diff options
Diffstat (limited to 'arch/powerpc/kernel')
95 files changed, 2003 insertions, 854 deletions
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index e8b9818..ce4f7f1 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -76,6 +76,7 @@ obj-$(CONFIG_MODULES) += module.o module_$(CONFIG_WORD_SIZE).o obj-$(CONFIG_44x) += cpu_setup_44x.o obj-$(CONFIG_PPC_FSL_BOOK3E) += cpu_setup_fsl_booke.o dbell.o obj-$(CONFIG_PPC_BOOK3E_64) += dbell.o +obj-$(CONFIG_JUMP_LABEL) += jump_label.o extra-y := head_$(CONFIG_WORD_SIZE).o extra-$(CONFIG_40x) := head_40x.o diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 4c12a751..cc20b0a 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -44,10 +44,14 @@ #include <asm/compat.h> #include <asm/mmu.h> #include <asm/hvcall.h> +#include <asm/xics.h> #endif #ifdef CONFIG_PPC_ISERIES #include <asm/iseries/alpaca.h> #endif +#ifdef CONFIG_PPC_POWERNV +#include <asm/opal.h> +#endif #if defined(CONFIG_KVM) || defined(CONFIG_KVM_GUEST) #include <linux/kvm_host.h> #endif @@ -83,6 +87,9 @@ int main(void) DEFINE(KSP, offsetof(struct thread_struct, ksp)); DEFINE(KSP_LIMIT, offsetof(struct thread_struct, ksp_limit)); DEFINE(PT_REGS, offsetof(struct thread_struct, regs)); +#ifdef CONFIG_BOOKE + DEFINE(THREAD_NORMSAVES, offsetof(struct thread_struct, normsave[0])); +#endif DEFINE(THREAD_FPEXC_MODE, offsetof(struct thread_struct, fpexc_mode)); DEFINE(THREAD_FPR0, offsetof(struct thread_struct, fpr[0])); DEFINE(THREAD_FPSCR, offsetof(struct thread_struct, fpscr)); @@ -129,6 +136,7 @@ int main(void) DEFINE(ICACHEL1LINESPERPAGE, offsetof(struct ppc64_caches, ilines_per_page)); /* paca */ DEFINE(PACA_SIZE, sizeof(struct paca_struct)); + DEFINE(PACA_LOCK_TOKEN, offsetof(struct paca_struct, lock_token)); DEFINE(PACAPACAINDEX, offsetof(struct paca_struct, paca_index)); DEFINE(PACAPROCSTART, offsetof(struct paca_struct, cpu_start)); DEFINE(PACAKSAVE, offsetof(struct paca_struct, kstack)); @@ -188,7 +196,9 @@ int main(void) DEFINE(LPPACASRR1, offsetof(struct lppaca, saved_srr1)); DEFINE(LPPACAANYINT, offsetof(struct lppaca, int_dword.any_int)); DEFINE(LPPACADECRINT, offsetof(struct lppaca, int_dword.fields.decr_int)); + DEFINE(LPPACA_PMCINUSE, offsetof(struct lppaca, pmcregs_in_use)); DEFINE(LPPACA_DTLIDX, offsetof(struct lppaca, dtl_idx)); + DEFINE(LPPACA_YIELDCOUNT, offsetof(struct lppaca, yield_count)); DEFINE(PACA_DTL_RIDX, offsetof(struct paca_struct, dtl_ridx)); #endif /* CONFIG_PPC_STD_MMU_64 */ DEFINE(PACAEMERGSP, offsetof(struct paca_struct, emergency_sp)); @@ -199,11 +209,6 @@ int main(void) DEFINE(PACA_USER_TIME, offsetof(struct paca_struct, user_time)); DEFINE(PACA_SYSTEM_TIME, offsetof(struct paca_struct, system_time)); DEFINE(PACA_TRAP_SAVE, offsetof(struct paca_struct, trap_save)); -#ifdef CONFIG_KVM_BOOK3S_64_HANDLER - DEFINE(PACA_KVM_SVCPU, offsetof(struct paca_struct, shadow_vcpu)); - DEFINE(SVCPU_SLB, offsetof(struct kvmppc_book3s_shadow_vcpu, slb)); - DEFINE(SVCPU_SLB_MAX, offsetof(struct kvmppc_book3s_shadow_vcpu, slb_max)); -#endif #endif /* CONFIG_PPC64 */ /* RTAS */ @@ -398,67 +403,160 @@ int main(void) DEFINE(VCPU_HOST_PID, offsetof(struct kvm_vcpu, arch.host_pid)); DEFINE(VCPU_GPRS, offsetof(struct kvm_vcpu, arch.gpr)); DEFINE(VCPU_VRSAVE, offsetof(struct kvm_vcpu, arch.vrsave)); + DEFINE(VCPU_FPRS, offsetof(struct kvm_vcpu, arch.fpr)); + DEFINE(VCPU_FPSCR, offsetof(struct kvm_vcpu, arch.fpscr)); +#ifdef CONFIG_ALTIVEC + DEFINE(VCPU_VRS, offsetof(struct kvm_vcpu, arch.vr)); + DEFINE(VCPU_VSCR, offsetof(struct kvm_vcpu, arch.vscr)); +#endif +#ifdef CONFIG_VSX + DEFINE(VCPU_VSRS, offsetof(struct kvm_vcpu, arch.vsr)); +#endif + DEFINE(VCPU_XER, offsetof(struct kvm_vcpu, arch.xer)); + DEFINE(VCPU_CTR, offsetof(struct kvm_vcpu, arch.ctr)); + DEFINE(VCPU_LR, offsetof(struct kvm_vcpu, arch.lr)); + DEFINE(VCPU_CR, offsetof(struct kvm_vcpu, arch.cr)); + DEFINE(VCPU_PC, offsetof(struct kvm_vcpu, arch.pc)); +#ifdef CONFIG_KVM_BOOK3S_64_HV + DEFINE(VCPU_MSR, offsetof(struct kvm_vcpu, arch.shregs.msr)); + DEFINE(VCPU_SRR0, offsetof(struct kvm_vcpu, arch.shregs.srr0)); + DEFINE(VCPU_SRR1, offsetof(struct kvm_vcpu, arch.shregs.srr1)); + DEFINE(VCPU_SPRG0, offsetof(struct kvm_vcpu, arch.shregs.sprg0)); + DEFINE(VCPU_SPRG1, offsetof(struct kvm_vcpu, arch.shregs.sprg1)); + DEFINE(VCPU_SPRG2, offsetof(struct kvm_vcpu, arch.shregs.sprg2)); + DEFINE(VCPU_SPRG3, offsetof(struct kvm_vcpu, arch.shregs.sprg3)); +#endif DEFINE(VCPU_SPRG4, offsetof(struct kvm_vcpu, arch.sprg4)); DEFINE(VCPU_SPRG5, offsetof(struct kvm_vcpu, arch.sprg5)); DEFINE(VCPU_SPRG6, offsetof(struct kvm_vcpu, arch.sprg6)); DEFINE(VCPU_SPRG7, offsetof(struct kvm_vcpu, arch.sprg7)); DEFINE(VCPU_SHADOW_PID, offsetof(struct kvm_vcpu, arch.shadow_pid)); + DEFINE(VCPU_SHADOW_PID1, offsetof(struct kvm_vcpu, arch.shadow_pid1)); DEFINE(VCPU_SHARED, offsetof(struct kvm_vcpu, arch.shared)); DEFINE(VCPU_SHARED_MSR, offsetof(struct kvm_vcpu_arch_shared, msr)); + DEFINE(VCPU_SHADOW_MSR, offsetof(struct kvm_vcpu, arch.shadow_msr)); /* book3s */ +#ifdef CONFIG_KVM_BOOK3S_64_HV + DEFINE(KVM_LPID, offsetof(struct kvm, arch.lpid)); + DEFINE(KVM_SDR1, offsetof(struct kvm, arch.sdr1)); + DEFINE(KVM_HOST_LPID, offsetof(struct kvm, arch.host_lpid)); + DEFINE(KVM_HOST_LPCR, offsetof(struct kvm, arch.host_lpcr)); + DEFINE(KVM_HOST_SDR1, offsetof(struct kvm, arch.host_sdr1)); + DEFINE(KVM_TLBIE_LOCK, offsetof(struct kvm, arch.tlbie_lock)); + DEFINE(KVM_ONLINE_CPUS, offsetof(struct kvm, online_vcpus.counter)); + DEFINE(KVM_LAST_VCPU, offsetof(struct kvm, arch.last_vcpu)); + DEFINE(KVM_LPCR, offsetof(struct kvm, arch.lpcr)); + DEFINE(KVM_RMOR, offsetof(struct kvm, arch.rmor)); + DEFINE(VCPU_DSISR, offsetof(struct kvm_vcpu, arch.shregs.dsisr)); + DEFINE(VCPU_DAR, offsetof(struct kvm_vcpu, arch.shregs.dar)); +#endif #ifdef CONFIG_PPC_BOOK3S - DEFINE(VCPU_HOST_RETIP, offsetof(struct kvm_vcpu, arch.host_retip)); - DEFINE(VCPU_HOST_MSR, offsetof(struct kvm_vcpu, arch.host_msr)); - DEFINE(VCPU_SHADOW_MSR, offsetof(struct kvm_vcpu, arch.shadow_msr)); - DEFINE(VCPU_TRAMPOLINE_LOWMEM, offsetof(struct kvm_vcpu, arch.trampoline_lowmem)); - DEFINE(VCPU_TRAMPOLINE_ENTER, offsetof(struct kvm_vcpu, arch.trampoline_enter)); - DEFINE(VCPU_HIGHMEM_HANDLER, offsetof(struct kvm_vcpu, arch.highmem_handler)); - DEFINE(VCPU_RMCALL, offsetof(struct kvm_vcpu, arch.rmcall)); + DEFINE(VCPU_KVM, offsetof(struct kvm_vcpu, kvm)); + DEFINE(VCPU_VCPUID, offsetof(struct kvm_vcpu, vcpu_id)); + DEFINE(VCPU_PURR, offsetof(struct kvm_vcpu, arch.purr)); + DEFINE(VCPU_SPURR, offsetof(struct kvm_vcpu, arch.spurr)); + DEFINE(VCPU_DSCR, offsetof(struct kvm_vcpu, arch.dscr)); + DEFINE(VCPU_AMR, offsetof(struct kvm_vcpu, arch.amr)); + DEFINE(VCPU_UAMOR, offsetof(struct kvm_vcpu, arch.uamor)); + DEFINE(VCPU_CTRL, offsetof(struct kvm_vcpu, arch.ctrl)); + DEFINE(VCPU_DABR, offsetof(struct kvm_vcpu, arch.dabr)); DEFINE(VCPU_HFLAGS, offsetof(struct kvm_vcpu, arch.hflags)); + DEFINE(VCPU_DEC, offsetof(struct kvm_vcpu, arch.dec)); + DEFINE(VCPU_DEC_EXPIRES, offsetof(struct kvm_vcpu, arch.dec_expires)); + DEFINE(VCPU_PENDING_EXC, offsetof(struct kvm_vcpu, arch.pending_exceptions)); + DEFINE(VCPU_CEDED, offsetof(struct kvm_vcpu, arch.ceded)); + DEFINE(VCPU_PRODDED, offsetof(struct kvm_vcpu, arch.prodded)); + DEFINE(VCPU_VPA, offsetof(struct kvm_vcpu, arch.vpa)); + DEFINE(VCPU_MMCR, offsetof(struct kvm_vcpu, arch.mmcr)); + DEFINE(VCPU_PMC, offsetof(struct kvm_vcpu, arch.pmc)); + DEFINE(VCPU_SLB, offsetof(struct kvm_vcpu, arch.slb)); + DEFINE(VCPU_SLB_MAX, offsetof(struct kvm_vcpu, arch.slb_max)); + DEFINE(VCPU_SLB_NR, offsetof(struct kvm_vcpu, arch.slb_nr)); + DEFINE(VCPU_LAST_CPU, offsetof(struct kvm_vcpu, arch.last_cpu)); + DEFINE(VCPU_FAULT_DSISR, offsetof(struct kvm_vcpu, arch.fault_dsisr)); + DEFINE(VCPU_FAULT_DAR, offsetof(struct kvm_vcpu, arch.fault_dar)); + DEFINE(VCPU_LAST_INST, offsetof(struct kvm_vcpu, arch.last_inst)); + DEFINE(VCPU_TRAP, offsetof(struct kvm_vcpu, arch.trap)); + DEFINE(VCPU_PTID, offsetof(struct kvm_vcpu, arch.ptid)); + DEFINE(VCORE_ENTRY_EXIT, offsetof(struct kvmppc_vcore, entry_exit_count)); + DEFINE(VCORE_NAP_COUNT, offsetof(struct kvmppc_vcore, nap_count)); + DEFINE(VCORE_IN_GUEST, offsetof(struct kvmppc_vcore, in_guest)); + DEFINE(VCORE_NAPPING_THREADS, offsetof(struct kvmppc_vcore, napping_threads)); DEFINE(VCPU_SVCPU, offsetof(struct kvmppc_vcpu_book3s, shadow_vcpu) - offsetof(struct kvmppc_vcpu_book3s, vcpu)); - DEFINE(SVCPU_CR, offsetof(struct kvmppc_book3s_shadow_vcpu, cr)); - DEFINE(SVCPU_XER, offsetof(struct kvmppc_book3s_shadow_vcpu, xer)); - DEFINE(SVCPU_CTR, offsetof(struct kvmppc_book3s_shadow_vcpu, ctr)); - DEFINE(SVCPU_LR, offsetof(struct kvmppc_book3s_shadow_vcpu, lr)); - DEFINE(SVCPU_PC, offsetof(struct kvmppc_book3s_shadow_vcpu, pc)); - DEFINE(SVCPU_R0, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[0])); - DEFINE(SVCPU_R1, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[1])); - DEFINE(SVCPU_R2, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[2])); - DEFINE(SVCPU_R3, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[3])); - DEFINE(SVCPU_R4, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[4])); - DEFINE(SVCPU_R5, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[5])); - DEFINE(SVCPU_R6, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[6])); - DEFINE(SVCPU_R7, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[7])); - DEFINE(SVCPU_R8, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[8])); - DEFINE(SVCPU_R9, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[9])); - DEFINE(SVCPU_R10, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[10])); - DEFINE(SVCPU_R11, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[11])); - DEFINE(SVCPU_R12, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[12])); - DEFINE(SVCPU_R13, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[13])); - DEFINE(SVCPU_HOST_R1, offsetof(struct kvmppc_book3s_shadow_vcpu, host_r1)); - DEFINE(SVCPU_HOST_R2, offsetof(struct kvmppc_book3s_shadow_vcpu, host_r2)); - DEFINE(SVCPU_VMHANDLER, offsetof(struct kvmppc_book3s_shadow_vcpu, - vmhandler)); - DEFINE(SVCPU_SCRATCH0, offsetof(struct kvmppc_book3s_shadow_vcpu, - scratch0)); - DEFINE(SVCPU_SCRATCH1, offsetof(struct kvmppc_book3s_shadow_vcpu, - scratch1)); - DEFINE(SVCPU_IN_GUEST, offsetof(struct kvmppc_book3s_shadow_vcpu, - in_guest)); - DEFINE(SVCPU_FAULT_DSISR, offsetof(struct kvmppc_book3s_shadow_vcpu, - fault_dsisr)); - DEFINE(SVCPU_FAULT_DAR, offsetof(struct kvmppc_book3s_shadow_vcpu, - fault_dar)); - DEFINE(SVCPU_LAST_INST, offsetof(struct kvmppc_book3s_shadow_vcpu, - last_inst)); - DEFINE(SVCPU_SHADOW_SRR1, offsetof(struct kvmppc_book3s_shadow_vcpu, - shadow_srr1)); + DEFINE(VCPU_SLB_E, offsetof(struct kvmppc_slb, orige)); + DEFINE(VCPU_SLB_V, offsetof(struct kvmppc_slb, origv)); + DEFINE(VCPU_SLB_SIZE, sizeof(struct kvmppc_slb)); + +#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_KVM_BOOK3S_PR +# define SVCPU_FIELD(x, f) DEFINE(x, offsetof(struct paca_struct, shadow_vcpu.f)) +#else +# define SVCPU_FIELD(x, f) +#endif +# define HSTATE_FIELD(x, f) DEFINE(x, offsetof(struct paca_struct, kvm_hstate.f)) +#else /* 32-bit */ +# define SVCPU_FIELD(x, f) DEFINE(x, offsetof(struct kvmppc_book3s_shadow_vcpu, f)) +# define HSTATE_FIELD(x, f) DEFINE(x, offsetof(struct kvmppc_book3s_shadow_vcpu, hstate.f)) +#endif + + SVCPU_FIELD(SVCPU_CR, cr); + SVCPU_FIELD(SVCPU_XER, xer); + SVCPU_FIELD(SVCPU_CTR, ctr); + SVCPU_FIELD(SVCPU_LR, lr); + SVCPU_FIELD(SVCPU_PC, pc); + SVCPU_FIELD(SVCPU_R0, gpr[0]); + SVCPU_FIELD(SVCPU_R1, gpr[1]); + SVCPU_FIELD(SVCPU_R2, gpr[2]); + SVCPU_FIELD(SVCPU_R3, gpr[3]); + SVCPU_FIELD(SVCPU_R4, gpr[4]); + SVCPU_FIELD(SVCPU_R5, gpr[5]); + SVCPU_FIELD(SVCPU_R6, gpr[6]); + SVCPU_FIELD(SVCPU_R7, gpr[7]); + SVCPU_FIELD(SVCPU_R8, gpr[8]); + SVCPU_FIELD(SVCPU_R9, gpr[9]); + SVCPU_FIELD(SVCPU_R10, gpr[10]); + SVCPU_FIELD(SVCPU_R11, gpr[11]); + SVCPU_FIELD(SVCPU_R12, gpr[12]); + SVCPU_FIELD(SVCPU_R13, gpr[13]); + SVCPU_FIELD(SVCPU_FAULT_DSISR, fault_dsisr); + SVCPU_FIELD(SVCPU_FAULT_DAR, fault_dar); + SVCPU_FIELD(SVCPU_LAST_INST, last_inst); + SVCPU_FIELD(SVCPU_SHADOW_SRR1, shadow_srr1); #ifdef CONFIG_PPC_BOOK3S_32 - DEFINE(SVCPU_SR, offsetof(struct kvmppc_book3s_shadow_vcpu, sr)); + SVCPU_FIELD(SVCPU_SR, sr); #endif -#else +#ifdef CONFIG_PPC64 + SVCPU_FIELD(SVCPU_SLB, slb); + SVCPU_FIELD(SVCPU_SLB_MAX, slb_max); +#endif + + HSTATE_FIELD(HSTATE_HOST_R1, host_r1); + HSTATE_FIELD(HSTATE_HOST_R2, host_r2); + HSTATE_FIELD(HSTATE_HOST_MSR, host_msr); + HSTATE_FIELD(HSTATE_VMHANDLER, vmhandler); + HSTATE_FIELD(HSTATE_SCRATCH0, scratch0); + HSTATE_FIELD(HSTATE_SCRATCH1, scratch1); + HSTATE_FIELD(HSTATE_IN_GUEST, in_guest); + HSTATE_FIELD(HSTATE_RESTORE_HID5, restore_hid5); + HSTATE_FIELD(HSTATE_NAPPING, napping); + +#ifdef CONFIG_KVM_BOOK3S_64_HV + HSTATE_FIELD(HSTATE_KVM_VCPU, kvm_vcpu); + HSTATE_FIELD(HSTATE_KVM_VCORE, kvm_vcore); + HSTATE_FIELD(HSTATE_XICS_PHYS, xics_phys); + HSTATE_FIELD(HSTATE_MMCR, host_mmcr); + HSTATE_FIELD(HSTATE_PMC, host_pmc); + HSTATE_FIELD(HSTATE_PURR, host_purr); + HSTATE_FIELD(HSTATE_SPURR, host_spurr); + HSTATE_FIELD(HSTATE_DSCR, host_dscr); + HSTATE_FIELD(HSTATE_DABR, dabr); + HSTATE_FIELD(HSTATE_DECEXP, dec_expires); + DEFINE(IPI_PRIORITY, IPI_PRIORITY); +#endif /* CONFIG_KVM_BOOK3S_64_HV */ + +#else /* CONFIG_PPC_BOOK3S */ DEFINE(VCPU_CR, offsetof(struct kvm_vcpu, arch.cr)); DEFINE(VCPU_XER, offsetof(struct kvm_vcpu, arch.xer)); DEFINE(VCPU_LR, offsetof(struct kvm_vcpu, arch.lr)); @@ -468,7 +566,7 @@ int main(void) DEFINE(VCPU_FAULT_DEAR, offsetof(struct kvm_vcpu, arch.fault_dear)); DEFINE(VCPU_FAULT_ESR, offsetof(struct kvm_vcpu, arch.fault_esr)); #endif /* CONFIG_PPC_BOOK3S */ -#endif +#endif /* CONFIG_KVM */ #ifdef CONFIG_KVM_GUEST DEFINE(KVM_MAGIC_SCRATCH1, offsetof(struct kvm_vcpu_arch_shared, @@ -498,6 +596,13 @@ int main(void) DEFINE(TLBCAM_MAS7, offsetof(struct tlbcam, MAS7)); #endif +#if defined(CONFIG_KVM) && defined(CONFIG_SPE) + DEFINE(VCPU_EVR, offsetof(struct kvm_vcpu, arch.evr[0])); + DEFINE(VCPU_ACC, offsetof(struct kvm_vcpu, arch.acc)); + DEFINE(VCPU_SPEFSCR, offsetof(struct kvm_vcpu, arch.spefscr)); + DEFINE(VCPU_HOST_SPEFSCR, offsetof(struct kvm_vcpu, arch.host_spefscr)); +#endif + #ifdef CONFIG_KVM_EXIT_TIMING DEFINE(VCPU_TIMING_EXIT_TBU, offsetof(struct kvm_vcpu, arch.timing_exit.tv32.tbu)); @@ -509,5 +614,12 @@ int main(void) arch.timing_last_enter.tv32.tbl)); #endif +#ifdef CONFIG_PPC_POWERNV + DEFINE(OPAL_MC_GPR3, offsetof(struct opal_machine_check_event, gpr3)); + DEFINE(OPAL_MC_SRR0, offsetof(struct opal_machine_check_event, srr0)); + DEFINE(OPAL_MC_SRR1, offsetof(struct opal_machine_check_event, srr1)); + DEFINE(PACA_OPAL_MC_EVT, offsetof(struct paca_struct, opal_mc_evt)); +#endif + return 0; } diff --git a/arch/powerpc/kernel/btext.c b/arch/powerpc/kernel/btext.c index 60b3e37..ac8f527 100644 --- a/arch/powerpc/kernel/btext.c +++ b/arch/powerpc/kernel/btext.c @@ -6,7 +6,7 @@ #include <linux/kernel.h> #include <linux/string.h> #include <linux/init.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/memblock.h> #include <asm/sections.h> diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c index a3c684b..4f15565 100644 --- a/arch/powerpc/kernel/cacheinfo.c +++ b/arch/powerpc/kernel/cacheinfo.c @@ -62,12 +62,22 @@ struct cache_type_info { }; /* These are used to index the cache_type_info array. */ -#define CACHE_TYPE_UNIFIED 0 -#define CACHE_TYPE_INSTRUCTION 1 -#define CACHE_TYPE_DATA 2 +#define CACHE_TYPE_UNIFIED 0 /* cache-size, cache-block-size, etc. */ +#define CACHE_TYPE_UNIFIED_D 1 /* d-cache-size, d-cache-block-size, etc */ +#define CACHE_TYPE_INSTRUCTION 2 +#define CACHE_TYPE_DATA 3 static const struct cache_type_info cache_type_info[] = { { + /* Embedded systems that use cache-size, cache-block-size, + * etc. for the Unified (typically L2) cache. */ + .name = "Unified", + .size_prop = "cache-size", + .line_size_props = { "cache-line-size", + "cache-block-size", }, + .nr_sets_prop = "cache-sets", + }, + { /* PowerPC Processor binding says the [di]-cache-* * must be equal on unified caches, so just use * d-cache properties. */ @@ -293,7 +303,8 @@ static struct cache *cache_find_first_sibling(struct cache *cache) { struct cache *iter; - if (cache->type == CACHE_TYPE_UNIFIED) + if (cache->type == CACHE_TYPE_UNIFIED || + cache->type == CACHE_TYPE_UNIFIED_D) return cache; list_for_each_entry(iter, &cache_list, list) @@ -324,15 +335,29 @@ static bool cache_node_is_unified(const struct device_node *np) return of_get_property(np, "cache-unified", NULL); } -static struct cache *__cpuinit cache_do_one_devnode_unified(struct device_node *node, int level) +/* + * Unified caches can have two different sets of tags. Most embedded + * use cache-size, etc. for the unified cache size, but open firmware systems + * use d-cache-size, etc. Check on initialization for which type we have, and + * return the appropriate structure type. Assume it's embedded if it isn't + * open firmware. If it's yet a 3rd type, then there will be missing entries + * in /sys/devices/system/cpu/cpu0/cache/index2/, and this code will need + * to be extended further. + */ +static int cache_is_unified_d(const struct device_node *np) { - struct cache *cache; + return of_get_property(np, + cache_type_info[CACHE_TYPE_UNIFIED_D].size_prop, NULL) ? + CACHE_TYPE_UNIFIED_D : CACHE_TYPE_UNIFIED; +} +/* + */ +static struct cache *__cpuinit cache_do_one_devnode_unified(struct device_node *node, int level) +{ pr_debug("creating L%d ucache for %s\n", level, node->full_name); - cache = new_cache(CACHE_TYPE_UNIFIED, level, node); - - return cache; + return new_cache(cache_is_unified_d(node), level, node); } static struct cache *__cpuinit cache_do_one_devnode_split(struct device_node *node, int level) @@ -788,6 +813,9 @@ static void remove_cache_dir(struct cache_dir *cache_dir) { remove_index_dirs(cache_dir); + /* Remove cache dir from sysfs */ + kobject_del(cache_dir->kobj); + kobject_put(cache_dir->kobj); kfree(cache_dir); diff --git a/arch/powerpc/kernel/clock.c b/arch/powerpc/kernel/clock.c index ce668f5..a764b47 100644 --- a/arch/powerpc/kernel/clock.c +++ b/arch/powerpc/kernel/clock.c @@ -6,7 +6,7 @@ #include <linux/clk.h> #include <linux/err.h> #include <linux/errno.h> -#include <linux/module.h> +#include <linux/export.h> #include <asm/clk_interface.h> struct clk_interface clk_functions; diff --git a/arch/powerpc/kernel/cpu_setup_power7.S b/arch/powerpc/kernel/cpu_setup_power7.S index 4f9a93f..76797c5 100644 --- a/arch/powerpc/kernel/cpu_setup_power7.S +++ b/arch/powerpc/kernel/cpu_setup_power7.S @@ -45,12 +45,12 @@ _GLOBAL(__restore_cpu_power7) blr __init_hvmode_206: - /* Disable CPU_FTR_HVMODE_206 and exit if MSR:HV is not set */ + /* Disable CPU_FTR_HVMODE and exit if MSR:HV is not set */ mfmsr r3 rldicl. r0,r3,4,63 bnelr ld r5,CPU_SPEC_FEATURES(r4) - LOAD_REG_IMMEDIATE(r6,CPU_FTR_HVMODE_206) + LOAD_REG_IMMEDIATE(r6,CPU_FTR_HVMODE) xor r5,r5,r6 std r5,CPU_SPEC_FEATURES(r4) blr @@ -61,19 +61,23 @@ __init_LPCR: * LPES = 0b01 (HSRR0/1 used for 0x500) * PECE = 0b111 * DPFD = 4 + * HDICE = 0 + * VC = 0b100 (VPM0=1, VPM1=0, ISL=0) + * VRMASD = 0b10000 (L=1, LP=00) * * Other bits untouched for now */ mfspr r3,SPRN_LPCR - ori r3,r3,(LPCR_LPES0|LPCR_LPES1) - xori r3,r3, LPCR_LPES0 + li r5,1 + rldimi r3,r5, LPCR_LPES_SH, 64-LPCR_LPES_SH-2 ori r3,r3,(LPCR_PECE0|LPCR_PECE1|LPCR_PECE2) - li r5,7 - sldi r5,r5,LPCR_DPFD_SH - andc r3,r3,r5 li r5,4 - sldi r5,r5,LPCR_DPFD_SH - or r3,r3,r5 + rldimi r3,r5, LPCR_DPFD_SH, 64-LPCR_DPFD_SH-3 + clrrdi r3,r3,1 /* clear HDICE */ + li r5,4 + rldimi r3,r5, LPCR_VC_SH, 0 + li r5,0x10 + rldimi r3,r5, LPCR_VRMASD_SH, 64-LPCR_VRMASD_SH-5 mtspr SPRN_LPCR,r3 isync blr diff --git a/arch/powerpc/kernel/cpu_setup_ppc970.S b/arch/powerpc/kernel/cpu_setup_ppc970.S index 27f2507..12fac8d 100644 --- a/arch/powerpc/kernel/cpu_setup_ppc970.S +++ b/arch/powerpc/kernel/cpu_setup_ppc970.S @@ -76,7 +76,7 @@ _GLOBAL(__setup_cpu_ppc970) /* Do nothing if not running in HV mode */ mfmsr r0 rldicl. r0,r0,4,63 - beqlr + beq no_hv_mode mfspr r0,SPRN_HID0 li r11,5 /* clear DOZE and SLEEP */ @@ -90,7 +90,7 @@ _GLOBAL(__setup_cpu_ppc970MP) /* Do nothing if not running in HV mode */ mfmsr r0 rldicl. r0,r0,4,63 - beqlr + beq no_hv_mode mfspr r0,SPRN_HID0 li r11,0x15 /* clear DOZE and SLEEP */ @@ -109,6 +109,14 @@ load_hids: sync isync + /* Try to set LPES = 01 in HID4 */ + mfspr r0,SPRN_HID4 + clrldi r0,r0,1 /* clear LPES0 */ + ori r0,r0,HID4_LPES1 /* set LPES1 */ + sync + mtspr SPRN_HID4,r0 + isync + /* Save away cpu state */ LOAD_REG_ADDR(r5,cpu_state_storage) @@ -117,11 +125,21 @@ load_hids: std r3,CS_HID0(r5) mfspr r3,SPRN_HID1 std r3,CS_HID1(r5) - mfspr r3,SPRN_HID4 - std r3,CS_HID4(r5) + mfspr r4,SPRN_HID4 + std r4,CS_HID4(r5) mfspr r3,SPRN_HID5 std r3,CS_HID5(r5) + /* See if we successfully set LPES1 to 1; if not we are in Apple mode */ + andi. r4,r4,HID4_LPES1 + bnelr + +no_hv_mode: + /* Disable CPU_FTR_HVMODE and exit, since we don't have HV mode */ + ld r5,CPU_SPEC_FEATURES(r4) + LOAD_REG_IMMEDIATE(r6,CPU_FTR_HVMODE) + andc r5,r5,r6 + std r5,CPU_SPEC_FEATURES(r4) blr /* Called with no MMU context (typically MSR:IR/DR off) to diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 421c9a0..b92b756 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -14,7 +14,7 @@ #include <linux/sched.h> #include <linux/threads.h> #include <linux/init.h> -#include <linux/module.h> +#include <linux/export.h> #include <asm/oprofile_impl.h> #include <asm/cputable.h> @@ -2051,7 +2051,8 @@ static struct cpu_spec __initdata cpu_specs[] = { static struct cpu_spec the_cpu_spec; -static void __init setup_cpu_spec(unsigned long offset, struct cpu_spec *s) +static struct cpu_spec * __init setup_cpu_spec(unsigned long offset, + struct cpu_spec *s) { struct cpu_spec *t = &the_cpu_spec; struct cpu_spec old; @@ -2114,6 +2115,8 @@ static void __init setup_cpu_spec(unsigned long offset, struct cpu_spec *s) t->cpu_setup(offset, t); } #endif /* CONFIG_PPC64 || CONFIG_BOOKE */ + + return t; } struct cpu_spec * __init identify_cpu(unsigned long offset, unsigned int pvr) @@ -2124,10 +2127,8 @@ struct cpu_spec * __init identify_cpu(unsigned long offset, unsigned int pvr) s = PTRRELOC(s); for (i = 0; i < ARRAY_SIZE(cpu_specs); i++,s++) { - if ((pvr & s->pvr_mask) == s->pvr_value) { - setup_cpu_spec(offset, s); - return s; - } + if ((pvr & s->pvr_mask) == s->pvr_value) + return setup_cpu_spec(offset, s); } BUG(); diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c index cc6a9d5..d879809 100644 --- a/arch/powerpc/kernel/crash.c +++ b/arch/powerpc/kernel/crash.c @@ -17,6 +17,7 @@ #include <linux/reboot.h> #include <linux/kexec.h> #include <linux/bootmem.h> +#include <linux/export.h> #include <linux/crash_dump.h> #include <linux/delay.h> #include <linux/elf.h> diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c index 424afb6..39787c9 100644 --- a/arch/powerpc/kernel/crash_dump.c +++ b/arch/powerpc/kernel/crash_dump.c @@ -108,17 +108,19 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf, size_t csize, unsigned long offset, int userbuf) { void *vaddr; + phys_addr_t paddr; if (!csize) return 0; csize = min_t(size_t, csize, PAGE_SIZE); + paddr = pfn << PAGE_SHIFT; - if ((min_low_pfn < pfn) && (pfn < max_pfn)) { - vaddr = __va(pfn << PAGE_SHIFT); + if (memblock_is_region_memory(paddr, csize)) { + vaddr = __va(paddr); csize = copy_oldmem_vaddr(vaddr, buf, csize, offset, userbuf); } else { - vaddr = __ioremap(pfn << PAGE_SHIFT, PAGE_SIZE, 0); + vaddr = __ioremap(paddr, PAGE_SIZE, 0); csize = copy_oldmem_vaddr(vaddr, buf, csize, offset, userbuf); iounmap(vaddr); } diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c index 2cc451a..6856062 100644 --- a/arch/powerpc/kernel/dbell.c +++ b/arch/powerpc/kernel/dbell.c @@ -28,6 +28,8 @@ void doorbell_setup_this_cpu(void) void doorbell_cause_ipi(int cpu, unsigned long data) { + /* Order previous accesses vs. msgsnd, which is treated as a store */ + mb(); ppc_msgsnd(PPC_DBELL, 0, data); } diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c index e755415..3f6464b 100644 --- a/arch/powerpc/kernel/dma-iommu.c +++ b/arch/powerpc/kernel/dma-iommu.c @@ -5,6 +5,7 @@ * busses using the iommu infrastructure */ +#include <linux/export.h> #include <asm/iommu.h> /* @@ -90,13 +91,27 @@ static int dma_iommu_dma_supported(struct device *dev, u64 mask) return 1; } +static u64 dma_iommu_get_required_mask(struct device *dev) +{ + struct iommu_table *tbl = get_iommu_table_base(dev); + u64 mask; + if (!tbl) + return 0; + + mask = 1ULL < (fls_long(tbl->it_offset + tbl->it_size) - 1); + mask += mask - 1; + + return mask; +} + struct dma_map_ops dma_iommu_ops = { - .alloc_coherent = dma_iommu_alloc_coherent, - .free_coherent = dma_iommu_free_coherent, - .map_sg = dma_iommu_map_sg, - .unmap_sg = dma_iommu_unmap_sg, - .dma_supported = dma_iommu_dma_supported, - .map_page = dma_iommu_map_page, - .unmap_page = dma_iommu_unmap_page, + .alloc_coherent = dma_iommu_alloc_coherent, + .free_coherent = dma_iommu_free_coherent, + .map_sg = dma_iommu_map_sg, + .unmap_sg = dma_iommu_unmap_sg, + .dma_supported = dma_iommu_dma_supported, + .map_page = dma_iommu_map_page, + .unmap_page = dma_iommu_unmap_page, + .get_required_mask = dma_iommu_get_required_mask, }; EXPORT_SYMBOL(dma_iommu_ops); diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c index 4295e0b..1ebc918 100644 --- a/arch/powerpc/kernel/dma-swiotlb.c +++ b/arch/powerpc/kernel/dma-swiotlb.c @@ -24,6 +24,21 @@ unsigned int ppc_swiotlb_enable; +static u64 swiotlb_powerpc_get_required(struct device *dev) +{ + u64 end, mask, max_direct_dma_addr = dev->archdata.max_direct_dma_addr; + + end = memblock_end_of_DRAM(); + if (max_direct_dma_addr && end > max_direct_dma_addr) + end = max_direct_dma_addr; + end += get_dma_offset(dev); + + mask = 1ULL << (fls64(end) - 1); + mask += mask - 1; + + return mask; +} + /* * At the moment, all platforms that use this code only require * swiotlb to be used if we're operating on HIGHMEM. Since @@ -44,6 +59,7 @@ struct dma_map_ops swiotlb_dma_ops = { .sync_sg_for_cpu = swiotlb_sync_sg_for_cpu, .sync_sg_for_device = swiotlb_sync_sg_for_device, .mapping_error = swiotlb_dma_mapping_error, + .get_required_mask = swiotlb_powerpc_get_required, }; void pci_dma_dev_setup_swiotlb(struct pci_dev *pdev) diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c index d238c08..7d0233c 100644 --- a/arch/powerpc/kernel/dma.c +++ b/arch/powerpc/kernel/dma.c @@ -10,6 +10,7 @@ #include <linux/dma-debug.h> #include <linux/gfp.h> #include <linux/memblock.h> +#include <linux/export.h> #include <asm/bug.h> #include <asm/abs_addr.h> #include <asm/machdep.h> @@ -96,6 +97,18 @@ static int dma_direct_dma_supported(struct device *dev, u64 mask) #endif } +static u64 dma_direct_get_required_mask(struct device *dev) +{ + u64 end, mask; + + end = memblock_end_of_DRAM() + get_dma_offset(dev); + + mask = 1ULL << (fls64(end) - 1); + mask += mask - 1; + + return mask; +} + static inline dma_addr_t dma_direct_map_page(struct device *dev, struct page *page, unsigned long offset, @@ -137,13 +150,14 @@ static inline void dma_direct_sync_single(struct device *dev, #endif struct dma_map_ops dma_direct_ops = { - .alloc_coherent = dma_direct_alloc_coherent, - .free_coherent = dma_direct_free_coherent, - .map_sg = dma_direct_map_sg, - .unmap_sg = dma_direct_unmap_sg, - .dma_supported = dma_direct_dma_supported, - .map_page = dma_direct_map_page, - .unmap_page = dma_direct_unmap_page, + .alloc_coherent = dma_direct_alloc_coherent, + .free_coherent = dma_direct_free_coherent, + .map_sg = dma_direct_map_sg, + .unmap_sg = dma_direct_unmap_sg, + .dma_supported = dma_direct_dma_supported, + .map_page = dma_direct_map_page, + .unmap_page = dma_direct_unmap_page, + .get_required_mask = dma_direct_get_required_mask, #ifdef CONFIG_NOT_COHERENT_CACHE .sync_single_for_cpu = dma_direct_sync_single, .sync_single_for_device = dma_direct_sync_single, @@ -161,9 +175,7 @@ int dma_set_mask(struct device *dev, u64 dma_mask) if (ppc_md.dma_set_mask) return ppc_md.dma_set_mask(dev, dma_mask); - if (unlikely(dma_ops == NULL)) - return -EIO; - if (dma_ops->set_dma_mask != NULL) + if ((dma_ops != NULL) && (dma_ops->set_dma_mask != NULL)) return dma_ops->set_dma_mask(dev, dma_mask); if (!dev->dma_mask || !dma_supported(dev, dma_mask)) return -EIO; @@ -172,6 +184,23 @@ int dma_set_mask(struct device *dev, u64 dma_mask) } EXPORT_SYMBOL(dma_set_mask); +u64 dma_get_required_mask(struct device *dev) +{ + struct dma_map_ops *dma_ops = get_dma_ops(dev); + + if (ppc_md.dma_get_required_mask) + return ppc_md.dma_get_required_mask(dev); + + if (unlikely(dma_ops == NULL)) + return 0; + + if (dma_ops->get_required_mask) + return dma_ops->get_required_mask(dev); + + return DMA_BIT_MASK(8 * sizeof(dma_addr_t)); +} +EXPORT_SYMBOL_GPL(dma_get_required_mask); + static int __init dma_init(void) { dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES); diff --git a/arch/powerpc/kernel/e500-pmu.c b/arch/powerpc/kernel/e500-pmu.c index b150b51..cb2e294 100644 --- a/arch/powerpc/kernel/e500-pmu.c +++ b/arch/powerpc/kernel/e500-pmu.c @@ -75,6 +75,11 @@ static int e500_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { [C(OP_WRITE)] = { -1, -1 }, [C(OP_PREFETCH)] = { -1, -1 }, }, + [C(NODE)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { -1, -1 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, }; static int num_events = 128; diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 56212bc..4f80cf1 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -215,7 +215,22 @@ reenable_mmu: /* re-enable mmu so we can */ stw r9,8(r1) stw r11,12(r1) stw r3,ORIG_GPR3(r1) + /* + * The trace_hardirqs_off will use CALLER_ADDR0 and CALLER_ADDR1. + * If from user mode there is only one stack frame on the stack, and + * accessing CALLER_ADDR1 will cause oops. So we need create a dummy + * stack frame to make trace_hardirqs_off happy. + */ + andi. r12,r12,MSR_PR + beq 11f + stwu r1,-16(r1) + bl trace_hardirqs_off + addi r1,r1,16 + b 12f + +11: bl trace_hardirqs_off +12: lwz r0,GPR0(r1) lwz r3,ORIG_GPR3(r1) lwz r4,GPR4(r1) diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index d24d440..429983c 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -120,6 +120,12 @@ std r14,PACA_EXMC+EX_R14(r13); \ std r15,PACA_EXMC+EX_R15(r13) +#define PROLOG_ADDITION_DOORBELL_GEN \ + lbz r11,PACASOFTIRQEN(r13); /* are irqs soft-disabled ? */ \ + cmpwi cr0,r11,0; /* yes -> go out of line */ \ + beq masked_doorbell_book3e + + /* Core exception code for all exceptions except TLB misses. * XXX: Needs to make SPRN_SPRG_GEN depend on exception type */ @@ -522,7 +528,13 @@ kernel_dbg_exc: MASKABLE_EXCEPTION(0x260, perfmon, .performance_monitor_exception, ACK_NONE) /* Doorbell interrupt */ - MASKABLE_EXCEPTION(0x2070, doorbell, .doorbell_exception, ACK_NONE) + START_EXCEPTION(doorbell) + NORMAL_EXCEPTION_PROLOG(0x2070, PROLOG_ADDITION_DOORBELL) + EXCEPTION_COMMON(0x2070, PACA_EXGEN, INTS_DISABLE_ALL) + CHECK_NAPPING() + addi r3,r1,STACK_FRAME_OVERHEAD + bl .doorbell_exception + b .ret_from_except_lite /* Doorbell critical Interrupt */ START_EXCEPTION(doorbell_crit); @@ -545,8 +557,16 @@ kernel_dbg_exc: * An interrupt came in while soft-disabled; clear EE in SRR1, * clear paca->hard_enabled and return. */ +masked_doorbell_book3e: + mtcr r10 + /* Resend the doorbell to fire again when ints enabled */ + mfspr r10,SPRN_PIR + PPC_MSGSND(r10) + b masked_interrupt_book3e_common + masked_interrupt_book3e: mtcr r10 +masked_interrupt_book3e_common: stb r11,PACAHARDIRQEN(r13) mfspr r10,SPRN_SRR1 rldicl r11,r10,48,1 /* clear MSR_EE */ diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index a85f487..8c3baa0 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -40,7 +40,6 @@ __start_interrupts: .globl system_reset_pSeries; system_reset_pSeries: HMT_MEDIUM; - DO_KVM 0x100; SET_SCRATCH0(r13) #ifdef CONFIG_PPC_P7_NAP BEGIN_FTR_SECTION @@ -50,82 +49,73 @@ BEGIN_FTR_SECTION * state loss at this time. */ mfspr r13,SPRN_SRR1 - rlwinm r13,r13,47-31,30,31 - cmpwi cr0,r13,1 - bne 1f - b .power7_wakeup_noloss -1: cmpwi cr0,r13,2 - bne 1f - b .power7_wakeup_loss + rlwinm. r13,r13,47-31,30,31 + beq 9f + + /* waking up from powersave (nap) state */ + cmpwi cr1,r13,2 /* Total loss of HV state is fatal, we could try to use the * PIR to locate a PACA, then use an emergency stack etc... * but for now, let's just stay stuck here */ -1: cmpwi cr0,r13,3 - beq . -END_FTR_SECTION_IFSET(CPU_FTR_HVMODE_206) + bgt cr1,. + GET_PACA(r13) + +#ifdef CONFIG_KVM_BOOK3S_64_HV + lbz r0,PACAPROCSTART(r13) + cmpwi r0,0x80 + bne 1f + li r0,0 + stb r0,PACAPROCSTART(r13) + b kvm_start_guest +1: +#endif + + beq cr1,2f + b .power7_wakeup_noloss +2: b .power7_wakeup_loss +9: +END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) #endif /* CONFIG_PPC_P7_NAP */ - EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD) + EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD, + NOTEST, 0x100) . = 0x200 -_machine_check_pSeries: - HMT_MEDIUM - DO_KVM 0x200 - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common, EXC_STD) +machine_check_pSeries_1: + /* This is moved out of line as it can be patched by FW, but + * some code path might still want to branch into the original + * vector + */ + b machine_check_pSeries . = 0x300 .globl data_access_pSeries data_access_pSeries: HMT_MEDIUM - DO_KVM 0x300 SET_SCRATCH0(r13) +#ifndef CONFIG_POWER4_ONLY BEGIN_FTR_SECTION - GET_PACA(r13) - std r9,PACA_EXSLB+EX_R9(r13) - std r10,PACA_EXSLB+EX_R10(r13) - mfspr r10,SPRN_DAR - mfspr r9,SPRN_DSISR - srdi r10,r10,60 - rlwimi r10,r9,16,0x20 - mfcr r9 - cmpwi r10,0x2c - beq do_stab_bolted_pSeries - ld r10,PACA_EXSLB+EX_R10(r13) - std r11,PACA_EXGEN+EX_R11(r13) - ld r11,PACA_EXSLB+EX_R9(r13) - std r12,PACA_EXGEN+EX_R12(r13) - GET_SCRATCH0(r12) - std r10,PACA_EXGEN+EX_R10(r13) - std r11,PACA_EXGEN+EX_R9(r13) - std r12,PACA_EXGEN+EX_R13(r13) - EXCEPTION_PROLOG_PSERIES_1(data_access_common, EXC_STD) -FTR_SECTION_ELSE - EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, data_access_common, EXC_STD) -ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_SLB) + b data_access_check_stab +data_access_not_stab: +END_MMU_FTR_SECTION_IFCLR(MMU_FTR_SLB) +#endif + EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, data_access_common, EXC_STD, + KVMTEST_PR, 0x300) . = 0x380 .globl data_access_slb_pSeries data_access_slb_pSeries: HMT_MEDIUM - DO_KVM 0x380 SET_SCRATCH0(r13) - GET_PACA(r13) + EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST_PR, 0x380) std r3,PACA_EXSLB+EX_R3(r13) mfspr r3,SPRN_DAR - std r9,PACA_EXSLB+EX_R9(r13) /* save r9 - r12 */ - mfcr r9 #ifdef __DISABLED__ /* Keep that around for when we re-implement dynamic VSIDs */ cmpdi r3,0 bge slb_miss_user_pseries #endif /* __DISABLED__ */ - std r10,PACA_EXSLB+EX_R10(r13) - std r11,PACA_EXSLB+EX_R11(r13) - std r12,PACA_EXSLB+EX_R12(r13) - GET_SCRATCH0(r10) - std r10,PACA_EXSLB+EX_R13(r13) - mfspr r12,SPRN_SRR1 /* and SRR1 */ + mfspr r12,SPRN_SRR1 #ifndef CONFIG_RELOCATABLE b .slb_miss_realmode #else @@ -147,24 +137,16 @@ data_access_slb_pSeries: .globl instruction_access_slb_pSeries instruction_access_slb_pSeries: HMT_MEDIUM - DO_KVM 0x480 SET_SCRATCH0(r13) - GET_PACA(r13) + EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST_PR, 0x480) std r3,PACA_EXSLB+EX_R3(r13) mfspr r3,SPRN_SRR0 /* SRR0 is faulting address */ - std r9,PACA_EXSLB+EX_R9(r13) /* save r9 - r12 */ - mfcr r9 #ifdef __DISABLED__ /* Keep that around for when we re-implement dynamic VSIDs */ cmpdi r3,0 bge slb_miss_user_pseries #endif /* __DISABLED__ */ - std r10,PACA_EXSLB+EX_R10(r13) - std r11,PACA_EXSLB+EX_R11(r13) - std r12,PACA_EXSLB+EX_R12(r13) - GET_SCRATCH0(r10) - std r10,PACA_EXSLB+EX_R13(r13) - mfspr r12,SPRN_SRR1 /* and SRR1 */ + mfspr r12,SPRN_SRR1 #ifndef CONFIG_RELOCATABLE b .slb_miss_realmode #else @@ -184,26 +166,46 @@ instruction_access_slb_pSeries: hardware_interrupt_pSeries: hardware_interrupt_hv: BEGIN_FTR_SECTION - _MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt, EXC_STD) + _MASKABLE_EXCEPTION_PSERIES(0x502, hardware_interrupt, + EXC_HV, SOFTEN_TEST_HV) + KVM_HANDLER(PACA_EXGEN, EXC_HV, 0x502) FTR_SECTION_ELSE - _MASKABLE_EXCEPTION_PSERIES(0x502, hardware_interrupt, EXC_HV) - ALT_FTR_SECTION_END_IFCLR(CPU_FTR_HVMODE_206) + _MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt, + EXC_STD, SOFTEN_TEST_HV_201) + KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x500) + ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) STD_EXCEPTION_PSERIES(0x600, 0x600, alignment) + KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x600) + STD_EXCEPTION_PSERIES(0x700, 0x700, program_check) + KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x700) + STD_EXCEPTION_PSERIES(0x800, 0x800, fp_unavailable) + KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x800) MASKABLE_EXCEPTION_PSERIES(0x900, 0x900, decrementer) - MASKABLE_EXCEPTION_HV(0x980, 0x980, decrementer) + MASKABLE_EXCEPTION_HV(0x980, 0x982, decrementer) STD_EXCEPTION_PSERIES(0xa00, 0xa00, trap_0a) + KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xa00) + STD_EXCEPTION_PSERIES(0xb00, 0xb00, trap_0b) + KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xb00) . = 0xc00 .globl system_call_pSeries system_call_pSeries: HMT_MEDIUM - DO_KVM 0xc00 +#ifdef CONFIG_KVM_BOOK3S_64_HANDLER + SET_SCRATCH0(r13) + GET_PACA(r13) + std r9,PACA_EXGEN+EX_R9(r13) + std r10,PACA_EXGEN+EX_R10(r13) + mfcr r9 + KVMTEST(0xc00) + GET_SCRATCH0(r13) +#endif BEGIN_FTR_SECTION cmpdi r0,0x1ebe beq- 1f @@ -220,6 +222,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE) rfid b . /* prevent speculative execution */ + KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xc00) + /* Fast LE/BE switch system call */ 1: mfspr r12,SPRN_SRR1 xori r12,r12,MSR_LE @@ -228,6 +232,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE) b . STD_EXCEPTION_PSERIES(0xd00, 0xd00, single_step) + KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xd00) /* At 0xe??? we have a bunch of hypervisor exceptions, we branch * out of line to handle them @@ -262,30 +267,93 @@ vsx_unavailable_pSeries_1: #ifdef CONFIG_CBE_RAS STD_EXCEPTION_HV(0x1200, 0x1202, cbe_system_error) + KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0x1202) #endif /* CONFIG_CBE_RAS */ + STD_EXCEPTION_PSERIES(0x1300, 0x1300, instruction_breakpoint) + KVM_HANDLER_PR_SKIP(PACA_EXGEN, EXC_STD, 0x1300) + #ifdef CONFIG_CBE_RAS STD_EXCEPTION_HV(0x1600, 0x1602, cbe_maintenance) + KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0x1602) #endif /* CONFIG_CBE_RAS */ + STD_EXCEPTION_PSERIES(0x1700, 0x1700, altivec_assist) + KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x1700) + #ifdef CONFIG_CBE_RAS STD_EXCEPTION_HV(0x1800, 0x1802, cbe_thermal) + KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0x1802) #endif /* CONFIG_CBE_RAS */ . = 0x3000 /*** Out of line interrupts support ***/ + /* moved from 0x200 */ +machine_check_pSeries: + .globl machine_check_fwnmi +machine_check_fwnmi: + HMT_MEDIUM + SET_SCRATCH0(r13) /* save r13 */ + EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common, + EXC_STD, KVMTEST, 0x200) + KVM_HANDLER_SKIP(PACA_EXMC, EXC_STD, 0x200) + +#ifndef CONFIG_POWER4_ONLY + /* moved from 0x300 */ +data_access_check_stab: + GET_PACA(r13) + std r9,PACA_EXSLB+EX_R9(r13) + std r10,PACA_EXSLB+EX_R10(r13) + mfspr r10,SPRN_DAR + mfspr r9,SPRN_DSISR + srdi r10,r10,60 + rlwimi r10,r9,16,0x20 +#ifdef CONFIG_KVM_BOOK3S_PR + lbz r9,HSTATE_IN_GUEST(r13) + rlwimi r10,r9,8,0x300 +#endif + mfcr r9 + cmpwi r10,0x2c + beq do_stab_bolted_pSeries + mtcrf 0x80,r9 + ld r9,PACA_EXSLB+EX_R9(r13) + ld r10,PACA_EXSLB+EX_R10(r13) + b data_access_not_stab +do_stab_bolted_pSeries: + std r11,PACA_EXSLB+EX_R11(r13) + std r12,PACA_EXSLB+EX_R12(r13) + GET_SCRATCH0(r10) + std r10,PACA_EXSLB+EX_R13(r13) + EXCEPTION_PROLOG_PSERIES_1(.do_stab_bolted, EXC_STD) +#endif /* CONFIG_POWER4_ONLY */ + + KVM_HANDLER_PR_SKIP(PACA_EXGEN, EXC_STD, 0x300) + KVM_HANDLER_PR_SKIP(PACA_EXSLB, EXC_STD, 0x380) + KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x400) + KVM_HANDLER_PR(PACA_EXSLB, EXC_STD, 0x480) + KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x900) + KVM_HANDLER(PACA_EXGEN, EXC_HV, 0x982) + + .align 7 /* moved from 0xe00 */ - STD_EXCEPTION_HV(., 0xe00, h_data_storage) - STD_EXCEPTION_HV(., 0xe20, h_instr_storage) - STD_EXCEPTION_HV(., 0xe40, emulation_assist) - STD_EXCEPTION_HV(., 0xe60, hmi_exception) /* need to flush cache ? */ + STD_EXCEPTION_HV(., 0xe02, h_data_storage) + KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0xe02) + STD_EXCEPTION_HV(., 0xe22, h_instr_storage) + KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe22) + STD_EXCEPTION_HV(., 0xe42, emulation_assist) + KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe42) + STD_EXCEPTION_HV(., 0xe62, hmi_exception) /* need to flush cache ? */ + KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe62) /* moved from 0xf00 */ STD_EXCEPTION_PSERIES(., 0xf00, performance_monitor) + KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf00) STD_EXCEPTION_PSERIES(., 0xf20, altivec_unavailable) + KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf20) STD_EXCEPTION_PSERIES(., 0xf40, vsx_unavailable) + KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf40) /* * An interrupt came in while soft-disabled; clear EE in SRR1, @@ -317,14 +385,6 @@ masked_Hinterrupt: hrfid b . - .align 7 -do_stab_bolted_pSeries: - std r11,PACA_EXSLB+EX_R11(r13) - std r12,PACA_EXSLB+EX_R12(r13) - GET_SCRATCH0(r10) - std r10,PACA_EXSLB+EX_R13(r13) - EXCEPTION_PROLOG_PSERIES_1(.do_stab_bolted, EXC_STD) - #ifdef CONFIG_PPC_PSERIES /* * Vectors for the FWNMI option. Share common code. @@ -334,14 +394,8 @@ do_stab_bolted_pSeries: system_reset_fwnmi: HMT_MEDIUM SET_SCRATCH0(r13) /* save r13 */ - EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD) - - .globl machine_check_fwnmi - .align 7 -machine_check_fwnmi: - HMT_MEDIUM - SET_SCRATCH0(r13) /* save r13 */ - EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common, EXC_STD) + EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD, + NOTEST, 0x100) #endif /* CONFIG_PPC_PSERIES */ @@ -373,12 +427,6 @@ slb_miss_user_pseries: b . /* prevent spec. execution */ #endif /* __DISABLED__ */ -/* KVM's trampoline code needs to be close to the interrupt handlers */ - -#ifdef CONFIG_KVM_BOOK3S_64_HANDLER -#include "../kvm/book3s_rmhandlers.S" -#endif - .align 7 .globl __end_interrupts __end_interrupts: @@ -415,7 +463,7 @@ machine_check_common: STD_EXCEPTION_COMMON(0xb00, trap_0b, .unknown_exception) STD_EXCEPTION_COMMON(0xd00, single_step, .single_step_exception) STD_EXCEPTION_COMMON(0xe00, trap_0e, .unknown_exception) - STD_EXCEPTION_COMMON(0xe40, emulation_assist, .program_check_exception) + STD_EXCEPTION_COMMON(0xe40, emulation_assist, .emulation_assist_interrupt) STD_EXCEPTION_COMMON(0xe60, hmi_exception, .unknown_exception) STD_EXCEPTION_COMMON_IDLE(0xf00, performance_monitor, .performance_monitor_exception) STD_EXCEPTION_COMMON(0x1300, instruction_breakpoint, .instruction_breakpoint_exception) @@ -1085,7 +1133,7 @@ _GLOBAL(do_stab_bolted) rfid b . /* prevent speculative execution */ -#ifdef CONFIG_PPC_PSERIES +#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) /* * Data area reserved for FWNMI option. * This address (0x7000) is fixed by the RPA. @@ -1093,7 +1141,7 @@ _GLOBAL(do_stab_bolted) .