diff options
Diffstat (limited to 'arch/powerpc/kernel')
39 files changed, 1167 insertions, 245 deletions
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 41a283956a29..8d1d94d9c649 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -203,6 +203,15 @@ int main(void) DEFINE(PACA_MC_STACK, offsetof(struct paca_struct, mc_kstack)); DEFINE(PACA_CRIT_STACK, offsetof(struct paca_struct, crit_kstack)); DEFINE(PACA_DBG_STACK, offsetof(struct paca_struct, dbg_kstack)); + DEFINE(PACA_TCD_PTR, offsetof(struct paca_struct, tcd_ptr)); + + DEFINE(TCD_ESEL_NEXT, + offsetof(struct tlb_core_data, esel_next)); + DEFINE(TCD_ESEL_MAX, + offsetof(struct tlb_core_data, esel_max)); + DEFINE(TCD_ESEL_FIRST, + offsetof(struct tlb_core_data, esel_first)); + DEFINE(TCD_LOCK, offsetof(struct tlb_core_data, lock)); #endif /* CONFIG_PPC_BOOK3E */ #ifdef CONFIG_PPC_STD_MMU_64 @@ -580,6 +589,7 @@ int main(void) HSTATE_FIELD(HSTATE_VMHANDLER, vmhandler); HSTATE_FIELD(HSTATE_SCRATCH0, scratch0); HSTATE_FIELD(HSTATE_SCRATCH1, scratch1); + HSTATE_FIELD(HSTATE_SCRATCH2, scratch2); HSTATE_FIELD(HSTATE_IN_GUEST, in_guest); HSTATE_FIELD(HSTATE_RESTORE_HID5, restore_hid5); HSTATE_FIELD(HSTATE_NAPPING, napping); diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c index 654932727873..abfa011344d9 100644 --- a/arch/powerpc/kernel/cacheinfo.c +++ b/arch/powerpc/kernel/cacheinfo.c @@ -12,7 +12,6 @@ #include <linux/cpu.h> #include <linux/cpumask.h> -#include <linux/init.h> #include <linux/kernel.h> #include <linux/kobject.h> #include <linux/list.h> diff --git a/arch/powerpc/kernel/cpu_setup_fsl_booke.S b/arch/powerpc/kernel/cpu_setup_fsl_booke.S index bfb18c7290b7..cc2d8962e090 100644 --- a/arch/powerpc/kernel/cpu_setup_fsl_booke.S +++ b/arch/powerpc/kernel/cpu_setup_fsl_booke.S @@ -53,11 +53,57 @@ _GLOBAL(__e500_dcache_setup) isync blr +/* + * FIXME - we haven't yet done testing to determine a reasonable default + * value for PW20_WAIT_IDLE_BIT. + */ +#define PW20_WAIT_IDLE_BIT 50 /* 1ms, TB frequency is 41.66MHZ */ +_GLOBAL(setup_pw20_idle) + mfspr r3, SPRN_PWRMGTCR0 + + /* Set PW20_WAIT bit, enable pw20 state*/ + ori r3, r3, PWRMGTCR0_PW20_WAIT + li r11, PW20_WAIT_IDLE_BIT + + /* Set Automatic PW20 Core Idle Count */ + rlwimi r3, r11, PWRMGTCR0_PW20_ENT_SHIFT, PWRMGTCR0_PW20_ENT + + mtspr SPRN_PWRMGTCR0, r3 + + blr + +/* + * FIXME - we haven't yet done testing to determine a reasonable default + * value for AV_WAIT_IDLE_BIT. + */ +#define AV_WAIT_IDLE_BIT 50 /* 1ms, TB frequency is 41.66MHZ */ +_GLOBAL(setup_altivec_idle) + mfspr r3, SPRN_PWRMGTCR0 + + /* Enable Altivec Idle */ + oris r3, r3, PWRMGTCR0_AV_IDLE_PD_EN@h + li r11, AV_WAIT_IDLE_BIT + + /* Set Automatic AltiVec Idle Count */ + rlwimi r3, r11, PWRMGTCR0_AV_IDLE_CNT_SHIFT, PWRMGTCR0_AV_IDLE_CNT + + mtspr SPRN_PWRMGTCR0, r3 + + blr + _GLOBAL(__setup_cpu_e6500) mflr r6 #ifdef CONFIG_PPC64 bl .setup_altivec_ivors + /* Touch IVOR42 only if the CPU supports E.HV category */ + mfspr r10,SPRN_MMUCFG + rlwinm. r10,r10,0,MMUCFG_LPIDSIZE + beq 1f + bl .setup_lrat_ivor +1: #endif + bl setup_pw20_idle + bl setup_altivec_idle bl __setup_cpu_e5500 mtlr r6 blr @@ -119,6 +165,14 @@ _GLOBAL(__setup_cpu_e5500) _GLOBAL(__restore_cpu_e6500) mflr r5 bl .setup_altivec_ivors + /* Touch IVOR42 only if the CPU supports E.HV category */ + mfspr r10,SPRN_MMUCFG + rlwinm. r10,r10,0,MMUCFG_LPIDSIZE + beq 1f + bl .setup_lrat_ivor +1: + bl .setup_pw20_idle + bl .setup_altivec_idle bl __restore_cpu_e5500 mtlr r5 blr diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c index fdcd8f551aff..18d7c80ddeb9 100644 --- a/arch/powerpc/kernel/crash.c +++ b/arch/powerpc/kernel/crash.c @@ -17,7 +17,6 @@ #include <linux/export.h> #include <linux/crash_dump.h> #include <linux/delay.h> -#include <linux/init.h> #include <linux/irq.h> #include <linux/types.h> diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index f4b7a227f183..148db72a8c43 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -921,6 +921,13 @@ void eeh_add_device_late(struct pci_dev *dev) eeh_sysfs_remove_device(edev->pdev); edev->mode &= ~EEH_DEV_SYSFS; + /* + * We definitely should have the PCI device removed + * though it wasn't correctly. So we needn't call + * into error handler afterwards. + */ + edev->mode |= EEH_DEV_NO_HANDLER; + edev->pdev = NULL; dev->dev.archdata.edev = NULL; } @@ -1023,6 +1030,14 @@ void eeh_remove_device(struct pci_dev *dev) else edev->mode |= EEH_DEV_DISCONNECTED; + /* + * We're removing from the PCI subsystem, that means + * the PCI device driver can't support EEH or not + * well. So we rely on hotplug completely to do recovery + * for the specific PCI device. + */ + edev->mode |= EEH_DEV_NO_HANDLER; + eeh_addr_cache_rmv_dev(dev); eeh_sysfs_remove_device(dev); edev->mode &= ~EEH_DEV_SYSFS; diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 4ef59c33777f..7bb30dca4e19 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -217,7 +217,8 @@ static void *eeh_report_mmio_enabled(void *data, void *userdata) if (!driver) return NULL; if (!driver->err_handler || - !driver->err_handler->mmio_enabled) { + !driver->err_handler->mmio_enabled || + (edev->mode & EEH_DEV_NO_HANDLER)) { eeh_pcid_put(dev); return NULL; } @@ -258,7 +259,8 @@ static void *eeh_report_reset(void *data, void *userdata) eeh_enable_irq(dev); if (!driver->err_handler || - !driver->err_handler->slot_reset) { + !driver->err_handler->slot_reset || + (edev->mode & EEH_DEV_NO_HANDLER)) { eeh_pcid_put(dev); return NULL; } @@ -297,7 +299,9 @@ static void *eeh_report_resume(void *data, void *userdata) eeh_enable_irq(dev); if (!driver->err_handler || - !driver->err_handler->resume) { + !driver->err_handler->resume || + (edev->mode & EEH_DEV_NO_HANDLER)) { + edev->mode &= ~EEH_DEV_NO_HANDLER; eeh_pcid_put(dev); return NULL; } @@ -369,7 +373,9 @@ static void *eeh_rmv_device(void *data, void *userdata) edev->mode |= EEH_DEV_DISCONNECTED; (*removed)++; + pci_lock_rescan_remove(); pci_stop_and_remove_bus_device(dev); + pci_unlock_rescan_remove(); return NULL; } @@ -416,10 +422,13 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus) * into pcibios_add_pci_devices(). */ eeh_pe_state_mark(pe, EEH_PE_KEEP); - if (bus) + if (bus) { + pci_lock_rescan_remove(); pcibios_remove_pci_devices(bus); - else if (frozen_bus) + pci_unlock_rescan_remove(); + } else if (frozen_bus) { eeh_pe_dev_traverse(pe, eeh_rmv_device, &removed); + } /* Reset the pci controller. (Asserts RST#; resets config space). * Reconfigure bridges and devices. Don't try to bring the system @@ -429,6 +438,8 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus) if (rc) return rc; + pci_lock_rescan_remove(); + /* Restore PE */ eeh_ops->configure_bridge(pe); eeh_pe_restore_bars(pe); @@ -462,6 +473,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus) pe->tstamp = tstamp; pe->freeze_count = cnt; + pci_unlock_rescan_remove(); return 0; } @@ -618,92 +630,103 @@ perm_error: eeh_pe_dev_traverse(pe, eeh_report_failure, NULL); /* Shut down the device drivers for good. */ - if (frozen_bus) + if (frozen_bus) { + pci_lock_rescan_remove(); pcibios_remove_pci_devices(frozen_bus); + pci_unlock_rescan_remove(); + } } static void eeh_handle_special_event(void) { struct eeh_pe *pe, *phb_pe; struct pci_bus *bus; - struct pci_controller *hose, *tmp; + struct pci_controller *hose; unsigned long flags; - int rc = 0; + int rc; - /* - * The return value from next_error() has been classified as follows. - * It might be good to enumerate them. However, next_error() is only - * supported by PowerNV platform for now. So it would be fine to use - * integer directly: - * - * 4 - Dead IOC 3 - Dead PHB - * 2 - Fenced PHB 1 - Frozen PE - * 0 - No error found - * - */ - rc = eeh_ops->next_error(&pe); - if (rc <= 0) - return; - switch (rc) { - case 4: - /* Mark all PHBs in dead state */ - eeh_serialize_lock(&flags); - list_for_each_entry_safe(hose, tmp, - &hose_list, list_node) { - phb_pe = eeh_phb_pe_get(hose); - if (!phb_pe) continue; - - eeh_pe_state_mark(phb_pe, - EEH_PE_ISOLATED | EEH_PE_PHB_DEAD); + do { + rc = eeh_ops->next_error(&pe); + + switch (rc) { + case EEH_NEXT_ERR_DEAD_IOC: + /* Mark all PHBs in dead state */ + eeh_serialize_lock(&flags); + + /* Purge all events */ + eeh_remove_event(NULL); + + list_for_each_entry(hose, &hose_list, list_node) { + phb_pe = eeh_phb_pe_get(hose); + if (!phb_pe) continue; + + eeh_pe_state_mark(phb_pe, + EEH_PE_ISOLATED | EEH_PE_PHB_DEAD); + } + + eeh_serialize_unlock(flags); + + break; + case EEH_NEXT_ERR_FROZEN_PE: + case EEH_NEXT_ERR_FENCED_PHB: + case EEH_NEXT_ERR_DEAD_PHB: + /* Mark the PE in fenced state */ + eeh_serialize_lock(&flags); + + /* Purge all events of the PHB */ + eeh_remove_event(pe); + + if (rc == EEH_NEXT_ERR_DEAD_PHB) + eeh_pe_state_mark(pe, + EEH_PE_ISOLATED | EEH_PE_PHB_DEAD); + else + eeh_pe_state_mark(pe, + EEH_PE_ISOLATED | EEH_PE_RECOVERING); + + eeh_serialize_unlock(flags); + + break; + case EEH_NEXT_ERR_NONE: + return; + default: + pr_warn("%s: Invalid value %d from next_error()\n", + __func__, rc); + return; } - eeh_serialize_unlock(flags); - - /* Purge all events */ - eeh_remove_event(NULL); - break; - case 3: - case 2: - case 1: - /* Mark the PE in fenced state */ - eeh_serialize_lock(&flags); - if (rc == 3) - eeh_pe_state_mark(pe, - EEH_PE_ISOLATED | EEH_PE_PHB_DEAD); - else - eeh_pe_state_mark(pe, - EEH_PE_ISOLATED | EEH_PE_RECOVERING); - eeh_serialize_unlock(flags); - - /* Purge all events of the PHB */ - eeh_remove_event(pe); - break; - default: - pr_err("%s: Invalid value %d from next_error()\n", - __func__, rc); - return; - } - /* - * For fenced PHB and frozen PE, it's handled as normal - * event. We have to remove the affected PHBs for dead - * PHB and IOC - */ - if (rc == 2 || rc == 1) - eeh_handle_normal_event(pe); - else { - list_for_each_entry_safe(hose, tmp, - &hose_list, list_node) { - phb_pe = eeh_phb_pe_get(hose); - if (!phb_pe || !(phb_pe->state & EEH_PE_PHB_DEAD)) - continue; - - bus = eeh_pe_bus_get(phb_pe); - /* Notify all devices that they're about to go down. */ - eeh_pe_dev_traverse(pe, eeh_report_failure, NULL); - pcibios_remove_pci_devices(bus); + /* + * For fenced PHB and frozen PE, it's handled as normal + * event. We have to remove the affected PHBs for dead + * PHB and IOC + */ + if (rc == EEH_NEXT_ERR_FROZEN_PE || + rc == EEH_NEXT_ERR_FENCED_PHB) { + eeh_handle_normal_event(pe); + } else { + pci_lock_rescan_remove(); + list_for_each_entry(hose, &hose_list, list_node) { + phb_pe = eeh_phb_pe_get(hose); + if (!phb_pe || + !(phb_pe->state & EEH_PE_PHB_DEAD)) + continue; + + /* Notify all devices to be down */ + bus = eeh_pe_bus_get(phb_pe); + eeh_pe_dev_traverse(pe, + eeh_report_failure, NULL); + pcibios_remove_pci_devices(bus); + } + pci_unlock_rescan_remove(); } - } + + /* + * If we have detected dead IOC, we needn't proceed + * any more since all PHBs would have been removed + */ + if (rc == EEH_NEXT_ERR_DEAD_IOC) + break; + } while (rc != EEH_NEXT_ERR_NONE); } /** diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index f9450537e335..f0c353fa655a 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -25,7 +25,6 @@ #include <linux/delay.h> #include <linux/export.h> #include <linux/gfp.h> -#include <linux/init.h> #include <linux/kernel.h> #include <linux/pci.h> #include <linux/string.h> @@ -737,6 +736,9 @@ static void *eeh_restore_one_device_bars(void *data, void *flag) else eeh_restore_device_bars(edev, dn); + if (eeh_ops->restore_config) + eeh_ops->restore_config(dn); + return NULL; } diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 770d6d65c47b..662c6dd98072 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -184,11 +184,6 @@ syscall_exit: bl .do_show_syscall_exit ld r3,RESULT(r1) #endif -#ifdef CONFIG_PPC_BOOK3S_64 -BEGIN_FTR_SECTION - bl .machine_check_process_queued_event -END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) -#endif CURRENT_THREAD_INFO(r12, r1) ld r8,_MSR(r1) @@ -669,8 +664,16 @@ _GLOBAL(ret_from_except_lite) bl .restore_interrupts SCHEDULE_USER b .ret_from_except_lite - -2: bl .save_nvgprs +2: +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + andi. r0,r4,_TIF_USER_WORK_MASK & ~_TIF_RESTORE_TM + bne 3f /* only restore TM if nothing else to do */ + addi r3,r1,STACK_FRAME_OVERHEAD + bl .restore_tm_state + b restore +3: +#endif + bl .save_nvgprs bl .restore_interrupts addi r3,r1,STACK_FRAME_OVERHEAD bl .do_notify_resume diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index e7751561fd1d..063b65dd4f27 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -308,6 +308,7 @@ interrupt_base_book3e: /* fake trap */ EXCEPTION_STUB(0x2e0, guest_doorbell_crit) EXCEPTION_STUB(0x300, hypercall) EXCEPTION_STUB(0x320, ehpriv) + EXCEPTION_STUB(0x340, lrat_error) .globl interrupt_end_book3e interrupt_end_book3e: @@ -677,6 +678,17 @@ kernel_dbg_exc: bl .unknown_exception b .ret_from_except +/* LRAT Error interrupt */ + START_EXCEPTION(lrat_error); + NORMAL_EXCEPTION_PROLOG(0x340, BOOKE_INTERRUPT_LRAT_ERROR, + PROLOG_ADDITION_NONE) + EXCEPTION_COMMON(0x340, PACA_EXGEN, INTS_KEEP) + addi r3,r1,STACK_FRAME_OVERHEAD + bl .save_nvgprs + INTS_RESTORE_HARD + bl .unknown_exception + b .ret_from_except + /* * An interrupt came in while soft-disabled; We mark paca->irq_happened * accordingly and if the interrupt is level sensitive, we hard disable @@ -859,6 +871,7 @@ BAD_STACK_TRAMPOLINE(0x2e0) BAD_STACK_TRAMPOLINE(0x300) BAD_STACK_TRAMPOLINE(0x310) BAD_STACK_TRAMPOLINE(0x320) +BAD_STACK_TRAMPOLINE(0x340) BAD_STACK_TRAMPOLINE(0x400) BAD_STACK_TRAMPOLINE(0x500) BAD_STACK_TRAMPOLINE(0x600) @@ -1055,12 +1068,9 @@ skpinv: addi r6,r6,1 /* Increment */ mtspr SPRN_MAS0,r3 tlbre mfspr r6,SPRN_MAS1 - rlwinm r6,r6,0,2,0 /* clear IPROT */ + rlwinm r6,r6,0,2,31 /* clear IPROT and VALID */ mtspr SPRN_MAS1,r6 tlbwe - - /* Invalidate TLB1 */ - PPC_TLBILX_ALL(0,R0) sync isync @@ -1114,12 +1124,9 @@ skpinv: addi r6,r6,1 /* Increment */ mtspr SPRN_MAS0,r4 tlbre mfspr r5,SPRN_MAS1 - rlwinm r5,r5,0,2,0 /* clear IPROT */ + rlwinm r5,r5,0,2,31 /* clear IPROT and VALID */ mtspr SPRN_MAS1,r5 tlbwe - - /* Invalidate TLB1 */ - PPC_TLBILX_ALL(0,R0) sync isync @@ -1414,3 +1421,7 @@ _GLOBAL(setup_ehv_ivors) SET_IVOR(38, 0x2c0) /* Guest Processor Doorbell */ SET_IVOR(39, 0x2e0) /* Guest Processor Doorbell Crit/MC */ blr + +_GLOBAL(setup_lrat_ivor) + SET_IVOR(42, 0x340) /* LRAT Error */ + blr diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S index f7f5b8bed68f..9ad236e5d2c9 100644 --- a/arch/powerpc/kernel/fpu.S +++ b/arch/powerpc/kernel/fpu.S @@ -81,6 +81,22 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX) #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ /* + * Enable use of the FPU, and VSX if possible, for the caller. + */ +_GLOBAL(fp_enable) + mfmsr r3 + ori r3,r3,MSR_FP +#ifdef CONFIG_VSX +BEGIN_FTR_SECTION + oris r3,r3,MSR_VSX@h +END_FTR_SECTION_IFSET(CPU_FTR_VSX) +#endif + SYNC + MTMSRD(r3) + isync /* (not necessary for arch 2.02 and later) */ + blr + +/* * Load state from memory into FP registers including FPSCR. * Assumes the caller has enabled FP in the MSR. */ diff --git a/arch/powerpc/kernel/fsl_booke_entry_mapping.S b/arch/powerpc/kernel/fsl_booke_entry_mapping.S index a92c79be2728..f22e7e44fbf3 100644 --- a/arch/powerpc/kernel/fsl_booke_entry_mapping.S +++ b/arch/powerpc/kernel/fsl_booke_entry_mapping.S @@ -176,6 +176,8 @@ skpinv: addi r6,r6,1 /* Increment */ /* 7. Jump to KERNELBASE mapping */ lis r6,(KERNELBASE & ~0xfff)@h ori r6,r6,(KERNELBASE & ~0xfff)@l + rlwinm r7,r25,0,0x03ffffff + add r6,r7,r6 #elif defined(ENTRY_MAPPING_KEXEC_SETUP) /* diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 4f0946de2d5c..b7363bd42452 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -23,6 +23,7 @@ */ #include <linux/threads.h> +#include <linux/init.h> #include <asm/reg.h> #include <asm/page.h> #include <asm/mmu.h> diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S index f45726a1d963..b497188a94a1 100644 --- a/arch/powerpc/kernel/head_fsl_booke.S +++ b/arch/powerpc/kernel/head_fsl_booke.S @@ -65,29 +65,78 @@ _ENTRY(_start); nop /* Translate