diff options
Diffstat (limited to 'arch/powerpc/kernel')
46 files changed, 2197 insertions, 391 deletions
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 445cb6e39d5..904d713366f 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -39,6 +39,7 @@ obj-$(CONFIG_PPC64) += setup_64.o sys_ppc32.o \ obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_ppc970.o cpu_setup_pa6t.o obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_power.o +obj-$(CONFIG_PPC_BOOK3S_64) += mce.o mce_power.o obj64-$(CONFIG_RELOCATABLE) += reloc_64.o obj-$(CONFIG_PPC_BOOK3E_64) += exceptions-64e.o idle_book3e.o obj-$(CONFIG_PPC_A2) += cpu_setup_a2.o diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index d3de01066f7..8d1d94d9c64 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 @@ -232,6 +241,10 @@ int main(void) DEFINE(PACA_DTL_RIDX, offsetof(struct paca_struct, dtl_ridx)); #endif /* CONFIG_PPC_STD_MMU_64 */ DEFINE(PACAEMERGSP, offsetof(struct paca_struct, emergency_sp)); +#ifdef CONFIG_PPC_BOOK3S_64 + DEFINE(PACAMCEMERGSP, offsetof(struct paca_struct, mc_emergency_sp)); + DEFINE(PACA_IN_MCE, offsetof(struct paca_struct, in_mce)); +#endif DEFINE(PACAHWCPUID, offsetof(struct paca_struct, hw_cpu_id)); DEFINE(PACAKEXECSTATE, offsetof(struct paca_struct, kexec_state)); DEFINE(PACA_STARTTIME, offsetof(struct paca_struct, starttime)); diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c index 65493272787..abfa011344d 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 bfb18c7290b..cc2d8962e09 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/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S index 18b5b9cf8e3..37d1bb002aa 100644 --- a/arch/powerpc/kernel/cpu_setup_power.S +++ b/arch/powerpc/kernel/cpu_setup_power.S @@ -29,7 +29,7 @@ _GLOBAL(__setup_cpu_power7) mtspr SPRN_LPID,r0 mfspr r3,SPRN_LPCR bl __init_LPCR - bl __init_TLB + bl __init_tlb_power7 mtlr r11 blr @@ -42,7 +42,7 @@ _GLOBAL(__restore_cpu_power7) mtspr SPRN_LPID,r0 mfspr r3,SPRN_LPCR bl __init_LPCR - bl __init_TLB + bl __init_tlb_power7 mtlr r11 blr @@ -59,7 +59,7 @@ _GLOBAL(__setup_cpu_power8) oris r3, r3, LPCR_AIL_3@h bl __init_LPCR bl __init_HFSCR - bl __init_TLB + bl __init_tlb_power8 bl __init_PMU_HV mtlr r11 blr @@ -78,7 +78,7 @@ _GLOBAL(__restore_cpu_power8) oris r3, r3, LPCR_AIL_3@h bl __init_LPCR bl __init_HFSCR - bl __init_TLB + bl __init_tlb_power8 bl __init_PMU_HV mtlr r11 blr @@ -134,15 +134,31 @@ __init_HFSCR: mtspr SPRN_HFSCR,r3 blr -__init_TLB: - /* - * Clear the TLB using the "IS 3" form of tlbiel instruction - * (invalidate by congruence class). P7 has 128 CCs, P8 has 512 - * so we just always do 512 - */ +/* + * Clear the TLB using the specified IS form of tlbiel instruction + * (invalidate by congruence class). P7 has 128 CCs., P8 has 512. + * + * r3 = IS field + */ +__init_tlb_power7: + li r3,0xc00 /* IS field = 0b11 */ +_GLOBAL(__flush_tlb_power7) + li r6,128 + mtctr r6 + mr r7,r3 /* IS field */ + ptesync +2: tlbiel r7 + addi r7,r7,0x1000 + bdnz 2b + ptesync +1: blr + +__init_tlb_power8: + li r3,0xc00 /* IS field = 0b11 */ +_GLOBAL(__flush_tlb_power8) li r6,512 mtctr r6 - li r7,0xc00 /* IS field = 0b11 */ + mr r7,r3 /* IS field */ ptesync 2: tlbiel r7 addi r7,r7,0x1000 diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 597d954e586..6c8dd5da4de 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -71,6 +71,10 @@ extern void __restore_cpu_power7(void); extern void __setup_cpu_power8(unsigned long offset, struct cpu_spec* spec); extern void __restore_cpu_power8(void); extern void __restore_cpu_a2(void); +extern void __flush_tlb_power7(unsigned long inval_selector); +extern void __flush_tlb_power8(unsigned long inval_selector); +extern long __machine_check_early_realmode_p7(struct pt_regs *regs); +extern long __machine_check_early_realmode_p8(struct pt_regs *regs); #endif /* CONFIG_PPC64 */ #if defined(CONFIG_E500) extern void __setup_cpu_e5500(unsigned long offset, struct cpu_spec* spec); @@ -440,6 +444,8 @@ static struct cpu_spec __initdata cpu_specs[] = { .oprofile_cpu_type = "ppc64/ibm-compat-v1", .cpu_setup = __setup_cpu_power7, .cpu_restore = __restore_cpu_power7, + .flush_tlb = __flush_tlb_power7, + .machine_check_early = __machine_check_early_realmode_p7, .platform = "power7", }, { /* 2.07-compliant processor, i.e. Power8 "architected" mode */ @@ -456,6 +462,8 @@ static struct cpu_spec __initdata cpu_specs[] = { .oprofile_cpu_type = "ppc64/ibm-compat-v1", .cpu_setup = __setup_cpu_power8, .cpu_restore = __restore_cpu_power8, + .flush_tlb = __flush_tlb_power8, + .machine_check_early = __machine_check_early_realmode_p8, .platform = "power8", }, { /* Power7 */ @@ -474,6 +482,8 @@ static struct cpu_spec __initdata cpu_specs[] = { .oprofile_type = PPC_OPROFILE_POWER4, .cpu_setup = __setup_cpu_power7, .cpu_restore = __restore_cpu_power7, + .flush_tlb = __flush_tlb_power7, + .machine_check_early = __machine_check_early_realmode_p7, .platform = "power7", }, { /* Power7+ */ @@ -492,6 +502,8 @@ static struct cpu_spec __initdata cpu_specs[] = { .oprofile_type = PPC_OPROFILE_POWER4, .cpu_setup = __setup_cpu_power7, .cpu_restore = __restore_cpu_power7, + .flush_tlb = __flush_tlb_power7, + .machine_check_early = __machine_check_early_realmode_p7, .platform = "power7+", }, { /* Power8E */ @@ -510,6 +522,8 @@ static struct cpu_spec __initdata cpu_specs[] = { .oprofile_type = PPC_OPROFILE_INVALID, .cpu_setup = __setup_cpu_power8, .cpu_restore = __restore_cpu_power8, + .flush_tlb = __flush_tlb_power8, + .machine_check_early = __machine_check_early_realmode_p8, .platform = "power8", }, { /* Power8 */ @@ -528,6 +542,8 @@ static struct cpu_spec __initdata cpu_specs[] = { .oprofile_type = PPC_OPROFILE_INVALID, .cpu_setup = __setup_cpu_power8, .cpu_restore = __restore_cpu_power8, + .flush_tlb = __flush_tlb_power8, + .machine_check_early = __machine_check_early_realmode_p8, .platform = "power8", }, { /* Cell Broadband Engine */ diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c index fdcd8f551af..18d7c80ddeb 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/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c index e4897523de4..54d0116256f 100644 --- a/arch/powerpc/kernel/dma-iommu.c +++ b/arch/powerpc/kernel/dma-iommu.c @@ -83,10 +83,10 @@ static int dma_iommu_dma_supported(struct device *dev, u64 mask) return 0; } - if (tbl->it_offset > (mask >> IOMMU_PAGE_SHIFT)) { + if (tbl->it_offset > (mask >> tbl->it_page_shift)) { dev_info(dev, "Warning: IOMMU offset too big for device mask\n"); dev_info(dev, "mask: 0x%08llx, table offset: 0x%08lx\n", - mask, tbl->it_offset << IOMMU_PAGE_SHIFT); + mask, tbl->it_offset << tbl->it_page_shift); return 0; } else return 1; diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 4bd687d5e7a..148db72a8c4 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -84,7 +84,7 @@ #define EEH_MAX_FAILS 2100000 /* Time to wait for a PCI slot to report status, in milliseconds */ -#define PCI_BUS_RESET_WAIT_MSEC (60*1000) +#define PCI_BUS_RESET_WAIT_MSEC (5*60*1000) /* Platform dependent EEH operations */ struct eeh_ops *eeh_ops = NULL; @@ -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 c17f90d0f73..7bb30dca4e1 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; } @@ -476,7 +480,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus) /* The longest amount of time to wait for a pci device * to come back on line, in seconds. */ -#define MAX_WAIT_FOR_RECOVERY 150 +#define MAX_WAIT_FOR_RECOVERY 300 static void eeh_handle_normal_event(struct eeh_pe *pe) { @@ -637,86 +641,92 @@ 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 { - pci_lock_rescan_remove(); - 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(); } - 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 f9450537e33..f0c353fa655 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 bbfb0294b35..662c6dd9807 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -664,8 +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 e7751561fd1..063b65dd4f2 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/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 9f905e40922..38d507306a1 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -155,8 +155,30 @@ machine_check_pSeries_1: */ HMT_MEDIUM_PPR_DISCARD SET_SCRATCH0(r13) /* save r13 */ +#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. + */ + 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. let's just stay stuck here */ + bgt cr1,. +9: +END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) +#endif /* CONFIG_PPC_P7_NAP */ EXCEPTION_PROLOG_0(PACA_EXMC) +BEGIN_FTR_SECTION + b machine_check_pSeries_early +FTR_SECTION_ELSE b machine_check_pSeries_0 +ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE) . = 0x300 .globl data_access_pSeries @@ -405,6 +427,64 @@ denorm_exception_hv: .align 7 /* moved from 0x200 */ +machine_check_pSeries_early: +BEGIN_FTR_SECTION + EXCEPTION_PROLOG_1(PACA_EXMC, NOTEST, 0x200) + /* + * Register contents: + * R13 = PACA + * R9 = CR + * Original R9 to R13 is saved on PACA_EXMC + * + * Switch to mc_emergency stack and handle re-entrancy (though we + * currently don't test for overflow). Save MCE registers srr1, + * srr0, dar and dsisr and then set ME=1 + * + * We use paca->in_mce to check whether this is the first entry or + * nested machine check. We increment paca->in_mce to track nested + * machine checks. + * + * If this is the first entry then set stack pointer to + * paca->mc_emergency_sp, otherwise r1 is already pointing to + * stack frame on mc_emergency stack. + * + * NOTE: We are here with MSR_ME=0 (off), which means we risk a + * checkstop if we get another machine check exception before we do + * rfid with MSR_ME=1. + */ + mr r11,r1 /* Save r1 */ + lhz r10,PACA_IN_MCE(r13) + cmpwi r10,0 /* Are we in nested machine check */ + bne 0f /* Yes, we are. */ + /* First machine check entry */ + ld r1,PACAMCEMERGSP(r13) /* Use MC emergency stack */ +0: subi r1,r1,INT_FRAME_SIZE /* alloc stack frame */ + addi r10,r10,1 /* increment paca->in_mce */ + sth r10,PACA_IN_MCE(r13) + std r11,GPR1(r1) /* Save r1 on the stack. */ + std r11,0(r1) /* make stack chain pointer */ + mfspr r11,SPRN_SRR0 /* Save SRR0 */ + std r11,_NIP(r1) + mfspr r11,SPRN_SRR1 /* Save SRR1 */ + std r11,_MSR(r1) + mfspr r11,SPRN_DAR /* Save DAR */ + std r11,_DAR(r1) + mfspr r11,SPRN_DSISR /* Save DSISR */ + std r11,_DSISR(r1) + std r9,_CCR(r1) /* Save CR in stackframe */ + /* Save r9 through r13 from EXMC save area to stack frame. */ + EXCEPTION_PROLOG_COMMON_2(PACA_EXMC) + mfmsr r11 /* get MSR value */ + ori r11,r11,MSR_ME /* turn on ME bit */ + ori r11,r11,MSR_RI /* turn on RI bit */ + ld r12,PACAKBASE(r13) /* get high part of &label */ + LOAD_HANDLER(r12, machine_check_handle_early) + mtspr SPRN_SRR0,r12 + mtspr SPRN_SRR1,r11 + rfid + b . /* prevent speculative execution */ +END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) + machine_check_pSeries: .globl machine_check_fwnmi machine_check_fwnmi: @@ -688,30 +768,6 @@ kvmppc_skip_Hinterrupt: STD_EXCEPTION_COMMON(0x100, system_reset, .system_reset_exception) - /* - * Machine check is different because we use a different - * save area: PACA_EXMC instead of PACA_EXGEN. - */ - .align 7 - .globl machine_check_common -machine_check_common: - - mfspr r10,SPRN_DAR - std r10,PACA_EXGEN+EX_DAR(r13) - mfspr r10,SPRN_DSISR - stw r10,PACA_EXGEN+EX_DSISR(r13) - EXCEPTION_PROLOG_COMMON(0x200, PACA_EXMC) - FINISH_NAP - DISABLE_INTS - ld r3,PACA_EXGEN+EX_DAR(r13) - lwz r4,PACA_EXGEN+EX_DSISR(r13) - std r3,_DAR(r1) - std r4,_DSISR(r1) - bl .save_nvgprs - addi r3,r1,STACK_FRAME_OVERHEAD - bl .machine_check_exception - b .ret_from_except - STD_EXCEPTION_COMMON_ASYNC(0x500, hardware_interrupt, do_IRQ) STD_EXCEPTION_COMMON_ASYNC(0x900, decrementer, .timer_interrupt) STD_EXCEPTION_COMMON(0x980, hdecrementer, .hdec_interrupt) @@ -1080,6 +1136,30 @@ unrecov_user_slb: #endif /* __DISABLED__ */ + /* + * Machine check is different because we use a different + * save area: PACA_EXMC instead of PACA_EXGEN. + */ + .align 7 + .globl machine_check_common +machine_check_common: + + mfspr r10,SPRN_DAR + std r10,PACA_EXGEN+EX_DAR(r13) + mfspr r10,SPRN_DSISR + stw r10,PACA_EXGEN+EX_DSISR(r13) + EXCEPTION_PROLOG_COMMON(0x200, PACA_EXMC) + FINISH_NAP + DISABLE_INTS + ld r3,PACA_EXGEN+EX_DAR(r13) + lwz r4,PACA_EXGEN+EX_DSISR(r13) + std r3,_DAR(r1) + std r4,_DSISR(r1) + bl .save_nvgprs + addi r3,r1,STACK_FRAME_OVERHEAD + bl .machine_check_exception + b .ret_from_except + .align 7 .globl alignment_common alignment_common: @@ -1263,6 +1343,120 @@ _GLOBAL(opal_mc_secondary_handler) #endif /* CONFIG_PPC_POWERNV */ +#define MACHINE_CHECK_HANDLER_WINDUP \ + /* Clear MSR_RI before setting SRR0 and SRR1. */\ + li r0,MSR_RI; \ + mfmsr r9; /* get MSR value */ \ + andc r9,r9,r0; \ + mtmsrd r9,1; /* Clear MSR_RI */ \ + /* Move original SRR0 and SRR1 into the respective regs */ \ + ld r9,_MSR(r1); \ + mtspr SPRN_SRR1,r9; \ + ld r3,_NIP(r1); \ + mtspr SPRN_SRR0,r3; \ + ld r9,_CTR(r1); \ + mtctr r9; \ + ld r9,_XER(r1); \ + mtxer r9; \ + ld r9,_LINK(r1); \ + mtlr r9; \ + REST_GPR(0, r1); \ + REST_8GPRS(2, r1); \ + REST_GPR(10, r1); \ + ld r11,_CCR(r1); \ + mtcr r11; \ + /* Decrement paca->in_mce. */ \ + lhz r12,PACA_IN_MCE(r13); \ + subi r12,r12,1; \ + sth r12,PACA_IN_MCE(r13); \ + REST_GPR(11, r1); \ + REST_2GPRS(12, r1); \ + /* restore original r1. */ \ + ld r1,GPR1(r1) + + /* + * Handle machine check early in real mode. We come here with + * ME=1, MMU (IR=0 and DR=0) off and using MC emergency stack. + */ + .align 7 + .globl machine_check_handle_early +machine_check_handle_early: + std r0,GPR0(r1) /* Save r0 */ + EXCEPTION_PROLOG_COMMON_3(0x200) + bl .save_nvgprs + addi r3,r1,STACK_FRAME_OVERHEAD + bl .machine_check_early + ld r12,_MSR(r1) +#ifdef CONFIG_PPC_P7_NAP + /* + * Check if thread was in power saving mode. We come here when any + * of the following is true: + * a. thread wasn't in power saving mode + * b. thread was in power saving mode with no state loss or + * supervisor state loss + * + * Go back to nap again if (b) is true. + */ + rlwinm. r11,r12,47-31,30,31 /* Was it in power saving mode? */ + beq 4f /* No, it wasn;t */ + /* Thread was in power saving mode. Go back to nap again. */ + cmpwi r11,2 + bne 3f + /* Supervisor state loss */ + li r0,1 + stb r0,PACA_NAPSTATELOST(r13) +3: bl .machine_check_queue_event + MACHINE_CHECK_HANDLER_WINDUP + GET_PACA(r13) + ld r1,PACAR1(r13) + b .power7_enter_nap_mode +4: +#endif + /* + * Check if we are coming from hypervisor userspace. If yes then we + * continue in host kernel in V mode to deliver the MC event. + */ + rldicl. r11,r12,4,63 /* See if MC hit while in HV mode. */ + beq 5f + andi. r11,r12,MSR_PR /* See if coming from user. */ + bne 9f /* continue in V mode if we are. */ + +5: +#ifdef CONFIG_KVM_BOOK3S_64_HV + /* + * We are coming from kernel context. Check if we are coming from + * guest. if yes, then we can continue. We will fall through + * do_kvm_200->kvmppc_interrupt to deliver the MC event to guest. + */ + lbz r11,HSTATE_IN_GUEST(r13) + cmpwi r11,0 /* Check if coming from guest */ + bne 9f /* continue if we are. */ +#endif + /* + * At this point we are not sure about what context we come from. + * Queue