= 0x7000 .globl fwnmi_data_area fwnmi_data_area: -#endif /* CONFIG_PPC_PSERIES */ +#endif /* defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) */ /* iSeries does not use the FWNMI stuff, so it is safe to put * this here, even if we later allow kernels that will boot on @@ -1118,9 +1166,12 @@ xLparMap: #endif /* CONFIG_PPC_ISERIES */ -#ifdef CONFIG_PPC_PSERIES +#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) + /* pseries and powernv need to keep the whole page from + * 0x7000 to 0x8000 free for use by the firmware + */ . = 0x8000 -#endif /* CONFIG_PPC_PSERIES */ +#endif /* defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) */ /* * Space for CPU0's segment table. @@ -1135,3 +1186,19 @@ xLparMap: .globl initial_stab initial_stab: .space 4096 +#ifdef CONFIG_PPC_POWERNV +_GLOBAL(opal_mc_secondary_handler) + HMT_MEDIUM + SET_SCRATCH0(r13) + GET_PACA(r13) + clrldi r3,r3,2 + tovirt(r3,r3) + std r3,PACA_OPAL_MC_EVT(r13) + ld r13,OPAL_MC_SRR0(r3) + mtspr SPRN_SRR0,r13 + ld r13,OPAL_MC_SRR1(r3) + mtspr SPRN_SRR1,r13 + ld r3,OPAL_MC_GPR3(r3) + GET_SCRATCH0(r13) + b machine_check_pSeries +#endif /* CONFIG_PPC_POWERNV */ diff --git a/arch/powerpc/kernel/firmware.c b/arch/powerpc/kernel/firmware.c index 6b1f427..2eae447 100644 --- a/arch/powerpc/kernel/firmware.c +++ b/arch/powerpc/kernel/firmware.c @@ -13,7 +13,8 @@ * 2 of the License, or (at your option) any later version. */ -#include <linux/module.h> +#include <linux/export.h> +#include <linux/cache.h> #include <asm/firmware.h> diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index ba250d5..0654dba 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -139,8 +139,7 @@ __start: trap #endif /* CONFIG_PPC_PMAC */ -1: mr r31,r3 /* save parameters */ - mr r30,r4 +1: mr r31,r3 /* save device tree ptr */ li r24,0 /* cpu # */ /* @@ -964,8 +963,8 @@ start_here: * Do early platform-specific initialization, * and set up the MMU. */ - mr r3,r31 - mr r4,r30 + li r3,0 + mr r4,r31 bl machine_init bl __save_cpu_setup bl MMU_init diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S index a91626d..872a6af 100644 --- a/arch/powerpc/kernel/head_40x.S +++ b/arch/powerpc/kernel/head_40x.S @@ -58,13 +58,7 @@ _ENTRY(_stext); _ENTRY(_start); - /* Save parameters we are passed. - */ - mr r31,r3 - mr r30,r4 - mr r29,r5 - mr r28,r6 - mr r27,r7 + mr r31,r3 /* save device tree ptr */ /* We have to turn on the MMU right away so we get cache modes * set correctly. @@ -849,11 +843,8 @@ start_here: /* * Decide what sort of machine this is and initialize the MMU. */ - mr r3,r31 - mr r4,r30 - mr r5,r29 - mr r6,r28 - mr r7,r27 + li r3,0 + mr r4,r31 bl machine_init bl MMU_init diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S index 5e12b74..b725dab 100644 --- a/arch/powerpc/kernel/head_44x.S +++ b/arch/powerpc/kernel/head_44x.S @@ -61,14 +61,7 @@ _ENTRY(_start); * of abatron_pteptrs */ nop -/* - * Save parameters we are passed - */ - mr r31,r3 - mr r30,r4 - mr r29,r5 - mr r28,r6 - mr r27,r7 + mr r31,r3 /* save device tree ptr */ li r24,0 /* CPU number */ bl init_cpu_state @@ -93,14 +86,35 @@ _ENTRY(_start); bl early_init +#ifdef CONFIG_RELOCATABLE + /* + * r25 will contain RPN/ERPN for the start address of memory + * + * Add the difference between KERNELBASE and PAGE_OFFSET to the + * start of physical memory to get kernstart_addr. + */ + lis r3,kernstart_addr@ha + la r3,kernstart_addr@l(r3) + + lis r4,KERNELBASE@h + ori r4,r4,KERNELBASE@l + lis r5,PAGE_OFFSET@h + ori r5,r5,PAGE_OFFSET@l + subf r4,r5,r4 + + rlwinm r6,r25,0,28,31 /* ERPN */ + rlwinm r7,r25,0,0,3 /* RPN - assuming 256 MB page size */ + add r7,r7,r4 + + stw r6,0(r3) + stw r7,4(r3) +#endif + /* * Decide what sort of machine this is and initialize the MMU. */ - mr r3,r31 - mr r4,r30 - mr r5,r29 - mr r6,r28 - mr r7,r27 + li r3,0 + mr r4,r31 bl machine_init bl MMU_init @@ -1001,9 +1015,6 @@ clear_utlb_entry: lis r3,PAGE_OFFSET@h ori r3,r3,PAGE_OFFSET@l - /* Kernel is at the base of RAM */ - li r4, 0 /* Load the kernel physical address */ - /* Load the kernel PID = 0 */ li r0,0 mtspr SPRN_PID,r0 @@ -1013,9 +1024,8 @@ clear_utlb_entry: clrrwi r3,r3,12 /* Mask off the effective page number */ ori r3,r3,PPC47x_TLB0_VALID | PPC47x_TLB0_256M - /* Word 1 */ - clrrwi r4,r4,12 /* Mask off the real page number */ - /* ERPN is 0 for first 4GB page */ + /* Word 1 - use r25. RPN is the same as the original entry */ + /* Word 2 */ li r5,0 ori r5,r5,PPC47x_TLB2_S_RWX @@ -1026,7 +1036,7 @@ clear_utlb_entry: /* We write to way 0 and bolted 0 */ lis r0,0x8800 tlbwe r3,r0,0 - tlbwe r4,r0,1 + tlbwe r25,r0,1 tlbwe r5,r0,2 /* @@ -1124,7 +1134,13 @@ head_start_common: lis r4,interrupt_base@h /* IVPR only uses the high 16-bits */ mtspr SPRN_IVPR,r4 - addis r22,r22,KERNELBASE@h + /* + * If the kernel was loaded at a non-zero 256 MB page, we need to + * mask off the most significant 4 bits to get the relative address + * from the start of physical memory + */ + rlwinm r22,r22,0,4,31 + addis r22,r22,PAGE_OFFSET@h mtlr r22 isync blr diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index a5031c3..2c49227 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -51,6 +51,11 @@ * For pSeries or server processors: * 1. The MMU is off & open firmware is running in real mode. * 2. The kernel is entered at __start + * -or- For OPAL entry: + * 1. The MMU is off, processor in HV mode, primary CPU enters at 0 + * with device-tree in gpr3. We also get OPAL base in r8 and + * entry in r9 for debugging purposes + * 2. Secondary processors enter at 0x60 with PIR in gpr3 * * For iSeries: * 1. The MMU is on (as it always is for iSeries) @@ -255,7 +260,7 @@ generic_secondary_common_init: mtctr r23 bctrl -3: LOAD_REG_ADDR(r3, boot_cpu_count) /* Decrement boot_cpu_count */ +3: LOAD_REG_ADDR(r3, spinning_secondaries) /* Decrement spinning_secondaries */ lwarx r4,0,r3 subi r4,r4,1 stwcx. r4,0,r3 @@ -331,6 +336,11 @@ _GLOBAL(__start_initialization_multiplatform) /* Save parameters */ mr r31,r3 mr r30,r4 +#ifdef CONFIG_PPC_EARLY_DEBUG_OPAL + /* Save OPAL entry */ + mr r28,r8 + mr r29,r9 +#endif #ifdef CONFIG_PPC_BOOK3E bl .start_initialization_book3e @@ -675,9 +685,9 @@ _GLOBAL(enable_64b_mode) _GLOBAL(relative_toc) mflr r0 bcl 20,31,$+4 -0: mflr r9 - ld r2,(p_toc - 0b)(r9) - add r2,r2,r9 +0: mflr r11 + ld r2,(p_toc - 0b)(r11) + add r2,r2,r11 mtlr r0 blr @@ -708,6 +718,12 @@ _INIT_STATIC(start_here_multiplatform) bdnz 3b 4: +#ifdef CONFIG_PPC_EARLY_DEBUG_OPAL + /* Setup OPAL entry */ + std r28,0(r11); + std r29,8(r11); +#endif + #ifndef CONFIG_PPC_BOOK3E mfmsr r6 ori r6,r6,MSR_RI diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index 1cbf64e..b68cb17 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -76,11 +76,7 @@ _ENTRY(_start); */ .globl __start __start: - mr r31,r3 /* save parameters */ - mr r30,r4 - mr r29,r5 - mr r28,r6 - mr r27,r7 + mr r31,r3 /* save device tree ptr */ /* We have to turn on the MMU right away so we get cache modes * set correctly. @@ -723,11 +719,8 @@ start_here: /* * Decide what sort of machine this is and initialize the MMU. */ - mr r3,r31 - mr r4,r30 - mr r5,r29 - mr r6,r28 - mr r7,r27 + li r3,0 + mr r4,r31 bl machine_init bl MMU_init diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h index a0bf158..fc921bf 100644 --- a/arch/powerpc/kernel/head_booke.h +++ b/arch/powerpc/kernel/head_booke.h @@ -20,33 +20,43 @@ addi reg,reg,val@l #endif +/* + * Macro used to get to thread save registers. + * Note that entries 0-3 are used for the prolog code, and the remaining + * entries are available for specific exception use in the event a handler + * requires more than 4 scratch registers. + */ +#define THREAD_NORMSAVE(offset) (THREAD_NORMSAVES + (offset * 4)) + #define NORMAL_EXCEPTION_PROLOG \ - mtspr SPRN_SPRG_WSCRATCH0,r10;/* save two registers to work with */\ - mtspr SPRN_SPRG_WSCRATCH1,r11; \ - mtspr SPRN_SPRG_WSCRATCH2,r1; \ - mfcr r10; /* save CR in r10 for now */\ + mtspr SPRN_SPRG_WSCRATCH0, r10; /* save one register */ \ + mfspr r10, SPRN_SPRG_THREAD; \ + stw r11, THREAD_NORMSAVE(0)(r10); \ + stw r13, THREAD_NORMSAVE(2)(r10); \ + mfcr r13; /* save CR in r13 for now */\ mfspr r11,SPRN_SRR1; /* check whether user or kernel */\ andi. r11,r11,MSR_PR; \ + mr r11, r1; \ beq 1f; \ - mfspr r1,SPRN_SPRG_THREAD; /* if from user, start at top of */\ - lwz r1,THREAD_INFO-THREAD(r1); /* this thread's kernel stack */\ - ALLOC_STACK_FRAME(r1, THREAD_SIZE); \ -1: subi r1,r1,INT_FRAME_SIZE; /* Allocate an exception frame */\ - mr r11,r1; \ - stw r10,_CCR(r11); /* save various registers */\ + /* if from user, start at top of this thread's kernel stack */ \ + lwz r11, THREAD_INFO-THREAD(r10); \ + ALLOC_STACK_FRAME(r11, THREAD_SIZE); \ +1 : subi r11, r11, INT_FRAME_SIZE; /* Allocate exception frame */ \ + stw r13, _CCR(r11); /* save various registers */ \ stw r12,GPR12(r11); \ stw r9,GPR9(r11); \ - mfspr r10,SPRN_SPRG_RSCRATCH0; \ - stw r10,GPR10(r11); \ - mfspr r12,SPRN_SPRG_RSCRATCH1; \ + mfspr r13, SPRN_SPRG_RSCRATCH0; \ + stw r13, GPR10(r11); \ + lwz r12, THREAD_NORMSAVE(0)(r10); \ stw r12,GPR11(r11); \ + lwz r13, THREAD_NORMSAVE(2)(r10); /* restore r13 */ \ mflr r10; \ stw r10,_LINK(r11); \ - mfspr r10,SPRN_SPRG_RSCRATCH2; \ mfspr r12,SPRN_SRR0; \ - stw r10,GPR1(r11); \ + stw r1, GPR1(r11); \ mfspr r9,SPRN_SRR1; \ - stw r10,0(r11); \ + stw r1, 0(r11); \ + mr r1, r11; \ rlwinm r9,r9,0,14,12; /* clear MSR_WE (necessary?) */\ stw r0,GPR0(r11); \ lis r10, STACK_FRAME_REGS_MARKER@ha;/* exception frame marker */ \ diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S index 5ecf54c..9f5d210 100644 --- a/arch/powerpc/kernel/head_fsl_booke.S +++ b/arch/powerpc/kernel/head_fsl_booke.S @@ -63,17 +63,30 @@ _ENTRY(_start); * of abatron_pteptrs */ nop -/* - * Save parameters we are passed - */ - mr r31,r3 - mr r30,r4 - mr r29,r5 - mr r28,r6 - mr r27,r7 - li r25,0 /* phys kernel start (low) */ - li r24,0 /* CPU number */ - li r23,0 /* phys kernel start (high) */ + + /* Translate device tree address to physical, save in r30/r31 */ + mfmsr r16 + mfspr r17,SPRN_PID + rlwinm r17,r17,16,0x3fff0000 /* turn PID into MAS6[SPID] */ + rlwimi r17,r16,28,0x00000001 /* turn MSR[DS] into MAS6[SAS] */ + mtspr SPRN_MAS6,r17 + + tlbsx 0,r3 /* must succeed */ + + mfspr r16,SPRN_MAS1 + mfspr r20,SPRN_MAS3 + rlwinm r17,r16,25,0x1f /* r17 = log2(page size) */ + li r18,1024 + slw r18,r18,r17 /* r18 = page size */ + addi r18,r18,-1 + and r19,r3,r18 /* r19 = page offset */ + andc r31,r20,r18 /* r31 = page base */ + or r31,r31,r19 /* r31 = devtree phys addr */ + mfspr r30,SPRN_MAS7 + + li r25,0 /* phys kernel start (low) */ + li r24,0 /* CPU number */ + li r23,0 /* phys kernel start (high) */ /* We try to not make any assumptions about how the boot loader * setup or used the TLBs. We invalidate all mappings from the @@ -198,11 +211,8 @@ _ENTRY(__early_start) /* * Decide what sort of machine this is and initialize the MMU. */ - mr r3,r31 - mr r4,r30 - mr r5,r29 - mr r6,r28 - mr r7,r27 + mr r3,r30 + mr r4,r31 bl machine_init bl MMU_init @@ -236,8 +246,24 @@ _ENTRY(__early_start) * if we find the pte (fall through): * r11 is low pte word * r12 is pointer to the pte + * r10 is the pshift from the PGD, if we're a hugepage */ #ifdef CONFIG_PTE_64BIT +#ifdef CONFIG_HUGETLB_PAGE +#define FIND_PTE \ + rlwinm r12, r10, 13, 19, 29; /* Compute pgdir/pmd offset */ \ + lwzx r11, r12, r11; /* Get pgd/pmd entry */ \ + rlwinm. r12, r11, 0, 0, 20; /* Extract pt base address */ \ + blt 1000f; /* Normal non-huge page */ \ + beq 2f; /* Bail if no table */ \ + oris r11, r11, PD_HUGE@h; /* Put back address bit */ \ + andi. r10, r11, HUGEPD_SHIFT_MASK@l; /* extract size field */ \ + xor r12, r10, r11; /* drop size bits from pointer */ \ + b 1001f; \ +1000: rlwimi r12, r10, 23, 20, 28; /* Compute pte address */ \ + li r10, 0; /* clear r10 */ \ +1001: lwz r11, 4(r12); /* Get pte entry */ +#else #define FIND_PTE \ rlwinm r12, r10, 13, 19, 29; /* Compute pgdir/pmd offset */ \ lwzx r11, r12, r11; /* Get pgd/pmd entry */ \ @@ -245,7 +271,8 @@ _ENTRY(__early_start) beq 2f; /* Bail if no table */ \ rlwimi r12, r10, 23, 20, 28; /* Compute pte address */ \ lwz r11, 4(r12); /* Get pte entry */ -#else +#endif /* HUGEPAGE */ +#else /* !PTE_64BIT */ #define FIND_PTE \ rlwimi r11, r10, 12, 20, 29; /* Create L1 (pgdir/pmd) address */ \ lwz r11, 0(r11); /* Get L1 entry */ \ @@ -346,11 +373,12 @@ interrupt_base: /* Data TLB Error Interrupt */ START_EXCEPTION(DataTLBError) mtspr SPRN_SPRG_WSCRATCH0, r10 /* Save some working registers */ - mtspr SPRN_SPRG_WSCRATCH1, r11 - mtspr SPRN_SPRG_WSCRATCH2, r12 - mtspr SPRN_SPRG_WSCRATCH3, r13 - mfcr r11 - mtspr SPRN_SPRG_WSCRATCH4, r11 + mfspr r10, SPRN_SPRG_THREAD + stw r11, THREAD_NORMSAVE(0)(r10) + stw r12, THREAD_NORMSAVE(1)(r10) + stw r13, THREAD_NORMSAVE(2)(r10) + mfcr r13 + stw r13, THREAD_NORMSAVE(3)(r10) mfspr r10, SPRN_DEAR /* Get faulting address */ /* If we are faulting a kernel address, we have to use the @@ -401,8 +429,8 @@ interrupt_base: #ifdef CONFIG_PTE_64BIT #ifdef CONFIG_SMP - subf r10,r11,r12 /* create false data dep */ - lwzx r13,r11,r10 /* Get upper pte bits */ + subf r13,r11,r12 /* create false data dep */ + lwzx r13,r11,r13 /* Get upper pte bits */ #else lwz r13,0(r12) /* Get upper pte bits */ #endif @@ -416,11 +444,12 @@ interrupt_base: /* The bailout. Restore registers to pre-exception conditions * and call the heavyweights to help us out. */ - mfspr r11, SPRN_SPRG_RSCRATCH4 + mfspr r10, SPRN_SPRG_THREAD + lwz r11, THREAD_NORMSAVE(3)(r10) mtcr r11 - mfspr r13, SPRN_SPRG_RSCRATCH3 - mfspr r12, SPRN_SPRG_RSCRATCH2 - mfspr r11, SPRN_SPRG_RSCRATCH1 + lwz r13, THREAD_NORMSAVE(2)(r10) + lwz r12, THREAD_NORMSAVE(1)(r10) + lwz r11, THREAD_NORMSAVE(0)(r10) mfspr r10, SPRN_SPRG_RSCRATCH0 b DataStorage @@ -432,11 +461,12 @@ interrupt_base: */ START_EXCEPTION(InstructionTLBError) mtspr SPRN_SPRG_WSCRATCH0, r10 /* Save some working registers */ - mtspr SPRN_SPRG_WSCRATCH1, r11 - mtspr SPRN_SPRG_WSCRATCH2, r12 - mtspr SPRN_SPRG_WSCRATCH3, r13 - mfcr r11 - mtspr SPRN_SPRG_WSCRATCH4, r11 + mfspr r10, SPRN_SPRG_THREAD + stw r11, THREAD_NORMSAVE(0)(r10) + stw r12, THREAD_NORMSAVE(1)(r10) + stw r13, THREAD_NORMSAVE(2)(r10) + mfcr r13 + stw r13, THREAD_NORMSAVE(3)(r10) mfspr r10, SPRN_SRR0 /* Get faulting address */ /* If we are faulting a kernel address, we have to use the @@ -480,8 +510,8 @@ interrupt_base: #ifdef CONFIG_PTE_64BIT #ifdef CONFIG_SMP - subf r10,r11,r12 /* create false data dep */ - lwzx r13,r11,r10 /* Get upper pte bits */ + subf r13,r11,r12 /* create false data dep */ + lwzx r13,r11,r13 /* Get upper pte bits */ #else lwz r13,0(r12) /* Get upper pte bits */ #endif @@ -496,11 +526,12 @@ interrupt_base: /* The bailout. Restore registers to pre-exception conditions * and call the heavyweights to help us out. */ - mfspr r11, SPRN_SPRG_RSCRATCH4 + mfspr r10, SPRN_SPRG_THREAD + lwz r11, THREAD_NORMSAVE(3)(r10) mtcr r11 - mfspr r13, SPRN_SPRG_RSCRATCH3 - mfspr r12, SPRN_SPRG_RSCRATCH2 - mfspr r11, SPRN_SPRG_RSCRATCH1 + lwz r13, THREAD_NORMSAVE(2)(r10) + lwz r12, THREAD_NORMSAVE(1)(r10) + lwz r11, THREAD_NORMSAVE(0)(r10) mfspr r10, SPRN_SPRG_RSCRATCH0 b InstructionStorage @@ -544,7 +575,7 @@ interrupt_base: /* * Both the instruction and data TLB miss get to this * point to load the TLB. - * r10 - available to use + * r10 - tsize encoding (if HUGETLB_PAGE) or available to use * r11 - TLB (info from Linux PTE) * r12 - available to use * r13 - upper bits of PTE (if PTE_64BIT) or available to use @@ -554,21 +585,73 @@ interrupt_base: * Upon exit, we reload everything and RFI. */ finish_tlb_load: +#ifdef CONFIG_HUGETLB_PAGE + cmpwi 6, r10, 0 /* check for huge page */ + beq 6, finish_tlb_load_cont /* !huge */ + + /* Alas, we need more scratch registers for hugepages */ + mfspr r12, SPRN_SPRG_THREAD + stw r14, THREAD_NORMSAVE(4)(r12) + stw r15, THREAD_NORMSAVE(5)(r12) + stw r16, THREAD_NORMSAVE(6)(r12) + stw r17, THREAD_NORMSAVE(7)(r12) + + /* Get the next_tlbcam_idx percpu var */ +#ifdef CONFIG_SMP + lwz r12, THREAD_INFO-THREAD(r12) + lwz r15, TI_CPU(r12) + lis r14, __per_cpu_offset@h + ori r14, r14, __per_cpu_offset@l + rlwinm r15, r15, 2, 0, 29 + lwzx r16, r14, r15 +#else + li r16, 0 +#endif + lis r17, next_tlbcam_idx@h + ori r17, r17, next_tlbcam_idx@l + add r17, r17, r16 /* r17 = *next_tlbcam_idx */ + lwz r15, 0(r17) /* r15 = next_tlbcam_idx */ + + lis r14, MAS0_TLBSEL(1)@h /* select TLB1 (TLBCAM) */ + rlwimi r14, r15, 16, 4, 15 /* next_tlbcam_idx entry */ + mtspr SPRN_MAS0, r14 + + /* Extract TLB1CFG(NENTRY) */ + mfspr r16, SPRN_TLB1CFG + andi. r16, r16, 0xfff + + /* Update next_tlbcam_idx, wrapping when necessary */ + addi r15, r15, 1 + cmpw r15, r16 + blt 100f + lis r14, tlbcam_index@h + ori r14, r14, tlbcam_index@l + lwz r15, 0(r14) +100: stw r15, 0(r17) + + /* + * Calc MAS1_TSIZE from r10 (which has pshift encoded) + * tlb_enc = (pshift - 10). + */ + subi r15, r10, 10 + mfspr r16, SPRN_MAS1 + rlwimi r16, r15, 7, 20, 24 + mtspr SPRN_MAS1, r16 + + /* copy the pshift for use later */ + mr r14, r10 + + /* fall through */ + +#endif /* CONFIG_HUGETLB_PAGE */ + /* * We set execute, because we don't have the granularity to * properly set this at the page level (Linux problem). * Many of these bits are software only. Bits we don't set * here we (properly should) assume have the appropriate value. */ - - mfspr r12, SPRN_MAS2 -#ifdef CONFIG_PTE_64BIT - rlwimi r12, r11, 32-19, 27, 31 /* extract WIMGE from pte */ -#else - rlwimi r12, r11, 26, 27, 31 /* extract WIMGE from pte */ -#endif - mtspr SPRN_MAS2, r12 - +finish_tlb_load_cont: #ifdef CONFIG_PTE_64BIT rlwinm r12, r11, 32-2, 26, 31 /* Move in perm bits */ andi. r10, r11, _PAGE_DIRTY @@ -577,22 +660,40 @@ finish_tlb_load: andc r12, r12, r10 1: rlwimi r12, r13, 20, 0, 11 /* grab RPN[32:43] */ rlwimi r12, r11, 20, 12, 19 /* grab RPN[44:51] */ - mtspr SPRN_MAS3, r12 +2: mtspr SPRN_MAS3, r12 BEGIN_MMU_FTR_SECTION srwi r10, r13, 12 /* grab RPN[12:31] */ mtspr SPRN_MAS7, r10 END_MMU_FTR_SECTION_IFSET(MMU_FTR_BIG_PHYS) #else li r10, (_PAGE_EXEC | _PAGE_PRESENT) + mr r13, r11 rlwimi r10, r11, 31, 29, 29 /* extract _PAGE_DIRTY into SW */ and r12, r11, r10 andi. r10, r11, _PAGE_USER /* Test for _PAGE_USER */ slwi r10, r12, 1 or r10, r10, r12 iseleq r12, r12, r10 - rlwimi r11, r12, 0, 20, 31 /* Extract RPN from PTE and merge with perms */ - mtspr SPRN_MAS3, r11 + rlwimi r13, r12, 0, 20, 31 /* Get RPN from PTE, merge w/ perms */ + mtspr SPRN_MAS3, r13 #endif + + mfspr r12, SPRN_MAS2 +#ifdef CONFIG_PTE_64BIT + rlwimi r12, r11, 32-19, 27, 31 /* extract WIMGE from pte */ +#else + rlwimi r12, r11, 26, 27, 31 /* extract WIMGE from pte */ +#endif +#ifdef CONFIG_HUGETLB_PAGE + beq 6, 3f /* don't mask if page isn't huge */ + li r13, 1 + slw r13, r13, r14 + subi r13, r13, 1 + rlwinm r13, r13, 0, 0, 19 /* bottom bits used for WIMGE/etc */ + andc r12, r12, r13 /* mask off ea bits within the page */ +#endif +3: mtspr SPRN_MAS2, r12 + #ifdef CONFIG_E200 /* Round robin TLB1 entries assignment */ mfspr r12, SPRN_MAS0 @@ -618,14 +719,23 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_BIG_PHYS) mtspr SPRN_MAS0,r12 #endif /* CONFIG_E200 */ +tlb_write_entry: tlbwe /* Done...restore registers and get out of here. */ - mfspr r11, SPRN_SPRG_RSCRATCH4 + mfspr r10, SPRN_SPRG_THREAD +#ifdef CONFIG_HUGETLB_PAGE + beq 6, 8f /* skip restore for 4k page faults */ + lwz r14, THREAD_NORMSAVE(4)(r10) + lwz r15, THREAD_NORMSAVE(5)(r10) + lwz r16, THREAD_NORMSAVE(6)(r10) + lwz r17, THREAD_NORMSAVE(7)(r10) +#endif +8: lwz r11, THREAD_NORMSAVE(3)(r10) mtcr r11 - mfspr r13, SPRN_SPRG_RSCRATCH3 - mfspr r12, SPRN_SPRG_RSCRATCH2 - mfspr r11, SPRN_SPRG_RSCRATCH1 + lwz r13, THREAD_NORMSAVE(2)(r10) + lwz r12, THREAD_NORMSAVE(1)(r10) + lwz r11, THREAD_NORMSAVE(0)(r10) mfspr r10, SPRN_SPRG_RSCRATCH0 rfi /* Force context change */ @@ -656,7 +766,7 @@ load_up_spe: cmpi 0,r4,0 beq 1f addi r4,r4,THREAD /* want THREAD of last_task_used_spe */ - SAVE_32EVRS(0,r10,r4) + SAVE_32EVRS(0,r10,r4,THREAD_EVR0) evxor evr10, evr10, evr10 /* clear out evr10 */ evmwumiaa evr10, evr10, evr10 /* evr10 <- ACC = 0 * 0 + ACC */ li r5,THREAD_ACC @@ -676,7 +786,7 @@ load_up_spe: stw r4,THREAD_USED_SPE(r5) evlddx evr4,r10,r5 evmra evr4,evr4 - REST_32EVRS(0,r10,r5) + REST_32EVRS(0,r10,r5,THREAD_EVR0) #ifndef CONFIG_SMP subi r4,r5,THREAD stw r4,last_task_used_spe@l(r3) @@ -787,13 +897,11 @@ _GLOBAL(giveup_spe) addi r3,r3,THREAD /* want THREAD of task */ lwz r5,PT_REGS(r3) cmpi 0,r5,0 - SAVE_32EVRS(0, r4, r3) + SAVE_32EVRS(0, r4, r3, THREAD_EVR0) evxor evr6, evr6, evr6 /* clear out evr6 */ evmwumiaa evr6, evr6, evr6 /* evr6 <- ACC = 0 * 0 + ACC */ li r4,THREAD_ACC evstddx evr6, r4, r3 /* save off accumulator */ - mfspr r6,SPRN_SPEFSCR - stw r6,THREAD_SPEFSCR(r3) /* save spefscr register value */ beq 1f lwz r4,_MSR-STACK_FRAME_OVERHEAD(r5) lis r3,MSR_SPE@h diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index 5ecd040..2bc0584 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -27,7 +27,6 @@ #include <linux/kprobes.h> #include <linux/percpu.h> #include <linux/kernel.h> -#include <linux/module.h> #include <linux/sched.h> #include <linux/init.h> #include <linux/smp.h> diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c index 28581f1..d39ae60 100644 --- a/arch/powerpc/kernel/ibmebus.c +++ b/arch/powerpc/kernel/ibmebus.c @@ -37,12 +37,14 @@ */ #include <linux/init.h> +#include <linux/export.h> #include <linux/console.h> #include <linux/kobject.h> #include <linux/dma-mapping.h> #include <linux/interrupt.h> #include <linux/of.h> #include <linux/slab.h> +#include <linux/stat.h> #include <linux/of_platform.h> #include <asm/ibmebus.h> #include <asm/abs_addr.h> @@ -125,17 +127,23 @@ static void ibmebus_unmap_sg(struct device *dev, static int ibmebus_dma_supported(struct device *dev, u64 mask) { - return 1; + return mask == DMA_BIT_MASK(64); +} + +static u64 ibmebus_dma_get_required_mask(struct device *dev) +{ + return DMA_BIT_MASK(64); } static struct dma_map_ops ibmebus_dma_ops = { - .alloc_coherent = ibmebus_alloc_coherent, - .free_coherent = ibmebus_free_coherent, - .map_sg = ibmebus_map_sg, - .unmap_sg = ibmebus_unmap_sg, - .dma_supported = ibmebus_dma_supported, - .map_page = ibmebus_map_page, - .unmap_page = ibmebus_unmap_page, + .alloc_coherent = ibmebus_alloc_coherent, + .free_coherent = ibmebus_free_coherent, + .map_sg = ibmebus_map_sg, + .unmap_sg = ibmebus_unmap_sg, + .dma_supported = ibmebus_dma_supported, + .get_required_mask = ibmebus_dma_get_required_mask, + .map_page = ibmebus_map_page, + .unmap_page = ibmebus_unmap_page, }; static int ibmebus_match_path(struct device *dev, void *data) diff --git a/arch/powerpc/kernel/idle_e500.S b/arch/powerpc/kernel/idle_e500.S index 47a1a98..4f0ab85 100644 --- a/arch/powerpc/kernel/idle_e500.S +++ b/arch/powerpc/kernel/idle_e500.S @@ -26,6 +26,17 @@ _GLOBAL(e500_idle) ori r4,r4,_TLF_NAPPING /* so when we take an exception */ stw r4,TI_LOCAL_FLAGS(r3) /* it will return to our caller */ +#ifdef CONFIG_PPC_E500MC + wrteei 1 +1: wait + + /* + * Guard against spurious wakeups (e.g. from a hypervisor) -- + * any real interrupt will cause us to return to LR due to + * _TLF_NAPPING. + */ + b 1b +#else /* Check if we can nap or doze, put HID0 mask in r3 */ lis r3,0 BEGIN_FTR_SECTION @@ -72,6 +83,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_L2CSR|CPU_FTR_CAN_NAP) mtmsr r7 isync 2: b 2b +#endif /* !E500MC */ /* * Return from NAP/DOZE mode, restore some CPU specific registers, diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S index f8f0bc7..3a70845 100644 --- a/arch/powerpc/kernel/idle_power7.S +++ b/arch/powerpc/kernel/idle_power7.S @@ -73,7 +73,6 @@ _GLOBAL(power7_idle) b . _GLOBAL(power7_wakeup_loss) - GET_PACA(r13) ld r1,PACAR1(r13) REST_NVGPRS(r1) REST_GPR(2, r1) @@ -87,7 +86,6 @@ _GLOBAL(power7_wakeup_loss) rfid _GLOBAL(power7_wakeup_noloss) - GET_PACA(r13) ld r1,PACAR1(r13) ld r4,_MSR(r1) ld r5,_NIP(r1) diff --git a/arch/powerpc/kernel/init_task.c b/arch/powerpc/kernel/init_task.c index 2375b7e..d076d46 100644 --- a/arch/powerpc/kernel/init_task.c +++ b/arch/powerpc/kernel/init_task.c @@ -1,5 +1,5 @@ #include <linux/mm.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/sched.h> #include <linux/init.h> #include <linux/init_task.h> diff --git a/arch/powerpc/kernel/io-workarounds.c b/arch/powerpc/kernel/io-workarounds.c index ffafaea..12d329b 100644 --- a/arch/powerpc/kernel/io-workarounds.c +++ b/arch/powerpc/kernel/io-workarounds.c @@ -12,6 +12,7 @@ #undef DEBUG #include <linux/kernel.h> +#include <linux/sched.h> /* for init_mm */ #include <asm/io.h> #include <asm/machdep.h> diff --git a/arch/powerpc/kernel/io.c b/arch/powerpc/kernel/io.c index 8dc7547..886381f 100644 --- a/arch/powerpc/kernel/io.c +++ b/arch/powerpc/kernel/io.c @@ -19,7 +19,7 @@ #include <linux/kernel.h> #include <linux/types.h> #include <linux/compiler.h> -#include <linux/module.h> +#include <linux/export.h> #include <asm/io.h> #include <asm/firmware.h> diff --git a/arch/powerpc/kernel/iomap.c b/arch/powerpc/kernel/iomap.c index 1577434..2627918 100644 --- a/arch/powerpc/kernel/iomap.c +++ b/arch/powerpc/kernel/iomap.c @@ -6,6 +6,7 @@ #include <linux/init.h> #include <linux/pci.h> #include <linux/mm.h> +#include <linux/export.h> #include <asm/io.h> #include <asm/pci-bridge.h> @@ -117,6 +118,7 @@ void ioport_unmap(void __iomem *addr) EXPORT_SYMBOL(ioport_map); EXPORT_SYMBOL(ioport_unmap); +#ifdef CONFIG_PCI void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long max) { resource_size_t start = pci_resource_start(dev, bar); @@ -146,3 +148,4 @@ void pci_iounmap(struct pci_dev *dev, void __iomem *addr) EXPORT_SYMBOL(pci_iomap); EXPORT_SYMBOL(pci_iounmap); +#endif /* CONFIG_PCI */ diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 795e807..d0b205c 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -501,6 +501,14 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid) tbl->it_map = page_address(page); memset(tbl->it_map, 0, sz); + /* + * Reserve page 0 so it will not be used for any mappings. + * This avoids buggy drivers that consider page 0 to be invalid + * to crash the machine or even lose data. + */ + if (tbl->it_offset == 0) + set_bit(0, tbl->it_map); + tbl->it_hint = 0; tbl->it_largehint = tbl->it_halfpoint; spin_lock_init(&tbl->it_lock); diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index ca2987d..745c1e7 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -30,7 +30,7 @@ #undef DEBUG -#include <linux/module.h> +#include <linux/export.h> #include <linux/threads.h> #include <linux/kernel_stat.h> #include <linux/signal.h> @@ -157,12 +157,6 @@ notrace void arch_local_irq_restore(unsigned long en) if (get_hard_enabled()) return; -#if defined(CONFIG_BOOKE) && defined(CONFIG_SMP) - /* Check for pending doorbell interrupts and resend to ourself */ - if (cpu_has_feature(CPU_FTR_DBELL)) - smp_muxed_ipi_resend(); -#endif - /* * Need to hard-enable interrupts here. Since currently disabled, * no need to take further asm precautions against preemption; but @@ -454,11 +448,18 @@ static inline void do_softirq_onstack(void) curtp = current_thread_info(); irqtp = softirq_ctx[smp_processor_id()]; irqtp->task = curtp->task; + irqtp->flags = 0; current->thread.ksp_limit = (unsigned long)irqtp + _ALIGN_UP(sizeof(struct thread_info), 16); call_do_softirq(irqtp); current->thread.ksp_limit = saved_sp_limit; irqtp->task = NULL; + + /* Set any flag that may have been set on the + * alternate stack + */ + if (irqtp->flags) + set_bits(irqtp->flags, &curtp->flags); } void do_softirq(void) @@ -747,7 +748,7 @@ unsigned int irq_create_mapping(struct irq_host *host, if (irq_setup_virq(host, virq, hwirq)) return NO_IRQ; - printk(KERN_DEBUG "irq: irq %lu on host %s mapped to virtual irq %u\n", + pr_debug("irq: irq %lu on host %s mapped to virtual irq %u\n", hwirq, host->of_node ? host->of_node->full_name : "null", virq); return virq; @@ -879,6 +880,41 @@ unsigned int irq_find_mapping(struct irq_host *host, } EXPORT_SYMBOL_GPL(irq_find_mapping); +#ifdef CONFIG_SMP +int irq_choose_cpu(const struct cpumask *mask) +{ + int cpuid; + + if (cpumask_equal(mask, cpu_all_mask)) { + static int irq_rover; + static DEFINE_RAW_SPINLOCK(irq_rover_lock); + unsigned long flags; + + /* Round-robin distribution... */ +do_round_robin: + raw_spin_lock_irqsave(&irq_rover_lock, flags); + + irq_rover = cpumask_next(irq_rover, cpu_online_mask); + if (irq_rover >= nr_cpu_ids) + irq_rover = cpumask_first(cpu_online_mask); + + cpuid = irq_rover; + + raw_spin_unlock_irqrestore(&irq_rover_lock, flags); + } else { + cpuid = cpumask_first_and(mask, cpu_online_mask); + if (cpuid >= nr_cpu_ids) + goto do_round_robin; + } + + return get_hard_smp_processor_id(cpuid); +} +#else +int irq_choose_cpu(const struct cpumask *mask) +{ + return hard_smp_processor_id(); +} +#endif unsigned int irq_radix_revmap_lookup(struct irq_host *host, irq_hw_number_t hwirq) diff --git a/arch/powerpc/kernel/isa-bridge.c b/arch/powerpc/kernel/isa-bridge.c index 4d5731b..4797529 100644 --- a/arch/powerpc/kernel/isa-bridge.c +++ b/arch/powerpc/kernel/isa-bridge.c @@ -18,6 +18,7 @@ #include <linux/kernel.h> #include <linux/pci.h> #include <linux/string.h> +#include <linux/export.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/notifier.h> diff --git a/arch/powerpc/kernel/jump_label.c b/arch/powerpc/kernel/jump_label.c new file mode 100644 index 0000000..a1ed8a8 --- /dev/null +++ b/arch/powerpc/kernel/jump_label.c @@ -0,0 +1,25 @@ +/* + * Copyright 2010 Michael Ellerman, IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/kernel.h> +#include <linux/jump_label.h> +#include <asm/code-patching.h> + +#ifdef HAVE_JUMP_LABEL +void arch_jump_label_transform(struct jump_entry *entry, + enum jump_label_type type) +{ + u32 *addr = (u32 *)(unsigned long)entry->code; + + if (type == JUMP_LABEL_ENABLE) + patch_branch(addr, entry->target, 0); + else + patch_instruction(addr, PPC_INST_NOP); +} +#endif diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c index ad892f7..2985338 100644 --- a/arch/powerpc/kernel/kvm.c +++ b/arch/powerpc/kernel/kvm.c @@ -20,6 +20,7 @@ #include <linux/kvm_host.h> #include <linux/init.h> +#include <linux/export.h> #include <linux/kvm_para.h> #include <linux/slab.h> #include <linux/of.h> diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c index 2b97b80..c77159d 100644 --- a/arch/powerpc/kernel/legacy_serial.c +++ b/arch/powerpc/kernel/legacy_serial.c @@ -6,6 +6,7 @@ #include <linux/pci.h> #include <linux/of_address.h> #include <linux/of_device.h> +#include <linux/serial_reg.h> #include <asm/io.h> #include <asm/mmu.h> #include <asm/prom.h> @@ -47,6 +48,27 @@ static struct __initdata of_device_id legacy_serial_parents[] = { static unsigned int legacy_serial_count; static int legacy_serial_console = -1; +static const upf_t legacy_port_flags = UPF_BOOT_AUTOCONF | UPF_SKIP_TEST | + UPF_SHARE_IRQ | UPF_FIXED_PORT; + +static unsigned int tsi_serial_in(struct uart_port *p, int offset) +{ + unsigned int tmp; + offset = offset << p->regshift; + if (offset == UART_IIR) { + tmp = readl(p->membase + (UART_IIR & ~3)); + return (tmp >> 16) & 0xff; /* UART_IIR % 4 == 2 */ + } else + return readb(p->membase + offset); +} + +static void tsi_serial_out(struct uart_port *p, int offset, int value) +{ + offset = offset << p->regshift; + if (!((offset == UART_IER) && (value & UART_IER_UUE))) + writeb(value, p->membase + offset); +} + static int __init add_legacy_port(struct device_node *np, int want_index, int iotype, phys_addr_t base, phys_addr_t taddr, unsigned long irq, @@ -102,6 +124,7 @@ static int __init add_legacy_port(struct device_node *np, int want_index, legacy_serial_ports[index].iobase = base; else legacy_serial_ports[index].mapbase = base; + legacy_serial_ports[index].iotype = iotype; legacy_serial_ports[index].uartclk = clock; legacy_serial_ports[index].irq = irq; @@ -112,6 +135,11 @@ static int __init add_legacy_port(struct device_node *np, int want_index, legacy_serial_infos[index].speed = spd ? be32_to_cpup(spd) : 0; legacy_serial_infos[index].irq_check_parent = irq_check_parent; + if (iotype == UPIO_TSI) { + legacy_serial_ports[index].serial_in = tsi_serial_in; + legacy_serial_ports[index].serial_out = tsi_serial_out; + } + printk(KERN_DEBUG "Found legacy serial port %d for %s\n", index, np->full_name); printk(KERN_DEBUG " %s=%llx, taddr=%llx, irq=%lx, clk=%d, speed=%d\n", @@ -128,8 +156,6 @@ static int __init add_legacy_soc_port(struct device_node *np, { u64 addr; const u32 *addrp; - upf_t flags = UPF_BOOT_AUTOCONF | UPF_SKIP_TEST | UPF_SHARE_IRQ - | UPF_FIXED_PORT; struct device_node *tsi = of_get_parent(np); /* We only support ports that have a clock frequency properly @@ -160,9 +186,11 @@ static int __init add_legacy_soc_port(struct device_node *np, * IO port value. It will be fixed up later along with the irq */ if (tsi && !strcmp(tsi->type, "tsi-bridge")) - return add_legacy_port(np, -1, UPIO_TSI, addr, addr, NO_IRQ, flags, 0); + return add_legacy_port(np, -1, UPIO_TSI, addr, addr, + NO_IRQ, legacy_port_flags, 0); else - return add_legacy_port(np, -1, UPIO_MEM, addr, addr, NO_IRQ, flags, 0); + return add_legacy_port(np, -1, UPIO_MEM, addr, addr, + NO_IRQ, legacy_port_flags, 0); } static int __init add_legacy_isa_port(struct device_node *np, @@ -203,7 +231,7 @@ static int __init add_legacy_isa_port(struct device_node *np, /* Add port, irq will be dealt with later */ return add_legacy_port(np, index, UPIO_PORT, be32_to_cpu(reg[1]), taddr, - NO_IRQ, UPF_BOOT_AUTOCONF, 0); + NO_IRQ, legacy_port_flags, 0); } @@ -276,7 +304,7 @@ static int __init add_legacy_pci_port(struct device_node *np, * IO port value. It will be fixed up later along with the irq */ return add_legacy_port(np, index, iotype, base, addr, NO_IRQ, - UPF_BOOT_AUTOCONF, np != pci_dev); + legacy_port_flags, np != pci_dev); } #endif diff --git a/arch/powerpc/kernel/lparcfg.c b/arch/powerpc/kernel/lparcfg.c index 84daabe..26af24b 100644 --- a/arch/powerpc/kernel/lparcfg.c +++ b/arch/powerpc/kernel/lparcfg.c @@ -37,7 +37,13 @@ #include <asm/vdso_datapage.h> #include <asm/vio.h> #include <asm/mmu.h> +#include <asm/machdep.h> + +/* + * This isn't a module but we expose that to userspace + * via /proc so leave the definitions here + */ #define MODULE_VERS "1.9" #define MODULE_NAME "lparcfg" @@ -369,6 +375,7 @@ static void parse_system_parameter_string(struct seq_file *m) __pa(rtas_data_buf), RTAS_DATA_BUF_SIZE); memcpy(local_buffer, rtas_data_buf, SPLPAR_MAXLENGTH); + local_buffer[SPLPAR_MAXLENGTH - 1] = '\0'; spin_unlock(&rtas_data_buf_lock); if (call_status != 0) { @@ -487,7 +494,8 @@ static void parse_em_data(struct seq_file *m) { unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; - if (plpar_hcall(H_GET_EM_PARMS, retbuf) == H_SUCCESS) + if (firmware_has_feature(FW_FEATURE_LPAR) && + plpar_hcall(H_GET_EM_PARMS, retbuf) == H_SUCCESS) seq_printf(m, "power_mode_data=%016lx\n", retbuf[0]); } @@ -772,7 +780,6 @@ static int lparcfg_open(struct inode *inode, struct file *file) } static const struct file_operations lparcfg_fops = { - .owner = THIS_MODULE, .read = seq_read, .write = lparcfg_write, .open = lparcfg_open, @@ -799,15 +806,4 @@ static int __init lparcfg_init(void) proc_ppc64_lparcfg = ent; return 0; } - -static void __exit lparcfg_cleanup(void) -{ - if (proc_ppc64_lparcfg) - remove_proc_entry("lparcfg", proc_ppc64_lparcfg->parent); -} - -module_init(lparcfg_init); -module_exit(lparcfg_cleanup); -MODULE_DESCRIPTION("Interface for LPAR configuration data"); -MODULE_AUTHOR("Dave Engebretsen"); -MODULE_LICENSE("GPL"); +machine_device_initcall(pseries, lparcfg_init); diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c index 7ee50f0..9ce1672 100644 --- a/arch/powerpc/kernel/machine_kexec.c +++ b/arch/powerpc/kernel/machine_kexec.c @@ -126,7 +126,7 @@ void __init reserve_crashkernel(void) /* We might have got these values via the command line or the * device tree, either way sanitise them now. */ - crash_size = crashk_res.end - crashk_res.start + 1; + crash_size = resource_size(&crashk_res); #ifndef CONFIG_RELOCATABLE if (crashk_res.start != KDUMP_KERNELBASE) @@ -136,12 +136,16 @@ void __init reserve_crashkernel(void) crashk_res.start = KDUMP_KERNELBASE; #else if (!crashk_res.start) { +#ifdef CONFIG_PPC64 /* - * unspecified address, choose a region of specified size - * can overlap with initrd (ignoring corruption when retained) - * ppc64 requires kernel and some stacks to be in first segemnt + * On 64bit we split the RMO in half but cap it at half of + * a small SLB (128MB) since the crash kernel needs to place + * itself and some stacks to be in the first segment. */ + crashk_res.start = min(0x80000000ULL, (ppc64_rma_size / 2)); +#else crashk_res.start = KDUMP_KERNELBASE; +#endif } crash_base = PAGE_ALIGN(crashk_res.start); @@ -222,7 +226,7 @@ static void __init export_crashk_values(struct device_node *node) if (crashk_res.start != 0) { prom_add_property(node, &crashk_base_prop); - crashk_size = crashk_res.end - crashk_res.start + 1; + crashk_size = resource_size(&crashk_res); prom_add_property(node, &crashk_size_prop); } } diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c index cac9d2c..4c0908d 100644 --- a/arch/powerpc/kernel/machine_kexec_64.c +++ b/arch/powerpc/kernel/machine_kexec_64.c @@ -74,8 +74,7 @@ int default_machine_kexec_prepare(struct kimage *image) } /* We also should not overwrite the tce tables */ - for (node = of_find_node_by_type(NULL, "pci"); node != NULL; - node = of_find_node_by_type(node, "pci")) { + for_each_node_by_type(node, "pci") { basep = of_get_property(node, "linux,tce-base", NULL); sizep = of_get_property(node, "linux,tce-size", NULL); if (basep == NULL || sizep == NULL) diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index 998a100..7cd07b4 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -8,6 +8,8 @@ * kexec bits: * Copyright (C) 2002-2003 Eric Biederman <ebiederm@xmission.com> * GameCube/ppc32 port Copyright (C) 2004 Albert Herranz + * PPC44x port. Copyright (C) 2011, IBM Corporation + * Author: Suzuki Poulose <suzuki@in.ibm.com> * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -736,6 +738,175 @@ relocate_new_kernel: mr r5, r31 li r0, 0 +#elif defined(CONFIG_44x) && !defined(CONFIG_PPC_47x) + +/* + * Code for setting up 1:1 mapping for PPC440x for KEXEC + * + * We cannot switch off the MMU on PPC44x. + * So we: + * 1) Invalidate all the mappings except the one we are running from. + * 2) Create a tmp mapping for our code in the other address space(TS) and + * jump to it. Invalidate the entry we started in. + * 3) Create a 1:1 mapping for 0-2GiB in chunks of 256M in original TS. + * 4) Jump to the 1:1 mapping in original TS. + * 5) Invalidate the tmp mapping. + * + * - Based on the kexec support code for FSL BookE + * - Doesn't support 47x yet. + * + */ + /* Save our parameters */ + mr r29, r3 + mr r30, r4 + mr r31, r5 + + /* Load our MSR_IS and TID to MMUCR for TLB search */ + mfspr r3,SPRN_PID + mfmsr r4 + andi. r4,r4,MSR_IS@l + beq wmmucr + oris r3,r3,PPC44x_MMUCR_STS@h +wmmucr: + mtspr SPRN_MMUCR,r3 + sync + + /* + * Invalidate all the TLB entries except the current entry + * where we are running from + */ + bl 0f /* Find our address */ +0: mflr r5 /* Make it accessible */ + tlbsx r23,0,r5 /* Find entry we are in */ + li r4,0 /* Start at TLB entry 0 */ + li r3,0 /* Set PAGEID inval value */ +1: cmpw r23,r4 /* Is this our entry? */ + beq skip /* If so, skip the inval */ + tlbwe r3,r4,PPC44x_TLB_PAGEID /* If not, inval the entry */ +skip: + addi r4,r4,1 /* Increment */ + cmpwi r4,64 /* Are we done? */ + bne 1b /* If not, repeat */ + isync + + /* Create a temp mapping and jump to it */ + andi. r6, r23, 1 /* Find the index to use */ + addi r24, r6, 1 /* r24 will contain 1 or 2 */ + + mfmsr r9 /* get the MSR */ + rlwinm r5, r9, 27, 31, 31 /* Extract the MSR[IS] */ + xori r7, r5, 1 /* Use the other address space */ + + /* Read the current mapping entries */ + tlbre r3, r23, PPC44x_TLB_PAGEID + tlbre r4, r23, PPC44x_TLB_XLAT + tlbre r5, r23, PPC44x_TLB_ATTRIB + + /* Save our current XLAT entry */ + mr r25, r4 + + /* Extract the TLB PageSize */ + li r10, 1 /* r10 will hold PageSize */ + rlwinm r11, r3, 0, 24, 27 /* bits 24-27 */ + + /* XXX: As of now we use 256M, 4K pages */ + cmpwi r11, PPC44x_TLB_256M + bne tlb_4k + rotlwi r10, r10, 28 /* r10 = 256M */ + b write_out +tlb_4k: + cmpwi r11, PPC44x_TLB_4K + bne default + rotlwi r10, r10, 12 /* r10 = 4K */ + b write_out +default: + rotlwi r10, r10, 10 /* r10 = 1K */ + +write_out: + /* + * Write out the tmp 1:1 mapping for this code in other address space + * Fixup EPN = RPN , TS=other address space + */ + insrwi r3, r7, 1, 23 /* Bit 23 is TS for PAGEID field */ + + /* Write out the tmp mapping entries */ + tlbwe r3, r24, PPC44x_TLB_PAGEID + tlbwe r4, r24, PPC44x_TLB_XLAT + tlbwe r5, r24, PPC44x_TLB_ATTRIB + + subi r11, r10, 1 /* PageOffset Mask = PageSize - 1 */ + not r10, r11 /* Mask for PageNum */ + + /* Switch to other address space in MSR */ + insrwi r9, r7, 1, 26 /* Set MSR[IS] = r7 */ + + bl 1f +1: mflr r8 + addi r8, r8, (2f-1b) /* Find the target offset */ + + /* Jump to the tmp mapping */ + mtspr SPRN_SRR0, r8 + mtspr SPRN_SRR1, r9 + rfi + +2: + /* Invalidate the entry we were executing from */ + li r3, 0 + tlbwe r3, r23, PPC44x_TLB_PAGEID + + /* attribute fields. rwx for SUPERVISOR mode */ + li r5, 0 + ori r5, r5, (PPC44x_TLB_SW | PPC44x_TLB_SR | PPC44x_TLB_SX | PPC44x_TLB_G) + + /* Create 1:1 