diff options
Diffstat (limited to 'arch/powerpc')
24 files changed, 244 insertions, 231 deletions
diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index c9aac24b02e2..0554ab062bdc 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -86,8 +86,8 @@ static inline bool arch_irqs_disabled(void) } #ifdef CONFIG_PPC_BOOK3E -#define __hard_irq_enable() asm volatile("wrteei 1" : : : "memory"); -#define __hard_irq_disable() asm volatile("wrteei 0" : : : "memory"); +#define __hard_irq_enable() asm volatile("wrteei 1" : : : "memory") +#define __hard_irq_disable() asm volatile("wrteei 0" : : : "memory") #else #define __hard_irq_enable() __mtmsrd(local_paca->kernel_msr | MSR_EE, 1) #define __hard_irq_disable() __mtmsrd(local_paca->kernel_msr, 1) @@ -100,6 +100,14 @@ static inline void hard_irq_disable(void) get_paca()->irq_happened |= PACA_IRQ_HARD_DIS; } +/* include/linux/interrupt.h needs hard_irq_disable to be a macro */ +#define hard_irq_disable hard_irq_disable + +static inline bool lazy_irq_pending(void) +{ + return !!(get_paca()->irq_happened & ~PACA_IRQ_HARD_DIS); +} + /* * This is called by asynchronous interrupts to conditionally * re-enable hard interrupts when soft-disabled after having @@ -117,6 +125,8 @@ static inline bool arch_irq_disabled_regs(struct pt_regs *regs) return !regs->softe; } +extern bool prep_irq_for_idle(void); + #else /* CONFIG_PPC64 */ #define SET_MSR_EE(x) mtmsr(x) diff --git a/arch/powerpc/include/asm/posix_types.h b/arch/powerpc/include/asm/posix_types.h index f1393252bbda..2958c5b97b2d 100644 --- a/arch/powerpc/include/asm/posix_types.h +++ b/arch/powerpc/include/asm/posix_types.h @@ -16,9 +16,6 @@ typedef int __kernel_ssize_t; typedef long __kernel_ptrdiff_t; #define __kernel_size_t __kernel_size_t -typedef unsigned short __kernel_nlink_t; -#define __kernel_nlink_t __kernel_nlink_t - typedef short __kernel_ipc_pid_t; #define __kernel_ipc_pid_t __kernel_ipc_pid_t #endif diff --git a/arch/powerpc/include/asm/stat.h b/arch/powerpc/include/asm/stat.h index e4edc510b530..84880b80cc1c 100644 --- a/arch/powerpc/include/asm/stat.h +++ b/arch/powerpc/include/asm/stat.h @@ -30,11 +30,11 @@ struct stat { unsigned long st_dev; ino_t st_ino; #ifdef __powerpc64__ - nlink_t st_nlink; + unsigned long st_nlink; mode_t st_mode; #else mode_t st_mode; - nlink_t st_nlink; + unsigned short st_nlink; #endif uid_t st_uid; gid_t st_gid; diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index a556ccc16b58..68831e9cf82f 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -140,7 +140,23 @@ static inline void set_restore_sigmask(void) { struct thread_info *ti = current_thread_info(); ti->local_flags |= _TLF_RESTORE_SIGMASK; - set_bit(TIF_SIGPENDING, &ti->flags); + WARN_ON(!test_bit(TIF_SIGPENDING, &ti->flags)); +} +static inline void clear_restore_sigmask(void) +{ + current_thread_info()->local_flags &= ~_TLF_RESTORE_SIGMASK; +} +static inline bool test_restore_sigmask(void) +{ + return current_thread_info()->local_flags & _TLF_RESTORE_SIGMASK; +} +static inline bool test_and_clear_restore_sigmask(void) +{ + struct thread_info *ti = current_thread_info(); + if (!