diff options
Diffstat (limited to 'arch/powerpc/kernel')
28 files changed, 607 insertions, 424 deletions
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index f5808a35688c..83afacd3ba7b 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -28,7 +28,7 @@ endif obj-y := cputable.o ptrace.o syscalls.o \ irq.o align.o signal_32.o pmc.o vdso.o \ - init_task.o process.o systbl.o idle.o \ + process.o systbl.o idle.o \ signal.o sysfs.o cacheinfo.o time.o \ prom.o traps.o setup-common.o \ udbg.o misc.o io.o dma.o \ diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 34b8afe94a50..4554dc2fe857 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -188,10 +188,6 @@ int main(void) DEFINE(SLBSHADOW_STACKESID, offsetof(struct slb_shadow, save_area[SLB_NUM_BOLTED - 1].esid)); DEFINE(SLBSHADOW_SAVEAREA, offsetof(struct slb_shadow, save_area)); - DEFINE(LPPACASRR0, offsetof(struct lppaca, saved_srr0)); - DEFINE(LPPACASRR1, offsetof(struct lppaca, saved_srr1)); - DEFINE(LPPACAANYINT, offsetof(struct lppaca, int_dword.any_int)); - DEFINE(LPPACADECRINT, offsetof(struct lppaca, int_dword.fields.decr_int)); DEFINE(LPPACA_PMCINUSE, offsetof(struct lppaca, pmcregs_in_use)); DEFINE(LPPACA_DTLIDX, offsetof(struct lppaca, dtl_idx)); DEFINE(LPPACA_YIELDCOUNT, offsetof(struct lppaca, yield_count)); diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c index 3f6464b4d970..bcfdcd22c766 100644 --- a/arch/powerpc/kernel/dma-iommu.c +++ b/arch/powerpc/kernel/dma-iommu.c @@ -17,7 +17,8 @@ * to the dma address (mapping) of the first page. */ static void *dma_iommu_alloc_coherent(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t flag) + dma_addr_t *dma_handle, gfp_t flag, + struct dma_attrs *attrs) { return iommu_alloc_coherent(dev, get_iommu_table_base(dev), size, dma_handle, dev->coherent_dma_mask, flag, @@ -25,7 +26,8 @@ static void *dma_iommu_alloc_coherent(struct device *dev, size_t size, } static void dma_iommu_free_coherent(struct device *dev, size_t size, - void *vaddr, dma_addr_t dma_handle) + void *vaddr, dma_addr_t dma_handle, + struct dma_attrs *attrs) { iommu_free_coherent(get_iommu_table_base(dev), size, vaddr, dma_handle); } @@ -105,8 +107,8 @@ static u64 dma_iommu_get_required_mask(struct device *dev) } struct dma_map_ops dma_iommu_ops = { - .alloc_coherent = dma_iommu_alloc_coherent, - .free_coherent = dma_iommu_free_coherent, + .alloc = dma_iommu_alloc_coherent, + .free = dma_iommu_free_coherent, .map_sg = dma_iommu_map_sg, .unmap_sg = dma_iommu_unmap_sg, .dma_supported = dma_iommu_dma_supported, diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c index 1ebc9189aada..4ab88dafb235 100644 --- a/arch/powerpc/kernel/dma-swiotlb.c +++ b/arch/powerpc/kernel/dma-swiotlb.c @@ -47,8 +47,8 @@ static u64 swiotlb_powerpc_get_required(struct device *dev) * for everything else. */ struct dma_map_ops swiotlb_dma_ops = { - .alloc_coherent = dma_direct_alloc_coherent, - .free_coherent = dma_direct_free_coherent, + .alloc = dma_direct_alloc_coherent, + .free = dma_direct_free_coherent, .map_sg = swiotlb_map_sg_attrs, .unmap_sg = swiotlb_unmap_sg_attrs, .dma_supported = swiotlb_dma_supported, diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c index 7d0233c12ee3..b1ec983dcec8 100644 --- a/arch/powerpc/kernel/dma.c +++ b/arch/powerpc/kernel/dma.c @@ -26,7 +26,8 @@ void *dma_direct_alloc_coherent(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t flag) + dma_addr_t *dma_handle, gfp_t flag, + struct dma_attrs *attrs) { void *ret; #ifdef CONFIG_NOT_COHERENT_CACHE @@ -54,7 +55,8 @@ void *dma_direct_alloc_coherent(struct device *dev, size_t size, } void dma_direct_free_coherent(struct device *dev, size_t size, - void *vaddr, dma_addr_t dma_handle) + void *vaddr, dma_addr_t dma_handle, + struct dma_attrs *attrs) { #ifdef CONFIG_NOT_COHERENT_CACHE __dma_free_coherent(size, vaddr); @@ -150,8 +152,8 @@ static inline void dma_direct_sync_single(struct device *dev, #endif struct dma_map_ops dma_direct_ops = { - .alloc_coherent = dma_direct_alloc_coherent, - .free_coherent = dma_direct_free_coherent, + .alloc = dma_direct_alloc_coherent, + .free = dma_direct_free_coherent, .map_sg = dma_direct_map_sg, .unmap_sg = dma_direct_unmap_sg, .dma_supported = dma_direct_dma_supported, diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 3e57a00b8cba..ba3aeb4bc06a 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -206,40 +206,43 @@ reenable_mmu: /* re-enable mmu so we can */ andi. r10,r10,MSR_EE /* Did EE change? */ beq 1f - /* Save handler and return address into the 2 unused words - * of the STACK_FRAME_OVERHEAD (sneak sneak sneak). Everything - * else can be recovered from the pt_regs except r3 which for - * normal interrupts has been set to pt_regs and for syscalls - * is an argument, so we temporarily use ORIG_GPR3 to save it - */ - stw r9,8(r1) - stw r11,12(r1) - stw r3,ORIG_GPR3(r1) /* * The trace_hardirqs_off will use CALLER_ADDR0 and CALLER_ADDR1. * If from user mode there is only one stack frame on the stack, and * accessing CALLER_ADDR1 will cause oops. So we need create a dummy * stack frame to make trace_hardirqs_off happy. + * + * This is handy because we also need to save a bunch of GPRs, + * r3 can be different from GPR3(r1) at this point, r9 and r11 + * contains the old MSR and handler address respectively, + * r4 & r5 can contain page fault arguments that need to be passed + * along as well. r12, CCR, CTR, XER etc... are left clobbered as + * they aren't useful past this point (aren't syscall arguments), + * the rest is restored from the exception frame. */ + stwu r1,-32(r1) + stw r9,8(r1) + stw r11,12(r1) + stw r3,16(r1) + stw r4,20(r1) + stw r5,24(r1) andi. r12,r12,MSR_PR - beq 11f - stwu r1,-16(r1) + b 11f bl trace_hardirqs_off - addi r1,r1,16 b 12f - 11: bl trace_hardirqs_off 12: + lwz r5,24(r1) + lwz r4,20(r1) + lwz r3,16(r1) + lwz r11,12(r1) + lwz r9,8(r1) + addi r1,r1,32 lwz r0,GPR0(r1) - lwz r3,ORIG_GPR3(r1) - lwz r4,GPR4(r1) - lwz r5,GPR5(r1) lwz r6,GPR6(r1) lwz r7,GPR7(r1) lwz r8,GPR8(r1) - lwz r9,8(r1) - lwz r11,12(r1) 1: mtctr r11 