mapping in 256M pages */ + xori r7, r7, 1 /* Revert back to Original TS */ + + li r8, 0 /* PageNumber */ + li r6, 3 /* TLB Index, start at 3 */ + +next_tlb: + rotlwi r3, r8, 28 /* Create EPN (bits 0-3) */ + mr r4, r3 /* RPN = EPN */ + ori r3, r3, (PPC44x_TLB_VALID | PPC44x_TLB_256M) /* SIZE = 256M, Valid */ + insrwi r3, r7, 1, 23 /* Set TS from r7 */ + + tlbwe r3, r6, PPC44x_TLB_PAGEID /* PageID field : EPN, V, SIZE */ + tlbwe r4, r6, PPC44x_TLB_XLAT /* Address translation : RPN */ + tlbwe r5, r6, PPC44x_TLB_ATTRIB /* Attributes */ + + addi r8, r8, 1 /* Increment PN */ + addi r6, r6, 1 /* Increment TLB Index */ + cmpwi r8, 8 /* Are we done ? */ + bne next_tlb + isync + + /* Jump to the new mapping 1:1 */ + li r9,0 + insrwi r9, r7, 1, 26 /* Set MSR[IS] = r7 */ + + bl 1f +1: mflr r8 + and r8, r8, r11 /* Get our offset within page */ + addi r8, r8, (2f-1b) + + and r5, r25, r10 /* Get our target PageNum */ + or r8, r8, r5 /* Target jump address */ + + mtspr SPRN_SRR0, r8 + mtspr SPRN_SRR1, r9 + rfi +2: + /* Invalidate the tmp entry we used */ + li r3, 0 + tlbwe r3, r24, PPC44x_TLB_PAGEID + sync + + /* Restore the parameters */ + mr r3, r29 + mr r4, r30 + mr r5, r31 + + li r0, 0 #else li r0, 0 diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index e89df59..616921e 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -339,7 +339,7 @@ _GLOBAL(real_205_writeb) #endif /* CONFIG_PPC_PASEMI */ -#ifdef CONFIG_CPU_FREQ_PMAC64 +#if defined(CONFIG_CPU_FREQ_PMAC64) || defined(CONFIG_CPU_FREQ_MAPLE) /* * SCOM access functions for 970 (FX only for now) * @@ -408,7 +408,7 @@ _GLOBAL(scom970_write) /* restore interrupts */ mtmsrd r5,1 blr -#endif /* CONFIG_CPU_FREQ_PMAC64 */ +#endif /* CONFIG_CPU_FREQ_PMAC64 || CONFIG_CPU_FREQ_MAPLE */ /* diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c index 49cee9d..2d27570 100644 --- a/arch/powerpc/kernel/module.c +++ b/arch/powerpc/kernel/module.c @@ -16,7 +16,6 @@ along with this program; if not, write to the Free Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ -#include <linux/module.h> #include <linux/elf.h> #include <linux/moduleloader.h> #include <linux/err.h> @@ -31,20 +30,6 @@ LIST_HEAD(module_bug_list); -void *module_alloc(unsigned long size) -{ - if (size == 0) - return NULL; - - return vmalloc_exec(size); -} - -/* Free memory returned from module_alloc */ -void module_free(struct module *mod, void *module_region) -{ - vfree(module_region); -} - static const Elf_Shdr *find_section(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, const char *name) @@ -93,7 +78,3 @@ int module_finalize(const Elf_Ehdr *hdr, return 0; } - -void module_arch_cleanup(struct module *mod) -{ -} diff --git a/arch/powerpc/kernel/module_32.c b/arch/powerpc/kernel/module_32.c index 449a7e0..2e3200c 100644 --- a/arch/powerpc/kernel/module_32.c +++ b/arch/powerpc/kernel/module_32.c @@ -174,17 +174,6 @@ int module_frob_arch_sections(Elf32_Ehdr *hdr, return 0; } -int apply_relocate(Elf32_Shdr *sechdrs, - const char *strtab, - unsigned int symindex, - unsigned int relsec, - struct module *module) -{ - printk(KERN_ERR "%s: Non-ADD RELOCATION unsupported\n", - module->name); - return -ENOEXEC; -} - static inline int entry_matches(struct ppc_plt_entry *entry, Elf32_Addr val) { if (entry->jump[0] == 0x3d800000 + ((val + 0x8000) >> 16) diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 8fbb125..9f44a77 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -243,16 +243,6 @@ int module_frob_arch_sections(Elf64_Ehdr *hdr, return 0; } -int apply_relocate(Elf64_Shdr *sechdrs, - const char *strtab, - unsigned int symindex, - unsigned int relsec, - struct module *me) -{ - printk(KERN_ERR "%s: Non-ADD RELOCATION unsupported\n", me->name); - return -ENOEXEC; -} - /* r2 is the TOC pointer: it actually points 0x8000 into the TOC (this gives the value maximum span in an instruction which uses a signed offset) */ diff --git a/arch/powerpc/kernel/mpc7450-pmu.c b/arch/powerpc/kernel/mpc7450-pmu.c index 2cc5e03..fe21b51 100644 --- a/arch/powerpc/kernel/mpc7450-pmu.c +++ b/arch/powerpc/kernel/mpc7450-pmu.c @@ -388,6 +388,11 @@ static int mpc7450_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { [C(OP_WRITE)] = { -1, -1 }, [C(OP_PREFETCH)] = { -1, -1 }, }, + [C(NODE)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { -1, -1 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, }; struct power_pmu mpc7450_pmu = { @@ -405,7 +410,7 @@ struct power_pmu mpc7450_pmu = { .cache_events = &mpc7450_cache_events, }; -static int init_mpc7450_pmu(void) +static int __init init_mpc7450_pmu(void) { if (!cur_cpu_spec->oprofile_cpu_type || strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc/7450")) diff --git a/arch/powerpc/kernel/of_platform.c b/arch/powerpc/kernel/of_platform.c index 2458218..e1612df 100644 --- a/arch/powerpc/kernel/of_platform.c +++ b/arch/powerpc/kernel/of_platform.c @@ -15,7 +15,7 @@ #include <linux/string.h> #include <linux/kernel.h> #include <linux/init.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/mod_devicetable.h> #include <linux/pci.h> #include <linux/of.h> @@ -26,7 +26,7 @@ #include <asm/topology.h> #include <asm/pci-bridge.h> #include <asm/ppc-pci.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #ifdef CONFIG_PPC_OF_PLATFORM_PCI diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index efeb881..41456ff 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -8,7 +8,7 @@ */ #include <linux/smp.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/memblock.h> #include <asm/firmware.h> @@ -167,7 +167,7 @@ void setup_paca(struct paca_struct *new_paca) * if we do a GET_PACA() before the feature fixups have been * applied */ - if (cpu_has_feature(CPU_FTR_HVMODE_206)) + if (cpu_has_feature(CPU_FTR_HVMODE)) mtspr(SPRN_SPRG_HPACA, local_paca); #endif mtspr(SPRN_SPRG_PACA, local_paca); diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 893af2a..12659ab 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -21,6 +21,7 @@ #include <linux/string.h> #include <linux/init.h> #include <linux/bootmem.h> +#include <linux/export.h> #include <linux/of_address.h> #include <linux/of_pci.h> #include <linux/mm.h> @@ -50,7 +51,7 @@ static int global_phb_number; /* Global phb counter */ resource_size_t isa_mem_base; /* Default PCI flags is 0 on ppc32, modified at boot on ppc64 */ -unsigned int ppc_pci_flags = 0; +unsigned int pci_flags = 0; static struct dma_map_ops *pci_dma_ops = &dma_direct_ops; @@ -107,7 +108,7 @@ static resource_size_t pcibios_io_size(const struct pci_controller *hose) #ifdef CONFIG_PPC64 return hose->pci_io_size; #else - return hose->io_resource.end - hose->io_resource.start + 1; + return resource_size(&hose->io_resource); #endif } @@ -362,7 +363,6 @@ static pgprot_t __pci_mmap_set_pgprot(struct pci_dev *dev, struct resource *rp, enum pci_mmap_state mmap_state, int write_combine) { - unsigned long prot = pgprot_val(protection); /* Write combine is always 0 on non-memory space mappings. On * memory space, if the user didn't pass 1, we check for a @@ -379,9 +379,9 @@ static pgprot_t __pci_mmap_set_pgprot(struct pci_dev *dev, struct resource *rp, /* XXX would be nice to have a way to ask for write-through */ if (write_combine) - return pgprot_noncached_wc(prot); + return pgprot_noncached_wc(protection); else - return pgprot_noncached(prot); + return pgprot_noncached(protection); } /* @@ -842,9 +842,9 @@ int pci_proc_domain(struct pci_bus *bus) { struct pci_controller *hose = pci_bus_to_host(bus); - if (!(ppc_pci_flags & PPC_PCI_ENABLE_PROC_DOMAINS)) + if (!pci_has_flag(PCI_ENABLE_PROC_DOMAINS)) return 0; - if (ppc_pci_flags & PPC_PCI_COMPAT_DOMAIN_0) + if (pci_has_flag(PCI_COMPAT_DOMAIN_0)) return hose->global_number != 0; return 1; } @@ -920,13 +920,13 @@ static void __devinit pcibios_fixup_resources(struct pci_dev *dev) struct resource *res = dev->resource + i; if (!res->flags) continue; - /* On platforms that have PPC_PCI_PROBE_ONLY set, we don't + /* On platforms that have PCI_PROBE_ONLY set, we don't * consider 0 as an unassigned BAR value. It's technically * a valid value, but linux doesn't like it... so when we can * re-assign things, we do so, but if we can't, we keep it * around and hope for the best... */ - if (res->start == 0 && !(ppc_pci_flags & PPC_PCI_PROBE_ONLY)) { + if (res->start == 0 && !pci_has_flag(PCI_PROBE_ONLY)) { pr_debug("PCI:%s Resource %d %016llx-%016llx [%x] is unassigned\n", pci_name(dev), i, (unsigned long long)res->start, @@ -973,7 +973,7 @@ static int __devinit pcibios_uninitialized_bridge_resource(struct pci_bus *bus, int i; /* We don't do anything if PCI_PROBE_ONLY is set */ - if (ppc_pci_flags & PPC_PCI_PROBE_ONLY) + if (pci_has_flag(PCI_PROBE_ONLY)) return 0; /* Job is a bit different between memory and IO */ @@ -1097,9 +1097,6 @@ void __devinit pcibios_setup_bus_devices(struct pci_bus *bus) if (dev->is_added) continue; - /* Setup OF node pointer in the device */ - dev->dev.of_node = pci_device_to_OF_node(dev); - /* Fixup NUMA node as it may not be setup yet by the generic * code and is needed by the DMA init */ @@ -1146,7 +1143,7 @@ void __devinit pci_fixup_cardbus(struct pci_bus *bus) static int skip_isa_ioresource_align(struct pci_dev *dev) { - if ((ppc_pci_flags & PPC_PCI_CAN_SKIP_ISA_ALIGN) && + if (pci_has_flag(PCI_CAN_SKIP_ISA_ALIGN) && !(dev->bus->bridge_ctl & PCI_BRIDGE_CTL_ISA)) return 1; return 0; @@ -1274,7 +1271,7 @@ void pcibios_allocate_bus_resources(struct pci_bus *bus) * and as such ensure proper re-allocation * later. */ - if (ppc_pci_flags & PPC_PCI_REASSIGN_ALL_RSRC) + if (pci_has_flag(PCI_REASSIGN_ALL_RSRC)) goto clear_resource; pr = pci_find_parent_resource(bus->self, res); if (pr == res) { @@ -1459,7 +1456,7 @@ void __init pcibios_resource_survey(void) list_for_each_entry(b, &pci_root_buses, node) pcibios_allocate_bus_resources(b); - if (!(ppc_pci_flags & PPC_PCI_REASSIGN_ALL_RSRC)) { + if (!pci_has_flag(PCI_REASSIGN_ALL_RSRC)) { pcibios_allocate_resources(0); pcibios_allocate_resources(1); } @@ -1468,7 +1465,7 @@ void __init pcibios_resource_survey(void) * the low IO area and the VGA memory area if they intersect the * bus available resources to avoid allocating things on top of them */ - if (!(ppc_pci_flags & PPC_PCI_PROBE_ONLY)) { + if (!pci_has_flag(PCI_PROBE_ONLY)) { list_for_each_entry(b, &pci_root_buses, node) pcibios_reserve_legacy_regions(b); } @@ -1476,7 +1473,7 @@ void __init pcibios_resource_survey(void) /* Now, if the platform didn't decide to blindly trust the firmware, * we proceed to assigning things that were left unassigned */ - if (!(ppc_pci_flags & PPC_PCI_PROBE_ONLY)) { + if (!pci_has_flag(PCI_PROBE_ONLY)) { pr_debug("PCI: Assigning unassigned resources...\n"); pci_assign_unassigned_resources(); } @@ -1685,6 +1682,13 @@ int early_find_capability(struct pci_controller *hose, int bus, int devfn, return pci_bus_find_capability(fake_pci_bus(hose, bus), devfn, cap); } +struct device_node *pcibios_get_phb_of_node(struct pci_bus *bus) +{ + struct pci_controller *hose = bus->sysdata; + + return of_node_get(hose->dn); +} + /** * pci_scan_phb - Given a pci_controller, setup and scan the PCI bus * @hose: Pointer to the PCI host controller instance structure @@ -1705,7 +1709,6 @@ void __devinit pcibios_scan_phb(struct pci_controller *hose) hose->global_number); return; } - bus->dev.of_node = of_node_get(node); bus->secondary = hose->first_busno; hose->bus = bus; @@ -1727,4 +1730,33 @@ void __devinit pcibios_scan_phb(struct pci_controller *hose) if (mode == PCI_PROBE_NORMAL) hose->last_busno = bus->subordinate = pci_scan_child_bus(bus); + + /* Configure PCI Express settings */ + if (bus && !pci_has_flag(PCI_PROBE_ONLY)) { + struct pci_bus *child; + list_for_each_entry(child, &bus->children, node) { + struct pci_dev *self = child->self; + if (!self) + continue; + pcie_bus_configure_settings(child, self->pcie_mpss); + } + } +} + +static void fixup_hide_host_resource_fsl(struct pci_dev *dev) +{ + int i, class = dev->class >> 8; + + if ((class == PCI_CLASS_PROCESSOR_POWERPC || + class == PCI_CLASS_BRIDGE_OTHER) && + (dev->hdr_type == PCI_HEADER_TYPE_NORMAL) && + (dev->bus->parent == NULL)) { + for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) { + dev->resource[i].start = 0; + dev->resource[i].end = 0; + dev->resource[i].flags = 0; + } + } } +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MOTOROLA, PCI_ANY_ID, fixup_hide_host_resource_fsl); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_FREESCALE, PCI_ANY_ID, fixup_hide_host_resource_fsl); diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c index bedb370..fdd1a3d 100644 --- a/arch/powerpc/kernel/pci_32.c +++ b/arch/powerpc/kernel/pci_32.c @@ -15,6 +15,7 @@ #include <linux/list.h> #include <linux/of.h> #include <linux/slab.h> +#include <linux/export.h> #include <asm/processor.h> #include <asm/io.h> @@ -51,25 +52,6 @@ struct pci_dev *isa_bridge_pcidev; EXPORT_SYMBOL_GPL(isa_bridge_pcidev); static void -fixup_hide_host_resource_fsl(struct pci_dev *dev) -{ - int i, class = dev->class >> 8; - - if ((class == PCI_CLASS_PROCESSOR_POWERPC || - class == PCI_CLASS_BRIDGE_OTHER) && - (dev->hdr_type == PCI_HEADER_TYPE_NORMAL) && - (dev->bus->parent == NULL)) { - for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) { - dev->resource[i].start = 0; - dev->resource[i].end = 0; - dev->resource[i].flags = 0; - } - } -} -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MOTOROLA, PCI_ANY_ID, fixup_hide_host_resource_fsl); -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_FREESCALE, PCI_ANY_ID, fixup_hide_host_resource_fsl); - -static void fixup_cpc710_pci64(struct pci_dev* dev) { /* Hide the PCI64 BARs from the kernel as their content doesn't @@ -167,150 +149,26 @@ pcibios_make_OF_bus_map(void) #endif } -typedef int (*pci_OF_scan_iterator)(struct device_node* node, void* data); - -static struct device_node* -scan_OF_pci_childs(struct device_node *parent, pci_OF_scan_iterator filter, void* data) -{ - struct device_node *node; - struct device_node* sub_node; - - for_each_child_of_node(parent, node) { - const unsigned int *class_code; - - if (filter(node, data)) { - of_node_put(node); - return node; - } - - /* For PCI<->PCI bridges or CardBus bridges, we go down - * Note: some OFs create a parent node "multifunc-device" as - * a fake root for all functions of a multi-function device, - * we go down them as well. - */ - class_code = of_get_property(node, "class-code", NULL); - if ((!class_code || ((*class_code >> 8) != PCI_CLASS_BRIDGE_PCI && - (*class_code >> 8) != PCI_CLASS_BRIDGE_CARDBUS)) && - strcmp(node->name, "multifunc-device")) - continue; - sub_node = scan_OF_pci_childs(node, filter, data); - if (sub_node) { - of_node_put(node); - return sub_node; - } - } - return NULL; -} - -static struct device_node *scan_OF_for_pci_dev(struct device_node *parent, - unsigned int devfn) -{ - struct device_node *np, *cnp; - const u32 *reg; - unsigned int psize; - - for_each_child_of_node(parent, np) { - reg = of_get_property(np, "reg", &psize); - if (reg && psize >= 4 && ((reg[0] >> 8) & 0xff) == devfn) - return np; - - /* Note: some OFs create a parent node "multifunc-device" as - * a fake root for all functions of a multi-function device, - * we go down them as well. */ - if (!strcmp(np->name, "multifunc-device")) { - cnp = scan_OF_for_pci_dev(np, devfn); - if (cnp) - return cnp; - } - } - return NULL; -} - - -static struct device_node *scan_OF_for_pci_bus(struct pci_bus *bus) -{ - struct device_node *parent, *np; - - /* Are we a root bus ? */ - if (bus->self == NULL || bus->parent == NULL) { - struct pci_controller *hose = pci_bus_to_host(bus); - if (hose == NULL) - return NULL; - return of_node_get(hose->dn); - } - - /* not a root bus, we need to get our parent */ - parent = scan_OF_for_pci_bus(bus->parent); - if (parent == NULL) - return NULL; - - /* now iterate for children for a match */ - np = scan_OF_for_pci_dev(parent, bus->self->devfn); - of_node_put(parent); - - return np; -} - -/* - * Scans the OF tree for a device node matching a PCI device - */ -struct device_node * -pci_busdev_to_OF_node(struct pci_bus *bus, int devfn) -{ - struct device_node *parent, *np; - - pr_debug("pci_busdev_to_OF_node(%d,0x%x)\n", bus->number, devfn); - parent = scan_OF_for_pci_bus(bus); - if (parent == NULL) - return NULL; - pr_debug(" parent is %s\n", parent ? parent->full_name : "<NULL>"); - np = scan_OF_for_pci_dev(parent, devfn); - of_node_put(parent); - pr_debug(" result is %s\n", np ? np->full_name : "<NULL>"); - - /* XXX most callers don't release the returned node - * mostly because ppc64 doesn't increase the refcount, - * we need to fix that. - */ - return np; -} -EXPORT_SYMBOL(pci_busdev_to_OF_node); - -struct device_node* -pci_device_to_OF_node(struct pci_dev *dev) -{ - return pci_busdev_to_OF_node(dev->bus, dev->devfn); -} -EXPORT_SYMBOL(pci_device_to_OF_node); - -static int -find_OF_pci_device_filter(struct device_node* node, void* data) -{ - return ((void *)node == data); -} /* * Returns the PCI device matching a given OF node */ -int -pci_device_from_OF_node(struct device_node* node, u8* bus, u8* devfn) +int pci_device_from_OF_node(struct device_node *node, u8 *bus, u8 *devfn) { - const unsigned int *reg; - struct pci_controller* hose; - struct pci_dev* dev = NULL; - - /* Make sure it's really a PCI device */ - hose = pci_find_hose_for_OF_device(node); - if (!hose || !hose->dn) - return -ENODEV; - if (!scan_OF_pci_childs(hose->dn, - find_OF_pci_device_filter, (void *)node)) + struct pci_dev *dev = NULL; + const __be32 *reg; + int size; + + /* Check if it might have a chance to be a PCI device */ + if (!pci_find_hose_for_OF_device(node)) return -ENODEV; - reg = of_get_property(node, "reg", NULL); - if (!reg) + + reg = of_get_property(node, "reg", &size); + if (!reg || size < 5 * sizeof(u32)) return -ENODEV; - *bus = (reg[0] >> 16) & 0xff; - *devfn = ((reg[0] >> 8) & 0xff); + + *bus = (be32_to_cpup(®[0]) >> 16) & 0xff; + *devfn = (be32_to_cpup(®[0]) >> 8) & 0xff; /* Ok, here we need some tweak. If we have already renumbered * all busses, we can't rely on the OF bus number any more. @@ -373,7 +231,7 @@ static int __init pcibios_init(void) printk(KERN_INFO "PCI: Probing PCI hardware\n"); - if (ppc_pci_flags & PPC_PCI_REASSIGN_ALL_BUS) + if (pci_has_flag(PCI_REASSIGN_ALL_BUS)) pci_assign_all_buses = 1; /* Scan all of the recorded PCI controllers. */ diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index fc6452b..bcf4bf9 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -18,6 +18,7 @@ #include <linux/string.h> #include <linux/init.h> #include <linux/bootmem.h> +#include <linux/export.h> #include <linux/mm.h> #include <linux/list.h> #include <linux/syscalls.h> @@ -55,12 +56,12 @@ static int __init pcibios_init(void) ppc_md.phys_mem_access_prot = pci_phys_mem_access_prot; if (pci_probe_only) - ppc_pci_flags |= PPC_PCI_PROBE_ONLY; + pci_add_flags(PCI_PROBE_ONLY); /* On ppc64, we always enable PCI domains and we keep domain 0 * backward compatible in /proc for video cards */ - ppc_pci_flags |= PPC_PCI_ENABLE_PROC_DOMAINS | PPC_PCI_COMPAT_DOMAIN_0; + pci_add_flags(PCI_ENABLE_PROC_DOMAINS | PCI_COMPAT_DOMAIN_0); /* Scan all of the recorded PCI controllers. */ list_for_each_entry_safe(hose, tmp, &hose_list, list_node) { diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c index 6baabc1..4e69deb 100644 --- a/arch/powerpc/kernel/pci_dn.c +++ b/arch/powerpc/kernel/pci_dn.c @@ -22,6 +22,7 @@ #include <linux/kernel.h> #include <linux/pci.h> #include <linux/string.h> +#include <linux/export.h> #include <linux/init.h> #include <linux/gfp.h> @@ -142,53 +143,6 @@ void __devinit pci_devs_phb_init_dynamic(struct pci_controller *phb) traverse_pci_devices(dn, update_dn_pci_info, phb); } -/* - * Traversal func that looks for a <busno,devfcn> value. - * If found, the pci_dn is returned (thus terminating the traversal). - */ -static void *is_devfn_node(struct device_node *dn, void *data) -{ - int busno = ((unsigned long)data >> 8) & 0xff; - int devfn = ((unsigned long)data) & 0xff; - struct pci_dn *pci = dn->data; - - if (pci && (devfn == pci->devfn) && (busno == pci->busno)) - return dn; - return NULL; -} - -/* - * This is the "slow" path for looking up a device_node from a - * pci_dev. It will hunt for the device under its parent's - * phb and then update of_node pointer. - * - * It may also do fixups on the actual device since this happens - * on the first read/write. - * - * Note that it also must deal with devices that don't exist. - * In this case it may probe for real hardware ("just in case") - * and add a device_node to the device tree if necessary. - * - * Is this function necessary anymore now that dev->dev.of_node is - * used to store the node pointer? - * - */ -struct device_node *fetch_dev_dn(struct pci_dev *dev) -{ - struct pci_controller *phb = dev->sysdata; - struct device_node *dn; - unsigned long searchval = (dev->bus->number << 8) | dev->devfn; - - if (WARN_ON(!phb)) - return NULL; - - dn = traverse_pci_devices(phb->dn, is_devfn_node, (void *)searchval); - if (dn) - dev->dev.of_node = dn; - return dn; -} -EXPORT_SYMBOL(fetch_dev_dn); - /** * pci_devs_phb_init - Initialize phbs and pci devs under them. * diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c index 1e89a72..b37d0b5 100644 --- a/arch/powerpc/kernel/pci_of_scan.c +++ b/arch/powerpc/kernel/pci_of_scan.c @@ -15,6 +15,7 @@ */ #include <linux/pci.h> +#include <linux/export.h> #include <asm/pci-bridge.h> #include <asm/prom.h> @@ -202,9 +203,9 @@ EXPORT_SYMBOL(of_create_pci_dev); * this routine in turn call of_scan_bus() recusively to scan for more child * devices. */ -void __devinit of_scan_pci_bridge(struct device_node *node, - struct pci_dev *dev) +void __devinit of_scan_pci_bridge(struct pci_dev *dev) { + struct device_node *node = dev->dev.of_node; struct pci_bus *bus; const u32 *busrange, *ranges; int len, i, mode; @@ -238,7 +239,6 @@ void __devinit of_scan_pci_bridge(struct device_node *node, bus->primary = dev->bus->number; bus->subordinate = busrange[1]; bus->bridge_ctl = 0; - bus->dev.of_node = of_node_get(node); /* parse ranges property */ /* PCI #address-cells == 3 and #size-cells == 2 always */ @@ -335,9 +335,7 @@ static void __devinit __of_scan_bus(struct device_node *node, list_for_each_entry(dev, &bus->devices, bus_list) { if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE || dev->hdr_type == PCI_HEADER_TYPE_CARDBUS) { - struct device_node *child = pci_device_to_OF_node(dev); - if (child) - of_scan_pci_bridge(child, dev); + of_scan_pci_bridge(dev); } } } diff --git a/arch/powerpc/kernel/perf_callchain.c b/arch/powerpc/kernel/perf_callchain.c index d05ae42..e80026c 100644 --- a/arch/powerpc/kernel/perf_callchain.c +++ b/arch/powerpc/kernel/perf_callchain.c @@ -154,8 +154,12 @@ static int read_user_stack_64(unsigned long __user *ptr, unsigned long *ret) ((unsigned long)ptr & 7)) return -EFAULT; - if (!