diff options
Diffstat (limited to 'arch/powerpc/kernel')
39 files changed, 644 insertions, 459 deletions
diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c index 34f55524d456..86150fbb42c3 100644 --- a/arch/powerpc/kernel/align.c +++ b/arch/powerpc/kernel/align.c @@ -908,7 +908,7 @@ int fix_alignment(struct pt_regs *regs) flush_fp_to_thread(current); } - if ((nb == 16)) { + if (nb == 16) { if (flags & F) { /* Special case for 16-byte FP loads and stores */ PPC_WARN_ALIGNMENT(fp_pair, regs); diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 9d7dede2847c..e624f9646350 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -489,7 +489,6 @@ int main(void) DEFINE(KVM_HOST_LPID, offsetof(struct kvm, arch.host_lpid)); DEFINE(KVM_HOST_LPCR, offsetof(struct kvm, arch.host_lpcr)); DEFINE(KVM_HOST_SDR1, offsetof(struct kvm, arch.host_sdr1)); - DEFINE(KVM_TLBIE_LOCK, offsetof(struct kvm, arch.tlbie_lock)); DEFINE(KVM_NEED_FLUSH, offsetof(struct kvm, arch.need_tlb_flush.bits)); DEFINE(KVM_ENABLED_HCALLS, offsetof(struct kvm, arch.enabled_hcalls)); DEFINE(KVM_LPCR, offsetof(struct kvm, arch.lpcr)); @@ -499,6 +498,7 @@ int main(void) DEFINE(VCPU_DAR, offsetof(struct kvm_vcpu, arch.shregs.dar)); DEFINE(VCPU_VPA, offsetof(struct kvm_vcpu, arch.vpa.pinned_addr)); DEFINE(VCPU_VPA_DIRTY, offsetof(struct kvm_vcpu, arch.vpa.dirty)); + DEFINE(VCPU_HEIR, offsetof(struct kvm_vcpu, arch.emul_inst)); #endif #ifdef CONFIG_PPC_BOOK3S DEFINE(VCPU_VCPUID, offsetof(struct kvm_vcpu, vcpu_id)); @@ -727,10 +727,14 @@ int main(void) #endif #ifdef CONFIG_PPC_POWERNV - DEFINE(OPAL_MC_GPR3, offsetof(struct opal_machine_check_event, gpr3)); - DEFINE(OPAL_MC_SRR0, offsetof(struct opal_machine_check_event, srr0)); - DEFINE(OPAL_MC_SRR1, offsetof(struct opal_machine_check_event, srr1)); - DEFINE(PACA_OPAL_MC_EVT, offsetof(struct paca_struct, opal_mc_evt)); + DEFINE(PACA_CORE_IDLE_STATE_PTR, + offsetof(struct paca_struct, core_idle_state_ptr)); + DEFINE(PACA_THREAD_IDLE_STATE, + offsetof(struct paca_struct, thread_idle_state)); + DEFINE(PACA_THREAD_MASK, + offsetof(struct paca_struct, thread_mask)); + DEFINE(PACA_SUBCORE_SIBLING_MASK, + offsetof(struct paca_struct, subcore_sibling_mask)); #endif return 0; diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c index c78e6dac4d7d..cfa0f81a5bb0 100644 --- a/arch/powerpc/kernel/crash_dump.c +++ b/arch/powerpc/kernel/crash_dump.c @@ -12,7 +12,6 @@ #undef DEBUG #include <linux/crash_dump.h> -#include <linux/bootmem.h> #include <linux/io.h> #include <linux/memblock.h> #include <asm/code-patching.h> diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c index d55c76c571f3..f4217819cc31 100644 --- a/arch/powerpc/kernel/dbell.c +++ b/arch/powerpc/kernel/dbell.c @@ -41,7 +41,7 @@ void doorbell_exception(struct pt_regs *regs) may_hard_irq_enable(); - __get_cpu_var(irq_stat).doorbell_irqs++; + __this_cpu_inc(irq_stat.doorbell_irqs); smp_ipi_demux(); diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c index 54d0116256f7..4c68bfe4108a 100644 --- a/arch/powerpc/kernel/dma-iommu.c +++ b/arch/powerpc/kernel/dma-iommu.c @@ -60,16 +60,16 @@ static int dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist, int nelems, enum dma_data_direction direction, struct dma_attrs *attrs) { - return iommu_map_sg(dev, get_iommu_table_base(dev), sglist, nelems, - device_to_mask(dev), direction, attrs); + return ppc_iommu_map_sg(dev, get_iommu_table_base(dev), sglist, nelems, + device_to_mask(dev), direction, attrs); } static void dma_iommu_unmap_sg(struct device *dev, struct scatterlist *sglist, int nelems, enum dma_data_direction direction, struct dma_attrs *attrs) { - iommu_unmap_sg(get_iommu_table_base(dev), sglist, nelems, direction, - attrs); + ppc_iommu_unmap_sg(get_iommu_table_base(dev), sglist, nelems, + direction, attrs); } /* We support DMA to/from any memory page via the iommu */ diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 2248a1999c64..e1b6d8e17289 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -143,6 +143,8 @@ static int __init eeh_setup(char *str) { if (!strcmp(str, "off")) eeh_add_flag(EEH_FORCE_DISABLED); + else if (!strcmp(str, "early_log")) + eeh_add_flag(EEH_EARLY_DUMP_LOG); return 1; } @@ -758,30 +760,41 @@ static void eeh_reset_pe_once(struct eeh_pe *pe) int eeh_reset_pe(struct eeh_pe *pe) { int flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE); - int i, rc; + int i, state, ret; + + /* Mark as reset and block config space */ + eeh_pe_state_mark(pe, EEH_PE_RESET | EEH_PE_CFG_BLOCKED); /* Take three shots at resetting the bus */ - for (i=0; i<3; i++) { + for (i = 0; i < 3; i++) { eeh_reset_pe_once(pe); /* * EEH_PE_ISOLATED is expected to be removed after * BAR restore. */ - rc = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC); - if ((rc & flags) == flags) - return 0; + state = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC); + if ((state & flags) == flags) { + ret = 0; + goto out; + } - if (rc < 0) { - pr_err("%s: Unrecoverable slot failure on PHB#%d-PE#%x", + if (state < 0) { + pr_warn("%s: Unrecoverable slot failure on PHB#%d-PE#%x", __func__, pe->phb->global_number, pe->addr); - return -1; + ret = -ENOTRECOVERABLE; + goto out; } - pr_err("EEH: bus reset %d failed on PHB#%d-PE#%x, rc=%d\n", - i+1, pe->phb->global_number, pe->addr, rc); + + /* We might run out of credits */ + ret = -EIO; + pr_warn("%s: Failure %d resetting PHB#%x-PE#%x\n (%d)\n", + __func__, state, pe->phb->global_number, pe->addr, (i + 1)); } - return -1; +out: + eeh_pe_state_clear(pe, EEH_PE_RESET | EEH_PE_CFG_BLOCKED); + return ret; } /** @@ -920,11 +933,8 @@ int eeh_init(void) pr_warn("%s: Platform EEH operation not found\n", __func__); return -EEXIST; - } else if ((ret = eeh_ops->init())) { - pr_warn("%s: Failed to call platform init function (%d)\n", - __func__, ret); + } else if ((ret = eeh_ops->init())) return ret; - } /* Initialize EEH event */ ret = eeh_event_init(); @@ -1209,6 +1219,7 @@ int eeh_unfreeze_pe(struct eeh_pe *pe, bool sw_state) static struct pci_device_id eeh_reset_ids[] = { { PCI_DEVICE(0x19a2, 0x0710) }, /* Emulex, BE */ { PCI_DEVICE(0x10df, 0xe220) }, /* Emulex, Lancer */ + { PCI_DEVICE(0x14e4, 0x1657) }, /* Broadcom BCM5719 */ { 0 } }; diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 6535936bdf27..b17e793ba67e 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -528,13 +528,11 @@ int eeh_pe_reset_and_recover(struct eeh_pe *pe) eeh_pe_dev_traverse(pe, eeh_report_error, &result); /* Issue reset */ - eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED); ret = eeh_reset_pe(pe); if (ret) { - eeh_pe_state_clear(pe, EEH_PE_RECOVERING | EEH_PE_CFG_BLOCKED); + eeh_pe_state_clear(pe, EEH_PE_RECOVERING); return ret; } - eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED); /* Unfreeze the PE */ ret = eeh_clear_pe_frozen_state(pe, true); @@ -601,19 +599,15 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus) * config accesses. So we prefer to block them. However, controlled * PCI config accesses initiated from EEH itself are allowed. */ - eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED); rc = eeh_reset_pe(pe); - if (rc) { - eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED); + if (rc) return rc; - } pci_lock_rescan_remove(); /* Restore PE */ eeh_ops->configure_bridge(pe); eeh_pe_restore_bars(pe); - eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED); /* Clear frozen state */ rc = eeh_clear_pe_frozen_state(pe, false); diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 22b45a4955cd..10a093579191 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -1424,12 +1424,18 @@ _GLOBAL(ftrace_graph_caller) lwz r4, 44(r1) subi r4, r4, MCOUNT_INSN_SIZE - /* get the parent address */ - addi r3, r1, 52 + /* Grab the LR out of the caller stack frame */ + lwz r3,52(r1) bl prepare_ftrace_return nop + /* + * prepare_ftrace_return gives us the address we divert to. + * Change the LR in the callers stack frame to this. + */ + stw r3,52(r1) + MCOUNT_RESTORE_FRAME /* old link register ends up in ctr reg */ bctr @@ -1457,4 +1463,4 @@ _GLOBAL(return_to_handler) blr #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ -#endif /* CONFIG_MCOUNT */ +#endif /* CONFIG_FUNCTION_TRACER */ diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 0905c8da90f1..194e46dcf08d 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -1227,13 +1227,20 @@ _GLOBAL(ftrace_graph_caller) ld r4, 128(r1) subi r4, r4, MCOUNT_INSN_SIZE - /* get the parent address */ + /* Grab the LR out of the caller stack frame */ ld r11, 112(r1) - addi r3, r11, 16 + ld r3, 16(r11) bl prepare_ftrace_return nop + /* + * prepare_ftrace_return gives us the address we divert to. + * Change the LR in the callers stack frame to this. + */ + ld r11, 112(r1) + std r3, 16(r11) + ld r0, 128(r1) mtlr r0 addi r1, r1, 112 @@ -1241,28 +1248,6 @@ _GLOBAL(ftrace_graph_caller) _GLOBAL(return_to_handler) /* need to save return values */ - std r4, -24(r1) - std r3, -16(r1) - std r31, -8(r1) - mr r31, r1 - stdu r1, -112(r1) - - bl ftrace_return_to_handler - nop - - /* return value has real return address */ - mtlr r3 - - ld r1, 0(r1) - ld r4, -24(r1) - ld r3, -16(r1) - ld r31, -8(r1) - - /* Jump back to real return address */ - blr - -_GLOBAL(mod_return_to_handler) - /* need to save return values */ std r4, -32(r1) std r3, -24(r1) /* save TOC */ @@ -1272,7 +1257,7 @@ _GLOBAL(mod_return_to_handler) stdu r1, -112(r1) /* - * We are in a module using the module's TOC. + * We might be called from a module. * Switch to our TOC to run inside the core kernel. */ ld r2, PACATOC(r13) diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 72e783ea0681..c2df8150bd7a 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -15,6 +15,7 @@ #include <asm/hw_irq.h> #include <asm/exception-64s.h> #include <asm/ptrace.h> +#include <asm/cpuidle.h> /* * We layout physical memory as follows: @@ -101,23 +102,34 @@ system_reset_pSeries: #ifdef CONFIG_PPC_P7_NAP BEGIN_FTR_SECTION /* Running native on arch 2.06 or later, check if we are - * waking up from nap. We only handle no state loss and - * supervisor state loss. We do -not- handle hypervisor - * state loss at this time. + * waking up from nap/sleep/winkle. */ mfspr r13,SPRN_SRR1 rlwinm. r13,r13,47-31,30,31 beq 9f - /* waking up from powersave (nap) state */ - cmpwi cr1,r13,2 - /* Total loss of HV state is fatal, we could try to use the - * PIR to locate a PACA, then use an emergency stack etc... - * OPAL v3 based powernv platforms have new idle states - * which fall in this catagory. + cmpwi cr3,r13,2 + + /* + * Check if last bit of HSPGR0 is set. This indicates whether we are + * waking up from winkle. */ - bgt cr1,8f GET_PACA(r13) + clrldi r5,r13,63 + clrrdi r13,r13,1 + cmpwi cr4,r5,1 + mtspr SPRN_HSPRG0,r13 + + lbz r0,PACA_THREAD_IDLE_STATE(r13) + cmpwi cr2,r0,PNV_THREAD_NAP + bgt cr2,8f /* Either sleep or Winkle */ + + /* Waking up from nap should not cause hypervisor state loss */ + bgt cr3,. + + /* Waking up from nap */ + li r0,PNV_THREAD_RUNNING + stb r0,PACA_THREAD_IDLE_STATE(r13) /* Clear thread state */ #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE li r0,KVM_HWTHREAD_IN_KERNEL @@ -131,7 +143,9 @@ BEGIN_FTR_SECTION 1: #endif - beq cr1,2f + /* Return SRR1 from power7_nap() */ + mfspr r3,SPRN_SRR1 + beq cr3,2f b power7_wakeup_noloss 2: b power7_wakeup_loss @@ -292,15 +306,26 @@ decrementer_pSeries: . = 0xc00 .globl system_call_pSeries system_call_pSeries: - HMT_MEDIUM + /* + * If CONFIG_KVM_BOOK3S_64_HANDLER is set, save the PPR (on systems + * that support it) before changing to HMT_MEDIUM. That allows the KVM + * code to save that value into the guest state (it is the guest's PPR + * value). Otherwise just change to HMT_MEDIUM as userspace has + * already saved the PPR. + */ #ifdef CONFIG_KVM_BOOK3S_64_HANDLER SET_SCRATCH0(r13) GET_PACA(r13) std r9,PACA_EXGEN+EX_R9(r13) + OPT_GET_SPR(r9, SPRN_PPR, CPU_FTR_HAS_PPR); + HMT_MEDIUM; std r10,PACA_EXGEN+EX_R10(r13) + OPT_SAVE_REG_TO_PACA(PACA_EXGEN+EX_PPR, r9, CPU_FTR_HAS_PPR); mfcr r9 KVMTEST(0xc00) GET_SCRATCH0(r13) +#else + HMT_MEDIUM; #endif SYSCALL_PSERIES_1 SYSCALL_PSERIES_2_RFID @@ -1301,23 +1326,6 @@ hmi_exception_after_realmode: EXCEPTION_PROLOG_0(PACA_EXGEN) b hmi_exception_hv -#ifdef CONFIG_PPC_POWERNV -_GLOBAL(opal_mc_secondary_handler) - HMT_MEDIUM_PPR_DISCARD - SET_SCRATCH0(r13) - GET_PACA(r13) - clrldi r3,r3,2 - tovirt(r3,r3) - std r3,PACA_OPAL_MC_EVT(r13) - ld r13,OPAL_MC_SRR0(r3) - mtspr SPRN_SRR0,r13 - ld r13,OPAL_MC_SRR1(r3) - mtspr SPRN_SRR1,r13 - ld r3,OPAL_MC_GPR3(r3) - GET_SCRATCH0(r13) - b machine_check_pSeries -#endif /* CONFIG_PPC_POWERNV */ - #define MACHINE_CHECK_HANDLER_WINDUP \ /* Clear MSR_RI before setting SRR0 and SRR1. */\ @@ -1386,6 +1394,7 @@ machine_check_handle_early: MACHINE_CHECK_HANDLER_WINDUP GET_PACA(r13) ld r1,PACAR1(r13) + li r3,PNV_THREAD_NAP b power7_enter_nap_mode 4: #endif @@ -1571,9 +1580,11 @@ do_hash_page: * r3 contains the faulting address * r4 contains the required access permissions * r5 contains the trap number + * r6 contains dsisr * * at return r3 = 0 for success, 1 for page fault, negative for error */ + ld r6,_DSISR(r1) bl hash_page /* build HPTE if possible */ cmpdi r3,0 /* see if hash_page succeeded */ diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c index 390311c0f03d..44d4d8eb3c85 100644 --- a/arch/powerpc/kernel/ftrace.c +++ b/arch/powerpc/kernel/ftrace.c @@ -449,7 +449,7 @@ void ftrace_replace_code(int enable) rec = ftrace_rec_iter_record(iter); ret = __ftrace_replace_code(rec, enable); if (ret) { - ftrace_bug(ret, rec->ip); + ftrace_bug(ret, rec); return; } } @@ -510,79 +510,36 @@ int ftrace_disable_ftrace_graph_caller(void) } #endif /* CONFIG_DYNAMIC_FTRACE */ -#ifdef CONFIG_PPC64 -extern void mod_return_to_handler(void); -#endif - /* * Hook the return address and push it in the stack of return addrs - * in current thread info. + * in current thread info. Return the address we want to divert to. */ -void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) +unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip) { - unsigned long old; - int faulted; struct ftrace_graph_ent trace; - unsigned long return_hooker = (unsigned long)&return_to_handler; + unsigned long return_hooker; if (unlikely(ftrace_graph_is_dead())) - return; + goto out; if (unlikely(atomic_read(¤t->tracing_graph_pause))) - return; - -#ifdef CONFIG_PPC64 - /* non core kernel code needs to save and restore the TOC */ - if (REGION_ID(self_addr) != KERNEL_REGION_ID) - return_hooker = (unsigned long)&mod_return_to_handler; -#endif - - return_hooker = ppc_function_entry((void *)return_hooker); + goto out; - /* - * Protect against fault, even if it shouldn't - * happen. This tool is too much intrusive to - * ignore such a protection. - */ - asm volatile( - "1: " PPC_LL "%[old], 0(%[parent])\n" - "2: " PPC_STL "%[return_hooker], 0(%[parent])\n" - " li %[faulted], 0\n" - "3:\n" - - ".section .fixup, \"ax\"\n" - "4: li %[faulted], 1\n" - " b 3b\n" - ".previous\n" - - ".section __ex_table,\"a\"\n" - PPC_LONG_ALIGN "\n" - PPC_LONG "1b,4b\n" - PPC_LONG "2b,4b\n" - ".previous" - - : [old] "=&r" (old), [faulted] "=r" (faulted) - : [parent] "r" (parent), [return_hooker] "r" (return_hooker) - : "memory" - ); - - if (unlikely(faulted)) { - ftrace_graph_stop(); - WARN_ON(1); - return; - } + return_hooker = ppc_function_entry(return_to_handler); - trace.func = self_addr; + trace.func = ip; trace.depth = current->curr_ret_stack + 1; /* Only trace if the calling function expects to */ - if (!ftrace_graph_entry(&trace)) { - *parent = old; - return; - } + if (!ftrace_graph_entry(&trace)) + goto out; + + if (ftrace_push_return_trace(parent, ip, &trace.depth, 0) == -EBUSY) + goto out; - if (ftrace_push_return_trace(old, self_addr, &trace.depth, 0) == -EBUSY) - *parent = old; + parent = return_hooker; +out: + return parent; } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index fafff8dbd5d9..d99aac0d69f1 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -33,13 +33,31 @@ /* Macro to make the code more readable. */ #ifdef CONFIG_8xx_CPU6 -#define DO_8xx_CPU6(val, reg) \ - li reg, val; \ - stw reg, 12(r0); \ - lwz reg, 12(r0); +#define SPRN_MI_TWC_ADDR 0x2b80 +#define SPRN_MI_RPN_ADDR 0x2d80 +#define SPRN_MD_TWC_ADDR 0x3b80 +#define SPRN_MD_RPN_ADDR 0x3d80 + +#define MTSPR_CPU6(spr, reg, treg) \ + li treg, spr##_ADDR; \ + stw treg, 12(r0); \ + lwz treg, 12(r0); \ + mtspr spr, reg #else -#define DO_8xx_CPU6(val, reg) +#define MTSPR_CPU6(spr, reg, treg) \ + mtspr spr, reg #endif + +/* + * Value for the bits that have fixed value in RPN entries. + * Also used for tagging DAR for DTLBerror. + */ +#ifdef CONFIG_PPC_16K_PAGES +#define RPN_PATTERN (0x00f0 | MD_SPS16K) +#else +#define RPN_PATTERN 0x00f0 +#endif + __HEAD _ENTRY(_stext); _ENTRY(_start); @@ -65,13 +83,6 @@ _ENTRY(_start); * 8M 1:1. I also mapped an additional I/O space 