diff options
Diffstat (limited to 'arch/powerpc/kernel/process.c')
| -rw-r--r-- | arch/powerpc/kernel/process.c | 919 |
1 files changed, 645 insertions, 274 deletions
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 84906d3fc86..be99774d3f4 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -25,10 +25,9 @@ #include <linux/slab.h> #include <linux/user.h> #include <linux/elf.h> -#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> @@ -41,20 +40,31 @@ #include <asm/pgtable.h> #include <asm/uaccess.h> -#include <asm/system.h> #include <asm/io.h> #include <asm/processor.h> #include <asm/mmu.h> #include <asm/prom.h> #include <asm/machdep.h> #include <asm/time.h> +#include <asm/runlatch.h> #include <asm/syscalls.h> +#include <asm/switch_to.h> +#include <asm/tm.h> +#include <asm/debug.h> #ifdef CONFIG_PPC64 #include <asm/firmware.h> #endif +#include <asm/code-patching.h> #include <linux/kprobes.h> #include <linux/kdebug.h> +/* Transactional Memory debug */ +#ifdef TM_DEBUG_SW +#define TM_DEBUG(x...) printk(KERN_INFO x) +#else +#define TM_DEBUG(x...) do { } while(0) +#endif + extern unsigned long _get_SP(void); #ifndef CONFIG_SMP @@ -64,6 +74,49 @@ struct task_struct *last_task_used_vsx = NULL; 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.tm_orig_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.tm_orig_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. @@ -91,11 +144,13 @@ void flush_fp_to_thread(struct task_struct *tsk) */ 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) { @@ -103,11 +158,11 @@ void enable_kernel_fp(void) #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); @@ -119,11 +174,11 @@ void enable_kernel_altivec(void) #ifdef CONFIG_SMP if (current->thread.regs && (current->thread.regs->msr & MSR_VEC)) - giveup_altivec(current); + giveup_altivec_maybe_transactional(current); else - giveup_altivec(NULL); /* just enable AltiVec for kernel - force */ + 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); @@ -140,11 +195,12 @@ void flush_altivec_to_thread(struct task_struct *tsk) #ifdef CONFIG_SMP BUG_ON(tsk != current); #endif - giveup_altivec(tsk); + giveup_altivec_maybe_transactional(tsk); } preempt_enable(); } } +EXPORT_SYMBOL_GPL(flush_altivec_to_thread); #endif /* CONFIG_ALTIVEC */ #ifdef CONFIG_VSX @@ -168,8 +224,8 @@ EXPORT_SYMBOL(enable_kernel_vsx); 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); } @@ -186,6 +242,7 @@ 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 +270,7 @@ 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(); @@ -252,6 +310,7 @@ void do_send_trap(struct pt_regs *regs, unsigned long address, { siginfo_t info; + current->thread.trap_nr = signal_code; if (notify_die(DIE_DABR_MATCH, "dabr_match", regs, error_code, 11, SIGSEGV) == NOTIFY_STOP) return; @@ -264,20 +323,21 @@ void do_send_trap(struct pt_regs *regs, unsigned long address, force_sig_info(SIGTRAP, &info, current); } #else /* !CONFIG_PPC_ADV_DEBUG_REGS */ -void do_dabr(struct pt_regs *regs, unsigned long address, +void do_break (struct pt_regs *regs, unsigned long address, unsigned long error_code) { siginfo_t info; + current->thread.trap_nr = TRAP_HWBKPT; if (notify_die(DIE_DABR_MATCH, "dabr_match", regs, error_code, 11, SIGSEGV) == NOTIFY_STOP) return; - if (debugger_dabr_match(regs)) + if (debugger_break_match(regs)) return; - /* Clear the DABR */ - set_dabr(0); + /* Clear the breakpoint */ + hw_breakpoint_disable(); /* Deliver the signal to userspace */ info.si_signo = SIGTRAP; @@ -288,7 +348,7 @@ void do_dabr(struct pt_regs *regs, unsigned long address, } #endif /* CONFIG_PPC_ADV_DEBUG_REGS */ -static DEFINE_PER_CPU(unsigned long, current_dabr); +static DEFINE_PER_CPU(struct arch_hw_breakpoint, current_brk); #ifdef CONFIG_PPC_ADV_DEBUG_REGS /* @@ -296,49 +356,56 @@ static DEFINE_PER_CPU(unsigned long, current_dabr); */ 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) { - mtspr(SPRN_IAC1, thread->iac1); - mtspr(SPRN_IAC2, thread->iac2); + /* + * We could have inherited MSR_DE from userspace, since + * it doesn't get cleared on exception entry. Make sure + * MSR_DE is clear before we enable any debug events. + */ + mtmsr(mfmsr() & ~MSR_DE); + + 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 } /* @@ -346,53 +413,359 @@ static void prime_debug_regs(struct thread_struct *thread) * 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) { - if (thread->dabr) { - thread->dabr = 0; - set_dabr(0); - } + thread->hw_brk.address = 0; + thread->hw_brk.type = 0; + set_breakpoint(&thread->hw_brk); } +#endif /* !CONFIG_HAVE_HW_BREAKPOINT */ #endif /* CONFIG_PPC_ADV_DEBUG_REGS */ -int set_dabr(unsigned long dabr) -{ - __get_cpu_var(current_dabr) = dabr; - - if (ppc_md.set_dabr) - return ppc_md.set_dabr(dabr); - - /* XXX should we have a CPU_FTR_HAS_DABR ? */ #ifdef CONFIG_PPC_ADV_DEBUG_REGS +static inline int __set_dabr(unsigned long dabr, unsigned long dabrx) +{ mtspr(SPRN_DAC1, dabr); #ifdef CONFIG_PPC_47x isync(); #endif + return 0; +} #elif defined(CONFIG_PPC_BOOK3S) +static inline int __set_dabr(unsigned long dabr, unsigned long dabrx) +{ mtspr(SPRN_DABR, dabr); + if (cpu_has_feature(CPU_FTR_DABRX)) + mtspr(SPRN_DABRX, dabrx); + return 0; +} +#else +static inline int __set_dabr(unsigned long dabr, unsigned long dabrx) +{ + return -EINVAL; +} #endif +static inline int set_dabr(struct arch_hw_breakpoint *brk) +{ + unsigned long dabr, dabrx; + + dabr = brk->address | (brk->type & HW_BRK_TYPE_DABR); + dabrx = ((brk->type >> 3) & 0x7); + if (ppc_md.set_dabr) + return ppc_md.set_dabr(dabr, dabrx); + + return __set_dabr(dabr, dabrx); +} + +static inline int set_dawr(struct arch_hw_breakpoint *brk) +{ + unsigned long dawr, dawrx, mrd; + + dawr = brk->address; + + dawrx = (brk->type & (HW_BRK_TYPE_READ | HW_BRK_TYPE_WRITE)) \ + << (63 - 58); //* read/write bits */ + dawrx |= ((brk->type & (HW_BRK_TYPE_TRANSLATE)) >> 2) \ + << (63 - 59); //* translate */ + dawrx |= (brk->type & (HW_BRK_TYPE_PRIV_ALL)) \ + >> 3; //* PRIM bits */ + /* dawr length is stored in field MDR bits 48:53. Matches range in + doublewords (64 bits) baised by -1 eg. 0b000000=1DW and + 0b111111=64DW. + brk->len is in bytes. + This aligns up to double word size, shifts and does the bias. + */ + mrd = ((brk->len + 7) >> 3) - 1; + dawrx |= (mrd & 0x3f) << (63 - 53); + + if (ppc_md.set_dawr) + return ppc_md.set_dawr(dawr, dawrx); + mtspr(SPRN_DAWR, dawr); + mtspr(SPRN_DAWRX, dawrx); return 0; } +void __set_breakpoint(struct arch_hw_breakpoint *brk) +{ + __get_cpu_var(current_brk) = *brk; + + if (cpu_has_feature(CPU_FTR_DAWR)) + set_dawr(brk); + else + set_dabr(brk); +} + +void set_breakpoint(struct arch_hw_breakpoint *brk) +{ + preempt_disable(); + __set_breakpoint(brk); + preempt_enable(); +} + #ifdef CONFIG_PPC64 DEFINE_PER_CPU(struct cpu_usage, cpu_usage_array); #endif +static inline bool hw_brk_match(struct arch_hw_breakpoint *a, + struct arch_hw_breakpoint *b) +{ + if (a->address != b->address) + return false; + if (a->type != b->type) + return false; + if (a->len != b->len) + 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->tm_orig_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; + } + + 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 + * middle of a transaction. + * + * In switching we need to maintain a 2nd register state as + * oldtask->thread.ckpt_regs. We tm_reclaim(oldproc); this saves the + * checkpointed (tbegin) state in ckpt_regs and saves the transactional + * (current) FPRs into oldtask->thread.transact_fpr[]. + * + * We also context switch (save) TFHAR/TEXASR/TFIAR in here. + */ + struct thread_struct *thr = &tsk->thread; + + if (!thr->regs) + return; + + if (!MSR_TM_ACTIVE(thr->regs->msr)) + goto out_and_saveregs; + + /* 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. If the TIF_RESTORE_TM flag is set, + * tm_orig_msr is already set. + */ + if (!test_ti_thread_flag(task_thread_info(tsk), TIF_RESTORE_TM)) + thr->tm_orig_msr = thr->regs->msr; + + TM_DEBUG("--- tm_reclaim on pid %d (NIP=%lx, " + "ccr=%lx, msr=%lx, trap=%lx)\n", + tsk->pid, thr->regs->nip, + thr->regs->ccr, thr->regs->msr, + thr->regs->trap); + + tm_reclaim_thread(thr, task_thread_info(tsk), TM_CAUSE_RESCHED); + + TM_DEBUG("--- tm_reclaim on pid %d complete\n", + tsk->pid); + +out_and_saveregs: + /* Always save the regs here, even if a transaction's not active. + * This context-switches a thread's TM info SPRs. We do it here to + * be consistent with the restore path (in recheckpoint) which + * cannot happen later in _switch(). + */ + tm_save_sprs(thr); +} + +extern void __tm_recheckpoint(struct thread_struct *thread, + unsigned long orig_msr); + +void tm_recheckpoint(struct thread_struct *thread, + unsigned long orig_msr) +{ + unsigned long flags; + + /* We really can't be interrupted here as the TEXASR registers can't + * change and later in the trecheckpoint code, we have a userspace R1. + * So let's hard disable over this region. + */ + local_irq_save(flags); + hard_irq_disable(); + + /* The TM SPRs are restored here, so that TEXASR.FS can be set + * before the trecheckpoint and no explosion occurs. + */ + tm_restore_sprs(thread); + + __tm_recheckpoint(thread, orig_msr); + + local_irq_restore(flags); +} + +static inline void tm_recheckpoint_new_task(struct task_struct *new) +{ + unsigned long msr; + + if (!cpu_has_feature(CPU_FTR_TM)) + return; + + /* Recheckpoint the registers of the thread we're about to switch to. + * + * If the task was using FP, we non-lazily reload both the original and + * the speculative FP register states. This is because the kernel + * doesn't see if/when a TM rollback occurs, so if we take an FP + * unavoidable later, we are unable to determine which set of FP regs + * need to be restored. + */ + if (!new->thread.regs) + return; + + if (!MSR_TM_ACTIVE(new->thread.regs->msr)){ + tm_restore_sprs(&new->thread); + return; + } + msr = new->thread.tm_orig_msr; + /* Recheckpoint to restore original checkpointed register state. */ + TM_DEBUG("*** tm_recheckpoint of pid %d " + "(new->msr 0x%lx, new->origmsr 0x%lx)\n", + new->pid, new->thread.regs->msr, msr); + + /* This loads the checkpointed FP/VEC state, if used */ + tm_recheckpoint(&new->thread, msr); + + /* This loads the speculative FP/VEC state, if used */ + if (msr & MSR_FP) { + do_load_up_transact_fpu(&new->thread); + new->thread.regs->msr |= + (MSR_FP | new->thread.fpexc_mode); + } +#ifdef