diff options
Diffstat (limited to 'arch/powerpc/kernel')
40 files changed, 1261 insertions, 560 deletions
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 794f22adf..2da380fcc 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -16,14 +16,14 @@ endif ifdef CONFIG_FUNCTION_TRACER # Do not trace early boot code -CFLAGS_REMOVE_cputable.o = -pg -mno-sched-epilog -CFLAGS_REMOVE_prom_init.o = -pg -mno-sched-epilog -CFLAGS_REMOVE_btext.o = -pg -mno-sched-epilog -CFLAGS_REMOVE_prom.o = -pg -mno-sched-epilog +CFLAGS_REMOVE_cputable.o = -mno-sched-epilog $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_prom_init.o = -mno-sched-epilog $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_btext.o = -mno-sched-epilog $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_prom.o = -mno-sched-epilog $(CC_FLAGS_FTRACE) # do not trace tracer code -CFLAGS_REMOVE_ftrace.o = -pg -mno-sched-epilog +CFLAGS_REMOVE_ftrace.o = -mno-sched-epilog $(CC_FLAGS_FTRACE) # timers used by tracing -CFLAGS_REMOVE_time.o = -pg -mno-sched-epilog +CFLAGS_REMOVE_time.o = -mno-sched-epilog $(CC_FLAGS_FTRACE) endif obj-y := cputable.o ptrace.o syscalls.o \ diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 07cebc351..0d0183d31 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -95,12 +95,14 @@ int main(void) DEFINE(THREAD_FPSTATE, offsetof(struct thread_struct, fp_state)); DEFINE(THREAD_FPSAVEAREA, offsetof(struct thread_struct, fp_save_area)); DEFINE(FPSTATE_FPSCR, offsetof(struct thread_fp_state, fpscr)); + DEFINE(THREAD_LOAD_FP, offsetof(struct thread_struct, load_fp)); #ifdef CONFIG_ALTIVEC DEFINE(THREAD_VRSTATE, offsetof(struct thread_struct, vr_state)); DEFINE(THREAD_VRSAVEAREA, offsetof(struct thread_struct, vr_save_area)); DEFINE(THREAD_VRSAVE, offsetof(struct thread_struct, vrsave)); DEFINE(THREAD_USED_VR, offsetof(struct thread_struct, used_vr)); DEFINE(VRSTATE_VSCR, offsetof(struct thread_vr_state, vscr)); + DEFINE(THREAD_LOAD_VEC, offsetof(struct thread_struct, load_vec)); #endif /* CONFIG_ALTIVEC */ #ifdef CONFIG_VSX DEFINE(THREAD_USED_VSR, offsetof(struct thread_struct, used_vsr)); @@ -374,6 +376,7 @@ int main(void) DEFINE(CPU_SPEC_FEATURES, offsetof(struct cpu_spec, cpu_features)); DEFINE(CPU_SPEC_SETUP, offsetof(struct cpu_spec, cpu_setup)); DEFINE(CPU_SPEC_RESTORE, offsetof(struct cpu_spec, cpu_restore)); + DEFINE(CPU_DOWN_FLUSH, offsetof(struct cpu_spec, cpu_down_flush)); DEFINE(pbe_address, offsetof(struct pbe, address)); DEFINE(pbe_orig_address, offsetof(struct pbe, orig_address)); diff --git a/arch/powerpc/kernel/cpu_setup_fsl_booke.S b/arch/powerpc/kernel/cpu_setup_fsl_booke.S index dddba3e94..462aed9bc 100644 --- a/arch/powerpc/kernel/cpu_setup_fsl_booke.S +++ b/arch/powerpc/kernel/cpu_setup_fsl_booke.S @@ -13,11 +13,13 @@ * */ +#include <asm/page.h> #include <asm/processor.h> #include <asm/cputable.h> #include <asm/ppc_asm.h> #include <asm/mmu-book3e.h> #include <asm/asm-offsets.h> +#include <asm/mpc85xx.h> _GLOBAL(__e500_icache_setup) mfspr r0, SPRN_L1CSR1 @@ -233,3 +235,113 @@ _GLOBAL(__setup_cpu_e5500) mtlr r5 blr #endif + +/* flush L1 date cache, it can apply to e500v2, e500mc and e5500 */ +_GLOBAL(flush_dcache_L1) + mfmsr r10 + wrteei 0 + + mfspr r3,SPRN_L1CFG0 + rlwinm r5,r3,9,3 /* Extract cache block size */ + twlgti r5,1 /* Only 32 and 64 byte cache blocks + * are currently defined. + */ + li r4,32 + subfic r6,r5,2 /* r6 = log2(1KiB / cache block size) - + * log2(number of ways) + */ + slw r5,r4,r5 /* r5 = cache block size */ + + rlwinm r7,r3,0,0xff /* Extract number of KiB in the cache */ + mulli r7,r7,13 /* An 8-way cache will require 13 + * loads per set. + */ + slw r7,r7,r6 + + /* save off HID0 and set DCFA */ + mfspr r8,SPRN_HID0 + ori r9,r8,HID0_DCFA@l + mtspr SPRN_HID0,r9 + isync + + LOAD_REG_IMMEDIATE(r6, KERNELBASE) + mr r4, r6 + mtctr r7 + +1: lwz r3,0(r4) /* Load... */ + add r4,r4,r5 + bdnz 1b + + msync + mr r4, r6 + mtctr r7 + +1: dcbf 0,r4 /* ...and flush. */ + add r4,r4,r5 + bdnz 1b + + /* restore HID0 */ + mtspr SPRN_HID0,r8 + isync + + wrtee r10 + + blr + +has_L2_cache: + /* skip L2 cache on P2040/P2040E as they have no L2 cache */ + mfspr r3, SPRN_SVR + /* shift right by 8 bits and clear E bit of SVR */ + rlwinm r4, r3, 24, ~0x800 + + lis r3, SVR_P2040@h + ori r3, r3, SVR_P2040@l + cmpw r4, r3 + beq 1f + + li r3, 1 + blr +1: + li r3, 0 + blr + +/* flush backside L2 cache */ +flush_backside_L2_cache: + mflr r10 + bl has_L2_cache + mtlr r10 + cmpwi r3, 0 + beq 2f + + /* Flush the L2 cache */ + mfspr r3, SPRN_L2CSR0 + ori r3, r3, L2CSR0_L2FL@l + msync + isync + mtspr SPRN_L2CSR0,r3 + isync + + /* check if it is complete */ +1: mfspr r3,SPRN_L2CSR0 + andi. r3, r3, L2CSR0_L2FL@l + bne 1b +2: + blr + +_GLOBAL(cpu_down_flush_e500v2) + mflr r0 + bl flush_dcache_L1 + mtlr r0 + blr + +_GLOBAL(cpu_down_flush_e500mc) +_GLOBAL(cpu_down_flush_e5500) + mflr r0 + bl flush_dcache_L1 + bl flush_backside_L2_cache + mtlr r0 + blr + +/* L1 Data Cache of e6500 contains no modified data, no flush is required */ +_GLOBAL(cpu_down_flush_e6500) + blr diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S index 9c9b7411b..584e119fa 100644 --- a/arch/powerpc/kernel/cpu_setup_power.S +++ b/arch/powerpc/kernel/cpu_setup_power.S @@ -15,6 +15,7 @@ #include <asm/ppc_asm.h> #include <asm/asm-offsets.h> #include <asm/cache.h> +#include <asm/book3s/64/mmu-hash.h> /* Entry: r3 = crap, r4 = ptr to cputable entry * @@ -83,6 +84,39 @@ _GLOBAL(__restore_cpu_power8) mtlr r11 blr +_GLOBAL(__setup_cpu_power9) + mflr r11 + bl __init_FSCR + bl __init_hvmode_206 + mtlr r11 + beqlr + li r0,0 + mtspr SPRN_LPID,r0 + mfspr r3,SPRN_LPCR + ori r3, r3, LPCR_PECEDH + bl __init_LPCR + bl __init_HFSCR + bl __init_tlb_power9 + mtlr r11 + blr + +_GLOBAL(__restore_cpu_power9) + mflr r11 + bl __init_FSCR + mfmsr r3 + rldicl. r0,r3,4,63 + mtlr r11 + beqlr + li r0,0 + mtspr SPRN_LPID,r0 + mfspr r3,SPRN_LPCR + ori r3, r3, LPCR_PECEDH + bl __init_LPCR + bl __init_HFSCR + bl __init_tlb_power9 + mtlr r11 + blr + __init_hvmode_206: /* Disable CPU_FTR_HVMODE and exit if MSR:HV is not set */ mfmsr r3 @@ -139,7 +173,7 @@ __init_HFSCR: * (invalidate by congruence class). P7 has 128 CCs., P8 has 512. */ __init_tlb_power7: - li r6,128 + li r6,POWER7_TLB_SETS mtctr r6 li r7,0xc00 /* IS field = 0b11 */ ptesync @@ -150,7 +184,18 @@ __init_tlb_power7: 1: blr __init_tlb_power8: - li r6,512 + li r6,POWER8_TLB_SETS + mtctr r6 + li r7,0xc00 /* IS field = 0b11 */ + ptesync +2: tlbiel r7 + addi r7,r7,0x1000 + bdnz 2b + ptesync +1: blr + +__init_tlb_power9: + li r6,POWER9_TLB_SETS_HASH mtctr r6 li r7,0xc00 /* IS field = 0b11 */ ptesync diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 7d80bfdfb..6c662b8de 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -70,9 +70,12 @@ extern void __setup_cpu_power7(unsigned long offset, struct cpu_spec* spec); 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 __setup_cpu_power9(unsigned long offset, struct cpu_spec* spec); +extern void __restore_cpu_power9(void); extern void __restore_cpu_a2(void); extern void __flush_tlb_power7(unsigned int action); extern void __flush_tlb_power8(unsigned int action); +extern void __flush_tlb_power9(unsigned int action); 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 */ @@ -116,6 +119,11 @@ extern void __restore_cpu_e6500(void); #define COMMON_USER_PA6T (COMMON_USER_PPC64 | PPC_FEATURE_PA6T |\ PPC_FEATURE_TRUE_LE | \ PPC_FEATURE_HAS_ALTIVEC_COMP) +#define COMMON_USER_POWER9 COMMON_USER_POWER8 +#define COMMON_USER2_POWER9 (COMMON_USER2_POWER8 | \ + PPC_FEATURE2_ARCH_3_00 | \ + PPC_FEATURE2_HAS_IEEE128) + #ifdef CONFIG_PPC_BOOK3E_64 #define COMMON_USER_BOOKE (COMMON_USER_PPC64 | PPC_FEATURE_BOOKE) #else @@ -499,6 +507,25 @@ static struct cpu_spec __initdata cpu_specs[] = { .machine_check_early = __machine_check_early_realmode_p8, .platform = "power8", }, + { /* Power9 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x004e0000, + .cpu_name = "POWER9 (raw)", + .cpu_features = CPU_FTRS_POWER9, + .cpu_user_features = COMMON_USER_POWER9, + .cpu_user_features2 = COMMON_USER2_POWER9, + .mmu_features = MMU_FTRS_POWER9, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .pmc_type = PPC_PMC_IBM, + .oprofile_cpu_type = "ppc64/power9", + .oprofile_type = PPC_OPROFILE_INVALID, + .cpu_setup = __setup_cpu_power9, + .cpu_restore = __restore_cpu_power9, + .flush_tlb = __flush_tlb_power9, + .platform = "power9", + }, { /* Cell Broadband Engine */ .pvr_mask = 0xffff0000, .pvr_value = 0x00700000, @@ -2023,6 +2050,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_setup = __setup_cpu_e500v2, .machine_check = machine_check_e500, .platform = "ppc8548", + .cpu_down_flush = cpu_down_flush_e500v2, }, #else { /* e500mc */ @@ -2042,6 +2070,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_setup = __setup_cpu_e500mc, .machine_check = machine_check_e500mc, .platform = "ppce500mc", + .cpu_down_flush = cpu_down_flush_e500mc, }, #endif /* CONFIG_PPC_E500MC */ #endif /* CONFIG_PPC32 */ @@ -2066,6 +2095,7 @@ static struct cpu_spec __initdata cpu_specs[] = { #endif .machine_check = machine_check_e500mc, .platform = "ppce5500", + .cpu_down_flush = cpu_down_flush_e5500, }, { /* e6500 */ .pvr_mask = 0xffff0000, @@ -2088,6 +2118,7 @@ static struct cpu_spec __initdata cpu_specs[] = { #endif .machine_check = machine_check_e500mc, .platform = "ppce6500", + .cpu_down_flush = cpu_down_flush_e6500, }, #endif /* CONFIG_PPC_E500MC */ #ifdef CONFIG_PPC32 diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 40e4d4a27..675848479 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -268,13 +268,6 @@ static void *eeh_dump_pe_log(void *data, void *flag) struct eeh_dev *edev, *tmp; size_t *plen = flag; - /* If the PE's config space is blocked, 0xFF's will be - * returned. It's pointless to collect the log in this - * case. - */ - if (pe->state & EEH_PE_CFG_BLOCKED) - return NULL; - eeh_pe_for_each_dev(pe, edev, tmp) *plen += eeh_dump_dev_log(edev, pci_regs_buf + *plen, EEH_PCI_REGS_LOG_LEN - *plen); @@ -677,7 +670,7 @@ int eeh_pci_enable(struct eeh_pe *pe, int function) /* Check if the request is finished successfully */ if (active_flag) { rc = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC); - if (rc <= 0) + if (rc < 0) return rc; if (rc & active_flag) @@ -739,7 +732,7 @@ static void *eeh_restore_dev_state(void *data, void *userdata) } /** - * pcibios_set_pcie_slot_reset - Set PCI-E reset state + * pcibios_set_pcie_reset_state - Set PCI-E reset state * @dev: pci device struct * @state: reset state to enter * @@ -761,7 +754,8 @@ int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state stat case pcie_deassert_reset: eeh_ops->reset(pe, EEH_RESET_DEACTIVATE); eeh_unfreeze_pe(pe, false); - eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED); + if (!