mtlr r9 bctr /* jump to handler */ diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index f8a7a1a1a9f4..ed1718feb9d9 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -63,15 +63,9 @@ system_call_common: std r0,GPR0(r1) std r10,GPR1(r1) ACCOUNT_CPU_USER_ENTRY(r10, r11) - /* - * This "crclr so" clears CR0.SO, which is the error indication on - * return from this system call. There must be no cmp instruction - * between it and the "mfcr r9" below, otherwise if XER.SO is set, - * CR0.SO will get set, causing all system calls to appear to fail. - */ - crclr so std r2,GPR2(r1) std r3,GPR3(r1) + mfcr r2 std r4,GPR4(r1) std r5,GPR5(r1) std r6,GPR6(r1) @@ -82,18 +76,20 @@ system_call_common: std r11,GPR10(r1) std r11,GPR11(r1) std r11,GPR12(r1) + std r11,_XER(r1) + std r11,_CTR(r1) std r9,GPR13(r1) - mfcr r9 mflr r10 + /* + * This clears CR0.SO (bit 28), which is the error indication on + * return from this system call. + */ + rldimi r2,r11,28,(63-28) li r11,0xc01 - std r9,_CCR(r1) std r10,_LINK(r1) std r11,_TRAP(r1) - mfxer r9 - mfctr r10 - std r9,_XER(r1) - std r10,_CTR(r1) std r3,ORIG_GPR3(r1) + std r2,_CCR(r1) ld r2,PACATOC(r13) addi r9,r1,STACK_FRAME_OVERHEAD ld r11,exception_marker@toc(r2) @@ -154,7 +150,7 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR) ld r10,TI_FLAGS(r11) andi. r11,r10,_TIF_SYSCALL_T_OR_A bne- syscall_dotrace -syscall_dotrace_cont: +.Lsyscall_dotrace_cont: cmpldi 0,r0,NR_syscalls bge- syscall_enosys @@ -211,7 +207,7 @@ syscall_exit: cmpld r3,r11 ld r5,_CCR(r1) bge- syscall_error -syscall_error_cont: +.Lsyscall_error_cont: ld r7,_NIP(r1) BEGIN_FTR_SECTION stdcx. r0,0,r1 /* to clear the reservation */ @@ -246,7 +242,7 @@ syscall_error: oris r5,r5,0x1000 /* Set SO bit in CR */ neg r3,r3 std r5,_CCR(r1) - b syscall_error_cont + b .Lsyscall_error_cont /* Traced system call support */ syscall_dotrace: @@ -268,7 +264,7 @@ syscall_dotrace: addi r9,r1,STACK_FRAME_OVERHEAD clrrdi r10,r1,THREAD_SHIFT ld r10,TI_FLAGS(r10) - b syscall_dotrace_cont + b .Lsyscall_dotrace_cont syscall_enosys: li r3,-ENOSYS @@ -588,23 +584,19 @@ _GLOBAL(ret_from_except_lite) fast_exc_return_irq: restore: /* - * This is the main kernel exit path, we first check if we - * have to change our interrupt state. + * This is the main kernel exit path. First we check if we + * are about to re-enable interrupts */ ld r5,SOFTE(r1) lbz r6,PACASOFTIRQEN(r13) - cmpwi cr1,r5,0 - cmpw cr0,r5,r6 - beq cr0,4f + cmpwi cr0,r5,0 + beq restore_irq_off - /* We do, handle disable first, which is easy */ - bne cr1,3f; - li r0,0 - stb r0,PACASOFTIRQEN(r13); - TRACE_DISABLE_INTS - b 4f + /* We are enabling, were we already enabled ? Yes, just return */ + cmpwi cr0,r6,1 + beq cr0,do_restore -3: /* + /* * We are about to soft-enable interrupts (we are hard disabled * at this point). We check if there's anything that needs to * be replayed first. @@ -626,7 +618,7 @@ restore_no_replay: /* * Final return path. BookE is handled in a different file */ -4: +do_restore: #ifdef CONFIG_PPC_BOOK3E b .exception_return_book3e #else @@ -700,6 +692,25 @@ fast_exception_return: #endif /* CONFIG_PPC_BOOK3E */ /* + * We are returning to a context with interrupts soft disabled. + * + * However, we may also about to hard enable, so we need to + * make sure that in this case, we also clear PACA_IRQ_HARD_DIS + * or that bit can get out of sync and bad things will happen + */ +restore_irq_off: + ld r3,_MSR(r1) + lbz r7,PACAIRQHAPPENED(r13) + andi. r0,r3,MSR_EE + beq 1f + rlwinm r7,r7,0,~PACA_IRQ_HARD_DIS + stb r7,PACAIRQHAPPENED(r13) +1: li r0,0 + stb r0,PACASOFTIRQEN(r13); + TRACE_DISABLE_INTS + b do_restore + + /* * Something did happen, check if a re-emit is needed * (this also clears paca->irq_happened) */ @@ -748,6 +759,9 @@ 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? */ @@ -767,16 +781,6 @@ do_work: SOFT_DISABLE_INTS(r3,r4) 1: bl .preempt_schedule_irq - /* Hard-disable interrupts again (and update PACA) */ -#ifdef CONFIG_PPC_BOOK3E - wrteei 0 -#else - ld r10,PACAKMSR(r13) /* Get kernel MSR without EE */ - mtmsrd r10,1 -#endif /* CONFIG_PPC_BOOK3E */ - li r0,PACA_IRQ_HARD_DIS - stb r0,PACAIRQHAPPENED(r13) - /* Re-test flags and eventually loop */ clrrdi r9,r1,THREAD_SHIFT ld r4,TI_FLAGS(r9) @@ -787,14 +791,6 @@ do_work: user_work: #endif /* CONFIG_PREEMPT */ - /* Enable interrupts */ -#ifdef CONFIG_PPC_BOOK3E - wrteei 1 -#else - ori r10,r10,MSR_EE - mtmsrd r10,1 -#endif /* CONFIG_PPC_BOOK3E */ - andi. r0,r4,_TIF_NEED_RESCHED beq 1f bl .restore_interrupts diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index cb705fdbb458..f7bed44ee165 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -94,12 +94,10 @@ machine_check_pSeries_1: data_access_pSeries: HMT_MEDIUM SET_SCRATCH0(r13) -#ifndef CONFIG_POWER4_ONLY BEGIN_FTR_SECTION b data_access_check_stab data_access_not_stab: END_MMU_FTR_SECTION_IFCLR(MMU_FTR_SLB) -#endif EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, data_access_common, EXC_STD, KVMTEST, 0x300) @@ -301,7 +299,6 @@ machine_check_fwnmi: EXC_STD, KVMTEST, 0x200) KVM_HANDLER_SKIP(PACA_EXMC, EXC_STD, 0x200) -#ifndef CONFIG_POWER4_ONLY /* moved from 0x300 */ data_access_check_stab: GET_PACA(r13) @@ -328,7 +325,6 @@ do_stab_bolted_pSeries: GET_SCRATCH0(r10) std r10,PACA_EXSLB+EX_R13(r13) EXCEPTION_PROLOG_PSERIES_1(.do_stab_bolted, EXC_STD) -#endif /* CONFIG_POWER4_ONLY */ KVM_HANDLER_SKIP(PACA_EXGEN, EXC_STD, 0x300) KVM_HANDLER_SKIP(PACA_EXSLB, EXC_STD, 0x380) @@ -768,8 +764,8 @@ alignment_common: std r3,_DAR(r1) std r4,_DSISR(r1) bl .save_nvgprs + DISABLE_INTS addi r3,r1,STACK_FRAME_OVERHEAD - ENABLE_INTS bl .alignment_exception b .ret_from_except diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index cfe7a38708c3..18bdf74fa164 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -40,6 +40,8 @@ #include <asm/prom.h> #include <asm/rtas.h> #include <asm/fadump.h> +#include <asm/debug.h> +#include <asm/setup.h> static struct fw_dump fw_dump; static struct fadump_mem_struct fdm; diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S index 7dd2981bcc50..22d608e8bb7d 