(ti->local_flags & _TLF_RESTORE_SIGMASK)) + return false; + ti->local_flags &= ~_TLF_RESTORE_SIGMASK; + return true; } static inline bool test_thread_local_flags(unsigned int flags) diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index ed1718feb9d9..5971c85df136 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -558,27 +558,54 @@ _GLOBAL(ret_from_except_lite) mtmsrd r10,1 /* Update machine state */ #endif /* CONFIG_PPC_BOOK3E */ -#ifdef CONFIG_PREEMPT clrrdi r9,r1,THREAD_SHIFT /* current_thread_info() */ - li r0,_TIF_NEED_RESCHED /* bits to check */ ld r3,_MSR(r1) ld r4,TI_FLAGS(r9) - /* Move MSR_PR bit in r3 to _TIF_SIGPENDING position in r0 */ - rlwimi r0,r3,32+TIF_SIGPENDING-MSR_PR_LG,_TIF_SIGPENDING - and. r0,r4,r0 /* check NEED_RESCHED and maybe SIGPENDING */ - bne do_work - -#else /* !CONFIG_PREEMPT */ - ld r3,_MSR(r1) /* Returning to user mode? */ andi. r3,r3,MSR_PR - beq restore /* if not, just restore regs and return */ + beq resume_kernel /* Check current_thread_info()->flags */ + andi. r0,r4,_TIF_USER_WORK_MASK + beq restore + + andi. r0,r4,_TIF_NEED_RESCHED + beq 1f + bl .restore_interrupts + bl .schedule + b .ret_from_except_lite + +1: bl .save_nvgprs + bl .restore_interrupts + addi r3,r1,STACK_FRAME_OVERHEAD + bl .do_notify_resume + b .ret_from_except + +resume_kernel: +#ifdef CONFIG_PREEMPT + /* Check if we need to preempt */ + andi. r0,r4,_TIF_NEED_RESCHED + beq+ restore + /* Check that preempt_count() == 0 and interrupts are enabled */ + lwz r8,TI_PREEMPT(r9) + cmpwi cr1,r8,0 + ld r0,SOFTE(r1) + cmpdi r0,0 + crandc eq,cr1*4+eq,eq + bne restore + + /* + * Here we are preempting the current task. We want to make + * sure we are soft-disabled first + */ + SOFT_DISABLE_INTS(r3,r4) +1: bl .preempt_schedule_irq + + /* Re-test flags and eventually loop */ clrrdi r9,r1,THREAD_SHIFT ld r4,TI_FLAGS(r9) - andi. r0,r4,_TIF_USER_WORK_MASK - bne do_work -#endif /* !CONFIG_PREEMPT */ + andi. r0,r4,_TIF_NEED_RESCHED + bne 1b +#endif /* CONFIG_PREEMPT */ .globl fast_exc_return_irq fast_exc_return_irq: @@ -759,50 +786,6 @@ restore_check_irq_replay: #endif /* CONFIG_PPC_BOOK3E */ 1: b .ret_from_except /* What else to do here ? */ - - -3: -do_work: -#ifdef CONFIG_PREEMPT - andi. r0,r3,MSR_PR /* Returning to user mode? */ - bne user_work - /* Check that preempt_count() == 0 and interrupts are enabled */ - lwz r8,TI_PREEMPT(r9) - cmpwi cr1,r8,0 - ld r0,SOFTE(r1) - cmpdi r0,0 - crandc eq,cr1*4+eq,eq - bne restore - - /* - * Here we are preempting the current task. We want to make - * sure we are soft-disabled first - */ - SOFT_DISABLE_INTS(r3,r4) -1: bl .preempt_schedule_irq - - /* Re-test flags and eventually loop */ - clrrdi r9,r1,THREAD_SHIFT - ld r4,TI_FLAGS(r9) - andi. r0,r4,_TIF_NEED_RESCHED - bne 1b - b restore - -user_work: -#endif /* CONFIG_PREEMPT */ - - andi. r0,r4,_TIF_NEED_RESCHED - beq 1f - bl .restore_interrupts - bl .schedule - b .ret_from_except_lite - -1: bl .save_nvgprs - bl .restore_interrupts - addi r3,r1,STACK_FRAME_OVERHEAD - bl .do_notify_resume - b .ret_from_except - unrecov_restore: addi r3,r1,STACK_FRAME_OVERHEAD bl .unrecoverable_exception diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 7835a5e1ea5f..1f017bb7a7ce 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -229,7 +229,7 @@ notrace void arch_local_irq_restore(unsigned long en) */ if (unlikely(irq_happened != PACA_IRQ_HARD_DIS)) __hard_irq_disable(); -#ifdef CONFIG_TRACE_IRQFLAG +#ifdef CONFIG_TRACE_IRQFLAGS else { /* * We should already be hard disabled here. We had bugs @@ -277,7 +277,7 @@ EXPORT_SYMBOL(arch_local_irq_restore); * NOTE: This is called with interrupts hard disabled but not marked * as such in paca->irq_happened, so we need to resync this. */ -void restore_interrupts(void) +void notrace restore_interrupts(void) { if (irqs_disabled()) { local_paca->irq_happened |= PACA_IRQ_HARD_DIS; @@ -286,6 +286,52 @@ void restore_interrupts(void) __hard_irq_enable(); } +/* + * This is a helper to use when about to go into idle low-power + * when the latter has the side effect of re-enabling interrupts + * (such as calling H_CEDE under pHyp). + * + * You call this function with interrupts soft-disabled (this is + * already the case when ppc_md.power_save is called). The function + * will return whether to enter power save or just return. + * + * In the former case, it will have notified lockdep of interrupts + * being re-enabled and generally sanitized the lazy irq state, + * and in the latter case it will leave with interrupts hard + * disabled and marked as such, so the local_irq_enable() call + * in cpu_idle() will properly re-enable everything. + */ +bool prep_irq_for_idle(void) +{ + /* + * First we need to hard disable to ensure no interrupt + * occurs before we effectively enter the low power state + */ + hard_irq_disable(); + + /* + * If anything happened while we were soft-disabled, + * we return now and do not enter the low power state. + */ + if (lazy_irq_pending()) + return false; + + /* Tell lockdep we are about to re-enable */ + trace_hardirqs_on(); + + /* + * Mark interrupts as soft-enabled and clear the + * PACA_IRQ_HARD_DIS from the pending mask since we + * are about to hard enable as well as a side effect + * of entering the low power state. + */ + local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS; + local_paca->soft_enabled = 1; + + /* Tell the caller to enter the low power state */ + return true; +} + #endif /* CONFIG_PPC64 */ int arch_show_interrupts(struct seq_file *p, int prec) diff --git a/arch/powerpc/kernel/module_32.c b/arch/powerpc/kernel/module_32.c index 0b6d79617d7b..2e3200ca485f 100644 --- a/arch/powerpc/kernel/module_32.c +++ b/arch/powerpc/kernel/module_32.c @@ -176,8 +176,8 @@ int module_frob_arch_sections(Elf32_Ehdr *hdr, static inline int entry_matches(struct ppc_plt_entry *entry, Elf32_Addr val) { - if (entry->jump[0] == 0x3d600000 + ((val + 0x8000) >> 16) - && entry->jump[1] == 0x396b0000 + (val & 0xffff)) + if (entry->jump[0] == 0x3d800000 + ((val + 0x8000) >> 16) + && entry->jump[1] == 0x398c0000 + (val & 0xffff)) return 1; return 0; } @@ -204,10 +204,9 @@ static uint32_t do_plt_call(void *location, entry++; } - /* Stolen from Paul Mackerras as well... */ - entry->jump[0] = 0x3d600000+((val+0x8000)>>16); /* lis r11,sym@ha */ - entry->jump[1] = 0x396b0000 + (val&0xffff); /* addi r11,r11,sym@l*/ - entry->jump[2] = 0x7d6903a6; /* mtctr r11 */ + entry->jump[0] = 0x3d800000+((val+0x8000)>>16); /* lis r12,sym@ha */ + entry->jump[1] = 0x398c0000 + (val&0xffff); /* addi r12,r12,sym@l*/ + entry->jump[2] = 0x7d8903a6; /* mtctr r12 */ entry->jump[3] = 0x4e800420; /* bctr */ DEBUGP("Initialized plt for 0x%x at %p\n", val, entry); diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 1b488e5305c5..0794a3017b1b 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -1312,7 +1312,7 @@ static struct opal_secondary_data { extern char opal_secondary_entry; -static void prom_query_opal(void) +static void __init prom_query_opal(void) { long rc; @@ -1436,7 +1436,7 @@ static void __init prom_opal_hold_cpus(void) prom_debug("prom_opal_hold_cpus: end...\n"); } -static void prom_opal_takeover(void) +static void __init prom_opal_takeover(void) { struct opal_secondary_data *data = &RELOC(opal_secondary_data); struct opal_takeover_args *args = &data->args; diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index 651c5963662b..5c023c9cf16e 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -51,16 +51,6 @@ void __user * get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, return (void __user *)newsp; } - -/* - * Restore the user process's signal mask - */ -void restore_sigmask(sigset_t *set) -{ - sigdelsetmask(set, ~_BLOCKABLE); - set_current_blocked(set); -} - static void check_syscall_restart(struct pt_regs *regs, struct k_sigaction *ka, int