1:1 so we can get to * the "internal" processor registers before MMU_init is called. * - * The TLB code currently contains a major hack. Since I use the condition - * code register, I have to save and restore it. I am out of registers, so - * I just store it in memory location 0 (the TLB handlers are not reentrant). - * To avoid making any decisions, I need to use the "segment" valid bit - * in the first level table, but that would require many changes to the - * Linux page directory/table functions that I don't want to do right now. - * * -- Dan */ .globl __start @@ -211,7 +222,7 @@ MachineCheck: EXCEPTION_PROLOG mfspr r4,SPRN_DAR stw r4,_DAR(r11) - li r5,0x00f0 + li r5,RPN_PATTERN mtspr SPRN_DAR,r5 /* Tag DAR, to be used in DTLB Error */ mfspr r5,SPRN_DSISR stw r5,_DSISR(r11) @@ -219,30 +230,16 @@ MachineCheck: EXC_XFER_STD(0x200, machine_check_exception) /* Data access exception. - * This is "never generated" by the MPC8xx. We jump to it for other - * translation errors. + * This is "never generated" by the MPC8xx. */ . = 0x300 DataAccess: - EXCEPTION_PROLOG - mfspr r10,SPRN_DSISR - stw r10,_DSISR(r11) - mr r5,r10 - mfspr r4,SPRN_DAR - li r10,0x00f0 - mtspr SPRN_DAR,r10 /* Tag DAR, to be used in DTLB Error */ - EXC_XFER_LITE(0x300, handle_page_fault) /* Instruction access exception. - * This is "never generated" by the MPC8xx. We jump to it for other - * translation errors. + * This is "never generated" by the MPC8xx. */ . = 0x400 InstructionAccess: - EXCEPTION_PROLOG - mr r4,r12 - mr r5,r9 - EXC_XFER_LITE(0x400, handle_page_fault) /* External interrupt */ EXCEPTION(0x500, HardwareInterrupt, do_IRQ, EXC_XFER_LITE) @@ -253,7 +250,7 @@ Alignment: EXCEPTION_PROLOG mfspr r4,SPRN_DAR stw r4,_DAR(r11) - li r5,0x00f0 + li r5,RPN_PATTERN mtspr SPRN_DAR,r5 /* Tag DAR, to be used in DTLB Error */ mfspr r5,SPRN_DSISR stw r5,_DSISR(r11) @@ -292,8 +289,8 @@ SystemCall: . = 0x1100 /* * For the MPC8xx, this is a software tablewalk to load the instruction - * TLB. It is modelled after the example in the Motorola manual. The task - * switch loads the M_TWB register with the pointer to the first level table. + * TLB. The task switch loads the M_TW register with the pointer to the first + * level table. * If we discover there is no second level table (value is zero) or if there * is an invalid pte, we load that into the TLB, which causes another fault * into the TLB Error interrupt where we can handle such problems. @@ -302,20 +299,17 @@ SystemCall: */ InstructionTLBMiss: #ifdef CONFIG_8xx_CPU6 - stw r3, 8(r0) + mtspr SPRN_DAR, r3 #endif EXCEPTION_PROLOG_0 mtspr SPRN_SPRG_SCRATCH2, r10 mfspr r10, SPRN_SRR0 /* Get effective address of fault */ #ifdef CONFIG_8xx_CPU15 - addi r11, r10, 0x1000 + addi r11, r10, PAGE_SIZE tlbie r11 - addi r11, r10, -0x1000 + addi r11, r10, -PAGE_SIZE tlbie r11 #endif - DO_8xx_CPU6(0x3780, r3) - mtspr SPRN_MD_EPN, r10 /* Have to use MD_EPN for walk, MI_EPN can't */ - mfspr r10, SPRN_M_TWB /* Get level 1 table entry address */ /* If we are faulting a kernel address, we have to use the * kernel page tables. @@ -323,32 +317,37 @@ InstructionTLBMiss: #ifdef CONFIG_MODULES /* Only modules will cause ITLB Misses as we always * pin the first 8MB of kernel memory */ - andi. r11, r10, 0x0800 /* Address >= 0x80000000 */ + andis. r11, r10, 0x8000 /* Address >= 0x80000000 */ +#endif + mfspr r11, SPRN_M_TW /* Get level 1 table base address */ +#ifdef CONFIG_MODULES beq 3f - lis r11, swapper_pg_dir@h - ori r11, r11, swapper_pg_dir@l - rlwimi r10, r11, 0, 2, 19 + lis r11, (swapper_pg_dir-PAGE_OFFSET)@h + ori r11, r11, (swapper_pg_dir-PAGE_OFFSET)@l 3: #endif - lwz r11, 0(r10) /* Get the level 1 entry */ + /* Extract level 1 index */ + rlwinm r10, r10, 32 - ((PAGE_SHIFT - 2) << 1), (PAGE_SHIFT - 2) << 1, 29 + lwzx r11, r10, r11 /* Get the level 1 entry */ rlwinm. r10, r11,0,0,19 /* Extract page descriptor page address */ beq 2f /* If zero, don't try to find a pte */ /* We have a pte table, so load the MI_TWC with the attributes * for this "segment." */ - ori r11,r11,1 /* Set valid bit */ - DO_8xx_CPU6(0x2b80, r3) - mtspr SPRN_MI_TWC, r11 /* Set segment attributes */ - DO_8xx_CPU6(0x3b80, r3) - mtspr SPRN_MD_TWC, r11 /* Load pte table base address */ - mfspr r11, SPRN_MD_TWC /* ....and get the pte address */ - lwz r10, 0(r11) /* Get the pte */ + MTSPR_CPU6(SPRN_MI_TWC, r11, r3) /* Set segment attributes */ + mfspr r11, SPRN_SRR0 /* Get effective address of fault */ + /* Extract level 2 index */ + rlwinm r11, r11, 32 - (PAGE_SHIFT - 2), 32 - PAGE_SHIFT, 29 + lwzx r10, r10, r11 /* Get the pte */ #ifdef CONFIG_SWAP andi. r11, r10, _PAGE_ACCESSED | _PAGE_PRESENT cmpwi cr0, r11, _PAGE_ACCESSED | _PAGE_PRESENT + li r11, RPN_PATTERN bne- cr0, 2f +#else + li r11, RPN_PATTERN #endif /* The Linux PTE won't go exactly into the MMU TLB. * Software indicator bits 21 and 28 must be clear. @@ -356,62 +355,63 @@ InstructionTLBMiss: * set. All other Linux PTE bits control the behavior * of the MMU. */ - li r11, 0x00f0 rlwimi r10, r11, 0, 0x07f8 /* Set 24-27, clear 21-23,28 */ - DO_8xx_CPU6(0x2d80, r3) - mtspr SPRN_MI_RPN, r10 /* Update TLB entry */ + MTSPR_CPU6(SPRN_MI_RPN, r10, r3) /* Update TLB entry */ /* Restore registers */ #ifdef CONFIG_8xx_CPU6 - lwz r3, 8(r0) + mfspr r3, SPRN_DAR + mtspr SPRN_DAR, r11 /* Tag DAR */ #endif mfspr r10, SPRN_SPRG_SCRATCH2 EXCEPTION_EPILOG_0 rfi 2: - mfspr r11, SPRN_SRR1 + mfspr r10, SPRN_SRR1 /* clear all error bits as TLB Miss * sets a few unconditionally */ - rlwinm r11, r11, 0, 0xffff - mtspr SPRN_SRR1, r11 + rlwinm r10, r10, 0, 0xffff + mtspr SPRN_SRR1, r10 /* Restore registers */ #ifdef CONFIG_8xx_CPU6 - lwz r3, 8(r0) + mfspr r3, SPRN_DAR + mtspr SPRN_DAR, r11 /* Tag DAR */ #endif mfspr r10, SPRN_SPRG_SCRATCH2 - EXCEPTION_EPILOG_0 - b InstructionAccess + b InstructionTLBError1 . = 0x1200 DataStoreTLBMiss: #ifdef CONFIG_8xx_CPU6 - stw r3, 8(r0) + mtspr SPRN_DAR, r3 #endif EXCEPTION_PROLOG_0 mtspr SPRN_SPRG_SCRATCH2, r10 - mfspr r10, SPRN_M_TWB /* Get level 1 table entry address */ + mfspr r10, SPRN_MD_EPN /* If we are faulting a kernel address, we have to use the * kernel page tables. */ - andi. r11, r10, 0x0800 + andis. r11, r10, 0x8000 + mfspr r11, SPRN_M_TW /* Get level 1 table base address */ beq 3f - lis r11, swapper_pg_dir@h - ori r11, r11, swapper_pg_dir@l - rlwimi r10, r11, 0, 2, 19 + lis r11, (swapper_pg_dir-PAGE_OFFSET)@h + ori r11, r11, (swapper_pg_dir-PAGE_OFFSET)@l 3: - lwz r11, 0(r10) /* Get the level 1 entry */ + /* Extract level 1 index */ + rlwinm r10, r10, 32 - ((PAGE_SHIFT - 2) << 1), (PAGE_SHIFT - 2) << 1, 29 + lwzx r11, r10, r11 /* Get the level 1 entry */ rlwinm. r10, r11,0,0,19 /* Extract page descriptor page address */ beq 2f /* If zero, don't try to find a pte */ /* We have a pte table, so load fetch the pte from the table. */ - ori r11, r11, 1 /* Set valid bit in physical L2 page */ - DO_8xx_CPU6(0x3b80, r3) - mtspr SPRN_MD_TWC, r11 /* Load pte table base address */ - mfspr r10, SPRN_MD_TWC /* ....and get the pte address */ + mfspr r10, SPRN_MD_EPN /* Get address of fault */ + /* Extract level 2 index */ + rlwinm r10, r10, 32 - (PAGE_SHIFT - 2), 32 - PAGE_SHIFT, 29 + rlwimi r10, r11, 0, 0, 32 - PAGE_SHIFT - 1 /* Add level 2 base */ lwz r10, 0(r10) /* Get the pte */ /* Insert the Guarded flag into the TWC from the Linux PTE. @@ -425,8 +425,7 @@ DataStoreTLBMiss: * It is bit 25 in the Linux PTE and bit 30 in the TWC */ rlwimi r11, r10, 32-5, 30, 30 - DO_8xx_CPU6(0x3b80, r3) - mtspr SPRN_MD_TWC, r11 + MTSPR_CPU6(SPRN_MD_TWC, r11, r3) /* Both _PAGE_ACCESSED and _PAGE_PRESENT has to be set. * We also need to know if the insn is a load/store, so: @@ -442,14 +441,8 @@ DataStoreTLBMiss: and r11, r11, r10 rlwimi r10, r11, 0, _PAGE_PRESENT #endif - /* Honour kernel RO, User NA */ - /* 0x200 == Extended encoding, bit 22 */ - rlwimi r10, r10, 32-2, 0x200 /* Copy USER to bit 22, 0x200 */ - /* r11 = (r10 & _PAGE_RW) >> 1 */ - rlwinm r11, r10, 32-1, 0x200 - or r10, r11, r10 - /* invert RW and 0x200 bits */ - xori r10, r10, _PAGE_RW | 0x200 + /* invert RW */ + xori r10, r10, _PAGE_RW /* The Linux PTE won't go exactly into the MMU TLB. * Software indicator bits 22 and 28 must be clear. @@ -457,14 +450,13 @@ DataStoreTLBMiss: * set. All other Linux PTE bits control the behavior * of the MMU. */ -2: li r11, 0x00f0 +2: li r11, RPN_PATTERN rlwimi r10, r11, 0, 24, 28 /* Set 24-27, clear 28 */ - DO_8xx_CPU6(0x3d80, r3) - mtspr SPRN_MD_RPN, r10 /* Update TLB entry */ + MTSPR_CPU6(SPRN_MD_RPN, r10, r3) /* Update TLB entry */ /* Restore registers */ #ifdef CONFIG_8xx_CPU6 - lwz r3, 8(r0) + mfspr r3, SPRN_DAR #endif mtspr SPRN_DAR, r11 /* Tag DAR */ mfspr r10, SPRN_SPRG_SCRATCH2 @@ -477,7 +469,17 @@ DataStoreTLBMiss: */ . = 0x1300 InstructionTLBError: - b InstructionAccess + EXCEPTION_PROLOG_0 +InstructionTLBError1: + EXCEPTION_PROLOG_1 + EXCEPTION_PROLOG_2 + mr r4,r12 + mr r5,r9 + andis. r10,r5,0x4000 + beq+ 1f + tlbie r4 + /* 0x400 is InstructionAccess exception, needed by bad_page_fault() */ +1: EXC_XFER_LITE(0x400, handle_page_fault) /* This is the data TLB error on the MPC8xx. This could be due to * many reasons, including a dirty update to a pte. We bail out to @@ -488,11 +490,21 @@ DataTLBError: EXCEPTION_PROLOG_0 mfspr r11, SPRN_DAR - cmpwi cr0, r11, 0x00f0 + cmpwi cr0, r11, RPN_PATTERN beq- FixupDAR /* must be a buggy dcbX, icbi insn. */ DARFixed:/* Return from dcbx instruction bug workaround */ - EXCEPTION_EPILOG_0 - b DataAccess + EXCEPTION_PROLOG_1 + EXCEPTION_PROLOG_2 + mfspr r5,SPRN_DSISR + stw r5,_DSISR(r11) + mfspr r4,SPRN_DAR + andis. r10,r5,0x4000 + beq+ 1f + tlbie r4 +1: li r10,RPN_PATTERN + mtspr SPRN_DAR,r10 /* Tag DAR, to be used in DTLB Error */ + /* 0x300 is DataAccess exception, needed by bad_page_fault() */ + EXC_XFER_LITE(0x300, handle_page_fault) EXCEPTION(0x1500, Trap_15, unknown_exception, EXC_XFER_EE) EXCEPTION(0x1600, Trap_16, unknown_exception, EXC_XFER_EE) @@ -521,29 +533,30 @@ DARFixed:/* Return from dcbx instruction bug workaround */ #define NO_SELF_MODIFYING_CODE FixupDAR:/* Entry point for dcbx workaround. */ #ifdef CONFIG_8xx_CPU6 - stw r3, 8(r0) + mtspr SPRN_DAR, r3 #endif mtspr SPRN_SPRG_SCRATCH2, r10 /* fetch instruction from memory. */ mfspr r10, SPRN_SRR0 andis. r11, r10, 0x8000 /* Address >= 0x80000000 */ - DO_8xx_CPU6(0x3780, r3) - mtspr SPRN_MD_EPN, r10 - mfspr r11, SPRN_M_TWB /* Get level 1 table entry address */ + mfspr r11, SPRN_M_TW /* Get level 1 table base address */ beq- 3f /* Branch if user space */ lis r11, (swapper_pg_dir-PAGE_OFFSET)@h ori r11, r11, (swapper_pg_dir-PAGE_OFFSET)@l - rlwimi r11, r10, 32-20, 0xffc /* r11 = r11&~0xffc|(r10>>20)&0xffc */ -3: lwz r11, 0(r11) /* Get the level 1 entry */ - DO_8xx_CPU6(0x3b80, r3) - mtspr SPRN_MD_TWC, r11 /* Load pte table base address */ - mfspr r11, SPRN_MD_TWC /* ....and get the pte address */ - lwz r11, 0(r11) /* Get the pte */ + /* Extract level 1 index */ +3: rlwinm r10, r10, 32 - ((PAGE_SHIFT - 2) << 1), (PAGE_SHIFT - 2) << 1, 29 + lwzx r11, r10, r11 /* Get the level 1 entry */ + rlwinm r10, r11,0,0,19 /* Extract page descriptor page address */ + mfspr r11, SPRN_SRR0 /* Get effective address of fault */ + /* Extract level 2 index */ + rlwinm r11, r11, 32 - (PAGE_SHIFT - 2), 32 - PAGE_SHIFT, 29 + lwzx r11, r10, r11 /* Get the pte */ #ifdef CONFIG_8xx_CPU6 - lwz r3, 8(r0) /* restore r3 from memory */ + mfspr r3, SPRN_DAR #endif /* concat physical page address(r11) and page offset(r10) */ - rlwimi r11, r10, 0, 20, 31 + mfspr r10, SPRN_SRR0 + rlwimi r11, r10, 0, 32 - PAGE_SHIFT, 31 lwz r11,0(r11) /* Check if it really is a dcbx instruction. */ /* dcbt and dcbtst does not generate DTLB Misses/Errors, @@ -698,11 +711,11 @@ start_here: #ifdef CONFIG_8xx_CPU6 lis r4, cpu6_errata_word@h ori r4, r4, cpu6_errata_word@l - li r3, 0x3980 + li r3, 0x3f80 stw r3, 12(r4) lwz r3, 12(r4) #endif - mtspr SPRN_M_TWB, r6 + mtspr SPRN_M_TW, r6 lis r4,2f@h ori r4,r4,2f@l tophys(r4,r4) @@ -876,10 +889,10 @@ _GLOBAL(set_context) lis r6, cpu6_errata_word@h ori r6, r6, cpu6_errata_word@l tophys (r4, r4) - li r7, 0x3980 + li r7, 0x3f80 stw r7, 12(r6) lwz r7, 12(r6) - mtspr SPRN_M_TWB, r4 /* Update MMU base address */ + mtspr SPRN_M_TW, r4 /* Update MMU base address */ li r7, 0x3380 stw r7, 12(r6) lwz r7, 12(r6) @@ -887,7 +900,7 @@ _GLOBAL(set_context) #else mtspr SPRN_M_CASID,r3 /* Update context */ tophys (r4, r4) - mtspr SPRN_M_TWB, r4 /* and pgd */ + mtspr SPRN_M_TW, r4 /* and pgd */ #endif SYNC blr @@ -919,12 +932,13 @@ set_dec_cpu6: .globl sdata sdata: .globl empty_zero_page + .align PAGE_SHIFT empty_zero_page: - .space 4096 + .space PAGE_SIZE .globl swapper_pg_dir swapper_pg_dir: - .space 4096 + .space PGD_TABLE_SIZE /* Room for two PTE table poiners, usually the kernel and current user * pointer to their respective root page table (pgdir). diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index 1f7d84e2e8b2..05e804cdecaa 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -63,7 +63,7 @@ int hw_breakpoint_slots(int type) int arch_install_hw_breakpoint(struct perf_event *bp) { struct arch_hw_breakpoint *info = counter_arch_bp(bp); - struct perf_event **slot = &__get_cpu_var(bp_per_reg); + struct perf_event **slot = this_cpu_ptr(&bp_per_reg); *slot = bp; @@ -88,7 +88,7 @@ int arch_install_hw_breakpoint(struct perf_event *bp) */ void arch_uninstall_hw_breakpoint(struct perf_event *bp) { - struct perf_event **slot = &__get_cpu_var(bp_per_reg); + struct perf_event **slot = this_cpu_ptr(&bp_per_reg); if (*slot != bp) { WARN_ONCE(1, "Can't find the breakpoint"); @@ -226,7 +226,7 @@ int __kprobes hw_breakpoint_handler(struct die_args *args) */ rcu_read_lock(); - bp = __get_cpu_var(bp_per_reg); + bp = __this_cpu_read(bp_per_reg); if (!bp) goto out; info = counter_arch_bp(bp); diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S index c0754bbf8118..05adc8bbdef8 100644 --- a/arch/powerpc/kernel/idle_power7.S +++ b/arch/powerpc/kernel/idle_power7.S @@ -18,9 +18,25 @@ #include <asm/hw_irq.h> #include <asm/kvm_book3s_asm.h> #include <asm/opal.h> +#include <asm/cpuidle.h> +#include <asm/mmu-hash64.h> #undef DEBUG +/* + * Use unused space in the interrupt stack to save and restore + * registers for winkle support. + */ +#define _SDR1 GPR3 +#define _RPR GPR4 +#define _SPURR GPR5 +#define _PURR GPR6 +#define _TSCR GPR7 +#define _DSCR GPR8 +#define _AMOR GPR9 +#define _WORT GPR10 +#define _WORC GPR11 + /* Idle state entry routines */ #define IDLE_STATE_ENTER_SEQ(IDLE_INST) \ @@ -37,8 +53,7 @@ /* * Pass requested state in r3: - * 0 - nap - * 1 - sleep + * r3 - PNV_THREAD_NAP/SLEEP/WINKLE * * To check IRQ_HAPPENED in r4 * 0 - don't check @@ -101,18 +116,105 @@ _GLOBAL(power7_powersave_common) std r9,_MSR(r1) std r1,PACAR1(r13) -_GLOBAL(power7_enter_nap_mode) + /* + * Go to real mode to do the nap, as required by the architecture. + * Also, we need to be in real mode before setting hwthread_state, + * because as soon as we do that, another thread can switch + * the MMU context to the guest. + */ + LOAD_REG_IMMEDIATE(r5, MSR_IDLE) + li r6, MSR_RI + andc r6, r9, r6 + LOAD_REG_ADDR(r7, power7_enter_nap_mode) + mtmsrd r6, 1 /* clear RI before setting SRR0/1 */ + mtspr SPRN_SRR0, r7 + mtspr SPRN_SRR1, r5 + rfid + + .globl power7_enter_nap_mode +power7_enter_nap_mode: #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE /* Tell KVM we're napping */ li r4,KVM_HWTHREAD_IN_NAP stb r4,HSTATE_HWTHREAD_STATE(r13) #endif - cmpwi cr0,r3,1 - beq 2f + stb r3,PACA_THREAD_IDLE_STATE(r13) + cmpwi cr3,r3,PNV_THREAD_SLEEP + bge cr3,2f IDLE_STATE_ENTER_SEQ(PPC_NAP) /* No return */ -2: IDLE_STATE_ENTER_SEQ(PPC_SLEEP) - /* No return */ +2: + /* Sleep or winkle */ + lbz r7,PACA_THREAD_MASK(r13) + ld r14,PACA_CORE_IDLE_STATE_PTR(r13) +lwarx_loop1: + lwarx r15,0,r14 + andc r15,r15,r7 /* Clear thread bit */ + + andi. r15,r15,PNV_CORE_IDLE_THREAD_BITS + +/* + * If cr0 = 0, then current thread is the last thread of the core entering + * sleep. Last thread needs to execute the hardware bug workaround code if + * required by the platform. + * Make the workaround call unconditionally here. The below branch call is + * patched out when the idle states are discovered if the platform does not + * require it. + */ +.global pnv_fastsleep_workaround_at_entry +pnv_fastsleep_workaround_at_entry: + beq fastsleep_workaround_at_entry + + stwcx. r15,0,r14 + bne- lwarx_loop1 + isync + +common_enter: /* common code for all the threads entering sleep or winkle */ + bgt cr3,enter_winkle + IDLE_STATE_ENTER_SEQ(PPC_SLEEP) + +fastsleep_workaround_at_entry: + ori r15,r15,PNV_CORE_IDLE_LOCK_BIT + stwcx. r15,0,r14 + bne- lwarx_loop1 + isync + + /* Fast sleep workaround */ + li r3,1 + li r4,1 + li r0,OPAL_CONFIG_CPU_IDLE_STATE + bl opal_call_realmode + + /* Clear Lock bit */ + li r0,0 + lwsync + stw r0,0(r14) + b common_enter + +enter_winkle: + /* + * Note all register i.e per-core, per-subcore or