(pe->type & EEH_PE_VF)) + eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED); eeh_pe_dev_traverse(pe, eeh_restore_dev_state, dev); eeh_pe_state_clear(pe, EEH_PE_ISOLATED); break; @@ -769,14 +763,16 @@ int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state stat eeh_pe_state_mark_with_cfg(pe, EEH_PE_ISOLATED); eeh_ops->set_option(pe, EEH_OPT_FREEZE_PE); eeh_pe_dev_traverse(pe, eeh_disable_and_save_dev_state, dev); - eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED); + if (!(pe->type & EEH_PE_VF)) + eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED); eeh_ops->reset(pe, EEH_RESET_HOT); break; case pcie_warm_reset: eeh_pe_state_mark_with_cfg(pe, EEH_PE_ISOLATED); eeh_ops->set_option(pe, EEH_OPT_FREEZE_PE); eeh_pe_dev_traverse(pe, eeh_disable_and_save_dev_state, dev); - eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED); + if (!(pe->type & EEH_PE_VF)) + eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED); eeh_ops->reset(pe, EEH_RESET_FUNDAMENTAL); break; default: @@ -1072,7 +1068,7 @@ void eeh_add_device_early(struct pci_dn *pdn) struct pci_controller *phb; struct eeh_dev *edev = pdn_to_eeh_dev(pdn); - if (!edev || !eeh_enabled()) + if (!edev) return; if (!eeh_has_flag(EEH_PROBE_MODE_DEVTREE)) @@ -1243,6 +1239,14 @@ void eeh_remove_device(struct pci_dev *dev) * from the parent PE during the BAR resotre. */ edev->pdev = NULL; + + /* + * The flag "in_error" is used to trace EEH devices for VFs + * in error state or not. It's set in eeh_report_error(). If + * it's not set, eeh_report_{reset,resume}() won't be called + * for the VF EEH device. + */ + edev->in_error = false; dev->dev.archdata.edev = NULL; if (!(edev->pe->state & EEH_PE_KEEP)) eeh_rmv_from_parent_pe(edev); @@ -1537,6 +1541,17 @@ int eeh_pe_get_state(struct eeh_pe *pe) if (!eeh_ops || !eeh_ops->get_state) return -ENOENT; + /* + * If the parent PE is owned by the host kernel and is undergoing + * error recovery, we should return the PE state as temporarily + * unavailable so that the error recovery on the guest is suspended + * until the recovery completes on the host. + */ + if (pe->parent && + !(pe->state & EEH_PE_REMOVED) && + (pe->parent->state & (EEH_PE_ISOLATED | EEH_PE_RECOVERING))) + return EEH_PE_STATE_UNAVAIL; + result = eeh_ops->get_state(pe, NULL); rst_active = !!(result & EEH_STATE_RESET_ACTIVE); dma_en = !!(result & EEH_STATE_DMA_ENABLED); diff --git a/arch/powerpc/kernel/eeh_cache.c b/arch/powerpc/kernel/eeh_cache.c index a1e86e172..ddbcfab7e 100644 --- a/arch/powerpc/kernel/eeh_cache.c +++ b/arch/powerpc/kernel/eeh_cache.c @@ -195,8 +195,11 @@ static void __eeh_addr_cache_insert_dev(struct pci_dev *dev) return; } - /* Walk resources on this device, poke them into the tree */ - for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) { + /* + * Walk resources on this device, poke the first 7 (6 normal BAR and 1 + * ROM BAR) into the tree. + */ + for (i = 0; i <= PCI_ROM_RESOURCE; i++) { resource_size_t start = pci_resource_start(dev,i); resource_size_t end = pci_resource_end(dev,i); unsigned long flags = pci_resource_flags(dev,i); @@ -222,10 +225,6 @@ void eeh_addr_cache_insert_dev(struct pci_dev *dev) { unsigned long flags; - /* Ignore PCI bridges */ - if ((dev->class >> 16) == PCI_BASE_CLASS_BRIDGE) - return; - spin_lock_irqsave(&pci_io_addr_cache_root.piar_lock, flags); __eeh_addr_cache_insert_dev(dev); spin_unlock_irqrestore(&pci_io_addr_cache_root.piar_lock, flags); diff --git a/arch/powerpc/kernel/eeh_dev.c b/arch/powerpc/kernel/eeh_dev.c index aabba94ff..7815095fe 100644 --- a/arch/powerpc/kernel/eeh_dev.c +++ b/arch/powerpc/kernel/eeh_dev.c @@ -67,6 +67,7 @@ void *eeh_dev_init(struct pci_dn *pdn, void *data) edev->pdn = pdn; edev->phb = phb; INIT_LIST_HEAD(&edev->list); + INIT_LIST_HEAD(&edev->rmv_list); return NULL; } diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 650cfb31e..31e4c7e1a 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -34,6 +34,11 @@ #include <asm/prom.h> #include <asm/rtas.h> +struct eeh_rmv_data { + struct list_head edev_list; + int removed; +}; + /** * eeh_pcid_name - Retrieve name of PCI device driver * @pdev: PCI device @@ -166,6 +171,16 @@ static void *eeh_dev_save_state(void *data, void *userdata) if (!edev) return NULL; + /* + * We cannot access the config space on some adapters. + * Otherwise, it will cause fenced PHB. We don't save + * the content in their config space and will restore + * from the initial config space saved when the EEH + * device is created. + */ + if (edev->pe && (edev->pe->state & EEH_PE_CFG_RESTRICTED)) + return NULL; + pdev = eeh_dev_to_pci_dev(edev); if (!pdev) return NULL; @@ -190,7 +205,7 @@ static void *eeh_report_error(void *data, void *userdata) enum pci_ers_result rc, *res = userdata; struct pci_driver *driver; - if (!dev || eeh_dev_removed(edev)) + if (!dev || eeh_dev_removed(edev) || eeh_pe_passed(edev->pe)) return NULL; dev->error_state = pci_channel_io_frozen; @@ -211,6 +226,7 @@ static void *eeh_report_error(void *data, void *userdata) if (rc == PCI_ERS_RESULT_NEED_RESET) *res = rc; if (*res == PCI_ERS_RESULT_NONE) *res = rc; + edev->in_error = true; eeh_pcid_put(dev); return NULL; } @@ -231,7 +247,7 @@ static void *eeh_report_mmio_enabled(void *data, void *userdata) enum pci_ers_result rc, *res = userdata; struct pci_driver *driver; - if (!dev || eeh_dev_removed(edev)) + if (!dev || eeh_dev_removed(edev) || eeh_pe_passed(edev->pe)) return NULL; driver = eeh_pcid_get(dev); @@ -271,7 +287,7 @@ static void *eeh_report_reset(void *data, void *userdata) enum pci_ers_result rc, *res = userdata; struct pci_driver *driver; - if (!dev || eeh_dev_removed(edev)) + if (!dev || eeh_dev_removed(edev) || eeh_pe_passed(edev->pe)) return NULL; dev->error_state = pci_channel_io_normal; @@ -282,7 +298,8 @@ static void *eeh_report_reset(void *data, void *userdata) if (!driver->err_handler || !driver->err_handler->slot_reset || - (edev->mode & EEH_DEV_NO_HANDLER)) { + (edev->mode & EEH_DEV_NO_HANDLER) || + (!edev->in_error)) { eeh_pcid_put(dev); return NULL; } @@ -305,6 +322,19 @@ static void *eeh_dev_restore_state(void *data, void *userdata) if (!edev) return NULL; + /* + * The content in the config space isn't saved because + * the blocked config space on some adapters. We have + * to restore the initial saved config space when the + * EEH device is created. + */ + if (edev->pe && (edev->pe->state & EEH_PE_CFG_RESTRICTED)) { + if (list_is_last(&edev->list, &edev->pe->edevs)) + eeh_pe_restore_bars(edev->pe); + + return NULL; + } + pdev = eeh_dev_to_pci_dev(edev); if (!pdev) return NULL; @@ -326,20 +356,23 @@ static void *eeh_report_resume(void *data, void *userdata) { struct eeh_dev *edev = (struct eeh_dev *)data; struct pci_dev *dev = eeh_dev_to_pci_dev(edev); + bool was_in_error; struct pci_driver *driver; - if (!dev || eeh_dev_removed(edev)) + if (!dev || eeh_dev_removed(edev) || eeh_pe_passed(edev->pe)) return NULL; dev->error_state = pci_channel_io_normal; driver = eeh_pcid_get(dev); if (!driver) return NULL; + was_in_error = edev->in_error; + edev->in_error = false; eeh_enable_irq(dev); if (!driver->err_handler || !driver->err_handler->resume || - (edev->mode & EEH_DEV_NO_HANDLER)) { + (edev->mode & EEH_DEV_NO_HANDLER) || !was_in_error) { edev->mode &= ~EEH_DEV_NO_HANDLER; eeh_pcid_put(dev); return NULL; @@ -365,7 +398,7 @@ static void *eeh_report_failure(void *data, void *userdata) struct pci_dev *dev = eeh_dev_to_pci_dev(edev); struct pci_driver *driver; - if (!dev || eeh_dev_removed(edev)) + if (!dev || eeh_dev_removed(edev) || eeh_pe_passed(edev->pe)) return NULL; dev->error_state = pci_channel_io_perm_failure; @@ -386,12 +419,40 @@ static void *eeh_report_failure(void *data, void *userdata) return NULL; } +static void *eeh_add_virt_device(void *data, void *userdata) +{ + struct pci_driver *driver; + struct eeh_dev *edev = (struct eeh_dev *)data; + struct pci_dev *dev = eeh_dev_to_pci_dev(edev); + struct pci_dn *pdn = eeh_dev_to_pdn(edev); + + if (!(edev->physfn)) { + pr_warn("%s: EEH dev %04x:%02x:%02x.