has_handler) { @@ -114,30 +104,21 @@ static void check_syscall_restart(struct pt_regs *regs, struct k_sigaction *ka, static int do_signal(struct pt_regs *regs) { - sigset_t *oldset; + sigset_t *oldset = sigmask_to_save(); siginfo_t info; int signr; struct k_sigaction ka; int ret; int is32 = is_32bit_task(); - if (current_thread_info()->local_flags & _TLF_RESTORE_SIGMASK) - oldset = ¤t->saved_sigmask; - else - oldset = ¤t->blocked; - signr = get_signal_to_deliver(&info, &ka, regs, NULL); /* Is there any syscall restart business here ? */ check_syscall_restart(regs, &ka, signr > 0); if (signr <= 0) { - struct thread_info *ti = current_thread_info(); /* No signal to deliver -- put the saved sigmask back */ - if (ti->local_flags & _TLF_RESTORE_SIGMASK) { - ti->local_flags &= ~_TLF_RESTORE_SIGMASK; - sigprocmask(SIG_SETMASK, ¤t->saved_sigmask, NULL); - } + restore_saved_sigmask(); regs->trap = 0; return 0; /* no signals delivered */ } @@ -167,18 +148,7 @@ static int do_signal(struct pt_regs *regs) regs->trap = 0; if (ret) { - block_sigmask(&ka, signr); - - /* - * A signal was successfully delivered; the saved sigmask is in - * its frame, and we can clear the TLF_RESTORE_SIGMASK flag. - */ - current_thread_info()->local_flags &= ~_TLF_RESTORE_SIGMASK; - - /* - * Let tracing know that we've done the handler setup. - */ - tracehook_signal_handler(signr, &info, &ka, regs, + signal_delivered(signr, &info, &ka, regs, test_thread_flag(TIF_SINGLESTEP)); } @@ -193,8 +163,6 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags) if (thread_info_flags & _TIF_NOTIFY_RESUME) { clear_thread_flag(TIF_NOTIFY_RESUME); tracehook_notify_resume(regs); - if (current->replacement_session_keyring) - key_replace_session_keyring(); } } diff --git a/arch/powerpc/kernel/signal.h b/arch/powerpc/kernel/signal.h index 8dde973aaaf5..e00acb413934 100644 --- a/arch/powerpc/kernel/signal.h +++ b/arch/powerpc/kernel/signal.h @@ -10,13 +10,10 @@ #ifndef _POWERPC_ARCH_SIGNAL_H #define _POWERPC_ARCH_SIGNAL_H -#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) - extern void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags); extern void __user * get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, int is_32); -extern void restore_sigmask(sigset_t *set); extern int handle_signal32(unsigned long sig, struct k_sigaction *ka, siginfo_t *info, sigset_t *oldset, diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 61f6aff25edc..8b4c049aee20 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -919,7 +919,7 @@ static int do_setcontext(struct ucontext __user *ucp, struct pt_regs *regs, int if (!access_ok(VERIFY_READ, mcp, sizeof(*mcp))) return -EFAULT; #endif - restore_sigmask(&set); + set_current_blocked(&set); if (restore_user_regs(regs, mcp, sig)) return -EFAULT; @@ -1273,7 +1273,7 @@ long sys_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8, set.sig[0] = sigctx.oldmask; set.sig[1] = sigctx._unused[3]; #endif - restore_sigmask(&set); + set_current_blocked(&set); sr = (struct mcontext __user *)from_user_ptr(sigctx.regs); addr = sr; diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 2692efdb154e..d183f8719a50 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -335,7 +335,7 @@ int sys_swapcontext(struct ucontext __user *old_ctx, if (__copy_from_user(&set, &new_ctx->uc_sigmask, sizeof(set))) do_exit(SIGSEGV); - restore_sigmask(&set); + set_current_blocked(&set); if (restore_sigcontext(regs, NULL, 0, &new_ctx->uc_mcontext)) do_exit(SIGSEGV); @@ -364,7 +364,7 @@ int sys_rt_sigreturn(unsigned long r3, unsigned long r4, unsigned long r5, if (__copy_from_user(&set, &uc->uc_sigmask, sizeof(set))) goto