diff options
Diffstat (limited to 'arch/powerpc')
51 files changed, 676 insertions, 278 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index c33e3ad2c8f..fe404e77246 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -572,7 +572,7 @@ config SCHED_SMT config PPC_DENORMALISATION bool "PowerPC denormalisation exception handling" depends on PPC_BOOK3S_64 - default "n" + default "y" if PPC_POWERNV ---help--- Add support for handling denormalisation of single precision values. Useful for bare metal only. If unsure say Y here. @@ -986,6 +986,7 @@ config RELOCATABLE must live at a different physical address than the primary kernel. +# This value must have zeroes in the bottom 60 bits otherwise lots will break config PAGE_OFFSET hex default "0xc000000000000000" diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index 46793b58a76..e17d94d429a 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -264,7 +264,7 @@ do_kvm_##n: \ subi r1,r1,INT_FRAME_SIZE; /* alloc frame on kernel stack */ \ beq- 1f; \ ld r1,PACAKSAVE(r13); /* kernel stack to use */ \ -1: cmpdi cr1,r1,0; /* check if r1 is in userspace */ \ +1: cmpdi cr1,r1,-INT_FRAME_SIZE; /* check if r1 is in userspace */ \ blt+ cr1,3f; /* abort if it is */ \ li r1,(n); /* will be reloaded later */ \ sth r1,PACA_TRAP_SAVE(r13); \ @@ -358,12 +358,12 @@ label##_relon_pSeries: \ /* No guest interrupts come through here */ \ SET_SCRATCH0(r13); /* save r13 */ \ EXCEPTION_RELON_PROLOG_PSERIES(PACA_EXGEN, label##_common, \ - EXC_STD, KVMTEST_PR, vec) + EXC_STD, NOTEST, vec) #define STD_RELON_EXCEPTION_PSERIES_OOL(vec, label) \ .globl label##_relon_pSeries; \ label##_relon_pSeries: \ - EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST_PR, vec); \ + EXCEPTION_PROLOG_1(PACA_EXGEN, NOTEST, vec); \ EXCEPTION_RELON_PROLOG_PSERIES_1(label##_common, EXC_STD) #define STD_RELON_EXCEPTION_HV(loc, vec, label) \ @@ -374,12 +374,12 @@ label##_relon_hv: \ /* No guest interrupts come through here */ \ SET_SCRATCH0(r13); /* save r13 */ \ EXCEPTION_RELON_PROLOG_PSERIES(PACA_EXGEN, label##_common, \ - EXC_HV, KVMTEST, vec) + EXC_HV, NOTEST, vec) #define STD_RELON_EXCEPTION_HV_OOL(vec, label) \ .globl label##_relon_hv; \ label##_relon_hv: \ - EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST, vec); \ + EXCEPTION_PROLOG_1(PACA_EXGEN, NOTEST, vec); \ EXCEPTION_RELON_PROLOG_PSERIES_1(label##_common, EXC_HV) /* This associate vector numbers with bits in paca->irq_happened */ diff --git a/arch/powerpc/include/asm/jump_label.h b/arch/powerpc/include/asm/jump_label.h index ae098c438f0..f016bb699b5 100644 --- a/arch/powerpc/include/asm/jump_label.h +++ b/arch/powerpc/include/asm/jump_label.h @@ -19,7 +19,7 @@ static __always_inline bool arch_static_branch(struct static_key *key) { - asm goto("1:\n\t" + asm_volatile_goto("1:\n\t" "nop\n\t" ".pushsection __jump_table, \"aw\"\n\t" JUMP_ENTRY_TYPE "1b, %l[l_yes], %c0\n\t" diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h index c1df590ec44..49fa55bfbac 100644 --- a/arch/powerpc/include/asm/module.h +++ b/arch/powerpc/include/asm/module.h @@ -82,10 +82,9 @@ struct exception_table_entry; void sort_ex_table(struct exception_table_entry *start, struct exception_table_entry *finish); -#ifdef CONFIG_MODVERSIONS +#if defined(CONFIG_MODVERSIONS) && defined(CONFIG_PPC64) #define ARCH_RELOCATES_KCRCTAB - -extern const unsigned long reloc_start[]; +#define reloc_start PHYSICAL_START #endif #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_MODULE_H */ diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h index 988c812aab5..b9f426212d3 100644 --- a/arch/powerpc/include/asm/page.h +++ b/arch/powerpc/include/asm/page.h @@ -211,9 +211,19 @@ extern long long virt_phys_offset; #define __va(x) ((void *)(unsigned long)((phys_addr_t)(x) + VIRT_PHYS_OFFSET)) #define __pa(x) ((unsigned long)(x) - VIRT_PHYS_OFFSET) #else +#ifdef CONFIG_PPC64 +/* + * gcc miscompiles (unsigned long)(&static_var) - PAGE_OFFSET + * with -mcmodel=medium, so we use & and | instead of - and + on 64-bit. + */ +#define __va(x) ((void *)(unsigned long)((phys_addr_t)(x) | PAGE_OFFSET)) +#define __pa(x) ((unsigned long)(x) & 0x0fffffffffffffffUL) + +#else /* 32-bit, non book E */ #define __va(x) ((void *)(unsigned long)((phys_addr_t)(x) + PAGE_OFFSET - MEMORY_START)) #define __pa(x) ((unsigned long)(x) - PAGE_OFFSET + MEMORY_START) #endif +#endif /* * Unfortunately the PLT is in the BSS in the PPC32 ELF ABI, diff --git a/arch/powerpc/include/asm/pgalloc-32.h b/arch/powerpc/include/asm/pgalloc-32.h index 27b2386f738..842846c1b71 100644 --- a/arch/powerpc/include/asm/pgalloc-32.h +++ b/arch/powerpc/include/asm/pgalloc-32.h @@ -84,10 +84,8 @@ static inline void pgtable_free_tlb(struct mmu_gather *tlb, static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table, unsigned long address) { - struct page *page = page_address(table); - tlb_flush_pgtable(tlb, address); - pgtable_page_dtor(page); - pgtable_free_tlb(tlb, page, 0); + pgtable_page_dtor(table); + pgtable_free_tlb(tlb, page_address(table), 0); } #endif /* _ASM_POWERPC_PGALLOC_32_H */ diff --git a/arch/powerpc/include/asm/pgalloc-64.h b/arch/powerpc/include/asm/pgalloc-64.h index b66ae722a8e..64aaf016b47 100644 --- a/arch/powerpc/include/asm/pgalloc-64.h +++ b/arch/powerpc/include/asm/pgalloc-64.h @@ -144,11 +144,9 @@ static inline void pgtable_free_tlb(struct mmu_gather *tlb, static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table, unsigned long address) { - struct page *page = page_address(table); - tlb_flush_pgtable(tlb, address); - pgtable_page_dtor(page); - pgtable_free_tlb(tlb, page, 0); + pgtable_page_dtor(table); + pgtable_free_tlb(tlb, page_address(table), 0); } #else /* if CONFIG_PPC_64K_PAGES */ diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 14a65836369..419e7125cce 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -247,6 +247,10 @@ struct thread_struct { unsigned long tm_orig_msr; /* Thread's MSR on ctx switch */ struct pt_regs ckpt_regs; /* Checkpointed registers */ + unsigned long tm_tar; + unsigned long tm_ppr; + unsigned long tm_dscr; + /* * Transactional FP and VSX 0-31 register set. * NOTE: the sense of these is the opposite of the integer ckpt_regs! diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h index bc2da154f68..ac204e02292 100644 --- a/arch/powerpc/include/asm/prom.h +++ b/arch/powerpc/include/asm/prom.h @@ -43,9 +43,6 @@ void of_parse_dma_window(struct device_node *dn, const void *dma_window_prop, extern void kdump_move_device_tree(void); -/* CPU OF node matching */ -struct device_node *of_get_cpu_node(int cpu, unsigned int *thread); - /* cache lookup */ struct device_node *of_find_next_cache_node(struct device_node *np); diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 4a9e408644f..e1fb161252e 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -254,19 +254,28 @@ #define SPRN_HRMOR 0x139 /* Real mode offset register */ #define SPRN_HSRR0 0x13A /* Hypervisor Save/Restore 0 */ #define SPRN_HSRR1 0x13B /* Hypervisor Save/Restore 1 */ +/* HFSCR and FSCR bit numbers are the same */ +#define FSCR_TAR_LG 8 /* Enable Target Address Register */ +#define FSCR_EBB_LG 7 /* Enable Event Based Branching */ +#define FSCR_TM_LG 5 /* Enable Transactional Memory */ +#define FSCR_PM_LG 4 /* Enable prob/priv access to PMU SPRs */ +#define FSCR_BHRB_LG 3 /* Enable Branch History Rolling Buffer*/ +#define FSCR_DSCR_LG 2 /* Enable Data Stream Control Register */ +#define FSCR_VECVSX_LG 1 /* Enable VMX/VSX */ +#define FSCR_FP_LG 0 /* Enable Floating Point */ #define SPRN_FSCR 0x099 /* Facility Status & Control Register */ -#define FSCR_TAR (1 << (63-55)) /* Enable Target Address Register */ -#define FSCR_EBB (1 << (63-56)) /* Enable Event Based Branching */ -#define FSCR_DSCR (1 << (63-61)) /* Enable Data Stream Control Register */ +#define FSCR_TAR __MASK(FSCR_TAR_LG) +#define FSCR_EBB __MASK(FSCR_EBB_LG) +#define FSCR_DSCR __MASK(FSCR_DSCR_LG) #define SPRN_HFSCR 0xbe /* HV=1 Facility Status & Control Register */ -#define HFSCR_TAR (1 << (63-55)) /* Enable Target Address Register */ -#define HFSCR_EBB (1 << (63-56)) /* Enable Event Based Branching */ -#define HFSCR_TM (1 << (63-58)) /* Enable Transactional Memory */ -#define HFSCR_PM (1 << (63-60)) /* Enable prob/priv access to PMU SPRs */ -#define HFSCR_BHRB (1 << (63-59)) /* Enable Branch History Rolling Buffer*/ -#define HFSCR_DSCR (1 << (63-61)) /* Enable Data Stream Control Register */ -#define HFSCR_VECVSX (1 << (63-62)) /* Enable VMX/VSX */ -#define HFSCR_FP (1 << (63-63)) /* Enable Floating Point */ +#define HFSCR_TAR __MASK(FSCR_TAR_LG) +#define HFSCR_EBB __MASK(FSCR_EBB_LG) +#define HFSCR_TM __MASK(FSCR_TM_LG) +#define HFSCR_PM __MASK(FSCR_PM_LG) +#define HFSCR_BHRB __MASK(FSCR_BHRB_LG) +#define HFSCR_DSCR __MASK(FSCR_DSCR_LG) +#define HFSCR_VECVSX __MASK(FSCR_VECVSX_LG) +#define HFSCR_FP __MASK(FSCR_FP_LG) #define SPRN_TAR 0x32f /* Target Address Register */ #define SPRN_LPCR 0x13E /* LPAR Control Register */ #define LPCR_VPM0 (1ul << (63-0)) @@ -626,6 +635,7 @@ #define MMCR0_TRIGGER 0x00002000UL /* TRIGGER enable */ #define MMCR0_PMAO 0x00000080UL /* performance monitor alert has occurred, set to 0 after handling exception */ #define MMCR0_SHRFC 0x00000040UL /* SHRre freeze conditions between threads */ +#define MMCR0_FC56 0x00000010UL /* freeze counters 5 and 6 */ #define MMCR0_FCTI 0x00000008UL /* freeze counters in tags inactive mode */ #define MMCR0_FCTA 0x00000004UL /* freeze counters in tags active mode */ #define MMCR0_FCWAIT 0x00000002UL /* freeze counter in WAIT state */ diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h index ffbaabebcdc..48cfc858abd 100644 --- a/arch/powerpc/include/asm/smp.h +++ b/arch/powerpc/include/asm/smp.h @@ -145,6 +145,10 @@ extern void __cpu_die(unsigned int cpu); #define smp_setup_cpu_maps() static inline void inhibit_secondary_onlining(void) {} static inline void uninhibit_secondary_onlining(void) {} +static inline const struct cpumask *cpu_sibling_mask(int cpu) +{ + return cpumask_of(cpu); +} #endif /* CONFIG_SMP */ diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h index 200d763a0a6..685ecc86aa8 100644 --- a/arch/powerpc/include/asm/switch_to.h +++ b/arch/powerpc/include/asm/switch_to.h @@ -15,6 +15,15 @@ extern struct task_struct *__switch_to(struct task_struct *, struct thread_struct; extern struct task_struct *_switch(struct thread_struct *prev, struct thread_struct *next); +#ifdef CONFIG_PPC_BOOK3S_64 +static inline void save_tar(struct thread_struct *prev) +{ + if (cpu_has_feature(CPU_FTR_ARCH_207S)) + prev->tar = mfspr(SPRN_TAR); +} +#else +static inline void save_tar(struct thread_struct *prev) {} +#endif extern void giveup_fpu(struct task_struct *); extern void load_up_fpu(void); diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index 161ab662843..884b001bafc 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -22,7 +22,15 @@ struct device_node; static inline int cpu_to_node(int cpu) { - return numa_cpu_lookup_table[cpu]; + int nid; + + nid = numa_cpu_lookup_table[cpu]; + + /* + * During early boot, the numa-cpu lookup table might not have been + * setup for all CPUs yet. In such cases, default to node 0. + */ + return (nid < 0) ? 0 : nid; } #define parent_node(node) (node) diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c index ee5b690a0be..52e5758ea36 100644 --- a/arch/powerpc/kernel/align.c +++ b/arch/powerpc/kernel/align.c @@ -764,6 +764,16 @@ int fix_alignment(struct pt_regs *regs) nb = aligninfo[instr].len; flags = aligninfo[instr].flags; + /* ldbrx/stdbrx overlap lfs/stfs in the DSISR unfortunately */ + if (IS_XFORM(instruction) && ((instruction >> 1) & 0x3ff) == 532) { + nb = 8; + flags = LD+SW; + } else if (IS_XFORM(instruction) && + ((instruction >> 1) & 0x3ff) == 660) { + nb = 8; + flags = ST+SW; + } + /* Byteswap little endian loads and stores */ swiz = 0; if (regs->msr & MSR_LE) { diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 6f16ffafa6f..302886b77de 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -139,6 +139,9 @@ int main(void) DEFINE(THREAD_TM_TFHAR, offsetof(struct thread_struct, tm_tfhar)); DEFINE(THREAD_TM_TEXASR, offsetof(struct thread_struct, tm_texasr)); DEFINE(THREAD_TM_TFIAR, offsetof(struct thread_struct, tm_tfiar)); + DEFINE(THREAD_TM_TAR, offsetof(struct thread_struct, tm_tar)); + DEFINE(THREAD_TM_PPR, offsetof(struct thread_struct, tm_ppr)); + DEFINE(THREAD_TM_DSCR, offsetof(struct thread_struct, tm_dscr)); DEFINE(PT_CKPT_REGS, offsetof(struct thread_struct, ckpt_regs)); DEFINE(THREAD_TRANSACT_VR0, offsetof(struct thread_struct, transact_vr[0])); diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c index 92c6b008dd2..b4437e8a7a8 100644 --- a/arch/powerpc/kernel/cacheinfo.c +++ b/arch/powerpc/kernel/cacheinfo.c @@ -788,6 +788,9 @@ static void remove_cache_dir(struct cache_dir *cache_dir) { remove_index_dirs(cache_dir); + /* Remove cache dir from sysfs */ + kobject_del(cache_dir->kobj); + kobject_put(cache_dir->kobj); kfree(cache_dir); diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c index 9ec3fe174cb..555ae67e408 100644 --- a/arch/powerpc/kernel/crash_dump.c +++ b/arch/powerpc/kernel/crash_dump.c @@ -108,17 +108,19 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf, size_t csize, unsigned long offset, int userbuf) { void *vaddr; + phys_addr_t paddr; if (!csize) return 0; csize = min_t(size_t, csize, PAGE_SIZE); + paddr = pfn << PAGE_SHIFT; - if ((min_low_pfn < pfn) && (pfn < max_pfn)) { - vaddr = __va(pfn << PAGE_SHIFT); + if (memblock_is_region_memory(paddr, csize)) { + vaddr = __va(paddr); csize = copy_oldmem_vaddr(vaddr, buf, csize, offset, userbuf); } else { - vaddr = __ioremap(pfn << PAGE_SHIFT, PAGE_SIZE, 0); + vaddr = __ioremap(paddr, PAGE_SIZE, 0); csize = copy_oldmem_vaddr(vaddr, buf, csize, offset, userbuf); iounmap(vaddr); } diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 8741c854e03..38847767012 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -449,15 +449,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_DSCR) #ifdef CONFIG_PPC_BOOK3S_64 BEGIN_FTR_SECTION - /* - * Back up the TAR across context switches. Note that the TAR is not - * available for use in the kernel. (To provide this, the TAR should - * be backed up/restored on exception entry/exit instead, and be in - * pt_regs. FIXME, this should be in pt_regs anyway (for debug).) - */ - mfspr r0,SPRN_TAR - std r0,THREAD_TAR(r3) - /* Event based branch registers */ mfspr r0, SPRN_BESCR std r0, THREAD_BESCR(r3) @@ -584,9 +575,34 @@ BEGIN_FTR_SECTION ld r7,DSCR_DEFAULT@toc(2) ld r0,THREAD_DSCR(r4) cmpwi r6,0 + li r8, FSCR_DSCR bne 1f ld r0,0(r7) -1: cmpd r0,r25 + b 3f +1: + BEGIN_FTR_SECTION_NESTED(70) + mfspr r6, SPRN_FSCR + or r6, r6, r8 + mtspr SPRN_FSCR, r6 + BEGIN_FTR_SECTION_NESTED(69) + mfspr r6, SPRN_HFSCR + or r6, r6, r8 + mtspr SPRN_HFSCR, r6 + END_FTR_SECTION_NESTED(CPU_FTR_HVMODE, CPU_FTR_HVMODE, 69) + b 4f + END_FTR_SECTION_NESTED(CPU_FTR_ARCH_207S, CPU_FTR_ARCH_207S, 70) +3: + BEGIN_FTR_SECTION_NESTED(70) + mfspr r6, SPRN_FSCR + andc r6, r6, r8 + mtspr SPRN_FSCR, r6 + BEGIN_FTR_SECTION_NESTED(69) + mfspr r6, SPRN_HFSCR + andc r6, r6, r8 + mtspr SPRN_HFSCR, r6 + END_FTR_SECTION_NESTED(CPU_FTR_HVMODE, CPU_FTR_HVMODE, 69) + END_FTR_SECTION_NESTED(CPU_FTR_ARCH_207S, CPU_FTR_ARCH_207S, 70) +4: cmpd r0,r25 beq 2f mtspr SPRN_DSCR,r0 2: diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 40e4a17c8ba..902ca3c6b4b 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -341,10 +341,17 @@ vsx_unavailable_pSeries_1: EXCEPTION_PROLOG_0(PACA_EXGEN) b vsx_unavailable_pSeries +facility_unavailable_trampoline: . = 0xf60 SET_SCRATCH0(r13) EXCEPTION_PROLOG_0(PACA_EXGEN) - b tm_unavailable_pSeries + b facility_unavailable_pSeries + +hv_facility_unavailable_trampoline: + . = 0xf80 + SET_SCRATCH0(r13) + EXCEPTION_PROLOG_0(PACA_EXGEN) + b facility_unavailable_hv #ifdef CONFIG_CBE_RAS STD_EXCEPTION_HV(0x1200, 0x1202, cbe_system_error) @@ -522,8 +529,10 @@ denorm_done: KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf20) STD_EXCEPTION_PSERIES_OOL(0xf40, vsx_unavailable) KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf40) - STD_EXCEPTION_PSERIES_OOL(0xf60, tm_unavailable) + STD_EXCEPTION_PSERIES_OOL(0xf60, facility_unavailable) KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf60) + STD_EXCEPTION_HV_OOL(0xf82, facility_unavailable) + KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xf82) /* * An