CONFIG_ALTIVEC + if (msr & MSR_VEC) { + do_load_up_transact_altivec(&new->thread); + new->thread.regs->msr |= MSR_VEC; + } +#endif + /* We may as well turn on VSX too since all the state is restored now */ + if (msr & MSR_VSX) + new->thread.regs->msr |= MSR_VSX; + + TM_DEBUG("*** tm_recheckpoint of pid %d complete " + "(kernel msr 0x%lx)\n", + new->pid, mfmsr()); +} + +static inline void __switch_to_tm(struct task_struct *prev) +{ + if (cpu_has_feature(CPU_FTR_TM)) { + tm_enable(); + 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.tm_orig_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) +#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ + struct task_struct *__switch_to(struct task_struct *prev, 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 + + 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 and DSCR here before we do treclaim/trecheckpoint as + * these will change them. + */ + save_early_sprs(&prev->thread); + + __switch_to_tm(prev); #ifdef CONFIG_SMP /* avoid complexity of lazy save/restore of fpu @@ -461,15 +834,15 @@ struct task_struct *__switch_to(struct task_struct *prev, #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(__get_cpu_var(current_dabr) != new->thread.dabr)) - set_dabr(new->thread.dabr); + if (unlikely(!hw_brk_match(&__get_cpu_var(current_brk), &new->thread.hw_brk))) + __set_breakpoint(&new->thread.hw_brk); #endif /* CONFIG_HAVE_HW_BREAKPOINT */ #endif @@ -477,28 +850,6 @@ 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 @@ -511,12 +862,17 @@ struct task_struct *__switch_to(struct task_struct *prev, old_thread->accum_tb += (current_tb - start_tb); new_thread->start_tb = current_tb; } -#endif - - local_irq_save(flags); - - account_system_vtime(current); - account_process_vtime(current); +#endif /* CONFIG_PPC64 */ + +#ifdef CONFIG_PPC_BOOK3S_64 + batch = &__get_cpu_var(ppc64_tlb_batch); + if (batch->active) { + current_thread_info()->local_flags |= _TLF_LAZY_MMU; + if (batch->index) + __flush_tlb_pending(batch); + batch->active = 0; + } +#endif /* CONFIG_PPC_BOOK3S_64 */ /* * We can't take a PMU exception inside _switch() since there is a @@ -524,9 +880,18 @@ struct task_struct *__switch_to(struct task_struct *prev, * of sync. Hard disable here. */ hard_irq_disable(); + + tm_recheckpoint_new_task(new); + last = _switch(old_thread, new_thread); - local_irq_restore(flags); +#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->active = 1; + } +#endif /* CONFIG_PPC_BOOK3S_64 */ return last; } @@ -561,12 +926,12 @@ static void show_instructions(struct pt_regs *regs) */ if (!__kernel_text_address(pc) || __get_user(instr, (unsigned int __user *)pc)) { - printk("XXXXXXXX "); + printk(KERN_CONT "XXXXXXXX "); } else { if (regs->nip == pc) - printk("<%08x> ", instr); + printk(KERN_CONT "<%08x> ", instr); else - printk("%08x ", instr); + printk(KERN_CONT "%08x ", instr); } pc += sizeof(int); @@ -579,16 +944,32 @@ static struct regbit { unsigned long bit; const char *name; } msr_bits[] = { +#if defined(CONFIG_PPC64) && !defined(CONFIG_BOOKE) + {MSR_SF, "SF"}, + {MSR_HV, "HV"}, +#endif + {MSR_VEC, "VEC"}, + {MSR_VSX, "VSX"}, +#ifdef CONFIG_BOOKE + {MSR_CE, "CE"}, +#endif {MSR_EE, "EE"}, {MSR_PR, "PR"}, {MSR_FP, "FP"}, - {MSR_VEC, "VEC"}, - {MSR_VSX, "VSX"}, {MSR_ME, "ME"}, - {MSR_CE, "CE"}, +#ifdef CONFIG_BOOKE {MSR_DE, "DE"}, +#else + {MSR_SE, "SE"}, + {MSR_BE, "BE"}, +#endif {MSR_IR, "IR"}, {MSR_DR, "DR"}, + {MSR_PMM, "PMM"}, +#ifndef