--- zzzz-none-000/linux-3.10.107/arch/powerpc/kernel/process.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/arch/powerpc/kernel/process.c 2021-02-04 17:41:59.000000000 +0000 @@ -25,7 +25,6 @@ #include #include #include -#include #include #include #include @@ -38,9 +37,9 @@ #include #include #include +#include #include -#include #include #include #include @@ -55,6 +54,7 @@ #ifdef CONFIG_PPC64 #include #endif +#include #include #include @@ -74,6 +74,49 @@ struct task_struct *last_task_used_spe = NULL; #endif +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM +void giveup_fpu_maybe_transactional(struct task_struct *tsk) +{ + /* + * If we are saving the current thread's registers, and the + * thread is in a transactional state, set the TIF_RESTORE_TM + * bit so that we know to restore the registers before + * returning to userspace. + */ + if (tsk == current && tsk->thread.regs && + MSR_TM_ACTIVE(tsk->thread.regs->msr) && + !test_thread_flag(TIF_RESTORE_TM)) { + tsk->thread.ckpt_regs.msr = tsk->thread.regs->msr; + set_thread_flag(TIF_RESTORE_TM); + } + + giveup_fpu(tsk); +} + +void giveup_altivec_maybe_transactional(struct task_struct *tsk) +{ + /* + * If we are saving the current thread's registers, and the + * thread is in a transactional state, set the TIF_RESTORE_TM + * bit so that we know to restore the registers before + * returning to userspace. + */ + if (tsk == current && tsk->thread.regs && + MSR_TM_ACTIVE(tsk->thread.regs->msr) && + !test_thread_flag(TIF_RESTORE_TM)) { + tsk->thread.ckpt_regs.msr = tsk->thread.regs->msr; + set_thread_flag(TIF_RESTORE_TM); + } + + giveup_altivec(tsk); +} + +#else +#define giveup_fpu_maybe_transactional(tsk) giveup_fpu(tsk) +#define giveup_altivec_maybe_transactional(tsk) giveup_altivec(tsk) +#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ + +#ifdef CONFIG_PPC_FPU /* * Make sure the floating-point register state in the * the thread_struct is up to date for task tsk. @@ -101,12 +144,13 @@ */ BUG_ON(tsk != current); #endif - giveup_fpu(tsk); + giveup_fpu_maybe_transactional(tsk); } preempt_enable(); } } EXPORT_SYMBOL_GPL(flush_fp_to_thread); +#endif /* CONFIG_PPC_FPU */ void enable_kernel_fp(void) { @@ -114,11 +158,11 @@ #ifdef CONFIG_SMP if (current->thread.regs && (current->thread.regs->msr & MSR_FP)) - giveup_fpu(current); + giveup_fpu_maybe_transactional(current); else giveup_fpu(NULL); /* just enables FP for kernel */ #else - giveup_fpu(last_task_used_math); + giveup_fpu_maybe_transactional(last_task_used_math); #endif /* CONFIG_SMP */ } EXPORT_SYMBOL(enable_kernel_fp); @@ -130,11 +174,11 @@ #ifdef CONFIG_SMP if (current->thread.regs && (current->thread.regs->msr & MSR_VEC)) - giveup_altivec(current); + giveup_altivec_maybe_transactional(current); else giveup_altivec_notask(); #else - giveup_altivec(last_task_used_altivec); + giveup_altivec_maybe_transactional(last_task_used_altivec); #endif /* CONFIG_SMP */ } EXPORT_SYMBOL(enable_kernel_altivec); @@ -151,7 +195,7 @@ #ifdef CONFIG_SMP BUG_ON(tsk != current); #endif - giveup_altivec(tsk); + giveup_altivec_maybe_transactional(tsk); } preempt_enable(); } @@ -160,8 +204,6 @@ #endif /* CONFIG_ALTIVEC */ #ifdef CONFIG_VSX -#if 0 -/* not currently used, but some