interrupt came in while soft-disabled. We set paca->irq_happened, then: @@ -793,14 +802,10 @@ system_call_relon_pSeries: STD_RELON_EXCEPTION_PSERIES(0x4d00, 0xd00, single_step) . = 0x4e00 - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b h_data_storage_relon_hv + b . /* Can't happen, see v2.07 Book III-S section 6.5 */ . = 0x4e20 - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b h_instr_storage_relon_hv + b . /* Can't happen, see v2.07 Book III-S section 6.5 */ . = 0x4e40 SET_SCRATCH0(r13) @@ -808,9 +813,7 @@ system_call_relon_pSeries: b emulation_assist_relon_hv . = 0x4e60 - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b hmi_exception_relon_hv + b . /* Can't happen, see v2.07 Book III-S section 6.5 */ . = 0x4e80 SET_SCRATCH0(r13) @@ -835,11 +838,17 @@ vsx_unavailable_relon_pSeries_1: EXCEPTION_PROLOG_0(PACA_EXGEN) b vsx_unavailable_relon_pSeries -tm_unavailable_relon_pSeries_1: +facility_unavailable_relon_trampoline: . = 0x4f60 SET_SCRATCH0(r13) EXCEPTION_PROLOG_0(PACA_EXGEN) - b tm_unavailable_relon_pSeries + b facility_unavailable_relon_pSeries + +hv_facility_unavailable_relon_trampoline: + . = 0x4f80 + SET_SCRATCH0(r13) + EXCEPTION_PROLOG_0(PACA_EXGEN) + b hv_facility_unavailable_relon_hv STD_RELON_EXCEPTION_PSERIES(0x5300, 0x1300, instruction_breakpoint) #ifdef CONFIG_PPC_DENORMALISATION @@ -1165,36 +1174,22 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX) bl .vsx_unavailable_exception b .ret_from_except - .align 7 - .globl tm_unavailable_common -tm_unavailable_common: - EXCEPTION_PROLOG_COMMON(0xf60, PACA_EXGEN) - bl .save_nvgprs - DISABLE_INTS - addi r3,r1,STACK_FRAME_OVERHEAD - bl .tm_unavailable_exception - b .ret_from_except + STD_EXCEPTION_COMMON(0xf60, facility_unavailable, .facility_unavailable_exception) + STD_EXCEPTION_COMMON(0xf80, hv_facility_unavailable, .facility_unavailable_exception) .align 7 .globl __end_handlers __end_handlers: /* Equivalents to the above handlers for relocation-on interrupt vectors */ - STD_RELON_EXCEPTION_HV_OOL(0xe00, h_data_storage) - KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe00) - STD_RELON_EXCEPTION_HV_OOL(0xe20, h_instr_storage) - KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe20) STD_RELON_EXCEPTION_HV_OOL(0xe40, emulation_assist) - KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe40) - STD_RELON_EXCEPTION_HV_OOL(0xe60, hmi_exception) - KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe60) MASKABLE_RELON_EXCEPTION_HV_OOL(0xe80, h_doorbell) - KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe80) STD_RELON_EXCEPTION_PSERIES_OOL(0xf00, performance_monitor) STD_RELON_EXCEPTION_PSERIES_OOL(0xf20, altivec_unavailable) STD_RELON_EXCEPTION_PSERIES_OOL(0xf40, vsx_unavailable) - STD_RELON_EXCEPTION_PSERIES_OOL(0xf60, tm_unavailable) + STD_RELON_EXCEPTION_PSERIES_OOL(0xf60, facility_unavailable) + STD_RELON_EXCEPTION_HV_OOL(0xf80, hv_facility_unavailable) #if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) /* diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index b61363d557b..192a3f562bd 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -467,6 +467,7 @@ _STATIC(__after_prom_start) mtctr r8 bctr +.balign 8 p_end: .llong _end - _stext 4: /* Now copy the rest of the kernel up to _end */ diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index a949bdfc962..f0b47d1a6b0 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -176,7 +176,7 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) length_max = 512 ; /* 64 doublewords */ /* DAWR region can't cross 512 boundary */ if ((bp->attr.bp_addr >> 10) != - ((bp->attr.bp_addr + bp->attr.bp_len) >> 10)) + ((bp->attr.bp_addr + bp->attr.bp_len - 1) >> 10)) return -EINVAL; } if (info->len > @@ -250,6 +250,7 @@ int __kprobes hw_breakpoint_handler(struct die_args *args) * we still need to single-step the instruction, but we don't * generate an event. */ + info->type &= ~HW_BRK_TYPE_EXTRANEOUS_IRQ; if (!((bp->attr.bp_addr <= dar) && (dar - bp->attr.bp_addr < bp->attr.bp_len))) info->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ; diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index c0d0dbddfba..93d8d96840b 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -658,7 +658,7 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid) /* number of bytes needed for the bitmap */ sz = BITS_TO_LONGS(tbl->it_size) * sizeof(unsigned long); - page = alloc_pages_node(nid, GFP_ATOMIC, get_order(sz)); + page = alloc_pages_node(nid, GFP_KERNEL, get_order(sz)); if (!page) panic("iommu_init_table: Can't allocate %ld bytes\n", sz); tbl->it_map = page_address(page); diff --git a/arch/powerpc/kernel/lparcfg.c b/arch/powerpc/kernel/lparcfg.c index d92f3871e9c..e2a0a162299 100644 --- a/arch/powerpc/kernel/lparcfg.c +++ b/arch/powerpc/kernel/lparcfg.c @@ -35,7 +35,13 @@ #include <asm/vdso_datapage.h> #include <asm/vio.h> #include <asm/mmu.h> +#include <asm/machdep.h> + +/* + * This isn't a module but we expose that to userspace + * via /proc so leave the definitions here + */ #define MODULE_VERS "1.9" #define MODULE_NAME "lparcfg" @@ -418,7 +424,8 @@ static void parse_em_data(struct seq_file *m) { unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; - if (plpar_hcall(H_GET_EM_PARMS, retbuf) == H_SUCCESS) + if (firmware_has_feature(FW_FEATURE_LPAR) && + plpar_hcall(H_GET_EM_PARMS, retbuf) == H_SUCCESS) seq_printf(m, "power_mode_data=%016lx\n", retbuf[0]); } @@ -677,7 +684,6 @@ static int lparcfg_open(struct inode *inode, struct file *file) } static const struct file_operations lparcfg_fops = { - .owner = THIS_MODULE, .read = seq_read, .write = lparcfg_write, .open = lparcfg_open, @@ -699,14 +705,4 @@ static int __init lparcfg_init(void) } return 0; } - -static void __exit lparcfg_cleanup(void) -{ - remove_proc_subtree("powerpc/lparcfg", NULL); -} - -module_init(lparcfg_init); -module_exit(lparcfg_cleanup); -MODULE_DESCRIPTION("Interface for LPAR configuration data"); -MODULE_AUTHOR("Dave Engebretsen"); -MODULE_LICENSE("GPL"); +machine_device_initcall(pseries, lparcfg_init); diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 076d1242507..7baa27b7abb 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -600,6 +600,16 @@ struct task_struct *__switch_to(struct task_struct *prev, struct ppc64_tlb_batch *batch; #endif + /* Back up the TAR across context switches. + * Note that the TAR is not available for use in the kernel. (To + * provide this, the TAR should be backed up/restored on exception + * entry/exit instead, and be in pt_regs. FIXME, this should be in + * pt_regs anyway (for debug).) + * Save the TAR here before we do treclaim/trecheckpoint as these + * will change the TAR. + */ + save_tar(&prev->thread); + __switch_to_tm(prev); #ifdef CONFIG_SMP diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 8b6f7a99cce..00610a34fb9 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -827,49 +827,10 @@ static int __init prom_reconfig_setup(void) __initcall(prom_reconfig_setup); #endif -/* Find the device node for a given logical cpu number, also returns the cpu - * local thread number (index in ibm,interrupt-server#s) if relevant and - * asked for (non NULL) - */ -struct device_node *of_get_cpu_node(int cpu, unsigned int *thread) +bool arch_match_cpu_phys_id(int cpu, u64 phys_id) { - int hardid; - struct device_node *np; - - hardid = get_hard_smp_processor_id(cpu); - - for_each_node_by_type(np, "cpu") { - const u32 *intserv; - unsigned int plen, t; - - /* Check for ibm,ppc-interrupt-server#s. If it doesn't exist - * fallback to "reg" property and assume no threads - */ - intserv = of_get_property(np, "ibm,ppc-interrupt-server#s", - &plen); - if (intserv == NULL) { - const u32 *reg = of_get_property(np, "reg", NULL); - if (reg == NULL) - continue; - if (*reg == hardid) { - if (thread) - *thread = 0; - return np; - } - } else { - plen /= sizeof(u32); - for (t = 0; t < plen; t++) { - if (hardid == intserv[t]) { - if (thread) - *thread = t; - return np; - } - } - } - } - return NULL; + return (int)phys_id == get_hard_smp_processor_id(cpu); } -EXPORT_SYMBOL(of_get_cpu_node); #if