm.end_data = (unsigned long) _edata; + init_mm.brk = klimit; +#ifdef CONFIG_PPC_64K_PAGES + init_mm.context.pte_frag = NULL; +#endif +#ifdef CONFIG_SPAPR_TCE_IOMMU + mm_iommu_init(&init_mm.context); +#endif + irqstack_early_init(); + exc_lvl_early_init(); + emergency_stack_init(); + + initmem_init(); + +#ifdef CONFIG_DUMMY_CONSOLE + conswitchp = &dummy_con; +#endif + if (ppc_md.setup_arch) + ppc_md.setup_arch(); + + paging_init(); + + /* Initialize the MMU context management stuff. */ + mmu_context_init(); + +#ifdef CONFIG_PPC64 + /* Interrupt code needs to be 64K-aligned. */ + if ((unsigned long)_stext & 0xffff) + panic("Kernelbase not 64K-aligned (0x%lx)!\n", + (unsigned long)_stext); +#endif +} diff --git a/arch/powerpc/kernel/setup.h b/arch/powerpc/kernel/setup.h new file mode 100644 index 000000000..cfba134b3 --- /dev/null +++ b/arch/powerpc/kernel/setup.h @@ -0,0 +1,58 @@ +/* + * Prototypes for functions that are shared between setup_(32|64|common).c + * + * Copyright 2016 Michael Ellerman, IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#ifndef __ARCH_POWERPC_KERNEL_SETUP_H +#define __ARCH_POWERPC_KERNEL_SETUP_H + +void initialize_cache_info(void); +void irqstack_early_init(void); + +#ifdef CONFIG_PPC32 +void setup_power_save(void); +#else +static inline void setup_power_save(void) { }; +#endif + +#if defined(CONFIG_PPC64) && defined(CONFIG_SMP) +void check_smt_enabled(void); +#else +static inline void check_smt_enabled(void) { }; +#endif + +#if defined(CONFIG_PPC_BOOK3E) && defined(CONFIG_SMP) +void setup_tlb_core_data(void); +#else +static inline void setup_tlb_core_data(void) { }; +#endif + +#if defined(CONFIG_PPC_BOOK3E) || defined(CONFIG_BOOKE) || defined(CONFIG_40x) +void exc_lvl_early_init(void); +#else +static inline void exc_lvl_early_init(void) { }; +#endif + +#ifdef CONFIG_PPC64 +void emergency_stack_init(void); +#else +static inline void emergency_stack_init(void) { }; +#endif + +/* + * Having this in kvm_ppc.h makes include dependencies too + * tricky to solve for setup-common.c so have it here. + */ +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE +void kvm_cma_reserve(void); +#else +static inline void kvm_cma_reserve(void) { }; +#endif + +#endif /* __ARCH_POWERPC_KERNEL_SETUP_H */ diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index d544fa311..24ec3ea4b 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -36,9 +36,8 @@ #include <asm/time.h> #include <asm/serial.h> #include <asm/udbg.h> -#include <asm/mmu_context.h> -#include <asm/epapr_hcalls.h> #include <asm/code-patching.h> +#include <asm/cpu_has_feature.h> #define DBG(fmt...) @@ -62,9 +61,7 @@ int icache_bsize; int ucache_bsize; /* - * We're called here very early in the boot. We determine the machine - * type and call the appropriate low-level setup functions. - * -- Cort <cort@fsmlabs.com> + * We're called here very early in the boot. * * Note that the kernel may be running at an address which is different * from the address that it was linked at, so we must use RELOC/PTRRELOC @@ -73,7 +70,6 @@ int ucache_bsize; notrace unsigned long __init early_init(unsigned long dt_ptr) { unsigned long offset = reloc_offset(); - struct cpu_spec *spec; /* First zero the BSS -- use memset_io, some platforms don't have * caches on yet */ @@ -84,36 +80,29 @@ notrace unsigned long __init early_init(unsigned long dt_ptr) * Identify the CPU type and fix up code sections * that depend on which cpu we have. */ - spec = identify_cpu(offset, mfspr(SPRN_PVR)); + identify_cpu(offset, mfspr(SPRN_PVR)); - do_feature_fixups(spec->cpu_features, - PTRRELOC(&__start___ftr_fixup), - PTRRELOC(&__stop___ftr_fixup)); - - do_feature_fixups(spec->mmu_features, - PTRRELOC(&__start___mmu_ftr_fixup), - PTRRELOC(&__stop___mmu_ftr_fixup)); - - do_lwsync_fixups(spec->cpu_features, - PTRRELOC(&__start___lwsync_fixup), - PTRRELOC(&__stop___lwsync_fixup)); - - do_final_fixups(); + apply_feature_fixups(); return KERNELBASE + offset; } /* - * Find out what kind of machine we're on and save any data we need - * from the early boot process (devtree is copied on pmac by prom_init()). - * This is called very early on the boot process, after a minimal - * MMU environment has been set up but before MMU_init is called. + * This is run before start_kernel(), the kernel has been relocated + * and we are running with enough of the MMU enabled to have our + * proper kernel virtual addresses + * + * We do the initial parsing of the flat device-tree and prepares + * for the MMU to be fully initialized. */ extern unsigned int memset_nocache_branch; /* Insn to be replaced by NOP */ notrace void __init machine_init(u64 dt_ptr) { + /* Configure static keys first, now that we're relocated. */ + setup_feature_keys(); + /* Enable early debugging if any specified (see udbg.h) */ udbg_early_init(); @@ -123,27 +112,9 @@ notrace void __init machine_init(u64 dt_ptr) /* Do some early initialization based on the flat device tree */ early_init_devtree(__va(dt_ptr)); - epapr_paravirt_early_init(); - early_init_mmu(); - probe_machine(); - setup_kdump_trampoline(); - -#ifdef CONFIG_6xx - if (cpu_has_feature(CPU_FTR_CAN_DOZE) || - cpu_has_feature(CPU_FTR_CAN_NAP)) - ppc_md.power_save = ppc6xx_idle; -#endif - -#ifdef CONFIG_E500 - if (cpu_has_feature(CPU_FTR_CAN_DOZE) || - cpu_has_feature(CPU_FTR_CAN_NAP)) - ppc_md.power_save = e500_idle; -#endif - if (ppc_md.progress) - ppc_md.progress("id mach(): done", 0x200); } /* Checks "l2cr=xxxx" command-line option */ @@ -221,7 +192,7 @@ int __init ppc_init(void) arch_initcall(ppc_init); -static void __init irqstack_early_init(void) +void __init irqstack_early_init(void) { unsigned int i; @@ -236,7 +207,7 @@ static void __init irqstack_early_init(void) } #if defined(CONFIG_BOOKE) || defined(CONFIG_40x) -static void __init exc_lvl_early_init(void) +void __init exc_lvl_early_init(void) { unsigned int i, hw_cpu; @@ -259,33 +230,25 @@ static void __init exc_lvl_early_init(void) #endif } } -#else -#define exc_lvl_early_init() #endif -/* Warning, IO base is not yet inited */ -void __init setup_arch(char **cmdline_p) +void __init setup_power_save(void) { - *cmdline_p = boot_command_line; - - /* so udelay does something sensible, assume <= 1000 bogomips */ - loops_per_jiffy = 500000000 / HZ; - - unflatten_device_tree(); - check_for_initrd(); - - if (ppc_md.init_early) - ppc_md.init_early(); - - find_legacy_serial_ports(); - - smp_setup_cpu_maps(); - - /* Register early console */ - register_early_udbg_console(); +#ifdef CONFIG_6xx + if (cpu_has_feature(CPU_FTR_CAN_DOZE) || + cpu_has_feature(CPU_FTR_CAN_NAP)) + ppc_md.power_save = ppc6xx_idle; +#endif - xmon_setup(); +#ifdef CONFIG_E500 + if (cpu_has_feature(CPU_FTR_CAN_DOZE) || + cpu_has_feature(CPU_FTR_CAN_NAP)) + ppc_md.power_save = e500_idle; +#endif +} +__init void initialize_cache_info(void) +{ /* * Set cache line size based on type of cpu as a default. * Systems with OF can look in the properties on the cpu node(s) @@ -296,32 +259,4 @@ void __init setup_arch(char **cmdline_p) ucache_bsize = 0; if (cpu_has_feature(CPU_FTR_UNIFIED_ID_CACHE)) ucache_bsize = icache_bsize = dcache_bsize; - - if (ppc_md.panic) - setup_panic(); - - init_mm.start_code = (unsigned long)_stext; - init_mm.end_code = (unsigned long) _etext; - init_mm.end_data = (unsigned long) _edata; - init_mm.brk = klimit; - - exc_lvl_early_init(); - - irqstack_early_init(); - - initmem_init(); - if ( ppc_md.progress ) ppc_md.progress("setup_arch: initmem", 0x3eab); - -#ifdef CONFIG_DUMMY_CONSOLE - conswitchp = &dummy_con; -#endif - - if (ppc_md.setup_arch) - ppc_md.setup_arch(); - if ( ppc_md.progress ) ppc_md.progress("arch: exit", 0x3eab); - - paging_init(); - - /* Initialize the MMU context management stuff */ - mmu_context_init(); } diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 96d4a2b23..7ac8e6eaa 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -35,7 +35,6 @@ #include <linux/pci.h> #include <linux/lockdep.h> #include <linux/memblock.h> -#include <linux/hugetlb.h> #include <linux/memory.h> #include <linux/nmi.h> @@ -64,12 +63,10 @@ #include <asm/xmon.h> #include <asm/udbg.h> #include <asm/kexec.h> -#include <asm/mmu_context.h> #include <asm/code-patching.h> -#include <asm/kvm_ppc.h> -#include <asm/hugetlb.h> -#include <asm/epapr_hcalls.h> #include <asm/livepatch.h> +#include <asm/opal.h> +#include <asm/cputhreads.h> #ifdef DEBUG #define DBG(fmt...) udbg_printf(fmt) @@ -100,7 +97,7 @@ int icache_bsize; int ucache_bsize; #if defined(CONFIG_PPC_BOOK3E) && defined(CONFIG_SMP) -static void setup_tlb_core_data(void) +void __init setup_tlb_core_data(void) { int cpu; @@ -133,10 +130,6 @@ static void setup_tlb_core_data(void) } } } -#else -static void setup_tlb_core_data(void) -{ -} #endif #ifdef CONFIG_SMP @@ -144,7 +137,7 @@ static void setup_tlb_core_data(void) static char *smt_enabled_cmdline; /* Look for ibm,smt-enabled OF option */ -static void check_smt_enabled(void) +void __init check_smt_enabled(void) { struct device_node *dn; const char *smt_option; @@ -193,12 +186,10 @@ static int __init early_smt_enabled(char *p) } early_param("smt-enabled", early_smt_enabled); -#else -#define check_smt_enabled() #endif /* CONFIG_SMP */ /** Fix up paca fields required for the boot cpu */ -static void fixup_boot_paca(void) +static void __init fixup_boot_paca(void) { /* The boot cpu is started */ get_paca()->cpu_start = 1; @@ -206,23 +197,50 @@ static void fixup_boot_paca(void) get_paca()->data_offset = 0; } -static void cpu_ready_for_interrupts(void) +static void __init configure_exceptions(void) { - /* Set IR and DR in PACA MSR */ - get_paca()->kernel_msr = MSR_KERNEL; - /* - * Enable AIL if supported, and we are in hypervisor mode. If we are - * not in hypervisor mode, we enable relocation-on interrupts later - * in pSeries_setup_arch() using the H_SET_MODE hcall. + * Setup the trampolines from the lowmem exception vectors + * to the kdump kernel when not using a relocatable kernel. */ - if (cpu_has_feature(CPU_FTR_HVMODE) && - cpu_has_feature(CPU_FTR_ARCH_207S)) { - unsigned long lpcr = mfspr(SPRN_LPCR); - mtspr(SPRN_LPCR, lpcr | LPCR_AIL_3); + setup_kdump_trampoline(); + + /* Under a PAPR hypervisor, we need hypercalls */ + if (firmware_has_feature(FW_FEATURE_SET_MODE)) { + /* Enable AIL if possible */ + pseries_enable_reloc_on_exc(); + + /* + * Tell the hypervisor that we want our exceptions to + * be taken in little endian mode. + * + * We don't call this for big endian as our calling convention + * makes us always enter in BE, and the call may fail under + * some circumstances with kdump. + */ +#ifdef __LITTLE_ENDIAN__ + pseries_little_endian_exceptions(); +#endif + } else { + /* Set endian mode using OPAL */ + if (firmware_has_feature(FW_FEATURE_OPAL)) + opal_configure_cores(); + + /* Enable AIL if supported, and we are in hypervisor mode */ + if (early_cpu_has_feature(CPU_FTR_HVMODE) && + early_cpu_has_feature(CPU_FTR_ARCH_207S)) { + unsigned long lpcr = mfspr(SPRN_LPCR); + mtspr(SPRN_LPCR, lpcr | LPCR_AIL_3); + } } } +static void cpu_ready_for_interrupts(void) +{ + /* Set IR and DR in PACA MSR */ + get_paca()->kernel_msr = MSR_KERNEL; +} + /* * Early initialization entry point. This is called by head.S * with MMU translation disabled. We rely on the "feature" of @@ -270,18 +288,19 @@ void __init early_setup(unsigned long dt_ptr) */ early_init_devtree(__va(dt_ptr)); - epapr_paravirt_early_init(); - /* Now we know the logical id of our boot cpu, setup the paca. */ setup_paca(&paca[boot_cpuid]); fixup_boot_paca(); - /* Probe the machine type */ - probe_machine(); - - setup_kdump_trampoline(); + /* + * Configure exception handlers. This include setting up trampolines + * if needed, setting exception endian mode, etc... + */ + configure_exceptions(); - DBG("Found, Initializing memory management...\n"); + /* Apply all the dynamic patching */ + apply_feature_fixups(); + setup_feature_keys(); /* Initialize the hash table or TLB handling */ early_init_mmu(); @@ -293,16 +312,6 @@ void __init early_setup(unsigned long dt_ptr) */ cpu_ready_for_interrupts(); - /* Reserve large chunks of memory for use by CMA for KVM */ - kvm_cma_reserve(); - - /* - * Reserve any gigantic pages requested on the command line. - * memblock needs to have been initialized by the time this is - * called since this will reserve memory. - */ - reserve_hugetlb_gpages(); - DBG(" <- early_setup()\n"); #ifdef CONFIG_PPC_EARLY_DEBUG_BOOTX @@ -321,7 +330,7 @@ void __init early_setup(unsigned long dt_ptr) #ifdef CONFIG_SMP void early_setup_secondary(void) { - /* Mark interrupts enabled in PACA */ + /* Mark interrupts disabled in PACA */ get_paca()->soft_enabled = 0; /* Initialize the hash table or TLB handling */ @@ -391,7 +400,7 @@ void smp_release_cpus(void) * cache informations about the CPU that will be used by cache flush * routines and/or provided to userland */ -static void __init initialize_cache_info(void) +void __init initialize_cache_info(void) { struct device_node *np; unsigned long num_cpus = 0; @@ -456,127 +465,11 @@ static void __init initialize_cache_info(void) } } - DBG(" <- initialize_cache_info()\n"); -} - - -/* - * Do some initial setup of the system. The parameters are those which - * were passed in from the bootloader. - */ -void __init setup_system(void) -{ - DBG(" -> setup_system()\n"); - - /* Apply the CPUs-specific and firmware specific fixups to kernel - * text (nop out sections not relevant to this CPU or this firmware) - */ - do_feature_fixups(cur_cpu_spec->cpu_features, - &__start___ftr_fixup, &__stop___ftr_fixup); - do_feature_fixups(cur_cpu_spec->mmu_features, - &__start___mmu_ftr_fixup, &__stop___mmu_ftr_fixup); - do_feature_fixups(powerpc_firmware_features, - &__start___fw_ftr_fixup, &__stop___fw_ftr_fixup); - do_lwsync_fixups(cur_cpu_spec->cpu_features, - &__start___lwsync_fixup, &__stop___lwsync_fixup); - do_final_fixups(); - - /* - * Unflatten the device-tree passed by prom_init or kexec - */ - unflatten_device_tree(); - - /* - * Fill the ppc64_caches & systemcfg structures with informations - * retrieved from the device-tree. - */ - initialize_cache_info(); - -#ifdef CONFIG_PPC_RTAS - /* - * Initialize RTAS if available - */ - rtas_initialize(); -#endif /* CONFIG_PPC_RTAS */ - - /* - * Check if we have an initrd provided via the device-tree - */ - check_for_initrd(); - - /* - * Do some platform specific early initializations, that includes - * setting up the hash table pointers. It also sets up some interrupt-mapping - * related options that will be used by finish_device_tree() - */ - if (ppc_md.init_early) - ppc_md.init_early(); - - /* - * We can discover serial ports now since the above did setup the - * hash table management for us, thus ioremap works. We do that early - * so that further code can be debugged - */ - find_legacy_serial_ports(); - - /* - * Register early console - */ - register_early_udbg_console(); - - /* - * Initialize xmon - */ - xmon_setup(); - - smp_setup_cpu_maps(); - check_smt_enabled(); - setup_tlb_core_data(); - - /* - * Freescale Book3e parts spin in a loop provided by firmware, - * so smp_release_cpus() does nothing for them - */ -#if defined(CONFIG_SMP) - /* Release secondary cpus out of their spinloops at 0x60 now that - * we can map physical -> logical CPU ids - */ - smp_release_cpus(); -#endif - - pr_info("Starting Linux %s %s\n", init_utsname()->machine, - init_utsname()->version); - - pr_info("-----------------------------------------------------\n"); - pr_info("ppc64_pft_size = 0x%llx\n", ppc64_pft_size); - pr_info("phys_mem_size = 0x%llx\n", memblock_phys_mem_size()); - - if (ppc64_caches.dline_size != 0x80) - pr_info("dcache_line_size = 0x%x\n", ppc64_caches.dline_size); - if (ppc64_caches.iline_size != 0x80) - pr_info("icache_line_size = 0x%x\n", ppc64_caches.iline_size); - - pr_info("cpu_features = 0x%016lx\n", cur_cpu_spec->cpu_features); - pr_info(" possible = 0x%016lx\n", CPU_FTRS_POSSIBLE); - pr_info(" always = 0x%016lx\n", CPU_FTRS_ALWAYS); - pr_info("cpu_user_features = 0x%08x 0x%08x\n", cur_cpu_spec->cpu_user_features, - cur_cpu_spec->cpu_user_features2); - pr_info("mmu_features = 0x%08x\n", cur_cpu_spec->mmu_features); - pr_info("firmware_features = 0x%016lx\n", powerpc_firmware_features); - -#ifdef CONFIG_PPC_STD_MMU_64 - if (htab_address) - pr_info("htab_address = 0x%p\n", htab_address); - - pr_info("htab_hash_mask = 0x%lx\n", htab_hash_mask); -#endif - - if (PHYSICAL_START > 0) - pr_info("physical_start = 0x%llx\n", - (unsigned long long)PHYSICAL_START); - pr_info("-----------------------------------------------------\n"); + /* For use by binfmt_elf */ + dcache_bsize = ppc64_caches.dline_size; + icache_bsize = ppc64_caches.iline_size; - DBG(" <- setup_system()\n"); + DBG(" <- initialize_cache_info()\n"); } /* This returns the limit below which memory accesses to the linear @@ -584,7 +477,7 @@ void __init setup_system(void) * used to allocate interrupt or emergency stacks for which our * exception entry path doesn't deal with being interrupted. */ -static u64 safe_stack_limit(void) +static __init u64 safe_stack_limit(void) { #ifdef CONFIG_PPC_BOOK3E /* Freescale BookE bolts the entire linear mapping */ @@ -600,7 +493,7 @@ static u64 safe_stack_limit(void) #endif } -static void __init irqstack_early_init(void) +void __init irqstack_early_init(void) { u64 limit = safe_stack_limit(); unsigned int i; @@ -620,7 +513,7 @@ static void __init irqstack_early_init(void) } #ifdef CONFIG_PPC_BOOK3E -static void __init exc_lvl_early_init(void) +void __init exc_lvl_early_init(void) { unsigned int i; unsigned long sp; @@ -642,8 +535,6 @@ static void __init exc_lvl_early_init(void) if (cpu_has_feature(CPU_FTR_DEBUG_LVL_EXC)) patch_exception(0x040, exc_debug_debug_book3e); } -#else -#define exc_lvl_early_init() #endif /* @@ -651,7 +542,7 @@ static void __init exc_lvl_early_init(void) * early in SMP boots before relocation is enabled. Exclusive emergency * stack for machine checks. */ -static void __init emergency_stack_init(void) +void __init emergency_stack_init(void) { u64 limit; unsigned int i; @@ -682,61 +573,6 @@ static void __init emergency_stack_init(void) } } -/* - * Called into from start_kernel this initializes memblock, which is used - * to manage page allocation until mem_init is called. - */ -void __init setup_arch(char **cmdline_p) -{ - *cmdline_p = boot_command_line; - - /* - * Set cache line size based on type of cpu as a default. - * Systems with OF can look in the properties on the cpu node(s) - * for a possibly more accurate value. - */ - dcache_bsize = ppc64_caches.dline_size; - icache_bsize = ppc64_caches.iline_size; - - if (ppc_md.panic) - setup_panic(); - - klp_init_thread_info(&init_thread_info); - - init_mm.start_code = (unsigned long)_stext; - init_mm.end_code = (unsigned long) _etext; - init_mm.end_data = (unsigned long) _edata; - init_mm.brk = klimit; -#ifdef CONFIG_PPC_64K_PAGES - init_mm.context.pte_frag = NULL; -#endif -#ifdef CONFIG_SPAPR_TCE_IOMMU - mm_iommu_init(&init_mm.context); -#endif - irqstack_early_init(); - exc_lvl_early_init(); - emergency_stack_init(); - - initmem_init(); - -#ifdef CONFIG_DUMMY_CONSOLE - conswitchp = &dummy_con; -#endif - - if (ppc_md.setup_arch) - ppc_md.setup_arch(); - - paging_init(); - - /* Initialize the MMU context management stuff */ - mmu_context_init(); - - /* Interrupt code needs to be 64K-aligned */ - if ((unsigned long)_stext & 0xffff) - panic("Kernelbase not 64K-aligned (0x%lx)!\n", - (unsigned long)_stext); -} - #ifdef CONFIG_SMP #define PCPU_DYN_SIZE () diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index b6aa378af..a7daf749b 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -1226,7 +1226,21 @@ long sys_rt_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8, (regs->gpr[1] + __SIGNAL_FRAMESIZE + 16); if (!access_ok(VERIFY_READ, rt_sf, sizeof(*rt_sf))) goto bad; + #ifdef CONFIG_PPC_TRANSACTIONAL_MEM + /* + * If there is a transactional state then throw it away. + * The purpose of a sigreturn is to destroy all traces of the + * signal frame, this includes any transactional state created + * within in. We only check for suspended as we can never be + * active in the kernel, we are active, there is nothing better to + * do than go ahead and Bad Thing later. + * The cause is not important as there will never be a + * recheckpoint so it's not user visible. + */ + if (MSR_TM_SUSPENDED(mfmsr())) + tm_reclaim_current(0); + if (__get_user(tmp, &rt_sf->uc.uc_link)) goto bad; uc_transact = (struct ucontext __user *)(uintptr_t)tmp; diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 