crazy RAID module might want to later */ void enable_kernel_vsx(void) { WARN_ON(preemptible()); @@ -176,14 +218,14 @@ #endif /* CONFIG_SMP */ } EXPORT_SYMBOL(enable_kernel_vsx); -#endif void giveup_vsx(struct task_struct *tsk) { - giveup_fpu(tsk); - giveup_altivec(tsk); + giveup_fpu_maybe_transactional(tsk); + giveup_altivec_maybe_transactional(tsk); __giveup_vsx(tsk); } +EXPORT_SYMBOL(giveup_vsx); void flush_vsx_to_thread(struct task_struct *tsk) { @@ -312,32 +354,32 @@ */ static void set_debug_reg_defaults(struct thread_struct *thread) { - thread->iac1 = thread->iac2 = 0; + thread->debug.iac1 = thread->debug.iac2 = 0; #if CONFIG_PPC_ADV_DEBUG_IACS > 2 - thread->iac3 = thread->iac4 = 0; + thread->debug.iac3 = thread->debug.iac4 = 0; #endif - thread->dac1 = thread->dac2 = 0; + thread->debug.dac1 = thread->debug.dac2 = 0; #if CONFIG_PPC_ADV_DEBUG_DVCS > 0 - thread->dvc1 = thread->dvc2 = 0; + thread->debug.dvc1 = thread->debug.dvc2 = 0; #endif - thread->dbcr0 = 0; + thread->debug.dbcr0 = 0; #ifdef CONFIG_BOOKE /* * Force User/Supervisor bits to b11 (user-only MSR[PR]=1) */ - thread->dbcr1 = DBCR1_IAC1US | DBCR1_IAC2US | \ + thread->debug.dbcr1 = DBCR1_IAC1US | DBCR1_IAC2US | DBCR1_IAC3US | DBCR1_IAC4US; /* * Force Data Address Compare User/Supervisor bits to be User-only * (0b11 MSR[PR]=1) and set all other bits in DBCR2 register to be 0. */ - thread->dbcr2 = DBCR2_DAC1US | DBCR2_DAC2US; + thread->debug.dbcr2 = DBCR2_DAC1US | DBCR2_DAC2US; #else - thread->dbcr1 = 0; + thread->debug.dbcr1 = 0; #endif } -static void prime_debug_regs(struct thread_struct *thread) +static void prime_debug_regs(struct debug_reg *debug) { /* * We could have inherited MSR_DE from userspace, since @@ -346,22 +388,22 @@ */ mtmsr(mfmsr() & ~MSR_DE); - mtspr(SPRN_IAC1, thread->iac1); - mtspr(SPRN_IAC2, thread->iac2); + mtspr(SPRN_IAC1, debug->iac1); + mtspr(SPRN_IAC2, debug->iac2); #if CONFIG_PPC_ADV_DEBUG_IACS > 2 - mtspr(SPRN_IAC3, thread->iac3); - mtspr(SPRN_IAC4, thread->iac4); + mtspr(SPRN_IAC3, debug->iac3); + mtspr(SPRN_IAC4, debug->iac4); #endif - mtspr(SPRN_DAC1, thread->dac1); - mtspr(SPRN_DAC2, thread->dac2); + mtspr(SPRN_DAC1, debug->dac1); + mtspr(SPRN_DAC2, debug->dac2); #if CONFIG_PPC_ADV_DEBUG_DVCS > 0 - mtspr(SPRN_DVC1, thread->dvc1); - mtspr(SPRN_DVC2, thread->dvc2); + mtspr(SPRN_DVC1, debug->dvc1); + mtspr(SPRN_DVC2, debug->dvc2); #endif - mtspr(SPRN_DBCR0, thread->dbcr0); - mtspr(SPRN_DBCR1, thread->dbcr1); + mtspr(SPRN_DBCR0, debug->dbcr0); + mtspr(SPRN_DBCR1, debug->dbcr1); #ifdef CONFIG_BOOKE - mtspr(SPRN_DBCR2, thread->dbcr2); + mtspr(SPRN_DBCR2, debug->dbcr2); #endif } /* @@ -369,12 +411,13 @@ * debug registers, set the debug registers from the values * stored in the new thread. */ -static void switch_booke_debug_regs(struct thread_struct *new_thread) +void switch_booke_debug_regs(struct debug_reg *new_debug) { - if ((current->thread.dbcr0 & DBCR0_IDM) - || (new_thread->dbcr0 & DBCR0_IDM)) - prime_debug_regs(new_thread); + if ((current->thread.debug.dbcr0 & DBCR0_IDM) + || (new_debug->dbcr0 & DBCR0_IDM)) + prime_debug_regs(new_debug); } +EXPORT_SYMBOL_GPL(switch_booke_debug_regs); #else /* !CONFIG_PPC_ADV_DEBUG_REGS */ #ifndef CONFIG_HAVE_HW_BREAKPOINT static void