badframe; - restore_sigmask(&set); + set_current_blocked(&set); if (restore_sigcontext(regs, NULL, 1, &uc->uc_mcontext)) goto badframe; diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 99a995c2a3f2..be171ee73bf8 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -475,6 +475,7 @@ void timer_interrupt(struct pt_regs * regs) struct pt_regs *old_regs; u64 *next_tb = &__get_cpu_var(decrementers_next_tb); struct clock_event_device *evt = &__get_cpu_var(decrementers); + u64 now; /* Ensure a positive value is written to the decrementer, or else * some CPUs will continue to take decrementer exceptions. @@ -509,9 +510,16 @@ void timer_interrupt(struct pt_regs * regs) irq_work_run(); } - *next_tb = ~(u64)0; - if (evt->event_handler) - evt->event_handler(evt); + now = get_tb_or_rtc(); + if (now >= *next_tb) { + *next_tb = ~(u64)0; + if (evt->event_handler) + evt->event_handler(evt); + } else { + now = *next_tb - now; + if (now <= DECREMENTER_MAX) + set_dec((int)now); + } #ifdef CONFIG_PPC64 /* collect purr register values often, for accurate calculations */ diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index c6af1d623839..3abe1b86e583 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -268,24 +268,45 @@ static unsigned long do_h_register_vpa(struct kvm_vcpu *vcpu, return err; } -static void kvmppc_update_vpa(struct kvm *kvm, struct kvmppc_vpa *vpap) +static void kvmppc_update_vpa(struct kvm_vcpu *vcpu, struct kvmppc_vpa *vpap) { + struct kvm *kvm = vcpu->kvm; void *va; unsigned long nb; + unsigned long gpa; - vpap->update_pending = 0; - va = NULL; - if (vpap->next_gpa) { - va = kvmppc_pin_guest_page(kvm, vpap->next_gpa, &nb); - if (nb < vpap->len) { - /* - * If it's now too short, it must be that userspace - * has changed the mappings underlying guest memory, - * so unregister the region. - */ + /* + * We need to pin the page pointed to by vpap->next_gpa, + * but we can't call kvmppc_pin_guest_page under the lock + * as it does get_user_pages() and down_read(). So we + * have to drop the lock, pin the page, then get the lock + * again and check that a new area didn't get registered + * in the meantime. + */ + for (;;) { + gpa = vpap->next_gpa; + spin_unlock(&vcpu->arch.vpa_update_lock); + va = NULL; + nb = 0; + if (gpa) + va = kvmppc_pin_guest_page(kvm, vpap->next_gpa, &nb); + spin_lock(&vcpu->arch.vpa_update_lock); + if (gpa == vpap->next_gpa) + break; + /* sigh... unpin that one and try again */ + if (va) kvmppc_unpin_guest_page(kvm, va); - va = NULL; - } + } + + vpap->update_pending = 0; + if (va && nb < vpap->len) { + /* + * If it's now too short, it must be that userspace + * has changed the mappings underlying guest memory, + * so unregister the region. + */ + kvmppc_unpin_guest_page(kvm, va); + va = NULL; } if (vpap->pinned_addr) kvmppc_unpin_guest_page(kvm, vpap->pinned_addr); @@ -296,20 +317,18 @@ static void kvmppc_update_vpa(struct kvm *kvm, struct kvmppc_vpa *vpap) static void kvmppc_update_vpas(struct kvm_vcpu *vcpu) { - struct kvm *kvm = vcpu->kvm; - spin_lock(&vcpu->arch.vpa_update_lock); if (vcpu->arch.vpa.update_pending) { - kvmppc_update_vpa(kvm, &vcpu->arch.vpa); + kvmppc_update_vpa(vcpu, &vcpu->arch.vpa); init_vpa(vcpu, vcpu->arch.vpa.pinned_addr); } if (vcpu->arch.dtl.update_pending) { - kvmppc_update_vpa(kvm, &vcpu->arch.dtl); + kvmppc_update_vpa(vcpu, &vcpu->arch.dtl); vcpu->arch.dtl_ptr = vcpu->arch.dtl.pinned_addr; vcpu->arch.dtl_index = 0; } if (vcpu->arch.slb_shadow.update_pending) - kvmppc_update_vpa(kvm, &vcpu->arch.slb_shadow); + kvmppc_update_vpa(vcpu, &vcpu->arch.slb_shadow); spin_unlock(&vcpu->arch.vpa_update_lock); } @@ -800,12 +819,39 @@ static int