per-thread is saved + * here since any thread in the core might wake up first + */ + mfspr r3,SPRN_SDR1 + std r3,_SDR1(r1) + mfspr r3,SPRN_RPR + std r3,_RPR(r1) + mfspr r3,SPRN_SPURR + std r3,_SPURR(r1) + mfspr r3,SPRN_PURR + std r3,_PURR(r1) + mfspr r3,SPRN_TSCR + std r3,_TSCR(r1) + mfspr r3,SPRN_DSCR + std r3,_DSCR(r1) + mfspr r3,SPRN_AMOR + std r3,_AMOR(r1) + mfspr r3,SPRN_WORT + std r3,_WORT(r1) + mfspr r3,SPRN_WORC + std r3,_WORC(r1) + IDLE_STATE_ENTER_SEQ(PPC_WINKLE) _GLOBAL(power7_idle) /* Now check if user or arch enabled NAP mode */ @@ -125,48 +227,21 @@ _GLOBAL(power7_idle) _GLOBAL(power7_nap) mr r4,r3 - li r3,0 + li r3,PNV_THREAD_NAP b power7_powersave_common /* No return */ _GLOBAL(power7_sleep) - li r3,1 + li r3,PNV_THREAD_SLEEP li r4,1 b power7_powersave_common /* No return */ -/* - * Make opal call in realmode. This is a generic function to be called - * from realmode from reset vector. It handles endianess. - * - * r13 - paca pointer - * r1 - stack pointer - * r3 - opal token - */ -opal_call_realmode: - mflr r12 - std r12,_LINK(r1) - ld r2,PACATOC(r13) - /* Set opal return address */ - LOAD_REG_ADDR(r0,return_from_opal_call) - mtlr r0 - /* Handle endian-ness */ - li r0,MSR_LE - mfmsr r12 - andc r12,r12,r0 - mtspr SPRN_HSRR1,r12 - mr r0,r3 /* Move opal token to r0 */ - LOAD_REG_ADDR(r11,opal) - ld r12,8(r11) - ld r2,0(r11) - mtspr SPRN_HSRR0,r12 - hrfid - -return_from_opal_call: - FIXUP_ENDIAN - ld r0,_LINK(r1) - mtlr r0 - blr +_GLOBAL(power7_winkle) + li r3,3 + li r4,1 + b power7_powersave_common + /* No return */ #define CHECK_HMI_INTERRUPT \ mfspr r0,SPRN_SRR1; \ @@ -181,7 +256,7 @@ ALT_FTR_SECTION_END_NESTED_IFSET(CPU_FTR_ARCH_207S, 66); \ ld r2,PACATOC(r13); \ ld r1,PACAR1(r13); \ std r3,ORIG_GPR3(r1); /* Save original r3 */ \ - li r3,OPAL_HANDLE_HMI; /* Pass opal token argument*/ \ + li r0,OPAL_HANDLE_HMI; /* Pass opal token argument*/ \ bl opal_call_realmode; \ ld r3,ORIG_GPR3(r1); /* Restore original r3 */ \ 20: nop; @@ -190,16 +265,190 @@ ALT_FTR_SECTION_END_NESTED_IFSET(CPU_FTR_ARCH_207S, 66); \ _GLOBAL(power7_wakeup_tb_loss) ld r2,PACATOC(r13); ld r1,PACAR1(r13) + /* + * Before entering any idle state, the NVGPRs are saved in the stack + * and they are restored before switching to the process context. Hence + * until they are restored, they are free to be used. + * + * Save SRR1 in a NVGPR as it might be clobbered in opal_call_realmode + * (called in CHECK_HMI_INTERRUPT). SRR1 is required to determine the + * wakeup reason if we branch to kvm_start_guest. + */ + mfspr r16,SPRN_SRR1 BEGIN_FTR_SECTION CHECK_HMI_INTERRUPT END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) + + lbz r7,PACA_THREAD_MASK(r13) + ld r14,PACA_CORE_IDLE_STATE_PTR(r13) +lwarx_loop2: + lwarx r15,0,r14 + andi. r9,r15,PNV_CORE_IDLE_LOCK_BIT + /* + * Lock bit is set in one of the 2 cases- + * a. In the sleep/winkle enter path, the last thread is executing + * fastsleep workaround code. + * b. In the wake up path, another thread is executing fastsleep + * workaround undo code or resyncing timebase or restoring context + * In either case loop until the lock bit is cleared. + */ + bne core_idle_lock_held + + cmpwi cr2,r15,0 + lbz r4,PACA_SUBCORE_SIBLING_MASK(r13) + and r4,r4,r15 + cmpwi cr1,r4,0 /* Check if first in subcore */ + + /* + * At this stage + * cr1 - 0b0100 if first thread to wakeup in subcore + * cr2 - 0b0100 if first thread to wakeup in core + * cr3- 0b0010 if waking up from sleep or winkle + * cr4 - 0b0100 if waking up from winkle + */ + + or r15,r15,r7 /* Set thread bit */ + + beq cr1,first_thread_in_subcore + + /* Not first thread in subcore to wake up */ + stwcx. r15,0,r14 + bne- lwarx_loop2 + isync + b common_exit + +core_idle_lock_held: + HMT_LOW +core_idle_lock_loop: + lwz r15,0(14) + andi. r9,r15,PNV_CORE_IDLE_LOCK_BIT + bne core_idle_lock_loop + HMT_MEDIUM + b lwarx_loop2 + +first_thread_in_subcore: + /* First thread in subcore to wakeup */ + ori r15,r15,PNV_CORE_IDLE_LOCK_BIT + stwcx. r15,0,r14 + bne- lwarx_loop2 + isync + + /* + * If waking up from sleep, subcore state is not lost. Hence + * skip subcore state restore + */ + bne cr4,subcore_state_restored + + /* Restore per-subcore state */ + ld r4,_SDR1(r1) + mtspr SPRN_SDR1,r4 + ld r4,_RPR(r1) + mtspr SPRN_RPR,r4 + ld r4,_AMOR(r1) + mtspr SPRN_AMOR,r4 + +subcore_state_restored: + /* + * Check if the thread is also the first thread in the core. If not, + * skip to clear_lock. + */ + bne cr2,clear_lock + +first_thread_in_core: + + /* + * First thread in the core waking up from fastsleep. It needs to + * call the fastsleep workaround code if the platform requires it. + * Call it unconditionally here. The below branch instruction will + * be patched out when the idle states are discovered if platform + * does not require workaround. + */ +.global pnv_fastsleep_workaround_at_exit +pnv_fastsleep_workaround_at_exit: + b fastsleep_workaround_at_exit + +timebase_resync: + /* Do timebase resync if we are waking up from sleep. Use cr3 value + * set in exceptions-64s.S */ + ble cr3,clear_lock /* Time base re-sync */ - li r3,OPAL_RESYNC_TIMEBASE + li r0,OPAL_RESYNC_TIMEBASE bl opal_call_realmode; - /* TODO: Check r3 for failure */ + /* + * If waking up from sleep, per core state is not lost, skip to + * clear_lock. + */ + bne cr4,clear_lock + + /* Restore per core state */ + ld r4,_TSCR(r1) + mtspr SPRN_TSCR,r4 + ld r4,_WORC(r1) + mtspr SPRN_WORC,r4 + +clear_lock: + andi. r15,r15,PNV_CORE_IDLE_THREAD_BITS + lwsync + stw r15,0(r14) + +common_exit: + /* + * Common to all threads. + * + * If waking up from sleep, hypervisor state is not lost. Hence + * skip hypervisor state restore. + */ + bne cr4,hypervisor_state_restored + + /* Waking up from winkle */ + + /* Restore per thread state */ + bl __restore_cpu_power8 + + /* Restore SLB from PACA */ + ld r8,PACA_SLBSHADOWPTR(r13) + + .rept SLB_NUM_BOLTED + li r3, SLBSHADOW_SAVEAREA + LDX_BE r5, r8, r3 + addi r3, r3, 8 + LDX_BE r6, r8, r3 + andis. r7,r5,SLB_ESID_V@h + beq 1f + slbmte r6,r5 +1: addi r8,r8,16 + .endr + + ld r4,_SPURR(r1) + mtspr SPRN_SPURR,r4 + ld r4,_PURR(r1) + mtspr SPRN_PURR,r4 + ld r4,_DSCR(r1) + mtspr SPRN_DSCR,r4 + ld r4,_WORT(r1) + mtspr SPRN_WORT,r4 + +hypervisor_state_restored: + + li r5,PNV_THREAD_RUNNING + stb r5,PACA_THREAD_IDLE_STATE(r13) + + mtspr SPRN_SRR1,r16 +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + li r0,KVM_HWTHREAD_IN_KERNEL + stb r0,HSTATE_HWTHREAD_STATE(r13) + /* Order setting hwthread_state vs. testing hwthread_req */ + sync + lbz r0,HSTATE_HWTHREAD_REQ(r13) + cmpwi r0,0 + beq 6f + b kvm_start_guest +6: +#endif + REST_NVGPRS(r1) REST_GPR(2, r1) ld r3,_CCR(r1) @@ -212,6 +461,17 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) mtspr SPRN_SRR0,r5 rfid +fastsleep_workaround_at_exit: + li r3,1 + li r4,0 + li r0,OPAL_CONFIG_CPU_IDLE_STATE + bl opal_call_realmode + b timebase_resync + +/* + * R3 here contains the value that will be returned to the caller + * of power7_nap. + */ _GLOBAL(power7_wakeup_loss) ld r1,PACAR1(r13) BEGIN_FTR_SECTION @@ -219,15 +479,19 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) REST_NVGPRS(r1) REST_GPR(2, r1) - ld r3,_CCR(r1) + ld r6,_CCR(r1) ld r4,_MSR(r1) ld r5,_NIP(r1) addi r1,r1,INT_FRAME_SIZE - mtcr r3 + mtcr r6 mtspr SPRN_SRR1,r4 mtspr SPRN_SRR0,r5 rfid +/* + * R3 here contains the value that will be returned to the caller + * of power7_nap. + */ _GLOBAL(power7_wakeup_noloss) lbz r0,PACA_NAPSTATELOST(r13) cmpwi r0,0 diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index a10642a0d861..5d3968c4d799 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -208,7 +208,7 @@ static unsigned long iommu_range_alloc(struct device *dev, * We don't need to disable preemption here because any CPU can * safely use any IOMMU pool. */ - pool_nr = __raw_get_cpu_var(iommu_pool_hash) & (tbl->nr_pools - 1); + pool_nr = __this_cpu_read(iommu_pool_hash) & (tbl->nr_pools - 1); if (largealloc) pool = &(tbl->large_pool); @@ -428,10 +428,10 @@ static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr, ppc_md.tce_flush(tbl); } -int iommu_map_sg(struct device *dev, struct iommu_table *tbl, - struct scatterlist *sglist, int nelems, - unsigned long mask, enum dma_data_direction direction, - struct dma_attrs *attrs) +int ppc_iommu_map_sg(struct device *dev, struct iommu_table *tbl, + struct scatterlist *sglist, int nelems, + unsigned long mask, enum dma_data_direction direction, + struct dma_attrs *attrs) { dma_addr_t dma_next = 0, dma_addr; struct scatterlist *s, *outs, *segstart; @@ -539,7 +539,7 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl, DBG("mapped %d elements:\n", outcount); - /* For the sake of iommu_unmap_sg, we clear out the length in the + /* For the sake of ppc_iommu_unmap_sg, we clear out the length in the * next entry of the sglist if we didn't fill the list completely */ if (outcount < incount) { @@ -572,9 +572,9 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl, } -void iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist, - int nelems, enum dma_data_direction direction, - struct dma_attrs *attrs) +void ppc_iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist, + int nelems, enum dma_data_direction direction, + struct dma_attrs *attrs) { struct scatterlist *sg; diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index c14383575fe8..45096033d37b 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -50,7 +50,6 @@ #include <linux/list.h> #include <linux/radix-tree.h> #include <linux/mutex.h> -#include <linux/bootmem.h> #include <linux/pci.h> #include <linux/debugfs.h> #include <linux/of.h> @@ -114,7 +113,7 @@ static inline notrace void set_soft_enabled(unsigned long enable) static inline notrace int decrementer_check_overflow(void) { u64 now = get_tb_or_rtc(); - u64 *next_tb = &__get_cpu_var(decrementers_next_tb); + u64 *next_tb = this_cpu_ptr(&decrementers_next_tb); return now >= *next_tb; } @@ -499,7 +498,7 @@ void __do_irq(struct pt_regs *regs) /* And finally process it */ if (unlikely(irq == NO_IRQ)) - __get_cpu_var(irq_stat).spurious_irqs++; + __this_cpu_inc(irq_stat.spurious_irqs); else generic_handle_irq(irq); diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c index 8504657379f1..e77c3ccf8dcf 100644 --- a/arch/powerpc/kernel/kgdb.c +++ b/arch/powerpc/kernel/kgdb.c @@ -155,7 +155,7 @@ static int kgdb_singlestep(struct pt_regs *regs) { struct thread_info *thread_info, *exception_thread_info; struct thread_info *backup_current_thread_info = - &__get_cpu_var(kgdb_thread_info); + this_cpu_ptr(&kgdb_thread_info); if (user_mode(regs)) return 0; diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index 2f72af82513c..7c053f281406 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -119,7 +119,7 @@ static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb) static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb) { - __get_cpu_var(current_kprobe) = kcb->prev_kprobe.kp; + __this_cpu_write(current_kprobe, kcb->prev_kprobe.kp); kcb->kprobe_status = kcb->prev_kprobe.status; kcb->kprobe_saved_msr = kcb->prev_kprobe.saved_msr; } @@ -127,7 +127,7 @@ static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb) static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb) { - __get_cpu_var(current_kprobe) = p; + __this_cpu_write(current_kprobe, p); kcb->kprobe_saved_msr = regs->msr; } @@ -192,7 +192,7 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) ret = 1; goto no_kprobe; } - p = __get_cpu_var(current_kprobe); + p = __this_cpu_read(current_kprobe); if (p->break_handler && p->break_handler(p, regs)) { goto ss_probe; } diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c index 879b3aacac32..f96d1ec24189 100644 --- a/arch/powerpc/kernel/machine_kexec_64.c +++ b/arch/powerpc/kernel/machine_kexec_64.c @@ -330,7 +330,7 @@ void default_machine_kexec(struct kimage *image) * using debugger IPI. */ - if (crashing_cpu == -1) + if (!kdump_in_progress()) kexec_prepare_cpus(); pr_debug("kexec: Starting switchover sequence.\n"); diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c index a7fd4cb78b78..15c99b649b04 100644 --- a/arch/powerpc/kernel/mce.c +++ b/arch/powerpc/kernel/mce.c @@ -73,8 +73,8 @@ void save_mce_event(struct pt_regs *regs, long handled, uint64_t nip, uint64_t addr) { uint64_t srr1; - int index = __get_cpu_var(mce_nest_count)++; - struct machine_check_event *mce = &__get_cpu_var(mce_event[index]); + int index = __this_cpu_inc_return(mce_nest_count); + struct machine_check_event *mce = this_cpu_ptr(&mce_event[index]); /* * Return if we don't have enough space to log mce event. @@ -143,7 +143,7 @@ void save_mce_event(struct pt_regs *regs, long handled, */ int get_mce_event(struct machine_check_event *mce, bool release) { - int index = __get_cpu_var(mce_nest_count) - 1; + int index = __this_cpu_read(mce_nest_count) - 1; struct machine_check_event *mc_evt; int ret = 0; @@ -153,7 +153,7 @@ int get_mce_event(struct machine_check_event *mce, bool release) /* Check if we have MCE info to process. */ if (index < MAX_MC_EVT) { - mc_evt = &__get_cpu_var(mce_event[index]); + mc_evt = this_cpu_ptr(&mce_event[index]); /* Copy the event structure and release the original */ if (mce) *mce = *mc_evt; @@ -163,7 +163,7 @@ int get_mce_event(struct machine_check_event *mce, bool release) } /* Decrement the count to free the slot. */ if (release) - __get_cpu_var(mce_nest_count)--; + __this_cpu_dec(mce_nest_count); return ret; } @@ -184,13 +184,13 @@ void machine_check_queue_event(void) if (!get_mce_event(&evt, MCE_EVENT_RELEASE)) return; - index = __get_cpu_var(mce_queue_count)++; + index = __this_cpu_inc_return(mce_queue_count); /* If queue is full, just return for now. */ if (index >= MAX_MC_EVT) { - __get_cpu_var(mce_queue_count)--; + __this_cpu_dec(mce_queue_count); return; } - __get_cpu_var(mce_event_queue[index]) = evt; + memcpy(this_cpu_ptr(&mce_event_queue[index]), &evt, sizeof(evt)); /* Queue irq work to process this event later. */ irq_work_queue(&mce_event_process_work); @@ -208,11 +208,11 @@ static void machine_check_process_queued_event(struct irq_work *work) * For now just print it to console. * TODO: log this error event to FSP or nvram. */ - while (__get_cpu_var(mce_queue_count) > 0) { - index = __get_cpu_var(mce_queue_count) - 1; + while (__this_cpu_read(mce_queue_count) > 0) { + index = __this_cpu_read(mce_queue_count) - 1; machine_check_print_event_info( - &__get_cpu_var(mce_event_queue[index])); - __get_cpu_var(mce_queue_count)--; + this_cpu_ptr(&mce_event_queue[index])); + __this_cpu_dec(mce_queue_count); } } diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c index aa9aff3d6ad3..b6f123ab90ed 100644 --- a/arch/powerpc/kernel/mce_power.c +++ b/arch/powerpc/kernel/mce_power.c @@ -79,7 +79,7 @@ static long mce_handle_derror(uint64_t dsisr, uint64_t slb_error_bits) } if (dsisr & P7_DSISR_MC_TLB_MULTIHIT_MFTLB) { if (cur_cpu_spec && cur_cpu_spec->flush_tlb) - cur_cpu_spec->flush_tlb(TLBIEL_INVAL_PAGE); + cur_cpu_spec->flush_tlb(TLBIEL_INVAL_SET); /* reset error bits */ dsisr &= ~P7_DSISR_MC_TLB_MULTIHIT_MFTLB; } @@ -110,7 +110,7 @@ static long mce_handle_common_ierror(uint64_t srr1) break; case P7_SRR1_MC_IFETCH_TLB_MULTIHIT: if (cur_cpu_spec && cur_cpu_spec->flush_tlb) { - cur_cpu_spec->flush_tlb(TLBIEL_INVAL_PAGE); + cur_cpu_spec->flush_tlb(TLBIEL_INVAL_SET); handled = 1; } break; diff --git a/arch/powerpc/kernel/of_platform.c b/arch/powerpc/kernel/of_platform.c index f87bc1b4bdda..2f35a72642c6 100644 --- a/arch/powerpc/kernel/of_platform.c +++ b/arch/powerpc/kernel/of_platform.c @@ -110,7 +110,6 @@ static struct platform_driver of_pci_phb_driver = { .probe = of_pci_phb_probe, .driver = { .name = "of-pci", - .owner = THIS_MODULE, .of_match_table = of_pci_phb_ids, }, }; diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index e5dad9a9edc0..37d512d35943 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -20,7 +20,6 @@ #include <linux/pci.h> #include <linux/string.h> #include <linux/init.h> -#include <linux/bootmem.h> #include <linux/delay.h> #include <linux/export.h> #include <linux/of_address.h> @@ -1464,7 +1463,7 @@ static void pcibios_setup_phb_resources(struct pci_controller *hose, res = &hose->io_resource; if (!res->flags) { - printk(KERN_WARNING "PCI: I/O resource not set for host" + pr_info("PCI: I/O resource not set for host" " bridge %s (domain %d)\n", hose->dn->full_name, hose->global_number); } else { diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c index 432459c817fa..1f7930037cb7 100644 --- a/arch/powerpc/kernel/pci_32.c +++ b/arch/powerpc/kernel/pci_32.c @@ -199,9 +199,7 @@ pci_create_OF_bus_map(void) struct property* of_prop; struct device_node *dn; - of_prop = (struct property*) alloc_bootmem(sizeof(struct property) + 256); - if (!of_prop) - return; + of_prop = memblock_virt_alloc(sizeof(struct property) + 256, 0); dn = of_find_node_by_path("/"); if (dn) { memset(of_prop, -1, sizeof(struct