up the MCE event and return from the interrupt. + * But before that, check if this is an un-recoverable exception. + * If yes, then stay on emergency stack and panic. + */ + andi. r11,r12,MSR_RI + bne 2f +1: addi r3,r1,STACK_FRAME_OVERHEAD + bl .unrecoverable_exception + b 1b +2: + /* + * Return from MC interrupt. + * Queue up the MCE event so that we can log it later, while + * returning from kernel or opal call. + */ + bl .machine_check_queue_event + MACHINE_CHECK_HANDLER_WINDUP + rfid +9: + /* Deliver the machine check to host kernel in V mode. */ + MACHINE_CHECK_HANDLER_WINDUP + b machine_check_pSeries + /* * r13 points to the PACA, r9 contains the saved CR, * r12 contain the saved SRR1, SRR0 is still ready for return diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S index f7f5b8bed68..9ad236e5d2c 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 a92c79be272..f22e7e44fbf 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 4f0946de2d5..b7363bd4245 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 f45726a1d96..b497188a94a 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 f0b47d1a6b0..b0a1792279b 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/idle_power7.S b/arch/powerpc/kernel/idle_power7.S index 847e40e62fc..3fdef0f0c67 100644 --- a/arch/powerpc/kernel/idle_power7.S +++ b/arch/powerpc/kernel/idle_power7.S @@ -84,6 +84,7 @@ _GLOBAL(power7_nap) std r9,_MSR(r1) std r1,PACAR1(r13) +_GLOBAL(power7_enter_nap_mode) #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE /* Tell KVM we're napping */ li r4,KVM_HWTHREAD_IN_NAP diff --git a/arch/powerpc/kernel/iomap.c b/arch/powerpc/kernel/iomap.c index 97a3715ac8b..b82227e7e21 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 572bb5b95f3..d773dd440a4 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -251,14 +251,13 @@ again: if (dev) boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1, - 1 << IOMMU_PAGE_SHIFT); + 1 << tbl->it_page_shift); else - boundary_size = ALIGN(1UL << 32, 1 << IOMMU_PAGE_SHIFT); + boundary_size = ALIGN(1UL << 32, 1 << tbl->it_page_shift); /* 4GB boundary for iseries_hv_alloc and iseries_hv_map */ - n = iommu_area_alloc(tbl->it_map, limit, start, npages, - tbl->it_offset, boundary_size >> IOMMU_PAGE_SHIFT, - align_mask); + n = iommu_area_alloc(tbl->it_map, limit, start, npages, tbl->it_offset, + boundary_size >> tbl->it_page_shift, align_mask); if (n == -1) { if (likely(pass == 0)) { /* First try the pool from the start */ @@ -320,12 +319,12 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl, return DMA_ERROR_CODE; entry += tbl->it_offset; /* Offset into real TCE table */ - ret = entry << IOMMU_PAGE_SHIFT; /* Set the return dma address */ + ret = entry << tbl->it_page_shift; /* Set the return dma address */ /* Put the TCEs in the HW table */ build_fail = ppc_md.tce_build(tbl, entry, npages, - (unsigned long)page & IOMMU_PAGE_MASK, - direction, attrs); + (unsigned long)page & + IOMMU_PAGE_MASK(tbl), direction, attrs); /* ppc_md.tce_build() only returns non-zero for transient errors. * Clean up the table bitmap in this case and return @@ -352,7 +351,7 @@ static bool iommu_free_check(struct iommu_table *tbl, dma_addr_t dma_addr, { unsigned long entry, free_entry; - entry = dma_addr >> IOMMU_PAGE_SHIFT; + entry = dma_addr >> tbl->it_page_shift; free_entry = entry - tbl->it_offset; if (((free_entry + npages) > tbl->it_size) || @@ -401,7 +400,7 @@ static void __iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr, unsigned long flags; struct iommu_pool *pool; - entry = dma_addr >> IOMMU_PAGE_SHIFT; + entry = dma_addr >> tbl->it_page_shift; free_entry = entry - tbl->it_offset; pool = get_pool(tbl, free_entry); @@ -468,13 +467,13 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl, } /* Allocate iommu entries for that segment */ vaddr = (unsigned long) sg_virt(s); - npages = iommu_num_pages(vaddr, slen, IOMMU_PAGE_SIZE); + npages = iommu_num_pages(vaddr, slen, IOMMU_PAGE_SIZE(tbl)); align = 0; - if (IOMMU_PAGE_SHIFT < PAGE_SHIFT && slen >= PAGE_SIZE && + if (tbl->it_page_shift < PAGE_SHIFT && slen >= PAGE_SIZE && (vaddr & ~PAGE_MASK) == 0) - align = PAGE_SHIFT - IOMMU_PAGE_SHIFT; + align = PAGE_SHIFT - tbl->it_page_shift; entry = iommu_range_alloc(dev, tbl, npages, &handle, - mask >> IOMMU_PAGE_SHIFT, align); + mask >> tbl->it_page_shift, align); DBG(" - vaddr: %lx, size: %lx\n", vaddr, slen); @@ -489,16 +488,16 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl, /* Convert entry to a dma_addr_t */ entry += tbl->it_offset; - dma_addr = entry << IOMMU_PAGE_SHIFT; - dma_addr |= (s->offset & ~IOMMU_PAGE_MASK); + dma_addr = entry << tbl->it_page_shift; + dma_addr |= (s->offset & ~IOMMU_PAGE_MASK(tbl)); DBG(" - %lu pages, entry: %lx, dma_addr: %lx\n", npages, entry, dma_addr); /* Insert into HW table */ build_fail = ppc_md.tce_build(tbl, entry, npages, - vaddr & IOMMU_PAGE_MASK, - direction, attrs); + vaddr & IOMMU_PAGE_MASK(tbl), + direction, attrs); if(unlikely(build_fail)) goto failure; @@ -559,9 +558,9 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl, if (s->dma_length != 0) { unsigned long vaddr, npages; - vaddr = s->dma_address & IOMMU_PAGE_MASK; + vaddr = s->dma_address & IOMMU_PAGE_MASK(tbl); npages = iommu_num_pages(s->dma_address, s->dma_length, - IOMMU_PAGE_SIZE); + IOMMU_PAGE_SIZE(tbl)); __iommu_free(tbl, vaddr, npages); s->dma_address = DMA_ERROR_CODE; s->dma_length = 0; @@ -592,7 +591,7 @@ void iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist, if (sg->dma_length == 0) break; npages = iommu_num_pages(dma_handle, sg->dma_length, - IOMMU_PAGE_SIZE); + IOMMU_PAGE_SIZE(tbl)); __iommu_free(tbl, dma_handle, npages); sg = sg_next(sg); } @@ -676,7 +675,7 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid) set_bit(0, tbl->it_map); /* We only split the IOMMU table if we have 1GB or more of space */ - if ((tbl->it_size << IOMMU_PAGE_SHIFT) >= (1UL * 1024 * 1024 * 1024)) + if ((tbl->it_size << tbl->it_page_shift) >= (1UL * 1024 * 1024 * 1024)) tbl->nr_pools = IOMMU_NR_POOLS; else tbl->nr_pools = 1; @@ -768,16 +767,16 @@ dma_addr_t iommu_map_page(struct device *dev, struct iommu_table *tbl, vaddr = page_address(page) + offset; uaddr = (unsigned long)vaddr; - npages = iommu_num_pages(uaddr, size, IOMMU_PAGE_SIZE); + npages = iommu_num_pages(uaddr, size, IOMMU_PAGE_SIZE(tbl)); if (tbl) { align = 0; - if (IOMMU_PAGE_SHIFT < PAGE_SHIFT && size >= PAGE_SIZE && + if (tbl->it_page_shift < PAGE_SHIFT && size >= PAGE_SIZE && ((unsigned long)vaddr & ~PAGE_MASK) == 0) - align = PAGE_SHIFT - IOMMU_PAGE_SHIFT; + align = PAGE_SHIFT - tbl->it_page_shift; dma_handle = iommu_alloc(dev, tbl, vaddr, npages, direction, - mask >> IOMMU_PAGE_SHIFT, align, + mask >> tbl->it_page_shift, align, attrs); if (dma_handle == DMA_ERROR_CODE) { if (printk_ratelimit()) { @@ -786,7 +785,7 @@ dma_addr_t iommu_map_page(struct device *dev, struct iommu_table *tbl, npages); } } else - dma_handle |= (uaddr & ~IOMMU_PAGE_MASK); + dma_handle |= (uaddr & ~IOMMU_PAGE_MASK(tbl)); } return dma_handle; @@ -801,7 +800,8 @@ void iommu_unmap_page(struct iommu_table *tbl, dma_addr_t dma_handle, BUG_ON(direction == DMA_NONE); if (tbl) { - npages = iommu_num_pages(dma_handle, size, IOMMU_PAGE_SIZE); + npages = iommu_num_pages(dma_handle, size, + IOMMU_PAGE_SIZE(tbl)); iommu_free(tbl, dma_handle, npages); } } @@ -845,10 +845,10 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl, memset(ret, 0, size); /* Set up tces to cover the allocated range */ - nio_pages = size >> IOMMU_PAGE_SHIFT; - io_order = get_iommu_order(size); + nio_pages = size >> tbl->it_page_shift; + io_order = get_iommu_order(size, tbl); mapping = iommu_alloc(dev, tbl, ret, nio_pages, DMA_BIDIRECTIONAL, - mask >> IOMMU_PAGE_SHIFT, io_order, NULL); + mask >> tbl->it_page_shift, io_order, NULL); if (mapping == DMA_ERROR_CODE) { free_pages((unsigned long)ret, order); return NULL; @@ -864,7 +864,7 @@ void iommu_free_coherent(struct iommu_table *tbl, size_t size, unsigned int nio_pages; size = PAGE_ALIGN(size); - nio_pages = size >> IOMMU_PAGE_SHIFT; + nio_pages = size >> tbl->it_page_shift; iommu_free(tbl, dma_handle, nio_pages); size = PAGE_ALIGN(size); free_pages((unsigned long)vaddr, get_order(size)); @@ -935,10 +935,10 @@ int iommu_tce_clear_param_check(struct iommu_table *tbl, if (tce_value) return -EINVAL; - if (ioba & ~IOMMU_PAGE_MASK) + if (ioba & ~IOMMU_PAGE_MASK(tbl)) return -EINVAL; - ioba >>= IOMMU_PAGE_SHIFT; + ioba >>= tbl->it_page_shift; if (ioba < tbl->it_offset) return -EINVAL; @@ -955,13 +955,13 @@ int iommu_tce_put_param_check(struct iommu_table *tbl, if (!