100644 --- a/arch/powerpc/kernel/head_44x.S +++ b/arch/powerpc/kernel/head_44x.S @@ -778,14 +778,6 @@ _GLOBAL(__fixup_440A_mcheck) blr /* - * extern void giveup_altivec(struct task_struct *prev) - * - * The 44x core does not have an AltiVec unit. - */ -_GLOBAL(giveup_altivec) - blr - -/* * extern void giveup_fpu(struct task_struct *prev) * * The 44x core does not have an FPU. diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S index 28e62598d0e8..de80e0f9a2bd 100644 --- a/arch/powerpc/kernel/head_fsl_booke.S +++ b/arch/powerpc/kernel/head_fsl_booke.S @@ -874,14 +874,6 @@ _GLOBAL(__setup_e500mc_ivors) sync blr -/* - * extern void giveup_altivec(struct task_struct *prev) - * - * The e500 core does not have an AltiVec unit. - */ -_GLOBAL(giveup_altivec) - blr - #ifdef CONFIG_SPE /* * extern void giveup_spe(struct task_struct *prev) diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c index 79bb282e6501..b01d14eeca8d 100644 --- a/arch/powerpc/kernel/ibmebus.c +++ b/arch/powerpc/kernel/ibmebus.c @@ -65,7 +65,8 @@ static struct of_device_id __initdata ibmebus_matches[] = { static void *ibmebus_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, - gfp_t flag) + gfp_t flag, + struct dma_attrs *attrs) { void *mem; @@ -77,7 +78,8 @@ static void *ibmebus_alloc_coherent(struct device *dev, static void ibmebus_free_coherent(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_handle) + dma_addr_t dma_handle, + struct dma_attrs *attrs) { kfree(vaddr); } @@ -136,8 +138,8 @@ static u64 ibmebus_dma_get_required_mask(struct device *dev) } static struct dma_map_ops ibmebus_dma_ops = { - .alloc_coherent = ibmebus_alloc_coherent, - .free_coherent = ibmebus_free_coherent, + .alloc = ibmebus_alloc_coherent, + .free = ibmebus_free_coherent, .map_sg = ibmebus_map_sg, .unmap_sg = ibmebus_unmap_sg, .dma_supported = ibmebus_dma_supported, diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c index 6d2209ac0c44..2099d9a879e8 100644 --- a/arch/powerpc/kernel/idle.c +++ b/arch/powerpc/kernel/idle.c @@ -113,29 +113,6 @@ void cpu_idle(void) } } - -/* - * cpu_idle_wait - Used to ensure that all the CPUs come out of the old - * idle loop and start using the new idle loop. - * Required while changing idle handler on SMP systems. - * Caller must have changed idle handler to the new value before the call. - * This window may be larger on shared systems. - */ -void cpu_idle_wait(void) -{ - int cpu; - smp_mb(); - - /* kick all the CPUs so that they exit out of old idle routine */ - get_online_cpus(); - for_each_online_cpu(cpu) { - if (cpu != smp_processor_id()) - smp_send_reschedule(cpu); - } - put_online_cpus(); -} -EXPORT_SYMBOL_GPL(cpu_idle_wait); - int powersave_nap; #ifdef CONFIG_SYSCTL diff --git a/arch/powerpc/kernel/init_task.c b/arch/powerpc/kernel/init_task.c deleted file mode 100644 index d076d465dbd1..000000000000 --- a/arch/powerpc/kernel/init_task.c +++ /dev/null @@ -1,29 +0,0 @@ -#include <linux/mm.h> -#include <linux/export.h> -#include <linux/sched.h> -#include <linux/init.h> -#include <linux/init_task.h> -#include <linux/fs.h> -#include <linux/mqueue.h> -#include <asm/uaccess.h> - -static struct signal_struct init_signals = INIT_SIGNALS(init_signals); -static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand); -/* - * Initial thread structure. - * - * We need to make sure that this is 16384-byte aligned due to the - * way process stacks are handled. This is done by having a special - * "init_task" linker map entry.. - */ -union thread_union init_thread_union __init_task_data = - { INIT_THREAD_INFO(init_task) }; - -/* - * Initial task structure. - * - * All other task structs will be allocated on slabs in fork.c - */ -struct task_struct init_task = INIT_TASK(init_task); - -EXPORT_SYMBOL(init_task); diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 243dbabfe74d..7835a5e1ea5f 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -229,6 +229,19 @@ notrace void arch_local_irq_restore(unsigned long en) */ if (unlikely(irq_happened != PACA_IRQ_HARD_DIS)) __hard_irq_disable(); +#ifdef CONFIG_TRACE_IRQFLAG + else { + /* + * We should already be hard disabled here. We had bugs + * where that wasn't the case so let's dbl check it and + * warn if we are wrong. Only do that when IRQ tracing + * is enabled as mfmsr() can be costly. + */ + if (WARN_ON(mfmsr() & MSR_EE)) + __hard_irq_disable(); + } +#endif /* CONFIG_TRACE_IRQFLAG */ + set_soft_enabled(0); /* @@ -260,11 +273,17 @@ EXPORT_SYMBOL(arch_local_irq_restore); * if they are currently disabled. This is typically called before * schedule() or do_signal() when returning to userspace. We do it * in C to avoid the burden of dealing with lockdep etc... + * + * 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) { - if (irqs_disabled()) + if (irqs_disabled()) { + local_paca->irq_happened |= PACA_IRQ_HARD_DIS; local_irq_enable(); + } else + __hard_irq_enable(); } #endif /* CONFIG_PPC64 */ @@ -330,14 +349,10 @@ void migrate_irqs(void) alloc_cpumask_var(&mask, GFP_KERNEL); - for_each_irq(irq) { + for_each_irq_desc(irq, desc) { struct irq_data *data; struct irq_chip *chip; - desc = irq_to_desc(irq); - if (!desc) - continue; - data = irq_desc_get_irq_data(desc); if (irqd_is_per_cpu(data)) continue; @@ -560,12 +575,6 @@ void do_softirq(void) local_irq_restore(flags); } -irq_hw_number_t irqd_to_hwirq(struct irq_data *d) -{ - return d->hwirq; -} -EXPORT_SYMBOL_GPL(irqd_to_hwirq); - irq_hw_number_t virq_to_hw(unsigned int virq) { struct irq_data *irq_data = irq_get_irq_data(virq); @@ -578,7 +587,7 @@ int irq_choose_cpu(const struct cpumask *mask) { int cpuid; - if (cpumask_equal(mask, cpu_all_mask)) { + if (cpumask_equal(mask, cpu_online_mask)) { static int irq_rover; static DEFINE_RAW_SPINLOCK(irq_rover_lock); unsigned long flags; diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c index 76a6e40a6f7c..782bd0a3c2f0 100644 --- a/arch/powerpc/kernel/kgdb.c +++ b/arch/powerpc/kernel/kgdb.c @@ -24,6 +24,7 @@ #include <asm/current.h> #include <asm/processor.h> #include <asm/machdep.h> +#include <asm/debug.h> /* * This table contains the mapping between PowerPC hardware trap types, and diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c index c957b1202bdc..5df777794403 100644 --- a/arch/powerpc/kernel/machine_kexec.c +++ b/arch/powerpc/kernel/machine_kexec.c @@ -23,14 +23,11 @@ void machine_kexec_mask_interrupts(void) { unsigned int i; + struct irq_desc *desc; - for_each_irq(i) { - struct irq_desc *desc = irq_to_desc(i); + for_each_irq_desc(i, desc) { struct irq_chip *chip; - if (!desc) - continue; - chip = irq_desc_get_chip(desc); if (!chip) continue; diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index 7cd07b42ca1a..386d57f66f28 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -738,8 +738,23 @@ relocate_new_kernel: mr r5, r31 li r0, 0 -#elif defined(CONFIG_44x) && !defined(CONFIG_PPC_47x) +#elif defined(CONFIG_44x) + /* Save our parameters */ + mr r29, r3 + mr r30, r4 + mr r31, r5 + +#ifdef CONFIG_PPC_47x + /* Check for 47x cores */ + mfspr r3,SPRN_PVR + srwi r3,r3,16 + cmplwi cr0,r3,PVR_476@h + beq setup_map_47x + cmplwi cr0,r3,PVR_476_ISS@h + beq setup_map_47x +#endif /* CONFIG_PPC_47x */ + /* * Code for setting up 1:1 mapping for PPC440x for KEXEC * @@ -753,16 +768,15 @@ relocate_new_kernel: * 5) Invalidate the tmp mapping. * * - Based on the kexec support code for FSL BookE - * - Doesn't support 47x yet. * */ - /* Save our parameters */ - mr r29, r3 - mr r30, r4 - mr r31, r5 - /* Load our MSR_IS and TID to MMUCR for TLB search */ - mfspr r3,SPRN_PID + /* + * Load the PID with kernel PID (0). + * Also load our MSR_IS and TID to MMUCR for TLB search. + */ + li r3, 0 + mtspr SPRN_PID, r3 mfmsr r4 andi. r4,r4,MSR_IS@l beq wmmucr @@ -900,6 +914,179 @@ next_tlb: li r3, 0 tlbwe r3, r24, PPC44x_TLB_PAGEID sync + b ppc44x_map_done + +#ifdef CONFIG_PPC_47x + + /* 1:1 mapping for 47x */ + +setup_map_47x: + + /* + * Load the kernel pid (0) to PID and also to MMUCR[TID]. + * Also set the MSR IS->MMUCR STS + */ + li r3, 0 + mtspr SPRN_PID, r3 /* Set PID */ + mfmsr r4 /* Get MSR */ + andi. r4, r4, MSR_IS@l /* TS=1? */ + beq 1f /* If not, leave STS=0 */ + oris r3, r3, PPC47x_MMUCR_STS@h /* Set STS=1 */ +1: mtspr SPRN_MMUCR, r3 /* Put MMUCR */ + sync + + /* Find the entry we are running from */ + bl 2f +2: mflr r23 + tlbsx r23, 0, r23 + tlbre r24, r23, 0 /* TLB Word 0 */ + tlbre r25, r23, 1 /* TLB Word 1 */ + tlbre r26, r23, 2 /* TLB Word 2 */ + + + /* + * Invalidates all the tlb entries by writing to 256 RPNs(r4) + * of 4k page size in all 4 ways (0-3 in r3). + * This would invalidate the entire UTLB including the one we are + * running from. However the shadow TLB entries would help us + * to continue the execution, until we flush them (rfi/isync). + */ + addis r3, 0, 0x8000 /* specify the way */ + addi r4, 0, 0 /* TLB Word0 = (EPN=0, VALID = 0) */ + addi r5, 0, 0 + b clear_utlb_entry + + /* Align the loop to speed things up. from head_44x.S */ + .align 6 + +clear_utlb_entry: + + tlbwe r4, r3, 0 + tlbwe r5, r3, 1 + tlbwe r5, r3, 2 + addis r3, r3, 0x2000 /* Increment the way */ + cmpwi r3, 0 + bne clear_utlb_entry + addis r3, 0, 0x8000 + addis r4, r4, 0x100 /* Increment the EPN */ + cmpwi r4, 0 + bne clear_utlb_entry + + /* Create the entries in the other address space */ + mfmsr r5 + rlwinm r7, r5, 27, 31, 31 /* Get the TS (Bit 26) from MSR */ + xori r7, r7, 1 /* r7 = !TS */ + + insrwi r24, r7, 1, 21 /* Change the TS in the saved TLB word 0 */ + + /* + * write out the TLB entries for the tmp mapping + * Use way '0' so that we could easily invalidate it later. + */ + lis r3, 0x8000 /* Way '0' */ + + tlbwe r24, r3, 0 + tlbwe r25, r3, 1 + tlbwe r26, r3, 2 + + /* Update the msr to the new TS */ + insrwi r5, r7, 1, 26 + + bl 1f +1: mflr r6 + addi r6, r6, (2f-1b) + + mtspr SPRN_SRR0, r6 + mtspr SPRN_SRR1, r5 + rfi + + /* + * Now we are in the tmp address space. + * Create a 1:1 mapping for 0-2GiB in the original TS. + */ +2: + li r3, 0 + li r4, 0 /* TLB Word 0 */ + li r5, 0 /* TLB Word 1 */ + li r6, 0 + ori r6, r6, PPC47x_TLB2_S_RWX /* TLB word 2 */ + + li r8, 0 /* PageIndex */ + + xori r7, r7, 1 /* revert back to original TS */ + +write_utlb: + rotlwi r5, r8, 28 /* RPN = PageIndex * 256M */ + /* ERPN = 0 as we don't use memory above 2G */ + + mr r4, r5 /* EPN = RPN */ + ori r4, r4, (PPC47x_TLB0_VALID | PPC47x_TLB0_256M) + insrwi r4, r7, 1, 21 /* Insert the TS to Word 0 */ + + tlbwe r4, r3, 0 /* Write out the entries */ + tlbwe r5, r3, 1 + tlbwe r6, r3, 2 + addi r8, r8, 1 + cmpwi r8, 8 /* Have we completed ? */ + bne write_utlb + + /* make sure we complete the TLB write up */ + isync + + /* + * Prepare to jump to the 1:1 mapping. + * 1) Extract page size of the tmp mapping + * DSIZ = TLB_Word0[22:27] + * 2) Calculate the physical address of the address + * to jump to. + */ + rlwinm r10, r24, 0, 22, 27 + + cmpwi r10, PPC47x_TLB0_4K + bne 0f + li r10, 0x1000 /* r10 = 4k */ + bl 1f + +0: + /* Defaults to 256M */ + lis r10, 0x1000 + + bl 1f +1: mflr r4 + addi r4, r4, (2f-1b) /* virtual address of 2f */ + + subi r11, r10, 1 /* offsetmask = Pagesize - 1 */ + not r10, r11 /* Pagemask = ~(offsetmask) */ + + and r5, r25, r10 /* Physical page */ + and r6, r4, r11 /* offset within the current page */ + + or r5, r5, r6 /* Physical address for 2f */ + + /* Switch the TS in MSR to the original one */ + mfmsr r8 + insrwi r8, r7, 1, 26 + + mtspr SPRN_SRR1, r8 + mtspr SPRN_SRR0, r5 + rfi + +2: + /* Invalidate the tmp mapping */ + lis r3, 0x8000 /* Way '0' */ + + clrrwi r24, r24, 12 /* Clear the valid bit */ + tlbwe r24, r3, 0 + tlbwe r25, r3, 1 + tlbwe r26, r3, 2 + + /* Make sure we complete the TLB write and flush the shadow TLB */ + isync + +#endif + +ppc44x_map_done: + /* Restore the parameters */ mr r3, r29 diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index 0bb1f98613ba..fbe1a12dc7f1 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -36,10 +36,7 @@ struct lppaca lppaca[] = { [0 ... (NR_LPPACAS-1)] = { .desc = 0xd397d781, /* "LpPa" */ .size = sizeof(struct lppaca), - .dyn_proc_status = 2, - .decr_val = 0x00ff0000, .fpregs_in_use = 1, - .end_of_quantum = 0xfffffffffffffffful, .slb_count = 64, .vmxregs_in_use = 0, .page_ins = 0, diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index f88698c0f332..710f400476de 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -124,7 +124,7 @@ void enable_kernel_altivec(void) if (current->thread.regs && (current->thread.regs->msr & MSR_VEC)) giveup_altivec(current); else - giveup_altivec(NULL); /* just enable AltiVec for kernel - force */ + giveup_altivec_notask(); #else giveup_altivec(last_task_used_altivec); #endif /* CONFIG_SMP */ @@ -711,18 +711,21 @@ 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); + flush_fp_to_thread(src); + flush_altivec_to_thread(src); + flush_vsx_to_thread(src); + flush_spe_to_thread(src); #ifdef CONFIG_HAVE_HW_BREAKPOINT - flush_ptrace_hw_breakpoint(tsk); + flush_ptrace_hw_breakpoint(src); #endif /* CONFIG_HAVE_HW_BREAKPOINT */ + + *dst = *src; + return 0; } /* @@ -1235,7 +1238,7 @@ void __ppc64_runlatch_on(void) ctrl |= CTRL_RUNLATCH; mtspr(SPRN_CTRLT, ctrl); - ti->local_flags |= TLF_RUNLATCH; + ti->local_flags |= _TLF_RUNLATCH; } /* Called with hard IRQs off */ @@ -1244,7 +1247,7 @@ void __ppc64_runlatch_off(void) struct thread_info *ti = current_thread_info(); unsigned long ctrl; - ti->local_flags &= ~TLF_RUNLATCH; + ti->local_flags &= ~_TLF_RUNLATCH; ctrl = mfspr(SPRN_CTRLF); ctrl &= ~CTRL_RUNLATCH; @@ -1252,37 +1255,6 @@ void __ppc64_runlatch_off(void) } #endif /* CONFIG_PPC64 */ -#if THREAD_SHIFT < PAGE_SHIFT - -static struct kmem_cache *thread_info_cache; - -struct thread_info *alloc_thread_info_node(struct task_struct *tsk, int node) -{ - struct thread_info *ti; - - ti = kmem_cache_alloc_node(thread_info_cache, GFP_KERNEL, node); - 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 */ - unsigned long arch_align_stack(unsigned long sp) { if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space) diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 99860273211b..1b488e5305c5 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -680,6 +680,9 @@ static void __init early_cmdline_parse(void) #define OV3_VMX 0x40 /* VMX/Altivec */ #define OV3_DFP 0x20 /* decimal FP */ +/* Option vector 4: IBM PAPR implementation */ +#define OV4_MIN_ENT_CAP 0x01 /* minimum VP entitled capacity */ + /* Option vector 5: PAPR/OF options supported */ #define OV5_LPAR 0x80 /* logical partitioning supported */ #define OV5_SPLPAR 0x40 /* shared-processor LPAR supported */ @@ -701,6 +704,8 @@ static void __init early_cmdline_parse(void) #define OV5_XCMO 0x00 #endif #define OV5_TYPE1_AFFINITY 0x80 /* Type 1 NUMA affinity */ +#define OV5_PFO_HW_RNG 0x80 /* PFO Random Number Generator */ +#define OV5_PFO_HW_ENCR 0x20 /* PFO Encryption Accelerator */ /* Option Vector 6: IBM PAPR hints */ #define OV6_LINUX 0x02 /* Linux is our OS */ @@ -744,11 +749,12 @@ static unsigned char ibm_architecture_vec[] = { OV3_FP | OV3_VMX | OV3_DFP, /* option vector 4: IBM PAPR implementation */ - 2 - 2, /* length */ + 3 - 2, /* length */ 0, /* don't halt */ + OV4_MIN_ENT_CAP, /* minimum VP entitled capacity */ /* option vector 5: PAPR/OF options */ - 13 - 2, /* length */ + 18 - 2, /* length */ 0, /* don't ignore, don't halt */ OV5_LPAR | OV5_SPLPAR | OV5_LARGE_PAGES | OV5_DRCONF_MEMORY | OV5_DONATE_DEDICATE_CPU | OV5_MSI, @@ -762,8 +768,13 @@ static unsigned char ibm_architecture_vec[] = { * must match by the macro below. Update the definition if * the structure layout changes. */ -#define IBM_ARCH_VEC_NRCORES_OFFSET 100 +#define IBM_ARCH_VEC_NRCORES_OFFSET 101 W(NR_CPUS), /* number of cores supported */ + 0, + 0, + 0, + 0, + OV5_PFO_HW_RNG | OV5_PFO_HW_ENCR, /* option vector 6: IBM PAPR hints */ 4 - 2, /* length */ diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index 8d8e028893be..c10fc28b9092 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -1432,40 +1432,6 @@ static long ppc_del_hwdebug(struct task_struct *child, long addr, long data) #endif } -/* - * Here are the old "legacy" powerpc specific getregs/setregs ptrace calls, - * we mark them as obsolete now, they will be removed in a future version - */ -static long arch_ptrace_old(struct task_struct *child, long request, - unsigned long addr, unsigned long data) -{ - void __user *datavp = (void __user *) data; - - switch (request) { - case PPC_PTRACE_GETREGS: /* Get GPRs 0 - 31. */ - return copy_regset_to_user(child, &user_ppc_native_view, - REGSET_GPR, 0, 32 * sizeof(long), - datavp); - - case PPC_PTRACE_SETREGS: /* Set GPRs 0 - 31. */ - return copy_regset_from_user(child, &user_ppc_native_view, - REGSET_GPR, 0, 32 * sizeof(long), - datavp); - - case PPC_PTRACE_GETFPREGS: /* Get FPRs 0 - 31. */ - return copy_regset_to_user(child, &user_ppc_native_view, - REGSET_FPR, 0, 32 * sizeof(double), - datavp); - - case PPC_PTRACE_SETFPREGS: /* Set FPRs 0 - 31. */ - return copy_regset_from_user(child, &user_ppc_native_view, - REGSET_FPR, 0, 32 * sizeof(double), - datavp); - } - - return -EPERM; -} - long arch_ptrace(struct task_struct *child, long request, unsigned long addr, unsigned long data) { @@ -1687,14 +1653,6 @@ long arch_ptrace(struct task_struct *child, long request, datavp); #endif - /* Old reverse args ptrace callss */ - case PPC_PTRACE_GETREGS: /* Get GPRs 0 - 31. */ - case PPC_PTRACE_SETREGS: /* Set GPRs 0 - 31. */ - case PPC_PTRACE_GETFPREGS: /* Get FPRs 0 - 31. */ - case PPC_PTRACE_SETFPREGS: /* Get FPRs 0 - 31. */ - ret = arch_ptrace_old(child, request, addr, data); - break; - default: ret = ptrace_request(child, request, addr, data); break; @@ -1710,7 +1668,7 @@ long do_syscall_trace_enter(struct pt_regs *regs) { long ret = 0; - secure_computing(regs->gpr[0]); + secure_computing_strict(regs->gpr[0]); if (test_thread_flag(TIF_SYSCALL_TRACE) && tracehook_report_syscall_entry(regs)) diff --git a/arch/powerpc/kernel/ptrace32.c b/arch/powerpc/kernel/ptrace32.c index 469349d14a97..8c21658719d9 100644 --- a/arch/powerpc/kernel/ptrace32.c +++ b/arch/powerpc/kernel/ptrace32.c @@ -39,30 +39,6 @@ * in exit.c or in signal.c. */ -/* - * Here are the old "legacy" powerpc