device tree address to physical, save in r30/r31 */ - mfmsr r16 - mfspr r17,SPRN_PID - rlwinm r17,r17,16,0x3fff0000 /* turn PID into MAS6[SPID] */ - rlwimi r17,r16,28,0x00000001 /* turn MSR[DS] into MAS6[SAS] */ - mtspr SPRN_MAS6,r17 - - tlbsx 0,r3 /* must succeed */ - - mfspr r16,SPRN_MAS1 - mfspr r20,SPRN_MAS3 - rlwinm r17,r16,25,0x1f /* r17 = log2(page size) */ - li r18,1024 - slw r18,r18,r17 /* r18 = page size */ - addi r18,r18,-1 - and r19,r3,r18 /* r19 = page offset */ - andc r31,r20,r18 /* r31 = page base */ - or r31,r31,r19 /* r31 = devtree phys addr */ - mfspr r30,SPRN_MAS7 + bl get_phys_addr + mr r30,r3 + mr r31,r4 li r25,0 /* phys kernel start (low) */ li r24,0 /* CPU number */ li r23,0 /* phys kernel start (high) */ +#ifdef CONFIG_RELOCATABLE + LOAD_REG_ADDR_PIC(r3, _stext) /* Get our current runtime base */ + + /* Translate _stext address to physical, save in r23/r25 */ + bl get_phys_addr + mr r23,r3 + mr r25,r4 + + bl 0f +0: mflr r8 + addis r3,r8,(is_second_reloc - 0b)@ha + lwz r19,(is_second_reloc - 0b)@l(r3) + + /* Check if this is the second relocation. */ + cmpwi r19,1 + bne 1f + + /* + * For the second relocation, we already get the real memstart_addr + * from device tree. So we will map PAGE_OFFSET to memstart_addr, + * then the virtual address of start kernel should be: + * PAGE_OFFSET + (kernstart_addr - memstart_addr) + * Since the offset between kernstart_addr and memstart_addr should + * never be beyond 1G, so we can just use the lower 32bit of them + * for the calculation. + */ + lis r3,PAGE_OFFSET@h + + addis r4,r8,(kernstart_addr - 0b)@ha + addi r4,r4,(kernstart_addr - 0b)@l + lwz r5,4(r4) + + addis r6,r8,(memstart_addr - 0b)@ha + addi r6,r6,(memstart_addr - 0b)@l + lwz r7,4(r6) + + subf r5,r7,r5 + add r3,r3,r5 + b 2f + +1: + /* + * We have the runtime (virutal) address of our base. + * We calculate our shift of offset from a 64M page. + * We could map the 64M page we belong to at PAGE_OFFSET and + * get going from there. + */ + lis r4,KERNELBASE@h + ori r4,r4,KERNELBASE@l + rlwinm r6,r25,0,0x3ffffff /* r6 = PHYS_START % 64M */ + rlwinm r5,r4,0,0x3ffffff /* r5 = KERNELBASE % 64M */ + subf r3,r5,r6 /* r3 = r6 - r5 */ + add r3,r4,r3 /* Required Virtual Address */ + +2: bl relocate + + /* + * For the second relocation, we already set the right tlb entries + * for the kernel space, so skip the code in fsl_booke_entry_mapping.S + */ + cmpwi r19,1 + beq set_ivor +#endif + /* We try to not make any assumptions about how the boot loader * setup or used the TLBs. We invalidate all mappings from the * boot loader and load a single entry in TLB1[0] to map the @@ -113,6 +162,7 @@ _ENTRY(__early_start) #include "fsl_booke_entry_mapping.S" #undef ENTRY_MAPPING_BOOT_SETUP +set_ivor: /* Establish the interrupt vector offsets */ SET_IVOR(0, CriticalInput); SET_IVOR(1, MachineCheck); @@ -166,8 +216,7 @@ _ENTRY(__early_start) /* Check to see if we're the second processor, and jump * to the secondary_start code if so */ - lis r24, boot_cpuid@h - ori r24, r24, boot_cpuid@l + LOAD_REG_ADDR_PIC(r24, boot_cpuid) lwz r24, 0(r24) cmpwi r24, -1 mfspr r24,SPRN_PIR @@ -197,6 +246,18 @@ _ENTRY(__early_start) bl early_init +#ifdef CONFIG_RELOCATABLE + mr r3,r30 + mr r4,r31 +#ifdef CONFIG_PHYS_64BIT + mr r5,r23 + mr r6,r25 +#else + mr r5,r25 +#endif + bl relocate_init +#endif + #ifdef CONFIG_DYNAMIC_MEMSTART lis r3,kernstart_addr@ha la r3,kernstart_addr@l(r3) @@ -856,6 +917,33 @@ KernelSPE: #endif /* CONFIG_SPE */ /* + * Translate the effec addr in r3 to phys addr. The phys addr will be put + * into r3(higher 32bit) and r4(lower 32bit) + */ +get_phys_addr: + mfmsr r8 + mfspr r9,SPRN_PID + rlwinm r9,r9,16,0x3fff0000 /* turn PID into MAS6[SPID] */ + rlwimi r9,r8,28,0x00000001 /* turn MSR[DS] into MAS6[SAS] */ + mtspr SPRN_MAS6,r9 + + tlbsx 0,r3 /* must succeed */ + + mfspr r8,SPRN_MAS1 + mfspr r12,SPRN_MAS3 + rlwinm r9,r8,25,0x1f /* r9 = log2(page size) */ + li r10,1024 + slw r10,r10,r9 /* r10 = page size */ + addi r10,r10,-1 + and r11,r3,r10 /* r11 = page offset */ + andc r4,r12,r10 /* r4 = page base */ + or r4,r4,r11 /* r4 = devtree phys addr */ +#ifdef CONFIG_PHYS_64BIT + mfspr r3,SPRN_MAS7 +#endif + blr + +/* * Global functions */ @@ -1057,24 +1145,36 @@ _GLOBAL(__flush_disable_L1) /* When we get here, r24 needs to hold the CPU # */ .globl __secondary_start __secondary_start: - lis r3,__secondary_hold_acknowledge@h - ori r3,r3,__secondary_hold_acknowledge@l - stw r24,0(r3) - - li r3,0 - mr r4,r24 /* Why? */ - bl call_setup_cpu - - lis r3,tlbcam_index@ha - lwz r3,tlbcam_index@l(r3) + LOAD_REG_ADDR_PIC(r3, tlbcam_index) + lwz r3,0(r3) mtctr r3 li r26,0 /* r26 safe? */ + bl switch_to_as1 + mr r27,r3 /* tlb entry */ /* Load each CAM entry */ 1: mr r3,r26 bl loadcam_entry addi r26,r26,1 bdnz 1b + mr r3,r27 /* tlb entry */ + LOAD_REG_ADDR_PIC(r4, memstart_addr) + lwz r4,0(r4) + mr r5,r25 /* phys kernel start */ + rlwinm r5,r5,0,~0x3ffffff /* aligned 64M */ + subf r4,r5,r4 /* memstart_addr - phys kernel start */ + li r5,0 /* no device tree */ + li r6,0 /* not boot cpu */ + bl restore_to_as0 + + + lis r3,__secondary_hold_acknowledge@h + ori r3,r3,__secondary_hold_acknowledge@l + stw r24,0(r3) + + li r3,0 + mr r4,r24 /* Why? */ + bl call_setup_cpu /* get current_thread_info and current */ lis r1,secondary_ti@ha @@ -1111,6 +1211,112 @@ __secondary_hold_acknowledge: #endif /* + * Create a tlb entry with the same effective and physical address as + * the tlb entry used by the current running code. But set the TS to 1. + * Then switch to the address space 1. It will return with the r3 set to + * the ESEL of the new created tlb. + */ +_GLOBAL(switch_to_as1) + mflr r5 + + /* Find a entry not used */ + mfspr r3,SPRN_TLB1CFG + andi. r3,r3,0xfff + mfspr r4,SPRN_PID + rlwinm r4,r4,16,0x3fff0000 /* turn PID into MAS6[SPID] */ + mtspr SPRN_MAS6,r4 +1: lis r4,0x1000 /* Set MAS0(TLBSEL) = 1 */ + addi r3,r3,-1 + rlwimi r4,r3,16,4,15 /* Setup MAS0 = TLBSEL | ESEL(r3) */ + mtspr SPRN_MAS0,r4 + tlbre + mfspr r4,SPRN_MAS1 + andis. r4,r4,MAS1_VALID@h + bne 1b + + /* Get the tlb entry used by the current running code */ + bl 0f +0: mflr r4 + tlbsx 0,r4 + + mfspr r4,SPRN_MAS1 + ori r4,r4,MAS1_TS /* Set the TS = 1 */ + mtspr SPRN_MAS1,r4 + + mfspr r4,SPRN_MAS0 + rlwinm r4,r4,0,~MAS0_ESEL_MASK + rlwimi r4,r3,16,4,15 /* Setup MAS0 = TLBSEL | ESEL(r3) */ + mtspr SPRN_MAS0,r4 + tlbwe + isync + sync + + mfmsr r4 + ori r4,r4,MSR_IS | MSR_DS + mtspr SPRN_SRR0,r5 + mtspr SPRN_SRR1,r4 + sync + rfi + +/* + * Restore to the address space 0 and also invalidate the tlb entry created + * by switch_to_as1. + * r3 - the tlb entry which should be invalidated + * r4 - __pa(PAGE_OFFSET in AS1) - __pa(PAGE_OFFSET in AS0) + * r5 - device tree virtual address. If r4 is 0, r5 is ignored. + * r6 - boot cpu +*/ +_GLOBAL(restore_to_as0) + mflr r0 + + bl 0f +0: mflr r9 + addi r9,r9,1f - 0b + + /* + * We may map the PAGE_OFFSET in AS0 to a different physical address, + * so we need calculate the right jump and device tree address based + * on the offset passed by r4. + */ + add r9,r9,r4 + add r5,r5,r4 + add r0,r0,r4 + +2: mfmsr r7 + li r8,(MSR_IS | MSR_DS) + andc r7,r7,r8 + + mtspr SPRN_SRR0,r9 + mtspr SPRN_SRR1,r7 + sync + rfi + + /* Invalidate the temporary tlb entry for AS1 */ +1: lis r9,0x1000 /* Set MAS0(TLBSEL) = 1 */ + rlwimi r9,r3,16,4,15 /* Setup MAS0 = TLBSEL | ESEL(r3) */ + mtspr SPRN_MAS0,r9 + tlbre + mfspr r9,SPRN_MAS1 + rlwinm r9,r9,0,2,31 /* Clear MAS1 Valid and IPPROT */ + mtspr SPRN_MAS1,r9 + tlbwe + isync + + cmpwi r4,0 + cmpwi cr1,r6,0 + cror eq,4*cr1+eq,eq + bne 3f /* offset != 0 && is_boot_cpu */ + mtlr r0 + blr + + /* + * The PAGE_OFFSET will map to a different physical address, + * jump to _start to do another relocation again. + */ +3: mr r3,r5 + bl _start + +/* * We put a few things here that have to be page-aligned. This stuff * goes at the beginning of the data segment, which is page-aligned. */ diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index f0b47d1a6b0e..b0a1792279bb 