(tce & (TCE_PCI_WRITE | TCE_PCI_READ))) return -EINVAL; - if (tce & ~(IOMMU_PAGE_MASK | TCE_PCI_WRITE | TCE_PCI_READ)) + if (tce & ~(IOMMU_PAGE_MASK(tbl) | TCE_PCI_WRITE | TCE_PCI_READ)) return -EINVAL; - if (ioba & ~IOMMU_PAGE_MASK) + if (ioba & ~IOMMU_PAGE_MASK(tbl)) return -EINVAL; - ioba >>= IOMMU_PAGE_SHIFT; + ioba >>= tbl->it_page_shift; if (ioba < tbl->it_offset) return -EINVAL; @@ -1037,7 +1037,7 @@ int iommu_tce_build(struct iommu_table *tbl, unsigned long entry, /* if (unlikely(ret)) pr_err("iommu_tce: %s failed on hwaddr=%lx ioba=%lx kva=%lx ret=%d\n", - __func__, hwaddr, entry << IOMMU_PAGE_SHIFT, + __func__, hwaddr, entry << IOMMU_PAGE_SHIFT(tbl), hwaddr, ret); */ return ret; @@ -1049,14 +1049,14 @@ int iommu_put_tce_user_mode(struct iommu_table *tbl, unsigned long entry, { int ret; struct page *page = NULL; - unsigned long hwaddr, offset = tce & IOMMU_PAGE_MASK & ~PAGE_MASK; + unsigned long hwaddr, offset = tce & IOMMU_PAGE_MASK(tbl) & ~PAGE_MASK; enum dma_data_direction direction = iommu_tce_direction(tce); ret = get_user_pages_fast(tce & PAGE_MASK, 1, direction != DMA_TO_DEVICE, &page); if (unlikely(ret != 1)) { /* pr_err("iommu_tce: get_user_pages_fast failed tce=%lx ioba=%lx ret=%d\n", - tce, entry << IOMMU_PAGE_SHIFT, ret); */ + tce, entry << IOMMU_PAGE_SHIFT(tbl), ret); */ return -EFAULT; } hwaddr = (unsigned long) page_address(page) + offset; @@ -1067,7 +1067,7 @@ int iommu_put_tce_user_mode(struct iommu_table *tbl, unsigned long entry, if (ret < 0) pr_err("iommu_tce: %s failed ioba=%lx, tce=%lx, ret=%d\n", - __func__, entry << IOMMU_PAGE_SHIFT, tce, ret); + __func__, entry << tbl->it_page_shift, tce, ret); return ret; } @@ -1105,7 +1105,7 @@ void iommu_release_ownership(struct iommu_table *tbl) } EXPORT_SYMBOL_GPL(iommu_release_ownership); -static int iommu_add_device(struct device *dev) +int iommu_add_device(struct device *dev) { struct iommu_table *tbl; int ret = 0; @@ -1127,6 +1127,12 @@ static int iommu_add_device(struct device *dev) pr_debug("iommu_tce: adding %s to iommu group %d\n", dev_name(dev), iommu_group_id(tbl->it_group)); + if (PAGE_SIZE < IOMMU_PAGE_SIZE(tbl)) { + pr_err("iommu_tce: unsupported iommu page size."); + pr_err("%s has not been added\n", dev_name(dev)); + return -EINVAL; + } + ret = iommu_group_add_device(tbl->it_group, dev); if (ret < 0) pr_err("iommu_tce: %s has not been added, ret=%d\n", @@ -1134,52 +1140,23 @@ static int iommu_add_device(struct device *dev) return ret; } +EXPORT_SYMBOL_GPL(iommu_add_device); -static void iommu_del_device(struct device *dev) -{ - iommu_group_remove_device(dev); -} - -static int iommu_bus_notifier(struct notifier_block *nb, - unsigned long action, void *data) +void iommu_del_device(struct device *dev) { - struct device *dev = data; - - switch (action) { - case BUS_NOTIFY_ADD_DEVICE: - return iommu_add_device(dev); - case BUS_NOTIFY_DEL_DEVICE: - iommu_del_device(dev); - return 0; - default: - return 0; + /* + * 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; } -} -static struct notifier_block tce_iommu_bus_nb = { - .notifier_call = iommu_bus_notifier, -}; - -static int __init tce_iommu_init(void) -{ - struct pci_dev *pdev = NULL; - - BUILD_BUG_ON(PAGE_SIZE < IOMMU_PAGE_SIZE); - - for_each_pci_dev(pdev) - iommu_add_device(&pdev->dev); - - bus_register_notifier(&pci_bus_type, &tce_iommu_bus_nb); - return 0; -} - -subsys_initcall_sync(tce_iommu_init); - -#else - -void iommu_register_group(struct iommu_table *tbl, - int pci_domain_number, unsigned long pe_num) -{ + iommu_group_remove_device(dev); } +EXPORT_SYMBOL_GPL(iommu_del_device); #endif /* CONFIG_IOMMU_API */ diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index ba016561521..9729b23bfb0 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -354,8 +354,13 @@ int arch_show_interrupts(struct seq_file *p, int prec) seq_printf(p, "%*s: ", prec, "LOC"); for_each_online_cpu(j) - seq_printf(p, "%10u ", per_cpu(irq_stat, j).timer_irqs); - seq_printf(p, " Local timer interrupts\n"); + seq_printf(p, "%10u ", per_cpu(irq_stat, j).timer_irqs_event); + seq_printf(p, " Local timer interrupts for timer event device\n"); + + seq_printf(p, "%*s: ", prec, "LOC"); + for_each_online_cpu(j) + seq_printf(p, "%10u ", per_cpu(irq_stat, j).timer_irqs_others); + seq_printf(p, " Local timer interrupts for others\n"); seq_printf(p, "%*s: ", prec, "SPU"); for_each_online_cpu(j) @@ -389,11 +394,12 @@ int arch_show_interrupts(struct seq_file *p, int prec) */ u64 arch_irq_stat_cpu(unsigned int cpu) { - u64 sum = per_cpu(irq_stat, cpu).timer_irqs; + u64 sum = per_cpu(irq_stat, cpu).timer_irqs_event; sum += per_cpu(irq_stat, cpu).pmu_irqs; sum += per_cpu(irq_stat, cpu).mce_exceptions; sum += per_cpu(irq_stat, cpu).spurious_irqs; + sum += per_cpu(irq_stat, cpu).timer_irqs_others; #ifdef CONFIG_PPC_DOORBELL sum += per_cpu(irq_stat, cpu).doorbell_irqs; #endif diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c index 83e89d31073..8504657379f 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 new file mode 100644 index 00000000000..cadef7e64e4 --- /dev/null +++ b/arch/powerpc/kernel/mce.c @@ -0,0 +1,352 @@ +/* + * Machine check exception handling. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright 2013 IBM Corporation + * Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> + */ + +#undef DEBUG +#define pr_fmt(fmt) "mce: " fmt + +#include <linux/types.h> +#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); +static DEFINE_PER_CPU(struct machine_check_event[MAX_MC_EVT], mce_event); + +/* Queue for delayed MCE events. */ +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) +{ + mce->error_type = mce_err->error_type; + switch (mce_err->error_type) { + case MCE_ERROR_TYPE_UE: + mce->u.ue_error.ue_error_type = mce_err->u.ue_error_type; + break; + case MCE_ERROR_TYPE_SLB: + mce->u.slb_error.slb_error_type = mce_err->u.slb_error_type; + break; + case MCE_ERROR_TYPE_ERAT: + mce->u.erat_error.erat_error_type = mce_err->u.erat_error_type; + break; + case MCE_ERROR_TYPE_TLB: + mce->u.tlb_error.tlb_error_type = mce_err->u.tlb_error_type; + break; + case MCE_ERROR_TYPE_UNKNOWN: + default: + break; + } +} + +/* + * Decode and save high level MCE information into per cpu buffer which + * is an array of machine_check_event structure. + */ +void save_mce_event(struct pt_regs *regs, long handled, + struct mce_error_info *mce_err, + 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]); + + /* + * Return if we don't have enough space to log mce event. + * mce_nest_count may go beyond MAX_MC_EVT but that's ok, + * the check below will stop buffer overrun. + */ + if (index >= MAX_MC_EVT) + return; + + /* Populate generic machine check info */ + mce->version = MCE_V1; + mce->srr0 = regs->nip; + mce->srr1 = regs->msr; + mce->gpr3 = regs->gpr[3]; + mce->in_use = 1; + + mce->initiator = MCE_INITIATOR_CPU; + if (handled) + mce->disposition = MCE_DISPOSITION_RECOVERED; + else + mce->disposition = MCE_DISPOSITION_NOT_RECOVERED; + mce->severity = MCE_SEV_ERROR_SYNC; + + srr1 = regs->msr; + + /* + * Populate the mce error_type and type-specific error_type. + */ + mce_set_error_info(mce, mce_err); + + if (!addr) + return; + + if (mce->error_type == MCE_ERROR_TYPE_TLB) { + mce->u.tlb_error.effective_address_provided = true; + mce->u.tlb_error.effective_address = addr; + } else if (mce->error_type == MCE_ERROR_TYPE_SLB) { + mce->u.slb_error.effective_address_provided = true; + mce->u.slb_error.effective_address = addr; + } else if (mce->error_type == MCE_ERROR_TYPE_ERAT) { + mce->u.erat_error.effective_address_provided = true; + mce->u.erat_error.effective_address = addr; + } else if (mce->error_type == MCE_ERROR_TYPE_UE) { + mce->u.ue_error.effective_address_provided = true; + mce->u.ue_error.effective_address = addr; + } + return; +} + +/* + * get_mce_event: + * mce Pointer to machine_check_event structure to be filled. + * release Flag to indicate whether to free the event slot or not. + * 0 <= do not release the mce event. Caller will invoke + * release_mce_event() once event has been consumed. + * 1 <= release the slot. + * + * return 1 = success + * 0 = failure + * + * get_mce_event() will be called by platform specific machine check + * handle routine and in KVM. + * When we call get_mce_event(), we are still in interrupt context and + * preemption will not be scheduled until ret_from_expect() routine + * is called. + */ +int get_mce_event(struct machine_check_event *mce, bool release) +{ + int index = __get_cpu_var(mce_nest_count) - 1; + struct machine_check_event *mc_evt; + int ret = 0; + + /* Sanity check */ + if (index < 0) + return ret; + + /* Check if we have MCE info to process. */ + if (index < MAX_MC_EVT) { + mc_evt = &__get_cpu_var(mce_event[index]); + /* Copy the event structure and release the original */ + if (mce) + *mce = *mc_evt; + if (release) + mc_evt->in_use = 0; + ret = 1; + } + /* Decrement the count to free the slot. */ + if (release) + __get_cpu_var(mce_nest_count)--; + + return ret; +} + +void release_mce_event(void) +{ + get_mce_event(NULL, true); +} + +/* + * Queue up the MCE event which then can be handled later. + */ +void machine_check_queue_event(void) +{ + int index; + struct machine_check_event evt; + + if (!get_mce_event(&evt, MCE_EVENT_RELEASE)) + return; + + index = __get_cpu_var(mce_queue_count)++; + /* If queue is full, just return for now. */ + if (index >= MAX_MC_EVT) { + __get_cpu_var(mce_queue_count)--; + 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. + */ +static void machine_check_process_queued_event(struct irq_work *work) +{ + int index; + + /* + * 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; + machine_check_print_event_info( + &__get_cpu_var(mce_event_queue[index])); + __get_cpu_var(mce_queue_count)--; + } +} + +void machine_check_print_event_info(struct machine_check_event *evt) +{ + const char *level, *sevstr, *subtype; + static const char *mc_ue_types[] = { + "Indeterminate", + "Instruction fetch", + "Page table walk ifetch", + "Load/Store", + "Page table walk Load/Store", + }; + static const char *mc_slb_types[] = { + "Indeterminate", + "Parity", + "Multihit", + }; + static const char *mc_erat_types[] = { + "Indeterminate", + "Parity", + "Multihit", + }; + static const char *mc_tlb_types[] = { + "Indeterminate", + "Parity", + "Multihit", + }; + + /* Print things out */ + if (evt->version != MCE_V1) { + pr_err("Machine Check Exception, Unknown event version %d !\n", + evt->version); + return; + } + switch (evt->severity) { + case MCE_SEV_NO_ERROR: + level = KERN_INFO; + sevstr = "Harmless"; + break; + case MCE_SEV_WARNING: + level = KERN_WARNING; + sevstr = ""; + break; + case MCE_SEV_ERROR_SYNC: + level = KERN_ERR; + sevstr = "Severe"; + break; + case MCE_SEV_FATAL: + default: + level = KERN_ERR; + sevstr = "Fatal"; + break; + } + + printk("%s%s Machine check interrupt [%s]\n", level, sevstr, + evt->disposition == MCE_DISPOSITION_RECOVERED ? + "Recovered" : "[Not recovered"); + printk("%s Initiator: %s\n", level, + evt->initiator == MCE_INITIATOR_CPU ? "CPU" : "Unknown"); + switch (evt->error_type) { + case MCE_ERROR_TYPE_UE: + subtype = evt->u.ue_error.ue_error_type < + ARRAY_SIZE(mc_ue_types) ? + mc_ue_types[evt->u.ue_error.ue_error_type] + : "Unknown"; + printk("%s Error type: UE [%s]\n", level, subtype); + if (evt->u.ue_error.effective_address_provided) + printk("%s Effective address: %016llx\n", + level, evt->u.ue_error.effective_address); + if (evt->u.ue_error.physical_address_provided) + printk("%s Physial address: %016llx\n", + level, evt->u.ue_error.physical_address); + break; + case MCE_ERROR_TYPE_SLB: + subtype = evt->u.slb_error.slb_error_type < + ARRAY_SIZE(mc_slb_types) ? + mc_slb_types[evt->u.slb_error.slb_error_type] + : "Unknown"; + printk("%s Error type: SLB [%s]\n", level, subtype); + if (evt->u.slb_error.effective_address_provided) + printk("%s Effective address: %016llx\n", + level, evt->u.slb_error.effective_address); + break; + case MCE_ERROR_TYPE_ERAT: + subtype = evt->u.erat_error.erat_error_type < + ARRAY_SIZE(mc_erat_types) ? + mc_erat_types[evt->u.erat_error.erat_error_type] + : "Unknown"; + printk("%s Error type: ERAT [%s]\n", level, subtype); + if (evt->u.erat_error.effective_address_provided) + printk("%s Effective address: %016llx\n", + level, evt->u.erat_error.effective_address); + break; + case MCE_ERROR_TYPE_TLB: + subtype = evt->u.tlb_error.tlb_error_type < + ARRAY_SIZE(mc_tlb_types) ? + mc_tlb_types[evt->u.tlb_error.tlb_error_type] + : "Unknown"; + printk("%s Error type: TLB [%s]\n", level, subtype); + if (evt->u.tlb_error.effective_address_provided) + printk("%s Effective address: %016llx\n", + level, evt->u.tlb_error.effective_address); + break; + default: + case MCE_ERROR_TYPE_UNKNOWN: + printk("%s Error type: Unknown\n", level); + break; + } +} + +uint64_t get_mce_fault_addr(struct machine_check_event *evt) +{ + switch (evt->error_type) { + case MCE_ERROR_TYPE_UE: + if (evt->u.ue_error.effective_address_provided) + return evt->u.ue_error.effective_address; + break; + case MCE_ERROR_TYPE_SLB: + if (evt->u.slb_error.effective_address_provided) + return evt->u.slb_error.effective_address; + break; + case MCE_ERROR_TYPE_ERAT: + if (evt->u.erat_error.effective_address_provided) + return evt->u.erat_error.effective_address; + break; + case MCE_ERROR_TYPE_TLB: + if (evt->u.tlb_error.effective_address_provided) + return evt->u.tlb_error.effective_address; + break; + default: + case MCE_ERROR_TYPE_UNKNOWN: + break; + } + return 0; +} +EXPORT_SYMBOL(get_mce_fault_addr); diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c new file mode 100644 index 00000000000..27c93f41166 --- /dev/null +++ b/arch/powerpc/kernel/mce_power.c @@ -0,0 +1,284 @@ +/* + * Machine check exception handling CPU-side for power7 and power8 + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright 2013 IBM Corporation + * Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> + */ + +#undef DEBUG +#define pr_fmt(fmt) "mce_power: " fmt + +#include <linux/types.h> +#include <linux/ptrace.h> +#include <asm/mmu.h> +#include <asm/mce.h> + +/* flush SLBs and reload */ +static void flush_and_reload_slb(void) +{ + struct slb_shadow *slb; + unsigned long