diff options
Diffstat (limited to 'arch/powerpc/kernel/process.c')
| -rw-r--r-- | arch/powerpc/kernel/process.c | 459 |
1 files changed, 288 insertions, 171 deletions
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 185beb290580..a45fe147868b 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -34,10 +34,8 @@ #include <linux/ftrace.h> #include <linux/kernel_stat.h> #include <linux/personality.h> -#include <linux/random.h> #include <linux/hw_breakpoint.h> #include <linux/uaccess.h> -#include <linux/elf-randomize.h> #include <linux/pkeys.h> #include <linux/seq_buf.h> @@ -45,7 +43,6 @@ #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> @@ -57,7 +54,7 @@ #include <asm/firmware.h> #include <asm/hw_irq.h> #endif -#include <asm/code-patching.h> +#include <asm/text-patching.h> #include <asm/exec.h> #include <asm/livepatch.h> #include <asm/cpu_has_feature.h> @@ -75,8 +72,6 @@ #define TM_DEBUG(x...) do { } while(0) #endif -extern unsigned long _get_SP(void); - #ifdef CONFIG_PPC_TRANSACTIONAL_MEM /* * Are we running in "Suspend disabled" mode? If so we have to block any @@ -130,7 +125,7 @@ unsigned long notrace msr_check_and_set(unsigned long bits) newmsr |= MSR_VSX; if (oldmsr != newmsr) - mtmsr_isync(newmsr); + newmsr = mtmsr_isync_irqsafe(newmsr); return newmsr; } @@ -148,7 +143,7 @@ void notrace __msr_check_and_clear(unsigned long bits) newmsr &= ~MSR_VSX; if (oldmsr != newmsr) - mtmsr_isync(newmsr); + mtmsr_isync_irqsafe(newmsr); } EXPORT_SYMBOL(__msr_check_and_clear); @@ -307,7 +302,7 @@ static void __giveup_vsx(struct task_struct *tsk) unsigned long msr = tsk->thread.regs->msr; /* - * We should never be ssetting MSR_VSX without also setting + * We should never be setting MSR_VSX without also setting * MSR_FP and MSR_VEC */ WARN_ON((msr & MSR_VSX) && !((msr & MSR_FP) && (msr & MSR_VEC))); @@ -628,7 +623,7 @@ static void do_break_handler(struct pt_regs *regs) { struct arch_hw_breakpoint null_brk = {0}; struct arch_hw_breakpoint *info; - struct ppc_inst instr = ppc_inst(0); + ppc_inst_t instr = ppc_inst(0); int type = 0; int size = 0; unsigned long ea; @@ -645,7 +640,7 @@ static void do_break_handler(struct pt_regs *regs) return; } - /* Otherwise findout which DAWR caused exception and disable it. */ + /* Otherwise find out which DAWR caused exception and disable it. */ wp_get_instr_detail(regs, &instr, &type, &size, &ea); for (i = 0; i < nr_wp_slots(); i++) { @@ -865,10 +860,8 @@ static inline int set_breakpoint_8xx(struct arch_hw_breakpoint *brk) return 0; } -void __set_breakpoint(int nr, struct arch_hw_breakpoint *brk) +static void set_hw_breakpoint(int nr, struct arch_hw_breakpoint *brk) { - memcpy(this_cpu_ptr(¤t_brk[nr]), brk, sizeof(*brk)); - if (dawr_enabled()) // Power8 or later set_dawr(nr, brk); @@ -882,6 +875,12 @@ void __set_breakpoint(int nr, struct arch_hw_breakpoint *brk) WARN_ON_ONCE(1); } +void __set_breakpoint(int nr, struct arch_hw_breakpoint *brk) +{ + memcpy(this_cpu_ptr(¤t_brk[nr]), brk, sizeof(*brk)); + set_hw_breakpoint(nr, brk); +} + /* Check if we have DAWR or DABR hardware */ bool ppc_breakpoint_available(void) { @@ -894,6 +893,34 @@ bool ppc_breakpoint_available(void) } EXPORT_SYMBOL_GPL(ppc_breakpoint_available); +/* Disable the breakpoint in hardware without touching current_brk[] */ +void suspend_breakpoints(void) +{ + struct arch_hw_breakpoint brk = {0}; + int i; + + if (!ppc_breakpoint_available()) + return; + + for (i = 0; i < nr_wp_slots(); i++) + set_hw_breakpoint(i, &brk); +} + +/* + * Re-enable