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -28,7 +28,6 @@ #include <linux/percpu.h> #include <linux/kernel.h> #include <linux/sched.h> -#include <linux/init.h> #include <linux/smp.h> #include <asm/hw_breakpoint.h> diff --git a/arch/powerpc/kernel/iomap.c b/arch/powerpc/kernel/iomap.c index 97a3715ac8bd..b82227e7e21b 100644 --- a/arch/powerpc/kernel/iomap.c +++ b/arch/powerpc/kernel/iomap.c @@ -3,7 +3,6 @@ * * (C) Copyright 2004 Linus Torvalds */ -#include <linux/init.h> #include <linux/pci.h> #include <linux/mm.h> #include <linux/export.h> diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index f58d8135aab2..d773dd440a45 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -1144,6 +1144,17 @@ EXPORT_SYMBOL_GPL(iommu_add_device); void iommu_del_device(struct device *dev) { + /* + * Some devices might not have IOMMU table and group + * and we needn't detach them from the associated + * IOMMU groups + */ + if (!dev->iommu_group) { + pr_debug("iommu_tce: skipping device %s with no tbl\n", + dev_name(dev)); + return; + } + iommu_group_remove_device(dev); } EXPORT_SYMBOL_GPL(iommu_del_device); diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c index 83e89d310734..8504657379f1 100644 --- a/arch/powerpc/kernel/kgdb.c +++ b/arch/powerpc/kernel/kgdb.c @@ -15,7 +15,6 @@ */ #include <linux/kernel.h> -#include <linux/init.h> #include <linux/kgdb.h> #include <linux/smp.h> #include <linux/signal.h> diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c index c0c52ec1fca7..cadef7e64e42 100644 --- a/arch/powerpc/kernel/mce.c +++ b/arch/powerpc/kernel/mce.c @@ -26,6 +26,7 @@ #include <linux/ptrace.h> #include <linux/percpu.h> #include <linux/export.h> +#include <linux/irq_work.h> #include <asm/mce.h> static DEFINE_PER_CPU(int, mce_nest_count); @@ -35,6 +36,11 @@ static DEFINE_PER_CPU(struct machine_check_event[MAX_MC_EVT], mce_event); static DEFINE_PER_CPU(int, mce_queue_count); static DEFINE_PER_CPU(struct machine_check_event[MAX_MC_EVT], mce_event_queue); +static void machine_check_process_queued_event(struct irq_work *work); +struct irq_work mce_event_process_work = { + .func = machine_check_process_queued_event, +}; + static void mce_set_error_info(struct machine_check_event *mce, struct mce_error_info *mce_err) { @@ -185,17 +191,19 @@ void machine_check_queue_event(void) return; } __get_cpu_var(mce_event_queue[index]) = evt; + + /* Queue irq work to process this event later. */ + irq_work_queue(&mce_event_process_work); } /* * process pending MCE event from the mce event queue. This function will be * called during syscall exit. */ -void machine_check_process_queued_event(void) +static void machine_check_process_queued_event(struct irq_work *work) { int index; - preempt_disable(); /* * For now just print it to console. * TODO: log this error event to FSP or nvram. @@ -206,7 +214,6 @@ void machine_check_process_queued_event(void) &__get_cpu_var(mce_event_queue[index])); __get_cpu_var(mce_queue_count)--; } - preempt_enable(); } void machine_check_print_event_info(struct machine_check_event *evt) diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index 623c356fe34f..bf0aada02fe4 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -160,6 +160,11 @@ void __init initialise_paca(struct paca_struct *new_paca, int cpu) #ifdef CONFIG_PPC_STD_MMU_64 new_paca->slb_shadow_ptr = init_slb_shadow(cpu); #endif /* CONFIG_PPC_STD_MMU_64 */ + +#ifdef CONFIG_PPC_BOOK3E + /* For now -- if we have threads this will be adjusted later */ + new_paca->tcd_ptr = &new_paca->tcd; +#endif } /* Put the paca pointer into r13 and SPRG_PACA */ diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index a1e3e40ca3fd..d9476c1fc959 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -835,7 +835,7 @@ static void pcibios_fixup_resources(struct pci_dev *dev) * at 0 as unset as well, except if PCI_PROBE_ONLY is also set * since in that case, we don't want to re-assign anything */ - pcibios_resource_to_bus(dev, ®, res); + pcibios_resource_to_bus(dev->bus, ®, res); if (pci_has_flag(PCI_REASSIGN_ALL_RSRC) || (reg.start == 0 && !pci_has_flag(PCI_PROBE_ONLY))) { /* Only print message if not re-assigning */ @@ -886,7 +886,7 @@ static int pcibios_uninitialized_bridge_resource(struct pci_bus *bus, /* Job is a bit different between memory and IO */ if (res->flags & IORESOURCE_MEM) { - pcibios_resource_to_bus(dev, ®ion, res); + pcibios_resource_to_bus(dev->bus, ®ion, res); /* If the BAR is non-0 then it's probably been initialized */ if (region.start != 0) diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c index ac0b034f9ae0..83c26d829991 100644 --- a/arch/powerpc/kernel/pci_of_scan.c +++ b/arch/powerpc/kernel/pci_of_scan.c @@ -111,7 +111,7 @@ static void of_pci_parse_addrs(struct device_node *node, struct pci_dev *dev) res->name = pci_name(dev); region.start = base; region.end = base + size - 1; - pcibios_bus_to_resource(dev, res, ®ion); + pcibios_bus_to_resource(dev->bus, res, ®ion); } } @@ -280,7 +280,7 @@ void of_scan_pci_bridge(struct pci_dev *dev) res->flags = flags; region.start = of_read_number(&ranges[1], 2); region.end = region.start + size - 1; - pcibios_bus_to_resource(dev, res, ®ion); + pcibios_bus_to_resource(dev->bus, res, ®ion); } sprintf(bus->name, "PCI Bus %04x:%02x", pci_domain_nr(bus), bus->number); diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 3386d8ab7eb0..64b7a6e61dd1 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -25,7 +25,6 @@ #include <linux/slab.h> #include <linux/user.h> #include <linux/elf.h> -#include <linux/init.h> #include <linux/prctl.h> #include <linux/init_task.h> #include <linux/export.h> @@ -74,6 +73,48 @@ struct task_struct *last_task_used_vsx = NULL; struct task_struct *last_task_used_spe = NULL; #endif +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM +void giveup_fpu_maybe_transactional(struct task_struct *tsk) +{ + /* + * If we are saving the current thread's registers, and the + * thread is in a transactional state, set the TIF_RESTORE_TM + * bit so that we know to restore the registers before + * returning to userspace. + */ + if (tsk == current && tsk->thread.regs && + MSR_TM_ACTIVE(tsk->thread.regs->msr) && + !test_thread_flag(TIF_RESTORE_TM)) { + tsk->thread.tm_orig_msr = tsk->thread.regs->msr; + set_thread_flag(TIF_RESTORE_TM); + } + + giveup_fpu(tsk); +} + +void giveup_altivec_maybe_transactional(struct task_struct *tsk) +{ + /* + * If we are saving the current thread's registers, and the + * thread is in a transactional state, set the TIF_RESTORE_TM + * bit so that we know to restore the registers before + * returning to userspace. + */ + if (tsk == current && tsk->thread.regs && + MSR_TM_ACTIVE(tsk->thread.regs->msr) && + !test_thread_flag(TIF_RESTORE_TM)) { + tsk->thread.tm_orig_msr = tsk->thread.regs->msr; + set_thread_flag(TIF_RESTORE_TM); + } + + giveup_altivec(tsk); +} + +#else +#define giveup_fpu_maybe_transactional(tsk) giveup_fpu(tsk) +#define giveup_altivec_maybe_transactional(tsk) giveup_altivec(tsk) +#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ + #ifdef CONFIG_PPC_FPU /* * Make sure the floating-point register state in the @@ -102,13 +143,13 @@ void flush_fp_to_thread(struct task_struct *tsk) */ BUG_ON(tsk != current); #endif - giveup_fpu(tsk); + giveup_fpu_maybe_transactional(tsk); } preempt_enable(); } } EXPORT_SYMBOL_GPL(flush_fp_to_thread); -#endif +#endif /* CONFIG_PPC_FPU */ void enable_kernel_fp(void) { @@ -116,11 +157,11 @@ void enable_kernel_fp(void) #ifdef CONFIG_SMP if (current->thread.regs && (current->thread.regs->msr & MSR_FP)) - giveup_fpu(current); + giveup_fpu_maybe_transactional(current); else giveup_fpu(NULL); /* just enables FP for kernel */ #else - giveup_fpu(last_task_used_math); + giveup_fpu_maybe_transactional(last_task_used_math); #endif /* CONFIG_SMP */ } EXPORT_SYMBOL(enable_kernel_fp); @@ -132,11 +173,11 @@ void enable_kernel_altivec(void) #ifdef CONFIG_SMP if (current->thread.regs && (current->thread.regs->msr & MSR_VEC)) - giveup_altivec(current); + giveup_altivec_maybe_transactional(current); else