%01x not for VF\n", + __func__, edev->phb->global_number, pdn->busno, + PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn)); + return NULL; + } + + driver = eeh_pcid_get(dev); + if (driver) { + eeh_pcid_put(dev); + if (driver->err_handler) + return NULL; + } + +#ifdef CONFIG_PPC_POWERNV + pci_iov_add_virtfn(edev->physfn, pdn->vf_index, 0); +#endif + return NULL; +} + static void *eeh_rmv_device(void *data, void *userdata) { struct pci_driver *driver; struct eeh_dev *edev = (struct eeh_dev *)data; struct pci_dev *dev = eeh_dev_to_pci_dev(edev); - int *removed = (int *)userdata; + struct eeh_rmv_data *rmv_data = (struct eeh_rmv_data *)userdata; + int *removed = rmv_data ? &rmv_data->removed : NULL; /* * Actually, we should remove the PCI bridges as well. @@ -416,7 +477,11 @@ static void *eeh_rmv_device(void *data, void *userdata) driver = eeh_pcid_get(dev); if (driver) { eeh_pcid_put(dev); - if (driver->err_handler && + if (removed && + eeh_pe_passed(edev->pe)) + return NULL; + if (removed && + driver->err_handler && driver->err_handler->error_detected && driver->err_handler->slot_reset) return NULL; @@ -427,11 +492,29 @@ static void *eeh_rmv_device(void *data, void *userdata) pci_name(dev)); edev->bus = dev->bus; edev->mode |= EEH_DEV_DISCONNECTED; - (*removed)++; + if (removed) + (*removed)++; - pci_lock_rescan_remove(); - pci_stop_and_remove_bus_device(dev); - pci_unlock_rescan_remove(); + if (edev->physfn) { +#ifdef CONFIG_PPC_POWERNV + struct pci_dn *pdn = eeh_dev_to_pdn(edev); + + pci_iov_remove_virtfn(edev->physfn, pdn->vf_index, 0); + edev->pdev = NULL; + + /* + * We have to set the VF PE number to invalid one, which is + * required to plug the VF successfully. + */ + pdn->pe_number = IODA_INVALID_PE; +#endif + if (rmv_data) + list_add(&edev->rmv_list, &rmv_data->edev_list); + } else { + pci_lock_rescan_remove(); + pci_stop_and_remove_bus_device(dev); + pci_unlock_rescan_remove(); + } return NULL; } @@ -504,9 +587,6 @@ int eeh_pe_reset_and_recover(struct eeh_pe *pe) /* Save states */ eeh_pe_dev_traverse(pe, eeh_dev_save_state, NULL); - /* Report error */ - eeh_pe_dev_traverse(pe, eeh_report_error, &result); - /* Issue reset */ ret = eeh_reset_pe(pe); if (ret) { @@ -545,11 +625,13 @@ int eeh_pe_reset_and_recover(struct eeh_pe *pe) * During the reset, udev might be invoked because those affected * PCI devices will be removed and then added. */ -static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus) +static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus, + struct eeh_rmv_data *rmv_data) { struct pci_bus *frozen_bus = eeh_pe_bus_get(pe); struct timeval tstamp; - int cnt, rc, removed = 0; + int cnt, rc; + struct eeh_dev *edev; /* pcibios will clear the counter; save the value */ cnt = pe->freeze_count; @@ -563,12 +645,16 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus) */ eeh_pe_state_mark(pe, EEH_PE_KEEP); if (bus) { - eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); - pci_lock_rescan_remove(); - pcibios_remove_pci_devices(bus); - pci_unlock_rescan_remove(); + if (pe->type & EEH_PE_VF) { + eeh_pe_dev_traverse(pe, eeh_rmv_device, NULL); + } else { + eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); + pci_lock_rescan_remove(); + pcibios_remove_pci_devices(bus); + pci_unlock_rescan_remove(); + } } else if (frozen_bus) { - eeh_pe_dev_traverse(pe, eeh_rmv_device, &removed); + eeh_pe_dev_traverse(pe, eeh_rmv_device, &rmv_data); } /* @@ -610,14 +696,22 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus) * PE. We should disconnect it so the binding can be * rebuilt when adding PCI devices. */ + edev = list_first_entry(&pe->edevs, struct eeh_dev, list); eeh_pe_traverse(pe, eeh_pe_detach_dev, NULL); - pcibios_add_pci_devices(bus); - } else if (frozen_bus && removed) { + if (pe->type & EEH_PE_VF) + eeh_add_virt_device(edev, NULL); + else + pcibios_add_pci_devices(bus); + } else if (frozen_bus && rmv_data->removed) { pr_info("EEH: Sleep 5s ahead of partial hotplug\n"); ssleep(5); + edev = list_first_entry(&pe->edevs, struct eeh_dev, list); eeh_pe_traverse(pe, eeh_pe_detach_dev, NULL); - pcibios_add_pci_devices(frozen_bus); + if (pe->type & EEH_PE_VF) + eeh_add_virt_device(edev, NULL); + else + pcibios_add_pci_devices(frozen_bus); } eeh_pe_state_clear(pe, EEH_PE_KEEP); @@ -636,8 +730,10 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus) static void eeh_handle_normal_event(struct eeh_pe *pe) { struct pci_bus *frozen_bus; + struct eeh_dev *edev, *tmp; int rc = 0; enum pci_ers_result result = PCI_ERS_RESULT_NONE; + struct eeh_rmv_data rmv_data = {LIST_HEAD_INIT(rmv_data.edev_list), 0}; frozen_bus = eeh_pe_bus_get(pe); if (!frozen_bus) { @@ -692,7 +788,7 @@ static void eeh_handle_normal_event(struct eeh_pe *pe) */ if (result == PCI_ERS_RESULT_NONE) { pr_info("EEH: Reset with hotplug activity\n"); - rc = eeh_reset_device(pe, frozen_bus); + rc = eeh_reset_device(pe, frozen_bus, NULL); if (rc) { pr_warn("%s: Unable to reset, err=%d\n", __func__, rc); @@ -744,7 +840,7 @@ static void eeh_handle_normal_event(struct eeh_pe *pe) /* If any device called out for a reset, then reset the slot */ if (result == PCI_ERS_RESULT_NEED_RESET) { pr_info("EEH: Reset without hotplug activity\n"); - rc = eeh_reset_device(pe, NULL); + rc = eeh_reset_device(pe, NULL, &rmv_data); if (rc) { pr_warn("%s: Cannot reset, err=%d\n", __func__, rc); @@ -764,6 +860,15 @@ static void eeh_handle_normal_event(struct eeh_pe *pe) goto hard_fail; } + /* + * For those hot removed VFs, we should add back them after PF get + * recovered properly. + */ + list_for_each_entry_safe(edev, tmp, &rmv_data.edev_list, rmv_list) { + eeh_add_virt_device(edev, NULL); + list_del(&edev->rmv_list); + } + /* Tell all device drivers that they can resume operations */ pr_info("EEH: Notify device driver to resume\n"); eeh_pe_dev_traverse(pe, eeh_report_resume, NULL); @@ -803,12 +908,17 @@ perm_error: * the their PCI config any more. */ if (frozen_bus) { - eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); - eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED); + if (pe->type & EEH_PE_VF) { + eeh_pe_dev_traverse(pe, eeh_rmv_device, NULL); + eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED); + } else { + eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); + eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED); - pci_lock_rescan_remove(); - pcibios_remove_pci_devices(frozen_bus); - pci_unlock_rescan_remove(); + pci_lock_rescan_remove(); + pcibios_remove_pci_devices(frozen_bus); + pci_unlock_rescan_remove(); + } } } diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index 98f81800e..eea48d8ba 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -299,7 +299,10 @@ static struct eeh_pe *eeh_pe_get_parent(struct eeh_dev *edev) * EEH device already having associated PE, but * the direct parent EEH device doesn't have yet. */ - pdn = pdn ? pdn->parent : NULL; + if (edev->physfn) + pdn = pci_get_pdn(edev->physfn); + else + pdn = pdn ? pdn->parent : NULL; while (pdn) { /* We're poking out of PCI territory */ parent = pdn_to_eeh_dev(pdn); @@ -382,7 +385,10 @@ int eeh_add_to_parent_pe(struct eeh_dev *edev) } /* Create a new EEH PE */ - pe = eeh_pe_alloc(edev->phb, EEH_PE_DEVICE); + if (edev->physfn) + pe = eeh_pe_alloc(edev->phb, EEH_PE_VF); + else + pe = eeh_pe_alloc(edev->phb, EEH_PE_DEVICE); if (!pe) { pr_err("%s: out of memory!\n", __func__); return -ENOMEM; @@ -920,25 +926,21 @@ const char *eeh_pe_loc_get(struct eeh_pe *pe) */ struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe) { - struct pci_bus *bus = NULL; struct eeh_dev *edev; struct pci_dev *pdev; - if (pe->type & EEH_PE_PHB) { - bus = pe->phb->bus; - } else if (pe->type & EEH_PE_BUS || - pe->type & EEH_PE_DEVICE) { - if (pe->state & EEH_PE_PRI_BUS) { - bus = pe->bus; - goto out; - } + if (pe->type & EEH_PE_PHB) + return pe->phb->bus; - edev = list_first_entry(&pe->edevs, struct eeh_dev, list); - pdev = eeh_dev_to_pci_dev(edev); - if (pdev) - bus = pdev->bus; - } + /* The primary bus might be cached during probe time */ + if (pe->state & EEH_PE_PRI_BUS) + return pe->bus; -out: - return bus; + /* Retrieve the parent PCI bus of first (top) PCI device */ + edev = list_first_entry_or_null(&pe->edevs, struct eeh_dev, list); + pdev = eeh_dev_to_pci_dev(edev); + if (pdev) + return pdev->bus; + + return NULL; } diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 0d525ce37..9916d150b 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -210,7 +210,29 @@ system_call: /* label this so stack traces look sane */ li r11,-MAX_ERRNO andi. r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK) bne- syscall_exit_work - cmpld r3,r11 + + andi. r0,r8,MSR_FP + beq 2f +#ifdef CONFIG_ALTIVEC + andis. r0,r8,MSR_VEC@h + bne 3f +#endif +2: addi r3,r1,STACK_FRAME_OVERHEAD +#ifdef CONFIG_PPC_BOOK3S + mtmsrd r10,1 /* Restore RI */ +#endif + bl restore_math +#ifdef CONFIG_PPC_BOOK3S + ld r10,PACAKMSR(r13) + li r9,MSR_RI + andc r11,r10,r9 /* Re-clear RI */ + mtmsrd r11,1 +#endif + ld r8,_MSR(r1) + ld r3,RESULT(r1) + li r11,-MAX_ERRNO + +3: cmpld r3,r11 ld r5,_CCR(r1) bge- syscall_error .Lsyscall_error_cont: @@ -602,8 +624,8 @@ _GLOBAL(ret_from_except_lite) /* Check current_thread_info()->flags */ andi. r0,r4,_TIF_USER_WORK_MASK -#ifdef CONFIG_PPC_BOOK3E bne 1f +#ifdef CONFIG_PPC_BOOK3E /* * Check to see if the dbcr0 register is set up to debug. * Use the internal debug mode bit to do this. @@ -618,7 +640,9 @@ _GLOBAL(ret_from_except_lite) mtspr SPRN_DBSR,r10 b restore #else - beq restore + addi r3,r1,STACK_FRAME_OVERHEAD + bl restore_math + b restore #endif 1: andi. r0,r4,_TIF_NEED_RESCHED beq 2f @@ -1143,8 +1167,12 @@ _GLOBAL(enter_prom) #ifdef CONFIG_DYNAMIC_FTRACE _GLOBAL(mcount) _GLOBAL(_mcount) - blr + mflr r12 + mtctr r12 + mtlr r0 + bctr +#ifndef CC_USING_MPROFILE_KERNEL _GLOBAL_TOC(ftrace_caller) /* Taken from output of objdump from lib64/glibc */ mflr r3 @@ -1166,6 +1194,115 @@ _GLOBAL(ftrace_graph_stub) ld r0, 128(r1) mtlr r0 addi r1, r1, 112 + +#else /* CC_USING_MPROFILE_KERNEL */ +/* + * + * ftrace_caller() is the function that replaces _mcount() when ftrace is + * active. + * + * We arrive here after a function A calls function B, and we are the trace + * function for B. When we enter r1 points to A's stack frame, B has not yet + * had a chance to allocate one yet. + * + * Additionally r2 may point either to the TOC for A, or B, depending on + * whether B did a TOC setup sequence before calling us. + * + * On entry the LR points back to the _mcount() call site, and r0 holds the + * saved LR as it was on entry to B, ie. the original return address at the + * call site in A. + * + * Our job is to save the register state into a struct pt_regs (on the stack) + * and then arrange for the ftrace function to be called. + */ +_GLOBAL(ftrace_caller) + /* Save the original return address in A's stack frame */ + std r0,LRSAVE(r1) + + /* Create our stack frame + pt_regs */ + stdu r1,-SWITCH_FRAME_SIZE(r1) + + /* Save all gprs to pt_regs */ + SAVE_8GPRS(0,r1) + SAVE_8GPRS(8,r1) + SAVE_8GPRS(16,r1) + SAVE_8GPRS(24,r1) + + /* Load special regs for save below */ + mfmsr r8 + mfctr r9 + mfxer r10 + mfcr r11 + + /* Get the _mcount() call site out of LR */ + mflr r7 + /* Save it as pt_regs->nip & pt_regs->link */ + std r7, _NIP(r1) + std r7, _LINK(r1) + + /* Save callee's TOC in the ABI compliant location */ + std r2, 24(r1) + ld r2,PACATOC(r13) /* get kernel TOC in r2 */ + + addis r3,r2,function_trace_op@toc@ha + addi r3,r3,function_trace_op@toc@l + ld r5,0(r3) + + /* Calculate ip from nip-4 into r3 for call below */ + subi r3, r7, MCOUNT_INSN_SIZE + + /* Put the original return address in r4 as parent_ip */ + mr r4, r0 + + /* Save special regs */ + std r8, _MSR(r1) + std r9, _CTR(r1) + std r10, _XER(r1) + std r11, _CCR(r1) + + /* Load &pt_regs in r6 for call below */ + addi r6, r1 ,STACK_FRAME_OVERHEAD + + /* ftrace_call(r3, r4, r5, r6) */ +.globl ftrace_call +ftrace_call: + bl ftrace_stub + nop + + /* Load ctr with the possibly modified NIP */ + ld r3, _NIP(r1) + mtctr r3 + + /* Restore gprs */ + REST_8GPRS(0,r1) + REST_8GPRS(8,r1) + REST_8GPRS(16,r1) + REST_8GPRS(24,r1) + + /* Restore callee's TOC */ + ld r2, 24(r1) + + /* Pop our stack frame */ + addi r1, r1, SWITCH_FRAME_SIZE + + /* Restore original LR for return to B */ + ld r0, LRSAVE(r1) + mtlr r0 + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + stdu r1, -112(r1) +.globl ftrace_graph_call +ftrace_graph_call: + b ftrace_graph_stub +_GLOBAL(ftrace_graph_stub) + addi r1, r1, 112 +#endif + + ld r0,LRSAVE(r1) /* restore callee's lr at _mcount site */ + mtlr r0 + bctr /* jump after _mcount site */ +#endif /* CC_USING_MPROFILE_KERNEL */ + _GLOBAL(ftrace_stub) blr #else @@ -1198,6 +1335,7 @@ _GLOBAL(ftrace_stub) #endif /* CONFIG_DYNAMIC_FTRACE */ #ifdef CONFIG_FUNCTION_GRAPH_TRACER +#ifndef CC_USING_MPROFILE_KERNEL _GLOBAL(ftrace_graph_caller) /* load r4 with local address */ ld r4, 128(r1) @@ -1222,6 +1360,56 @@ _GLOBAL(ftrace_graph_caller) addi r1, r1, 112 blr +#else /* CC_USING_MPROFILE_KERNEL */ +_GLOBAL(ftrace_graph_caller) + /* with -mprofile-kernel, parameter regs are still alive at _mcount */ + std r10, 104(r1) + std r9, 96(r1) + std r8, 88(r1) + std r7, 80(r1) + std r6, 72(r1) + std r5, 64(r1) + std r4, 56(r1) + std r3, 48(r1) + + /* Save callee's TOC in the ABI compliant location */ + std r2, 24(r1) + ld r2, PACATOC(r13) /* get kernel TOC in r2 */ + + mfctr r4 /* ftrace_caller has moved local addr here */ + std r4, 40(r1) + mflr r3 /* ftrace_caller has restored LR from stack */ + subi r4, r4, MCOUNT_INSN_SIZE + + bl prepare_ftrace_return + nop + + /* + * prepare_ftrace_return gives us the address we divert to. + * Change the LR to this. + */ + mtlr r3 + + ld r0, 40(r1) + mtctr r0 + ld r10, 104(r1) + ld r9, 96(r1) + ld r8, 88(r1) + ld r7, 80(r1) + ld r6, 72(r1) + ld r5, 64(r1) + ld r4, 56(r1) + ld r3, 48(r1) + + /* Restore callee's TOC */ + ld r2, 24(r1) + + addi r1, r1, 112 + mflr r0 + std r0, LRSAVE(r1) + bctr +#endif /* CC_USING_MPROFILE_KERNEL */ + _GLOBAL(return_to_handler) /* need to save return values */ std r4, -32(r1) diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 7716cebf4..2b66f25d4 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -953,11 +953,6 @@ hv_facility_unavailable_relon_trampoline: #endif STD_RELON_EXCEPTION_PSERIES(0x5700, 0x1700, altivec_assist) - /* Other future vectors */ - .align 7 - .globl __end_interrupts -__end_interrupts: - .align 7 system_call_entry: b system_call_common @@ -1244,6 +1239,17 @@ __end_handlers: STD_RELON_EXCEPTION_PSERIES_OOL(0xf60, facility_unavailable) STD_RELON_EXCEPTION_HV_OOL(0xf80, hv_facility_unavailable) + /* + * The __end_interrupts marker must be past the out-of-line (OOL) + * handlers, so that they are copied to real address 0x100 when running + * a relocatable kernel. This ensures they can be reached from the short + * trampoline handlers (like 0x4f00, 0x4f20, etc.) which branch + * directly, without using LOAD_HANDLER(). + */ + .align 7 + .globl __end_interrupts +__end_interrupts: + #if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) /* * Data area reserved for FWNMI option. diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S index 2117eaca3..15da2b5df 100644 --- a/arch/powerpc/kernel/fpu.S +++ b/arch/powerpc/kernel/fpu.S @@ -130,6 +130,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX) or r12,r12,r4 std r12,_MSR(r1) #endif + /* Don't care if r4 overflows, this is desired behaviour */ + lbz r4,THREAD_LOAD_FP(r5) + addi r4,r4,1 + stb r4,THREAD_LOAD_FP(r5) addi r10,r5,THREAD_FPSTATE lfd fr0,FPSTATE_FPSCR(r10) MTFSF_L(fr0) @@ -139,33 +143,20 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX) blr /* - * __giveup_fpu(tsk) - * Disable FP for the task given as the argument, - * and save the floating-point registers in its thread_struct. + * save_fpu(tsk) + * Save the floating-point registers in its thread_struct. * Enables the FPU for use in the kernel on return. */ -_GLOBAL(__giveup_fpu) +_GLOBAL(save_fpu) addi r3,r3,THREAD /* want THREAD of task */ PPC_LL r6,THREAD_FPSAVEAREA(r3) PPC_LL r5,PT_REGS(r3) PPC_LCMPI 0,r6,0 bne 2f addi r6,r3,THREAD_FPSTATE -2: PPC_LCMPI 0,r5,0 - SAVE_32FPVSRS(0, R4, R6) +2: SAVE_32FPVSRS(0, R4, R6) mffs fr0 stfd fr0,FPSTATE_FPSCR(r6) - beq 1f - PPC_LL r4,_MSR-STACK_FRAME_OVERHEAD(r5) - li r3,MSR_FP|MSR_FE0|MSR_FE1 -#ifdef CONFIG_VSX -BEGIN_FTR_SECTION - oris r3,r3,MSR_VSX@h -END_FTR_SECTION_IFSET(CPU_FTR_VSX) -#endif - andc r4,r4,r3 /* disable FP for previous task */ - PPC_STL r4,_MSR-STACK_FRAME_OVERHEAD(r5) -1: blr /* diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c index 44d4d8eb3..9dac18dab 100644 --- a/arch/powerpc/kernel/ftrace.c +++ b/arch/powerpc/kernel/ftrace.c @@ -61,8 +61,11 @@ ftrace_modify_code(unsigned long ip, unsigned int old, unsigned int new) return -EFAULT; /* Make sure it is what we expect it to be */ - if (replaced != old) + if (replaced != old) { + pr_err("%p: replaced (%#x) != old (%#x)", + (void *)ip, replaced, old); return -EINVAL; + } /* replace the text with the new text */ if (patch_instruction((unsigned int *)ip, new)) @@ -106,14 +109,15 @@ static int __ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr) { - unsigned int op; - unsigned long entry, ptr; + unsigned long entry, ptr, tramp; unsigned long ip = rec->ip; - void *tramp; + unsigned int op, pop; /* read where this goes */ - if (probe_kernel_read(&op, (void *)ip, sizeof(int))) + if (probe_kernel_read(&op, (void *)ip, sizeof(int))) { + pr_err("Fetching opcode failed.\n"); return -EFAULT; + } /* Make sure that that this is still a 24bit jump */ if (!is_bl_op(op)) { @@ -122,14 +126,9 @@ __ftrace_make_nop(struct module *mod, } /* lets find where the pointer goes */ - tramp = (void *)find_bl_target(ip, op); - - pr_devel("ip:%lx jumps to %p", ip, tramp); + tramp = find_bl_target(ip, op); - if (!is_module_trampoline(tramp)) { - pr_err("Not a trampoline\n"); - return -EINVAL; - } + pr_devel("ip:%lx jumps to %lx", ip, tramp); if (module_trampoline_target(mod, tramp, &ptr)) { pr_err("Failed to get trampoline target\n"); @@ -158,10 +157,42 @@ __ftrace_make_nop(struct module *mod, * * Use a b +8 to jump over the load. */ - op = 0x48000008; /* b +8 */ - if (patch_instruction((unsigned int *)ip, op)) + pop = PPC_INST_BRANCH | 8; /* b +8 */ + + /* + * Check what is in the next instruction. We can see ld r2,40(r1), but + * on first pass after boot we will see mflr r0. + */ + if (probe_kernel_read(&op, (void *)(ip+4), MCOUNT_INSN_SIZE)) { + pr_err("Fetching op failed.\n"); + return -EFAULT; + } + + if (op != PPC_INST_LD_TOC) { + unsigned int inst; + + if (probe_kernel_read(&inst, (void *)(ip - 4), 4)) { + pr_err("Fetching instruction at %lx failed.\n", ip - 4); + return -EFAULT; + } + + /* We expect either a mlfr r0, or a std r0, LRSAVE(r1) */ + if (inst != PPC_INST_MFLR && inst != PPC_INST_STD_LR) { + pr_err("Unexpected instructions around bl _mcount\n" + "when enabling dynamic ftrace!\t" + "(%08x,bl,%08x)\n", inst, op); + return -EINVAL; + } + + /* When using -mkernel_profile there is no load to jump over */ + pop = PPC_INST_NOP; + } + + if (patch_instruction((unsigned int *)ip, pop)) { + pr_err("Patching NOP failed.\n"); return -EPERM; + } return 0; } @@ -287,16 +318,15 @@ int ftrace_make_nop(struct module *mod, #ifdef CONFIG_MODULES #ifdef CONFIG_PPC64 +/* + * Examine the existing instructions for __ftrace_make_call. + * They should effectively be a NOP, and follow formal constraints, + * depending on the ABI. Return false if they don't. + */ +#ifndef CC_USING_MPROFILE_KERNEL static int -__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) +expected_nop_sequence(void *ip, unsigned int op0, unsigned int op1) { - unsigned int op[2]; - void *ip = (void *)rec->ip; - - /* read where this goes */ - if (probe_kernel_read(op, ip, sizeof(op))) - return -EFAULT; - /* * We expect to see: * @@ -306,8 +336,34 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) * The load offset is different depending on the ABI. For simplicity * just mask it out when doing the compare. */ - if ((op[0] != 0x48000008) || ((op[1] & 0xffff0000) != 0xe8410000)) { - pr_err("Unexpected call sequence: %x %x\n", op[0], op[1]); + if ((op0 != 0x48000008) || ((op1 & 0xffff0000) != 0xe8410000)) + return 0; + return 1; +} +#else +static int +expected_nop_sequence(void *ip, unsigned int op0, unsigned int op1) +{ + /* look for patched "NOP" on ppc64 with -mprofile-kernel */ + if (op0 != PPC_INST_NOP) + return 0; + return 1; +} +#endif + +static int +__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned int op[2]; + void *ip = (void *)rec->ip; + + /* read where this goes */ + if (probe_kernel_read(op, ip, sizeof(op))) + return -EFAULT; + + if (!expected_nop_sequence(ip, op[0], op[1])) { + pr_err("Unexpected call sequence at %p: %x %x\n", + ip, op[0], op[1]); return -EINVAL; } @@ -330,7 +386,16 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) return 0; } -#else + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, + unsigned long addr) +{ + return ftrace_make_call(rec, addr); +} +#endif + +#else /* !CONFIG_PPC64: */ static int __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) { @@ -455,20 +520,13 @@ void ftrace_replace_code(int enable) } } +/* + * Use the default ftrace_modify_all_code, but without + * stop_machine(). + */ void arch_ftrace_update_code(int command) { - if (command & FTRACE_UPDATE_CALLS) - ftrace_replace_code(1); - else if (command & FTRACE_DISABLE_CALLS) - ftrace_replace_code(0); - - if (command & FTRACE_UPDATE_TRACE_FUNC) - ftrace_update_ftrace_func(ftrace_trace_function); - - if (command & FTRACE_START_FUNC_RET) - ftrace_enable_ftrace_graph_caller(); - else if (command & FTRACE_STOP_FUNC_RET) - ftrace_disable_ftrace_graph_caller(); + ftrace_modify_all_code(command); } int __init ftrace_dyn_arch_init(void) diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S index b5061abbd..9cdf5c71e 100644 --- a/arch/powerpc/kernel/head_44x.S +++ b/arch/powerpc/kernel/head_44x.S @@ -806,7 +806,7 @@ _GLOBAL(set_context) _GLOBAL(init_cpu_state) mflr r22 #ifdef CONFIG_PPC_47x - /* We use the PVR to differenciate 44x cores from 476 */ + /* We use the PVR to differentiate 44x cores from 476 */ mfspr r3,SPRN_PVR srwi r3,r3,16 cmplwi cr0,r3,PVR_476FPE@h diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 1b7795607..4286775cb 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -40,6 +40,8 @@ #include <asm/kvm_book3s_asm.h> #include <asm/ptrace.h> #include <asm/hw_irq.h> +#include <asm/cputhreads.h> +#include <asm/ppc-opcode.h> /* The physical memory is laid out such that the secondary processor * spin code sits at 0x0000...0x00ff. On server, the vectors follow @@ -181,6 +183,64 @@ exception_marker: #endif #ifdef CONFIG_PPC_BOOK3E +/* + * The booting_thread_hwid holds the thread id we want to boot in cpu + * hotplug case. It is set by cpu hotplug code, and is invalid by default. + * The thread id is the same as the initial value of SPRN_PIR[THREAD_ID] + * bit field. + */ + .globl booting_thread_hwid +booting_thread_hwid: + .long INVALID_THREAD_HWID + .align 3 +/* + * start a thread in the same core + * input parameters: + * r3 = the thread physical id + * r4 = the entry point where thread starts + */ +_GLOBAL(book3e_start_thread) + LOAD_REG_IMMEDIATE(r5, MSR_KERNEL) + cmpi 0, r3, 0 + beq 10f + cmpi 0, r3, 1 + beq 11f + /* If the thread id is invalid, just exit. */ + b 13f +10: + MTTMR(TMRN_IMSR0, 5) + MTTMR(TMRN_INIA0, 4) + b 12f +11: + MTTMR(TMRN_IMSR1, 5) + MTTMR(TMRN_INIA1, 4) +12: + isync + li r6, 1 + sld r6, r6, r3 + mtspr SPRN_TENS, r6 +13: + blr + +/* + * stop a thread in the same core + * input parameter: + * r3 = the thread physical id + */ +_GLOBAL(book3e_stop_thread) + cmpi 0, r3, 0 + beq 10f + cmpi 0, r3, 1 + beq 10f + /* If the thread id is invalid, just exit. */ + b 13f +10: + li r4, 1 + sld r4, r4, r3 + mtspr SPRN_TENC, r4 +13: + blr + _GLOBAL(fsl_secondary_thread_init) mfspr r4,SPRN_BUCSR @@ -261,6 +321,44 @@ _GLOBAL(generic_secondary_smp_init) mr r3,r24 mr r4,r25 bl book3e_secondary_core_init + +/* + * After common core init has finished, check if the current thread is the + * one we wanted to boot. If not, start the specified thread and stop the + * current thread. + */ + LOAD_REG_ADDR(r4, booting_thread_hwid) + lwz r3, 0(r4) + li r5, INVALID_THREAD_HWID + cmpw r3, r5 + beq 20f + + /* + * The value of booting_thread_hwid has been stored in r3, + * so make it invalid. + */ + stw r5, 0(r4) + + /* + * Get the current thread id and check if it is the one we wanted. + * If not, start the one specified in booting_thread_hwid and stop + * the current thread. + */ + mfspr r8, SPRN_TIR + cmpw r3, r8 + beq 20f + + /* start the specified thread */ + LOAD_REG_ADDR(r5, fsl_secondary_thread_init) + ld r4, 0(r5) + bl book3e_start_thread + + /* stop the current thread */ + mr r3, r8 + bl book3e_stop_thread +10: + b 10b +20: #endif generic_secondary_common_init: diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index 78c1eba4c..80c694723 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -329,7 +329,7 @@ InstructionTLBMiss: /* If we are faulting a kernel address, we have to use the * kernel page tables. */ -#ifdef CONFIG_MODULES +#if defined(CONFIG_MODULES) || defined (CONFIG_DEBUG_PAGEALLOC) /* Only modules will cause ITLB Misses as we always * pin the first 8MB of kernel memory */ mfspr r11, SPRN_SRR0 /* Get effective address of fault */ @@ -385,27 +385,26 @@ InstructionTLBMiss: . = 0x1200 DataStoreTLBMiss: -#ifdef CONFIG_8xx_CPU6 mtspr SPRN_SPRG_SCRATCH2, r3 -#endif EXCEPTION_PROLOG_0 - mfcr r10 + mfcr r3 /* If we are faulting a kernel address, we have to use the * kernel page tables. */ - mfspr r11, SPRN_MD_EPN - IS_KERNEL(r11, r11) + mfspr r10, SPRN_MD_EPN + IS_KERNEL(r11, r10) mfspr r11, SPRN_M_TW /* Get level 1 table */ BRANCH_UNLESS_KERNEL(3f) lis r11, (swapper_pg_dir-PAGE_OFFSET)@ha 3: - mtcr r10 - mfspr r10, SPRN_MD_EPN /* Insert level 1 index */ rlwimi r11, r10, 32 - ((PAGE_SHIFT - 2) << 1), (PAGE_SHIFT - 2) << 1, 29 lwz r11, (swapper_pg_dir-PAGE_OFFSET)@l(r11) /* Get the level 1 entry */ + mtcr r11 + bt- 28,DTLBMiss8M /* bit 28 = Large page (8M) */ + mtcr r3 /* We have a pte table, so load fetch the pte from the table. */ @@ -453,13 +452,34 @@ DataStoreTLBMiss: MTSPR_CPU6(SPRN_MD_RPN, r10, r3) /* Update TLB entry */ /* Restore registers */ -#ifdef CONFIG_8xx_CPU6 mfspr r3, SPRN_SPRG_SCRATCH2 + mtspr SPRN_DAR, r11 /* Tag DAR */ + EXCEPTION_EPILOG_0 + rfi + +DTLBMiss8M: + mtcr r3 + ori r11, r11, MD_SVALID + MTSPR_CPU6(SPRN_MD_TWC, r11, r3) +#ifdef CONFIG_PPC_16K_PAGES + /* + * In 16k pages mode, each PGD entry defines a 64M block. + * Here we select the 8M page within the block. + */ + rlwimi r11, r10, 0, 0x03800000 #endif + rlwinm r10, r11, 0, 0xff800000 + ori r10, r10, 0xf0 | MD_SPS16K | _PAGE_SHARED | _PAGE_DIRTY | \ + _PAGE_PRESENT + MTSPR_CPU6(SPRN_MD_RPN, r10, r3) /* Update TLB entry */ + + li r11, RPN_PATTERN + mfspr r3, SPRN_SPRG_SCRATCH2 mtspr SPRN_DAR, r11 /* Tag DAR */ EXCEPTION_EPILOG_0 rfi + /* This is an instruction TLB error on the MPC8xx. This could be due * to many reasons, such as executing guarded memory or illegal instruction * addresses. There is nothing to do but handle a big time error fault. @@ -537,13 +557,15 @@ FixupDAR:/* Entry point for dcbx workaround. */ /* Insert level 1 index */ 3: rlwimi r11, r10, 32 - ((PAGE_SHIFT - 2) << 1), (PAGE_SHIFT - 2) << 1, 29 lwz r11, (swapper_pg_dir-PAGE_OFFSET)@l(r11) /* Get the level 1 entry */ + mtcr r11 + bt 28,200f /* bit 28 = Large page (8M) */ rlwinm r11, r11,0,0,19 /* Extract page descriptor page address */ /* Insert level 2 index */ rlwimi r11, r10, 32 - (PAGE_SHIFT - 2), 32 - PAGE_SHIFT, 29 lwz r11, 0(r11) /* Get the pte */ /* concat physical page address(r11) and page offset(r10) */ rlwimi r11, r10, 0, 32 - PAGE_SHIFT, 31 - lwz r11,0(r11) +201: lwz r11,0(r11) /* Check if it really is a dcbx instruction. */ /* dcbt and dcbtst does not generate DTLB Misses/Errors, * no need to include them here */ @@ -562,6 +584,10 @@ FixupDAR:/* Entry point for dcbx workaround. */ 141: mfspr r10,SPRN_SPRG_SCRATCH2 b DARFixed /* Nope, go back to normal TLB processing */ + /* concat physical page address(r11) and page offset(r10) */ +200: rlwimi r11, r10, 0, 32 - (PAGE_SHIFT << 1), 31 + b 201b + 144: mfspr r10, SPRN_DSISR rlwinm r10, r10,0,7,5 /* Clear store bit for buggy dcbst insn */ mtspr SPRN_DSISR, r10 @@ -857,68 +883,6 @@ initial_mmu: /* - * Set up to use a given MMU context. - * r3 is context number, r4 is PGD pointer. - * - * We place the physical address of the new task page directory loaded - * into the MMU base register, and set the ASID compare register with - * the new "context." - */ -_GLOBAL(set_context) - -#ifdef CONFIG_BDI_SWITCH - /* Context switch the PTE pointer for the Abatron BDI2000. - * The PGDIR is passed as second argument. - */ - lis r5, KERNELBASE@h - lwz r5, 0xf0(r5) - stw r4, 0x4(r5) -#endif - - /* Register M_TW will contain base address of level 1 table minus the - * lower part of the kernel PGDIR base address, so that all accesses to - * level 1 table are done relative to lower part of kernel PGDIR base - * address. - */ - li r5, (swapper_pg_dir-PAGE_OFFSET)@l - sub r4, r4, r5 - tophys (r4, r4) -#ifdef CONFIG_8xx_CPU6 - lis r6, cpu6_errata_word@h - ori r6, r6, cpu6_errata_word@l - li r7, 0x3f80 - stw r7, 12(r6) - lwz r7, 12(r6) -#endif - mtspr SPRN_M_TW, r4 /* Update pointeur to level 1 table */ -#ifdef CONFIG_8xx_CPU6 - li r7, 0x3380 - stw r7, 12(r6) - lwz r7, 12(r6) -#endif - mtspr SPRN_M_CASID, r3 /* Update context */ - SYNC - blr - -#ifdef CONFIG_8xx_CPU6 -/* It's here because it is unique to the 8xx. - * It is important we get called with interrupts disabled. I used to - * do that, but it appears that all code that calls this already had - * interrupt disabled. - */ - .globl set_dec_cpu6 -set_dec_cpu6: - lis r7, cpu6_errata_word@h - ori r7, r7, cpu6_errata_word@l - li r4, 0x2c00 - stw r4, 8(r7) - lwz r4, 8(r7) - mtspr 22, r3 /* Update Decrementer */ - SYNC - blr -#endif - -/* * 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/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S index f705171b9..3bfa31509 100644 --- a/arch/powerpc/kernel/head_fsl_booke.S +++ b/arch/powerpc/kernel/head_fsl_booke.S @@ -1037,80 +1037,6 @@ _GLOBAL(set_context) isync /* Force context change */ blr -_GLOBAL(flush_dcache_L1) - mfspr r3,SPRN_L1CFG0 - - rlwinm r5,r3,9,3 /* Extract cache block size */ - twlgti r5,1 /* Only 32 and 64 byte cache blocks - * are currently defined. - */ - li r4,32 - subfic r6,r5,2 /* r6 = log2(1KiB / cache block size) - - * log2(number of ways) - */ - slw r5,r4,r5 /* r5 = cache block size */ - - rlwinm r7,r3,0,0xff /* Extract number of