breakpoints suspended by suspend_breakpoints() in hardware + * from current_brk[] + */ +void restore_breakpoints(void) +{ + int i; + + if (!ppc_breakpoint_available()) + return; + + for (i = 0; i < nr_wp_slots(); i++) + set_hw_breakpoint(i, this_cpu_ptr(¤t_brk[i])); +} + #ifdef CONFIG_PPC_TRANSACTIONAL_MEM static inline bool tm_enabled(struct task_struct *tsk) @@ -973,7 +1000,7 @@ static inline void tm_reclaim_task(struct task_struct *tsk) WARN_ON(tm_suspend_disabled); - TM_DEBUG("--- tm_reclaim on pid %d (NIP=%lx, " + 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, @@ -981,7 +1008,7 @@ static inline void tm_reclaim_task(struct task_struct *tsk) tm_reclaim_thread(thr, TM_CAUSE_RESCHED); - TM_DEBUG("--- tm_reclaim on pid %d complete\n", + TM_DEBUG("---- tm_reclaim on pid %d complete\n", tsk->pid); out_and_saveregs: @@ -1153,8 +1180,48 @@ static inline void save_sprs(struct thread_struct *t) */ t->tar = mfspr(SPRN_TAR); } + + if (cpu_has_feature(CPU_FTR_DEXCR_NPHIE)) + t->hashkeyr = mfspr(SPRN_HASHKEYR); + + if (cpu_has_feature(CPU_FTR_ARCH_31)) + t->dexcr = mfspr(SPRN_DEXCR); +#endif +} + +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE +void kvmppc_save_user_regs(void) +{ + unsigned long usermsr; + + if (!current->thread.regs) + return; + + usermsr = current->thread.regs->msr; + + /* Caller has enabled FP/VEC/VSX/TM in MSR */ + if (usermsr & MSR_FP) + __giveup_fpu(current); + if (usermsr & MSR_VEC) + __giveup_altivec(current); + +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (usermsr & MSR_TM) { + current->thread.tm_tfhar = mfspr(SPRN_TFHAR); + current->thread.tm_tfiar = mfspr(SPRN_TFIAR); + current->thread.tm_texasr = mfspr(SPRN_TEXASR); + current->thread.regs->msr &= ~MSR_TM; + } #endif } +EXPORT_SYMBOL_GPL(kvmppc_save_user_regs); + +void kvmppc_save_current_sprs(void) +{ + save_sprs(¤t->thread); +} +EXPORT_SYMBOL_GPL(kvmppc_save_current_sprs); +#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */ static inline void restore_sprs(struct thread_struct *old_thread, struct thread_struct *new_thread) @@ -1197,6 +1264,14 @@ static inline void restore_sprs(struct thread_struct *old_thread, if (cpu_has_feature(CPU_FTR_P9_TIDR) && old_thread->tidr != new_thread->tidr) mtspr(SPRN_TIDR, new_thread->tidr); + + if (cpu_has_feature(CPU_FTR_DEXCR_NPHIE) && + old_thread->hashkeyr != new_thread->hashkeyr) + mtspr(SPRN_HASHKEYR, new_thread->hashkeyr); + + if (cpu_has_feature(CPU_FTR_ARCH_31) && + old_thread->dexcr != new_thread->dexcr) + mtspr(SPRN_DEXCR, new_thread->dexcr); #endif } @@ -1206,7 +1281,7 @@ struct task_struct *__switch_to(struct task_struct *prev, { struct thread_struct *new_thread, *old_thread; struct task_struct *last; -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU struct ppc64_tlb_batch *batch; #endif @@ -1215,7 +1290,7 @@ struct task_struct *__switch_to(struct task_struct *prev, WARN_ON(!irqs_disabled()); -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU batch = this_cpu_ptr(&ppc64_tlb_batch); if (batch->active) { current_thread_info()->local_flags |= _TLF_LAZY_MMU; @@ -1281,9 +1356,9 @@ struct task_struct *__switch_to(struct task_struct *prev, set_return_regs_changed(); /* _switch changes stack (and regs) */ -#ifdef CONFIG_PPC32 - kuap_assert_locked(); -#endif + if (!IS_ENABLED(CONFIG_PPC_BOOK3S_64)) + kuap_assert_locked(); + last = _switch(old_thread, new_thread); /* @@ -1294,6 +1369,7 @@ struct task_struct *__switch_to(struct task_struct *prev, */ #ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU /* * This applies to a process that was context switched while inside * arch_enter_lazy_mmu_mode(), to re-activate the batch that was @@ -1305,6 +1381,7 @@ struct task_struct *__switch_to(struct task_struct *prev, batch = this_cpu_ptr(&ppc64_tlb_batch); batch->active = 1; } +#endif /* * Math facilities are masked out of the child MSR in copy_thread. @@ -1326,7 +1403,7 @@ static void show_instructions(struct pt_regs *regs) unsigned long nip = regs->nip; unsigned long pc = regs->nip - (NR_INSN_TO_PRINT * 3 / 4 * sizeof(int)); - printk("Instruction dump:"); + printk("Code: "); /* * If we were executing with the MMU off for instructions, adjust pc @@ -1340,11 +1417,7 @@ static void show_instructions(struct pt_regs *regs) for (i = 0; i < NR_INSN_TO_PRINT; i++) { int instr; - if (!(i % 8)) - pr_cont("\n"); - - if (!__kernel_text_address(pc) || - get_kernel_nofault(instr, (const void *)pc)) { + if (get_kernel_nofault(instr, (const void *)pc)) { pr_cont("XXXXXXXX "); } else { if (nip == pc) @@ -1498,8 +1571,8 @@ static void __show_regs(struct pt_regs *regs) if (trap == INTERRUPT_MACHINE_CHECK || trap == INTERRUPT_DATA_STORAGE || trap == INTERRUPT_ALIGNMENT) { - if (IS_ENABLED(CONFIG_4xx) || IS_ENABLED(CONFIG_BOOKE)) - pr_cont("DEAR: "REG" ESR: "REG" ", regs->dar, regs->dsisr); + if (IS_ENABLED(CONFIG_BOOKE)) + pr_cont("DEAR: "REG" ESR: "REG" ", regs->dear, regs->esr); else pr_cont("DAR: "REG" DSISR: %08lx ", regs->dar, regs->dsisr); } @@ -1566,10 +1639,17 @@ void arch_setup_new_exec(void) current->thread.regs->amr = default_amr; current->thread.regs->iamr = default_iamr; #endif + +#ifdef CONFIG_PPC_BOOK3S_64 + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + current->thread.dexcr = current->thread.dexcr_onexec; + mtspr(SPRN_DEXCR, current->thread.dexcr); + } +#endif /* CONFIG_PPC_BOOK3S_64 */ } #ifdef CONFIG_PPC64 -/** +/* * Assign a TIDR (thread ID) for task @t and set it in the thread * structure. For now, we only support setting TIDR for 'current' task. * @@ -1579,7 +1659,7 @@ void arch_setup_new_exec(void) * cases will happen: * * 1. The correct thread is running, the wrong thread is not - * In this situation, the correct thread is woken and proceeds to pass it's + * In this situation, the correct thread is woken and proceeds to pass its * condition check. * * 2. Neither threads are running @@ -1589,15 +1669,15 @@ void arch_setup_new_exec(void) * for the wrong thread, or they will execute the condition check immediately. * * 3. The wrong thread is running, the correct thread is not - * The wrong thread will be woken, but will fail it's condition check and + * The wrong thread will be woken, but will fail its condition check and * re-execute wait. The correct thread, when scheduled, will execute either - * it's condition check (which will pass), or wait, which returns immediately - * when called the first time after the thread is scheduled, followed by it's + * its condition check (which will pass), or wait, which returns immediately + * when called the first time after the thread is scheduled, followed by its * condition check (which will pass). * * 4. Both threads are running - * Both threads will be woken. The wrong thread will fail it's condition check - * and execute another wait, while the correct thread will pass it's condition + * Both threads will be woken. The wrong thread will fail its condition check + * and execute another wait, while the correct thread will pass its condition * check. * * @t: the task to set the thread ID for @@ -1622,11 +1702,6 @@ EXPORT_SYMBOL_GPL(set_thread_tidr); #endif /* CONFIG_PPC64 */ -void -release_thread(struct task_struct *t) -{ -} - /* * this gets called so that we can store coprocessor state into memory and * copy the current task into the new thread. @@ -1655,7 +1730,7 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) static void setup_ksp_vsid(struct task_struct *p, unsigned long sp) { -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU unsigned long sp_vsid; unsigned long llp = mmu_psize_defs[mmu_linear_psize].sllp; @@ -1680,65 +1755,85 @@ static void setup_ksp_vsid(struct task_struct *p, unsigned long sp) /* * Copy architecture-specific thread state */ -int copy_thread(unsigned long clone_flags, unsigned long usp, - unsigned long kthread_arg, struct task_struct *p, - unsigned long tls) +int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { - struct pt_regs *childregs, *kregs; + struct pt_regs *kregs; /* Switch frame regs */ extern void ret_from_fork(void); extern void ret_from_fork_scv(void); - extern void ret_from_kernel_thread(void); + extern void ret_from_kernel_user_thread(void); + extern void start_kernel_thread(void); void (*f)(void); unsigned long sp = (unsigned long)task_stack_page(p) + THREAD_SIZE; - struct thread_info *ti = task_thread_info(p); #ifdef CONFIG_HAVE_HW_BREAKPOINT int i; #endif klp_init_thread_info(p); - /* Copy registers */ - sp -= sizeof(struct pt_regs); - childregs = (struct pt_regs *) sp; - if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { + if (unlikely(p->flags & PF_KTHREAD)) { /* kernel thread */ - memset(childregs, 0, sizeof(struct pt_regs)); - childregs->gpr[1] = sp + sizeof(struct pt_regs); - /* function */ - if (usp) - childregs->gpr[14] = ppc_function_entry((void *)usp); -#ifdef CONFIG_PPC64 - clear_tsk_thread_flag(p, TIF_32BIT); - childregs->softe = IRQS_ENABLED; -#endif - childregs->gpr[15] = kthread_arg; + + /* Create initial minimum stack frame. */ + sp -= STACK_FRAME_MIN_SIZE; + ((unsigned long *)sp)[0] = 0; + + f = start_kernel_thread; p->thread.regs = NULL; /* no user register state */ - ti->flags |= _TIF_RESTOREALL; - f = ret_from_kernel_thread; + clear_tsk_compat_task(p); } else { /* user thread */ - struct pt_regs *regs = current_pt_regs(); - *childregs = *regs; - if (usp) - childregs->gpr[1] = usp; - p->thread.regs = childregs; - /* 64s sets this in ret_from_fork */ - if (!IS_ENABLED(CONFIG_PPC_BOOK3S_64)) - childregs->gpr[3] = 0; /* Result from fork() */ - if (clone_flags & CLONE_SETTLS) { - if (!is_32bit_task()) - childregs->gpr[13] = tls; + struct pt_regs *childregs; + + /* Create initial user return stack frame. */ + sp -= STACK_USER_INT_FRAME_SIZE; + *(unsigned long *)(sp + STACK_INT_FRAME_MARKER) = STACK_FRAME_REGS_MARKER; + + childregs = (struct pt_regs *)(sp + STACK_INT_FRAME_REGS); + + if (unlikely(args->fn)) { + /* + * A user space thread, but it first runs a kernel + * thread, and then returns as though it had called + * execve rather than fork, so user regs will be + * filled in (e.g., by kernel_execve()). + */ + ((unsigned long *)sp)[0] = 0; + memset(childregs, 0, sizeof(struct pt_regs)); +#ifdef CONFIG_PPC64 + childregs->softe = IRQS_ENABLED; +#endif + f = ret_from_kernel_user_thread; + } else { + struct pt_regs *regs = current_pt_regs(); + u64 clone_flags = args->flags; + unsigned long usp = args->stack; + + /* Copy registers */ + *childregs = *regs; + if (usp) + childregs->gpr[1] = usp; + ((unsigned long *)sp)[0] = childregs->gpr[1]; +#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG + WARN_ON_ONCE(childregs->softe != IRQS_ENABLED); +#endif + if (clone_flags & CLONE_SETTLS) { + unsigned long tls = args->tls; + + if (!is_32bit_task()) + childregs->gpr[13] = tls; + else + childregs->gpr[2] = tls; + } + + if (trap_is_scv(regs)) + f = ret_from_fork_scv; else - childregs->gpr[2] = tls; + f = ret_from_fork; } - if (trap_is_scv(regs)) - f = ret_from_fork_scv; - else - f = ret_from_fork; + childregs->msr &= ~(MSR_FP|MSR_VEC|MSR_VSX); + p->thread.regs = childregs; } - childregs->msr &= ~(MSR_FP|MSR_VEC|MSR_VSX); - sp -= STACK_FRAME_OVERHEAD; /* * The way this works is that at some point in the future @@ -1748,11 +1843,22 @@ 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; + ((unsigned long *)sp)[STACK_FRAME_LR_SAVE] = (unsigned long)f; + sp -= STACK_SWITCH_FRAME_SIZE; + ((unsigned long *)sp)[0] = sp + STACK_SWITCH_FRAME_SIZE; + kregs = (struct pt_regs *)(sp + STACK_SWITCH_FRAME_REGS); + kregs->nip = ppc_function_entry(f); + if (unlikely(args->fn)) { + /* + * Put kthread fn, arg parameters in non-volatile GPRs in the + * switch frame so they are loaded by _switch before it returns + * to ret_from_kernel_thread. + */ + kregs->gpr[14] = ppc_function_entry((void *)args->fn); + kregs->gpr[15] = (unsigned long)args->fn_arg; + } p->thread.ksp = sp; + #ifdef CONFIG_HAVE_HW_BREAKPOINT for (i = 0; i < nr_wp_slots(); i++) p->thread.ptrace_bps[i] = NULL; @@ -1767,6 +1873,9 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, #if defined(CONFIG_PPC_BOOK3S_32) && defined(CONFIG_PPC_KUAP) p->thread.kuap = KUAP_NONE; #endif +#if defined(CONFIG_BOOKE) && defined(CONFIG_PPC_KUAP) + p->thread.pid = MMU_NO_CONTEXT; +#endif setup_ksp_vsid(p, sp); @@ -1775,27 +1884,19 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, p->thread.dscr_inherit = current->thread.dscr_inherit; p->thread.dscr = mfspr(SPRN_DSCR); } - if (cpu_has_feature(CPU_FTR_HAS_PPR)) - childregs->ppr = DEFAULT_PPR; p->thread.tidr = 0; #endif - /* - * Run with the current AMR value of the kernel - */ -#ifdef CONFIG_PPC_PKEY - if (mmu_has_feature(MMU_FTR_BOOK3S_KUAP)) - kregs->amr = AMR_KUAP_BLOCKED; +#ifdef CONFIG_PPC_BOOK3S_64 + if (cpu_has_feature(CPU_FTR_DEXCR_NPHIE)) + p->thread.hashkeyr = current->thread.hashkeyr; - if (mmu_has_feature(MMU_FTR_BOOK3S_KUEP)) - kregs->iamr = AMR_KUEP_BLOCKED; + if (cpu_has_feature(CPU_FTR_ARCH_31)) + p->thread.dexcr = mfspr(SPRN_DEXCR); #endif - kregs->nip = ppc_function_entry(f); return 0; } -void preload_new_slb_context(unsigned long start, unsigned long sp); - /* * Set up a thread for executing a new program */ @@ -1803,9 +1904,6 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp) { #ifdef CONFIG_PPC64 unsigned long load_addr = regs->gpr[2]; /* saved by ELF_PLAT_INIT */ - - if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && !radix_enabled()) - preload_new_slb_context(start, sp); #endif #ifdef CONFIG_PPC_TRANSACTIONAL_MEM @@ -1818,7 +1916,7 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp) tm_reclaim_current(0); #endif - memset(regs->gpr, 0, sizeof(regs->gpr)); + memset(®s->gpr[1], 0, sizeof(regs->gpr) - sizeof(regs->gpr[0])); regs->ctr = 0; regs->link = 0; regs->xer = 0; @@ -1857,8 +1955,8 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp) * 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); + 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. @@ -1907,6 +2005,12 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp) current->thread.tm_tfiar = 0; current->thread.load_tm = 0; #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ +#ifdef CONFIG_PPC_BOOK3S_64 + if (cpu_has_feature(CPU_FTR_DEXCR_NPHIE)) { + current->thread.hashkeyr = get_random_long(); + mtspr(SPRN_HASHKEYR, current->thread.hashkeyr); + } +#endif /* CONFIG_PPC_BOOK3S_64 */ } EXPORT_SYMBOL(start_thread); @@ -2052,6 +2156,9 @@ static inline int valid_irq_stack(unsigned long sp, struct task_struct *p, unsigned long stack_page; unsigned long cpu = task_cpu(p); + if (!hardirq_ctx[cpu] || !softirq_ctx[cpu]) + return 0; + stack_page = (unsigned long)hardirq_ctx[cpu]; if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes) return 1; @@ -2063,16 +2170,24 @@ static inline int valid_irq_stack(unsigned long sp, struct task_struct *p, return 0; } +#ifdef CONFIG_PPC64 static inline int valid_emergency_stack(unsigned long sp, struct task_struct *p, unsigned long nbytes) { -#ifdef CONFIG_PPC64 unsigned long stack_page; unsigned long cpu = task_cpu(p); if (!paca_ptrs) return 0; + if (!paca_ptrs[cpu]->emergency_sp) + return 0; + +# ifdef CONFIG_PPC_BOOK3S_64 + if (!paca_ptrs[cpu]->nmi_emergency_sp || !paca_ptrs[cpu]->mc_emergency_sp) + return 0; +#endif + stack_page = (unsigned long)paca_ptrs[cpu]->emergency_sp - THREAD_SIZE; if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes) return 1; @@ -2086,14 +2201,33 @@ static inline int valid_emergency_stack(unsigned long sp, struct task_struct *p, if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes) return 1; # endif -#endif return 0; } +#else +static inline int valid_emergency_stack(unsigned long sp, struct task_struct *p, + unsigned long nbytes) +{ + unsigned long stack_page; + unsigned long cpu = task_cpu(p); + + if (!IS_ENABLED(CONFIG_VMAP_STACK)) + return 0; + + stack_page = (unsigned long)emergency_ctx[cpu] - THREAD_SIZE; + if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes) + return 1; + return 0; +} +#endif -int validate_sp(unsigned long sp, struct task_struct *p, - unsigned long nbytes) +/* + * validate the stack frame of a particular minimum size, used for when we are + * looking at a certain object in the stack beyond the minimum. + */ +int validate_sp_size(unsigned long sp, struct task_struct *p, + unsigned long nbytes) { unsigned long stack_page = (unsigned long)task_stack_page(p); @@ -2109,27 +2243,26 @@ int validate_sp(unsigned long sp, struct task_struct *p, return valid_emergency_stack(sp, p, nbytes); } -EXPORT_SYMBOL(validate_sp); +int validate_sp(unsigned long sp, struct task_struct *p) +{ + return validate_sp_size(sp, p, STACK_FRAME_MIN_SIZE); +} -static unsigned long __get_wchan(struct task_struct *p) +static unsigned long ___get_wchan(struct task_struct *p) { unsigned long ip, sp; int count = 0; - if (!p || p == current || task_is_running(p)) - return 0; - sp = p->thread.ksp; - if (!validate_sp(sp, p, STACK_FRAME_OVERHEAD)) + if (!validate_sp(sp, p)) return 0; do { - sp = *(unsigned long *)sp; - if (!validate_sp(sp, p, STACK_FRAME_OVERHEAD) || - task_is_running(p)) + sp = READ_ONCE_NOCHECK(*(unsigned long *)sp); + if (!validate_sp(sp, p) || task_is_running(p)) return 0; if (count > 0) { - ip = ((unsigned long *)sp)[STACK_FRAME_LR_SAVE]; + ip = READ_ONCE_NOCHECK(((unsigned long *)sp)[STACK_FRAME_LR_SAVE]); if (!in_sched_functions(ip)) return ip; } @@ -2137,20 +2270,36 @@ static unsigned long __get_wchan(struct task_struct *p) return 0; } -unsigned long get_wchan(struct task_struct *p) +unsigned long __get_wchan(struct task_struct *p) { unsigned long ret; if (!try_get_task_stack(p)) return 0; - ret = __get_wchan(p); + ret = ___get_wchan(p); put_task_stack(p); return ret; } +static bool empty_user_regs(struct pt_regs *regs, struct task_struct *tsk) +{ + unsigned long stack_page; + + // A non-empty pt_regs should never have a zero MSR or TRAP value. + if (regs->msr || regs->trap) + return false; + + // Check it sits at the very base of the stack + stack_page = (unsigned long)task_stack_page(tsk); + if ((unsigned long)(regs + 1) != stack_page + THREAD_SIZE) + return false; + + return true; +} + static int kstack_depth_to_print = CONFIG_PRINT_STACK_DEPTH; void __no_sanitize_address show_stack(struct task_struct *tsk, @@ -2180,7 +2329,7 @@ void __no_sanitize_address show_stack(struct task_struct *tsk, lr = 0; printk("%sCall Trace:\n", loglvl); do { - if (!validate_sp(sp, tsk, STACK_FRAME_OVERHEAD)) + if (!validate_sp(sp, tsk)) break; stack = (unsigned long *) sp; @@ -2201,19 +2350,27 @@ void __no_sanitize_address show_stack(struct task_struct *tsk, /* * See if this is an exception frame. - * We look for the "regshere" marker in the current frame. + * We look for the "regs" marker in the current frame. + * + * STACK_SWITCH_FRAME_SIZE being the smallest frame that + * could hold a pt_regs, if that does not fit then it can't + * have regs. */ - if (validate_sp(sp, tsk, STACK_FRAME_WITH_PT_REGS) - && stack[STACK_FRAME_MARKER] == STACK_FRAME_REGS_MARKER) { + if (validate_sp_size(sp, tsk, STACK_SWITCH_FRAME_SIZE) + && stack[STACK_INT_FRAME_MARKER_LONGS] == STACK_FRAME_REGS_MARKER) { struct pt_regs *regs = (struct pt_regs *) - (sp + STACK_FRAME_OVERHEAD); + (sp + STACK_INT_FRAME_REGS); lr = regs->link; - printk("%s--- interrupt: %lx at %pS\n", + printk("%s---- interrupt: %lx at %pS\n", loglvl, regs->trap, (void *)regs->nip); - __show_regs(regs); - printk("%s--- interrupt: %lx\n", - loglvl, regs->trap); + + // Detect the case of an empty pt_regs at the very base + // of the stack and suppress showing it in full. + if (!empty_user_regs(regs, tsk)) { + __show_regs(regs); + printk("%s---- interrupt: %lx\n", loglvl, regs->trap); + } firstframe = 1; } @@ -2274,46 +2431,6 @@ void notrace __ppc64_runlatch_off(void) unsigned long arch_align_stack(unsigned long sp) { if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space) - sp -= get_random_int() & ~PAGE_MASK; + sp -= get_random_u32_below(PAGE_SIZE); return sp & ~0xf; } - -static inline unsigned long brk_rnd(void) -{ - unsigned long rnd = 0; - - /* 8MB for 32bit, 1GB for 64bit */ - if (is_32bit_task()) - rnd = (get_random_long() % (1UL<<(23-PAGE_SHIFT))); - else - rnd = (get_random_long() % (1UL<<(30-PAGE_SHIFT))); - - return rnd << PAGE_SHIFT; -} - -unsigned long arch_randomize_brk(struct mm_struct *mm) -{ - unsigned long base = mm->brk; - unsigned long ret; - -#ifdef CONFIG_PPC_BOOK3S_64 - /* - * If we are using 1TB segments and we are allowed to randomise - * the heap, we can put it above 1TB so it is backed by a 1TB - * segment. Otherwise the heap will be in the bottom 1TB - * which always uses 256MB segments and this may result in a - * performance penalty. We don't need to worry about radix. For - * radix, mmu_highuser_ssize remains unchanged from 256MB. - */ - if (!is_32bit_task() && (mmu_highuser_ssize == MMU_SEGSIZE_1T)) - base = max_t(unsigned long, mm->brk, 1UL << SID_SHIFT_1T); -#endif - - ret = PAGE_ALIGN(base + brk_rnd()); - - if (ret < mm->brk) - return mm->brk; - - return ret; -} - |