defined(CONFIG_DEBUG_FS) && defined(DEBUG) static struct debugfs_blob_wrapper flat_dt_blob; diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index 98c2fc19871..64f7bd5b1b0 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -1449,7 +1449,9 @@ static long ppc_set_hwdebug(struct task_struct *child, */ if (bp_info->addr_mode == PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE) { len = bp_info->addr2 - bp_info->addr; - } else if (bp_info->addr_mode != PPC_BREAKPOINT_MODE_EXACT) { + } else if (bp_info->addr_mode == PPC_BREAKPOINT_MODE_EXACT) + len = 1; + else { ptrace_put_breakpoints(child); return -EINVAL; } diff --git a/arch/powerpc/kernel/reloc_64.S b/arch/powerpc/kernel/reloc_64.S index b47a0e1ab00..c712ecec13b 100644 --- a/arch/powerpc/kernel/reloc_64.S +++ b/arch/powerpc/kernel/reloc_64.S @@ -81,6 +81,7 @@ _GLOBAL(relocate) 6: blr +.balign 8 p_dyn: .llong __dynamic_start - 0b p_rela: .llong __rela_dyn_start - 0b p_st: .llong _stext - 0b diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index e379d3fd169..389fb8077cc 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -76,7 +76,7 @@ #endif int boot_cpuid = 0; -int __initdata spinning_secondaries; +int spinning_secondaries; u64 ppc64_pft_size; /* Pick defaults since we might want to patch instructions diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 201385c3a1a..7e9dff80e1d 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -407,7 +407,8 @@ inline unsigned long copy_transact_fpr_from_user(struct task_struct *task, * altivec/spe instructions at some point. */ static int save_user_regs(struct pt_regs *regs, struct mcontext __user *frame, - int sigret, int ctx_has_vsx_region) + struct mcontext __user *tm_frame, int sigret, + int ctx_has_vsx_region) { unsigned long msr = regs->msr; @@ -441,6 +442,12 @@ static int save_user_regs(struct pt_regs *regs, struct mcontext __user *frame, #endif /* CONFIG_ALTIVEC */ if (copy_fpr_to_user(&frame->mc_fregs, current)) return 1; + + /* + * Clear the MSR VSX bit to indicate there is no valid state attached + * to this context, except in the specific case below where we set it. + */ + msr &= ~MSR_VSX; #ifdef CONFIG_VSX /* * Copy VSR 0-31 upper half from thread_struct to local @@ -475,6 +482,12 @@ static int save_user_regs(struct pt_regs *regs, struct mcontext __user *frame, if (__put_user(msr, &frame->mc_gregs[PT_MSR])) return 1; + /* We need to write 0 the MSR top 32 bits in the tm frame so that we + * can check it on the restore to see if TM is active + */ + if (tm_frame && __put_user(0, &tm_frame->mc_gregs[PT_MSR])) + return 1; + if (sigret) { /* Set up the sigreturn trampoline: li r0,sigret; sc */ if (__put_user(0x38000000UL + sigret, &frame->tramp[0]) @@ -747,7 +760,7 @@ static long restore_tm_user_regs(struct pt_regs *regs, struct mcontext __user *tm_sr) { long err; - unsigned long msr; + unsigned long msr, msr_hi; #ifdef CONFIG_VSX int i; #endif @@ -852,8 +865,11 @@ static long restore_tm_user_regs(struct pt_regs *regs, tm_enable(); /* This loads the checkpointed FP/VEC state, if used */ tm_recheckpoint(¤t->thread, msr); - /* The task has moved into TM state S, so ensure MSR reflects this */ - regs->msr = (regs->msr & ~MSR_TS_MASK) | MSR_TS_S; + /* Get the top half of the MSR */ + if (__get_user(msr_hi, &tm_sr->mc_gregs[PT_MSR])) + return 1; + /* Pull in MSR TM from user context */ + regs->msr = (regs->msr & ~MSR_TS_MASK) | ((msr_hi<<32) & MSR_TS_MASK); /* This loads the speculative FP/VEC state, if used */ if (msr & MSR_FP) { @@ -952,6 +968,7 @@ int handle_rt_signal32(unsigned long sig, struct k_sigaction *ka, { struct rt_sigframe __user *rt_sf; struct mcontext __user *frame; + struct mcontext __user *tm_frame = NULL; void __user *addr; unsigned long newsp = 0; int sigret; @@ -985,23 +1002,24 @@ int handle_rt_signal32(unsigned long sig, struct k_sigaction *ka, } #ifdef CONFIG_PPC_TRANSACTIONAL_MEM + tm_frame = &rt_sf->uc_transact.uc_mcontext; if (MSR_TM_ACTIVE(regs->msr)) { - if (save_tm_user_regs(regs, &rt_sf->uc.uc_mcontext, - &rt_sf->uc_transact.uc_mcontext, sigret)) + if (save_tm_user_regs(regs, frame, tm_frame, sigret)) goto badframe; } else #endif - if (save_user_regs(regs, frame, sigret, 1)) + { + if (save_user_regs(regs, frame, tm_frame, sigret, 1)) goto badframe; + } regs->link = tramp; #ifdef CONFIG_PPC_TRANSACTIONAL_MEM if (MSR_TM_ACTIVE(regs->msr)) { if (__put_user((unsigned long)&rt_sf->uc_transact, &rt_sf->uc.uc_link) - || __put_user(to_user_ptr(&rt_sf->uc_transact.uc_mcontext), - &rt_sf->uc_transact.uc_regs)) + || __put_user((unsigned long)tm_frame, &rt_sf->uc_transact.uc_regs)) goto badframe; } else @@ -1170,7 +1188,7 @@ long sys_swapcontext(struct ucontext __user *old_ctx, mctx = (struct mcontext __user *) ((unsigned long) &old_ctx->uc_mcontext & ~0xfUL); if (!access_ok(VERIFY_WRITE, old_ctx, ctx_size) - || save_user_regs(regs, mctx, 0, ctx_has_vsx_region) + || save_user_regs(regs, mctx, NULL, 0, ctx_has_vsx_region) || put_sigset_t(&old_ctx->uc_sigmask, ¤t->blocked) || __put_user(to_user_ptr(mctx), &old_ctx->uc_regs)) return -EFAULT; @@ -1233,7 +1251,7 @@ long sys_rt_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8, if (__get_user(msr_hi, &mcp->mc_gregs[PT_MSR])) goto bad; - if (MSR_TM_SUSPENDED(msr_hi<<32)) { + if (MSR_TM_ACTIVE(msr_hi<<32)) { /* We only recheckpoint on return if we're * transaction. */ @@ -1392,6 +1410,7 @@ int handle_signal32(unsigned long sig, struct k_sigaction *ka, { struct sigcontext __user *sc; struct sigframe __user *frame; + struct mcontext __user *tm_mctx = NULL; unsigned long newsp = 0; int sigret; unsigned long tramp; @@ -1425,6 +1444,7 @@ int handle_signal32(unsigned long sig, struct k_sigaction *ka, } #ifdef CONFIG_PPC_TRANSACTIONAL_MEM + tm_mctx = &frame->mctx_transact; if (MSR_TM_ACTIVE(regs->msr)) { if (save_tm_user_regs(regs, &frame->mctx, &frame->mctx_transact, sigret)) @@ -1432,8 +1452,10 @@ int handle_signal32(unsigned long sig, struct k_sigaction *ka, } else #endif - if (save_user_regs(regs, &frame->mctx, sigret, 1)) + { + if (save_user_regs(regs, &frame->mctx, tm_mctx, sigret, 1)) goto badframe; + } regs->link = tramp; @@ -1481,16 +1503,22 @@ badframe: long sys_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8, struct pt_regs *regs) { + struct sigframe __user *sf; struct sigcontext __user *sc; struct sigcontext sigctx; struct mcontext __user *sr; void __user *addr; sigset_t set; +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + struct mcontext __user *mcp, *tm_mcp; + unsigned long msr_hi; +#endif /* Always make any pending restarted system calls return -EINTR */ current_thread_info()->restart_block.fn = do_no_restart_syscall; - sc = (struct sigcontext __user *)(regs->gpr[1] + __SIGNAL_FRAMESIZE); + sf = (struct sigframe __user *)(regs->gpr[1] + __SIGNAL_FRAMESIZE); + sc = &sf->sctx; addr = sc; if (copy_from_user(&sigctx, sc, sizeof(sigctx))) goto badframe; @@ -1507,11 +1535,25 @@ long sys_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8, #endif set_current_blocked(&set); - sr = (struct mcontext __user *)from_user_ptr(sigctx.regs); - addr = sr; - if (!access_ok(VERIFY_READ, sr, sizeof(*sr)) - || restore_user_regs(regs, sr, 1)) +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + mcp = (struct mcontext __user *)&sf->mctx; + tm_mcp = (struct mcontext __user *)&sf->mctx_transact; + if (__get_user(msr_hi, &tm_mcp->mc_gregs[PT_MSR])) goto badframe; + if (MSR_TM_ACTIVE(msr_hi<<32)) { + if (!cpu_has_feature(CPU_FTR_TM)) + goto badframe; + if (restore_tm_user_regs(regs, mcp, tm_mcp)) + goto badframe; + } else +#endif + { + sr = (struct mcontext __user *)from_user_ptr(sigctx.regs); + addr = sr; + if (!access_ok(VERIFY_READ, sr, sizeof(*sr)) + || restore_user_regs(regs, sr, 1)) + goto badframe; + } set_thread_flag(TIF_RESTOREALL); return 0; diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 345947367ec..35c20a1fb36 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -121,6 +121,12 @@ static long setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs, flush_fp_to_thread(current); /* copy fpr regs and fpscr */ err |= copy_fpr_to_user(&sc->fp_regs, current); + + /* + * Clear