KiB in the cache */ - mulli r7,r7,13 /* An 8-way cache will require 13 - * loads per set. - */ - slw r7,r7,r6 - - /* save off HID0 and set DCFA */ - mfspr r8,SPRN_HID0 - ori r9,r8,HID0_DCFA@l - mtspr SPRN_HID0,r9 - isync - - lis r4,KERNELBASE@h - mtctr r7 - -1: lwz r3,0(r4) /* Load... */ - add r4,r4,r5 - bdnz 1b - - msync - lis r4,KERNELBASE@h - mtctr r7 - -1: dcbf 0,r4 /* ...and flush. */ - add r4,r4,r5 - bdnz 1b - - /* restore HID0 */ - mtspr SPRN_HID0,r8 - isync - - blr - -/* Flush L1 d-cache, invalidate and disable d-cache and i-cache */ -_GLOBAL(__flush_disable_L1) - mflr r10 - bl flush_dcache_L1 /* Flush L1 d-cache */ - mtlr r10 - - mfspr r4, SPRN_L1CSR0 /* Invalidate and disable d-cache */ - li r5, 2 - rlwimi r4, r5, 0, 3 - - msync - isync - mtspr SPRN_L1CSR0, r4 - isync - -1: mfspr r4, SPRN_L1CSR0 /* Wait for the invalidate to finish */ - andi. r4, r4, 2 - bne 1b - - mfspr r4, SPRN_L1CSR1 /* Invalidate and disable i-cache */ - li r5, 2 - rlwimi r4, r5, 0, 3 - - mtspr SPRN_L1CSR1, r4 - isync - - blr - #ifdef CONFIG_SMP /* When we get here, r24 needs to hold the CPU # */ .globl __secondary_start diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S index cf4fb5429..470ceebd2 100644 --- a/arch/powerpc/kernel/idle_power7.S +++ b/arch/powerpc/kernel/idle_power7.S @@ -19,7 +19,7 @@ #include <asm/kvm_book3s_asm.h> #include <asm/opal.h> #include <asm/cpuidle.h> -#include <asm/mmu-hash64.h> +#include <asm/book3s/64/mmu-hash.h> #undef DEBUG diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c index e77c3ccf8..dbf098121 100644 --- a/arch/powerpc/kernel/kgdb.c +++ b/arch/powerpc/kernel/kgdb.c @@ -445,7 +445,11 @@ int kgdb_arch_handle_exception(int vector, int signo, int err_code, * Global data */ struct kgdb_arch arch_kgdb_ops = { +#ifdef __LITTLE_ENDIAN__ + .gdb_bpt_instr = {0x08, 0x10, 0x82, 0x7d}, +#else .gdb_bpt_instr = {0x7d, 0x82, 0x10, 0x08}, +#endif }; static int kgdb_not_implemented(struct pt_regs *regs) diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c index 2c647b1e6..ee62b1975 100644 --- a/arch/powerpc/kernel/mce_power.c +++ b/arch/powerpc/kernel/mce_power.c @@ -54,8 +54,8 @@ static void flush_tlb_206(unsigned int num_sets, unsigned int action) } /* - * Generic routine to flush TLB on power7. This routine is used as - * flush_tlb hook in cpu_spec for Power7 processor. + * Generic routines to flush TLB on POWER processors. These routines + * are used as flush_tlb hook in the cpu_spec. * * action => TLB_INVAL_SCOPE_GLOBAL: Invalidate all TLBs. * TLB_INVAL_SCOPE_LPID: Invalidate TLB for current LPID. @@ -65,18 +65,17 @@ void __flush_tlb_power7(unsigned int action) flush_tlb_206(POWER7_TLB_SETS, action); } -/* - * Generic routine to flush TLB on power8. This routine is used as - * flush_tlb hook in cpu_spec for power8 processor. - * - * action => TLB_INVAL_SCOPE_GLOBAL: Invalidate all TLBs. - * TLB_INVAL_SCOPE_LPID: Invalidate TLB for current LPID. - */ void __flush_tlb_power8(unsigned int action) { flush_tlb_206(POWER8_TLB_SETS, action); } +void __flush_tlb_power9(unsigned int action) +{ + flush_tlb_206(POWER9_TLB_SETS_HASH, action); +} + + /* flush SLBs and reload */ static void flush_and_reload_slb(void) { diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index be8edd67f..bf5160fbf 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -91,17 +91,16 @@ _GLOBAL(mulhdu) addc r7,r0,r7 addze r4,r4 1: beqlr cr1 /* all done if high part of A is 0 */ - mr r10,r3 mullw r9,r3,r5 - mulhwu r3,r3,r5 + mulhwu r10,r3,r5 beq 2f - mullw r0,r10,r6 - mulhwu r8,r10,r6 + mullw r0,r3,r6 + mulhwu r8,r3,r6 addc r7,r0,r7 adde r4,r4,r8 - addze r3,r3 + addze r10,r10 2: addc r4,r4,r9 - addze r3,r3 + addze r3,r10 blr /* @@ -296,12 +295,9 @@ _GLOBAL(real_writeb) * Flush instruction cache. * This is a no-op on the 601. */ +#ifndef CONFIG_PPC_8xx _GLOBAL(flush_instruction_cache) -#if defined(CONFIG_8xx) - isync - lis r5, IDC_INVALL@h - mtspr SPRN_IC_CST, r5 -#elif defined(CONFIG_4xx) +#if defined(CONFIG_4xx) #ifdef CONFIG_403GCX li r3, 512 mtctr r3 @@ -334,9 +330,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_UNIFIED_ID_CACHE) mfspr r3,SPRN_HID0 ori r3,r3,HID0_ICFI mtspr SPRN_HID0,r3 -#endif /* CONFIG_8xx/4xx */ +#endif /* CONFIG_4xx */ isync blr +#endif /* CONFIG_PPC_8xx */ /* * Write any modified data cache blocks out to memory @@ -350,10 +347,9 @@ BEGIN_FTR_SECTION PURGE_PREFETCHED_INS blr /* for 601, do nothing */ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) - li r5,L1_CACHE_BYTES-1 - andc r3,r3,r5 + rlwinm r3,r3,0,0,31 - L1_CACHE_SHIFT subf r4,r3,r4 - add r4,r4,r5 + addi r4,r4,L1_CACHE_BYTES - 1 srwi. r4,r4,L1_CACHE_SHIFT beqlr mtctr r4 @@ -377,71 +373,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) isync blr /* - * Write any modified data cache blocks out to memory. - * Does not invalidate the corresponding cache lines (especially for - * any corresponding instruction cache). - * - * clean_dcache_range(unsigned long start, unsigned long stop) - */ -_GLOBAL(clean_dcache_range) - li r5,L1_CACHE_BYTES-1 - andc r3,r3,r5 - subf r4,r3,r4 - add r4,r4,r5 - srwi. r4,r4,L1_CACHE_SHIFT - beqlr - mtctr r4 - -1: dcbst 0,r3 - addi r3,r3,L1_CACHE_BYTES - bdnz 1b - sync /* wait for dcbst's to get to ram */ - blr - -/* - * Write any modified data cache blocks out to memory and invalidate them. - * Does not invalidate the corresponding instruction cache blocks. - * - * flush_dcache_range(unsigned long start, unsigned long stop) - */ -_GLOBAL(flush_dcache_range) - li r5,L1_CACHE_BYTES-1 - andc r3,r3,r5 - subf r4,r3,r4 - add r4,r4,r5 - srwi. r4,r4,L1_CACHE_SHIFT - beqlr - mtctr r4 - -1: dcbf 0,r3 - addi r3,r3,L1_CACHE_BYTES - bdnz 1b - sync /* wait for dcbst's to get to ram */ - blr - -/* - * Like above, but invalidate the D-cache. This is used by the 8xx - * to invalidate the cache so the PPC core doesn't get stale data - * from the CPM (no cache snooping here :-). - * - * invalidate_dcache_range(unsigned long start, unsigned long stop) - */ -_GLOBAL(invalidate_dcache_range) - li r5,L1_CACHE_BYTES-1 - andc r3,r3,r5 - subf r4,r3,r4 - add r4,r4,r5 - srwi. r4,r4,L1_CACHE_SHIFT - beqlr - mtctr r4 - -1: dcbi 0,r3 - addi r3,r3,L1_CACHE_BYTES - bdnz 1b - sync /* wait for dcbi's to get to ram */ - blr - -/* * Flush a particular page from the data cache to RAM. * Note: this is necessary because the instruction cache does *not* * snoop from the data cache. @@ -519,22 +450,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) #endif /* CONFIG_BOOKE */ /* - * Clear pages using the dcbz instruction, which doesn't cause any - * memory traffic (except to write out any cache lines which get - * displaced). This only works on cacheable memory. - * - * void clear_pages(void *page, int order) ; - */ -_GLOBAL(clear_pages) - li r0,PAGE_SIZE/L1_CACHE_BYTES - slw r0,r0,r4 - mtctr r0 -1: dcbz 0,r3 - addi r3,r3,L1_CACHE_BYTES - bdnz 1b - blr - -/* * Copy a whole page. We use the dcbz instruction on the destination * to reduce memory traffic (it eliminates the unnecessary reads of * the destination into cache). This requires that the destination diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c index 9547381b6..d1f1b35bf 100644 --- a/arch/powerpc/kernel/module.c +++ b/arch/powerpc/kernel/module.c @@ -47,6 +47,11 @@ int module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *me) { const Elf_Shdr *sect; + int rc; + + rc = module_finalize_ftrace(me, sechdrs); + if (rc) + return rc; /* Apply feature fixups */ sect = find_section(hdr, sechdrs, "__ftr_fixup"); diff --git a/arch/powerpc/kernel/module_32.c b/arch/powerpc/kernel/module_32.c index 2c01665eb..5a7a78f12 100644 --- a/arch/powerpc/kernel/module_32.c +++ b/arch/powerpc/kernel/module_32.c @@ -181,7 +181,7 @@ static inline int entry_matches(struct ppc_plt_entry *entry, Elf32_Addr val) /* Set up a trampoline in the PLT to bounce us to the distant function */ static uint32_t do_plt_call(void *location, Elf32_Addr val, - Elf32_Shdr *sechdrs, + const Elf32_Shdr *sechdrs, struct module *mod) { struct ppc_plt_entry *entry; @@ -294,11 +294,19 @@ int apply_relocate_add(Elf32_Shdr *sechdrs, return -ENOEXEC; } } + + return 0; +} + #ifdef CONFIG_DYNAMIC_FTRACE - module->arch.tramp = - do_plt_call(module->core_layout.base, - (unsigned long)ftrace_caller, - sechdrs, module); -#endif +int module_finalize_ftrace(struct module *module, const Elf_Shdr *sechdrs) +{ + module->arch.tramp = do_plt_call(module->core_layout.base, + (unsigned long)ftrace_caller, + sechdrs, module); + if (!module->arch.tramp) + return -ENOENT; + return 0; } +#endif diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 08b7a40de..9ce9a25f5 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -31,6 +31,7 @@ #include <asm/code-patching.h> #include <linux/sort.h> #include <asm/setup.h> +#include <asm/sections.h> /* FIXME: We don't do .init separately. To do this, we'd need to have a separate r2 value in the init and core section, and stub between @@ -41,7 +42,6 @@ --RR. */ #if defined(_CALL_ELF) && _CALL_ELF == 2 -#define R2_STACK_OFFSET 24 /* An address is simply the address of the function. */ typedef unsigned long func_desc_t; @@ -73,7 +73,6 @@ static unsigned int local_entry_offset(const Elf64_Sym *sym) return PPC64_LOCAL_ENTRY_OFFSET(sym->st_other); } #else -#define R2_STACK_OFFSET 40 /* An address is address of the OPD entry, which contains address of fn. */ typedef struct ppc64_opd_entry func_desc_t; @@ -96,6 +95,8 @@ static unsigned int local_entry_offset(const Elf64_Sym *sym) } #endif +#define STUB_MAGIC 0x73747562 /* stub */ + /* Like PPC32, we need little trampolines to do > 24-bit jumps (into the kernel itself). But on PPC64, these need to be used for every jump, actually, to reset r2 (TOC+0x8000). */ @@ -105,7 +106,8 @@ struct ppc64_stub_entry * need 6 instructions on ABIv2 but we always allocate 7 so * so we don't have to modify the trampoline load instruction. */ u32 jump[7]; - u32 unused; + /* Used by