diff options
Diffstat (limited to 'arch/powerpc')
25 files changed, 116 insertions, 47 deletions
diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h index 6fbce72..a0f358d 100644 --- a/arch/powerpc/include/asm/sections.h +++ b/arch/powerpc/include/asm/sections.h @@ -8,7 +8,7 @@ #ifdef __powerpc64__ -extern char _end[]; +extern char __end_interrupts[]; static inline int in_kernel_text(unsigned long addr) { diff --git a/arch/powerpc/include/asm/sparsemem.h b/arch/powerpc/include/asm/sparsemem.h index 54a47ea..0c5fa31 100644 --- a/arch/powerpc/include/asm/sparsemem.h +++ b/arch/powerpc/include/asm/sparsemem.h @@ -16,7 +16,7 @@ #endif /* CONFIG_SPARSEMEM */ #ifdef CONFIG_MEMORY_HOTPLUG -extern void create_section_mapping(unsigned long start, unsigned long end); +extern int create_section_mapping(unsigned long start, unsigned long end); extern int remove_section_mapping(unsigned long start, unsigned long end); #ifdef CONFIG_NUMA extern int hot_add_scn_to_nid(unsigned long scn_addr); diff --git a/arch/powerpc/include/asm/synch.h b/arch/powerpc/include/asm/synch.h index d7cab44..87878c6 100644 --- a/arch/powerpc/include/asm/synch.h +++ b/arch/powerpc/include/asm/synch.h @@ -13,6 +13,7 @@ extern unsigned int __start___lwsync_fixup, __stop___lwsync_fixup; extern void do_lwsync_fixups(unsigned long value, void *fixup_start, void *fixup_end); +extern void do_final_fixups(void); static inline void eieio(void) { diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h index fe6f7c2..bc3c745 100644 --- a/arch/powerpc/include/asm/time.h +++ b/arch/powerpc/include/asm/time.h @@ -219,5 +219,7 @@ DECLARE_PER_CPU(struct cpu_usage, cpu_usage_array); extern void secondary_cpu_time_init(void); extern void iSeries_time_init_early(void); +extern void decrementer_check_overflow(void); + #endif /* __KERNEL__ */ #endif /* __POWERPC_TIME_H */ diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 5b428e3..ca2987d 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -170,16 +170,13 @@ notrace void arch_local_irq_restore(unsigned long en) */ local_paca->hard_enabled = en; -#ifndef CONFIG_BOOKE - /* On server, re-trigger the decrementer if it went negative since - * some processors only trigger on edge transitions of the sign bit. - * - * BookE has a level sensitive decrementer (latches in TSR) so we - * don't need that + /* + * Trigger the decrementer if we have a pending event. Some processors + * only trigger on edge transitions of the sign bit. We might also + * have disabled interrupts long enough that the decrementer wrapped + * to positive. */ - if ((int)mfspr(SPRN_DEC) < 0) - mtspr(SPRN_DEC, 1); -#endif /* CONFIG_BOOKE */ + decrementer_check_overflow(); /* * Force the delivery of pending soft-disabled interrupts on PS3. diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c index b06bdae..ad892f7 100644 --- a/arch/powerpc/kernel/kvm.c +++ b/arch/powerpc/kernel/kvm.c @@ -131,7 +131,6 @@ static void kvm_patch_ins_b(u32 *inst, int addr) /* On relocatable kernels interrupts handlers and our code can be in different regions, so we don't patch them */ - extern u32 __end_interrupts; if ((ulong)inst < (ulong)&__end_interrupts) return; #endif diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c index 822f630..5793c4b 100644 --- a/arch/powerpc/kernel/perf_event.c +++ b/arch/powerpc/kernel/perf_event.c @@ -865,6 +865,7 @@ static void power_pmu_start(struct perf_event *event, int ef_flags) { unsigned long flags; s64 left; + unsigned long val; if (!event->hw.idx || !event->hw.sample_period) return; @@ -880,7 +881,12 @@ static void power_pmu_start(struct perf_event *event, int ef_flags) event->hw.state = 0; left = local64_read(&event->hw.period_left); - write_pmc(event->hw.idx, left); + + val = 0; + if (left < 0x80000000L) + val = 0x80000000L - left; + + write_pmc(event->hw.idx, val); perf_event_update_userpage(event); perf_pmu_enable(event->pmu); diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index 