the MSR VSX bit to indicate there is no valid state attached + * to this context, except in the specific case below where we set it. + */ + msr &= ~MSR_VSX; #ifdef CONFIG_VSX /* * Copy VSX low doubleword to local buffer for formatting, @@ -410,6 +416,10 @@ static long restore_tm_sigcontexts(struct pt_regs *regs, /* get MSR separately, transfer the LE bit if doing signal return */ err |= __get_user(msr, &sc->gp_regs[PT_MSR]); + /* pull in MSR TM from user context */ + regs->msr = (regs->msr & ~MSR_TS_MASK) | (msr & MSR_TS_MASK); + + /* pull in MSR LE from user context */ regs->msr = (regs->msr & ~MSR_LE) | (msr & MSR_LE); /* The following non-GPR non-FPR non-VR state is also checkpointed: */ @@ -505,8 +515,6 @@ static long restore_tm_sigcontexts(struct pt_regs *regs, tm_enable(); /* This loads the checkpointed FP/VEC state, if used */ tm_recheckpoint(¤t->thread, msr); - /* The task has moved into TM state S, so ensure MSR reflects this: */ - regs->msr = (regs->msr & ~MSR_TS_MASK) | __MASK(33); /* This loads the speculative FP/VEC state, if used */ if (msr & MSR_FP) { @@ -654,7 +662,7 @@ int sys_rt_sigreturn(unsigned long r3, unsigned long r4, unsigned long r5, #ifdef CONFIG_PPC_TRANSACTIONAL_MEM if (__get_user(msr, &uc->uc_mcontext.gp_regs[PT_MSR])) goto badframe; - if (MSR_TM_SUSPENDED(msr)) { + if (MSR_TM_ACTIVE(msr)) { /* We recheckpoint on return. */ struct ucontext __user *uc_transact; if (__get_user(uc_transact, &uc->uc_link)) diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index e68a84568b8..a15fd1a0690 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -17,6 +17,7 @@ #include <asm/machdep.h> #include <asm/smp.h> #include <asm/pmc.h> +#include <asm/firmware.h> #include "cacheinfo.h" @@ -179,15 +180,25 @@ SYSFS_PMCSETUP(spurr, SPRN_SPURR); SYSFS_PMCSETUP(dscr, SPRN_DSCR); SYSFS_PMCSETUP(pir, SPRN_PIR); +/* + Lets only enable read for phyp resources and + enable write when needed with a separate function. + Lets be conservative and default to pseries. +*/ static DEVICE_ATTR(mmcra, 0600, show_mmcra, store_mmcra); static DEVICE_ATTR(spurr, 0400, show_spurr, NULL); static DEVICE_ATTR(dscr, 0600, show_dscr, store_dscr); -static DEVICE_ATTR(purr, 0600, show_purr, store_purr); +static DEVICE_ATTR(purr, 0400, show_purr, store_purr); static DEVICE_ATTR(pir, 0400, show_pir, NULL); unsigned long dscr_default = 0; EXPORT_SYMBOL(dscr_default); +static void add_write_permission_dev_attr(struct device_attribute *attr) +{ + attr->attr.mode |= 0200; +} + static ssize_t show_dscr_default(struct device *dev, struct device_attribute *attr, char *buf) { @@ -394,8 +405,11 @@ static void __cpuinit register_cpu_online(unsigned int cpu) if (cpu_has_feature(CPU_FTR_MMCRA)) device_create_file(s, &dev_attr_mmcra); - if (cpu_has_feature(CPU_FTR_PURR)) + if (cpu_has_feature(CPU_FTR_PURR)) { + if (!firmware_has_feature(FW_FEATURE_LPAR)) + add_write_permission_dev_attr(&dev_attr_purr); device_create_file(s, &dev_attr_purr); + } if (cpu_has_feature(CPU_FTR_SPURR)) device_create_file(s, &dev_attr_spurr); diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S index 2da67e7a16d..f2abb219a17 100644 --- a/arch/powerpc/kernel/tm.S +++ b/arch/powerpc/kernel/tm.S @@ -79,6 +79,11 @@ _GLOBAL(tm_abort) TABORT(R3) blr + .section ".toc","aw" +DSCR_DEFAULT: + .tc dscr_default[TC],dscr_default + + .section ".text" /* void tm_reclaim(struct thread_struct *thread, * unsigned long orig_msr, @@ -178,11 +183,18 @@ dont_backup_fp: std r1, PACATMSCRATCH(r13) ld r1, PACAR1(r13) + /* Store the PPR in r11 and reset to decent value */ + std r11, GPR11(r1) /* Temporary stash */ + mfspr r11, SPRN_PPR + HMT_MEDIUM + /* Now get some more GPRS free */ std r7, GPR7(r1) /* Temporary stash */ std r12, GPR12(r1) /* '' '' '' */ ld r12, STACK_PARAM(0)(r1) /* Param 0, thread_struct * */ + std r11, THREAD_TM_PPR(r12) /* Store PPR and free r11 */ + addi r7, r12, PT_CKPT_REGS /* Thread's ckpt_regs */ /* Make r7 look like an exception frame so that we @@ -194,15 +206,19 @@ dont_backup_fp: SAVE_GPR(0, r7) /* user r0 */ SAVE_GPR(2, r7) /* user r2 */ SAVE_4GPRS(3, r7) /* user r3-r6 */ - SAVE_4GPRS(8, r7) /* user r8-r11 */ + SAVE_GPR(8, r7) /* user r8 */ + SAVE_GPR(9, r7) /* user r9 */ + SAVE_GPR(10, r7) /* user r10 */ ld r3, PACATMSCRATCH(r13) /* user r1 */ ld r4, GPR7(r1) /* user r7 */ - ld r5, GPR12(r1) /* user r12 */ - GET_SCRATCH0(6) /* user r13 */ + ld r5, GPR11(r1) /* user r11 */ + ld r6, GPR12(r1) /* user r12 */ + GET_SCRATCH0(8) /* user r13 */ std r3, GPR1(r7) std r4, GPR7(r7) - std r5, GPR12(r7) - std r6, GPR13(r7) + std r5, GPR11(r7) + std r6, GPR12(r7) + std r8, GPR13(r7) SAVE_NVGPRS(r7) /* user r14-r31 */ @@ -224,6 +240,14 @@ dont_backup_fp: std r5, _CCR(r7) std r6, _XER(r7) + + /* ******************** TAR, DSCR ********** */ + mfspr r3, SPRN_TAR + mfspr r4, SPRN_DSCR + + std r3, THREAD_TM_TAR(r12) + std r4, THREAD_TM_DSCR(r12) + /* MSR and flags: We don't change CRs, and we don't need to alter * MSR. */ @@ -239,7 +263,7 @@ dont_backup_fp: std r3, THREAD_TM_TFHAR(r12) std r4, THREAD_TM_TFIAR(r12) - /* AMR and PPR are checkpointed too, but are unsupported by Linux. */ + /* AMR is checkpointed too, but is unsupported by Linux. */ /* Restore original MSR/IRQ state & clear TM mode */ ld r14, TM_FRAME_L0(r1) /* Orig MSR */ @@ -255,6 +279,12 @@ dont_backup_fp: mtcr r4 mtlr r0 ld r2, 40(r1) + + /* Load system default DSCR */ + ld r4, DSCR_DEFAULT@toc(r2) + ld r0, 0(r4) + mtspr SPRN_DSCR, r0 + blr @@ -338,35 +368,51 @@ dont_restore_fp: mtmsr r6 /* FP/Vec off again! */ restore_gprs: + /* ******************** CR,LR,CCR,MSR ********** */ - ld r3, _CTR(r7) - ld r4, _LINK(r7) - ld r5, _CCR(r7) - ld r6, _XER(r7) + ld r4, _CTR(r7) + ld r5, _LINK(r7) + ld r6, _CCR(r7) + ld r8, _XER(r7) - mtctr r3 - mtlr r4 - mtcr r5 - mtxer r6 + mtctr r4 + mtlr r5 + mtcr r6 + mtxer r8 + + /* ******************** TAR ******************** */ + ld r4, THREAD_TM_TAR(r3) + mtspr SPRN_TAR, r4 + + /* Load up the PPR and DSCR in GPRs only at this stage */ + ld r5, THREAD_TM_DSCR(r3) + ld r6, THREAD_TM_PPR(r3) /* MSR and flags: We don't change CRs, and we don't need to alter * MSR. */ REST_4GPRS(0, r7) /* GPR0-3 */ - REST_GPR(4, r7) /* GPR4-6 */ - REST_GPR(5, r7) - REST_GPR(6, r7) + REST_GPR(4, r7) /* GPR4 */ REST_4GPRS(8, r7) /* GPR8-11 */ REST_2GPRS(12, r7) /* GPR12-13 */ REST_NVGPRS(r7) /* GPR14-31 */ - ld r7, GPR7(r7) /* GPR7 */ + /* Load up PPR and DSCR here so we don't run with user values for long + */ + mtspr SPRN_DSCR, r5 + mtspr SPRN_PPR, r6 + + REST_GPR(5, r7) /* GPR5-7 */ + REST_GPR(6, r7) + ld r7, GPR7(r7) /* Commit register state as checkpointed state: */ TRECHKPT + HMT_MEDIUM + /* Our transactional state has now changed. * * Now just get out of here. Transactional (current) state will be @@ -385,6 +431,12 @@ restore_gprs: mtcr r4 mtlr r0 ld r2, 40(r1) + + /* Load system default DSCR */ + ld r4, DSCR_DEFAULT@toc(r2) + ld r0, 0(r4) + mtspr SPRN_DSCR, r0 + blr /* ****************************************************************** */ diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index c0e5caf8ccc..88929b1f4f7 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -44,9 +44,7 @@ #include <asm/machdep.h> #include <asm/rtas.h> #include <asm/pmc.h> -#ifdef CONFIG_PPC32 #include <asm/reg.h> -#endif #ifdef CONFIG_PMAC_BACKLIGHT #include <asm/backlight.h> #endif @@ -1282,26 +1280,63 @@ void vsx_unavailable_exception(struct pt_regs *regs) die("Unrecoverable VSX Unavailable Exception", regs, SIGABRT); } -void tm_unavailable_exception(struct pt_regs *regs) +#ifdef CONFIG_PPC64 +void facility_unavailable_exception(struct pt_regs *regs) { + static char *facility_strings[] = { + [FSCR_FP_LG] = "FPU", + [FSCR_VECVSX_LG] = "VMX/VSX", + [FSCR_DSCR_LG] = "DSCR", + [FSCR_PM_LG] = "PMU SPRs", + [FSCR_BHRB_LG] = "BHRB", + [FSCR_TM_LG] = "TM", + [FSCR_EBB_LG] = "EBB", + [FSCR_TAR_LG] = "TAR", + }; + char *facility = "unknown"; + u64 value; + u8 status; + bool hv; + + hv = (regs->trap == 0xf80); + if (hv) + value = mfspr(SPRN_HFSCR); + else + value = mfspr(SPRN_FSCR); + + status = value >> 56; + if (status == FSCR_DSCR_LG) { + /* User is acessing the DSCR. Set the inherit bit and allow + * the