ftrace to identify stubs */ + u32 magic; /* Data for the above code */ func_desc_t funcdata; }; @@ -139,70 +141,39 @@ static u32 ppc64_stub_insns[] = { }; #ifdef CONFIG_DYNAMIC_FTRACE - -static u32 ppc64_stub_mask[] = { - 0xffff0000, - 0xffff0000, - 0xffffffff, - 0xffffffff, -#if !defined(_CALL_ELF) || _CALL_ELF != 2 - 0xffffffff, -#endif - 0xffffffff, - 0xffffffff -}; - -bool is_module_trampoline(u32 *p) +int module_trampoline_target(struct module *mod, unsigned long addr, + unsigned long *target) { - unsigned int i; - u32 insns[ARRAY_SIZE(ppc64_stub_insns)]; - - BUILD_BUG_ON(sizeof(ppc64_stub_insns) != sizeof(ppc64_stub_mask)); + struct ppc64_stub_entry *stub; + func_desc_t funcdata; + u32 magic; - if (probe_kernel_read(insns, p, sizeof(insns))) + if (!within_module_core(addr, mod)) { + pr_err("%s: stub %lx not in module %s\n", __func__, addr, mod->name); return -EFAULT; - - for (i = 0; i < ARRAY_SIZE(ppc64_stub_insns); i++) { - u32 insna = insns[i]; - u32 insnb = ppc64_stub_insns[i]; - u32 mask = ppc64_stub_mask[i]; - - if ((insna & mask) != (insnb & mask)) - return false; } - return true; -} - -int module_trampoline_target(struct module *mod, u32 *trampoline, - unsigned long *target) -{ - u32 buf[2]; - u16 upper, lower; - long offset; - void *toc_entry; + stub = (struct ppc64_stub_entry *)addr; - if (probe_kernel_read(buf, trampoline, sizeof(buf))) + if (probe_kernel_read(&magic, &stub->magic, sizeof(magic))) { + pr_err("%s: fault reading magic for stub %lx for %s\n", __func__, addr, mod->name); return -EFAULT; + } - upper = buf[0] & 0xffff; - lower = buf[1] & 0xffff; - - /* perform the addis/addi, both signed */ - offset = ((short)upper << 16) + (short)lower; + if (magic != STUB_MAGIC) { + pr_err("%s: bad magic for stub %lx for %s\n", __func__, addr, mod->name); + return -EFAULT; + } - /* - * Now get the address this trampoline jumps to. This - * is always 32 bytes into our trampoline stub. - */ - toc_entry = (void *)mod->arch.toc + offset + 32; + if (probe_kernel_read(&funcdata, &stub->funcdata, sizeof(funcdata))) { + pr_err("%s: fault reading funcdata for stub %lx for %s\n", __func__, addr, mod->name); + return -EFAULT; + } - if (probe_kernel_read(target, toc_entry, sizeof(*target))) - return -EFAULT; + *target = stub_func_addr(funcdata); return 0; } - #endif /* Count how many different 24-bit relocations (different symbol, @@ -413,7 +384,7 @@ int module_frob_arch_sections(Elf64_Ehdr *hdr, /* r2 is the TOC pointer: it actually points 0x8000 into the TOC (this gives the value maximum span in an instruction which uses a signed offset) */ -static inline unsigned long my_r2(Elf64_Shdr *sechdrs, struct module *me) +static inline unsigned long my_r2(const Elf64_Shdr *sechdrs, struct module *me) { return sechdrs[me->arch.toc_section].sh_addr + 0x8000; } @@ -426,7 +397,7 @@ static inline unsigned long my_r2(Elf64_Shdr *sechdrs, struct module *me) #define PPC_HA(v) PPC_HI ((v) + 0x8000) /* Patch stub to reference function and correct r2 value. */ -static inline int create_stub(Elf64_Shdr *sechdrs, +static inline int create_stub(const Elf64_Shdr *sechdrs, struct ppc64_stub_entry *entry, unsigned long addr, struct module *me) @@ -447,12 +418,14 @@ static inline int create_stub(Elf64_Shdr *sechdrs, entry->jump[0] |= PPC_HA(reladdr); entry->jump[1] |= PPC_LO(reladdr); entry->funcdata = func_desc(addr); + entry->magic = STUB_MAGIC; + return 1; } /* Create stub to jump to function described in this OPD/ptr: we need the stub to set up the TOC ptr (r2) for the function. */ -static unsigned long stub_for_addr(Elf64_Shdr *sechdrs, +static unsigned long stub_for_addr(const Elf64_Shdr *sechdrs, unsigned long addr, struct module *me) { @@ -476,17 +449,60 @@ static unsigned long stub_for_addr(Elf64_Shdr *sechdrs, return (unsigned long)&stubs[i]; } +#ifdef CC_USING_MPROFILE_KERNEL +static bool is_early_mcount_callsite(u32 *instruction) +{ + /* + * Check if this is one of the -mprofile-kernel sequences. + */ + if (instruction[-1] == PPC_INST_STD_LR && + instruction[-2] == PPC_INST_MFLR) + return true; + + if (instruction[-1] == PPC_INST_MFLR) + return true; + + return false; +} + +/* + * In case of _mcount calls, do not save the current callee's TOC (in r2) into + * the original caller's stack frame. If we did we would clobber the saved TOC + * value of the original caller. + */ +static void squash_toc_save_inst(const char *name, unsigned long addr) +{ + struct ppc64_stub_entry *stub = (struct ppc64_stub_entry *)addr; + + /* Only for calls to _mcount */ + if (strcmp("_mcount", name) != 0) + return; + + stub->jump[2] = PPC_INST_NOP; +} +#else +static void squash_toc_save_inst(const char *name, unsigned long addr) { } + +/* without -mprofile-kernel, mcount calls are never early */ +static bool is_early_mcount_callsite(u32 *instruction) +{ + return false; +} +#endif + /* We expect a noop next: if it is, replace it with instruction to restore r2. */ static int restore_r2(u32 *instruction, struct module *me) { if (*instruction != PPC_INST_NOP) { + if (is_early_mcount_callsite(instruction - 1)) + return 1; pr_err("%s: Expect noop after relocate, got %08x\n", me->name, *instruction); return 0; } /* ld r2,R2_STACK_OFFSET(r1) */ - *instruction = 0xe8410000 | R2_STACK_OFFSET; + *instruction = PPC_INST_LD_TOC; return 1; } @@ -611,6 +627,8 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, return -ENOENT; if (!restore_r2((u32 *)location + 1, me)) return -ENOEXEC; + + squash_toc_save_inst(strtab + sym->st_name, value); } else value += local_entry_offset(sym); @@ -693,12 +711,84 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, } } + return 0; +} + #ifdef CONFIG_DYNAMIC_FTRACE - me->arch.toc = my_r2(sechdrs, me); - me->arch.tramp = stub_for_addr(sechdrs, - (unsigned long)ftrace_caller, - me); + +#ifdef CC_USING_MPROFILE_KERNEL + +#define PACATOC offsetof(struct paca_struct, kernel_toc) + +/* + * For mprofile-kernel we use a special stub for ftrace_caller() because we + * can't rely on r2 containing this module's TOC when we enter the stub. + * + * That can happen if the function calling us didn't need to use the toc. In + * that case it won't have setup r2, and the r2 value will be either the + * kernel's toc, or possibly another modules toc. + * + * To deal with that this stub uses the kernel toc, which is always accessible + * via the paca (in r13). The target (ftrace_caller()) is responsible for + * saving and restoring the toc before returning. + */ +static unsigned long create_ftrace_stub(const Elf64_Shdr *sechdrs, struct module *me) +{ + struct ppc64_stub_entry *entry; + unsigned int i, num_stubs; + static u32 stub_insns[] = { + 0xe98d0000 | PACATOC, /* ld r12,PACATOC(r13) */ + 0x3d8c0000, /* addis r12,r12,<high> */ + 0x398c0000, /* addi r12,r12,<low> */ + 0x7d8903a6, /* mtctr r12 */ + 0x4e800420, /* bctr */ + }; + long reladdr; + + num_stubs = sechdrs[me->arch.stubs_section].sh_size / sizeof(*entry); + + /* Find the next available stub entry */ + entry = (void *)sechdrs[me->arch.stubs_section].sh_addr; + for (i = 0; i < num_stubs && stub_func_addr(entry->funcdata); i++, entry++); + + if (i >= num_stubs) { + pr_err("%s: Unable to find a free slot for ftrace stub.\n", me->name); + return 0; + } + + memcpy(entry->jump, stub_insns, sizeof(stub_insns)); + + /* Stub uses address relative to kernel toc (from the paca) */ + reladdr = (unsigned long)ftrace_caller - kernel_toc_addr(); + if (reladdr > 0x7FFFFFFF || reladdr < -(0x80000000L)) { + pr_err("%s: Address of ftrace_caller out of range of kernel_toc.\n", me->name); + return 0; + } + + entry->jump[1] |= PPC_HA(reladdr); + entry->jump[2] |= PPC_LO(reladdr); + + /* Eventhough we don't use funcdata in the stub, it's needed elsewhere. */ + entry->funcdata = func_desc((unsigned long)ftrace_caller); + entry->magic = STUB_MAGIC; + + return (unsigned long)entry; +} +#else +static unsigned long create_ftrace_stub(const Elf64_Shdr *sechdrs, struct module *me) +{ + return stub_for_addr(sechdrs, (unsigned long)ftrace_caller, me); +} #endif +int module_finalize_ftrace(struct module *mod, const Elf_Shdr *sechdrs) +{ + mod->arch.toc = my_r2(sechdrs, mod); + mod->arch.tramp = create_ftrace_stub(sechdrs, mod); + + if (!mod->arch.tramp) + return -ENOENT; + return 0; } +#endif diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index 01ea0edf0..93dae296b 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -17,10 +17,6 @@ #include <asm/pgtable.h> #include <asm/kexec.h> -/* This symbol is provided by the linker - let it fill in the paca - * field correctly */ -extern unsigned long __toc_start; - #ifdef CONFIG_PPC_BOOK3S /* @@ -149,11 +145,6 @@ EXPORT_SYMBOL(paca); void __init initialise_paca(struct paca_struct *new_paca, int cpu) { - /* The TOC register (GPR2) points 32kB into the TOC, so that 64kB - * of the TOC can be addressed using a single machine instruction. - */ - unsigned long kernel_toc = (unsigned long)(&__toc_start) + 0x8000UL; - #ifdef CONFIG_PPC_BOOK3S new_paca->lppaca_ptr = new_lppaca(cpu); #else @@ -161,7 +152,7 @@ void __init initialise_paca(struct paca_struct *new_paca, int cpu) #endif new_paca->lock_token = 0x8000; new_paca->paca_index = cpu; - new_paca->kernel_toc = kernel_toc; + new_paca->kernel_toc = kernel_toc_addr(); new_paca->kernelbase = (unsigned long) _stext; /* Only set MSR:IR/DR when MMU is initialized */ new_paca->kernel_msr = MSR_KERNEL & ~(MSR_IR | MSR_DR); diff --git a/arch/powerpc/kernel/pci-hotplug.c b/arch/powerpc/kernel/pci-hotplug.c index 7f9ed0c1f..59c436189 100644 --- a/arch/powerpc/kernel/pci-hotplug.c +++ b/arch/powerpc/kernel/pci-hotplug.c @@ -55,7 +55,7 @@ void pcibios_remove_pci_devices(struct pci_bus *bus) pr_debug("PCI: Removing devices on bus %04x:%02x\n", pci_domain_nr(bus), bus->number); - list_for_each_entry_safe(dev, tmp, &bus->devices, bus_list) { + list_for_each_entry_safe_reverse(dev, tmp, &bus->devices, bus_list) { pr_debug(" Removing %s...