kvmppc_run_core(struct kvmppc_vcore *vc) struct kvm_vcpu *vcpu, *vcpu0, *vnext; long ret; u64 now; - int ptid, i; + int ptid, i, need_vpa_update; /* don't start if any threads have a signal pending */ - list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) + need_vpa_update = 0; + list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) { if (signal_pending(vcpu->arch.run_task)) return 0; + need_vpa_update |= vcpu->arch.vpa.update_pending | + vcpu->arch.slb_shadow.update_pending | + vcpu->arch.dtl.update_pending; + } + + /* + * Initialize *vc, in particular vc->vcore_state, so we can + * drop the vcore lock if necessary. + */ + vc->n_woken = 0; + vc->nap_count = 0; + vc->entry_exit_count = 0; + vc->vcore_state = VCORE_RUNNING; + vc->in_guest = 0; + vc->napping_threads = 0; + + /* + * Updating any of the vpas requires calling kvmppc_pin_guest_page, + * which can't be called with any spinlocks held. + */ + if (need_vpa_update) { + spin_unlock(&vc->lock); + list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) + kvmppc_update_vpas(vcpu); + spin_lock(&vc->lock); + } /* * Make sure we are running on thread 0, and that @@ -838,20 +884,10 @@ static int kvmppc_run_core(struct kvmppc_vcore *vc) if (vcpu->arch.ceded) vcpu->arch.ptid = ptid++; - vc->n_woken = 0; - vc->nap_count = 0; - vc->entry_exit_count = 0; - vc->vcore_state = VCORE_RUNNING; vc->stolen_tb += mftb() - vc->preempt_tb; - vc->in_guest = 0; vc->pcpu = smp_processor_id(); - vc->napping_threads = 0; list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) { kvmppc_start_thread(vcpu); - if (vcpu->arch.vpa.update_pending || - vcpu->arch.slb_shadow.update_pending || - vcpu->arch.dtl.update_pending) - kvmppc_update_vpas(vcpu); kvmppc_create_dtl_entry(vcpu, vc); } /* Grab any remaining hw threads so they can't go into the kernel */ diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index a84aafce2a12..a1044f43becd 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -810,7 +810,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) lwz r3,VCORE_NAPPING_THREADS(r5) lwz r4,VCPU_PTID(r9) li r0,1 - sldi r0,r0,r4 + sld r0,r0,r4 andc. r3,r3,r0 /* no sense IPI'ing ourselves */ beq 43f mulli r4,r4,PACA_SIZE /* get paca for thread 0 */ diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c index 3ff9013d6e79..ee02b30878ed 100644 --- a/arch/powerpc/kvm/book3s_pr_papr.c +++ b/arch/powerpc/kvm/book3s_pr_papr.c @@ -241,6 +241,7 @@ int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd) case H_PUT_TCE: return kvmppc_h_pr_put_tce(vcpu); case H_CEDE: + vcpu->arch.shared->msr |= MSR_EE; kvm_vcpu_block(vcpu); clear_bit(KVM_REQ_UNHALT, &vcpu->requests); vcpu->stat.halt_wakeup++; diff --git a/arch/powerpc/mm/mmu_context_nohash.c b/arch/powerpc/mm/mmu_context_nohash.c index 5b63bd3da4a9..e779642c25e5 100644 --- a/arch/powerpc/mm/mmu_context_nohash.c +++ b/arch/powerpc/mm/mmu_context_nohash.c @@ -333,9 +333,7 @@ static int __cpuinit mmu_context_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) { unsigned int cpu = (unsigned int)(long)hcpu; -#ifdef CONFIG_HOTPLUG_CPU - struct task_struct *p; -#endif + /* We don't touch CPU 0 map, it's allocated at aboot and kept * around forever */ @@ -358,12 +356,7 @@ static int __cpuinit mmu_context_cpu_notify(struct notifier_block *self, stale_map[cpu] = NULL; /* We also clear the cpu_vm_mask bits of CPUs going away */ - read_lock(&tasklist_lock); - for_each_process(p) { - if (p->mm) - cpumask_clear_cpu(cpu, mm_cpumask(p->mm)); - } - read_unlock(&tasklist_lock); + clear_tasks_mm_cpumask(cpu); break; #endif /* CONFIG_HOTPLUG_CPU */ } diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index