user to set it directly in future by setting via the + * H/FSCR DSCR bit. + */ + current->thread.dscr_inherit = 1; + if (hv) + mtspr(SPRN_HFSCR, value | HFSCR_DSCR); + else + mtspr(SPRN_FSCR, value | FSCR_DSCR); + return; + } + + if ((status < ARRAY_SIZE(facility_strings)) && + facility_strings[status]) + facility = facility_strings[status]; + /* We restore the interrupt state now */ if (!arch_irq_disabled_regs(regs)) local_irq_enable(); - /* Currently we never expect a TMU exception. Catch - * this and kill the process! - */ - printk(KERN_EMERG "Unexpected TM unavailable exception at %lx " - "(msr %lx)\n", - regs->nip, regs->msr); + pr_err("%sFacility '%s' unavailable, exception at 0x%lx, MSR=%lx\n", + hv ? "Hypervisor " : "", facility, regs->nip, regs->msr); if (user_mode(regs)) { _exception(SIGILL, regs, ILL_ILLOPC, regs->nip); return; } - die("Unexpected TM unavailable exception", regs, SIGABRT); + die("Unexpected facility unavailable exception", regs, SIGABRT); } +#endif #ifdef CONFIG_PPC_TRANSACTIONAL_MEM diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c index 536016d792b..56d2e72c85d 100644 --- a/arch/powerpc/kernel/vio.c +++ b/arch/powerpc/kernel/vio.c @@ -1529,11 +1529,15 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, const char *cp; dn = dev->of_node; - if (!dn) - return -ENODEV; + if (!dn) { + strcpy(buf, "\n"); + return strlen(buf); + } cp = of_get_property(dn, "compatible", NULL); - if (!cp) - return -ENODEV; + if (!cp) { + strcpy(buf, "\n"); + return strlen(buf); + } return sprintf(buf, "vio:T%sS%s\n", vio_dev->type, cp); } diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 654e479802f..f096e72262f 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -38,9 +38,6 @@ jiffies = jiffies_64 + 4; #endif SECTIONS { - . = 0; - reloc_start = .; - . = KERNELBASE; /* diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 5880dfb3107..b616e364dbe 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -473,11 +473,14 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, slb_v = vcpu->kvm->arch.vrma_slb_v; } + preempt_disable(); /* Find the HPTE in the hash table */ index = kvmppc_hv_find_lock_hpte(kvm, eaddr, slb_v, HPTE_V_VALID | HPTE_V_ABSENT); - if (index < 0) + if (index < 0) { + preempt_enable(); return -ENOENT; + } hptep = (unsigned long *)(kvm->arch.hpt_virt + (index << 4)); v = hptep[0] & ~HPTE_V_HVLOCK; gr = kvm->arch.revmap[index].guest_rpte; @@ -485,6 +488,7 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, /* Unlock the HPTE */ asm volatile("lwsync" : : : "memory"); hptep[0] = v; + preempt_enable(); gpte->eaddr = eaddr; gpte->vpage = ((v & HPTE_V_AVPN) << 4) | ((eaddr >> 12) & 0xfff); diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 550f5928b39..102ad8a255f 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -82,10 +82,13 @@ void kvmppc_fast_vcpu_kick(struct kvm_vcpu *vcpu) /* CPU points to the first thread of the core */ if (cpu != me && cpu >= 0 && cpu < nr_cpu_ids) { +#ifdef CONFIG_KVM_XICS int real_cpu = cpu + vcpu->arch.ptid; if (paca[real_cpu].kvm_hstate.xics_phys) xics_wake_cpu(real_cpu); - else if (cpu_online(cpu)) + else +#endif + if (cpu_online(cpu)) smp_send_reschedule(cpu); } put_cpu(); @@ -1090,7 +1093,9 @@ static void kvmppc_start_thread(struct kvm_vcpu *vcpu) smp_wmb(); #if defined(CONFIG_PPC_ICP_NATIVE) && defined(CONFIG_SMP) if (vcpu->arch.ptid) { +#ifdef CONFIG_KVM_XICS xics_wake_cpu(cpu); +#endif ++vc->n_woken; } #endif diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c index 6dcbb49105a..049b899e40e 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c +++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c @@ -724,6 +724,10 @@ static int slb_base_page_shift[4] = { 20, /* 1M, unsupported */ }; +/* When called from virtmode, this func should be protected by + * preempt_disable(), otherwise, the holding of HPTE_V_HVLOCK + * can trigger deadlock issue. + */ long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v, unsigned long valid) { diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index b02f91e4c70..7bcd4d6e177 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -1054,7 +1054,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) BEGIN_FTR_SECTION mfspr r8, SPRN_DSCR ld r7, HSTATE_DSCR(r13) - std r8, VCPU_DSCR(r7) + std r8, VCPU_DSCR(r9) mtspr SPRN_DSCR, r7 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c index 94c1dd46b83..a3a5cb8ee7e 100644 --- a/arch/powerpc/kvm/book3s_xics.c +++ b/arch/powerpc/kvm/book3s_xics.c @@ -19,6 +19,7 @@ #include <asm/hvcall.h> #include <asm/xics.h> #include <asm/debug.h> +#include <asm/time.h> #include <linux/debugfs.h> #include <linux/seq_file.h> diff --git a/arch/powerpc/kvm/e500_mmu.c b/arch/powerpc/kvm/e500_mmu.c index 6d6f153b6c1..c17600de7d5 100644 --- a/arch/powerpc/kvm/e500_mmu.c +++ b/arch/powerpc/kvm/e500_mmu.c @@ -127,7 +127,7 @@ static int kvmppc_e500_tlb_index(struct kvmppc_vcpu_e500 *vcpu_e500, } static inline void kvmppc_e500_deliver_tlb_miss(struct kvm_vcpu *vcpu, - unsigned int eaddr, int as) + gva_t eaddr, int as) { struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu); unsigned int victim, tsized; diff --git a/arch/powerpc/lib/checksum_64.S b/arch/powerpc/lib/checksum_64.S index 167f72555d6..57a07206505 100644 --- a/arch/powerpc/lib/checksum_64.S +++ b/arch/powerpc/lib/checksum_64.S @@ -226,19 +226,35 @@ _GLOBAL(csum_partial) blr - .macro source + .macro srcnr 100: .section __ex_table,"a" .align 3 - .llong 100b,.Lsrc_error + .llong 100b,.Lsrc_error_nr .previous .endm - .macro dest + .macro source +150: + .section __ex_table,"a" + .align 3 + .llong 150b,.Lsrc_error + .previous + .endm + + .macro dstnr 200: .section __ex_table,"a" .align 3 - .llong 200b,.Ldest_error + .llong 200b,.Ldest_error_nr + .previous + .endm + + .macro dest +250: + .section __ex_table,"a" + .align 3 + .llong 250b,.Ldest_error .previous .endm @@ -269,16 +285,16 @@ _GLOBAL(csum_partial_copy_generic) rldicl. r6,r3,64-1,64-2 /* r6 = (r3 & 0x3) >> 1 */ beq .Lcopy_aligned - li r7,4 - sub r6,r7,r6 + li r9,4 + sub r6,r9,r6 mtctr r6 1: -source; lhz r6,0(r3) /* align to doubleword */ +srcnr; lhz r6,0(r3) /* align to doubleword */ subi r5,r5,2 addi r3,r3,2 adde r0,r0,r6 -dest; sth r6,0(r4) +dstnr; sth r6,0(r4) addi r4,r4,2 bdnz 1b @@ -392,10 +408,10 @@ dest; std r16,56(r4) mtctr r6 3: -source; ld r6,0(r3) +srcnr; ld r6,0(r3) addi r3,r3,8 adde r0,r0,r6 -dest; std r6,0(r4) +dstnr; std r6,0(r4) addi r4,r4,8 bdnz 3b @@ -405,10 +421,10 @@ dest; std r6,0(r4) srdi. r6,r5,2 beq .Lcopy_tail_halfword -source; lwz r6,0(r3) +srcnr; lwz r6,0(r3) addi r3,r3,4 adde r0,r0,r6 -dest; stw r6,0(r4) +dstnr; stw r6,0(r4) addi r4,r4,4 subi r5,r5,4 @@ -416,10 +432,10 @@ dest; stw r6,0(r4) srdi. r6,r5,1 beq .Lcopy_tail_byte -source; lhz r6,0(r3) +srcnr; lhz r6,0(r3) addi r3,r3,2 adde r0,r0,r6 -dest; sth r6,0(r4) +dstnr; sth r6,0(r4) addi r4,r4,2 subi r5,r5,2 @@ -427,10 +443,10 @@ dest; sth r6,0(r4) andi. r6,r5,1 beq .Lcopy_finish -source; lbz r6,0(r3) +srcnr; lbz r6,0(r3) sldi r9,r6,8 /* Pad the byte out to 16 bits */ adde r0,r0,r9 -dest; stb r6,0(r4) +dstnr; stb r6,0(r4) .Lcopy_finish: addze r0,r0 /* add in final carry */ @@ -440,6 +456,11 @@ dest; stb r6,0(r4) blr .Lsrc_error: + ld r14,STK_REG(R14)(r1) + ld r15,STK_REG(R15)(r1) + ld r16,STK_REG(R16)(r1) + addi r1,r1,STACKFRAMESIZE +.Lsrc_error_nr: cmpdi 0,r7,0 beqlr li r6,-EFAULT @@ -447,6 +468,11 @@ dest; stb r6,0(r4) blr .Ldest_error: + ld r14,STK_REG(R14)(r1) + ld r15,STK_REG(R15)(r1) + ld r16,STK_REG(R16)(r1) + addi r1,r1,STACKFRAMESIZE +.Ldest_error_nr: cmpdi 0,r8,0 beqlr li r6,-EFAULT diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 88c0425dc0a..b7293bba006 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -27,9 +27,12 @@ #include <linux/seq_file.h> #include <linux/uaccess.h> #include <linux/slab.h> +#include <asm/cputhreads.h> #include <asm/sparsemem.h> #include <asm/prom.h> #include <asm/smp.h> +#include <asm/cputhreads.h> +#include <asm/topology.h> #include <asm/firmware.h> #include <asm/paca.h> #include <asm/hvcall.h> @@ -151,9 +154,22 @@ static void __init get_node_active_region(unsigned long pfn, } } -static void map_cpu_to_node(int cpu, int