620d792..c7e7b8c 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -107,6 +107,8 @@ notrace unsigned long __init early_init(unsigned long dt_ptr) PTRRELOC(&__start___lwsync_fixup), PTRRELOC(&__stop___lwsync_fixup)); + do_final_fixups(); + return KERNELBASE + offset; } diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index a88bf27..7867fd1 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -352,6 +352,7 @@ void __init setup_system(void) &__start___fw_ftr_fixup, &__stop___fw_ftr_fixup); do_lwsync_fixups(cur_cpu_spec->cpu_features, &__start___lwsync_fixup, &__stop___lwsync_fixup); + do_final_fixups(); /* * Unflatten the device-tree passed by prom_init or kexec diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 03b29a6..2de304a 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -889,6 +889,15 @@ static void __init clocksource_init(void) clock->name, clock->mult, clock->shift); } +void decrementer_check_overflow(void) +{ + u64 now = get_tb_or_rtc(); + struct decrementer_clock *decrementer = &__get_cpu_var(decrementers); + + if (now >= decrementer->next_tb) + set_dec(1); +} + static int decrementer_set_next_event(unsigned long evt, struct clock_event_device *dev) { diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c index 0d08d01..7a8a748 100644 --- a/arch/powerpc/lib/feature-fixups.c +++ b/arch/powerpc/lib/feature-fixups.c @@ -18,6 +18,8 @@ #include <linux/init.h> #include <asm/cputable.h> #include <asm/code-patching.h> +#include <asm/page.h> +#include <asm/sections.h> struct fixup_entry { @@ -128,6 +130,27 @@ void do_lwsync_fixups(unsigned long value, void *fixup_start, void *fixup_end) } } +void do_final_fixups(void) +{ +#if defined(CONFIG_PPC64) && defined(CONFIG_RELOCATABLE) + int *src, *dest; + unsigned long length; + + if (PHYSICAL_START == 0) + return; + + src = (int *)(KERNELBASE + PHYSICAL_START); + dest = (int *)KERNELBASE; + length = (__end_interrupts - _stext) / sizeof(int); + + while (length--) { + patch_instruction(dest, *src); + src++; + dest++; + } +#endif +} + #ifdef CONFIG_FTR_FIXUP_SELFTEST #define check(x) \ diff --git a/arch/powerpc/mm/gup.c b/arch/powerpc/mm/gup.c index fec1320..d7efdbf 100644 --- a/arch/powerpc/mm/gup.c +++ b/arch/powerpc/mm/gup.c @@ -16,16 +16,6 @@ #ifdef __HAVE_ARCH_PTE_SPECIAL -static inline void get_huge_page_tail(struct page *page) -{ - /* - * __split_huge_page_refcount() cannot run - * from under us. - */ - VM_BUG_ON(atomic_read(&page->_count) < 0); - atomic_inc(&page->_count); -} - /* * The performance critical leaf functions are made noinline otherwise gcc * inlines everything into a single function which results in too much @@ -57,8 +47,6 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr, put_page(page); return 0; } - if (PageTail(page)) - get_huge_page_tail(page); pages[*nr] = page; (*nr)++; diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index 26b2872..07f9e9f 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -534,11 +534,11 @@ static unsigned long __init htab_get_table_size(void) } #ifdef CONFIG_MEMORY_HOTPLUG -void create_section_mapping(unsigned long start, unsigned long end) +int create_section_mapping(unsigned long start, unsigned long end) { - BUG_ON(htab_bolt_mapping(start, end, __pa(start), + return htab_bolt_mapping(start, end, __pa(start), pgprot_val(PAGE_KERNEL), mmu_linear_psize, - mmu_kernel_ssize)); + mmu_kernel_ssize); } int remove_section_mapping(unsigned long start, unsigned long end) diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 0b9a5c1..da5eb38 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -390,7 +390,7 @@ static noinline int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long add { unsigned long mask; unsigned long pte_end; - struct page *head, *page; + struct page *head, *page, *tail; pte_t pte; int refs; @@ -413,6 +413,7 @@ static noinline int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long add head = pte_page(pte); page = head + ((addr & (sz-1)) >> PAGE_SHIFT); + tail = page; do { VM_BUG_ON(compound_head(page) != head); pages[*nr] = page; @@ -428,10 +429,20 @@ static noinline int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long add if (unlikely(pte_val(pte) != pte_val(*ptep))) { /* Could be optimized better */ - while (*nr) { - put_page(page); - (*nr)--; - } + *nr -= refs; + while (refs--) + put_page(head); + return 0; + } + + /* + * Any tail page need their mapcount reference taken before we + * return. + */ + while (refs--) { + if (PageTail(tail)) + get_huge_page_tail(tail); + tail++; } return 1; diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 29d4dde..278ec8e 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -123,7 +123,8 @@ int arch_add_memory(int nid, u64 start, u64 size) pgdata = NODE_DATA(nid); start = (unsigned long)__va(start); - create_section_mapping(start, start + size); + if (create_section_mapping(start, start + size)) + return -EINVAL; /* this should work for most non-highmem platforms */ zone = pgdata->node_zones; diff --git a/arch/powerpc/mm/mmu_context_hash64.c b/arch/powerpc/mm/mmu_context_hash64.c index 3bafc3d..4ff587e 100644 --- a/arch/powerpc/mm/mmu_context_hash64.c +++ b/arch/powerpc/mm/mmu_context_hash64.c @@ -136,8 +136,8 @@ int use_cop(unsigned long acop, struct mm_struct *mm) if (!mm || !acop) return -EINVAL; - /* We need to make sure mm_users doesn't change */ - down_read(&mm->mmap_sem); + /* The page_table_lock ensures mm_users won't change under us */ + spin_lock(&mm->page_table_lock); spin_lock(mm->context.cop_lockp); if (mm->context.cop_pid == COP_PID_NONE) { @@ -164,7 +164,7 @@ int use_cop(unsigned long acop, struct mm_struct *mm) out: spin_unlock(mm->context.cop_lockp); - up_read(&mm->mmap_sem); + spin_unlock(&mm->page_table_lock); return ret; } @@ -185,8 +185,8 @@ void drop_cop(unsigned long acop, struct mm_struct *mm) if (WARN_ON_ONCE(!mm)) return; - /* We need to make sure mm_users doesn't change */ - down_read(&mm->mmap_sem); + /* The page_table_lock ensures mm_users won't change under us */ + spin_lock(&mm->page_table_lock); spin_lock(mm->context.cop_lockp); mm->context.acop &= ~acop; @@ -213,7 +213,7 @@ void drop_cop(unsigned long acop, struct mm_struct *mm) } spin_unlock(mm->context.cop_lockp); - up_read(&mm->mmap_sem); + spin_unlock(&mm->page_table_lock); } EXPORT_SYMBOL_GPL(drop_cop); diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 2164006..2c1ae7a 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -1214,11 +1214,12 @@ int hot_add_node_scn_to_nid(unsigned long scn_addr) break; } - of_node_put(memory); if (nid >= 0) break; } + of_node_put(memory); + return nid; } diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c index db092d7..53a6be7 100644 --- a/arch/powerpc/platforms/powermac/smp.c +++ b/arch/powerpc/platforms/powermac/smp.c @@ -414,7 +414,7 @@ static struct irqaction psurge_irqaction = { static void __init smp_psurge_setup_cpu(int cpu_nr) { - if (cpu_nr != 0) + if (cpu_nr != 0 || !psurge_start) return; /* reset the entry point so if we get another intr we won't diff --git a/arch/powerpc/platforms/ps3/interrupt.c b/arch/powerpc/platforms/ps3/interrupt.c index 600ed2c..1aa478b 100644 --- a/arch/powerpc/platforms/ps3/interrupt.c +++ b/arch/powerpc/platforms/ps3/interrupt.c @@ -88,6 +88,7 @@ struct ps3_private { struct ps3_bmp bmp __attribute__ ((aligned (PS3_BMP_MINALIGN))); u64 ppe_id; u64 thread_id; + unsigned long ipi_mask; }; static DEFINE_PER_CPU(struct ps3_private, ps3_private); @@ -144,7 +145,11 @@ static void ps3_chip_unmask(struct irq_data *d) static void ps3_chip_eoi(struct irq_data *d) { const struct ps3_private *pd = irq_data_get_irq_chip_data(d); - lv1_end_of_interrupt_ext(pd->ppe_id, pd->thread_id, d->irq); + + /* non-IPIs are EOIed here. */ + + if (!test_bit(63 - d->irq, &pd->ipi_mask)) + lv1_end_of_interrupt_ext(pd->ppe_id, pd->thread_id, d->irq); } /** @@ -691,6 +696,16 @@ void __init ps3_register_ipi_debug_brk(unsigned int cpu, unsigned int virq) cpu, virq, pd->bmp.ipi_debug_brk_mask); } +void __init ps3_register_ipi_irq(unsigned int cpu, unsigned int virq) +{ + struct ps3_private *pd = &per_cpu(ps3_private, cpu); + + set_bit(63 - virq, &pd->ipi_mask); + + DBG("%s:%d: cpu %u, virq %u, ipi_mask %lxh\n", __func__, __LINE__, + cpu, virq, pd->ipi_mask); +} + static unsigned int ps3_get_irq(void) { struct ps3_private *pd = &__get_cpu_var(ps3_private); @@ -720,6 +735,12 @@ static unsigned int ps3_get_irq(void) BUG(); } #endif + + /* IPIs are EOIed here. */ + + if (test_bit(63 - plug, &pd->ipi_mask)) + lv1_end_of_interrupt_ext(pd->ppe_id, pd->thread_id, plug); + return plug; } diff --git a/arch/powerpc/platforms/ps3/platform.h b/arch/powerpc/platforms/ps3/platform.h index 9a196a8..1a633ed 100644 --- a/arch/powerpc/platforms/ps3/platform.h +++ b/arch/powerpc/platforms/ps3/platform.h @@ -43,6 +43,7 @@ void ps3_mm_shutdown(void); void ps3_init_IRQ(void); void ps3_shutdown_IRQ(int cpu); void __init ps3_register_ipi_debug_brk(unsigned int cpu, unsigned int virq); +void __init ps3_register_ipi_irq(unsigned int cpu, unsigned int virq); /* smp */ diff --git a/arch/powerpc/platforms/ps3/smp.c b/arch/powerpc/platforms/ps3/smp.c index 4c44794..f609345 100644 --- a/arch/powerpc/platforms/ps3/smp.c +++ b/arch/powerpc/platforms/ps3/smp.c @@ -94,6 +94,8 @@ static void __init ps3_smp_setup_cpu(int cpu) if (result) virqs[i] = NO_IRQ; + else + ps3_register_ipi_irq(cpu, virqs[i]); } ps3_register_ipi_debug_brk(cpu, virqs[PPC_MSG_DEBUGGER_BREAK]); diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c index 57ceb92..82766e5 100644 --- a/arch/powerpc/platforms/pseries/dlpar.c +++ b/arch/powerpc/platforms/pseries/dlpar.c @@ -112,6 +112,7 @@ void dlpar_free_cc_nodes(struct device_node *dn) dlpar_free_one_cc_node(dn); } +#define COMPLETE 0 #define NEXT_SIBLING 1 #define NEXT_CHILD 2 #define NEXT_PROPERTY 3 @@ -158,6 +159,9 @@ struct device_node *dlpar_configure_connector(u32 drc_index) spin_unlock(&rtas_data_buf_lock); switch (rc) { + case COMPLETE: + break; + case NEXT_SIBLING: dn = dlpar_parse_cc_node(ccwa); if (!dn) diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c index 46b55cf..3608704 100644 --- a/arch/powerpc/platforms/pseries/eeh.c +++ b/arch/powerpc/platforms/pseries/eeh.c @@ -1338,7 +1338,7 @@ static const struct file_operations proc_eeh_operations = { static int __init eeh_init_proc(void) { if (machine_is(pseries)) - proc_create("ppc64/eeh", 0, NULL, &proc_eeh_operations); + proc_create("powerpc/eeh", 0, NULL, &proc_eeh_operations); return 0; } __initcall(eeh_init_proc); diff --git a/arch/powerpc/platforms/pseries/hvCall_inst.c b/arch/powerpc/platforms/pseries/hvCall_inst.c index f106662..c9311cf 100644 --- a/arch/powerpc/platforms/pseries/hvCall_inst.c +++ b/arch/powerpc/platforms/pseries/hvCall_inst.c @@ -109,7 +109,7 @@ static void probe_hcall_entry(void *ignored, unsigned long opcode, unsigned long if (opcode > MAX_HCALL_OPCODE) return; - h = &get_cpu_var(hcall_stats)[opcode / 4]; + h = &__get_cpu_var(hcall_stats)[opcode / 4]; h->tb_start = mftb(); h->purr_start = mfspr(SPRN_PURR); } @@ -126,8 +126,6 @@ static void probe_hcall_exit(void *ignored, unsigned long opcode, unsigned long h->num_calls++; h->tb_total += mftb() - h->tb_start; h->purr_total += mfspr(SPRN_PURR) - h->purr_start; - - put_cpu_var(hcall_stats); } static int __init hcall_inst_init(void) diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index ed96b37..81e30d9 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -745,6 +745,7 @@ void __trace_hcall_entry(unsigned long opcode, unsigned long *args) goto out; (*depth)++; + preempt_disable(); trace_hcall_entry(opcode, args); (*depth)--; @@ -767,6 +768,7 @@ void __trace_hcall_exit(long opcode, unsigned long retval, (*depth)++; trace_hcall_exit(opcode, retval, retbuf); + preempt_enable(); (*depth)--; out: |