b6edbb3b4a54..1e95556dc692 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -635,11 +635,11 @@ static inline int __init read_usm_ranges(const u32 **usm) */ static void __init parse_drconf_memory(struct device_node *memory) { - const u32 *dm, *usm; + const u32 *uninitialized_var(dm), *usm; unsigned int n, rc, ranges, is_kexec_kdump = 0; unsigned long lmb_size, base, size, sz; int nid; - struct assoc_arrays aa; + struct assoc_arrays aa = { .arrays = NULL }; n = of_get_drconf_memory(memory, &dm); if (!n) diff --git a/arch/powerpc/net/bpf_jit_64.S b/arch/powerpc/net/bpf_jit_64.S index 55ba3855a97f..7d3a3b5619a2 100644 --- a/arch/powerpc/net/bpf_jit_64.S +++ b/arch/powerpc/net/bpf_jit_64.S @@ -105,6 +105,7 @@ sk_load_byte_msh_positive_offset: mr r4, r_addr; \ li r6, SIZE; \ bl skb_copy_bits; \ + nop; \ /* R3 = 0 on success */ \ addi r1, r1, BPF_PPC_SLOWPATH_FRAME; \ ld r0, 16(r1); \ @@ -156,6 +157,7 @@ bpf_slow_path_byte_msh: mr r4, r_addr; \ li r5, SIZE; \ bl bpf_internal_load_pointer_neg_helper; \ + nop; \ /* R3 != 0 on success */ \ addi r1, r1, BPF_PPC_SLOWPATH_FRAME; \ ld r0, 16(r1); \ diff --git a/arch/powerpc/platforms/cell/pervasive.c b/arch/powerpc/platforms/cell/pervasive.c index efdacc829576..d17e98bc0c10 100644 --- a/arch/powerpc/platforms/cell/pervasive.c +++ b/arch/powerpc/platforms/cell/pervasive.c @@ -42,11 +42,9 @@ static void cbe_power_save(void) { unsigned long ctrl, thread_switch_control; - /* - * We need to hard disable interrupts, the local_irq_enable() done by - * our caller upon return will hard re-enable. - */ - hard_irq_disable(); + /* Ensure our interrupt state is properly tracked */ + if (!prep_irq_for_idle()) + return; ctrl = mfspr(SPRN_CTRLF); @@ -81,6 +79,9 @@ static void cbe_power_save(void) */ ctrl &= ~(CTRL_RUNLATCH | CTRL_TE); mtspr(SPRN_CTRLT, ctrl); + + /* Re-enable interrupts in MSR */ + __hard_irq_enable(); } static int cbe_system_reset_exception(struct pt_regs *regs) diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 0915b1ad66ce..2d311c0caf8e 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -106,7 +106,7 @@ static int tce_build_pSeries(struct iommu_table *tbl, long index, tcep++; } - if (tbl->it_type == TCE_PCI_SWINV_CREATE) + if (tbl->it_type & TCE_PCI_SWINV_CREATE) tce_invalidate_pSeries_sw(tbl, tces, tcep - 1); return 0; } @@ -121,7 +121,7 @@ static void tce_free_pSeries(struct iommu_table *tbl, long index, long npages) while (npages--) *(tcep++) = 0; - if (tbl->it_type == TCE_PCI_SWINV_FREE) + if (tbl->it_type & TCE_PCI_SWINV_FREE) tce_invalidate_pSeries_sw(tbl, tces, tcep - 1); } diff --git a/arch/powerpc/platforms/pseries/nvram.c b/arch/powerpc/platforms/pseries/nvram.c index 36f957f31842..8733a86ad52e 100644 --- a/arch/powerpc/platforms/pseries/nvram.c +++ b/arch/powerpc/platforms/pseries/nvram.c @@ -68,9 +68,7 @@ static const char *pseries_nvram_os_partitions[] = { }; static void oops_to_nvram(struct kmsg_dumper *dumper, - enum kmsg_dump_reason reason, - const char *old_msgs, unsigned long old_len, - const char *new_msgs, unsigned long new_len); + enum kmsg_dump_reason reason); static struct kmsg_dumper nvram_kmsg_dumper = { .dump = oops_to_nvram @@ -504,28 +502,6 @@ int __init pSeries_nvram_init(void) } /* - * Try to capture the last capture_len bytes of the printk buffer. Return - * the amount actually captured. - */ -static size_t capture_last_msgs(const char *old_msgs, size_t old_len, - const char *new_msgs, size_t new_len, - char *captured, size_t capture_len) -{ - if (new_len >= capture_len) { - memcpy(captured, new_msgs + (new_len - capture_len), - capture_len); - return capture_len; - } else { - /* Grab the end of