set_debug_reg_defaults(struct thread_struct *thread) @@ -451,14 +494,21 @@ return 0; } -int set_breakpoint(struct arch_hw_breakpoint *brk) +void __set_breakpoint(struct arch_hw_breakpoint *brk) { - __get_cpu_var(current_brk) = *brk; + memcpy(this_cpu_ptr(¤t_brk), brk, sizeof(*brk)); if (cpu_has_feature(CPU_FTR_DAWR)) - return set_dawr(brk); + set_dawr(brk); + else + set_dabr(brk); +} - return set_dabr(brk); +void set_breakpoint(struct arch_hw_breakpoint *brk) +{ + preempt_disable(); + __set_breakpoint(brk); + preempt_enable(); } #ifdef CONFIG_PPC64 @@ -476,7 +526,66 @@ return false; return true; } + #ifdef CONFIG_PPC_TRANSACTIONAL_MEM +static void tm_reclaim_thread(struct thread_struct *thr, + struct thread_info *ti, uint8_t cause) +{ + unsigned long msr_diff = 0; + + /* + * If FP/VSX registers have been already saved to the + * thread_struct, move them to the transact_fp array. + * We clear the TIF_RESTORE_TM bit since after the reclaim + * the thread will no longer be transactional. + */ + if (test_ti_thread_flag(ti, TIF_RESTORE_TM)) { + msr_diff = thr->ckpt_regs.msr & ~thr->regs->msr; + if (msr_diff & MSR_FP) + memcpy(&thr->transact_fp, &thr->fp_state, + sizeof(struct thread_fp_state)); + if (msr_diff & MSR_VEC) + memcpy(&thr->transact_vr, &thr->vr_state, + sizeof(struct thread_vr_state)); + clear_ti_thread_flag(ti, TIF_RESTORE_TM); + msr_diff &= MSR_FP | MSR_VEC | MSR_VSX | MSR_FE0 | MSR_FE1; + } + + /* + * Use the current MSR TM suspended bit to track if we have + * checkpointed state outstanding. + * On signal delivery, we'd normally reclaim the checkpointed + * state to obtain stack pointer (see:get_tm_stackpointer()). + * This will then directly return to userspace without going + * through __switch_to(). However, if the stack frame is bad, + * we need to exit this thread which calls __switch_to() which + * will again attempt to reclaim the already saved tm state. + * Hence we need to check that we've not already reclaimed + * this state. + * We do this using the current MSR, rather tracking it in + * some specific thread_struct bit, as it has the additional + * benifit of checking for a potential TM bad thing exception. + */ + if (!MSR_TM_SUSPENDED(mfmsr())) + return; + + tm_reclaim(thr, thr->regs->msr, cause); + + /* Having done the reclaim, we now have the checkpointed + * FP/VSX values in the registers. These might be valid + * even if we have previously called enable_kernel_fp() or + * flush_fp_to_thread(), so update thr->regs->msr to + * indicate their current validity. + */ + thr->regs->msr |= msr_diff; +} + +void tm_reclaim_current(uint8_t cause) +{ + tm_enable(); + tm_reclaim_thread(¤t->thread, current_thread_info(), cause); +} + static inline void tm_reclaim_task(struct task_struct *tsk) { /* We have to work out if we're switching from/to a task that's in the @@ -499,9 +608,11 @@ /* Stash the original thread MSR, as giveup_fpu et al will * modify it. We hold onto it to see whether the task used - * FP & vector regs. + * FP & vector regs. If the TIF_RESTORE_TM flag is set, + * ckpt_regs.msr is already set. */ - thr->tm_orig_msr = thr->regs->msr; + if (!test_ti_thread_flag(task_thread_info(tsk), TIF_RESTORE_TM)) + thr->ckpt_regs.msr = thr->regs->msr; TM_DEBUG("--- tm_reclaim on pid %d (NIP=%lx, " "ccr=%lx, msr=%lx, trap=%lx)\n", @@ -509,7 +620,7 @@ thr->regs->ccr, thr->regs->msr, thr->regs->trap); - tm_reclaim(thr, thr->regs->msr, TM_CAUSE_RESCHED); + tm_reclaim_thread(thr, task_thread_info(tsk), TM_CAUSE_RESCHED); TM_DEBUG("--- tm_reclaim on pid %d complete\n", tsk->pid); @@ -570,7 +681,7 @@ tm_restore_sprs(&new->thread); return; } - msr = new->thread.tm_orig_msr; + msr = new->thread.ckpt_regs.msr; /* Recheckpoint to restore original checkpointed register state. */ TM_DEBUG("*** tm_recheckpoint of pid %d " "(new->msr 0x%lx, new->origmsr 0x%lx)\n", @@ -607,6 +718,43 @@ tm_reclaim_task(prev); } } + +/* + * This is called if we are on the way out to userspace and the + * TIF_RESTORE_TM flag is set. It checks if we need to reload + * FP and/or vector state and does so if necessary. + * If userspace is inside a transaction (whether active or + * suspended) and FP/VMX/VSX instructions have ever been enabled + * inside that transaction, then we have to keep them enabled + * and keep the FP/VMX/VSX state loaded while ever the transaction + * continues. The reason is that if we didn't, and subsequently + * got a FP/VMX/VSX unavailable interrupt inside a transaction, + * we don't know whether it's the same transaction, and thus we + * don't know which of the checkpointed state and the transactional + * state to use. + */ +void restore_tm_state(struct pt_regs *regs) +{ + unsigned long msr_diff; + + clear_thread_flag(TIF_RESTORE_TM); + if (!MSR_TM_ACTIVE(regs->msr)) + return; + + msr_diff = current->thread.ckpt_regs.msr & ~regs->msr; + msr_diff &= MSR_FP | MSR_VEC | MSR_VSX; + if (msr_diff & MSR_FP) { + fp_enable(); + load_fp_state(¤t->thread.fp_state); + regs->msr |= current->thread.fpexc_mode; + } + if (msr_diff & MSR_VEC) { + vec_enable(); + load_vr_state(¤t->thread.vr_state); + } + regs->msr |= msr_diff; +} + #else #define tm_recheckpoint_new_task(new) #define __switch_to_tm(prev) @@ -616,21 +764,22 @@ struct task_struct *new) { struct thread_struct *new_thread, *old_thread; - unsigned long flags; struct task_struct *last; #ifdef CONFIG_PPC_BOOK3S_64 struct ppc64_tlb_batch *batch; #endif - /* Back up the TAR across context switches. + WARN_ON(!irqs_disabled()); + + /* Back up the TAR and DSCR across context switches. * Note that the TAR is not available for use in the kernel. (To * provide this, the TAR should be backed up/restored on exception * entry/exit instead, and be in pt_regs. FIXME, this should be in * pt_regs anyway (for debug).) - * Save the TAR here before we do treclaim/trecheckpoint as these - * will change the TAR. + * Save the TAR and DSCR here before we do treclaim/trecheckpoint as + * these will change them. */ - save_tar(&prev->thread); + save_early_sprs(&prev->thread); __switch_to_tm(prev); @@ -701,15 +850,15 @@ #endif /* CONFIG_SMP */ #ifdef CONFIG_PPC_ADV_DEBUG_REGS - switch_booke_debug_regs(&new->thread); + switch_booke_debug_regs(&new->thread.debug); #else /* * For PPC_BOOK3S_64, we use the hw-breakpoint interfaces that would * schedule DABR */ #ifndef CONFIG_HAVE_HW_BREAKPOINT - if (unlikely(hw_brk_match(&__get_cpu_var(current_brk), &new->thread.hw_brk))) - set_breakpoint(&new->thread.hw_brk); + if (unlikely(!hw_brk_match(this_cpu_ptr(¤t_brk), &new->thread.hw_brk))) + __set_breakpoint(&new->thread.hw_brk); #endif /* CONFIG_HAVE_HW_BREAKPOINT */ #endif @@ -722,7 +871,7 @@ * Collect processor utilization data per process */ if (firmware_has_feature(FW_FEATURE_SPLPAR)) { - struct cpu_usage *cu = &__get_cpu_var(cpu_usage_array); + struct cpu_usage *cu = this_cpu_ptr(&cpu_usage_array); long unsigned start_tb, current_tb; start_tb = old_thread->start_tb; cu->current_tb = current_tb = mfspr(SPRN_PURR); @@ -732,7 +881,7 @@ #endif /* CONFIG_PPC64 */ #ifdef CONFIG_PPC_BOOK3S_64 - batch = &__get_cpu_var(ppc64_tlb_batch); + batch = this_cpu_ptr(&ppc64_tlb_batch); if (batch->active) { current_thread_info()->local_flags |= _TLF_LAZY_MMU; if (batch->index) @@ -741,8 +890,6 @@ } #endif /* CONFIG_PPC_BOOK3S_64 */ - local_irq_save(flags); - /* * We can't take a PMU exception inside _switch() since there is a * window where the kernel stack SLB and the kernel stack are out @@ -757,13 +904,11 @@ #ifdef CONFIG_PPC_BOOK3S_64 if (current_thread_info()->local_flags & _TLF_LAZY_MMU) { current_thread_info()->local_flags &= ~_TLF_LAZY_MMU; - batch = &__get_cpu_var(ppc64_tlb_batch); + batch = this_cpu_ptr(&ppc64_tlb_batch); batch->active = 1; } #endif /* CONFIG_PPC_BOOK3S_64 */ - local_irq_restore(flags); - return last; } @@ -791,12 +936,8 @@ pc = (unsigned long)phys_to_virt(pc); #endif - /* We use __get_user here *only* to avoid an OOPS on a - * bad address because the pc *should* only be a - * kernel address. - */ if (!__kernel_text_address(pc) || - __get_user(instr, (unsigned int __user *)pc)) { + probe_kernel_address((unsigned int __user *)pc, instr)) { printk(KERN_CONT "XXXXXXXX "); } else { if (regs->nip == pc) @@ -880,17 +1021,21 @@ printk("MSR: "REG" ", regs->msr); printbits(regs->msr, msr_bits); printk(" CR: %08lx XER: %08lx\n", regs->ccr, regs->xer); -#ifdef CONFIG_PPC64 - printk("SOFTE: %ld\n", regs->softe); -#endif 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) + printk("CFAR: "REG" ", regs->orig_gpr3); + if (trap == 0x200 || trap == 0x300 || trap == 0x600) #if defined(CONFIG_4xx) || defined(CONFIG_BOOKE) - printk("DEAR: "REG", ESR: "REG"\n", regs->dar, regs->dsisr); + printk("DEAR: "REG" ESR: "REG" ", regs->dar, regs->dsisr); #else - printk("DAR: "REG", DSISR: %08lx\n", regs->dar, regs->dsisr); + printk("DAR: "REG" DSISR: %08lx ", regs->dar, regs->dsisr); +#endif +#ifdef CONFIG_PPC64 + printk("SOFTE: %ld ", regs->softe); +#endif +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (MSR_TM_ACTIVE(regs->msr)) + printk("\nPACATMSCRATCH: %016llx ", get_paca()->tm_scratch); #endif for (i = 0; i < 32; i++) { @@ -909,9 +1054,6 @@ printk("NIP ["REG"] %pS\n", regs->nip, (void *)regs->nip); printk("LR ["REG"] %pS\n", regs->link, (void *)regs->link); #endif -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM - printk("PACATMSCRATCH [%llx]\n", get_paca()->tm_scratch); -#endif show_stack(current, (unsigned long *) regs->gpr[1]); if (!user_mode(regs)) show_instructions(regs); @@ -949,26 +1091,48 @@ flush_vsx_to_thread(src); flush_spe_to_thread(src); /* - * Flush TM state out so we can copy it. __switch_to_tm() does this - * flush but it removes the checkpointed state