giveup_altivec_notask(); #else - giveup_altivec(last_task_used_altivec); + giveup_altivec_maybe_transactional(last_task_used_altivec); #endif /* CONFIG_SMP */ } EXPORT_SYMBOL(enable_kernel_altivec); @@ -153,7 +194,7 @@ void flush_altivec_to_thread(struct task_struct *tsk) #ifdef CONFIG_SMP BUG_ON(tsk != current); #endif - giveup_altivec(tsk); + giveup_altivec_maybe_transactional(tsk); } preempt_enable(); } @@ -182,8 +223,8 @@ EXPORT_SYMBOL(enable_kernel_vsx); void giveup_vsx(struct task_struct *tsk) { - giveup_fpu(tsk); - giveup_altivec(tsk); + giveup_fpu_maybe_transactional(tsk); + giveup_altivec_maybe_transactional(tsk); __giveup_vsx(tsk); } @@ -339,7 +380,7 @@ static void set_debug_reg_defaults(struct thread_struct *thread) #endif } -static void prime_debug_regs(struct thread_struct *thread) +static void prime_debug_regs(struct debug_reg *debug) { /* * We could have inherited MSR_DE from userspace, since @@ -348,22 +389,22 @@ static void prime_debug_regs(struct thread_struct *thread) */ mtmsr(mfmsr() & ~MSR_DE); - mtspr(SPRN_IAC1, thread->debug.iac1); - mtspr(SPRN_IAC2, thread->debug.iac2); + mtspr(SPRN_IAC1, debug->iac1); + mtspr(SPRN_IAC2, debug->iac2); #if CONFIG_PPC_ADV_DEBUG_IACS > 2 - mtspr(SPRN_IAC3, thread->debug.iac3); - mtspr(SPRN_IAC4, thread->debug.iac4); + mtspr(SPRN_IAC3, debug->iac3); + mtspr(SPRN_IAC4, debug->iac4); #endif - mtspr(SPRN_DAC1, thread->debug.dac1); - mtspr(SPRN_DAC2, thread->debug.dac2); + mtspr(SPRN_DAC1, debug->dac1); + mtspr(SPRN_DAC2, debug->dac2); #if CONFIG_PPC_ADV_DEBUG_DVCS > 0 - mtspr(SPRN_DVC1, thread->debug.dvc1); - mtspr(SPRN_DVC2, thread->debug.dvc2); + mtspr(SPRN_DVC1, debug->dvc1); + mtspr(SPRN_DVC2, debug->dvc2); #endif - mtspr(SPRN_DBCR0, thread->debug.dbcr0); - mtspr(SPRN_DBCR1, thread->debug.dbcr1); + mtspr(SPRN_DBCR0, debug->dbcr0); + mtspr(SPRN_DBCR1, debug->dbcr1); #ifdef CONFIG_BOOKE - mtspr(SPRN_DBCR2, thread->debug.dbcr2); + mtspr(SPRN_DBCR2, debug->dbcr2); #endif } /* @@ -371,11 +412,11 @@ static void prime_debug_regs(struct thread_struct *thread) * debug registers, set the debug registers from the values * stored in the new thread. */ -void switch_booke_debug_regs(struct thread_struct *new_thread) +void switch_booke_debug_regs(struct debug_reg *new_debug) { if ((current->thread.debug.dbcr0 & DBCR0_IDM) - || (new_thread->debug.dbcr0 & DBCR0_IDM)) - prime_debug_regs(new_thread); + || (new_debug->dbcr0 & DBCR0_IDM)) + prime_debug_regs(new_debug); } EXPORT_SYMBOL_GPL(switch_booke_debug_regs); #else /* !CONFIG_PPC_ADV_DEBUG_REGS */ @@ -479,7 +520,48 @@ static inline bool hw_brk_match(struct arch_hw_breakpoint *a, return false; return true; } + #ifdef CONFIG_PPC_TRANSACTIONAL_MEM +static void tm_reclaim_thread(struct thread_struct *thr, + struct thread_info *ti, uint8_t cause) +{ + unsigned long msr_diff = 0; + + /* + * If FP/VSX registers have been already saved to the + * thread_struct, move them to the transact_fp array. + * We clear the TIF_RESTORE_TM bit since after the reclaim + * the thread will no longer be transactional. + */ + if (test_ti_thread_flag(ti, TIF_RESTORE_TM)) { + msr_diff = thr->tm_orig_msr & ~thr->regs->msr; + if (msr_diff & MSR_FP) + memcpy(&thr->transact_fp, &thr->fp_state, + sizeof(struct thread_fp_state)); + if (msr_diff & MSR_VEC) + memcpy(&thr->transact_vr, &thr->vr_state, + sizeof(struct thread_vr_state)); + clear_ti_thread_flag(ti, TIF_RESTORE_TM); + msr_diff &= MSR_FP | MSR_VEC | MSR_VSX | MSR_FE0 | MSR_FE1; + } + + tm_reclaim(thr, thr->regs->msr, cause); + + /* Having done the reclaim, we now have the checkpointed + * FP/VSX values in the registers. These might be valid + * even if we have previously called enable_kernel_fp() or + * flush_fp_to_thread(), so update thr->regs->msr to + * indicate their current validity. + */ + thr->regs->msr |= msr_diff; +} + +void tm_reclaim_current(uint8_t cause) +{ + tm_enable(); + tm_reclaim_thread(¤t->thread, current_thread_info(), cause); +} + static inline void tm_reclaim_task(struct task_struct *tsk) { /* We have to work out if we're switching from/to a task that's in the @@ -502,9 +584,11 @@ static inline void tm_reclaim_task(struct task_struct *tsk) /* Stash the original thread MSR, as giveup_fpu et al will * modify it. We hold onto it to see whether the task used - * FP & vector regs. + * FP & vector regs. If the TIF_RESTORE_TM flag is set, + * tm_orig_msr is already set. */ - thr->tm_orig_msr = thr->regs->msr; + if (!test_ti_thread_flag(task_thread_info(tsk), TIF_RESTORE_TM)) + thr->tm_orig_msr = thr->regs->msr; TM_DEBUG("--- tm_reclaim on pid %d (NIP=%lx, " "ccr=%lx, msr=%lx, trap=%lx)\n", @@ -512,7 +596,7 @@ static inline void tm_reclaim_task(struct task_struct *tsk) thr->regs->ccr, thr->regs->msr, thr->regs->trap); - tm_reclaim(thr, thr->regs->msr, TM_CAUSE_RESCHED); + tm_reclaim_thread(thr, task_thread_info(tsk), TM_CAUSE_RESCHED); TM_DEBUG("--- tm_reclaim on pid %d complete\n", tsk->pid); @@ -588,6 +672,43 @@ static inline void __switch_to_tm(struct task_struct *prev) tm_reclaim_task(prev); } } + +/* + * This is called if we are on the way out to userspace and the + * TIF_RESTORE_TM flag is set. It checks if we need to reload + * FP and/or vector state and does so if necessary. + * If userspace is inside a transaction (whether active or + * suspended) and FP/VMX/VSX instructions have ever been enabled + * inside that transaction, then we have to keep them enabled + * and keep the FP/VMX/VSX state loaded while ever the transaction + * continues. The reason is that if we didn't, and subsequently + * got a FP/VMX/VSX unavailable interrupt inside a transaction, + * we don't know whether it's the same transaction, and thus we + * don't know which of the checkpointed state and the transactional + * state to use. + */ +void restore_tm_state(struct pt_regs *regs) +{ + unsigned long msr_diff; + + clear_thread_flag(TIF_RESTORE_TM); + if (!MSR_TM_ACTIVE(regs->msr)) + return; + + msr_diff = current->thread.tm_orig_msr & ~regs->msr; + msr_diff &= MSR_FP | MSR_VEC | MSR_VSX; + if (msr_diff & MSR_FP) { + fp_enable(); + load_fp_state(¤t->thread.fp_state); + regs->msr |= current->thread.fpexc_mode; + } + if (msr_diff & MSR_VEC) { + vec_enable(); + load_vr_state(¤t->thread.vr_state); + } + regs->msr |= msr_diff; +} + #else #define tm_recheckpoint_new_task(new) #define __switch_to_tm(prev) @@ -683,7 +804,7 @@ struct task_struct *__switch_to(struct task_struct *prev, #endif /* CONFIG_SMP */ #ifdef CONFIG_PPC_ADV_DEBUG_REGS - switch_booke_debug_regs(&new->thread); + switch_booke_debug_regs(&new->thread.debug); #else /* * For PPC_BOOK3S_64, we use the hw-breakpoint interfaces that would @@ -1175,6 +1296,19 @@ int set_fpexc_mode(struct task_struct *tsk, unsigned int val) if (val & PR_FP_EXC_SW_ENABLE) { #ifdef CONFIG_SPE if (cpu_has_feature(CPU_FTR_SPE)) { + /* + * When the sticky exception bits are set + * directly by userspace, it must call prctl + * with PR_GET_FPEXC (with PR_FP_EXC_SW_ENABLE + * in the existing prctl settings) or + * PR_SET_FPEXC (with PR_FP_EXC_SW_ENABLE in + * the bits being set). <fenv.h> functions + * saving and restoring the whole + * floating-point environment need to do so + * anyway to restore the prctl settings from + * the saved environment. + */ + tsk->thread.spefscr_last = mfspr(SPRN_SPEFSCR); tsk->thread.fpexc_mode = val & (PR_FP_EXC_SW_ENABLE | PR_FP_ALL_EXCEPT); return 0; @@ -1206,9 +1340,22 @@ int get_fpexc_mode(struct task_struct *tsk, unsigned long adr) if (tsk->thread.fpexc_mode & PR_FP_EXC_SW_ENABLE) #ifdef CONFIG_SPE - if (cpu_has_feature(CPU_FTR_SPE)) + if (cpu_has_feature(CPU_FTR_SPE)) { + /* + * When the sticky exception bits are set + * directly by userspace, it must call prctl + * with PR_GET_FPEXC (with PR_FP_EXC_SW_ENABLE + * in the existing prctl settings) or + * PR_SET_FPEXC (with PR_FP_EXC_SW_ENABLE in + * the bits being set). <fenv.h> functions + * saving and restoring the whole + * floating-point environment need to do so + * anyway to restore the prctl settings from + * the saved environment. + */ + tsk->thread.spefscr_last = mfspr(SPRN_SPEFSCR); val = tsk->thread.fpexc_mode; - else + } else return -EINVAL; #else return -EINVAL; diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index fa0ad8aafbcc..f58c0d3aaeb4 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -523,6 +523,20 @@ static int __init early_init_dt_scan_memory_ppc(unsigned long node, return early_init_dt_scan_memory(node, uname, depth, data); } +/* + * For a relocatable kernel, we need to get the memstart_addr first, + * then use it to calculate the virtual kernel start address. This has + * to happen at a very early stage (before machine_init). In this case, + * we just want to get the memstart_address and would not like to mess the + * memblock at this stage. So introduce a variable to skip the memblock_add() + * for this reason. + */ +#ifdef CONFIG_RELOCATABLE +static int add_mem_to_memblock = 1; +#else +#define add_mem_to_memblock 1 +#endif + void __init early_init_dt_add_memory_arch(u64 base, u64 size) { #ifdef CONFIG_PPC64 @@ -543,7 +557,8 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size) } /* Add the chunk to the MEMBLOCK list */ - memblock_add(base, size); + if (add_mem_to_memblock) + memblock_add(base, size); } static void __init early_reserve_mem_dt(void) @@ -740,6 +755,30 @@ void __init early_init_devtree(void *params) DBG(" <- early_init_devtree()\n"); } +#ifdef CONFIG_RELOCATABLE +/* + * This function run before early_init_devtree, so we have to init + * initial_boot_params. + */ +void __init early_get_first_memblock_info(void *params, phys_addr_t *size) +{ + /* Setup flat device-tree pointer */ + initial_boot_params = params; + + /* + * Scan the memory nodes and set add_mem_to_memblock to 0 to avoid + * mess the memblock. + */ + add_mem_to_memblock = 0; + of_scan_flat_dt(early_init_dt_scan_root, NULL); + of_scan_flat_dt(early_init_dt_scan_memory_ppc, NULL); + add_mem_to_memblock = 1; + + if (size) + *size = first_memblock_size; +} +#endif + /******* * * New implementation of the OF "find" APIs, return a refcounted diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index cb64a6e1dc51..078145acf7fb 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -1986,19 +1986,23 @@ static void __init prom_init_stdout(void) /* Get the full OF pathname of the stdout device */ memset(path, 0, 256); call_prom("instance-to-path", 3, 1, prom.stdout, path, 255); - stdout_node = call_prom("instance-to-package", 1, 1, prom.stdout); - val = cpu_to_be32(stdout_node); - prom_setprop(prom.chosen, "/chosen", "linux,stdout-package", - &val, sizeof(val)); prom_printf("OF stdout device is: %s\n", of_stdout_device); prom_setprop(prom.chosen, "/chosen", "linux,stdout-path", path, strlen(path) + 1); - /* If it's a display, note it */ - memset(type, 0, sizeof(type)); - prom_getprop(stdout_node, "device_type", type, sizeof(type)); - if (strcmp(type, "display") == 0) - prom_setprop(stdout_node, path, "linux,boot-display", NULL, 0); + /* instance-to-package fails on PA-Semi */ + stdout_node = call_prom("instance-to-package", 1, 1, prom.stdout); + if (stdout_node != PROM_ERROR) { + val = cpu_to_be32(stdout_node); + prom_setprop(prom.chosen, "/chosen", "linux,stdout-package", + &val, sizeof(val)); + + /* If it's a display, note it */ + memset(type, 0, sizeof(type)); + prom_getprop(stdout_node, "device_type", type, sizeof(type)); + if (strcmp(type, "display") == 0) + prom_setprop(stdout_node, path, "linux,boot-display", NULL, 0); + } } static int __init prom_find_machine_type(void) diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index b903dc5cf944..2b0da27eaee4 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -296,9 +296,6 @@ void __init setup_arch(char **cmdline_p) if (cpu_has_feature(CPU_FTR_UNIFIED_ID_CACHE)) ucache_bsize = icache_bsize = dcache_bsize; - /* reboot on panic */ - panic_timeout = 180; - if (ppc_md.panic) setup_panic(); diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 2232aff66059..f5f11a7d30e5 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -97,6 +97,36 @@ int dcache_bsize; int icache_bsize; int ucache_bsize; +#if defined(CONFIG_PPC_BOOK3E) && defined(CONFIG_SMP) +static void setup_tlb_core_data(void) +{ + int cpu; + + for_each_possible_cpu(cpu) { + int first = cpu_first_thread_sibling(cpu); + + paca[cpu].tcd_ptr = &paca[first].tcd; + + /* + * If we have threads, we need either tlbsrx. + * or e6500 tablewalk mode, or else TLB handlers + * will be racy and could produce duplicate entries. + */ + if (smt_enabled_at_boot >= 2 && + !mmu_has_feature(MMU_FTR_USE_TLBRSRV) && + book3e_htw_mode != PPC_HTW_E6500) { + /* Should we panic instead? */ + WARN_ONCE("%s: unsupported MMU configuration -- expect problems\n", + __func__); + } + } +} +#else +static void setup_tlb_core_data(void) +{ +} +#endif + #ifdef CONFIG_SMP static char *smt_enabled_cmdline; @@ -445,6 +475,7 @@ void __init setup_system(void) smp_setup_cpu_maps(); check_smt_enabled(); + setup_tlb_core_data(); #ifdef CONFIG_SMP /* Release secondary cpus out of their spinloops at 0x60 now that @@ -592,9 +623,6 @@ void __init setup_arch(char **cmdline_p) dcache_bsize = ppc64_caches.dline_size; icache_bsize = ppc64_caches.iline_size; - /* reboot on panic */ - panic_timeout = 180; - if (ppc_md.panic) setup_panic(); diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index 457e97aa2945..8fc4177ed65a 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -203,8 +203,7 @@ unsigned long get_tm_stackpointer(struct pt_regs *regs) #ifdef CONFIG_PPC_TRANSACTIONAL_MEM if (MSR_TM_ACTIVE(regs->msr)) { - tm_enable(); - tm_reclaim(¤t->thread, regs->msr, TM_CAUSE_SIGNAL); + tm_reclaim_current(TM_CAUSE_SIGNAL); if (MSR_TM_TRANSACTIONAL(regs->msr)) return current->thread.ckpt_regs.gpr[1]; } diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 68027bfa5f8e..6ce69e6f1fcb 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -519,6 +519,13 @@ static int save_tm_user_regs(struct pt_regs *regs, { unsigned long msr = regs->msr; + /* Remove TM bits from thread's MSR. The MSR in the sigcontext + * just indicates to userland that we were doing a transaction, but we + * don't want to return in transactional state. This also ensures + * that flush_fp_to_thread won't set TIF_RESTORE_TM again. + */ + regs->msr &= ~MSR_TS_MASK; + /* Make sure floating point registers are stored in regs */ flush_fp_to_thread(current); @@ -1056,13 +1063,6 @@ int handle_rt_signal32(unsigned long sig, struct k_sigaction *ka, /* enter the signal handler in native-endian mode */ regs->msr &= ~MSR_LE; regs->msr |= (MSR_KERNEL & MSR_LE); -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM - /* Remove TM bits from thread's MSR. The MSR in the sigcontext - * just indicates to userland that we were doing a transaction, but we - * don't want to return in transactional state: - */ - regs->msr &= ~MSR_TS_MASK; -#endif return 1; badframe: @@ -1484,13 +1484,6 @@ int handle_signal32(unsigned long sig, struct k_sigaction *ka, regs->nip = (unsigned long) ka->sa.sa_handler; /* enter the signal handler in big-endian mode */ regs->msr &= ~MSR_LE; -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM - /* Remove TM bits from thread's MSR. The MSR in the sigcontext - * just indicates to userland that we were doing a transaction, but we - * don't want to return in transactional state: - */ - regs->msr &= ~MSR_TS_MASK; -#endif return 1; badframe: diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 42991045349f..e35bf773df7a 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -192,6 +192,13 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc, BUG_ON(!MSR_TM_ACTIVE(regs->msr)); + /* Remove TM bits from thread's MSR. The MSR in the sigcontext + * just indicates to userland that we were doing a transaction, but we + * don't want to return in transactional state. This also ensures + * that flush_fp_to_thread won't set TIF_RESTORE_TM again. + */ + regs->msr &= ~MSR_TS_MASK; + flush_fp_to_thread(current); #ifdef CONFIG_ALTIVEC @@ -749,13 +756,6 @@ int handle_rt_signal64(int signr, struct k_sigaction *ka, siginfo_t *info, /* Make sure signal handler doesn't get spurious FP exceptions */ current->thread.fp_state.fpscr = 0; -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM - /* Remove TM bits from thread's MSR. The MSR in the sigcontext - * just indicates to userland that we were doing a transaction, but we - * don't want to return in transactional state: - */ - regs->msr &= ~MSR_TS_MASK; -#endif /* Set up to return from userspace. */ if (vdso64_rt_sigtramp && current->mm->context.vdso_base) { diff --git a/arch/powerpc/kernel/smp-tbsync.c b/arch/powerpc/kernel/smp-tbsync.c index e68fd1ae727a..7a37ecd3afa3 100644 --- a/arch/powerpc/kernel/smp-tbsync.c +++ b/arch/powerpc/kernel/smp-tbsync.c @@ -9,7 +9,6 @@ #include <linux/sched.h> #include <linux/smp.h> #include <linux/unistd.h> -#include <linux/init.h> #include <linux/slab.h> #include <linux/atomic.h> #include <asm/smp.h> diff --git a/arch/powerpc/kernel/swsusp_booke.S b/arch/powerpc/kernel/swsusp_booke.S index 0f204053e5b5..553c1405ee05 100644 --- a/arch/powerpc/kernel/swsusp_booke.S +++ b/arch/powerpc/kernel/swsusp_booke.S @@ -74,21 +74,21 @@ _GLOBAL(swsusp_arch_suspend) bne 1b /* Save SPRGs */ - mfsprg r4,0 + mfspr r4,SPRN_SPRG0 stw r4,SL_SPRG0(r11) - mfsprg r4,1 + mfspr r4,SPRN_SPRG1 stw r4,SL_SPRG1(r11) - mfsprg r4,2 + mfspr r4,SPRN_SPRG2 stw r4,SL_SPRG2(r11) - mfsprg r4,3 + mfspr r4,SPRN_SPRG3 stw r4,SL_SPRG3(r11) - mfsprg r4,4 + mfspr r4,SPRN_SPRG4 stw r4,SL_SPRG4(r11) - mfsprg r4,5 + mfspr r4,SPRN_SPRG5 stw r4,SL_SPRG5(r11) - mfsprg r4,6 + mfspr r4,SPRN_SPRG6 stw r4,SL_SPRG6(r11) - mfsprg r4,7 + mfspr r4,SPRN_SPRG7 stw r4,SL_SPRG7(r11) /* Call the low level suspend stuff (we should probably have made @@ -150,21 +150,21 @@ _GLOBAL(swsusp_arch_resume) bl _tlbil_all lwz r4,SL_SPRG0(r11) - mtsprg 0,r4 + mtspr SPRN_SPRG0,r4 lwz r4,SL_SPRG1(r11) - mtsprg 1,r4 + mtspr SPRN_SPRG1,r4 lwz r4,SL_SPRG2(r11) - mtsprg 2,r4 + mtspr SPRN_SPRG2,r4 lwz r4,SL_SPRG3(r11) - mtsprg 3,r4 + mtspr SPRN_SPRG3,r4 lwz r4,SL_SPRG4(r11) - mtsprg 4,r4 + mtspr SPRN_SPRG4,r4 lwz r4,SL_SPRG5(r11) - mtsprg 5,r4 + mtspr SPRN_SPRG5,r4 lwz r4,SL_SPRG6(r11) - mtsprg 6,r4 + mtspr SPRN_SPRG6,r4 lwz r4,SL_SPRG7(r11) - mtsprg 7,r4 + mtspr SPRN_SPRG7,r4 /* restore the MSR */ lwz r3,SL_MSR(r11) diff --git a/arch/powerpc/kernel/syscalls.c b/arch/powerpc/kernel/syscalls.c index 4e3cc47f26b9..cd9be9aa016d 100644 --- a/arch/powerpc/kernel/syscalls.c +++ b/arch/powerpc/kernel/syscalls.c @@ -34,7 +34,6 @@ #include <linux/ipc.h> #include <linux/utsname.h> #include <linux/file.h> -#include <linux/init.h> #include <linux/personality.h> #include <asm/uaccess.h> diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index cad777eb613a..d4a43e64a6a9 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -86,6 +86,304 @@ __setup("smt-snooze-delay=", setup_smt_snooze_delay); #endif /* CONFIG_PPC64 */ +#ifdef CONFIG_PPC_FSL_BOOK3E +#define MAX_BIT 63 + +static u64 pw20_wt; +static u64 altivec_idle_wt; + +static unsigned int get_idle_ticks_bit(u64 ns) +{ + u64 cycle; + + if (ns >= 10000) + cycle = div_u64(ns + 500, 1000) * tb_ticks_per_usec; + else + cycle = div_u64(ns * tb_ticks_per_usec, 1000); + + if (!cycle) + return 0; + + return ilog2(cycle); +} + +static void do_show_pwrmgtcr0(void *val) +{ + u32 *value = val; + + *value = mfspr(SPRN_PWRMGTCR0); +} + +static ssize_t show_pw20_state(struct device *dev, + struct device_attribute *attr, char *buf) +{ + u32 value; + unsigned int cpu = dev->id; + + smp_call_function_single(cpu, do_show_pwrmgtcr0, &value, 1); + + value &= PWRMGTCR0_PW20_WAIT; + + return sprintf(buf, "%u\n", value ? 1 : 0); +} + +static void do_store_pw20_state(void *val) +{ + u32 *value = val; + u32 pw20_state; + + pw20_state = mfspr(SPRN_PWRMGTCR0); + + if (*value) + pw20_state |= PWRMGTCR0_PW20_WAIT; + else + pw20_state &= ~PWRMGTCR0_PW20_WAIT; + + mtspr(SPRN_PWRMGTCR0, pw20_state); +} + +static ssize_t store_pw20_state(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + u32 value; + unsigned int cpu = dev->id; + + if (kstrtou32(buf, 0, &value)) + return -EINVAL; + + if (value > 1) + return -EINVAL; + + smp_call_function_single(cpu, do_store_pw20_state, &value, 1); + + return count; +} + +static ssize_t show_pw20_wait_time(struct device *dev, + struct device_attribute *attr, char *buf) +{ + u32 value; + u64 tb_cycle = 1; + u64 time; + + unsigned int cpu = dev->id; + + if (!pw20_wt) { + smp_call_function_single(cpu, do_show_pwrmgtcr0, &value, 1); + value = (value & PWRMGTCR0_PW20_ENT) >> + PWRMGTCR0_PW20_ENT_SHIFT; + + tb_cycle = (tb_cycle << (MAX_BIT - value + 1)); + /* convert ms to ns */ + if (tb_ticks_per_usec > 1000) { + time = div_u64(tb_cycle, tb_ticks_per_usec / 1000); + } else { + u32 rem_us; + + time = div_u64_rem(tb_cycle, tb_ticks_per_usec, + &rem_us); + time = time * 1000 + rem_us * 1000 / tb_ticks_per_usec; + } + } else { + time = pw20_wt; + } + + return sprintf(buf, "%llu\n", time > 0 ? time : 0); +} + +static void set_pw20_wait_entry_bit(void *val) +{ + u32 *value = val; + u32 pw20_idle; + + pw20_idle = mfspr(SPRN_PWRMGTCR0); + + /* Set Automatic PW20 Core Idle Count */ + /* clear count */ + pw20_idle &= ~PWRMGTCR0_PW20_ENT; + + /* set count */ + pw20_idle |= ((MAX_BIT - *value) << PWRMGTCR0_PW20_ENT_SHIFT); + + mtspr(SPRN_PWRMGTCR0, pw20_idle); +} + +static ssize_t store_pw20_wait_time(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + u32 entry_bit; + u64 value; + + unsigned int cpu = dev->id; + + if (kstrtou64(buf, 0, &value)) + return -EINVAL; + + if (!value) + return -EINVAL; + + entry_bit = get_idle_ticks_bit(value); + if (entry_bit > MAX_BIT) + return -EINVAL; + + pw20_wt = value; + + smp_call_function_single(cpu, set_pw20_wait_entry_bit, + &entry_bit, 1); + + return count; +} + +static ssize_t show_altivec_idle(struct device *dev, + struct device_attribute *attr, char *buf) +{ + u32 value; + unsigned int cpu = dev->id; + + smp_call_function_single(cpu, do_show_pwrmgtcr0, &value, 1); + + value &= PWRMGTCR0_AV_IDLE_PD_EN; + + return sprintf(buf, "%u\n", value ? 1 : 0); +} + +static void do_store_altivec_idle(void *val) +{ + u32 *value = val; + u32 altivec_idle; + + altivec_idle = mfspr(SPRN_PWRMGTCR0); + + if (*value) + altivec_idle |= PWRMGTCR0_AV_IDLE_PD_EN; + else + altivec_idle &= ~PWRMGTCR0_AV_IDLE_PD_EN; + + mtspr(SPRN_PWRMGTCR0, altivec_idle); +} + +static ssize_t store_altivec_idle(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + u32 value; + unsigned int cpu = dev->id; + + if (kstrtou32(buf, 0, &value)) + return -EINVAL; + + if (value > 1) + return -EINVAL; + + smp_call_function_single(cpu, do_store_altivec_idle, &value, 1); + + return count; +} + +static ssize_t show_altivec_idle_wait_time(struct device *dev, + struct device_attribute *attr, char *buf) +{ + u32 value; + u64 tb_cycle = 1; + u64 time; + + unsigned int cpu = dev->id; + + if (!altivec_idle_wt) { + smp_call_function_single(cpu, do_show_pwrmgtcr0, &value, 1); + value = (value & PWRMGTCR0_AV_IDLE_CNT) >> + PWRMGTCR0_AV_IDLE_CNT_SHIFT; + + tb_cycle = (tb_cycle << (MAX_BIT - value + 1)); + /* convert ms to ns */ + if (tb_ticks_per_usec > 1000) { + time = div_u64(tb_cycle, tb_ticks_per_usec / 1000); + } else { + u32 rem_us; + + time = div_u64_rem(tb_cycle, tb_ticks_per_usec, + &rem_us); + time = time * 1000 + rem_us * 1000 / tb_ticks_per_usec; + } + } else { + time = altivec_idle_wt; + } + + return sprintf(buf, "%llu\n", time > 0 ? time : 0); +} + +static void set_altivec_idle_wait_entry_bit(void *val) +{ + u32 *value = val; + u32 altivec_idle; + + altivec_idle = mfspr(SPRN_PWRMGTCR0); + + /* Set Automatic AltiVec Idle Count */ + /* clear count */ + altivec_idle &= ~PWRMGTCR0_AV_IDLE_CNT; + + /* set count */ + altivec_idle |= ((MAX_BIT - *value) << PWRMGTCR0_AV_IDLE_CNT_SHIFT); + + mtspr(SPRN_PWRMGTCR0, altivec_idle); +} + +static ssize_t store_altivec_idle_wait_time(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + u32 entry_bit; + u64 value; + + unsigned int cpu = dev->id; + + if (kstrtou64(buf, 0, &value)) + return -EINVAL; + + if (!value) + return -EINVAL; + + entry_bit = get_idle_ticks_bit(value); + if (entry_bit > MAX_BIT) + return -EINVAL; + + altivec_idle_wt = value; + + smp_call_function_single(cpu, set_altivec_idle_wait_entry_bit, + &entry_bit, 1); + + return count; +} + +/* + * Enable/Disable interface: + * 0, disable. 