i, n; + + /* Invalidate all SLBs */ + asm volatile("slbmte %0,%0; slbia" : : "r" (0)); + +#ifdef CONFIG_KVM_BOOK3S_HANDLER + /* + * If machine check is hit when in guest or in transition, we will + * only flush the SLBs and continue. + */ + if (get_paca()->kvm_hstate.in_guest) + return; +#endif + + /* For host kernel, reload the SLBs from shadow SLB buffer. */ + slb = get_slb_shadow(); + if (!slb) + return; + + n = min_t(u32, be32_to_cpu(slb->persistent), SLB_MIN_SIZE); + + /* Load up the SLB entries from shadow SLB */ + for (i = 0; i < n; i++) { + unsigned long rb = be64_to_cpu(slb->save_area[i].esid); + unsigned long rs = be64_to_cpu(slb->save_area[i].vsid); + + rb = (rb & ~0xFFFul) | i; + asm volatile("slbmte %0,%1" : : "r" (rs), "r" (rb)); + } +} + +static long mce_handle_derror(uint64_t dsisr, uint64_t slb_error_bits) +{ + long handled = 1; + + /* + * flush and reload SLBs for SLB errors and flush TLBs for TLB errors. + * reset the error bits whenever we handle them so that at the end + * we can check whether we handled all of them or not. + * */ + if (dsisr & slb_error_bits) { + flush_and_reload_slb(); + /* reset error bits */ + dsisr &= ~(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); + /* reset error bits */ + dsisr &= ~P7_DSISR_MC_TLB_MULTIHIT_MFTLB; + } + /* Any other errors we don't understand? */ + if (dsisr & 0xffffffffUL) + handled = 0; + + return handled; +} + +static long mce_handle_derror_p7(uint64_t dsisr) +{ + return mce_handle_derror(dsisr, P7_DSISR_MC_SLB_ERRORS); +} + +static long mce_handle_common_ierror(uint64_t srr1) +{ + long handled = 0; + + switch (P7_SRR1_MC_IFETCH(srr1)) { + case 0: + break; + case P7_SRR1_MC_IFETCH_SLB_PARITY: + case P7_SRR1_MC_IFETCH_SLB_MULTIHIT: + /* flush and reload SLBs for SLB errors. */ + flush_and_reload_slb(); + handled = 1; + 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); + handled = 1; + } + break; + default: + break; + } + + return handled; +} + +static long mce_handle_ierror_p7(uint64_t srr1) +{ + long handled = 0; + + handled = mce_handle_common_ierror(srr1); + + if (P7_SRR1_MC_IFETCH(srr1) == P7_SRR1_MC_IFETCH_SLB_BOTH) { + flush_and_reload_slb(); + handled = 1; + } + return handled; +} + +static void mce_get_common_ierror(struct mce_error_info *mce_err, uint64_t srr1) +{ + switch (P7_SRR1_MC_IFETCH(srr1)) { + case P7_SRR1_MC_IFETCH_SLB_PARITY: + mce_err->error_type = MCE_ERROR_TYPE_SLB; + mce_err->u.slb_error_type = MCE_SLB_ERROR_PARITY; + break; + case P7_SRR1_MC_IFETCH_SLB_MULTIHIT: + mce_err->error_type = MCE_ERROR_TYPE_SLB; + mce_err->u.slb_error_type = MCE_SLB_ERROR_MULTIHIT; + break; + case P7_SRR1_MC_IFETCH_TLB_MULTIHIT: + mce_err->error_type = MCE_ERROR_TYPE_TLB; + mce_err->u.tlb_error_type = MCE_TLB_ERROR_MULTIHIT; + break; + case P7_SRR1_MC_IFETCH_UE: + case P7_SRR1_MC_IFETCH_UE_IFU_INTERNAL: + mce_err->error_type = MCE_ERROR_TYPE_UE; + mce_err->u.ue_error_type = MCE_UE_ERROR_IFETCH; + break; + case P7_SRR1_MC_IFETCH_UE_TLB_RELOAD: + mce_err->error_type = MCE_ERROR_TYPE_UE; + mce_err->u.ue_error_type = + MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH; + break; + } +} + +static void mce_get_ierror_p7(struct mce_error_info *mce_err, uint64_t srr1) +{ + mce_get_common_ierror(mce_err, srr1); + if (P7_SRR1_MC_IFETCH(srr1) == P7_SRR1_MC_IFETCH_SLB_BOTH) { + mce_err->error_type = MCE_ERROR_TYPE_SLB; + mce_err->u.slb_error_type = MCE_SLB_ERROR_INDETERMINATE; + } +} + +static void mce_get_derror_p7(struct mce_error_info *mce_err, uint64_t dsisr) +{ + if (dsisr & P7_DSISR_MC_UE) { + mce_err->error_type = MCE_ERROR_TYPE_UE; + mce_err->u.ue_error_type = MCE_UE_ERROR_LOAD_STORE; + } else if (dsisr & P7_DSISR_MC_UE_TABLEWALK) { + mce_err->error_type = MCE_ERROR_TYPE_UE; + mce_err->u.ue_error_type = + MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE; + } else if (dsisr & P7_DSISR_MC_ERAT_MULTIHIT) { + mce_err->error_type = MCE_ERROR_TYPE_ERAT; + mce_err->u.erat_error_type = MCE_ERAT_ERROR_MULTIHIT; + } else if (dsisr & P7_DSISR_MC_SLB_MULTIHIT) { + mce_err->error_type = MCE_ERROR_TYPE_SLB; + mce_err->u.slb_error_type = MCE_SLB_ERROR_MULTIHIT; + } else if (dsisr & P7_DSISR_MC_SLB_PARITY_MFSLB) { + mce_err->error_type = MCE_ERROR_TYPE_SLB; + mce_err->u.slb_error_type = MCE_SLB_ERROR_PARITY; + } else if (dsisr & P7_DSISR_MC_TLB_MULTIHIT_MFTLB) { + mce_err->error_type = MCE_ERROR_TYPE_TLB; + mce_err->u.tlb_error_type = MCE_TLB_ERROR_MULTIHIT; + } else if (dsisr & P7_DSISR_MC_SLB_MULTIHIT_PARITY) { + mce_err->error_type = MCE_ERROR_TYPE_SLB; + mce_err->u.slb_error_type = MCE_SLB_ERROR_INDETERMINATE; + } +} + +long __machine_check_early_realmode_p7(struct pt_regs *regs) +{ + uint64_t srr1, addr; + long handled = 1; + struct mce_error_info mce_error_info = { 0 }; + + srr1 = regs->msr; + + /* + * Handle memory errors depending whether this was a load/store or + * ifetch exception. Also, populate the mce error_type and + * type-specific error_type from either SRR1 or DSISR, depending + * whether this was a load/store or ifetch exception + */ + if (P7_SRR1_MC_LOADSTORE(srr1)) { + handled = mce_handle_derror_p7(regs->dsisr); + mce_get_derror_p7(&mce_error_info, regs->dsisr); + addr = regs->dar; + } else { + handled = mce_handle_ierror_p7(srr1); + mce_get_ierror_p7(&mce_error_info, srr1); + addr = regs->nip; + } + + save_mce_event(regs, handled, &mce_error_info, addr); + return handled; +} + +static void mce_get_ierror_p8(struct mce_error_info *mce_err, uint64_t srr1) +{ + mce_get_common_ierror(mce_err, srr1); + if (P7_SRR1_MC_IFETCH(srr1) == P8_SRR1_MC_IFETCH_ERAT_MULTIHIT) { + mce_err->error_type = MCE_ERROR_TYPE_ERAT; + mce_err->u.erat_error_type = MCE_ERAT_ERROR_MULTIHIT; + } +} + +static void mce_get_derror_p8(struct mce_error_info *mce_err, uint64_t dsisr) +{ + mce_get_derror_p7(mce_err, dsisr); + if (dsisr & P8_DSISR_MC_ERAT_MULTIHIT_SEC) { + mce_err->error_type = MCE_ERROR_TYPE_ERAT; + mce_err->u.erat_error_type = MCE_ERAT_ERROR_MULTIHIT; + } +} + +static long mce_handle_ierror_p8(uint64_t srr1) +{ + long handled = 0; + + handled = mce_handle_common_ierror(srr1); + + if (P7_SRR1_MC_IFETCH(srr1) == P8_SRR1_MC_IFETCH_ERAT_MULTIHIT) { + flush_and_reload_slb(); + handled = 1; + } + return handled; +} + +static long mce_handle_derror_p8(uint64_t dsisr) +{ + return mce_handle_derror(dsisr, P8_DSISR_MC_SLB_ERRORS); +} + +long __machine_check_early_realmode_p8(struct pt_regs *regs) +{ + uint64_t srr1, addr; + long handled = 1; + struct mce_error_info mce_error_info = { 0 }; + + srr1 = regs->msr; + + if (P7_SRR1_MC_LOADSTORE(srr1)) { + handled = mce_handle_derror_p8(regs->dsisr); + mce_get_derror_p8(&mce_error_info, regs->dsisr); + addr = regs->dar; + } else { + handled = mce_handle_ierror_p8(srr1); + mce_get_ierror_p8(&mce_error_info, srr1); + addr = regs->nip; + } + + save_mce_event(regs, handled, &mce_error_info, addr); + return handled; +} diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index e47d268727a..879f09620f8 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -344,7 +344,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_UNIFIED_ID_CACHE) */ _KPROBE(flush_icache_range) BEGIN_FTR_SECTION - isync + PURGE_PREFETCHED_INS blr /* for 601, do nothing */ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) li r5,L1_CACHE_BYTES-1 @@ -448,6 +448,7 @@ _GLOBAL(invalidate_dcache_range) */ _GLOBAL(__flush_dcache_icache) BEGIN_FTR_SECTION + PURGE_PREFETCHED_INS blr END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) rlwinm r3,r3,0,0,31-PAGE_SHIFT /* Get page base address */ @@ -489,6 +490,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_44x) */ _GLOBAL(__flush_dcache_icache_phys) BEGIN_FTR_SECTION + PURGE_PREFETCHED_INS blr /* for 601, do nothing */ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) mfmsr r10 diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index 64bf8db12b1..3d0249599d5 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -67,6 +67,7 @@ PPC64_CACHES: _KPROBE(flush_icache_range) BEGIN_FTR_SECTION + PURGE_PREFETCHED_INS blr END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) /* @@ -211,6 +212,11 @@ _GLOBAL(__flush_dcache_icache) * Different systems have different cache line sizes */ +BEGIN_FTR_SECTION + PURGE_PREFETCHED_INS + blr +END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) + /* Flush the dcache */ ld r7,PPC64_CACHES@toc(r2) clrrdi r3,r3,PAGE_SHIFT /* Page align */ diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index 0620eaaaad4..bf0aada02fe 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -99,12 +99,28 @@ static inline void free_lppacas(void) { } * 3 persistent SLBs are registered here. The buffer will be zero * initially, hence will all be invaild until we actually write them. */ -struct slb_shadow slb_shadow[] __cacheline_aligned = { - [0 ... (NR_CPUS-1)] = { - .persistent = cpu_to_be32(SLB_NUM_BOLTED), - .buffer_length = cpu_to_be32(sizeof(struct slb_shadow)), - }, -}; +static struct slb_shadow *slb_shadow; + +static void __init allocate_slb_shadows(int nr_cpus, int limit) +{ + int size = PAGE_ALIGN(sizeof(struct slb_shadow) * nr_cpus); + slb_shadow = __va(memblock_alloc_base(size, PAGE_SIZE, limit)); + memset(slb_shadow, 0, size); +} + +static struct slb_shadow * __init init_slb_shadow(int cpu) +{ + struct slb_shadow *s = &slb_shadow[cpu]; + + s->persistent = cpu_to_be32(SLB_NUM_BOLTED); + s->buffer_length = cpu_to_be32(sizeof(*s)); + + return s; +} + +#else /* CONFIG_PPC_STD_MMU_64 */ + +static void __init allocate_slb_shadows(int nr_cpus, int limit) { } #endif /* CONFIG_PPC_STD_MMU_64 */ @@ -142,8 +158,13 @@ void __init initialise_paca(struct paca_struct *new_paca, int cpu) new_paca->__current = &init_task; new_paca->data_offset = 0xfeeeeeeeeeeeeeeeULL; #ifdef CONFIG_PPC_STD_MMU_64 - new_paca->slb_shadow_ptr = &slb_shadow[cpu]; + 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 */ @@ -190,6 +211,8 @@ void __init allocate_pacas(void) allocate_lppacas(nr_cpu_ids, limit); + allocate_slb_shadows(nr_cpu_ids, limit); + /* Can't use for_each_*_cpu, as they aren't functional yet */ for (cpu = 0; cpu < nr_cpu_ids; cpu++) initialise_paca(&paca[cpu], cpu); diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 4a96556fd2d..64b7a6e61dd 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); } @@ -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) @@ -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 fa0ad8aafbc..f58c0d3aaeb 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/setup_64.c b/arch/powerpc/kernel/setup_64.c index 856dd4e99bf..f5f11a7d30e 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 @@ -520,9 +551,6 @@ static void __init irqstack_early_init(void) #ifdef CONFIG_PPC_BOOK3E static void __init exc_lvl_early_init(void) { - extern unsigned int interrupt_base_book3e; - extern unsigned int exc_debug_debug_book3e; - unsigned int i; for_each_possible_cpu(i) { @@ -535,8 +563,7 @@ static void __init exc_lvl_early_init(void) } if (cpu_has_feature(CPU_FTR_DEBUG_LVL_EXC)) - patch_branch(&interrupt_base_book3e + (0x040 / 4) + 1, - (unsigned long)&exc_debug_debug_book3e, 0); + patch_exception(0x040, exc_debug_debug_book3e); } #else #define exc_lvl_early_init() @@ -544,7 +571,8 @@ static void __init exc_lvl_early_init(void) /* * Stack space used when we detect a bad kernel stack pointer, and - * early in SMP boots before relocation is enabled. + * early in SMP boots before relocation is enabled. Exclusive emergency + * stack for machine checks. */ static void __init emergency_stack_init(void) { @@ -567,6 +595,13 @@ static void __init emergency_stack_init(void) sp = memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit); sp += THREAD_SIZE; paca[i].emergency_sp = __va(sp); + +#ifdef CONFIG_PPC_BOOK3S_64 + /* emergency stack for machine check exception handling. */ + sp = memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit); + sp += THREAD_SIZE; + paca[i].mc_emergency_sp = __va(sp); +#endif } } diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index 457e97aa294..8fc4177ed65 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 68027bfa5f8..6ce69e6f1fc 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 42991045349..e35bf773df7 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 e68fd1ae727..7a37ecd3afa 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/smp.c b/arch/powerpc/kernel/smp.c index c1cf4a1522d..ac2621af315 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -369,13 +369,8 @@ void __init smp_prepare_cpus(unsigned int max_cpus) cpumask_set_cpu(boot_cpuid, cpu_sibling_mask(boot_cpuid)); cpumask_set_cpu(boot_cpuid, cpu_core_mask(boot_cpuid)); - if (smp_ops) - if (smp_ops->probe) - max_cpus = smp_ops->probe(); - else - max_cpus = NR_CPUS; - else - max_cpus = 1; + if (smp_ops && smp_ops->probe) + smp_ops->probe(); } void smp_prepare_boot_cpu(void) diff --git a/arch/powerpc/kernel/swsusp_booke.S b/arch/powerpc/kernel/swsusp_booke.S index 0f204053e5b..553c1405ee0 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 4e3cc47f26b..cd9be9aa016 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 b4e667663d9..d4a43e64a6a 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. @@ -108,14 +406,14 @@ void ppc_enable_pmcs(void) } EXPORT_SYMBOL(ppc_enable_pmcs); -#define SYSFS_PMCSETUP(NAME, ADDRESS) \ +#define __SYSFS_SPRSETUP(NAME, ADDRESS, EXTRA) \ static void read_##NAME(void *val) \ { \ *(unsigned long *)val = mfspr(ADDRESS); \ } \ static void write_##NAME(void *val) \ { \ - ppc_enable_pmcs(); \ + EXTRA; \ mtspr(ADDRESS, *(unsigned long *)val); \ } \ static ssize_t show_##NAME(struct device *dev, \ @@ -140,6 +438,10 @@ static ssize_t __used \ return count; \ } +#define SYSFS_PMCSETUP(NAME, ADDRESS) \ + __SYSFS_SPRSETUP(NAME, ADDRESS, ppc_enable_pmcs()) +#define SYSFS_SPRSETUP(NAME, ADDRESS) \ + __SYSFS_SPRSETUP(NAME, ADDRESS, ) /* Let's define all possible registers, we'll only hook up the ones * that are implemented on the current processor @@ -175,10 +477,10 @@ SYSFS_PMCSETUP(pmc7, SPRN_PMC7); SYSFS_PMCSETUP(pmc8, SPRN_PMC8); SYSFS_PMCSETUP(mmcra, SPRN_MMCRA); -SYSFS_PMCSETUP(purr, SPRN_PURR); -SYSFS_PMCSETUP(spurr, SPRN_SPURR); -SYSFS_PMCSETUP(dscr, SPRN_DSCR); -SYSFS_PMCSETUP(pir, SPRN_PIR); +SYSFS_SPRSETUP(purr, SPRN_PURR); +SYSFS_SPRSETUP(spurr, SPRN_SPURR); +SYSFS_SPRSETUP(dscr, SPRN_DSCR); +SYSFS_SPRSETUP(pir, SPRN_PIR); /* Lets only enable read for phyp resources and @@ -249,34 +551,34 @@ SYSFS_PMCSETUP(pa6t_pmc3, SPRN_PA6T_PMC3); SYSFS_PMCSETUP(pa6t_pmc4, SPRN_PA6T_PMC4); SYSFS_PMCSETUP(pa6t_pmc5, SPRN_PA6T_PMC5); #ifdef CONFIG_DEBUG_KERNEL -SYSFS_PMCSETUP(hid0, SPRN_HID0); -SYSFS_PMCSETUP(hid1, SPRN_HID1); -SYSFS_PMCSETUP(hid4, SPRN_HID4); -SYSFS_PMCSETUP(hid5, SPRN_HID5); -SYSFS_PMCSETUP(ima0, SPRN_PA6T_IMA0); -SYSFS_PMCSETUP(ima1, SPRN_PA6T_IMA1); -SYSFS_PMCSETUP(ima2, SPRN_PA6T_IMA2); -SYSFS_PMCSETUP(ima3, SPRN_PA6T_IMA3); -SYSFS_PMCSETUP(ima4, SPRN_PA6T_IMA4); -SYSFS_PMCSETUP(ima5, SPRN_PA6T_IMA5); -SYSFS_PMCSETUP(ima6, SPRN_PA6T_IMA6); -SYSFS_PMCSETUP(ima7, SPRN_PA6T_IMA7); -SYSFS_PMCSETUP(ima8, SPRN_PA6T_IMA8); -SYSFS_PMCSETUP(ima9, SPRN_PA6T_IMA9); -SYSFS_PMCSETUP(imaat, SPRN_PA6T_IMAAT); -SYSFS_PMCSETUP(btcr, SPRN_PA6T_BTCR); -SYSFS_PMCSETUP(pccr, SPRN_PA6T_PCCR); -SYSFS_PMCSETUP(rpccr, SPRN_PA6T_RPCCR); -SYSFS_PMCSETUP(der, SPRN_PA6T_DER); -SYSFS_PMCSETUP(mer, SPRN_PA6T_MER); -SYSFS_PMCSETUP(ber, SPRN_PA6T_BER); -SYSFS_PMCSETUP(ier, SPRN_PA6T_IER); -SYSFS_PMCSETUP(sier, SPRN_PA6T_SIER); -SYSFS_PMCSETUP(siar, SPRN_PA6T_SIAR); -SYSFS_PMCSETUP(tsr0, SPRN_PA6T_TSR0); -SYSFS_PMCSETUP(tsr1, SPRN_PA6T_TSR1); -SYSFS_PMCSETUP(tsr2, SPRN_PA6T_TSR2); -SYSFS_PMCSETUP(tsr3, SPRN_PA6T_TSR3); +SYSFS_SPRSETUP(hid0, SPRN_HID0); +SYSFS_SPRSETUP(hid1, SPRN_HID1); +SYSFS_SPRSETUP(hid4, SPRN_HID4); +SYSFS_SPRSETUP(hid5, SPRN_HID5); +SYSFS_SPRSETUP(ima0, SPRN_PA6T_IMA0); +SYSFS_SPRSETUP(ima1, SPRN_PA6T_IMA1); +SYSFS_SPRSETUP(ima2, SPRN_PA6T_IMA2); +SYSFS_SPRSETUP(ima3, SPRN_PA6T_IMA3); +SYSFS_SPRSETUP(ima4, SPRN_PA6T_IMA4); +SYSFS_SPRSETUP(ima5, SPRN_PA6T_IMA5); +SYSFS_SPRSETUP(ima6, SPRN_PA6T_IMA6); +SYSFS_SPRSETUP(ima7, SPRN_PA6T_IMA7); +SYSFS_SPRSETUP(ima8, SPRN_PA6T_IMA8); +SYSFS_SPRSETUP(ima9, SPRN_PA6T_IMA9); +SYSFS_SPRSETUP(imaat, SPRN_PA6T_IMAAT); +SYSFS_SPRSETUP(btcr, SPRN_PA6T_BTCR); +SYSFS_SPRSETUP(pccr, SPRN_PA6T_PCCR); +SYSFS_SPRSETUP(rpccr, SPRN_PA6T_RPCCR); +SYSFS_SPRSETUP(der, SPRN_PA6T_DER); +SYSFS_SPRSETUP(mer, SPRN_PA6T_MER); +SYSFS_SPRSETUP(ber, SPRN_PA6T_BER); +SYSFS_SPRSETUP(ier, SPRN_PA6T_IER); +SYSFS_SPRSETUP(sier, SPRN_PA6T_SIER); +SYSFS_SPRSETUP(siar, SPRN_PA6T_SIAR); +SYSFS_SPRSETUP(tsr0, SPRN_PA6T_TSR0); +SYSFS_SPRSETUP(tsr1, SPRN_PA6T_TSR1); +SYSFS_SPRSETUP(tsr2, SPRN_PA6T_TSR2); +SYSFS_SPRSETUP(tsr3, SPRN_PA6T_TSR3); #endif /* CONFIG_DEBUG_KERNEL */ #endif /* HAS_PPC_PMC_PA6T */ @@ -421,6 +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); } @@ -493,6 +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 b3b144121cc..b3dab20acf3 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -510,7 +510,6 @@ void timer_interrupt(struct pt_regs * regs) */ may_hard_irq_enable(); - __get_cpu_var(irq_stat).timer_irqs++; #if defined(CONFIG_PPC32) && defined(CONFIG_PMAC) if (atomic_read(&ppc_n_lost_interrupts) != 0) @@ -532,10 +531,15 @@ void timer_interrupt(struct pt_regs * regs) *next_tb = ~(u64)0; if (evt->event_handler) evt->event_handler(evt); + __get_cpu_var(irq_stat).timer_irqs_event++; } else { 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++; } #ifdef CONFIG_PPC64 @@ -801,8 +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 907a472f9a9..33cd7a0b8e7 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -285,6 +285,21 @@ void system_reset_exception(struct pt_regs *regs) /* What should we do here? We could issue a shutdown or hard reset. */ } + +/* + * This function is called in real mode. Strictly no printk's please. + * + * regs->nip and regs->msr contains srr0 and ssr1. + */ +long machine_check_early(struct pt_regs *regs) +{ + long handled = 0; + + if (cur_cpu_spec && cur_cpu_spec->machine_check_early) + handled = cur_cpu_spec->machine_check_early(regs); + return handled; +} + #endif /* @@ -1384,7 +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 @@ -1393,8 +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: */ @@ -1403,11 +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 @@ -1417,18 +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. * @@ -1440,18 +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/vdso32/vdso32_wrapper.S b/arch/powerpc/kernel/vdso32/vdso32_wrapper.S index 6e8f507ed32..79683d0393f 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 b8553d62b79..8df9e246300 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 0458a9aaba9..74f8050518d 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. */ diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c index 76a64821f4a..826d8bd9e52 100644 --- a/arch/powerpc/kernel/vio.c +++ b/arch/powerpc/kernel/vio.c @@ -518,16 +518,18 @@ static dma_addr_t vio_dma_iommu_map_page(struct device *dev, struct page *page, struct dma_attrs *attrs) { struct vio_dev *viodev = to_vio_dev(dev); + struct iommu_table *tbl; dma_addr_t ret = DMA_ERROR_CODE; - if (vio_cmo_alloc(viodev, roundup(size, IOMMU_PAGE_SIZE))) { + tbl = get_iommu_table_base(dev); + if (vio_cmo_alloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl)))) { atomic_inc(&viodev->cmo.allocs_failed); return ret; } ret = dma_iommu_ops.map_page(dev, page, offset, size, direction, attrs); if (unlikely(dma_mapping_error(dev, ret))) { - vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE)); + vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl))); atomic_inc(&viodev->cmo.allocs_failed); } @@ -540,10 +542,12 @@ static void vio_dma_iommu_unmap_page(struct device *dev, dma_addr_t dma_handle, struct dma_attrs *attrs) { struct vio_dev *viodev = to_vio_dev(dev); + struct iommu_table *tbl; + tbl = get_iommu_table_base(dev); dma_iommu_ops.unmap_page(dev, dma_handle, size, direction, attrs); - vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE)); + vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl))); } static int vio_dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist, @@ -551,12 +555,14 @@ static int vio_dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist, struct dma_attrs *attrs) { struct vio_dev *viodev = to_vio_dev(dev); + struct iommu_table *tbl; struct scatterlist *sgl; int ret, count = 0; size_t alloc_size = 0; + tbl = get_iommu_table_base(dev); for (sgl = sglist; count < nelems; count++, sgl++) - alloc_size += roundup(sgl->length, IOMMU_PAGE_SIZE); + alloc_size += roundup(sgl->length, IOMMU_PAGE_SIZE(tbl)); if (vio_cmo_alloc(viodev, alloc_size)) { atomic_inc(&viodev->cmo.allocs_failed); @@ -572,7 +578,7 @@ static int vio_dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist, } for (sgl = sglist, count = 0; count < ret; count++, sgl++) - alloc_size -= roundup(sgl->dma_length, IOMMU_PAGE_SIZE); + alloc_size -= roundup(sgl->dma_length, IOMMU_PAGE_SIZE(tbl)); if (alloc_size) vio_cmo_dealloc(viodev, alloc_size); @@ -585,12 +591,14 @@ static void vio_dma_iommu_unmap_sg(struct device *dev, struct dma_attrs *attrs) { struct vio_dev *viodev = to_vio_dev(dev); + struct iommu_table *tbl; struct scatterlist *sgl; size_t alloc_size = 0; int count = 0; + tbl = get_iommu_table_base(dev); for (sgl = sglist; count < nelems; count++, sgl++) - alloc_size += roundup(sgl->dma_length, IOMMU_PAGE_SIZE); + alloc_size += roundup(sgl->dma_length, IOMMU_PAGE_SIZE(tbl)); dma_iommu_ops.unmap_sg(dev, sglist, nelems, direction, attrs); @@ -706,11 +714,14 @@ static int vio_cmo_bus_probe(struct vio_dev *viodev) { struct vio_cmo_dev_entry *dev_ent; struct device *dev = &viodev->dev; + struct iommu_table *tbl; struct vio_driver *viodrv = to_vio_driver(dev->driver); unsigned long flags; size_t size; bool dma_capable = false; + tbl = get_iommu_table_base(dev); + /* A device requires entitlement if it has a DMA window property */ switch (viodev->family) { case VDEVICE: @@ -736,7 +747,8 @@ static int vio_cmo_bus_probe(struct vio_dev *viodev) return -EINVAL; } - viodev->cmo.desired = IOMMU_PAGE_ALIGN(viodrv->get_desired_dma(viodev)); + viodev->cmo.desired = + IOMMU_PAGE_ALIGN(viodrv->get_desired_dma(viodev), tbl); if (viodev->cmo.desired < VIO_CMO_MIN_ENT) viodev->cmo.desired = VIO_CMO_MIN_ENT; size = VIO_CMO_MIN_ENT; @@ -1176,9 +1188,10 @@ static struct iommu_table *vio_build_iommu_table(struct vio_dev *dev) &tbl->it_index, &offset, &size); /* TCE table size - measured in tce entries */ - tbl->it_size = size >> IOMMU_PAGE_SHIFT; + tbl->it_page_shift = IOMMU_PAGE_SHIFT_4K; + tbl->it_size = size >> tbl->it_page_shift; /* offset for VIO should always be 0 */ - tbl->it_offset = offset >> IOMMU_PAGE_SHIFT; + tbl->it_offset = offset >> tbl->it_page_shift; tbl->it_busno = 0; tbl->it_type = TCE_VB; tbl->it_blocksize = 16; |