from the current CPU and - * transitions the CPU out of TM mode. Hence we need to call - * tm_recheckpoint_new_task() (on the same task) to restore the - * checkpointed state back and the TM mode. - */ + * Flush TM state out so we can copy it. __switch_to_tm() does this + * flush but it removes the checkpointed state from the current CPU and + * transitions the CPU out of TM mode. Hence we need to call + * tm_recheckpoint_new_task() (on the same task) to restore the + * checkpointed state back and the TM mode. + */ __switch_to_tm(src); tm_recheckpoint_new_task(src); *dst = *src; + + clear_task_ebb(dst); + return 0; } +static void setup_ksp_vsid(struct task_struct *p, unsigned long sp) +{ +#ifdef CONFIG_PPC_STD_MMU_64 + unsigned long sp_vsid; + unsigned long llp = mmu_psize_defs[mmu_linear_psize].sllp; + + if (mmu_has_feature(MMU_FTR_1T_SEGMENT)) + sp_vsid = get_kernel_vsid(sp, MMU_SEGSIZE_1T) + << SLB_VSID_SHIFT_1T; + else + sp_vsid = get_kernel_vsid(sp, MMU_SEGSIZE_256M) + << SLB_VSID_SHIFT; + sp_vsid |= SLB_VSID_KERNEL | llp; + p->thread.ksp_vsid = sp_vsid; +#endif +} + /* * Copy a thread.. */ -extern unsigned long dscr_default; /* defined in arch/powerpc/kernel/sysfs.c */ +/* + * Copy architecture-specific thread state + */ int copy_thread(unsigned long clone_flags, unsigned long usp, - unsigned long arg, struct task_struct *p) + unsigned long kthread_arg, struct task_struct *p) { struct pt_regs *childregs, *kregs; extern void ret_from_fork(void); @@ -980,19 +1144,23 @@ sp -= sizeof(struct pt_regs); childregs = (struct pt_regs *) sp; if (unlikely(p->flags & PF_KTHREAD)) { + /* kernel thread */ struct thread_info *ti = (void *)task_stack_page(p); memset(childregs, 0, sizeof(struct pt_regs)); childregs->gpr[1] = sp + sizeof(struct pt_regs); - childregs->gpr[14] = usp; /* function */ + /* function */ + if (usp) + childregs->gpr[14] = ppc_function_entry((void *)usp); #ifdef CONFIG_PPC64 clear_tsk_thread_flag(p, TIF_32BIT); childregs->softe = 1; #endif - childregs->gpr[15] = arg; + childregs->gpr[15] = kthread_arg; p->thread.regs = NULL; /* no user register state */ ti->flags |= _TIF_RESTOREALL; f = ret_from_kernel_thread; } else { + /* user thread */ struct pt_regs *regs = current_pt_regs(); CHECK_FULL_REGS(regs); *childregs = *regs; @@ -1026,28 +1194,21 @@ kregs = (struct pt_regs *) sp; sp -= STACK_FRAME_OVERHEAD; p->thread.ksp = sp; +#ifdef CONFIG_PPC32 p->thread.ksp_limit = (unsigned long)task_stack_page(p) + _ALIGN_UP(sizeof(struct thread_info), 16); - +#endif #ifdef CONFIG_HAVE_HW_BREAKPOINT p->thread.ptrace_bps[0] = NULL; #endif -#ifdef CONFIG_PPC_STD_MMU_64 - if (mmu_has_feature(MMU_FTR_SLB)) { - unsigned long sp_vsid; - unsigned long llp = mmu_psize_defs[mmu_linear_psize].sllp; - - if (mmu_has_feature(MMU_FTR_1T_SEGMENT)) - sp_vsid = get_kernel_vsid(sp, MMU_SEGSIZE_1T) - << SLB_VSID_SHIFT_1T; - else - sp_vsid = get_kernel_vsid(sp, MMU_SEGSIZE_256M) - << SLB_VSID_SHIFT; - sp_vsid |= SLB_VSID_KERNEL | llp; - p->thread.ksp_vsid = sp_vsid; - } -#endif /* CONFIG_PPC_STD_MMU_64 */ + p->thread.fp_save_area = NULL; +#ifdef CONFIG_ALTIVEC + p->thread.vr_save_area = NULL; +#endif + + setup_ksp_vsid(p, sp); + #ifdef CONFIG_PPC64 if (cpu_has_feature(CPU_FTR_DSCR)) { p->thread.dscr_inherit = current->thread.dscr_inherit; @@ -1056,17 +1217,7 @@ if (cpu_has_feature(CPU_FTR_HAS_PPR)) p->thread.ppr = INIT_PPR; #endif - /* - * The PPC64 ABI makes use of a TOC to contain function - * pointers. The function (ret_from_except) is actually a pointer - * to the TOC entry. The first entry is a pointer to the actual - * function. - */ -#ifdef CONFIG_PPC64 - kregs->nip = *((unsigned long *)f); -#else - kregs->nip = (unsigned long)f; -#endif + kregs->nip = ppc_function_entry(f); return 0; } @@ -1088,6 +1239,16 @@ current->thread.regs = regs - 1; } +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + /* + * Clear any transactional state, we're exec()ing. The cause is + * not important as there will never be a recheckpoint so it's not + * user visible. + */ + if (MSR_TM_SUSPENDED(mfmsr())) + tm_reclaim_current(0); +#endif + memset(regs->gpr, 0, sizeof(regs->gpr)); regs->ctr = 0; regs->link = 0; @@ -1108,25 +1269,45 @@ regs->msr = MSR_USER; #else if (!is_32bit_task()) { - unsigned long entry, toc; + unsigned long entry; - /* start is a relocated pointer to the function descriptor for - * the elf _start routine. The first entry in the function - * descriptor is the entry address of _start and the second - * entry is the TOC value we need to use. - */ - __get_user(entry, (unsigned long __user *)start); - __get_user(toc, (unsigned long __user *)start+1); + if (is_elf2_task()) { + /* Look ma, no function descriptors! */ + entry = start; - /* Check whether the e_entry function descriptor entries - * need to be relocated before we can use them. - */ - if (load_addr != 0) { - entry += load_addr; - toc += load_addr; + /* + * Ulrich says: + * The latest iteration of the ABI requires that when + * calling a function (at its global entry point), + * the caller must ensure r12 holds the entry point + * address (so that the function can quickly + * establish addressability). + */ + regs->gpr[12] = start; + /* Make sure that's restored on entry to userspace. */ + set_thread_flag(TIF_RESTOREALL); + } else { + unsigned long toc; + + /* start is a relocated pointer to the function + * descriptor for the elf _start routine. The first + * entry in the function descriptor is the entry + * address of _start and the second entry is the TOC + * value we need to use. + */ + __get_user(entry, (unsigned long __user *)start); + __get_user(toc, (unsigned long __user *)start+1); + + /* Check whether the e_entry function descriptor entries + * need to be relocated before we can use them. + */ + if (load_addr != 0) { + entry += load_addr; + toc += load_addr; + } + regs->gpr[2] = toc; } regs->nip = entry; - regs->gpr[2] = toc; regs->msr = MSR_USER64; } else { regs->nip = start; @@ -1138,12 +1319,12 @@ #ifdef CONFIG_VSX current->thread.used_vsr = 0; #endif - memset(current->thread.fpr, 0, sizeof(current->thread.fpr)); - current->thread.fpscr.val = 0; + memset(¤t->thread.fp_state, 0, sizeof(current->thread.fp_state)); + current->thread.fp_save_area = NULL; #ifdef CONFIG_ALTIVEC - memset(current->thread.vr, 0, sizeof(current->thread.vr)); - memset(¤t->thread.vscr, 0, sizeof(current->thread.vscr)); - current->thread.vscr.u[3] = 0x00010000; /* Java mode disabled */ + memset(¤t->thread.vr_state, 