CONFIG_BOOKE + {MSR_RI, "RI"}, + {MSR_LE, "LE"}, +#endif {0, NULL} }; @@ -619,6 +1000,8 @@ void show_regs(struct pt_regs * regs) { int i, trap; + show_regs_print_info(KERN_DEFAULT); + printk("NIP: "REG" LR: "REG" CTR: "REG"\n", regs->nip, regs->link, regs->ctr); printk("REGS: %p TRAP: %04lx %s (%s)\n", @@ -627,18 +1010,21 @@ 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 (trap == 0x300 || trap == 0x600) -#ifdef CONFIG_PPC_ADV_DEBUG_REGS - printk("DEAR: "REG", ESR: "REG"\n", regs->dar, regs->dsisr); + if ((regs->trap != 0xc00) && cpu_has_feature(CPU_FTR_CFAR)) + 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" ", regs->dar, regs->dsisr); #else - printk("DAR: "REG", DSISR: "REG"\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 - printk("TASK = %p[%d] '%s' THREAD: %p", - current, task_pid_nr(current), current->comm, task_thread_info(current)); - -#ifdef CONFIG_SMP - printk(" CPU: %d", raw_smp_processor_id()); -#endif /* CONFIG_SMP */ for (i = 0; i < 32; i++) { if ((i % REGS_PER_LINE) == 0) @@ -670,11 +1056,11 @@ void flush_thread(void) { discard_lazy_cpu_state(); -#ifdef CONFIG_HAVE_HW_BREAKPOINTS +#ifdef CONFIG_HAVE_HW_BREAKPOINT flush_ptrace_hw_breakpoint(current); -#else /* CONFIG_HAVE_HW_BREAKPOINTS */ +#else /* CONFIG_HAVE_HW_BREAKPOINT */ set_debug_reg_defaults(¤t->thread); -#endif /* CONFIG_HAVE_HW_BREAKPOINTS */ +#endif /* CONFIG_HAVE_HW_BREAKPOINT */ } void @@ -683,48 +1069,72 @@ release_thread(struct task_struct *t) } /* - * This gets called before we allocate a new thread and copy - * the current task into it. + * this gets called so that we can store coprocessor state into memory and + * copy the current task into the new thread. */ -void prepare_to_copy(struct task_struct *tsk) +int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { - flush_fp_to_thread(current); - flush_altivec_to_thread(current); - flush_vsx_to_thread(current); - flush_spe_to_thread(current); -#ifdef CONFIG_HAVE_HW_BREAKPOINT - flush_ptrace_hw_breakpoint(tsk); -#endif /* CONFIG_HAVE_HW_BREAKPOINT */ + flush_fp_to_thread(src); + flush_altivec_to_thread(src); + 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. + */ + __switch_to_tm(src); + tm_recheckpoint_new_task(src); + + *dst = *src; + + clear_task_ebb(dst); + + return 0; } /* * Copy a thread.. */ +extern unsigned long dscr_default; /* defined in arch/powerpc/kernel/sysfs.c */ + int copy_thread(unsigned long clone_flags, unsigned long usp, - unsigned long unused, struct task_struct *p, - struct pt_regs *regs) + unsigned long arg, struct task_struct *p) { struct pt_regs *childregs, *kregs; extern void ret_from_fork(void); + extern void ret_from_kernel_thread(void); + void (*f)(void); unsigned long sp = (unsigned long)task_stack_page(p) + THREAD_SIZE; - CHECK_FULL_REGS(regs); /* Copy registers */ sp -= sizeof(struct pt_regs); childregs = (struct pt_regs *) sp; - *childregs = *regs; - if ((childregs->msr & MSR_PR) == 0) { - /* for kernel thread, set `current' and stackptr in new task */ + if (unlikely(p->flags & PF_KTHREAD)) { + struct thread_info *ti = (void *)task_stack_page(p); + memset(childregs, 0, sizeof(struct pt_regs)); childregs->gpr[1] = sp + sizeof(struct pt_regs); -#ifdef CONFIG_PPC32 - childregs->gpr[2] = (unsigned long) p; -#else + /* 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; p->thread.regs = NULL; /* no user register state */ + ti->flags |= _TIF_RESTOREALL; + f = ret_from_kernel_thread; } else { - childregs->gpr[1] = usp; + struct pt_regs *regs = current_pt_regs(); + CHECK_FULL_REGS(regs); + *childregs = *regs; + if (usp) + childregs->gpr[1] = usp; p->thread.regs = childregs; + childregs->gpr[3] = 0; /* Result from fork() */ if (clone_flags & CLONE_SETTLS) { #ifdef CONFIG_PPC64 if (!is_32bit_task()) @@ -733,8 +1143,9 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, #endif childregs->gpr[2] = childregs->gpr[6]; } + + f = ret_from_fork; } - childregs->gpr[3] = 0; /* Result from fork() */ sp -= STACK_FRAME_OVERHEAD; /* @@ -745,19 +1156,30 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, * do some house keeping and then return from the fork or clone * system call, using the stack frame created above. */ + ((unsigned long *)sp)[0] = 0; sp -= sizeof(struct pt_regs); 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 + + p->thread.fp_save_area = NULL; +#ifdef CONFIG_ALTIVEC + p->thread.vr_save_area = NULL; +#endif #ifdef CONFIG_PPC_STD_MMU_64 - if (cpu_has_feature(CPU_FTR_SLB)) { + if (mmu_has_feature(MMU_FTR_SLB)) { unsigned long sp_vsid; unsigned long llp = mmu_psize_defs[mmu_linear_psize].sllp; - if (cpu_has_feature(CPU_FTR_1T_SEGMENT)) + if (mmu_has_feature(MMU_FTR_1T_SEGMENT)) sp_vsid = get_kernel_vsid(sp, MMU_SEGSIZE_1T) << SLB_VSID_SHIFT_1T; else @@ -767,19 +1189,15 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, p->thread.ksp_vsid = sp_vsid; } #endif /* CONFIG_PPC_STD_MMU_64 */ - - /* - * 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 *)ret_from_fork); -#else - kregs->nip = (unsigned long)ret_from_fork; +#ifdef CONFIG_PPC64 + if (cpu_has_feature(CPU_FTR_DSCR)) { + p->thread.dscr_inherit = current->thread.dscr_inherit; + p->thread.dscr = current->thread.dscr; + } + if (cpu_has_feature(CPU_FTR_HAS_PPR)) + p->thread.ppr = INIT_PPR; #endif - + kregs->nip = ppc_function_entry(f); return 0; } @@ -792,8 +1210,6 @@ 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. @@ -823,25 +1239,45 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp) 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; @@ -849,17 +1285,16 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp) regs->msr = MSR_USER32; } #endif - discard_lazy_cpu_state(); #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 */ @@ -869,6 +1304,13 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp) current->thread.spefscr = 0; current->thread.used_spe = 0; #endif /* CONFIG_SPE */ +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (cpu_has_feature(CPU_FTR_TM)) + regs->msr |= MSR_TM; + current->thread.tm_tfhar = 0; + current->thread.tm_texasr = 0; + current->thread.tm_tfiar = 0; +#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ } #define PR_FP_ALL_EXCEPT (PR_FP_EXC_DIV | PR_FP_EXC_OVF | PR_FP_EXC_UND \ @@ -885,6 +1327,19 @@ int set_fpexc_mode(struct task_struct *tsk, unsigned int val) 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). <fenv.h> 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; @@ -916,9 +1371,22 @@ int get_fpexc_mode(struct task_struct *tsk, unsigned long adr) 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). <fenv.h> 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; @@ -983,64 +1451,6 @@ int get_unalign_ctl(struct task_struct *tsk, unsigned long adr) return put_user(tsk->thread.align_ctl, (unsigned int __user *)adr); } -#define TRUNC_PTR(x) ((typeof(x))(((unsigned long)(x)) & 0xffffffff)) - -int sys_clone(unsigned long clone_flags, unsigned long usp, - int __user *parent_tidp, void __user *child_threadptr, - int __user *child_tidp, int p6, - struct pt_regs *regs) -{ - CHECK_FULL_REGS(regs); - if (usp == 0) - usp = regs->gpr[1]; /* stack pointer for child */ -#ifdef CONFIG_PPC64 - if (is_32bit_task()) { - parent_tidp = TRUNC_PTR(parent_tidp); - child_tidp = TRUNC_PTR(child_tidp); - } -#endif - return do_fork(clone_flags, usp, regs, 0, parent_tidp, child_tidp); -} - -int sys_fork(unsigned long p1, unsigned long p2, unsigned long p3, - unsigned long p4, unsigned long p5, unsigned long p6, - struct pt_regs *regs) -{ - CHECK_FULL_REGS(regs); - return do_fork(SIGCHLD, regs->gpr[1], regs, 0, NULL, NULL); -} - -int sys_vfork(unsigned long p1, unsigned long p2, unsigned long p3, - unsigned long p4, unsigned long p5, unsigned long p6, - struct pt_regs *regs) -{ - CHECK_FULL_REGS(regs); - return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs->gpr[1], - regs, 0, NULL, NULL); -} - -int sys_execve(unsigned long a0, unsigned long a1, unsigned long a2, - unsigned long a3, unsigned long a4, unsigned long a5, - struct pt_regs *regs) -{ - int error; - char *filename; - - filename = getname((const char __user *) a0); - error = PTR_ERR(filename); - if (IS_ERR(filename)) - goto out; - flush_fp_to_thread(current); - flush_altivec_to_thread(current); - flush_spe_to_thread(current); - error = do_execve(filename, - (const char __user *const __user *) a1, - (const char __user *const __user *) a2, regs); - putname(filename); -out: - return error; -} - static inline int valid_irq_stack(unsigned long sp, struct task_struct *p, unsigned long nbytes) { @@ -1176,72 +1586,33 @@ void show_stack(struct task_struct *tsk, unsigned long *stack) } while (count++ < kstack_depth_to_print); } -void dump_stack(void) -{ - show_stack(current, NULL); -} -EXPORT_SYMBOL(dump_stack); - #ifdef CONFIG_PPC64 -void ppc64_runlatch_on(void) +/* Called with hard IRQs off */ +void notrace __ppc64_runlatch_on(void) { + struct thread_info *ti = current_thread_info(); unsigned long ctrl; - if (cpu_has_feature(CPU_FTR_CTRL) && !test_thread_flag(TIF_RUNLATCH)) { - HMT_medium(); - - ctrl = mfspr(SPRN_CTRLF); - ctrl |= CTRL_RUNLATCH; - mtspr(SPRN_CTRLT, ctrl); + ctrl = mfspr(SPRN_CTRLF); + ctrl |= CTRL_RUNLATCH; + mtspr(SPRN_CTRLT, ctrl); - set_thread_flag(TIF_RUNLATCH); - } + ti->local_flags |= _TLF_RUNLATCH; } -void __ppc64_runlatch_off(void) +/* Called with hard IRQs off */ +void notrace __ppc64_runlatch_off(void) { + struct thread_info *ti = current_thread_info(); unsigned long ctrl; - HMT_medium(); - - clear_thread_flag(TIF_RUNLATCH); + ti->local_flags &= ~_TLF_RUNLATCH; ctrl = mfspr(SPRN_CTRLF); ctrl &= ~CTRL_RUNLATCH; mtspr(SPRN_CTRLT, ctrl); } -#endif - -#if THREAD_SHIFT < PAGE_SHIFT - -static struct kmem_cache *thread_info_cache; - -struct thread_info *alloc_thread_info(struct task_struct *tsk) -{ - struct thread_info *ti; - - ti = kmem_cache_alloc(thread_info_cache, GFP_KERNEL); - if (unlikely(ti == NULL)) - return NULL; -#ifdef CONFIG_DEBUG_STACK_USAGE - memset(ti, 0, THREAD_SIZE); -#endif - return ti; -} - -void free_thread_info(struct thread_info *ti) -{ - kmem_cache_free(thread_info_cache, ti); -} - -void thread_info_cache_init(void) -{ - thread_info_cache = kmem_cache_create("thread_info", THREAD_SIZE, - THREAD_SIZE, 0, NULL); - BUG_ON(thread_info_cache == NULL); -} - -#endif /* THREAD_SHIFT < PAGE_SHIFT */ +#endif /* CONFIG_PPC64 */ unsigned long arch_align_stack(unsigned long sp) { |