__get_user_inatomic(*ret, ptr)) + pagefault_disable(); + if (!__get_user_inatomic(*ret, ptr)) { + pagefault_enable(); return 0; + } + pagefault_enable(); return read_user_stack_slow(ptr, ret, 8); } @@ -166,8 +170,12 @@ static int read_user_stack_32(unsigned int __user *ptr, unsigned int *ret) ((unsigned long)ptr & 3)) return -EFAULT; - if (!__get_user_inatomic(*ret, ptr)) + pagefault_disable(); + if (!__get_user_inatomic(*ret, ptr)) { + pagefault_enable(); return 0; + } + pagefault_enable(); return read_user_stack_slow(ptr, ret, 4); } @@ -235,7 +243,7 @@ static void perf_callchain_user_64(struct perf_callchain_entry *entry, sp = regs->gpr[1]; perf_callchain_store(entry, next_ip); - for (;;) { + while (entry->nr < PERF_MAX_STACK_DEPTH) { fp = (unsigned long __user *) sp; if (!valid_user_sp(sp, 1) || read_user_stack_64(fp, &next_sp)) return; @@ -294,11 +302,17 @@ static inline int current_is_64bit(void) */ static int read_user_stack_32(unsigned int __user *ptr, unsigned int *ret) { + int rc; + if ((unsigned long)ptr > TASK_SIZE - sizeof(unsigned int) || ((unsigned long)ptr & 3)) return -EFAULT; - return __get_user_inatomic(*ret, ptr); + pagefault_disable(); + rc = __get_user_inatomic(*ret, ptr); + pagefault_enable(); + + return rc; } static inline void perf_callchain_user_64(struct perf_callchain_entry *entry, diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c index 5793c4b..64483fd 100644 --- a/arch/powerpc/kernel/perf_event.c +++ b/arch/powerpc/kernel/perf_event.c @@ -1213,7 +1213,7 @@ struct pmu power_pmu = { * here so there is no possibility of being interrupted. */ static void record_and_restart(struct perf_event *event, unsigned long val, - struct pt_regs *regs, int nmi) + struct pt_regs *regs) { u64 period = event->hw.sample_period; s64 prev, delta, left; @@ -1264,7 +1264,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val, if (event->attr.sample_type & PERF_SAMPLE_ADDR) perf_get_data_addr(regs, &data.addr); - if (perf_event_overflow(event, nmi, &data, regs)) + if (perf_event_overflow(event, &data, regs)) power_pmu_stop(event, 0); } } @@ -1352,7 +1352,7 @@ static void perf_event_interrupt(struct pt_regs *regs) if ((int)val < 0) { /* event has overflowed */ found = 1; - record_and_restart(event, val, regs, nmi); + record_and_restart(event, val, regs); } } @@ -1414,7 +1414,7 @@ power_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu return NOTIFY_OK; } -int register_power_pmu(struct power_pmu *pmu) +int __cpuinit register_power_pmu(struct power_pmu *pmu) { if (ppmu) return -EBUSY; /* something's already registered */ diff --git a/arch/powerpc/kernel/perf_event_fsl_emb.c b/arch/powerpc/kernel/perf_event_fsl_emb.c index b0dc8f7..0a6d2a9 100644 --- a/arch/powerpc/kernel/perf_event_fsl_emb.c +++ b/arch/powerpc/kernel/perf_event_fsl_emb.c @@ -568,7 +568,7 @@ static struct pmu fsl_emb_pmu = { * here so there is no possibility of being interrupted. */ static void record_and_restart(struct perf_event *event, unsigned long val, - struct pt_regs *regs, int nmi) + struct pt_regs *regs) { u64 period = event->hw.sample_period; s64 prev, delta, left; @@ -616,7 +616,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val, perf_sample_data_init(&data, 0); data.period = event->hw.last_period; - if (perf_event_overflow(event, nmi, &data, regs)) + if (perf_event_overflow(event, &data, regs)) fsl_emb_pmu_stop(event, 0); } } @@ -644,7 +644,7 @@ static void perf_event_interrupt(struct pt_regs *regs) if (event) { /* event has overflowed */ found = 1; - record_and_restart(event, val, regs, nmi); + record_and_restart(event, val, regs); } else { /* * Disabled counter is negative, diff --git a/arch/powerpc/kernel/pmc.c b/arch/powerpc/kernel/pmc.c index 461499b..a841a9d 100644 --- a/arch/powerpc/kernel/pmc.c +++ b/arch/powerpc/kernel/pmc.c @@ -14,7 +14,7 @@ #include <linux/errno.h> #include <linux/spinlock.h> -#include <linux/module.h> +#include <linux/export.h> #include <asm/processor.h> #include <asm/cputable.h> diff --git a/arch/powerpc/kernel/power4-pmu.c b/arch/powerpc/kernel/power4-pmu.c index ead8b3c..b4f1dda 100644 --- a/arch/powerpc/kernel/power4-pmu.c +++ b/arch/powerpc/kernel/power4-pmu.c @@ -587,6 +587,11 @@ static int power4_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { [C(OP_WRITE)] = { -1, -1 }, [C(OP_PREFETCH)] = { -1, -1 }, }, + [C(NODE)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { -1, -1 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, }; static struct power_pmu power4_pmu = { @@ -604,7 +609,7 @@ static struct power_pmu power4_pmu = { .cache_events = &power4_cache_events, }; -static int init_power4_pmu(void) +static int __init init_power4_pmu(void) { if (!cur_cpu_spec->oprofile_cpu_type || strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power4")) diff --git a/arch/powerpc/kernel/power5+-pmu.c b/arch/powerpc/kernel/power5+-pmu.c index eca0ac5..a8757ba 100644 --- a/arch/powerpc/kernel/power5+-pmu.c +++ b/arch/powerpc/kernel/power5+-pmu.c @@ -653,6 +653,11 @@ static int power5p_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { [C(OP_WRITE)] = { -1, -1 }, [C(OP_PREFETCH)] = { -1, -1 }, }, + [C(NODE)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { -1, -1 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, }; static struct power_pmu power5p_pmu = { @@ -672,7 +677,7 @@ static struct power_pmu power5p_pmu = { .cache_events = &power5p_cache_events, }; -static int init_power5p_pmu(void) +static int __init init_power5p_pmu(void) { if (!cur_cpu_spec->oprofile_cpu_type || (strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power5+") diff --git a/arch/powerpc/kernel/power5-pmu.c b/arch/powerpc/kernel/power5-pmu.c index d5ff0f6..e7f06eb 100644 --- a/arch/powerpc/kernel/power5-pmu.c +++ b/arch/powerpc/kernel/power5-pmu.c @@ -595,6 +595,11 @@ static int power5_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { [C(OP_WRITE)] = { -1, -1 }, [C(OP_PREFETCH)] = { -1, -1 }, }, + [C(NODE)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { -1, -1 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, }; static struct power_pmu power5_pmu = { @@ -612,7 +617,7 @@ static struct power_pmu power5_pmu = { .cache_events = &power5_cache_events, }; -static int init_power5_pmu(void) +static int __init init_power5_pmu(void) { if (!cur_cpu_spec->oprofile_cpu_type || strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power5")) diff --git a/arch/powerpc/kernel/power6-pmu.c b/arch/powerpc/kernel/power6-pmu.c index 3160392..0bbc901 100644 --- a/arch/powerpc/kernel/power6-pmu.c +++ b/arch/powerpc/kernel/power6-pmu.c @@ -487,8 +487,8 @@ static int power6_generic_events[] = { */ static int power6_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { [C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */ - [C(OP_READ)] = { 0x80082, 0x80080 }, - [C(OP_WRITE)] = { 0x80086, 0x80088 }, + [C(OP_READ)] = { 0x280030, 0x80080 }, + [C(OP_WRITE)] = { 0x180032, 0x80088 }, [C(OP_PREFETCH)] = { 0x810a4, 0 }, }, [C(L1I)] = { /* RESULT_ACCESS RESULT_MISS */ @@ -516,6 +516,11 @@ static int power6_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { [C(OP_WRITE)] = { -1, -1 }, [C(OP_PREFETCH)] = { -1, -1 }, }, + [C(NODE)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { -1, -1 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, }; static struct power_pmu power6_pmu = { @@ -535,7 +540,7 @@ static struct power_pmu power6_pmu = { .cache_events = &power6_cache_events, }; -static int init_power6_pmu(void) +static int __init init_power6_pmu(void) { if (!cur_cpu_spec->oprofile_cpu_type || strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power6")) diff --git a/arch/powerpc/kernel/power7-pmu.c b/arch/powerpc/kernel/power7-pmu.c index 593740f..1251e4d 100644 --- a/arch/powerpc/kernel/power7-pmu.c +++ b/arch/powerpc/kernel/power7-pmu.c @@ -297,6 +297,8 @@ static void power7_disable_pmc(unsigned int pmc, unsigned long mmcr[]) static int power7_generic_events[] = { [PERF_COUNT_HW_CPU_CYCLES] = 0x1e, + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x100f8, /* GCT_NOSLOT_CYC */ + [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x4000a, /* CMPLU_STALL */ [PERF_COUNT_HW_INSTRUCTIONS] = 2, [PERF_COUNT_HW_CACHE_REFERENCES] = 0xc880, /* LD_REF_L1_LSU*/ [PERF_COUNT_HW_CACHE_MISSES] = 0x400f0, /* LD_MISS_L1 */ @@ -342,6 +344,11 @@ static int power7_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { [C(OP_WRITE)] = { -1, -1 }, [C(OP_PREFETCH)] = { -1, -1 }, }, + [C(NODE)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { -1, -1 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, }; static struct power_pmu power7_pmu = { @@ -360,7 +367,7 @@ static struct power_pmu power7_pmu = { .cache_events = &power7_cache_events, }; -static int init_power7_pmu(void) +static int __init init_power7_pmu(void) { if (!cur_cpu_spec->oprofile_cpu_type || strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power7")) diff --git a/arch/powerpc/kernel/ppc970-pmu.c b/arch/powerpc/kernel/ppc970-pmu.c index 9a6e093..8c21902 100644 --- a/arch/powerpc/kernel/ppc970-pmu.c +++ b/arch/powerpc/kernel/ppc970-pmu.c @@ -467,6 +467,11 @@ static int ppc970_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { [C(OP_WRITE)] = { -1, -1 }, [C(OP_PREFETCH)] = { -1, -1 }, }, + [C(NODE)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { -1, -1 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, }; static struct power_pmu ppc970_pmu = { @@ -484,7 +489,7 @@ static struct power_pmu ppc970_pmu = { .cache_events = &ppc970_cache_events, }; -static int init_ppc970_pmu(void) +static int __init init_ppc970_pmu(void) { if (!cur_cpu_spec->oprofile_cpu_type || (strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/970") diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c index 7d28f54..d3114a7 100644 --- a/arch/powerpc/kernel/ppc_ksyms.c +++ b/arch/powerpc/kernel/ppc_ksyms.c @@ -1,4 +1,4 @@ -#include <linux/module.h> +#include <linux/export.h> #include <linux/threads.h> #include <linux/smp.h> #include <linux/sched.h> @@ -18,7 +18,7 @@ #include <asm/cacheflush.h> #include <asm/uaccess.h> #include <asm/io.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <asm/checksum.h> #include <asm/pgtable.h> #include <asm/tlbflush.h> diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 5596397..d687e3f 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -28,7 +28,7 @@ #include <linux/init.h> #include <linux/prctl.h> #include <linux/init_task.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/kallsyms.h> #include <linux/mqueue.h> #include <linux/hardirq.h> @@ -96,6 +96,7 @@ void flush_fp_to_thread(struct task_struct *tsk) preempt_enable(); } } +EXPORT_SYMBOL_GPL(flush_fp_to_thread); void enable_kernel_fp(void) { @@ -145,6 +146,7 @@ void flush_altivec_to_thread(struct task_struct *tsk) preempt_enable(); } } +EXPORT_SYMBOL_GPL(flush_altivec_to_thread); #endif /* CONFIG_ALTIVEC */ #ifdef CONFIG_VSX @@ -186,6 +188,7 @@ void flush_vsx_to_thread(struct task_struct *tsk) preempt_enable(); } } +EXPORT_SYMBOL_GPL(flush_vsx_to_thread); #endif /* CONFIG_VSX */ #ifdef CONFIG_SPE @@ -213,6 +216,7 @@ void flush_spe_to_thread(struct task_struct *tsk) #ifdef CONFIG_SMP BUG_ON(tsk != current); #endif + tsk->thread.spefscr = mfspr(SPRN_SPEFSCR); giveup_spe(tsk); } preempt_enable(); @@ -482,28 +486,6 @@ struct task_struct *__switch_to(struct task_struct *prev, new_thread = &new->thread; old_thread = ¤t->thread; -#if defined(CONFIG_PPC_BOOK3E_64) - /* XXX Current Book3E code doesn't deal with kernel side DBCR0, - * we always hold the user values, so we set it now. - * - * However, we ensure the kernel MSR:DE is appropriately cleared too - * to avoid spurrious single step exceptions in the kernel. - * - * This will have to change to merge with the ppc32 code at some point, - * but I don't like much what ppc32 is doing today so there's some - * thinking needed there - */ - if ((new_thread->dbcr0 | old_thread->dbcr0) & DBCR0_IDM) { - u32 dbcr0; - - mtmsr(mfmsr() & ~MSR_DE); - isync(); - dbcr0 = mfspr(SPRN_DBCR0); - dbcr0 = (dbcr0 & DBCR0_EDM) | new_thread->dbcr0; - mtspr(SPRN_DBCR0, dbcr0); - } -#endif /* CONFIG_PPC64_BOOK3E */ - #ifdef CONFIG_PPC64 /* * Collect processor utilization data per process @@ -650,8 +632,10 @@ void show_regs(struct pt_regs * regs) printbits(regs->msr, msr_bits); printk(" CR: %08lx XER: %08lx\n", regs->ccr, regs->xer); trap = TRAP(regs); + if ((regs->trap != 0xc00) && cpu_has_feature(CPU_FTR_CFAR)) + printk("CFAR: "REG"\n", regs->orig_gpr3); if (trap == 0x300 || trap == 0x600) -#ifdef CONFIG_PPC_ADV_DEBUG_REGS +#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE) printk("DEAR: "REG", ESR: "REG"\n", regs->dar, regs->dsisr); #else printk("DAR: "REG", DSISR: %08lx\n", regs->dar, regs->dsisr); @@ -823,8 +807,6 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp) unsigned long load_addr = regs->gpr[2]; /* saved by ELF_PLAT_INIT */ #endif - set_fs(USER_DS); - /* * If we exec out of a kernel thread then thread.regs will not be * set. Do it now. diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 8c3112a..fa1235b 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -27,7 +27,7 @@ #include <linux/delay.h> #include <linux/initrd.h> #include <linux/bitops.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/kexec.h> #include <linux/debugfs.h> #include <linux/irq.h> @@ -54,6 +54,8 @@ #include <asm/pci-bridge.h> #include <asm/phyp_dump.h> #include <asm/kexec.h> +#include <asm/opal.h> + #include <mm/mmu_decl.h> #ifdef DEBUG @@ -69,6 +71,7 @@ unsigned long tce_alloc_start, tce_alloc_end; u64 ppc64_rma_size; #endif static phys_addr_t first_memblock_size; +static int __initdata boot_cpu_count; static int __init early_parse_mem(char *p) { @@ -706,11 +709,23 @@ void __init early_init_devtree(void *params) of_scan_flat_dt(early_init_dt_scan_rtas, NULL); #endif +#ifdef CONFIG_PPC_POWERNV + /* Some machines might need OPAL info for debugging, grab it now. */ + of_scan_flat_dt(early_init_dt_scan_opal, NULL); +#endif + #ifdef CONFIG_PHYP_DUMP /* scan tree to see if dump occurred during last boot */ of_scan_flat_dt(early_init_dt_scan_phyp_dump, NULL); #endif + /* Pre-initialize the cmd_line with the content of boot_commmand_line, + * which will be empty except when the content of the variable has + * been overriden by a bootloading mechanism. This happens typically + * with HAL takeover + */ + strlcpy(cmd_line, boot_command_line, COMMAND_LINE_SIZE); + /* Retrieve various informations from the /chosen node of the * device-tree, including the platform type, initrd location and * size, TCE reserve, and more ... @@ -722,12 +737,15 @@ void __init early_init_devtree(void *params) of_scan_flat_dt(early_init_dt_scan_root, NULL); of_scan_flat_dt(early_init_dt_scan_memory_ppc, NULL); - setup_initial_memory_limit(memstart_addr, first_memblock_size); /* Save command line for /proc/cmdline and then parse parameters */ strlcpy(boot_command_line, cmd_line, COMMAND_LINE_SIZE); parse_early_param(); + /* make sure we've parsed cmdline for mem= before this */ + if (memory_limit) + first_memblock_size = min(first_memblock_size, memory_limit); + setup_initial_memory_limit(memstart_addr, first_memblock_size); /* Reserve MEMBLOCK regions used by kernel, initrd, dt, etc... */ memblock_reserve(PHYSICAL_START, __pa(klimit) - PHYSICAL_START); /* If relocatable, reserve first 32k for interrupt vectors etc. */ @@ -769,6 +787,13 @@ void __init early_init_devtree(void *params) */ of_scan_flat_dt(early_init_dt_scan_cpus, NULL); +#if defined(CONFIG_SMP) && defined(CONFIG_PPC64) + /* We'll later wait for secondaries to check in; there are + * NCPUS-1 non-boot CPUs :-) + */ + spinning_secondaries = boot_cpu_count - 1; +#endif + DBG(" <- early_init_devtree()\n"); } @@ -862,16 +887,14 @@ static int prom_reconfig_notifier(struct notifier_block *nb, switch (action) { case PSERIES_RECONFIG_ADD: err = of_finish_dynamic_node(node); - if (err < 0) { + if (err < 0) printk(KERN_ERR "finish_node returned %d\n", err); - err = NOTIFY_BAD; - } break; default: - err = NOTIFY_DONE; + err = 0; break; } - return err; + return notifier_from_errno(err); } static struct notifier_block prom_reconfig_nb = { diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 3b22142..cc58486 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -43,6 +43,7 @@ #include <asm/btext.h> #include <asm/sections.h> #include <asm/machdep.h> +#include <asm/opal.h> #include <linux/linux_logo.h> @@ -139,7 +140,9 @@ struct mem_map_entry { typedef u32 cell_t; -extern void __start(unsigned long r3, unsigned long r4, unsigned long r5); +extern void __start(unsigned long r3, unsigned long r4, unsigned long r5, + unsigned long r6, unsigned long r7, unsigned long r8, + unsigned long r9); #ifdef CONFIG_PPC64 extern int enter_prom(struct prom_args *args, unsigned long entry); @@ -185,6 +188,7 @@ static unsigned long __initdata prom_tce_alloc_end; #define PLATFORM_LPAR 0x0001 #define PLATFORM_POWERMAC 0x0400 #define PLATFORM_GENERIC 0x0500 +#define PLATFORM_OPAL 0x0600 static int __initdata of_platform; @@ -644,7 +648,7 @@ static void __init early_cmdline_parse(void) } } -#ifdef CONFIG_PPC_PSERIES +#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) /* * There are two methods for telling firmware what our capabilities are. * Newer machines have an "ibm,client-architecture-support" method on the @@ -1274,6 +1278,284 @@ static void __init prom_init_mem(void) prom_printf(" ram_top : %x\n", RELOC(ram_top)); } +static void __init prom_close_stdin(void) +{ + struct prom_t *_prom = &RELOC(prom); + ihandle val; + + if (prom_getprop(_prom->chosen, "stdin", &val, sizeof(val)) > 0) + call_prom("close", 1, 0, val); +} + +#ifdef CONFIG_PPC_POWERNV + +static u64 __initdata prom_opal_size; +static u64 __initdata prom_opal_align; +static int __initdata prom_rtas_start_cpu; +static u64 __initdata prom_rtas_data; +static u64 __initdata prom_rtas_entry; + +#ifdef CONFIG_PPC_EARLY_DEBUG_OPAL +static u64 __initdata prom_opal_base; +static u64 __initdata prom_opal_entry; +#endif + +/* XXX Don't change this structure without updating opal-takeover.S */ +static struct opal_secondary_data { + s64 ack; /* 0 */ + u64 go; /* 8 */ + struct opal_takeover_args args; /* 16 */ +} opal_secondary_data; + +extern char opal_secondary_entry; + +static void prom_query_opal(void) +{ + long rc; + + /* We must not query for OPAL presence on a machine that + * supports TNK takeover (970 blades), as this uses the same + * h-call with different arguments and will crash + */ + if (PHANDLE_VALID(call_prom("finddevice", 1, 1, + ADDR("/tnk-memory-map")))) { + prom_printf("TNK takeover detected, skipping OPAL check\n"); + return; + } + + prom_printf("Querying for OPAL presence... "); + rc = opal_query_takeover(&RELOC(prom_opal_size), + &RELOC(prom_opal_align)); + prom_debug("(rc = %ld) ", rc); + if (rc != 0) { + prom_printf("not there.\n"); + return; + } + RELOC(of_platform) = PLATFORM_OPAL; + prom_printf(" there !