0, sizeof(current->thread.vr_state)); + current->thread.vr_state.vscr.u[3] = 0x00010000; /* Java mode disabled */ + current->thread.vr_save_area = NULL; current->thread.vrsave = 0; current->thread.used_vr = 0; #endif /* CONFIG_ALTIVEC */ @@ -1161,6 +1342,7 @@ current->thread.tm_tfiar = 0; #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ } +EXPORT_SYMBOL(start_thread); #define PR_FP_ALL_EXCEPT (PR_FP_EXC_DIV | PR_FP_EXC_OVF | PR_FP_EXC_UND \ | PR_FP_EXC_RES | PR_FP_EXC_INV) @@ -1176,6 +1358,19 @@ if (val & PR_FP_EXC_SW_ENABLE) { #ifdef CONFIG_SPE if (cpu_has_feature(CPU_FTR_SPE)) { + /* + * When the sticky exception bits are set + * directly by userspace, it must call prctl + * with PR_GET_FPEXC (with PR_FP_EXC_SW_ENABLE + * in the existing prctl settings) or + * PR_SET_FPEXC (with PR_FP_EXC_SW_ENABLE in + * the bits being set). functions + * saving and restoring the whole + * floating-point environment need to do so + * anyway to restore the prctl settings from + * the saved environment. + */ + tsk->thread.spefscr_last = mfspr(SPRN_SPEFSCR); tsk->thread.fpexc_mode = val & (PR_FP_EXC_SW_ENABLE | PR_FP_ALL_EXCEPT); return 0; @@ -1207,9 +1402,22 @@ if (tsk->thread.fpexc_mode & PR_FP_EXC_SW_ENABLE) #ifdef CONFIG_SPE - if (cpu_has_feature(CPU_FTR_SPE)) + if (cpu_has_feature(CPU_FTR_SPE)) { + /* + * When the sticky exception bits are set + * directly by userspace, it must call prctl + * with PR_GET_FPEXC (with PR_FP_EXC_SW_ENABLE + * in the existing prctl settings) or + * PR_SET_FPEXC (with PR_FP_EXC_SW_ENABLE in + * the bits being set). functions + * saving and restoring the whole + * floating-point environment need to do so + * anyway to restore the prctl settings from + * the saved environment. + */ + tsk->thread.spefscr_last = mfspr(SPRN_SPEFSCR); val = tsk->thread.fpexc_mode; - else + } else return -EINVAL; #else return -EINVAL; @@ -1348,13 +1556,6 @@ int curr_frame = current->curr_ret_stack; extern void return_to_handler(void); unsigned long rth = (unsigned long)return_to_handler; - unsigned long mrth = -1; -#ifdef CONFIG_PPC64 - extern void mod_return_to_handler(void); - rth = *(unsigned long *)rth; - mrth = (unsigned long)mod_return_to_handler; - mrth = *(unsigned long *)mrth; -#endif #endif sp = (unsigned long) stack; @@ -1362,7 +1563,7 @@ tsk = current; if (sp == 0) { if (tsk == current) - asm("mr %0,1" : "=r" (sp)); + sp = current_stack_pointer(); else sp = tsk->thread.ksp; } @@ -1379,7 +1580,7 @@ if (!firstframe || ip != lr) { printk("["REG"] ["REG"] %pS", sp, ip, (void *)ip); #ifdef CONFIG_FUNCTION_GRAPH_TRACER - if ((ip == rth || ip == mrth) && curr_frame >= 0) { + if ((ip == rth) && curr_frame >= 0) { printk(" (%pS)", (void *)current->ret_stack[curr_frame].ret); curr_frame--; @@ -1400,7 +1601,7 @@ struct pt_regs *regs = (struct pt_regs *) (sp + STACK_FRAME_OVERHEAD); lr = regs->link; - printk("--- Exception: %lx at %pS\n LR = %pS\n", + printk("--- interrupt: %lx at %pS\n LR = %pS\n", regs->trap, (void *)regs->nip, (void *)lr); firstframe = 1; } @@ -1482,12 +1683,3 @@ return ret; } -unsigned long randomize_et_dyn(unsigned long base) -{ - unsigned long ret = PAGE_ALIGN(base + brk_rnd()); - - if (ret < base) - return base; - - return ret; -}