25520794a..70409bb90 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -104,6 +104,7 @@ static long setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs, */ #ifdef CONFIG_ALTIVEC elf_vrreg_t __user *v_regs = sigcontext_vmx_regs(sc); + unsigned long vrsave; #endif unsigned long msr = regs->msr; long err = 0; @@ -125,9 +126,13 @@ static long setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs, /* We always copy to/from vrsave, it's 0 if we don't have or don't * use altivec. */ - if (cpu_has_feature(CPU_FTR_ALTIVEC)) - current->thread.vrsave = mfspr(SPRN_VRSAVE); - err |= __put_user(current->thread.vrsave, (u32 __user *)&v_regs[33]); + vrsave = 0; + if (cpu_has_feature(CPU_FTR_ALTIVEC)) { + vrsave = mfspr(SPRN_VRSAVE); + current->thread.vrsave = vrsave; + } + + err |= __put_user(vrsave, (u32 __user *)&v_regs[33]); #else /* CONFIG_ALTIVEC */ err |= __put_user(0, &sc->v_regs); #endif /* CONFIG_ALTIVEC */ @@ -671,7 +676,21 @@ 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; set_current_blocked(&set); + #ifdef CONFIG_PPC_TRANSACTIONAL_MEM + /* + * If there is a transactional state then throw it away. + * The purpose of a sigreturn is to destroy all traces of the + * signal frame, this includes any transactional state created + * within in. We only check for suspended as we can never be + * active in the kernel, we are active, there is nothing better to + * do than go ahead and Bad Thing later. + * The cause is not important as there will never be a + * recheckpoint so it's not user visible. + */ + if (MSR_TM_SUSPENDED(mfmsr())) + tm_reclaim_current(0); + if (__get_user(msr, &uc->uc_mcontext.gp_regs[PT_MSR])) goto badframe; if (MSR_TM_ACTIVE(msr)) { diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 55c924b65..9c6f3fd58 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -31,6 +31,7 @@ #include <linux/cpu.h> #include <linux/notifier.h> #include <linux/topology.h> +#include <linux/profile.h> #include <asm/ptrace.h> #include <linux/atomic.h> @@ -53,6 +54,8 @@ #include <asm/vdso.h> #include <asm/debug.h> #include <asm/kexec.h> +#include <asm/asm-prototypes.h> +#include <asm/cpu_has_feature.h> #ifdef DEBUG #include <asm/udbg.h> @@ -593,6 +596,7 @@ out: of_node_put(np); return id; } +EXPORT_SYMBOL_GPL(cpu_to_core_id); /* Helper routines for cpu to core mapping */ int cpu_core_index_of_thread(int cpu) @@ -826,7 +830,7 @@ int __cpu_disable(void) /* Update sibling maps */ base = cpu_first_thread_sibling(cpu); - for (i = 0; i < threads_per_core; i++) { + for (i = 0; i < threads_per_core && base + i < nr_cpu_ids; i++) { cpumask_clear_cpu(cpu, cpu_sibling_mask(base + i)); cpumask_clear_cpu(base + i, cpu_sibling_mask(cpu)); cpumask_clear_cpu(cpu, cpu_core_mask(base + i)); diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index 692873bff..c4f1d1f7b 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -35,7 +35,7 @@ static DEFINE_PER_CPU(struct cpu, cpu_devices); #ifdef CONFIG_PPC64 /* Time in microseconds we delay before sleeping in the idle loop */ -DEFINE_PER_CPU(long, smt_snooze_delay) = { 100 }; +static DEFINE_PER_CPU(long, smt_snooze_delay) = { 100 }; static ssize_t store_smt_snooze_delay(struct device *dev, struct device_attribute *attr, diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 3ed9a5a21..3efbedefb 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -56,6 +56,7 @@ #include <linux/irq_work.h> #include <linux/clk-provider.h> #include <linux/suspend.h> +#include <linux/rtc.h> #include <asm/trace.h> #include <asm/io.h> @@ -96,7 +97,8 @@ static struct clocksource clocksource_timebase = { .read = timebase_read, }; -#define DECREMENTER_MAX 0x7fffffff +#define DECREMENTER_DEFAULT_MAX 0x7FFFFFFF +u64 decrementer_max = DECREMENTER_DEFAULT_MAX; static int decrementer_set_next_event(unsigned long evt, struct clock_event_device *dev); @@ -166,7 +168,15 @@ DEFINE_PER_CPU(unsigned long, cputime_scaled_last_delta); cputime_t cputime_one_jiffy; +#ifdef CONFIG_PPC_SPLPAR void (*dtl_consumer)(struct dtl_entry *, u64); +#endif + +#ifdef CONFIG_PPC64 +#define get_accounting(tsk) (&get_paca()->accounting) +#else +#define get_accounting(tsk) (&task_thread_info(tsk)->accounting) +#endif static void calc_cputime_factors(void) { @@ -186,7 +196,7 @@ static void calc_cputime_factors(void) * Read the SPURR on systems that have it, otherwise the PURR, * or if that doesn't exist return the timebase value passed in. */ -static u64 read_spurr(u64 tb) +static unsigned long read_spurr(unsigned long tb) { if (cpu_has_feature(CPU_FTR_SPURR)) return mfspr(SPRN_SPURR); @@ -249,8 +259,8 @@ static u64 scan_dispatch_log(u64 stop_tb) void accumulate_stolen_time(void) { u64 sst, ust; - u8 save_soft_enabled = local_paca->soft_enabled; + struct cpu_accounting_data *acct = &local_paca->accounting; /* We are called early in the exception entry, before * soft/hard_enabled are sync'ed to the expected state @@ -260,10 +270,10 @@ void accumulate_stolen_time(void) */ local_paca->soft_enabled = 0; - sst = scan_dispatch_log(local_paca->starttime_user); - ust = scan_dispatch_log(local_paca->starttime); - local_paca->system_time -= sst; - local_paca->user_time -= ust; + sst = scan_dispatch_log(acct->starttime_user); + ust = scan_dispatch_log(acct->starttime); + acct->system_time -= sst; + acct->user_time -= ust; local_paca->stolen_time += ust + sst; local_paca->soft_enabled = save_soft_enabled; @@ -275,7 +285,7 @@ static inline u64 calculate_stolen_time(u64 stop_tb) if (get_paca()->dtl_ridx != be64_to_cpu(get_lppaca()->dtl_idx)) { stolen = scan_dispatch_log(stop_tb); - get_paca()->system_time -= stolen; + get_paca()->accounting.system_time -= stolen; } stolen += get_paca()->stolen_time; @@ -295,27 +305,29 @@ static inline u64 calculate_stolen_time(u64 stop_tb) * Account time for a transition between system, hard irq * or soft irq state. */ -static u64 vtime_delta(struct task_struct *tsk, - u64 *sys_scaled, u64 *stolen) +static unsigned long vtime_delta(struct task_struct *tsk, + unsigned long *sys_scaled, + unsigned long *stolen) { - u64 now, nowscaled, deltascaled; - u64 udelta, delta, user_scaled; + unsigned long now, nowscaled, deltascaled; + unsigned long udelta, delta, user_scaled; + struct cpu_accounting_data *acct = get_accounting(tsk); WARN_ON_ONCE(!irqs_disabled()); now = mftb(); nowscaled = read_spurr(now); - get_paca()->system_time += now - get_paca()->starttime; - get_paca()->starttime = now; - deltascaled = nowscaled - get_paca()->startspurr; - get_paca()->startspurr = nowscaled; + acct->system_time += now - acct->starttime; + acct->starttime = now; + deltascaled = nowscaled - acct->startspurr; + acct->startspurr = nowscaled; *stolen = calculate_stolen_time(now); - delta = get_paca()->system_time; - get_paca()->system_time = 0; - udelta = get_paca()->user_time - get_paca()->utime_sspurr; - get_paca()->utime_sspurr = get_paca()->user_time; + delta = acct->system_time; + acct->system_time = 0; + udelta = acct->user_time - acct->utime_sspurr; + acct->utime_sspurr = acct->user_time; /* * Because we don't read the SPURR on every kernel entry/exit, @@ -337,14 +349,14 @@ static u64 vtime_delta(struct task_struct *tsk, *sys_scaled = deltascaled; } } - get_paca()->user_time_scaled += user_scaled; + acct->user_time_scaled += user_scaled; return delta; } void vtime_account_system(struct task_struct *tsk) { - u64 delta, sys_scaled, stolen; + unsigned long delta, sys_scaled, stolen; delta = vtime_delta(tsk, &sys_scaled, &stolen); account_system_time(tsk, 0, delta, sys_scaled); @@ -355,7 +367,7 @@ EXPORT_SYMBOL_GPL(vtime_account_system); void vtime_account_idle(struct task_struct *tsk) { - u64 delta, sys_scaled, stolen; + unsigned long delta, sys_scaled, stolen; delta = vtime_delta(tsk, &sys_scaled, &stolen); account_idle_time(delta + stolen); @@ -373,15 +385,32 @@ void vtime_account_idle(struct task_struct *tsk) void vtime_account_user(struct task_struct *tsk) { cputime_t utime, utimescaled; + struct cpu_accounting_data *acct = get_accounting(tsk); - utime = get_paca()->user_time; - utimescaled = get_paca()->user_time_scaled; - get_paca()->user_time = 0; - get_paca()->user_time_scaled = 0; - get_paca()->utime_sspurr = 0; + utime = acct->user_time; + utimescaled = acct->user_time_scaled; + acct->user_time = 0; + acct->user_time_scaled = 0; + acct->utime_sspurr = 0; account_user_time(tsk, utime, utimescaled); } +#ifdef CONFIG_PPC32 +/* + * Called from the context switch with interrupts disabled, to charge all + * accumulated times to the current process, and to prepare accounting on + * the next process. + */ +void arch_vtime_task_switch(struct task_struct *prev) +{ + struct cpu_accounting_data *acct = get_accounting(current); + + acct->starttime = get_accounting(prev)->starttime; + acct->system_time = 0; + acct->user_time = 0; +} +#endif /* CONFIG_PPC32 */ + #else /* ! CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ #define calc_cputime_factors() #endif @@ -504,8 +533,8 @@ static void __timer_interrupt(void) __this_cpu_inc(irq_stat.timer_irqs_event); } else { now = *next_tb - now; - if (now <= DECREMENTER_MAX) - set_dec((int)now); + if (now <= decrementer_max) + set_dec(now); /* We may have raced with new irq work */ if (test_irq_work_pending()) set_dec(1); @@ -535,7 +564,7 @@ void timer_interrupt(struct pt_regs * regs) /* Ensure a positive value is written to the decrementer, or else * some CPUs will continue to take decrementer exceptions. */ - set_dec(DECREMENTER_MAX); + set_dec(decrementer_max); /* Some implementations of hotplug will get timer interrupts while * offline, just ignore these and we also need to set @@ -583,9 +612,9 @@ static void generic_suspend_disable_irqs(void) * with suspending. */ - set_dec(DECREMENTER_MAX); + set_dec(decrementer_max); local_irq_disable(); - set_dec(DECREMENTER_MAX); + set_dec(decrementer_max); } static void generic_suspend_enable_irqs(void) @@ -866,7 +895,7 @@ static int decrementer_set_next_event(unsigned long evt, static int decrementer_shutdown(struct clock_event_device *dev) { - decrementer_set_next_event(DECREMENTER_MAX, dev); + decrementer_set_next_event(decrementer_max, dev); return 0; } @@ -892,6 +921,49 @@ static void register_decrementer_clockevent(int cpu) clockevents_register_device(dec); } +static void enable_large_decrementer(void) +{ + if (!cpu_has_feature(CPU_FTR_ARCH_300)) + return; + + if (decrementer_max <= DECREMENTER_DEFAULT_MAX) + return; + + /* + * If we're running as the hypervisor we need to enable the LD manually + * otherwise firmware should have done it for us. + */ + if (cpu_has_feature(CPU_FTR_HVMODE)) + mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) | LPCR_LD); +} + +static void __init set_decrementer_max(void) +{ + struct device_node *cpu; + u32 bits = 32; + + /* Prior to ISAv3 the decrementer is always 32 bit */ + if (!cpu_has_feature(CPU_FTR_ARCH_300)) + return; + + cpu = of_find_node_by_type(NULL, "cpu"); + + if (of_property_read_u32(cpu, "ibm,dec-bits", &bits) == 0) { + if (bits > 64 || bits < 32) { + pr_warn("time_init: firmware supplied invalid ibm,dec-bits"); + bits = 32; + } + + /* calculate the signed maximum given this many bits */ + decrementer_max = (1ul << (bits - 1)) - 1; + } + + of_node_put(cpu); + + pr_info("time_init: %u bit decrementer (max: %llx)\n", + bits, decrementer_max); +} + static void __init init_decrementer_clockevent(void) { int cpu = smp_processor_id(); @@ -899,7 +971,7 @@ static void __init init_decrementer_clockevent(void) clockevents_calc_mult_shift(&decrementer_clockevent, ppc_tb_freq, 4); decrementer_clockevent.max_delta_ns = - clockevent_delta2ns(DECREMENTER_MAX, &decrementer_clockevent); + clockevent_delta2ns(decrementer_max, &decrementer_clockevent); decrementer_clockevent.min_delta_ns = clockevent_delta2ns(2, &decrementer_clockevent); @@ -908,6 +980,9 @@ static void __init init_decrementer_clockevent(void) void secondary_cpu_time_init(void) { + /* Enable and test the large decrementer for this cpu */ + enable_large_decrementer(); + /* Start the decrementer on CPUs that have manual control * such as BookE */ @@ -973,6 +1048,10 @@ void __init time_init(void) vdso_data->tb_update_count = 0; vdso_data->tb_ticks_per_sec = tb_ticks_per_sec; + /* initialise and enable the large decrementer (if we have one) */ + set_decrementer_max(); + enable_large_decrementer(); + /* Start the decrementer on CPUs that have manual control * such as BookE */ @@ -1081,6 +1160,29 @@ void calibrate_delay(void) loops_per_jiffy = tb_ticks_per_jiffy; } +#if IS_ENABLED(CONFIG_RTC_DRV_GENERIC) +static int rtc_generic_get_time(struct device *dev, struct rtc_time *tm) +{ + ppc_md.get_rtc_time(tm); + return rtc_valid_tm(tm); +} + +static int rtc_generic_set_time(struct device *dev, struct rtc_time *tm) +{ + if (!ppc_md.set_rtc_time) + return -EOPNOTSUPP; + + if (ppc_md.set_rtc_time(tm) < 0) + return -EOPNOTSUPP; + + return 0; +} + +static const struct rtc_class_ops rtc_generic_ops = { + .read_time = rtc_generic_get_time, + .set_time = rtc_generic_set_time, +}; + static int __init rtc_init(void) { struct platform_device *pdev; @@ -1088,9 +1190,12 @@ static int __init rtc_init(void) if (!ppc_md.get_rtc_time) return -ENODEV; - pdev = platform_device_register_simple("rtc-generic", -1, NULL, 0); + pdev = platform_device_register_data(NULL, "rtc-generic", -1, + &rtc_generic_ops, + sizeof(rtc_generic_ops)); return PTR_ERR_OR_ZERO(pdev); } device_initcall(rtc_init); +#endif diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 9229ba63c..62859ebe0 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -25,7 +25,8 @@ #include <linux/user.h> #include <linux/interrupt.h> #include <linux/init.h> -#include <linux/module.h> +#include <linux/extable.h> +#include <linux/module.h> /* print_modules */ #include <linux/prctl.h> #include <linux/delay.h> #include <linux/kprobes.h> @@ -60,6 +61,8 @@ #include <asm/switch_to.h> #include <asm/tm.h> #include <asm/debug.h> +#include <asm/asm-prototypes.h> +#include <asm/hmi.h> #include <sysdev/fsl_pci.h> #if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC) @@ -307,9 +310,13 @@ long hmi_exception_realmode(struct pt_regs *regs) { __this_cpu_inc(irq_stat.hmi_exceptions); + wait_for_subcore_guest_exit(); + if (ppc_md.hmi_exception_early) ppc_md.hmi_exception_early(regs); + wait_for_tb_resync(); + return 0; } @@ -1376,6 +1383,7 @@ void facility_unavailable_exception(struct pt_regs *regs) [FSCR_TM_LG] = "TM", [FSCR_EBB_LG] = "EBB", [FSCR_TAR_LG] = "TAR", + [FSCR_LM_LG] = "LM", }; char *facility = "unknown"; u64 value; @@ -1418,7 +1426,8 @@ void facility_unavailable_exception(struct pt_regs *regs) rd = (instword >> 21) & 0x1f; current->thread.dscr = regs->gpr[rd]; current->thread.dscr_inherit = 1; - mtspr(SPRN_FSCR, value | FSCR_DSCR); + current->thread.fscr |= FSCR_DSCR; + mtspr(SPRN_FSCR, current->thread.fscr); } /* Read from DSCR (mfspr RT, 0x03) */ @@ -1432,6 +1441,14 @@ void facility_unavailable_exception(struct pt_regs *regs) emulate_single_step(regs); } return; + } else if ((status == FSCR_LM_LG) && cpu_has_feature(CPU_FTR_ARCH_300)) { + /* + * This process has touched LM, so turn it on forever + * for this process + */ + current->thread.fscr |= FSCR_LM; + mtspr(SPRN_FSCR, current->thread.fscr); + return; } if ((status < ARRAY_SIZE(facility_strings)) && diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index 6767605ea..4111d30ba 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -22,6 +22,7 @@ #include <linux/security.h> #include <linux/memblock.h> +#include <asm/cpu_has_feature.h> #include <asm/pgtable.h> #include <asm/processor.h> #include <asm/mmu.h> diff --git a/arch/powerpc/kernel/vdso32/Makefile b/arch/powerpc/kernel/vdso32/Makefile index cbabd143a..78a7449bf 100644 --- a/arch/powerpc/kernel/vdso32/Makefile +++ b/arch/powerpc/kernel/vdso32/Makefile @@ -30,7 +30,7 @@ CPPFLAGS_vdso32.lds += -P -C -Upowerpc $(obj)/vdso32_wrapper.o : $(obj)/vdso32.so # link rule for the .so file, .lds has to be first -$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) +$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) FORCE $(call if_changed,vdso32ld) # strip rule for the .so file @@ -39,12 +39,12 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE $(call if_changed,objcopy) # assembly rules for the .S files -$(obj-vdso32): %.o: %.S +$(obj-vdso32): %.o: %.S FORCE $(call if_changed_dep,vdso32as) # actual build commands quiet_cmd_vdso32ld = VDSO32L $@ - cmd_vdso32ld = $(CROSS32CC) $(c_flags) -Wl,-T $^ -o $@ + cmd_vdso32ld = $(CROSS32CC) $(c_flags) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) quiet_cmd_vdso32as = VDSO32A $@ cmd_vdso32as = $(CROSS32CC) $(a_flags) -c -o $@ $< diff --git a/arch/powerpc/kernel/vdso64/Makefile b/arch/powerpc/kernel/vdso64/Makefile index c710802b8..366ae09b1 100644 --- a/arch/powerpc/kernel/vdso64/Makefile +++ b/arch/powerpc/kernel/vdso64/Makefile @@ -23,7 +23,7 @@ CPPFLAGS_vdso64.lds += -P -C -U$(ARCH) $(obj)/vdso64_wrapper.o : $(obj)/vdso64.so # link rule for the .so file, .lds has to be first -$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) +$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) FORCE $(call if_changed,vdso64ld) # strip rule for the .so file @@ -32,12 +32,12 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE $(call if_changed,objcopy) # assembly rules for the .S files -$(obj-vdso64): %.o: %.S +$(obj-vdso64): %.o: %.S FORCE $(call if_changed_dep,vdso64as) # actual build commands quiet_cmd_vdso64ld = VDSO64L $@ - cmd_vdso64ld = $(CC) $(c_flags) -Wl,-T $^ -o $@ + cmd_vdso64ld = $(CC) $(c_flags) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) quiet_cmd_vdso64as = VDSO64A $@ cmd_vdso64as = $(CC) $(a_flags) -c -o $@ $< diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S index 1c2e7a343..616a6d854 100644 --- a/arch/powerpc/kernel/vector.S +++ b/arch/powerpc/kernel/vector.S @@ -70,10 +70,11 @@ _GLOBAL(load_up_altivec) MTMSRD(r5) /* enable use of AltiVec now */ isync - /* Hack: if we get an altivec unavailable trap with VRSAVE - * set to all zeros, we assume this is a broken application - * that fails to set it properly, and thus we switch it to - * all 1's + /* + * While userspace in general ignores VRSAVE, glibc uses it as a boolean + * to optimise userspace context save/restore. Whenever we take an + * altivec unavailable exception we must set VRSAVE to something non + * zero. Set it to all 1s. See also the programming note in the ISA. */ mfspr r4,SPRN_VRSAVE cmpwi 0,r4,0 diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c index 8d7358f3a..b3813ddb2 100644 --- a/arch/powerpc/kernel/vio.c +++ b/arch/powerpc/kernel/vio.c @@ -482,7 +482,7 @@ static void vio_cmo_balance(struct work_struct *work) static void *vio_dma_iommu_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag, - struct dma_attrs *attrs) + unsigned long attrs) { struct vio_dev *viodev = to_vio_dev(dev); void *ret; @@ -503,7 +503,7 @@ static void *vio_dma_iommu_alloc_coherent(struct device *dev, size_t size, static void vio_dma_iommu_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle, - struct dma_attrs *attrs) + unsigned long attrs) { struct vio_dev *viodev = to_vio_dev(dev); @@ -515,7 +515,7 @@ static void vio_dma_iommu_free_coherent(struct device *dev, size_t size, static dma_addr_t vio_dma_iommu_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { struct vio_dev *viodev = to_vio_dev(dev); struct iommu_table *tbl; @@ -539,7 +539,7 @@ static dma_addr_t vio_dma_iommu_map_page(struct device *dev, struct page *page, static void vio_dma_iommu_unmap_page(struct device *dev, dma_addr_t dma_handle, size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { struct vio_dev *viodev = to_vio_dev(dev); struct iommu_table *tbl; @@ -552,7 +552,7 @@ static void vio_dma_iommu_unmap_page(struct device *dev, dma_addr_t dma_handle, static int vio_dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist, int nelems, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { struct vio_dev *viodev = to_vio_dev(dev); struct iommu_table *tbl; @@ -588,7 +588,7 @@ static int vio_dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist, static void vio_dma_iommu_unmap_sg(struct device *dev, struct scatterlist *sglist, int nelems, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { struct vio_dev *viodev = to_vio_dev(dev); struct iommu_table *tbl; diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 2dd91f79d..b5fba689f 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -165,7 +165,7 @@ SECTIONS . = ALIGN(8); .dynsym : AT(ADDR(.dynsym) - LOAD_OFFSET) { -#ifdef CONFIG_RELOCATABLE_PPC32 +#ifdef CONFIG_PPC32 __dynamic_symtab = .; #endif *(.dynsym) |