specific getregs/setregs ptrace calls, - * we mark them as obsolete now, they will be removed in a future version - */ -static long compat_ptrace_old(struct task_struct *child, long request, - long addr, long data) -{ - switch (request) { - case PPC_PTRACE_GETREGS: /* Get GPRs 0 - 31. */ - return copy_regset_to_user(child, - task_user_regset_view(current), 0, - 0, 32 * sizeof(compat_long_t), - compat_ptr(data)); - - case PPC_PTRACE_SETREGS: /* Set GPRs 0 - 31. */ - return copy_regset_from_user(child, - task_user_regset_view(current), 0, - 0, 32 * sizeof(compat_long_t), - compat_ptr(data)); - } - - return -EPERM; -} - /* Macros to workout the correct index for the FPR in the thread struct */ #define FPRNUMBER(i) (((i) - PT_FPR0) >> 1) #define FPRHALF(i) (((i) - PT_FPR0) & 1) @@ -308,8 +284,6 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, case PTRACE_SETVSRREGS: case PTRACE_GETREGS64: case PTRACE_SETREGS64: - case PPC_PTRACE_GETFPREGS: - case PPC_PTRACE_SETFPREGS: case PTRACE_KILL: case PTRACE_SINGLESTEP: case PTRACE_DETACH: @@ -322,12 +296,6 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, ret = arch_ptrace(child, request, addr, data); break; - /* Old reverse args ptrace callss */ - case PPC_PTRACE_GETREGS: /* Get GPRs 0 - 31. */ - case PPC_PTRACE_SETREGS: /* Set GPRs 0 - 31. */ - ret = compat_ptrace_old(child, request, addr, data); - break; - default: ret = compat_ptrace_request(child, request, addr, data); break; diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index 9825f29d1faf..ec8a53fa9e8f 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -150,6 +150,9 @@ notrace void __init machine_init(u64 dt_ptr) } #ifdef CONFIG_BOOKE_WDT +extern u32 booke_wdt_enabled; +extern u32 booke_wdt_period; + /* Checks wdt=x and wdt_period=xx command-line option */ notrace int __init early_parse_wdt(char *p) { diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index d9f94410fd7f..e4cb34322de4 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -57,27 +57,9 @@ #define DBG(fmt...) #endif - -/* Store all idle threads, this can be reused instead of creating -* a new thread. Also avoids complicated thread destroy functionality -* for idle threads. -*/ #ifdef CONFIG_HOTPLUG_CPU -/* - * Needed only for CONFIG_HOTPLUG_CPU because __cpuinitdata is - * removed after init for !CONFIG_HOTPLUG_CPU. - */ -static DEFINE_PER_CPU(struct task_struct *, idle_thread_array); -#define get_idle_for_cpu(x) (per_cpu(idle_thread_array, x)) -#define set_idle_for_cpu(x, p) (per_cpu(idle_thread_array, x) = (p)) - /* State of each CPU during hotplug phases */ static DEFINE_PER_CPU(int, cpu_state) = { 0 }; - -#else -static struct task_struct *idle_thread_array[NR_CPUS] __cpuinitdata ; -#define get_idle_for_cpu(x) (idle_thread_array[(x)]) -#define set_idle_for_cpu(x, p) (idle_thread_array[(x)] = (p)) #endif struct thread_info *secondary_ti; @@ -429,60 +411,19 @@ int generic_check_cpu_restart(unsigned int cpu) } #endif -struct create_idle { - struct work_struct work; - struct task_struct *idle; - struct completion done; - int cpu; -}; - -static void __cpuinit do_fork_idle(struct work_struct *work) +static void cpu_idle_thread_init(unsigned int cpu, struct task_struct *idle) { - struct create_idle *c_idle = - container_of(work, struct create_idle, work); - - c_idle->idle = fork_idle(c_idle->cpu); - complete(&c_idle->done); -} - -static int __cpuinit create_idle(unsigned int cpu) -{ - struct thread_info *ti; - struct create_idle c_idle = { - .cpu = cpu, - .done = COMPLETION_INITIALIZER_ONSTACK(c_idle.done), - }; - INIT_WORK_ONSTACK(&c_idle.work, do_fork_idle); - - c_idle.idle = get_idle_for_cpu(cpu); - - /* We can't use kernel_thread since we must avoid to - * reschedule the child. We use a workqueue because - * we want to fork from a kernel thread, not whatever - * userspace process happens to be trying to online us. - */ - if (!c_idle.idle) { - schedule_work(&c_idle.work); - wait_for_completion(&c_idle.done); - } else - init_idle(c_idle.idle, cpu); - if (IS_ERR(c_idle.idle)) { - pr_err("Failed fork for CPU %u: %li", cpu, PTR_ERR(c_idle.idle)); - return PTR_ERR(c_idle.idle); - } - ti = task_thread_info(c_idle.idle); + struct thread_info *ti = task_thread_info(idle); #ifdef CONFIG_PPC64 - paca[cpu].__current = c_idle.idle; + paca[cpu].__current = idle; paca[cpu].kstack = (unsigned long)ti + THREAD_SIZE - STACK_FRAME_OVERHEAD; #endif ti->cpu = cpu; - current_set[cpu] = ti; - - return 0; + secondary_ti = current_set[cpu] = ti; } -int __cpuinit __cpu_up(unsigned int cpu) +int __cpuinit __cpu_up(unsigned int cpu, struct task_struct *tidle) { int rc, c; @@ -490,12 +431,7 @@ int __cpuinit __cpu_up(unsigned int cpu) (smp_ops->cpu_bootable && !smp_ops->cpu_bootable(cpu))) return -EINVAL; - /* Make sure we have an idle thread */ - rc = create_idle(cpu); - if (rc) - return rc; - - secondary_ti = current_set[cpu]; + cpu_idle_thread_init(cpu, tidle); /* Make sure callin-map entry is 0 (can be leftover a CPU * hotplug diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 6aa0c663e247..158972341a2d 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -248,7 +248,7 @@ void _exception(int signr, struct pt_regs *regs, int code, unsigned long addr) addr, regs->nip, regs->link, code); } - if (!arch_irq_disabled_regs(regs)) + if (arch_irqs_disabled() && !arch_irq_disabled_regs(regs)) local_irq_enable(); memset(&info, 0, sizeof(info)); @@ -1019,7 +1019,9 @@ void __kprobes program_check_exception(struct pt_regs *regs) return; } - local_irq_enable(); + /* We restore the interrupt state now */ + if (!arch_irq_disabled_regs(regs)) + local_irq_enable(); #ifdef CONFIG_MATH_EMULATION /* (reason & REASON_ILLEGAL) would be the obvious thing here, @@ -1069,6 +1071,10 @@ void alignment_exception(struct pt_regs *regs) { int sig, code, fixed = 0; + /* We restore the interrupt state now */ + if (!arch_irq_disabled_regs(regs)) + local_irq_enable(); + /* we don't implement logging of alignment exceptions */ if (!