\n"); + prom_debug(" opal_size = 0x%lx\n", RELOC(prom_opal_size)); + prom_debug(" opal_align = 0x%lx\n", RELOC(prom_opal_align)); + if (RELOC(prom_opal_align) < 0x10000) + RELOC(prom_opal_align) = 0x10000; +} + +static int prom_rtas_call(int token, int nargs, int nret, int *outputs, ...) +{ + struct rtas_args rtas_args; + va_list list; + int i; + + rtas_args.token = token; + rtas_args.nargs = nargs; + rtas_args.nret = nret; + rtas_args.rets = (rtas_arg_t *)&(rtas_args.args[nargs]); + va_start(list, outputs); + for (i = 0; i < nargs; ++i) + rtas_args.args[i] = va_arg(list, rtas_arg_t); + va_end(list); + + for (i = 0; i < nret; ++i) + rtas_args.rets[i] = 0; + + opal_enter_rtas(&rtas_args, RELOC(prom_rtas_data), + RELOC(prom_rtas_entry)); + + if (nret > 1 && outputs != NULL) + for (i = 0; i < nret-1; ++i) + outputs[i] = rtas_args.rets[i+1]; + return (nret > 0)? rtas_args.rets[0]: 0; +} + +static void __init prom_opal_hold_cpus(void) +{ + int i, cnt, cpu, rc; + long j; + phandle node; + char type[64]; + u32 servers[8]; + struct prom_t *_prom = &RELOC(prom); + void *entry = (unsigned long *)&RELOC(opal_secondary_entry); + struct opal_secondary_data *data = &RELOC(opal_secondary_data); + + prom_debug("prom_opal_hold_cpus: start...\n"); + prom_debug(" - entry = 0x%x\n", entry); + prom_debug(" - data = 0x%x\n", data); + + data->ack = -1; + data->go = 0; + + /* look for cpus */ + for (node = 0; prom_next_node(&node); ) { + type[0] = 0; + prom_getprop(node, "device_type", type, sizeof(type)); + if (strcmp(type, RELOC("cpu")) != 0) + continue; + + /* Skip non-configured cpus. */ + if (prom_getprop(node, "status", type, sizeof(type)) > 0) + if (strcmp(type, RELOC("okay")) != 0) + continue; + + cnt = prom_getprop(node, "ibm,ppc-interrupt-server#s", servers, + sizeof(servers)); + if (cnt == PROM_ERROR) + break; + cnt >>= 2; + for (i = 0; i < cnt; i++) { + cpu = servers[i]; + prom_debug("CPU %d ... ", cpu); + if (cpu == _prom->cpu) { + prom_debug("booted !\n"); + continue; + } + prom_debug("starting ... "); + + /* Init the acknowledge var which will be reset by + * the secondary cpu when it awakens from its OF + * spinloop. + */ + data->ack = -1; + rc = prom_rtas_call(RELOC(prom_rtas_start_cpu), 3, 1, + NULL, cpu, entry, data); + prom_debug("rtas rc=%d ...", rc); + + for (j = 0; j < 100000000 && data->ack == -1; j++) { + HMT_low(); + mb(); + } + HMT_medium(); + if (data->ack != -1) + prom_debug("done, PIR=0x%x\n", data->ack); + else + prom_debug("timeout !\n"); + } + } + prom_debug("prom_opal_hold_cpus: end...\n"); +} + +static void prom_opal_takeover(void) +{ + struct opal_secondary_data *data = &RELOC(opal_secondary_data); + struct opal_takeover_args *args = &data->args; + u64 align = RELOC(prom_opal_align); + u64 top_addr, opal_addr; + + args->k_image = (u64)RELOC(_stext); + args->k_size = _end - _stext; + args->k_entry = 0; + args->k_entry2 = 0x60; + + top_addr = _ALIGN_UP(args->k_size, align); + + if (RELOC(prom_initrd_start) != 0) { + args->rd_image = RELOC(prom_initrd_start); + args->rd_size = RELOC(prom_initrd_end) - args->rd_image; + args->rd_loc = top_addr; + top_addr = _ALIGN_UP(args->rd_loc + args->rd_size, align); + } + + /* Pickup an address for the HAL. We want to go really high + * up to avoid problem with future kexecs. On the other hand + * we don't want to be all over the TCEs on P5IOC2 machines + * which are going to be up there too. We assume the machine + * has plenty of memory, and we ask for the HAL for now to + * be just below the 1G point, or above the initrd + */ + opal_addr = _ALIGN_DOWN(0x40000000 - RELOC(prom_opal_size), align); + if (opal_addr < top_addr) + opal_addr = top_addr; + args->hal_addr = opal_addr; + + /* Copy the command line to the kernel image */ + strlcpy(RELOC(boot_command_line), RELOC(prom_cmd_line), + COMMAND_LINE_SIZE); + + prom_debug(" k_image = 0x%lx\n", args->k_image); + prom_debug(" k_size = 0x%lx\n", args->k_size); + prom_debug(" k_entry = 0x%lx\n", args->k_entry); + prom_debug(" k_entry2 = 0x%lx\n", args->k_entry2); + prom_debug(" hal_addr = 0x%lx\n", args->hal_addr); + prom_debug(" rd_image = 0x%lx\n", args->rd_image); + prom_debug(" rd_size = 0x%lx\n", args->rd_size); + prom_debug(" rd_loc = 0x%lx\n", args->rd_loc); + prom_printf("Performing OPAL takeover,this can take a few minutes..\n"); + prom_close_stdin(); + mb(); + data->go = 1; + for (;;) + opal_do_takeover(args); +} + +/* + * Allocate room for and instantiate OPAL + */ +static void __init prom_instantiate_opal(void) +{ + phandle opal_node; + ihandle opal_inst; + u64 base, entry; + u64 size = 0, align = 0x10000; + u32 rets[2]; + + prom_debug("prom_instantiate_opal: start...\n"); + + opal_node = call_prom("finddevice", 1, 1, ADDR("/ibm,opal")); + prom_debug("opal_node: %x\n", opal_node); + if (!PHANDLE_VALID(opal_node)) + return; + + prom_getprop(opal_node, "opal-runtime-size", &size, sizeof(size)); + if (size == 0) + return; + prom_getprop(opal_node, "opal-runtime-alignment", &align, + sizeof(align)); + + base = alloc_down(size, align, 0); + if (base == 0) { + prom_printf("OPAL allocation failed !\n"); + return; + } + + opal_inst = call_prom("open", 1, 1, ADDR("/ibm,opal")); + if (!IHANDLE_VALID(opal_inst)) { + prom_printf("opening opal package failed (%x)\n", opal_inst); + return; + } + + prom_printf("instantiating opal at 0x%x...", base); + + if (call_prom_ret("call-method", 4, 3, rets, + ADDR("load-opal-runtime"), + opal_inst, + base >> 32, base & 0xffffffff) != 0 + || (rets[0] == 0 && rets[1] == 0)) { + prom_printf(" failed\n"); + return; + } + entry = (((u64)rets[0]) << 32) | rets[1]; + + prom_printf(" done\n"); + + reserve_mem(base, size); + + prom_debug("opal base = 0x%x\n", base); + prom_debug("opal align = 0x%x\n", align); + prom_debug("opal entry = 0x%x\n", entry); + prom_debug("opal size = 0x%x\n", (long)size); + + prom_setprop(opal_node, "/ibm,opal", "opal-base-address", + &base, sizeof(base)); + prom_setprop(opal_node, "/ibm,opal", "opal-entry-address", + &entry, sizeof(entry)); + +#ifdef CONFIG_PPC_EARLY_DEBUG_OPAL + RELOC(prom_opal_base) = base; + RELOC(prom_opal_entry) = entry; +#endif + prom_debug("prom_instantiate_opal: end...\n"); +} + +#endif /* CONFIG_PPC_POWERNV */ /* * Allocate room for and instantiate RTAS @@ -1297,10 +1579,8 @@ static void __init prom_instantiate_rtas(void) return; base = alloc_down(size, PAGE_SIZE, 0); - if (base == 0) { - prom_printf("RTAS allocation failed !\n"); - return; - } + if (base == 0) + prom_panic("Could not allocate memory for RTAS\n"); rtas_inst = call_prom("open", 1, 1, ADDR("/rtas")); if (!IHANDLE_VALID(rtas_inst)) { @@ -1326,6 +1606,12 @@ static void __init prom_instantiate_rtas(void) prom_setprop(rtas_node, "/rtas", "linux,rtas-entry", &entry, sizeof(entry)); +#ifdef CONFIG_PPC_POWERNV + /* PowerVN takeover hack */ + RELOC(prom_rtas_data) = base; + RELOC(prom_rtas_entry) = entry; + prom_getprop(rtas_node, "start-cpu", &RELOC(prom_rtas_start_cpu), 4); +#endif prom_debug("rtas base = 0x%x\n", base); prom_debug("rtas entry = 0x%x\n", entry); prom_debug("rtas size = 0x%x\n", (long)size); @@ -1543,7 +1829,7 @@ static void __init prom_hold_cpus(void) *acknowledge = (unsigned long)-1; if (reg != _prom->cpu) { - /* Primary Thread of non-boot cpu */ + /* Primary Thread of non-boot cpu or any thread */ prom_printf("starting cpu hw idx %lu... ", reg); call_prom("start-cpu", 3, 0, node, secondary_hold, reg); @@ -1652,15 +1938,6 @@ static void __init prom_init_stdout(void) prom_setprop(val, path, "linux,boot-display", NULL, 0); } -static void __init prom_close_stdin(void) -{ - struct prom_t *_prom = &RELOC(prom); - ihandle val; - - if (prom_getprop(_prom->chosen, "stdin", &val, sizeof(val)) > 0) - call_prom("close", 1, 0, val); -} - static int __init prom_find_machine_type(void) { struct prom_t *_prom = &RELOC(prom); @@ -1671,7 +1948,7 @@ static int __init prom_find_machine_type(void) int x; #endif - /* Look for a PowerMac */ + /* Look for a PowerMac or a Cell */ len = prom_getprop(_prom->root, "compatible", compat, sizeof(compat)-1); if (len > 0) { @@ -1697,7 +1974,11 @@ static int __init prom_find_machine_type(void) } } #ifdef CONFIG_PPC64 - /* If not a mac, try to figure out if it's an IBM pSeries or any other + /* Try to detect OPAL */ + if (PHANDLE_VALID(call_prom("finddevice", 1, 1, ADDR("/ibm,opal")))) + return PLATFORM_OPAL; + + /* Try to figure out if it's an IBM pSeries or any other * PAPR compliant platform. We assume it is if : * - /device_type is "chrp" (please, do NOT use that for future * non-IBM designs ! @@ -1830,10 +2111,12 @@ static void __init *make_room(unsigned long *mem_start, unsigned long *mem_end, if (room > DEVTREE_CHUNK_SIZE) room = DEVTREE_CHUNK_SIZE; if (room < PAGE_SIZE) - prom_panic("No memory for flatten_device_tree (no room)"); + prom_panic("No memory for flatten_device_tree " + "(no room)\n"); chunk = alloc_up(room, 0); if (chunk == 0) - prom_panic("No memory for flatten_device_tree (claim failed)"); + prom_panic("No memory for flatten_device_tree " + "(claim failed)\n"); *mem_end = chunk + room; } @@ -1922,7 +2205,7 @@ static void __init scan_dt_build_struct(phandle node, unsigned long *mem_start, unsigned long soff; unsigned char *valp; static char pname[MAX_PROPERTY_NAME]; - int l, room; + int l, room, has_phandle = 0; dt_push_token(OF_DT_BEGIN_NODE, mem_start, mem_end); @@ -2006,19 +2289,26 @@ static void __init scan_dt_build_struct(phandle node, unsigned long *mem_start, valp = make_room(mem_start, mem_end, l, 4); call_prom("getprop", 4, 1, node, RELOC(pname), valp, l); *mem_start = _ALIGN(*mem_start, 4); + + if (!strcmp(RELOC(pname), RELOC("phandle"))) + has_phandle = 1; } - /* Add a "linux,phandle" property. */ - soff = dt_find_string(RELOC("linux,phandle")); - if (soff == 0) - prom_printf("WARNING: Can't find string index for" - " <linux-phandle> node %s\n", path); - else { - dt_push_token(OF_DT_PROP, mem_start, mem_end); - dt_push_token(4, mem_start, mem_end); - dt_push_token(soff, mem_start, mem_end); - valp = make_room(mem_start, mem_end, 4, 4); - *(u32 *)valp = node; + /* Add a "linux,phandle" property if no "phandle" property already + * existed (can happen with OPAL) + */ + if (!has_phandle) { + soff = dt_find_string(RELOC("linux,phandle")); + if (soff == 0) + prom_printf("WARNING: Can't find string index for" + " <linux-phandle> node %s\n", path); + else { + dt_push_token(OF_DT_PROP, mem_start, mem_end); + dt_push_token(4, mem_start, mem_end); + dt_push_token(soff, mem_start, mem_end); + valp = make_room(mem_start, mem_end, 4, 4); + *(u32 *)valp = node; + } } /* do all our children */ @@ -2042,7 +2332,7 @@ static void __init flatten_device_tree(void) /* * Check how much room we have between alloc top & bottom (+/- a - * few pages), crop to 4Mb, as this is our "chuck" size + * few pages), crop to 1MB, as this is our "chunk" size */ room = RELOC(alloc_top) - RELOC(alloc_bottom) - 0x4000; if (room > DEVTREE_CHUNK_SIZE) @@ -2502,6 +2792,7 @@ static void __init prom_check_initrd(unsigned long r3, unsigned long r4) #endif /* CONFIG_BLK_DEV_INITRD */ } + /* * We enter here early on, when the Open Firmware prom is still * handling exceptions and the MMU hash table for us. @@ -2551,6 +2842,7 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4, * between pSeries SMP and pSeries LPAR */ RELOC(of_platform) = prom_find_machine_type(); + prom_printf("Detected machine type: %x\n", RELOC(of_platform)); #ifndef CONFIG_RELOCATABLE /* Bail if this is a kdump kernel. */ @@ -2563,7 +2855,7 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4, */ prom_check_initrd(r3, r4); -#ifdef CONFIG_PPC_PSERIES +#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) /* * On pSeries, inform the firmware about our capabilities */ @@ -2609,14 +2901,33 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4, #endif /* - * On non-powermacs, try to instantiate RTAS and puts all CPUs - * in spin-loops. PowerMacs don't have a working RTAS and use - * a different way to spin CPUs + * On non-powermacs, try to instantiate RTAS. PowerMacs don't + * have a usable RTAS implementation. */ - if (RELOC(of_platform) != PLATFORM_POWERMAC) { + if (RELOC(of_platform) != PLATFORM_POWERMAC && + RELOC(of_platform) != PLATFORM_OPAL) prom_instantiate_rtas(); + +#ifdef CONFIG_PPC_POWERNV + /* Detect HAL and try instanciating it & doing takeover */ + if (RELOC(of_platform) == PLATFORM_PSERIES_LPAR) { + prom_query_opal(); + if (RELOC(of_platform) == PLATFORM_OPAL) { + prom_opal_hold_cpus(); + prom_opal_takeover(); + } + } else if (RELOC(of_platform) == PLATFORM_OPAL) + prom_instantiate_opal(); +#endif + + /* + * On non-powermacs, put all CPUs in spin-loops. + * + * PowerMacs use a different mechanism to spin CPUs + */ + if (RELOC(of_platform) != PLATFORM_POWERMAC && + RELOC(of_platform) != PLATFORM_OPAL) prom_hold_cpus(); - } /* * Fill in some infos for use by the kernel later on @@ -2683,7 +2994,13 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4, reloc_got2(-offset); #endif - __start(hdr, kbase, 0); +#ifdef CONFIG_PPC_EARLY_DEBUG_OPAL + /* OPAL early debug gets the OPAL base & entry in r8 and r9 */ + __start(hdr, kbase, 0, 0, 0, + RELOC(prom_opal_base), RELOC(prom_opal_entry)); +#else + __start(hdr, kbase, 0, 0, 0, 0, 0); +#endif return 0; } diff --git a/arch/powerpc/kernel/prom_init_check.sh b/arch/powerpc/kernel/prom_init_check.sh index 9f82f49..70f4286 100644 --- a/arch/powerpc/kernel/prom_init_check.sh +++ b/arch/powerpc/kernel/prom_init_check.sh @@ -20,7 +20,9 @@ WHITELIST="add_reloc_offset __bss_start __bss_stop copy_and_flush _end enter_prom memcpy memset reloc_offset __secondary_hold __secondary_hold_acknowledge __secondary_hold_spinloop __start strcmp strcpy strlcpy strlen strncmp strstr logo_linux_clut224 -reloc_got2 kernstart_addr memstart_addr linux_banner" +reloc_got2 kernstart_addr memstart_addr linux_banner _stext +opal_query_takeover opal_do_takeover opal_enter_rtas opal_secondary_entry +boot_command_line" NM="$1" OBJ="$2" diff --git a/arch/powerpc/kernel/prom_parse.c b/arch/powerpc/kernel/prom_parse.c index 47187cc..4e1331b 100644 --- a/arch/powerpc/kernel/prom_parse.c +++ b/arch/powerpc/kernel/prom_parse.c @@ -2,7 +2,6 @@ #include <linux/kernel.h> #include <linux/string.h> -#include <linux/module.h> #include <linux/ioport.h> #include <linux/etherdevice.h> #include <linux/of_address.h> diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index 9321d0f..5de73db 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -30,9 +30,6 @@ #include <linux/seccomp.h> #include <linux/audit.h> #include <trace/syscall.h> -#ifdef CONFIG_PPC32 -#include <linux/module.h> -#endif #include <linux/hw_breakpoint.h> #include <linux/perf_event.h> @@ -882,7 +879,7 @@ void user_disable_single_step(struct task_struct *task) } #ifdef CONFIG_HAVE_HW_BREAKPOINT -void ptrace_triggered(struct perf_event *bp, int nmi, +void ptrace_triggered(struct perf_event *bp, struct perf_sample_data *data, struct pt_regs *regs) { struct perf_event_attr attr; @@ -973,7 +970,7 @@ int ptrace_set_debugreg(struct task_struct *task, unsigned long addr, &attr.bp_type); thread->ptrace_bps[0] = bp = register_user_hw_breakpoint(&attr, - ptrace_triggered, task); + ptrace_triggered, NULL, task); if (IS_ERR(bp)) { thread->ptrace_bps[0] = NULL; ptrace_put_breakpoints(task); diff --git a/arch/powerpc/kernel/reloc_64.S b/arch/powerpc/kernel/reloc_64.S index b47a0e1..c712ece 100644 --- a/arch/powerpc/kernel/reloc_64.S +++ b/arch/powerpc/kernel/reloc_64.S @@ -81,6 +81,7 @@ _GLOBAL(relocate) 6: blr +.balign 8 p_dyn: .llong __dynamic_start - 0b p_rela: .llong __rela_dyn_start - 0b p_st: .llong _stext - 0b diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 271ff63..434a180 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -15,15 +15,17 @@ #include <linux/kernel.h> #include <linux/types.h> #include <linux/spinlock.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/init.h> #include <linux/capability.h> #include <linux/delay.h> +#include <linux/cpu.h> #include <linux/smp.h> #include <linux/completion.h> #include <linux/cpumask.h> #include <linux/memblock.h> #include <linux/slab.h> +#include <linux/reboot.h> #include <asm/prom.h> #include <asm/rtas.h> @@ -38,7 +40,7 @@ #include <asm/udbg.h> #include <asm/syscalls.h> #include <asm/smp.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <asm/time.h> #include <asm/mmu.h> #include <asm/topology.h> @@ -715,7 +717,6 @@ static int __rtas_suspend_last_cpu(struct rtas_suspend_me_data *data, int wake_w int cpu; slb_set_size(SLB_MIN_SIZE); - stop_topology_update(); printk(KERN_DEBUG "calling ibm,suspend-me on cpu %i\n", smp_processor_id()); while (rc == H_MULTI_THREADS_ACTIVE && !atomic_read(&data->done) && @@ -731,7 +732,6 @@ static int __rtas_suspend_last_cpu(struct rtas_suspend_me_data *data, int wake_w rc = atomic_read(&data->error); atomic_set(&data->error, rc); - start_topology_update(); pSeries_coalesce_init(); if (wake_when_done) { @@ -810,6 +810,95 @@ static void rtas_percpu_suspend_me(void *info) __rtas_suspend_cpu((struct rtas_suspend_me_data *)info, 1); } +enum rtas_cpu_state { + DOWN, + UP, +}; + +#ifndef CONFIG_SMP +static int rtas_cpu_state_change_mask(enum rtas_cpu_state state, + cpumask_var_t cpus) +{ + if (!cpumask_empty(cpus)) { + cpumask_clear(cpus); + return -EINVAL; + } else + return 0; +} +#else +/* On return cpumask will be altered to indicate CPUs changed. + * CPUs with states changed will be set in the mask, + * CPUs with status unchanged will be unset in the mask. */ +static int rtas_cpu_state_change_mask(enum rtas_cpu_state state, + cpumask_var_t cpus) +{ + int cpu; + int cpuret = 0; + int ret = 0; + + if (cpumask_empty(cpus)) + return 0; + + for_each_cpu(cpu, cpus) { + switch (state) { + case DOWN: + cpuret = cpu_down(cpu); + break; + case UP: + cpuret = cpu_up(cpu); + break; + } + if (cpuret) { + pr_debug("%s: cpu_%s for cpu#%d returned %d.\n", + __func__, + ((state == UP) ? "up" : "down"), + cpu, cpuret); + if (!ret) + ret = cpuret; + if (state == UP) { + /* clear bits for unchanged cpus, return */ + cpumask_shift_right(cpus, cpus, cpu); + cpumask_shift_left(cpus, cpus, cpu); + break; + } else { + /* clear bit for unchanged cpu, continue */ + cpumask_clear_cpu(cpu, cpus); + } + } + } + + return ret; +} +#endif + +int rtas_online_cpus_mask(cpumask_var_t cpus) +{ + int ret; + + ret = rtas_cpu_state_change_mask(UP, cpus); + + if (ret) { + cpumask_var_t tmp_mask; + + if (!alloc_cpumask_var(&tmp_mask, GFP_TEMPORARY)) + return ret; + + /* Use tmp_mask to preserve cpus mask from first failure */ + cpumask_copy(tmp_mask, cpus); + rtas_offline_cpus_mask(tmp_mask); + free_cpumask_var(tmp_mask); + } + + return ret; +} +EXPORT_SYMBOL(rtas_online_cpus_mask); + +int rtas_offline_cpus_mask(cpumask_var_t cpus) +{ + return rtas_cpu_state_change_mask(DOWN, cpus); +} +EXPORT_SYMBOL(rtas_offline_cpus_mask); + int rtas_ibm_suspend_me(struct rtas_args *args) { long state; @@ -817,6 +906,8 @@ int rtas_ibm_suspend_me(struct rtas_args *args) unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; struct rtas_suspend_me_data data; DECLARE_COMPLETION_ONSTACK(done); + cpumask_var_t offline_mask; + int cpuret; if (!rtas_service_present("ibm,suspend-me")) return -ENOSYS; @@ -840,12 +931,26 @@ int rtas_ibm_suspend_me(struct rtas_args *args) return 0; } + if (!alloc_cpumask_var(&offline_mask, GFP_TEMPORARY)) + return -ENOMEM; + atomic_set(&data.working, 0); atomic_set(&data.done, 0); atomic_set(&data.error, 0); data.token = rtas_token("ibm,suspend-me"); data.complete = &done; + /* All present CPUs must be online */ + cpumask_andnot(offline_mask, cpu_present_mask, cpu_online_mask); + cpuret = rtas_online_cpus_mask(offline_mask); + if (cpuret) { + pr_err("%s: Could not bring present CPUs online.\n", __func__); + atomic_set(&data.error, cpuret); + goto out; + } + + stop_topology_update(); + /* Call function on all CPUs. One of us will make the * rtas call */ @@ -857,6 +962,16 @@ int rtas_ibm_suspend_me(struct rtas_args *args) if (atomic_read(&data.error) != 0) printk(KERN_ERR "Error doing global join\n"); + start_topology_update(); + + /* Take down CPUs not online prior to suspend */ + cpuret = rtas_offline_cpus_mask(offline_mask); + if (cpuret) + pr_warn("%s: Could not restore CPUs to offline state.\n", + __func__); + +out: + free_cpumask_var(offline_mask); return atomic_read(&data.error); } #else /* CONFIG_PPC_PSERIES */ diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c index bf5f5ce..e037c74 100644 --- a/arch/powerpc/kernel/rtas_flash.c +++ b/arch/powerpc/kernel/rtas_flash.c @@ -17,6 +17,7 @@ #include <linux/init.h> #include <linux/slab.h> #include <linux/proc_fs.h> +#include <linux/reboot.h> #include <asm/delay.h> #include <asm/uaccess.h> #include <asm/rtas.h> diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c index 54e66da..6cd8f01 100644 --- a/arch/powerpc/kernel/rtas_pci.c +++ b/arch/powerpc/kernel/rtas_pci.c @@ -291,7 +291,7 @@ void __init find_and_init_phbs(void) prop = of_get_property(of_chosen, "linux,pci-assign-all-buses", NULL); if (prop && *prop) - ppc_pci_flags |= PPC_PCI_REASSIGN_ALL_BUS; + pci_add_flags(PCI_REASSIGN_ALL_BUS); #endif /* CONFIG_PPC32 */ } } diff --git a/arch/powerpc/kernel/rtasd.c b/arch/powerpc/kernel/rtasd.c index 67f6c3b..481ef06 100644 --- a/arch/powerpc/kernel/rtasd.c +++ b/arch/powerpc/kernel/rtasd.c @@ -27,7 +27,7 @@ #include <asm/rtas.h> #include <asm/prom.h> #include <asm/nvram.