old_msgs. */ - size_t old_tail_len = min(old_len, capture_len - new_len); - memcpy(captured, old_msgs + (old_len - old_tail_len), - old_tail_len); - memcpy(captured + old_tail_len, new_msgs, new_len); - return old_tail_len + new_len; - } -} - -/* * Are we using the ibm,rtas-log for oops/panic reports? And if so, * would logging this oops/panic overwrite an RTAS event that rtas_errd * hasn't had a chance to read and process? Return 1 if so, else 0. @@ -541,27 +517,6 @@ static int clobbering_unread_rtas_event(void) NVRAM_RTAS_READ_TIMEOUT); } -/* Squeeze out each line's <n> severity prefix. */ -static size_t elide_severities(char *buf, size_t len) -{ - char *in, *out, *buf_end = buf + len; - /* Assume a <n> at the very beginning marks the start of a line. */ - int newline = 1; - - in = out = buf; - while (in < buf_end) { - if (newline && in+3 <= buf_end && - *in == '<' && isdigit(in[1]) && in[2] == '>') { - in += 3; - newline = 0; - } else { - newline = (*in == '\n'); - *out++ = *in++; - } - } - return out - buf; -} - /* Derived from logfs_compress() */ static int nvram_compress(const void *in, void *out, size_t inlen, size_t outlen) @@ -619,9 +574,7 @@ static int zip_oops(size_t text_len) * partition. If that's too much, go back and capture uncompressed text. */ static void oops_to_nvram(struct kmsg_dumper *dumper, - enum kmsg_dump_reason reason, - const char *old_msgs, unsigned long old_len, - const char *new_msgs, unsigned long new_len) + enum kmsg_dump_reason reason) { static unsigned int oops_count = 0; static bool panicking = false; @@ -660,14 +613,14 @@ static void oops_to_nvram(struct kmsg_dumper *dumper, return; if (big_oops_buf) { - text_len = capture_last_msgs(old_msgs, old_len, - new_msgs, new_len, big_oops_buf, big_oops_buf_sz); - text_len = elide_severities(big_oops_buf, text_len); + kmsg_dump_get_buffer(dumper, false, + big_oops_buf, big_oops_buf_sz, &text_len); rc = zip_oops(text_len); } if (rc != 0) { - text_len = capture_last_msgs(old_msgs, old_len, - new_msgs, new_len, oops_data, oops_data_sz); + kmsg_dump_rewind(dumper); + kmsg_dump_get_buffer(dumper, true, + oops_data, oops_data_sz, &text_len); err_type = ERR_TYPE_KERNEL_PANIC; *oops_len = (u16) text_len; } diff --git a/arch/powerpc/platforms/pseries/processor_idle.c b/arch/powerpc/platforms/pseries/processor_idle.c index 41a34bc4a9a2..c71be66bd5dc 100644 --- a/arch/powerpc/platforms/pseries/processor_idle.c +++ b/arch/powerpc/platforms/pseries/processor_idle.c @@ -99,15 +99,18 @@ out: static void check_and_cede_processor(void) { /* - * Interrupts are soft-disabled at this point, - * but not hard disabled. So an interrupt might have - * occurred before entering NAP, and would be potentially - * lost (edge events, decrementer events, etc...) unless - * we first hard disable then check. + * Ensure our interrupt state is properly tracked, + * also checks if no interrupt has occurred while we + * were soft-disabled */ - hard_irq_disable(); - if (get_paca()->irq_happened == 0) + if (prep_irq_for_idle()) { cede_processor(); +#ifdef CONFIG_TRACE_IRQFLAGS + /* Ensure that H_CEDE returns with IRQs on */ + if (WARN_ON(!(mfmsr() & MSR_EE))) + __hard_irq_enable(); +#endif + } } static int dedicated_cede_loop(struct cpuidle_device *dev, diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 0f3ab06d2222..eab3492a45c5 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -971,7 +971,7 @@ static int cpu_cmd(void) /* print cpus waiting or in xmon */ printf("cpus stopped:"); count = 0; - for (cpu = 0; cpu < NR_CPUS; ++cpu) { + for_each_possible_cpu(cpu) { if (cpumask_test_cpu(cpu, &cpus_in_xmon)) { if (count == 0) printf(" %x", cpu); |