1, enable. + */ +static DEVICE_ATTR(pw20_state, 0600, show_pw20_state, store_pw20_state); +static DEVICE_ATTR(altivec_idle, 0600, show_altivec_idle, store_altivec_idle); + +/* + * Set wait time interface:(Nanosecond) + * Example: Base on TBfreq is 41MHZ. + * 1~48(ns): TB[63] + * 49~97(ns): TB[62] + * 98~195(ns): TB[61] + * 196~390(ns): TB[60] + * 391~780(ns): TB[59] + * 781~1560(ns): TB[58] + * ... + */ +static DEVICE_ATTR(pw20_wait_time, 0600, + show_pw20_wait_time, + store_pw20_wait_time); +static DEVICE_ATTR(altivec_idle_wait_time, 0600, + show_altivec_idle_wait_time, + store_altivec_idle_wait_time); +#endif + /* * Enabling PMCs will slow partition context switch times so we only do * it the first time we write to the PMCs. @@ -425,6 +723,15 @@ static void register_cpu_online(unsigned int cpu) device_create_file(s, &dev_attr_pir); #endif /* CONFIG_PPC64 */ +#ifdef CONFIG_PPC_FSL_BOOK3E + if (PVR_VER(cur_cpu_spec->pvr_value) == PVR_VER_E6500) { + device_create_file(s, &dev_attr_pw20_state); + device_create_file(s, &dev_attr_pw20_wait_time); + + device_create_file(s, &dev_attr_altivec_idle); + device_create_file(s, &dev_attr_altivec_idle_wait_time); + } +#endif cacheinfo_cpu_online(cpu); } @@ -497,6 +804,15 @@ static void unregister_cpu_online(unsigned int cpu) device_remove_file(s, &dev_attr_pir); #endif /* CONFIG_PPC64 */ +#ifdef CONFIG_PPC_FSL_BOOK3E + if (PVR_VER(cur_cpu_spec->pvr_value) == PVR_VER_E6500) { + device_remove_file(s, &dev_attr_pw20_state); + device_remove_file(s, &dev_attr_pw20_wait_time); + + device_remove_file(s, &dev_attr_altivec_idle); + device_remove_file(s, &dev_attr_altivec_idle_wait_time); + } +#endif cacheinfo_cpu_offline(cpu); } diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index afb1b56ef4fa..b3dab20acf34 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -536,6 +536,9 @@ void timer_interrupt(struct pt_regs * regs) now = *next_tb - now; if (now <= DECREMENTER_MAX) set_dec((int)now); + /* We may have raced with new irq work */ + if (test_irq_work_pending()) + set_dec(1); __get_cpu_var(irq_stat).timer_irqs_others++; } @@ -802,8 +805,16 @@ static void __init clocksource_init(void) static int decrementer_set_next_event(unsigned long evt, struct clock_event_device *dev) { + /* Don't adjust the decrementer if some irq work is pending */ + if (test_irq_work_pending()) + return 0; __get_cpu_var(decrementers_next_tb) = get_tb_or_rtc() + evt; set_dec(evt); + + /* We may have raced with new irq work */ + if (test_irq_work_pending()) + set_dec(1); + return 0; } diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 330841766b09..33cd7a0b8e73 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -1399,7 +1399,6 @@ void fp_unavailable_tm(struct pt_regs *regs) TM_DEBUG("FP Unavailable trap whilst transactional at 0x%lx, MSR=%lx\n", regs->nip, regs->msr); - tm_enable(); /* We can only have got here if the task started using FP after * beginning the transaction. So, the transactional regs are just a @@ -1408,8 +1407,7 @@ void fp_unavailable_tm(struct pt_regs *regs) * transaction, and probably retry but now with FP enabled. So the * checkpointed FP registers need to be loaded. */ - tm_reclaim(¤t->thread, current->thread.regs->msr, - TM_CAUSE_FAC_UNAV); + tm_reclaim_current(TM_CAUSE_FAC_UNAV); /* Reclaim didn't save out any FPRs to transact_fprs. */ /* Enable FP for the task: */ @@ -1418,11 +1416,19 @@ void fp_unavailable_tm(struct pt_regs *regs) /* This loads and recheckpoints the FP registers from * thread.fpr[]. They will remain in registers after the * checkpoint so we don't need to reload them after. + * If VMX is in use, the VRs now hold checkpointed values, + * so we don't want to load the VRs from the thread_struct. */ - tm_recheckpoint(¤t->thread, regs->msr); + tm_recheckpoint(¤t->thread, MSR_FP); + + /* If VMX is in use, get the transactional values back */ + if (regs->msr & MSR_VEC) { + do_load_up_transact_altivec(¤t->thread); + /* At this point all the VSX state is loaded, so enable it */ + regs->msr |= MSR_VSX; + } } -#ifdef CONFIG_ALTIVEC void altivec_unavailable_tm(struct pt_regs *regs) { /* See the comments in fp_unavailable_tm(). This function operates @@ -1432,18 +1438,21 @@ void altivec_unavailable_tm(struct pt_regs *regs) TM_DEBUG("Vector Unavailable trap whilst transactional at 0x%lx," "MSR=%lx\n", regs->nip, regs->msr); - tm_enable(); - tm_reclaim(¤t->thread, current->thread.regs->msr, - TM_CAUSE_FAC_UNAV); + tm_reclaim_current(TM_CAUSE_FAC_UNAV); regs->msr |= MSR_VEC; - tm_recheckpoint(¤t->thread, regs->msr); + tm_recheckpoint(¤t->thread, MSR_VEC); current->thread.used_vr = 1; + + if (regs->msr & MSR_FP) { + do_load_up_transact_fpu(¤t->thread); + regs->msr |= MSR_VSX; + } } -#endif -#ifdef CONFIG_VSX void vsx_unavailable_tm(struct pt_regs *regs) { + unsigned long orig_msr = regs->msr; + /* See the comments in fp_unavailable_tm(). This works similarly, * though we're loading both FP and VEC registers in here. * @@ -1455,18 +1464,30 @@ void vsx_unavailable_tm(struct pt_regs *regs) "MSR=%lx\n", regs->nip, regs->msr); - tm_enable(); + current->thread.used_vsr = 1; + + /* If FP and VMX are already loaded, we have all the state we need */ + if ((orig_msr & (MSR_FP | MSR_VEC)) == (MSR_FP | MSR_VEC)) { + regs->msr |= MSR_VSX; + return; + } + /* This reclaims FP and/or VR regs if they're already enabled */ - tm_reclaim(¤t->thread, current->thread.regs->msr, - TM_CAUSE_FAC_UNAV); + tm_reclaim_current(TM_CAUSE_FAC_UNAV); regs->msr |= MSR_VEC | MSR_FP | current->thread.fpexc_mode | MSR_VSX; - /* This loads & recheckpoints FP and VRs. */ - tm_recheckpoint(¤t->thread, regs->msr); - current->thread.used_vsr = 1; + + /* This loads & recheckpoints FP and VRs; but we have + * to be sure not to overwrite previously-valid state. + */ + tm_recheckpoint(¤t->thread, regs->msr & ~orig_msr); + + if (orig_msr & MSR_FP) + do_load_up_transact_fpu(¤t->thread); + if (orig_msr & MSR_VEC) + do_load_up_transact_altivec(¤t->thread); } -#endif #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ void performance_monitor_exception(struct pt_regs *regs) diff --git a/arch/powerpc/kernel/uprobes.c b/arch/powerpc/kernel/uprobes.c index 59f419b935f2..003b20964ea0 100644 --- a/arch/powerpc/kernel/uprobes.c +++ b/arch/powerpc/kernel/uprobes.c @@ -186,7 +186,7 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) * emulate_step() returns 1 if the insn was successfully emulated. * For all other cases, we need to single-step in hardware. */ - ret = emulate_step(regs, auprobe->ainsn); + ret = emulate_step(regs, auprobe->insn); if (ret > 0) return true; diff --git a/arch/powerpc/kernel/vdso32/vdso32_wrapper.S b/arch/powerpc/kernel/vdso32/vdso32_wrapper.S index 6e8f507ed32b..79683d0393f5 100644 --- a/arch/powerpc/kernel/vdso32/vdso32_wrapper.S +++ b/arch/powerpc/kernel/vdso32/vdso32_wrapper.S @@ -1,4 +1,3 @@ -#include <linux/init.h> #include <linux/linkage.h> #include <asm/page.h> diff --git a/arch/powerpc/kernel/vdso64/vdso64_wrapper.S b/arch/powerpc/kernel/vdso64/vdso64_wrapper.S index b8553d62b792..8df9e2463007 100644 --- a/arch/powerpc/kernel/vdso64/vdso64_wrapper.S +++ b/arch/powerpc/kernel/vdso64/vdso64_wrapper.S @@ -1,4 +1,3 @@ -#include <linux/init.h> #include <linux/linkage.h> #include <asm/page.h> diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S index 0458a9aaba9d..74f8050518d6 100644 --- a/arch/powerpc/kernel/vector.S +++ b/arch/powerpc/kernel/vector.S @@ -37,6 +37,16 @@ _GLOBAL(do_load_up_transact_altivec) #endif /* + * Enable use of VMX/Altivec for the caller. + */ +_GLOBAL(vec_enable) + mfmsr r3 + oris r3,r3,MSR_VEC@h + MTMSRD(r3) + isync + blr + +/* * Load state from memory into VMX registers including VSCR. * Assumes the caller has enabled VMX in the MSR. */ |