property) + 256); diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index b15194e2c5fc..60bb187cb46a 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -17,7 +17,6 @@ #include <linux/pci.h> #include <linux/string.h> #include <linux/init.h> -#include <linux/bootmem.h> #include <linux/export.h> #include <linux/mm.h> #include <linux/list.h> diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 923cd2daba89..b4cc7bef6b16 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -37,9 +37,9 @@ #include <linux/personality.h> #include <linux/random.h> #include <linux/hw_breakpoint.h> +#include <linux/uaccess.h> #include <asm/pgtable.h> -#include <asm/uaccess.h> #include <asm/io.h> #include <asm/processor.h> #include <asm/mmu.h> @@ -499,7 +499,7 @@ static inline int set_dawr(struct arch_hw_breakpoint *brk) void __set_breakpoint(struct arch_hw_breakpoint *brk) { - __get_cpu_var(current_brk) = *brk; + memcpy(this_cpu_ptr(¤t_brk), brk, sizeof(*brk)); if (cpu_has_feature(CPU_FTR_DAWR)) set_dawr(brk); @@ -842,7 +842,7 @@ struct task_struct *__switch_to(struct task_struct *prev, * schedule DABR */ #ifndef CONFIG_HAVE_HW_BREAKPOINT - if (unlikely(!hw_brk_match(&__get_cpu_var(current_brk), &new->thread.hw_brk))) + if (unlikely(!hw_brk_match(this_cpu_ptr(¤t_brk), &new->thread.hw_brk))) __set_breakpoint(&new->thread.hw_brk); #endif /* CONFIG_HAVE_HW_BREAKPOINT */ #endif @@ -856,7 +856,7 @@ struct task_struct *__switch_to(struct task_struct *prev, * Collect processor utilization data per process */ if (firmware_has_feature(FW_FEATURE_SPLPAR)) { - struct cpu_usage *cu = &__get_cpu_var(cpu_usage_array); + struct cpu_usage *cu = this_cpu_ptr(&cpu_usage_array); long unsigned start_tb, current_tb; start_tb = old_thread->start_tb; cu->current_tb = current_tb = mfspr(SPRN_PURR); @@ -866,7 +866,7 @@ struct task_struct *__switch_to(struct task_struct *prev, #endif /* CONFIG_PPC64 */ #ifdef CONFIG_PPC_BOOK3S_64 - batch = &__get_cpu_var(ppc64_tlb_batch); + batch = this_cpu_ptr(&ppc64_tlb_batch); if (batch->active) { current_thread_info()->local_flags |= _TLF_LAZY_MMU; if (batch->index) @@ -889,7 +889,7 @@ struct task_struct *__switch_to(struct task_struct *prev, #ifdef CONFIG_PPC_BOOK3S_64 if (current_thread_info()->local_flags & _TLF_LAZY_MMU) { current_thread_info()->local_flags &= ~_TLF_LAZY_MMU; - batch = &__get_cpu_var(ppc64_tlb_batch); + batch = this_cpu_ptr(&ppc64_tlb_batch); batch->active = 1; } #endif /* CONFIG_PPC_BOOK3S_64 */ @@ -921,12 +921,8 @@ static void show_instructions(struct pt_regs *regs) pc = (unsigned long)phys_to_virt(pc); #endif - /* We use __get_user here *only* to avoid an OOPS on a - * bad address because the pc *should* only be a - * kernel address. - */ if (!__kernel_text_address(pc) || - __get_user(instr, (unsigned int __user *)pc)) { + probe_kernel_address((unsigned int __user *)pc, instr)) { printk(KERN_CONT "XXXXXXXX "); } else { if (regs->nip == pc) @@ -1531,13 +1527,6 @@ void show_stack(struct task_struct *tsk, unsigned long *stack) int curr_frame = current->curr_ret_stack; extern void return_to_handler(void); unsigned long rth = (unsigned long)return_to_handler; - unsigned long mrth = -1; -#ifdef CONFIG_PPC64 - extern void mod_return_to_handler(void); - rth = *(unsigned long *)rth; - mrth = (unsigned long)mod_return_to_handler; - mrth = *(unsigned long *)mrth; -#endif #endif sp = (unsigned long) stack; @@ -1562,7 +1551,7 @@ void show_stack(struct task_struct *tsk, unsigned long *stack) if (!firstframe || ip != lr) { printk("["REG"] ["REG"] %pS", sp, ip, (void *)ip); #ifdef CONFIG_FUNCTION_GRAPH_TRACER - if ((ip == rth || ip == mrth) && curr_frame >= 0) { + if ((ip == rth) && curr_frame >= 0) { printk(" (%pS)", (void *)current->ret_stack[curr_frame].ret); curr_frame--; @@ -1665,12 +1654,3 @@ unsigned long arch_randomize_brk(struct mm_struct *mm) return ret; } -unsigned long randomize_et_dyn(unsigned long base) -{ - unsigned long ret = PAGE_ALIGN(base + brk_rnd()); - - if (ret < base) - return base; - - return ret; -} diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 099f27e6d1b0..6a799b3cc6b4 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -160,6 +160,12 @@ static struct ibm_pa_feature { {CPU_FTR_NODSISRALIGN, 0, 0, 1, 1, 1}, {0, MMU_FTR_CI_LARGE_PAGE, 0, 1, 2, 0}, {CPU_FTR_REAL_LE, PPC_FEATURE_TRUE_LE, 5, 0, 0}, + /* + * If the kernel doesn't support TM (ie. CONFIG_PPC_TRANSACTIONAL_MEM=n), + * we don't want to turn on CPU_FTR_TM here, so we use CPU_FTR_TM_COMP + * which is 0 if the kernel doesn't support TM. + */ + {CPU_FTR_TM_COMP, 0, 0, 22, 0, 0}, }; static void __init scan_features(unsigned long node, const unsigned char *ftrs, @@ -696,10 +702,7 @@ void __init early_init_devtree(void *params) reserve_crashkernel(); early_reserve_mem(); - /* - * Ensure that total memory size is page-aligned, because otherwise - * mark_bootmem() gets upset. - */ + /* Ensure that total memory size is page-aligned. */ limit = ALIGN(memory_limit ?: memblock_phys_mem_size(), PAGE_SIZE); memblock_enforce_memory_limit(limit); diff --git a/arch/powerpc/kernel/rtas-proc.c b/arch/powerpc/kernel/rtas-proc.c index 8777fb02349f..fb2fb3ea85e5 100644 --- a/arch/powerpc/kernel/rtas-proc.c +++ b/arch/powerpc/kernel/rtas-proc.c @@ -113,17 +113,6 @@ #define SENSOR_PREFIX "ibm,sensor-" #define cel_to_fahr(x) ((x*9/5)+32) - -/* Globals */ -static struct rtas_sensors sensors; -static struct device_node *rtas_node = NULL; -static unsigned long power_on_time = 0; /* Save the time the user set */ -static char progress_led[MAX_LINELENGTH]; - -static unsigned long rtas_tone_frequency = 1000; -static unsigned long rtas_tone_volume = 0; - -/* ****************STRUCTS******************************************* */ struct individual_sensor { unsigned int token; unsigned int quant; @@ -134,6 +123,15 @@ struct rtas_sensors { unsigned int quant; }; +/* Globals */ +static struct rtas_sensors sensors; +static struct device_node *rtas_node = NULL; +static unsigned long power_on_time = 0; /* Save the time the user set */ +static char progress_led[MAX_LINELENGTH]; + +static unsigned long rtas_tone_frequency = 1000; +static unsigned long rtas_tone_volume = 0; + /* ****************************************************************** */ /* Declarations */ static int ppc_rtas_sensors_show(struct seq_file *m, void *v); diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 8b4c857c1421..4af905e81ab0 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -1091,8 +1091,8 @@ asmlinkage int ppc_rtas(struct rtas_args __user *uargs) } /* - * Call early during boot, before mem init or bootmem, to retrieve the RTAS - * informations from the device-tree and allocate the RMO buffer for userland + * Call early during boot, before mem init, to retrieve the RTAS + * information from the device-tree and allocate the RMO buffer for userland * accesses. */ void __init rtas_initialize(void) diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c index 7c55b86206b3..ce230da2c015 100644 --- a/arch/powerpc/kernel/rtas_pci.c +++ b/arch/powerpc/kernel/rtas_pci.c @@ -26,7 +26,6 @@ #include <linux/pci.h> #include <linux/string.h> #include <linux/init.h> -#include <linux/bootmem.h> #include <asm/io.h> #include <asm/pgtable.h> diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 1362cd62b3fa..44c8d03558ac 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -139,8 +139,8 @@ void machine_restart(char *cmd) void machine_power_off(void) { machine_shutdown(); - if (ppc_md.power_off) - ppc_md.power_off(); + if (pm_power_off) + pm_power_off(); #ifdef CONFIG_SMP smp_send_stop(); #endif @@ -151,7 +151,7 @@ void machine_power_off(void) /* Used by the G5 thermal driver */ EXPORT_SYMBOL_GPL(machine_power_off); -void (*pm_power_off)(void) = machine_power_off; +void (*pm_power_off)(void); EXPORT_SYMBOL_GPL(pm_power_off); void machine_halt(void) diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index 07831ed0d9ef..bb02e9f6944e 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -11,7 +11,6 @@ #include <linux/delay.h> #include <linux/initrd.h> #include <linux/tty.h> -#include <linux/bootmem.h> #include <linux/seq_file.h> #include <linux/root_dev.h> #include <linux/cpu.h> @@ -53,11 +52,6 @@ unsigned long ISA_DMA_THRESHOLD; unsigned int DMA_MODE_READ; unsigned int DMA_MODE_WRITE; -#ifdef CONFIG_VGA_CONSOLE -unsigned long vgacon_remap_base; -EXPORT_SYMBOL(vgacon_remap_base); -#endif - /* * These are used in binfmt_elf.c to put