(current->thread.align_ctl & PR_UNALIGN_SIGBUS)) fixed = fix_alignment(regs); diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S index 4d5a3edff49e..e830289d2e48 100644 --- a/arch/powerpc/kernel/vector.S +++ b/arch/powerpc/kernel/vector.S @@ -89,6 +89,16 @@ _GLOBAL(load_up_altivec) /* restore registers and return */ blr +_GLOBAL(giveup_altivec_notask) + mfmsr r3 + andis. r4,r3,MSR_VEC@h + bnelr /* Already enabled? */ + oris r3,r3,MSR_VEC@h + SYNC + MTMSRD(r3) /* enable use of VMX now */ + isync + blr + /* * giveup_altivec(tsk) * Disable VMX for the task given as the argument, diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c index b2f7c8480bf6..cb87301ccd55 100644 --- a/arch/powerpc/kernel/vio.c +++ b/arch/powerpc/kernel/vio.c @@ -14,7 +14,9 @@ * 2 of the License, or (at your option) any later version. */ +#include <linux/cpu.h> #include <linux/types.h> +#include <linux/delay.h> #include <linux/stat.h> #include <linux/device.h> #include <linux/init.h> @@ -482,7 +484,8 @@ static void vio_cmo_balance(struct work_struct *work) } static void *vio_dma_iommu_alloc_coherent(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t flag) + dma_addr_t *dma_handle, gfp_t flag, + struct dma_attrs *attrs) { struct vio_dev *viodev = to_vio_dev(dev); void *ret; @@ -492,7 +495,7 @@ static void *vio_dma_iommu_alloc_coherent(struct device *dev, size_t size, return NULL; } - ret = dma_iommu_ops.alloc_coherent(dev, size, dma_handle, flag); + ret = dma_iommu_ops.alloc(dev, size, dma_handle, flag, attrs); if (unlikely(ret == NULL)) { vio_cmo_dealloc(viodev, roundup(size, PAGE_SIZE)); atomic_inc(&viodev->cmo.allocs_failed); @@ -502,11 +505,12 @@ static void *vio_dma_iommu_alloc_coherent(struct device *dev, size_t size, } static void vio_dma_iommu_free_coherent(struct device *dev, size_t size, - void *vaddr, dma_addr_t dma_handle) + void *vaddr, dma_addr_t dma_handle, + struct dma_attrs *attrs) { struct vio_dev *viodev = to_vio_dev(dev); - dma_iommu_ops.free_coherent(dev, size, vaddr, dma_handle); + dma_iommu_ops.free(dev, size, vaddr, dma_handle, attrs); vio_cmo_dealloc(viodev, roundup(size, PAGE_SIZE)); } @@ -607,8 +611,8 @@ static u64 vio_dma_get_required_mask(struct device *dev) } struct dma_map_ops vio_dma_mapping_ops = { - .alloc_coherent = vio_dma_iommu_alloc_coherent, - .free_coherent = vio_dma_iommu_free_coherent, + .alloc = vio_dma_iommu_alloc_coherent, + .free = vio_dma_iommu_free_coherent, .map_sg = vio_dma_iommu_map_sg, .unmap_sg = vio_dma_iommu_unmap_sg, .map_page = vio_dma_iommu_map_page, @@ -707,13 +711,26 @@ static int vio_cmo_bus_probe(struct vio_dev *viodev) struct vio_driver *viodrv = to_vio_driver(dev->driver); unsigned long flags; size_t size; + bool dma_capable = false; + + /* A device requires entitlement if it has a DMA window property */ + switch (viodev->family) { + case VDEVICE: + if (of_get_property(viodev->dev.of_node, + "ibm,my-dma-window", NULL)) + dma_capable = true; + break; + case PFO: + dma_capable = false; + break; + default: + dev_warn(dev, "unknown device family: %d\n", viodev->family); + BUG(); + break; + } - /* - * Check to see that device has a DMA window and configure - * entitlement for the device. - */ - if (of_get_property(viodev->dev.of_node, - "ibm,my-dma-window", NULL)) { + /* Configure entitlement for the device. */ + if (dma_capable) { /* Check that the driver is CMO enabled and get desired DMA */ if (!viodrv->get_desired_dma) { dev_err(dev, "%s: device driver does not support CMO\n", @@ -1048,6 +1065,94 @@ static void vio_cmo_sysfs_init(void) { } EXPORT_SYMBOL(vio_cmo_entitlement_update); EXPORT_SYMBOL(vio_cmo_set_dev_desired); + +/* + * Platform Facilities Option (PFO) support + */ + +/** + * vio_h_cop_sync - Perform a synchronous PFO co-processor operation + * + * @vdev - Pointer to a struct vio_dev for device + * @op - Pointer to a struct vio_pfo_op for the operation parameters + * + * Calls the hypervisor to synchronously perform the PFO operation + * described in @op. In the case of a busy response from the hypervisor, + * the operation will be re-submitted indefinitely unless a non-zero timeout + * is specified or an error occurs. The timeout places a limit on when to + * stop re-submitting a operation, the total time can be exceeded if an + * operation is in progress. + * + * If op->hcall_ret is not NULL, this will be set to the return from the + * last h_cop_op call or it will be 0 if an error not involving the h_call + * was encountered. + * + * Returns: + * 0 on success, + * -EINVAL if the h_call fails due to an invalid parameter, + * -E2BIG if the h_call can not be performed synchronously, + * -EBUSY if a timeout is specified and has elapsed, + * -EACCES if the memory area for data/status has been rescinded, or + * -EPERM if a hardware fault has been indicated + */ +int vio_h_cop_sync(struct vio_dev *vdev, struct vio_pfo_op *op) +{ + struct device *dev = &vdev->dev; + unsigned long deadline = 0; + long hret = 0; + int ret = 0; + + if (op->timeout) + deadline = jiffies + msecs_to_jiffies(op->timeout); + + while (true) { + hret = plpar_hcall_norets(H_COP, op->flags, + vdev->resource_id, + op->in, op->inlen, op->out, + op->outlen, op->csbcpb); + + if (hret == H_SUCCESS || + (hret != H_NOT_ENOUGH_RESOURCES && + hret != H_BUSY && hret != H_RESOURCE) || + (op->timeout && time_after(deadline, jiffies))) + break; + + dev_dbg(dev, "%s: hcall ret(%ld), retrying.