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <asm/machdep.h> diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 79fca26..83940d7 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -12,7 +12,7 @@ #undef DEBUG -#include <linux/module.h> +#include <linux/export.h> #include <linux/string.h> #include <linux/sched.h> #include <linux/init.h> @@ -375,6 +375,9 @@ void __init check_for_initrd(void) int threads_per_core, threads_shift; cpumask_t threads_core_mask; +EXPORT_SYMBOL_GPL(threads_per_core); +EXPORT_SYMBOL_GPL(threads_shift); +EXPORT_SYMBOL_GPL(threads_core_mask); static void __init cpu_init_thread_core_maps(int tpc) { @@ -425,7 +428,7 @@ void __init smp_setup_cpu_maps(void) DBG("smp_setup_cpu_maps()\n"); while ((dn = of_find_node_by_type(dn, "cpu")) && cpu < nr_cpu_ids) { - const int *intserv; + const __be32 *intserv; int j, len; DBG(" * %s...\n", dn->full_name); @@ -444,10 +447,18 @@ void __init smp_setup_cpu_maps(void) } for (j = 0; j < nthreads && cpu < nr_cpu_ids; j++) { + bool avail; + DBG(" thread %d -> cpu %d (hard id %d)\n", - j, cpu, intserv[j]); - set_cpu_present(cpu, true); - set_hard_smp_processor_id(cpu, intserv[j]); + j, cpu, be32_to_cpu(intserv[j])); + + avail = of_device_is_available(dn); + if (!avail) + avail = !of_property_match_string(dn, + "enable-method", "spin-table"); + + set_cpu_present(cpu, avail); + set_hard_smp_processor_id(cpu, be32_to_cpu(intserv[j])); set_cpu_possible(cpu, true); cpu++; } @@ -704,29 +715,14 @@ static int powerpc_debugfs_init(void) arch_initcall(powerpc_debugfs_init); #endif -static int ppc_dflt_bus_notify(struct notifier_block *nb, - unsigned long action, void *data) +void ppc_printk_progress(char *s, unsigned short hex) { - struct device *dev = data; - - /* We are only intereted in device addition */ - if (action != BUS_NOTIFY_ADD_DEVICE) - return 0; - - set_dma_ops(dev, &dma_direct_ops); - - return NOTIFY_DONE; + pr_info("%s\n", s); } -static struct notifier_block ppc_dflt_plat_bus_notifier = { - .notifier_call = ppc_dflt_bus_notify, - .priority = INT_MAX, -}; - -static int __init setup_bus_notifier(void) +void arch_setup_pdev_archdata(struct platform_device *pdev) { - bus_register_notifier(&platform_bus_type, &ppc_dflt_plat_bus_notifier); - return 0; + pdev->archdata.dma_mask = DMA_BIT_MASK(32); + pdev->dev.dma_mask = &pdev->archdata.dma_mask; + set_dma_ops(&pdev->dev, &dma_direct_ops); } - -arch_initcall(setup_bus_notifier); diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index c7e7b8c..ac76108 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -48,8 +48,8 @@ extern void bootx_init(unsigned long r4, unsigned long phys); int boot_cpuid = -1; EXPORT_SYMBOL_GPL(boot_cpuid); -int __initdata boot_cpu_count; int boot_cpuid_phys; +EXPORT_SYMBOL_GPL(boot_cpuid_phys); int smp_hw_index[NR_CPUS]; @@ -119,7 +119,7 @@ notrace unsigned long __init early_init(unsigned long dt_ptr) * This is called very early on the boot process, after a minimal * MMU environment has been set up but before MMU_init is called. */ -notrace void __init machine_init(unsigned long dt_ptr) +notrace void __init machine_init(u64 dt_ptr) { lockdep_init(); @@ -129,6 +129,8 @@ notrace void __init machine_init(unsigned long dt_ptr) /* Do some early initialization based on the flat device tree */ early_init_devtree(__va(dt_ptr)); + early_init_mmu(); + probe_machine(); setup_kdump_trampoline(); diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 7867fd1..2c8890a 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -12,7 +12,7 @@ #undef DEBUG -#include <linux/module.h> +#include <linux/export.h> #include <linux/string.h> #include <linux/sched.h> #include <linux/init.h> @@ -63,6 +63,7 @@ #include <asm/kexec.h> #include <asm/mmu_context.h> #include <asm/code-patching.h> +#include <asm/kvm_ppc.h> #include "setup.h" @@ -73,7 +74,7 @@ #endif int boot_cpuid = 0; -int __initdata boot_cpu_count; +int spinning_secondaries; u64 ppc64_pft_size; /* Pick defaults since we might want to patch instructions @@ -253,11 +254,11 @@ void smp_release_cpus(void) for (i = 0; i < 100000; i++) { mb(); HMT_low(); - if (boot_cpu_count == 0) + if (spinning_secondaries == 0) break; udelay(1); } - DBG("boot_cpu_count = %d\n", boot_cpu_count); + DBG("spinning_secondaries = %d\n", spinning_secondaries); DBG(" <- smp_release_cpus()\n"); } @@ -277,14 +278,14 @@ static void __init initialize_cache_info(void) DBG(" -> initialize_cache_info()\n"); - for (np = NULL; (np = of_find_node_by_type(np, "cpu"));) { + for_each_node_by_type(np, "cpu") { num_cpus += 1; - /* We're assuming *all* of the CPUs have the same + /* + * We're assuming *all* of the CPUs have the same * d-cache and i-cache sizes... -Peter */ - - if ( num_cpus == 1 ) { + if (num_cpus == 1) { const u32 *sizep, *lsizep; u32 size, lsize; @@ -293,10 +294,13 @@ static void __init initialize_cache_info(void) sizep = of_get_property(np, "d-cache-size", NULL); if (sizep != NULL) size = *sizep; - lsizep = of_get_property(np, "d-cache-block-size", NULL); + lsizep = of_get_property(np, "d-cache-block-size", + NULL); /* fallback if block size missing */ if (lsizep == NULL) - lsizep = of_get_property(np, "d-cache-line-size", NULL); + lsizep = of_get_property(np, + "d-cache-line-size", + NULL); if (lsizep != NULL) lsize = *lsizep; if (sizep == 0 || lsizep == 0) @@ -313,9 +317,12 @@ static void __init initialize_cache_info(void) sizep = of_get_property(np, "i-cache-size", NULL); if (sizep != NULL) size = *sizep; - lsizep = of_get_property(np, "i-cache-block-size", NULL); + lsizep = of_get_property(np, "i-cache-block-size", + NULL); if (lsizep == NULL) - lsizep = of_get_property(np, "i-cache-line-size", NULL); + lsizep = of_get_property(np, + "i-cache-line-size", + NULL); if (lsizep != NULL) lsize = *lsizep; if (sizep == 0 || lsizep == 0) @@ -581,6 +588,8 @@ void __init setup_arch(char **cmdline_p) /* Initialize the MMU context management stuff */ mmu_context_init(); + kvm_rma_init(); + ppc64_boot_msg(0x15, "Setup Done"); } diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 78b76dc..fa1e56b 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -97,7 +97,7 @@ static inline int put_sigset_t(compat_sigset_t __user *uset, sigset_t *set) compat_sigset_t cset; switch (_NSIG_WORDS) { - case 4: cset.sig[5] = set->sig[3] & 0xffffffffull; + case 4: cset.sig[6] = set->sig[3] & 0xffffffffull; cset.sig[7] = set->sig[3] >> 32; case 3: cset.sig[4] = set->sig[2] & 0xffffffffull; cset.sig[5] = set->sig[2] >> 32; @@ -445,6 +445,12 @@ static int save_user_regs(struct pt_regs *regs, struct mcontext __user *frame, #endif /* CONFIG_ALTIVEC */ if (copy_fpr_to_user(&frame->mc_fregs, current)) return 1; + + /* + * Clear the MSR VSX bit to indicate there is no valid state attached + * to this context, except in the specific case below where we set it. + */ + msr &= ~MSR_VSX; #ifdef CONFIG_VSX /* * Copy VSR 0-31 upper half from thread_struct to local diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index e91c736..60d1f75 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -23,7 +23,6 @@ #include <linux/stddef.h> #include <linux/elf.h> #include <linux/ptrace.h> -#include <linux/module.h> #include <linux/ratelimit.h> #include <asm/sigcontext.h> @@ -117,6 +116,12 @@ static long setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs, flush_fp_to_thread(current); /* copy fpr regs and fpscr */ err |= copy_fpr_to_user(&sc->fp_regs, current); + + /* + * Clear the MSR VSX bit to indicate there is no valid state attached + * to this context, except in the specific case below where we set it. + */ + msr &= ~MSR_VSX; #ifdef CONFIG_VSX /* * Copy VSX low doubleword to local buffer for formatting, diff --git a/arch/powerpc/kernel/smp-tbsync.c b/arch/powerpc/kernel/smp-tbsync.c index 03e45c4..640de83 100644 --- a/arch/powerpc/kernel/smp-tbsync.c +++ b/arch/powerpc/kernel/smp-tbsync.c @@ -11,7 +11,7 @@ #include <linux/unistd.h> #include <linux/init.h> #include <linux/slab.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <asm/smp.h> #include <asm/time.h> diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 8ebc670..fe04b4a 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -18,7 +18,7 @@ #undef DEBUG #include <linux/kernel.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/sched.h> #include <linux/smp.h> #include <linux/interrupt.h> @@ -33,7 +33,7 @@ #include <linux/topology.h> #include <asm/ptrace.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <asm/irq.h> #include <asm/page.h> #include <asm/pgtable.h> @@ -70,6 +70,10 @@ static DEFINE_PER_CPU(struct task_struct *, idle_thread_array); #define get_idle_for_cpu(x) (per_cpu(idle_thread_array, x)) #define set_idle_for_cpu(x, p) (per_cpu(idle_thread_array, x) = (p)) + +/* State of each CPU during hotplug phases */ +static DEFINE_PER_CPU(int, cpu_state) = { 0 }; + #else static struct task_struct *idle_thread_array[NR_CPUS] __cpuinitdata ; #define get_idle_for_cpu(x) (idle_thread_array[(x)]) @@ -104,12 +108,25 @@ int __devinit smp_generic_kick_cpu(int nr) * cpu_start field to become non-zero After we set cpu_start, * the processor will continue on to secondary_start */ - paca[nr].cpu_start = 1; - smp_mb(); + if (!paca[nr].cpu_start) { + paca[nr].cpu_start = 1; + smp_mb(); + return 0; + } + +#ifdef CONFIG_HOTPLUG_CPU + /* + * Ok it's not there, so it might be soft-unplugged, let's + * try to bring it back + */ + per_cpu(cpu_state, nr) = CPU_UP_PREPARE; + smp_wmb(); + smp_send_reschedule(nr); +#endif /* CONFIG_HOTPLUG_CPU */ return 0; } -#endif +#endif /* CONFIG_PPC64 */ static irqreturn_t call_function_action(int irq, void *data) { @@ -170,7 +187,7 @@ int smp_request_message_ipi(int virq, int msg) return 1; } #endif - err = request_irq(virq, smp_ipi_action[msg], IRQF_DISABLED|IRQF_PERCPU, + err = request_irq(virq, smp_ipi_action[msg], IRQF_PERCPU, smp_ipi_name[msg], 0); WARN(err < 0, "unable to request_irq %d for %s (rc %d)\n", virq, smp_ipi_name[msg], err); @@ -197,19 +214,18 @@ void smp_muxed_ipi_message_pass(int cpu, int msg) struct cpu_messages *info = &per_cpu(ipi_message, cpu); char *message = (char *)&info->messages; + /* + * Order previous accesses before accesses in the IPI handler. + */ + smp_mb(); message[msg] = 1; - mb(); + /* + * cause_ipi functions are required to include a full barrier + * before doing whatever causes the IPI. + */ smp_ops->cause_ipi(cpu, info->data); } -void smp_muxed_ipi_resend(void) -{ - struct cpu_messages *info = &__get_cpu_var(ipi_message); - - if (info->messages) - smp_ops->cause_ipi(smp_processor_id(), info->data); -} - irqreturn_t smp_ipi_demux(void) { struct cpu_messages *info = &__get_cpu_var(ipi_message); @@ -218,7 +234,7 @@ irqreturn_t smp_ipi_demux(void) mb(); /* order any irq clear */ do { - all = xchg_local(&info->messages, 0); + all = xchg(&info->messages, 0); #ifdef __BIG_ENDIAN if (all & (1 << (24 - 8 * PPC_MSG_CALL_FUNCTION))) @@ -238,15 +254,26 @@ irqreturn_t smp_ipi_demux(void) } #endif /* CONFIG_PPC_SMP_MUXED_IPI */ +static inline void do_message_pass(int cpu, int msg) +{ + if (smp_ops->message_pass) + smp_ops->message_pass(cpu, msg); +#ifdef CONFIG_PPC_SMP_MUXED_IPI + else + smp_muxed_ipi_message_pass(cpu, msg); +#endif +} + void smp_send_reschedule(int cpu) { if (likely(smp_ops)) - smp_ops->message_pass(cpu, PPC_MSG_RESCHEDULE); + do_message_pass(cpu, PPC_MSG_RESCHEDULE); } +EXPORT_SYMBOL_GPL(smp_send_reschedule); void arch_send_call_function_single_ipi(int cpu) { - smp_ops->message_pass(cpu, PPC_MSG_CALL_FUNC_SINGLE); + do_message_pass(cpu, PPC_MSG_CALL_FUNC_SINGLE); } void arch_send_call_function_ipi_mask(const struct cpumask *mask) @@ -254,7 +281,7 @@ void arch_send_call_function_ipi_mask(const struct cpumask *mask) unsigned int cpu; for_each_cpu(cpu, mask) - smp_ops->message_pass(cpu, PPC_MSG_CALL_FUNCTION); + do_message_pass(cpu, PPC_MSG_CALL_FUNCTION); } #if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC) @@ -268,7 +295,7 @@ void smp_send_debugger_break(void) for_each_online_cpu(cpu) if (cpu != me) - smp_ops->message_pass(cpu, PPC_MSG_DEBUGGER_BREAK); + do_message_pass(cpu, PPC_MSG_DEBUGGER_BREAK); } #endif @@ -303,6 +330,10 @@ struct thread_info *current_set[NR_CPUS]; static void __devinit smp_store_cpu_info(int id) { per_cpu(cpu_pvr, id) = mfspr(SPRN_PVR); +#ifdef CONFIG_PPC_FSL_BOOK3E + per_cpu(next_tlbcam_idx, id) + = (mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY) - 1; +#endif } void __init smp_prepare_cpus(unsigned int max_cpus) @@ -350,8 +381,6 @@ void __devinit smp_prepare_boot_cpu(void) } #ifdef CONFIG_HOTPLUG_CPU -/* State of each CPU during hotplug phases */ -static DEFINE_PER_CPU(int, cpu_state) = { 0 }; int generic_cpu_disable(void) { @@ -399,6 +428,11 @@ void generic_set_cpu_dead(unsigned int cpu) { per_cpu(cpu_state, cpu) = CPU_DEAD; } + +int generic_check_cpu_restart(unsigned int cpu) +{ + return per_cpu(cpu_state, cpu) == CPU_UP_PREPARE; +} #endif struct create_idle { diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c index b0dbb1d..3d30ef1 100644 --- a/arch/powerpc/kernel/stacktrace.c +++ b/arch/powerpc/kernel/stacktrace.c @@ -10,7 +10,7 @@ * 2 of the License, or (at your option) any later version. */ -#include <linux/module.h> +#include <linux/export.h> #include <linux/sched.h> #include <linux/stacktrace.h> #include <asm/ptrace.h> diff --git a/arch/powerpc/kernel/swsusp.c b/arch/powerpc/kernel/swsusp.c index aa17b76..641f9ad 100644 --- a/arch/powerpc/kernel/swsusp.c +++ b/arch/powerpc/kernel/swsusp.c @@ -33,6 +33,6 @@ void save_processor_state(void) void restore_processor_state(void) { #ifdef CONFIG_PPC32 - switch_mmu_context(NULL, current->active_mm); + switch_mmu_context(current->active_mm, current->active_mm); #endif } diff --git a/arch/powerpc/kernel/swsusp_64.c b/arch/powerpc/kernel/swsusp_64.c index 6f3f069..168e884 100644 --- a/arch/powerpc/kernel/swsusp_64.c +++ b/arch/powerpc/kernel/swsusp_64.c @@ -9,6 +9,7 @@ #include <asm/system.h> #include <asm/iommu.h> #include <linux/irq.h> +#include <linux/sched.h> #include <linux/interrupt.h> void do_after_copyback(void) diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index cd51a5c..ca683a1 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -4,7 +4,7 @@ #include <linux/percpu.h> #include <linux/init.h> #include <linux/sched.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/nodemask.h> #include <linux/cpumask.h> #include <linux/notifier.h> @@ -18,6 +18,7 @@ #include <asm/machdep.h> #include <asm/smp.h> #include <asm/pmc.h> +#include <asm/firmware.h> #include "cacheinfo.h" @@ -178,14 +179,24 @@ SYSFS_PMCSETUP(purr, SPRN_PURR); SYSFS_PMCSETUP(spurr, SPRN_SPURR); SYSFS_PMCSETUP(dscr, SPRN_DSCR); +/* + Lets only enable read for phyp resources and + enable write when needed with a separate function. + Lets be conservative and default to pseries. +*/ static SYSDEV_ATTR(mmcra, 0600, show_mmcra, store_mmcra); static SYSDEV_ATTR(spurr, 0600, show_spurr, NULL); static SYSDEV_ATTR(dscr, 0600, show_dscr, store_dscr); -static SYSDEV_ATTR(purr, 0600, show_purr, store_purr); +static SYSDEV_ATTR(purr, 0400, show_purr, store_purr); unsigned long dscr_default = 0; EXPORT_SYMBOL(dscr_default); +static void add_write_permission_dev_attr(struct sysdev_attribute *attr) +{ + attr->attr.mode |= 0200; +} + static ssize_t show_dscr_default(struct sysdev_class *class, struct sysdev_class_attribute *attr, char *buf) { @@ -394,8 +405,11 @@ static void __cpuinit register_cpu_online(unsigned int cpu) if (cpu_has_feature(CPU_FTR_MMCRA)) sysdev_create_file(s, &attr_mmcra); - if (cpu_has_feature(CPU_FTR_PURR)) + if (cpu_has_feature(CPU_FTR_PURR)) { + if (!firmware_has_feature(FW_FEATURE_LPAR)) + add_write_permission_dev_attr(&attr_purr); sysdev_create_file(s, &attr_purr); + } if (cpu_has_feature(CPU_FTR_SPURR)) sysdev_create_file(s, &attr_spurr); diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 818d809..304680a 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -33,7 +33,7 @@ */ #include <linux/errno.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/sched.h> #include <linux/kernel.h> #include <linux/param.h> @@ -235,8 +235,6 @@ static u64 scan_dispatch_log(u64 stop_tb) if (i == vpa->dtl_idx) return 0; while (i < vpa->dtl_idx) { - if (dtl_consumer) - dtl_consumer(dtl, i); dtb = dtl->timebase; tb_delta = dtl->enqueue_to_dispatch_time + dtl->ready_to_enqueue_time; @@ -249,6 +247,8 @@ static u64 scan_dispatch_log(u64 stop_tb) } if (dtb > stop_tb) break; + if (dtl_consumer) + dtl_consumer(dtl, i); stolen += tb_delta; ++i; ++dtl; diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 6889f26..9844662 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -457,7 +457,14 @@ int machine_check_e500mc(struct pt_regs *regs) if (reason & MCSR_DCPERR_MC) { printk("Data Cache Parity Error\n"); - recoverable = 0; + + /* + * In write shadow mode we auto-recover from the error, but it + * may still get logged and cause a machine check. We should + * only treat the non-write shadow case as non-recoverable. + */ + if (!(mfspr(SPRN_L1CSR2) & L1CSR2_DCWS)) + recoverable = 0; } if (reason & MCSR_L2MMU_MHIT) { @@ -1029,6 +1036,16 @@ void __kprobes program_check_exception(struct pt_regs *regs) _exception(SIGILL, regs, ILL_ILLOPC, regs->nip); } +/* + * This occurs when running in hypervisor mode on POWER6 or later + * and an illegal instruction is encountered. + */ +void __kprobes emulation_assist_interrupt(struct pt_regs *regs) +{ + regs->msr |= REASON_ILLEGAL; + program_check_exception(regs); +} + void alignment_exception(struct pt_regs *regs) { int sig, code, fixed = 0; @@ -1292,14 +1309,12 @@ void __kprobes DebugException(struct pt_regs *regs, unsigned long debug_status) if (user_mode(regs)) { current->thread.dbcr0 &= ~DBCR0_IC; -#ifdef CONFIG_PPC_ADV_DEBUG_REGS if (DBCR_ACTIVE_EVENTS(current->thread.dbcr0, current->thread.dbcr1)) regs->msr |= MSR_DE; else /* Make sure the IDM bit is off */ current->thread.dbcr0 &= ~DBCR0_IDM; -#endif } _exception(SIGTRAP, regs, TRAP_TRACE, regs->nip); @@ -1388,10 +1403,7 @@ void SPEFloatingPointException(struct pt_regs *regs) int code = 0; int err; - preempt_disable(); - if (regs->msr & MSR_SPE) - giveup_spe(current); - preempt_enable(); + flush_spe_to_thread(current); spefscr = current->thread.spefscr; fpexc_mode = current->thread.fpexc_mode; diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c index 23d65ab..57fa2c0 100644 --- a/arch/powerpc/kernel/udbg.c +++ b/arch/powerpc/kernel/udbg.c @@ -31,6 +31,9 @@ void __init udbg_early_init(void) #if defined(CONFIG_PPC_EARLY_DEBUG_LPAR) /* For LPAR machines that have an HVC console on vterm 0 */ udbg_init_debug_lpar(); +#elif defined(CONFIG_PPC_EARLY_DEBUG_LPAR_HVSI) + /* For LPAR machines that have an HVSI console on vterm 0 */ + udbg_init_debug_lpar_hvsi(); #elif defined(CONFIG_PPC_EARLY_DEBUG_G5) /* For use on Apple G5 machines */ udbg_init_pmac_realmode(); @@ -64,10 +67,20 @@ void __init udbg_early_init(void) udbg_init_usbgecko(); #elif defined(CONFIG_PPC_EARLY_DEBUG_WSP) udbg_init_wsp(); +#elif defined(CONFIG_PPC_EARLY_DEBUG_EHV_BC) + udbg_init_ehv_bc(); +#elif defined(CONFIG_PPC_EARLY_DEBUG_PS3GELIC) + udbg_init_ps3gelic(); +#elif defined(CONFIG_PPC_EARLY_DEBUG_OPAL_RAW) + udbg_init_debug_opal_raw(); +#elif defined(CONFIG_PPC_EARLY_DEBUG_OPAL_HVSI) + udbg_init_debug_opal_hvsi(); #endif #ifdef CONFIG_PPC_EARLY_DEBUG console_loglevel = 10; + + register_early_udbg_console(); #endif } diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index 142ab10..7d14bb6 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -9,7 +9,6 @@ * 2 of the License, or (at your option) any later version. */ -#include <linux/module.h> #include <linux/errno.h> #include <linux/sched.h> #include <linux/kernel.h> diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c index c9f2ac8..dfb1c19 100644 --- a/arch/powerpc/kernel/vio.c +++ b/arch/powerpc/kernel/vio.c @@ -15,11 +15,12 @@ */ #include <linux/types.h> +#include <linux/stat.h> #include <linux/device.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/console.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/mm.h> #include <linux/dma-mapping.h> #include <linux/kobject.h> @@ -605,15 +606,20 @@ static int vio_dma_iommu_dma_supported(struct device *dev, u64 mask) return dma_iommu_ops.dma_supported(dev, mask); } -struct dma_map_ops vio_dma_mapping_ops = { - .alloc_coherent = vio_dma_iommu_alloc_coherent, - .free_coherent = vio_dma_iommu_free_coherent, - .map_sg = vio_dma_iommu_map_sg, - .unmap_sg = vio_dma_iommu_unmap_sg, - .map_page = vio_dma_iommu_map_page, - .unmap_page = vio_dma_iommu_unmap_page, - .dma_supported = vio_dma_iommu_dma_supported, +static u64 vio_dma_get_required_mask(struct device *dev) +{ + return dma_iommu_ops.get_required_mask(dev); +} +struct dma_map_ops vio_dma_mapping_ops = { + .alloc_coherent = vio_dma_iommu_alloc_coherent, + .free_coherent = vio_dma_iommu_free_coherent, + .map_sg = vio_dma_iommu_map_sg, + .unmap_sg = vio_dma_iommu_unmap_sg, + .map_page = vio_dma_iommu_map_page, + .unmap_page = vio_dma_iommu_unmap_page, + .dma_supported = vio_dma_iommu_dma_supported, + .get_required_mask = vio_dma_get_required_mask, }; /** @@ -1346,12 +1352,12 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, dn = dev->of_node; if (!dn) { - strcat(buf, "\n"); + strcpy(buf, "\n"); return strlen(buf); } cp = of_get_property(dn, "compatible", NULL); if (!cp) { - strcat(buf, "\n"); + strcpy(buf, "\n"); return strlen(buf); } diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 3e8fe4b..cec664a 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -212,6 +212,7 @@ SECTIONS *(.opd) } + . = ALIGN(256); .got : AT(ADDR(.got) - LOAD_OFFSET) { __toc_start = .; *(.got) |