aux entries on the stack * for each elf executable being started. @@ -311,9 +305,8 @@ void __init setup_arch(char **cmdline_p) irqstack_early_init(); - /* set up the bootmem stuff with available memory */ - do_init_bootmem(); - if ( ppc_md.progress ) ppc_md.progress("setup_arch: bootmem", 0x3eab); + initmem_init(); + if ( ppc_md.progress ) ppc_md.progress("setup_arch: initmem", 0x3eab); #ifdef CONFIG_DUMMY_CONSOLE conswitchp = &dummy_con; diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 4f3cfe1b6a33..49f553bbb360 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -660,13 +660,11 @@ static void __init emergency_stack_init(void) } /* - * Called into from start_kernel this initializes bootmem, which is used + * Called into from start_kernel this initializes memblock, which is used * to manage page allocation until mem_init is called. */ void __init setup_arch(char **cmdline_p) { - ppc64_boot_msg(0x12, "Setup Arch"); - *cmdline_p = boot_command_line; /* @@ -691,9 +689,7 @@ void __init setup_arch(char **cmdline_p) exc_lvl_early_init(); emergency_stack_init(); - /* set up the bootmem stuff with available memory */ - do_init_bootmem(); - sparse_init(); + initmem_init(); #ifdef CONFIG_DUMMY_CONSOLE conswitchp = &dummy_con; @@ -711,33 +707,6 @@ void __init setup_arch(char **cmdline_p) if ((unsigned long)_stext & 0xffff) panic("Kernelbase not 64K-aligned (0x%lx)!\n", (unsigned long)_stext); - - ppc64_boot_msg(0x15, "Setup Done"); -} - - -/* ToDo: do something useful if ppc_md is not yet setup. */ -#define PPC64_LINUX_FUNCTION 0x0f000000 -#define PPC64_IPL_MESSAGE 0xc0000000 -#define PPC64_TERM_MESSAGE 0xb0000000 - -static void ppc64_do_msg(unsigned int src, const char *msg) -{ - if (ppc_md.progress) { - char buf[128]; - - sprintf(buf, "%08X\n", src); - ppc_md.progress(buf, 0); - snprintf(buf, 128, "%s", msg); - ppc_md.progress(buf, 0); - } -} - -/* Print a boot progress message. */ -void ppc64_boot_msg(unsigned int src, const char *msg) -{ - ppc64_do_msg(PPC64_LINUX_FUNCTION|PPC64_IPL_MESSAGE|src, msg); - printk("[boot]%04x %s\n", src, msg); } #ifdef CONFIG_SMP diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 71e186d5f331..8b2d2dc8ef10 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -243,7 +243,7 @@ void smp_muxed_ipi_message_pass(int cpu, int msg) irqreturn_t smp_ipi_demux(void) { - struct cpu_messages *info = &__get_cpu_var(ipi_message); + struct cpu_messages *info = this_cpu_ptr(&ipi_message); unsigned int all; mb(); /* order any irq clear */ @@ -442,9 +442,9 @@ void generic_mach_cpu_die(void) idle_task_exit(); cpu = smp_processor_id(); printk(KERN_DEBUG "CPU%d offline\n", cpu); - __get_cpu_var(cpu_state) = CPU_DEAD; + __this_cpu_write(cpu_state, CPU_DEAD); smp_wmb(); - while (__get_cpu_var(cpu_state) != CPU_UP_PREPARE) + while (__this_cpu_read(cpu_state) != CPU_UP_PREPARE) cpu_relax(); } diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index 67fd2fd2620a..fa1fd8a0c867 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -394,10 +394,10 @@ void ppc_enable_pmcs(void) ppc_set_pmu_inuse(1); /* Only need to enable them once */ - if (__get_cpu_var(pmcs_enabled)) + if (__this_cpu_read(pmcs_enabled)) return; - __get_cpu_var(pmcs_enabled) = 1; + __this_cpu_write(pmcs_enabled, 1); if (ppc_md.enable_pmcs) ppc_md.enable_pmcs(); diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 7505599c2593..fa7c4f12104f 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -458,9 +458,9 @@ static inline void clear_irq_work_pending(void) DEFINE_PER_CPU(u8, irq_work_pending); -#define set_irq_work_pending_flag() __get_cpu_var(irq_work_pending) = 1 -#define test_irq_work_pending() __get_cpu_var(irq_work_pending) -#define clear_irq_work_pending() __get_cpu_var(irq_work_pending) = 0 +#define set_irq_work_pending_flag() __this_cpu_write(irq_work_pending, 1) +#define test_irq_work_pending() __this_cpu_read(irq_work_pending) +#define clear_irq_work_pending() __this_cpu_write(irq_work_pending, 0) #endif /* 32 vs 64 bit */ @@ -482,8 +482,8 @@ void arch_irq_work_raise(void) static void __timer_interrupt(void) { struct pt_regs *regs = get_irq_regs(); - u64 *next_tb = &__get_cpu_var(decrementers_next_tb); - struct clock_event_device *evt = &__get_cpu_var(decrementers); + u64 *next_tb = this_cpu_ptr(&decrementers_next_tb); + struct clock_event_device *evt = this_cpu_ptr(&decrementers); u64 now; trace_timer_interrupt_entry(regs); @@ -498,7 +498,7 @@ static void __timer_interrupt(void) *next_tb = ~(u64)0; if (evt->event_handler) evt->event_handler(evt); - __get_cpu_var(irq_stat).timer_irqs_event++; + __this_cpu_inc(irq_stat.timer_irqs_event); } else { now = *next_tb - now; if (now <= DECREMENTER_MAX) @@ -506,13 +506,13 @@ static void __timer_interrupt(void) /* We may have raced with new irq work */ if (test_irq_work_pending()) set_dec(1); - __get_cpu_var(irq_stat).timer_irqs_others++; + __this_cpu_inc(irq_stat.timer_irqs_others); } #ifdef CONFIG_PPC64 /* collect purr register values often, for accurate calculations */ if (firmware_has_feature(FW_FEATURE_SPLPAR)) { - struct cpu_usage *cu = &__get_cpu_var(cpu_usage_array); + struct cpu_usage *cu = this_cpu_ptr(&cpu_usage_array); cu->current_tb = mfspr(SPRN_PURR); } #endif @@ -527,7 +527,7 @@ static void __timer_interrupt(void) void timer_interrupt(struct pt_regs * regs) { struct pt_regs *old_regs; - u64 *next_tb = &__get_cpu_var(decrementers_next_tb); + u64 *next_tb = this_cpu_ptr(&decrementers_next_tb); /* Ensure a positive value is written to the decrementer, or else * some CPUs will continue to take decrementer exceptions. @@ -813,7 +813,7 @@ static void __init clocksource_init(void) static int decrementer_set_next_event(unsigned long evt, struct clock_event_device *dev) { - __get_cpu_var(decrementers_next_tb) = get_tb_or_rtc() + evt; + __this_cpu_write(decrementers_next_tb, get_tb_or_rtc() + evt); set_dec(evt); /* We may have raced with new irq work */ @@ -833,7 +833,7 @@ static void decrementer_set_mode(enum clock_event_mode mode, /* Interrupt handler for the timer broadcast IPI */ void tick_broadcast_ipi_handler(void) { - u64 *next_tb = &__get_cpu_var(decrementers_next_tb); + u64 *next_tb = this_cpu_ptr(&decrementers_next_tb); *next_tb = get_tb_or_rtc(); __timer_interrupt(); @@ -989,6 +989,7 @@ void GregorianDay(struct rtc_time * tm) tm->tm_wday = day % 7; } +EXPORT_SYMBOL_GPL(GregorianDay); void to_tm(int tim, struct rtc_time * tm) { diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 0dc43f9932cf..e6595b72269b 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -295,7 +295,7 @@ long machine_check_early(struct pt_regs *regs) { long handled = 0; - __get_cpu_var(irq_stat).mce_exceptions++; + __this_cpu_inc(irq_stat.mce_exceptions); if (cur_cpu_spec && cur_cpu_spec->machine_check_early) handled = cur_cpu_spec->machine_check_early(regs); @@ -304,7 +304,7 @@ long machine_check_early(struct pt_regs *regs) long hmi_exception_realmode(struct pt_regs *regs) { - __get_cpu_var(irq_stat).hmi_exceptions++; + __this_cpu_inc(irq_stat.hmi_exceptions); if (ppc_md.hmi_exception_early) ppc_md.hmi_exception_early(regs); @@ -700,7 +700,7 @@ void machine_check_exception(struct pt_regs *regs) enum ctx_state prev_state = exception_enter(); int recover = 0; - __get_cpu_var(irq_stat).mce_exceptions++; + __this_cpu_inc(irq_stat.mce_exceptions); /* See if any machine dependent calls. In theory, we would want * to call the CPU first, and call the ppc_md. one if the CPU @@ -1519,7 +1519,7 @@ void vsx_unavailable_tm(struct pt_regs *regs) void performance_monitor_exception(struct pt_regs *regs) { - __get_cpu_var(irq_stat).pmu_irqs++; + __this_cpu_inc(irq_stat.pmu_irqs); perf_irq(regs); } diff --git a/arch/powerpc/kernel/udbg_16550.c b/arch/powerpc/kernel/udbg_16550.c index 6e7c4923b5ea..411116c38da4 100644 --- a/arch/powerpc/kernel/udbg_16550.c +++ b/arch/powerpc/kernel/udbg_16550.c @@ -69,8 +69,12 @@ static void udbg_uart_putc(char c) static int udbg_uart_getc_poll(void) { - if (!udbg_uart_in || !(udbg_uart_in(UART_LSR) & LSR_DR)) + if (!udbg_uart_in) + return -1; + + if (!(udbg_uart_in(UART_LSR) & LSR_DR)) return udbg_uart_in(UART_RBR); + return -1; } diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index f174351842cf..305eb0d9b768 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -20,7 +20,6 @@ #include <linux/user.h> #include <linux/elf.h> #include <linux/security.h> -#include <linux/bootmem.h> #include <linux/memblock.h> #include <asm/pgtable.h> |