\n", __func__, hret); + } + + switch (hret) { + case H_SUCCESS: + ret = 0; + break; + case H_OP_MODE: + case H_TOO_BIG: + ret = -E2BIG; + break; + case H_RESCINDED: + ret = -EACCES; + break; + case H_HARDWARE: + ret = -EPERM; + break; + case H_NOT_ENOUGH_RESOURCES: + case H_RESOURCE: + case H_BUSY: + ret = -EBUSY; + break; + default: + ret = -EINVAL; + break; + } + + if (ret) + dev_dbg(dev, "%s: Sync h_cop_op failure (ret:%d) (hret:%ld)\n", + __func__, ret, hret); + + op->hcall_err = hret; + return ret; +} +EXPORT_SYMBOL(vio_h_cop_sync); + static struct iommu_table *vio_build_iommu_table(struct vio_dev *dev) { const unsigned char *dma_window; @@ -1209,35 +1314,87 @@ static void __devinit vio_dev_release(struct device *dev) struct vio_dev *vio_register_device_node(struct device_node *of_node) { struct vio_dev *viodev; + struct device_node *parent_node; const unsigned int *unit_address; + const unsigned int *pfo_resid = NULL; + enum vio_dev_family family; + const char *of_node_name = of_node->name ? of_node->name : "<unknown>"; - /* we need the 'device_type' property, in order to match with drivers */ - if (of_node->type == NULL) { - printk(KERN_WARNING "%s: node %s missing 'device_type'\n", - __func__, - of_node->name ? of_node->name : "<unknown>"); + /* + * Determine if this node is a under the /vdevice node or under the + * /ibm,platform-facilities node. This decides the device's family. + */ + parent_node = of_get_parent(of_node); + if (parent_node) { + if (!strcmp(parent_node->full_name, "/ibm,platform-facilities")) + family = PFO; + else if (!strcmp(parent_node->full_name, "/vdevice")) + family = VDEVICE; + else { + pr_warn("%s: parent(%s) of %s not recognized.\n", + __func__, + parent_node->full_name, + of_node_name); + of_node_put(parent_node); + return NULL; + } + of_node_put(parent_node); + } else { + pr_warn("%s: could not determine the parent of node %s.\n", + __func__, of_node_name); return NULL; } - unit_address = of_get_property(of_node, "reg", NULL); - if (unit_address == NULL) { - printk(KERN_WARNING "%s: node %s missing 'reg'\n", - __func__, - of_node->name ? of_node->name : "<unknown>"); - return NULL; + if (family == PFO) { + if (of_get_property(of_node, "interrupt-controller", NULL)) { + pr_debug("%s: Skipping the interrupt controller %s.\n", + __func__, of_node_name); + return NULL; + } } /* allocate a vio_dev for this node */ viodev = kzalloc(sizeof(struct vio_dev), GFP_KERNEL); - if (viodev == NULL) + if (viodev == NULL) { + pr_warn("%s: allocation failure for VIO device.\n", __func__); return NULL; + } - viodev->irq = irq_of_parse_and_map(of_node, 0); + /* we need the 'device_type' property, in order to match with drivers */ + viodev->family = family; + if (viodev->family == VDEVICE) { + if (of_node->type != NULL) + viodev->type = of_node->type; + else { + pr_warn("%s: node %s is missing the 'device_type' " + "property.\n", __func__, of_node_name); + goto out; + } + + unit_address = of_get_property(of_node, "reg", NULL); + if (unit_address == NULL) { + pr_warn("%s: node %s missing 'reg'\n", + __func__, of_node_name); + goto out; + } + dev_set_name(&viodev->dev, "%x", *unit_address); + viodev->irq = irq_of_parse_and_map(of_node, 0); + viodev->unit_address = *unit_address; + } else { + /* PFO devices need their resource_id for submitting COP_OPs + * This is an optional field for devices, but is required when + * performing synchronous ops */ + pfo_resid = of_get_property(of_node, "ibm,resource-id", NULL); + if (pfo_resid != NULL) + viodev->resource_id = *pfo_resid; + + unit_address = NULL; + dev_set_name(&viodev->dev, "%s", of_node_name); + viodev->type = of_node_name; + viodev->irq = 0; + } - dev_set_name(&viodev->dev, "%x", *unit_address); viodev->name = of_node->name; - viodev->type = of_node->type; - viodev->unit_address = *unit_address; viodev->dev.of_node = of_node_get(of_node); if (firmware_has_feature(FW_FEATURE_CMO)) @@ -1265,16 +1422,51 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node) } return viodev; + +out: /* Use this exit point for any return prior to device_register */ + kfree(viodev); + + return NULL; } EXPORT_SYMBOL(vio_register_device_node); +/* + * vio_bus_scan_for_devices - Scan OF and register each child device + * @root_name - OF node name for the root of the subtree to search. + * This must be non-NULL + * + * Starting from the root node provide, register the device node for + * each child beneath the root. + */ +static void vio_bus_scan_register_devices(char *root_name) +{ + struct device_node *node_root, *node_child; + + if (!root_name) + return; + + node_root = of_find_node_by_name(NULL, root_name); + if (node_root) { + + /* + * Create struct vio_devices for each virtual device in + * the device tree. Drivers will associate with them later. + */ + node_child = of_get_next_child(node_root, NULL); + while (node_child) { + vio_register_device_node(node_child); + node_child = of_get_next_child(node_root, node_child); + } + of_node_put(node_root); + } +} + /** * vio_bus_init: - Initialize the virtual IO bus */ static int __init vio_bus_init(void) { int err; - struct device_node *node_vroot; if (firmware_has_feature(FW_FEATURE_CMO)) vio_cmo_sysfs_init(); @@ -1299,19 +1491,8 @@ static int __init vio_bus_init(void) if (firmware_has_feature(FW_FEATURE_CMO)) vio_cmo_bus_init(); - node_vroot = of_find_node_by_name(NULL, "vdevice"); - if (node_vroot) { - struct device_node *of_node; - - /* - * Create struct vio_devices for each virtual device in - * the device tree. Drivers will associate with them later. - */ - for (of_node = node_vroot->child; of_node != NULL; - of_node = of_node->sibling) - vio_register_device_node(of_node); - of_node_put(node_vroot); - } + vio_bus_scan_register_devices("vdevice"); + vio_bus_scan_register_devices("ibm,platform-facilities"); return 0; } @@ -1434,12 +1615,28 @@ struct vio_dev *vio_find_node(struct device_node *vnode) { const uint32_t *unit_address; char kobj_name[20]; + struct device_node *vnode_parent; + const char *dev_type; + + vnode_parent = of_get_parent(vnode); + if (!vnode_parent) + return NULL; + + dev_type = of_get_property(vnode_parent, "device_type", NULL); + of_node_put(vnode_parent); + if (!dev_type) + return NULL; /* construct the kobject name from the device node */ - unit_address = of_get_property(vnode, "reg", NULL); - if (!unit_address) + if (!strcmp(dev_type, "vdevice")) { + unit_address = of_get_property(vnode, "reg", NULL); + if (!unit_address) + return NULL; + snprintf(kobj_name, sizeof(kobj_name), "%x", *unit_address); + } else if (!strcmp(dev_type, "ibm,platform-facilities")) + snprintf(kobj_name, sizeof(kobj_name), "%s", vnode->name); + else return NULL; - snprintf(kobj_name, sizeof(kobj_name), "%x", *unit_address); return vio_find_name(kobj_name); } |