node) +static void reset_numa_cpu_lookup_table(void) +{ + unsigned int cpu; + + for_each_possible_cpu(cpu) + numa_cpu_lookup_table[cpu] = -1; +} + +static void update_numa_cpu_lookup_table(unsigned int cpu, int node) { numa_cpu_lookup_table[cpu] = node; +} + +static void map_cpu_to_node(int cpu, int node) +{ + update_numa_cpu_lookup_table(cpu, node); dbg("adding cpu %d to node %d\n", cpu, node); @@ -518,11 +534,24 @@ static int of_drconf_to_nid_single(struct of_drconf_cell *drmem, */ static int __cpuinit numa_setup_cpu(unsigned long lcpu) { - int nid = 0; - struct device_node *cpu = of_get_cpu_node(lcpu, NULL); + int nid; + struct device_node *cpu; + + /* + * If a valid cpu-to-node mapping is already available, use it + * directly instead of querying the firmware, since it represents + * the most recent mapping notified to us by the platform (eg: VPHN). + */ + if ((nid = numa_cpu_lookup_table[lcpu]) >= 0) { + map_cpu_to_node(lcpu, nid); + return nid; + } + + cpu = of_get_cpu_node(lcpu, NULL); if (!cpu) { WARN_ON(1); + nid = 0; goto out; } @@ -1065,6 +1094,7 @@ void __init do_init_bootmem(void) */ setup_node_to_cpumask_map(); + reset_numa_cpu_lookup_table(); register_cpu_notifier(&ppc64_numa_nb); cpu_numa_callback(&ppc64_numa_nb, CPU_UP_PREPARE, (void *)(unsigned long)boot_cpuid); @@ -1319,7 +1349,8 @@ static int update_cpu_associativity_changes_mask(void) } } if (changed) { - cpumask_set_cpu(cpu, changes); + cpumask_or(changes, changes, cpu_sibling_mask(cpu)); + cpu = cpu_last_thread_sibling(cpu); } } @@ -1427,17 +1458,42 @@ static int update_cpu_topology(void *data) if (!data) return -EINVAL; - cpu = get_cpu(); + cpu = smp_processor_id(); for (update = data; update; update = update->next) { if (cpu != update->cpu) continue; - unregister_cpu_under_node(update->cpu, update->old_nid); unmap_cpu_from_node(update->cpu); map_cpu_to_node(update->cpu, update->new_nid); vdso_getcpu_init(); - register_cpu_under_node(update->cpu, update->new_nid); + } + + return 0; +} + +static int update_lookup_table(void *data) +{ + struct topology_update_data *update; + + if (!data) + return -EINVAL; + + /* + * Upon topology update, the numa-cpu lookup table needs to be updated + * for all threads in the core, including offline CPUs, to ensure that + * future hotplug operations respect the cpu-to-node associativity + * properly. + */ + for (update = data; update; update = update->next) { + int nid, base, j; + + nid = update->new_nid; + base = cpu_first_thread_sibling(update->cpu); + + for (j = 0; j < threads_per_core; j++) { + update_numa_cpu_lookup_table(base + j, nid); + } } return 0; @@ -1449,12 +1505,12 @@ static int update_cpu_topology(void *data) */ int arch_update_cpu_topology(void) { - unsigned int cpu, changed = 0; + unsigned int cpu, sibling, changed = 0; struct topology_update_data *updates, *ud; unsigned int associativity[VPHN_ASSOC_BUFSIZE] = {0}; cpumask_t updated_cpus; struct device *dev; - int weight, i = 0; + int weight, new_nid, i = 0; weight = cpumask_weight(&cpu_associativity_changes_mask); if (!weight) @@ -1467,24 +1523,62 @@ int arch_update_cpu_topology(void) cpumask_clear(&updated_cpus); for_each_cpu(cpu, &cpu_associativity_changes_mask) { - ud = &updates[i++]; - ud->cpu = cpu; - vphn_get_associativity(cpu, associativity); - ud->new_nid = associativity_to_nid(associativity); - - if (ud->new_nid < 0 || !node_online(ud->new_nid)) - ud->new_nid = first_online_node; + /* + * If siblings aren't flagged for changes, updates list + * will be too short. Skip on this update and set for next + * update. + */ + if (!cpumask_subset(cpu_sibling_mask(cpu), + &cpu_associativity_changes_mask)) { + pr_info("Sibling bits not set for associativity " + "change, cpu%d\n", cpu); + cpumask_or(&cpu_associativity_changes_mask, + &cpu_associativity_changes_mask, + cpu_sibling_mask(cpu)); + cpu = cpu_last_thread_sibling(cpu); + continue; + } - ud->old_nid = numa_cpu_lookup_table[cpu]; - cpumask_set_cpu(cpu, &updated_cpus); + /* Use associativity from first thread for all siblings */ + vphn_get_associativity(cpu, associativity); + new_nid = associativity_to_nid(associativity); + if (new_nid < 0 || !node_online(new_nid)) + new_nid = first_online_node; + + if (new_nid == numa_cpu_lookup_table[cpu]) { + cpumask_andnot(&cpu_associativity_changes_mask, + &cpu_associativity_changes_mask, + cpu_sibling_mask(cpu)); + cpu = cpu_last_thread_sibling(cpu); + continue; + } - if (i < weight) - ud->next = &updates[i]; + for_each_cpu(sibling, cpu_sibling_mask(cpu)) { + ud = &updates[i++]; + ud->cpu = sibling; + ud->new_nid = new_nid; + ud->old_nid = numa_cpu_lookup_table[sibling]; + cpumask_set_cpu(sibling, &updated_cpus); + if (i < weight) + ud->next = &updates[i]; + } + cpu = cpu_last_thread_sibling(cpu); } stop_machine(update_cpu_topology, &updates[0], &updated_cpus); + /* + * Update the numa-cpu lookup table with the new mappings, even for + * offline CPUs. It is best to perform this update from the stop- + * machine context. + */ + stop_machine(update_lookup_table, &updates[0], + cpumask_of(raw_smp_processor_id())); + for (ud = &updates[0]; ud; ud = ud->next) { + unregister_cpu_under_node(ud->cpu, ud->old_nid); + register_cpu_under_node(ud->cpu, ud->new_nid); + dev = get_cpu_device(ud->cpu); if (dev) kobject_uevent(&dev->kobj, KOBJ_CHANGE); diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c index 3e99c149271..7ce9cf3b698 100644 --- a/arch/powerpc/mm/slice.c +++ b/arch/powerpc/mm/slice.c @@ -258,7 +258,7 @@ static bool slice_scan_available(unsigned long addr, slice = GET_HIGH_SLICE_INDEX(addr); *boundary_addr = (slice + end) ? ((slice + end) << SLICE_HIGH_SHIFT) : SLICE_LOW_TOP; - return !!(available.high_slices & (1u << slice)); + return !!(available.high_slices & (1ul << slice)); } } diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index c427ae36374..a012a9747cd 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -209,10 +209,11 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image, } PPC_DIVWU(r_A, r_A, r_X); break; - case BPF_S_ALU_DIV_K: /* A = reciprocal_divide(A, K); */ + case BPF_S_ALU_DIV_K: /* A /= K */ + if (K == 1) + break; PPC_LI32(r_scratch1, K); - /* Top 32 bits of 64bit result -> A */ - PPC_MULHWU(r_A, r_A, r_scratch1); + PPC_DIVWU(r_A, r_A, r_scratch1); break; case BPF_S_ALU_AND_X: ctx->seen |= SEEN_XREG; diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 29c6482890c..d3ee2e50a3a 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -75,6 +75,8 @@ static unsigned int freeze_events_kernel = MMCR0_FCS; #define MMCR0_FCHV 0 #define MMCR0_PMCjCE MMCR0_PMCnCE +#define MMCR0_FC56 0 +#define MMCR0_PMAO 0 #define SPRN_MMCRA SPRN_MMCR2 #define MMCRA_SAMPLE_ENABLE 0 @@ -852,7 +854,7 @@ static void write_mmcr0(struct cpu_hw_events *cpuhw, unsigned long mmcr0) static void power_pmu_disable(struct pmu *pmu) { struct cpu_hw_events *cpuhw; - unsigned long flags; + unsigned long flags, val; if (!ppmu) return; @@ -860,9 +862,6 @@ static void power_pmu_disable(struct pmu *pmu) cpuhw = &__get_cpu_var(cpu_hw_events); if (!cpuhw->disabled) { - cpuhw->disabled = 1; - cpuhw->n_added = 0; - /* * Check if we ever enabled the PMU on this cpu. */ @@ -872,6 +871,21 @@ static void power_pmu_disable(struct pmu *pmu) } /* + * Set the 'freeze counters' bit, clear PMAO/FC56. + */ + val = mfspr(SPRN_MMCR0); + val |= MMCR0_FC; + val &= ~(MMCR0_PMAO | MMCR0_FC56); + + /* + * The barrier is to make sure the mtspr has been + * executed and the PMU has frozen the events etc. + * before we return. + */ + write_mmcr0(cpuhw, val); + mb(); + + /* * Disable instruction sampling if it was enabled */ if (cpuhw->mmcr[2] & MMCRA_SAMPLE_ENABLE) { @@ -880,14 +894,8 @@ static void power_pmu_disable(struct pmu *pmu) mb(); } - /* - * Set the 'freeze counters' bit. - * The barrier is to make sure the mtspr has been - * executed and the PMU has frozen the events - * before we return. - */ - write_mmcr0(cpuhw, mfspr(SPRN_MMCR0) | MMCR0_FC); - mb(); + cpuhw->disabled = 1; + cpuhw->n_added = 0; } local_irq_restore(flags); } @@ -911,12 +919,18 @@ static void power_pmu_enable(struct pmu *pmu) if (!ppmu) return; + local_irq_save(flags); + cpuhw = &__get_cpu_var(cpu_hw_events); - if (!cpuhw->disabled) { - local_irq_restore(flags); - return; + if (!cpuhw->disabled) + goto out; + + if (cpuhw->n_events == 0) { + ppc_set_pmu_inuse(0); + goto out; } + cpuhw->disabled = 0; /* @@ -928,8 +942,6 @@ static void power_pmu_enable(struct pmu *pmu) if (!cpuhw->n_added) { mtspr(SPRN_MMCRA, cpuhw->mmcr[2] & ~MMCRA_SAMPLE_ENABLE); mtspr(SPRN_MMCR1, cpuhw->mmcr[1]); - if (cpuhw->n_events == 0) - ppc_set_pmu_inuse(0); goto out_enable; } diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c index f7d1c4fff30..9aefaebedef 100644 --- a/arch/powerpc/perf/power8-pmu.c +++ b/arch/powerpc/perf/power8-pmu.c @@ -109,6 +109,16 @@ #define EVENT_IS_MARKED (EVENT_MARKED_MASK << EVENT_MARKED_SHIFT) #define EVENT_PSEL_MASK 0xff /* PMCxSEL value */ +#define EVENT_VALID_MASK \ + ((EVENT_THRESH_MASK << EVENT_THRESH_SHIFT) | \ + (EVENT_SAMPLE_MASK << EVENT_SAMPLE_SHIFT) | \ + (EVENT_CACHE_SEL_MASK << EVENT_CACHE_SEL_SHIFT) | \ + (EVENT_PMC_MASK << EVENT_PMC_SHIFT) | \ + (EVENT_UNIT_MASK << EVENT_UNIT_SHIFT) | \ + (EVENT_COMBINE_MASK << EVENT_COMBINE_SHIFT) | \ + (EVENT_MARKED_MASK << EVENT_MARKED_SHIFT) | \ + EVENT_PSEL_MASK) + /* MMCRA IFM bits - POWER8 */ #define POWER8_MMCRA_IFM1 0x0000000040000000UL #define POWER8_MMCRA_IFM2 0x0000000080000000UL @@ -184,6 +194,7 @@ #define MMCR1_UNIT_SHIFT(pmc) (60 - (4 * ((pmc) - 1))) #define MMCR1_COMBINE_SHIFT(pmc) (35 - ((pmc) - 1)) #define MMCR1_PMCSEL_SHIFT(pmc) (24 - (((pmc) - 1)) * 8) +#define MMCR1_FAB_SHIFT 36 #define MMCR1_DC_QUAL_SHIFT 47 #define MMCR1_IC_QUAL_SHIFT 46 @@ -212,6 +223,9 @@ static int power8_get_constraint(u64 event, unsigned long *maskp, unsigned long mask = value = 0; + if (event & ~EVENT_VALID_MASK) + return -1; + pmc = (event >> EVENT_PMC_SHIFT) & EVENT_PMC_MASK; unit = (event >> EVENT_UNIT_SHIFT) & EVENT_UNIT_MASK; cache = (event >> EVENT_CACHE_SEL_SHIFT) & EVENT_CACHE_SEL_MASK; @@ -354,8 +368,8 @@ static int power8_compute_mmcr(u64 event[], int n_ev, * the threshold bits are used for the match value. */ if (event_is_fab_match(event[i])) { - mmcr1 |= (event[i] >> EVENT_THR_CTL_SHIFT) & - EVENT_THR_CTL_MASK; + mmcr1 |= ((event[i] >> EVENT_THR_CTL_SHIFT) & + EVENT_THR_CTL_MASK) << MMCR1_FAB_SHIFT; } else { val = (event[i] >> EVENT_THR_CTL_SHIFT) & EVENT_THR_CTL_MASK; mmcra |= val << MMCRA_THR_CTL_SHIFT; @@ -378,6 +392,10 @@ static int power8_compute_mmcr(u64 event[], int n_ev, if (pmc_inuse & 0x7c) mmcr[0] |= MMCR0_PMCjCE; + /* If we're not using PMC 5 or 6, freeze them */ + if (!(pmc_inuse & 0x60)) + mmcr[0] |= MMCR0_FC56; + mmcr[1] = mmcr1; mmcr[2] = mmcra; diff --git a/arch/powerpc/platforms/52xx/Kconfig b/arch/powerpc/platforms/52xx/Kconfig index 90f4496017e..af54174801f 100644 --- a/arch/powerpc/platforms/52xx/Kconfig +++ b/arch/powerpc/platforms/52xx/Kconfig @@ -57,5 +57,5 @@ config PPC_MPC5200_BUGFIX config PPC_MPC5200_LPBFIFO tristate "MPC5200 LocalPlus bus FIFO driver" - depends on PPC_MPC52xx + depends on PPC_MPC52xx && PPC_BESTCOMM select PPC_BESTCOMM_GEN_BD diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 9c9d15e4cdf..f75607c93e8 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -151,13 +151,23 @@ static int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe) rid_end = pe->rid + 1; } - /* Associate PE in PELT */ + /* + * Associate PE in PELT. We need add the PE into the + * corresponding PELT-V as well. Otherwise, the error + * originated from the PE might contribute to other + * PEs. + */ rc = opal_pci_set_pe(phb->opal_id, pe->pe_number, pe->rid, bcomp, dcomp, fcomp, OPAL_MAP_PE); if (rc) { pe_err(pe, "OPAL error %ld trying to setup PELT table\n", rc); return -ENXIO; } + + rc = opal_pci_set_peltv(phb->opal_id, pe->pe_number, + pe->pe_number, OPAL_ADD_PE_TO_DOMAIN); + if (rc) + pe_warn(pe, "OPAL error %d adding self to PELTV\n", rc); opal_pci_eeh_freeze_clear(phb->opal_id, pe->pe_number, OPAL_EEH_ACTION_CLEAR_FREEZE_ALL); @@ -441,6 +451,17 @@ static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev set_iommu_table_base(&pdev->dev, &pe->tce32_table); } +static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus) +{ + struct pci_dev *dev; + + list_for_each_entry(dev, &bus->devices, bus_list) { + set_iommu_table_base(&dev->dev, &pe->tce32_table); + if (dev->subordinate) + pnv_ioda_setup_bus_dma(pe, dev->subordinate); + } +} + static void pnv_pci_ioda1_tce_invalidate(struct iommu_table *tbl, u64 *startp, u64 *endp) { @@ -596,6 +617,11 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb, } iommu_init_table(tbl, phb->hose->node); + if (pe->pdev) + set_iommu_table_base(&pe->pdev->dev, tbl); + else + pnv_ioda_setup_bus_dma(pe, pe->pbus); + return; fail: /* XXX Failure: Try to fallback to 64-bit only ? */ @@ -667,6 +693,11 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, } iommu_init_table(tbl, phb->hose->node); + if (pe->pdev) + set_iommu_table_base(&pe->pdev->dev, tbl); + else + pnv_ioda_setup_bus_dma(pe, pe->pbus); + return; fail: if (pe->tce32_seg >= 0) diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index 217ca5c75b2..2882d614221 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -34,12 +34,7 @@ #include "offline_states.h" /* This version can't take the spinlock, because it never returns */ -static struct rtas_args rtas_stop_self_args = { - .token = RTAS_UNKNOWN_SERVICE, - .nargs = 0, - .nret = 1, - .rets = &rtas_stop_self_args.args[0], -}; +static int rtas_stop_self_token = RTAS_UNKNOWN_SERVICE; static DEFINE_PER_CPU(enum cpu_state_vals, preferred_offline_state) = CPU_STATE_OFFLINE; @@ -92,15 +87,20 @@ void set_default_offline_state(int cpu) static void rtas_stop_self(void) { - struct rtas_args *args = &rtas_stop_self_args; + struct rtas_args args = { + .token = cpu_to_be32(rtas_stop_self_token), + .nargs = 0, + .nret = 1, + .rets = &args.args[0], + }; local_irq_disable(); - BUG_ON(args->token == RTAS_UNKNOWN_SERVICE); + BUG_ON(rtas_stop_self_token == RTAS_UNKNOWN_SERVICE); printk("cpu %u (hwid %u) Ready to die...\n", smp_processor_id(), hard_smp_processor_id()); - enter_rtas(__pa(args)); + enter_rtas(__pa(&args)); panic("Alas, I survived.\n"); } @@ -391,10 +391,10 @@ static int __init pseries_cpu_hotplug_init(void) } } - rtas_stop_self_args.token = rtas_token("stop-self"); + rtas_stop_self_token = rtas_token("stop-self"); qcss_tok = rtas_token("query-cpu-stopped-state"); - if (rtas_stop_self_args.token == RTAS_UNKNOWN_SERVICE || + if (rtas_stop_self_token == RTAS_UNKNOWN_SERVICE || qcss_tok == RTAS_UNKNOWN_SERVICE) { printk(KERN_INFO "CPU Hotplug not supported by firmware " "- disabling.\n"); diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index c11c8238797..54b998f2750 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -354,7 +354,7 @@ static int alloc_dispatch_log_kmem_cache(void) } early_initcall(alloc_dispatch_log_kmem_cache); -static void pSeries_idle(void) +static void pseries_lpar_idle(void) { /* This would call on the cpuidle framework, and the back-end pseries * driver to go to idle states @@ -362,10 +362,22 @@ static void pSeries_idle(void) if (cpuidle_idle_call()) { /* On error, execute default handler * to go into low thread priority and possibly - * low power mode. + * low power mode by cedeing processor to hypervisor */ - HMT_low(); - HMT_very_low(); + + /* Indicate to hypervisor that we are idle. */ + get_lppaca()->idle = 1; + + /* + * Yield the processor to the hypervisor. We return if + * an external interrupt occurs (which are driven prior + * to returning here) or if a prod occurs from another + * processor. When returning here, external interrupts + * are enabled. + */ + cede_processor(); + + get_lppaca()->idle = 0; } } @@ -456,15 +468,14 @@ static void __init pSeries_setup_arch(void) pSeries_nvram_init(); - if (firmware_has_feature(FW_FEATURE_SPLPAR)) { + if (firmware_has_feature(FW_FEATURE_LPAR)) { vpa_init(boot_cpuid); - ppc_md.power_save = pSeries_idle; - } - - if (firmware_has_feature(FW_FEATURE_LPAR)) + ppc_md.power_save = pseries_lpar_idle; ppc_md.enable_pmcs = pseries_lpar_enable_pmcs; - else + } else { + /* No special idle routine */ ppc_md.enable_pmcs = power4_enable_pmcs; + } ppc_md.pcibios_root_bridge_prepare = pseries_root_bridge_prepare; |