\n", pci_name(dev)); pci_stop_and_remove_bus_device(dev); } diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c index b3b4df91b..38102cb9b 100644 --- a/arch/powerpc/kernel/pci_dn.c +++ b/arch/powerpc/kernel/pci_dn.c @@ -139,6 +139,7 @@ struct pci_dn *pci_get_pdn(struct pci_dev *pdev) #ifdef CONFIG_PCI_IOV static struct pci_dn *add_one_dev_pci_data(struct pci_dn *parent, struct pci_dev *pdev, + int vf_index, int busno, int devfn) { struct pci_dn *pdn; @@ -158,6 +159,7 @@ static struct pci_dn *add_one_dev_pci_data(struct pci_dn *parent, pdn->busno = busno; pdn->devfn = devfn; #ifdef CONFIG_PPC_POWERNV + pdn->vf_index = vf_index; pdn->pe_number = IODA_INVALID_PE; #endif INIT_LIST_HEAD(&pdn->child_list); @@ -179,6 +181,7 @@ struct pci_dn *add_dev_pci_data(struct pci_dev *pdev) { #ifdef CONFIG_PCI_IOV struct pci_dn *parent, *pdn; + struct eeh_dev *edev; int i; /* Only support IOV for now */ @@ -196,7 +199,7 @@ struct pci_dn *add_dev_pci_data(struct pci_dev *pdev) return NULL; for (i = 0; i < pci_sriov_get_totalvfs(pdev); i++) { - pdn = add_one_dev_pci_data(parent, NULL, + pdn = add_one_dev_pci_data(parent, NULL, i, pci_iov_virtfn_bus(pdev, i), pci_iov_virtfn_devfn(pdev, i)); if (!pdn) { @@ -204,6 +207,12 @@ struct pci_dn *add_dev_pci_data(struct pci_dev *pdev) __func__, i); return NULL; } + + /* Create the EEH device for the VF */ + eeh_dev_init(pdn, pci_bus_to_host(pdev->bus)); + edev = pdn_to_eeh_dev(pdn); + BUG_ON(!edev); + edev->physfn = pdev; } #endif /* CONFIG_PCI_IOV */ @@ -215,6 +224,7 @@ void remove_dev_pci_data(struct pci_dev *pdev) #ifdef CONFIG_PCI_IOV struct pci_dn *parent; struct pci_dn *pdn, *tmp; + struct eeh_dev *edev; int i; /* @@ -256,6 +266,13 @@ void remove_dev_pci_data(struct pci_dev *pdev) pdn->devfn != pci_iov_virtfn_devfn(pdev, i)) continue; + /* Release EEH device for the VF */ + edev = pdn_to_eeh_dev(pdn); + if (edev) { + pdn->edev = NULL; + kfree(edev); + } + if (!list_empty(&pdn->list)) list_del(&pdn->list); diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c index 41e1607e8..9f01e28ec 100644 --- a/arch/powerpc/kernel/ppc_ksyms.c +++ b/arch/powerpc/kernel/ppc_ksyms.c @@ -6,7 +6,9 @@ #include <asm/cacheflush.h> #include <asm/epapr_hcalls.h> +#ifdef CONFIG_PPC64 EXPORT_SYMBOL(flush_dcache_range); +#endif EXPORT_SYMBOL(flush_icache_range); EXPORT_SYMBOL(empty_zero_page); @@ -28,10 +30,6 @@ EXPORT_SYMBOL(load_vr_state); EXPORT_SYMBOL(store_vr_state); #endif -#ifdef CONFIG_VSX -EXPORT_SYMBOL_GPL(__giveup_vsx); -#endif - #ifdef CONFIG_EPAPR_PARAVIRT EXPORT_SYMBOL(epapr_hypercall_start); #endif diff --git a/arch/powerpc/kernel/ppc_ksyms_32.c b/arch/powerpc/kernel/ppc_ksyms_32.c index 30ddd8a24..2bfaafe5b 100644 --- a/arch/powerpc/kernel/ppc_ksyms_32.c +++ b/arch/powerpc/kernel/ppc_ksyms_32.c @@ -10,7 +10,6 @@ #include <asm/pgtable.h> #include <asm/dcr.h> -EXPORT_SYMBOL(clear_pages); EXPORT_SYMBOL(ISA_DMA_THRESHOLD); EXPORT_SYMBOL(DMA_MODE_READ); EXPORT_SYMBOL(DMA_MODE_WRITE); diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 54ed9c766..b8500b4ac 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -133,6 +133,16 @@ void __msr_check_and_clear(unsigned long bits) EXPORT_SYMBOL(__msr_check_and_clear); #ifdef CONFIG_PPC_FPU +void __giveup_fpu(struct task_struct *tsk) +{ + save_fpu(tsk); + tsk->thread.regs->msr &= ~MSR_FP; +#ifdef CONFIG_VSX + if (cpu_has_feature(CPU_FTR_VSX)) + tsk->thread.regs->msr &= ~MSR_VSX; +#endif +} + void giveup_fpu(struct task_struct *tsk) { check_if_tm_restore_required(tsk); @@ -187,9 +197,32 @@ void enable_kernel_fp(void) } } EXPORT_SYMBOL(enable_kernel_fp); + +static int restore_fp(struct task_struct *tsk) { + if (tsk->thread.load_fp) { + load_fp_state(¤t->thread.fp_state); + current->thread.load_fp++; + return 1; + } + return 0; +} +#else +static int restore_fp(struct task_struct *tsk) { return 0; } #endif /* CONFIG_PPC_FPU */ #ifdef CONFIG_ALTIVEC +#define loadvec(thr) ((thr).load_vec) + +static void __giveup_altivec(struct task_struct *tsk) +{ + save_altivec(tsk); + tsk->thread.regs->msr &= ~MSR_VEC; +#ifdef CONFIG_VSX + if (cpu_has_feature(CPU_FTR_VSX)) + tsk->thread.regs->msr &= ~MSR_VSX; +#endif +} + void giveup_altivec(struct task_struct *tsk) { check_if_tm_restore_required(tsk); @@ -229,22 +262,49 @@ void flush_altivec_to_thread(struct task_struct *tsk) } } EXPORT_SYMBOL_GPL(flush_altivec_to_thread); + +static int restore_altivec(struct task_struct *tsk) +{ + if (cpu_has_feature(CPU_FTR_ALTIVEC) && tsk->thread.load_vec) { + load_vr_state(&tsk->thread.vr_state); + tsk->thread.used_vr = 1; + tsk->thread.load_vec++; + + return 1; + } + return 0; +} +#else +#define loadvec(thr) 0 +static inline int restore_altivec(struct task_struct *tsk) { return 0; } #endif /* CONFIG_ALTIVEC */ #ifdef CONFIG_VSX -void giveup_vsx(struct task_struct *tsk) +static void __giveup_vsx(struct task_struct *tsk) { - check_if_tm_restore_required(tsk); - - msr_check_and_set(MSR_FP|MSR_VEC|MSR_VSX); if (tsk->thread.regs->msr & MSR_FP) __giveup_fpu(tsk); if (tsk->thread.regs->msr & MSR_VEC) __giveup_altivec(tsk); + tsk->thread.regs->msr &= ~MSR_VSX; +} + +static void giveup_vsx(struct task_struct *tsk) +{ + check_if_tm_restore_required(tsk); + + msr_check_and_set(MSR_FP|MSR_VEC|MSR_VSX); __giveup_vsx(tsk); msr_check_and_clear(MSR_FP|MSR_VEC|MSR_VSX); } -EXPORT_SYMBOL(giveup_vsx); + +static void save_vsx(struct task_struct *tsk) +{ + if (tsk->thread.regs->msr & MSR_FP) + save_fpu(tsk); + if (tsk->thread.regs->msr & MSR_VEC) + save_altivec(tsk); +} void enable_kernel_vsx(void) { @@ -275,6 +335,19 @@ void flush_vsx_to_thread(struct task_struct *tsk) } } EXPORT_SYMBOL_GPL(flush_vsx_to_thread); + +static int restore_vsx(struct task_struct *tsk) +{ + if (cpu_has_feature(CPU_FTR_VSX)) { + tsk->thread.used_vsr = 1; + return 1; + } + + return 0; +} +#else +static inline int restore_vsx(struct task_struct *tsk) { return 0; } +static inline void save_vsx(struct task_struct *tsk) { } #endif /* CONFIG_VSX */ #ifdef CONFIG_SPE @@ -374,12 +447,76 @@ void giveup_all(struct task_struct *tsk) } EXPORT_SYMBOL(giveup_all); +void restore_math(struct pt_regs *regs) +{ + unsigned long msr; + + if (!current->thread.load_fp && !loadvec(current->thread)) + return; + + msr = regs->msr; + msr_check_and_set(msr_all_available); + + /* + * Only reload if the bit is not set in the user MSR, the bit BEING set + * indicates that the registers are hot + */ + if ((!(msr & MSR_FP)) && restore_fp(current)) + msr |= MSR_FP | current->thread.fpexc_mode; + + if ((!(msr & MSR_VEC)) && restore_altivec(current)) + msr |= MSR_VEC; + + if ((msr & (MSR_FP | MSR_VEC)) == (MSR_FP | MSR_VEC) && + restore_vsx(current)) { + msr |= MSR_VSX; + } + + msr_check_and_clear(msr_all_available); + + regs->msr = msr; +} + +void save_all(struct task_struct *tsk) +{ + unsigned long usermsr; + + if (!tsk->thread.regs) + return; + + usermsr = tsk->thread.regs->msr; + + if ((usermsr & msr_all_available) == 0) + return; + + msr_check_and_set(msr_all_available); + + /* + * Saving the way the register space is in hardware, save_vsx boils + * down to a save_fpu() and save_altivec() + */ + if (usermsr & MSR_VSX) { + save_vsx(tsk); + } else { + if (usermsr & MSR_FP) + save_fpu(tsk); + + if (usermsr & MSR_VEC) + save_altivec(tsk); + } + + if (usermsr & MSR_SPE) + __giveup_spe(tsk); + + msr_check_and_clear(msr_all_available); +} + void flush_all_to_thread(struct task_struct *tsk) { if (tsk->thread.regs) { preempt_disable(); BUG_ON(tsk != current); - giveup_all(tsk); + save_all(tsk); #ifdef CONFIG_SPE if (tsk->thread.regs->msr & MSR_SPE) @@ -832,17 +969,9 @@ void restore_tm_state(struct pt_regs *regs) msr_diff = current->thread.ckpt_regs.msr & ~regs->msr; msr_diff &= MSR_FP | MSR_VEC | MSR_VSX; - if (msr_diff & MSR_FP) { - msr_check_and_set(MSR_FP); - load_fp_state(¤t->thread.fp_state); - msr_check_and_clear(MSR_FP); - regs->msr |= current->thread.fpexc_mode; - } - if (msr_diff & MSR_VEC) { - msr_check_and_set(MSR_VEC); - load_vr_state(¤t->thread.vr_state); - msr_check_and_clear(MSR_VEC); - } + + restore_math(regs); + regs->msr |= msr_diff; } @@ -1006,6 +1135,10 @@ struct task_struct *__switch_to(struct task_struct *prev, batch = this_cpu_ptr(&ppc64_tlb_batch); batch->active = 1; } + + if (current_thread_info()->task->thread.regs) + restore_math(current_thread_info()->task->thread.regs); + #endif /* CONFIG_PPC_BOOK3S_64 */ return last; @@ -1307,6 +1440,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, f = ret_from_fork; } + childregs->msr &= ~(MSR_FP|MSR_VEC|MSR_VSX); sp -= STACK_FRAME_OVERHEAD; /* diff --git a/arch/powerpc/kernel/rtasd.c b/arch/powerpc/kernel/rtasd.c index 5a2c049c1..aa610ce87 100644 --- a/arch/powerpc/kernel/rtasd.c +++ b/arch/powerpc/kernel/rtasd.c @@ -49,7 +49,7 @@ static unsigned int rtas_error_log_buffer_max; static unsigned int event_scan; static unsigned int rtas_event_scan_rate; -static int full_rtas_msgs = 0; +static bool full_rtas_msgs; /* Stop logging to nvram after first fatal error */ static int logging_enabled; /* Until we initialize everything, @@ -592,11 +592,6 @@ __setup("surveillance=", surveillance_setup); static int __init rtasmsgs_setup(char *str) { - if (strcmp(str, "on") == 0) - full_rtas_msgs = 1; - else if (strcmp(str, "off") == 0) - full_rtas_msgs = 0; - - return 1; + return (kstrtobool(str, &full_rtas_msgs) == 0); } __setup("rtasmsgs=", rtasmsgs_setup); diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index ad8c9db61..d544fa311 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -114,8 +114,6 @@ extern unsigned int memset_nocache_branch; /* Insn to be replaced by NOP */ notrace void __init machine_init(u64 dt_ptr) { - lockdep_init(); - /* Enable early debugging if any specified (see udbg.h) */ udbg_early_init(); diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 5c03a6a9b..f98be8383 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -255,9 +255,6 @@ void __init early_setup(unsigned long dt_ptr) setup_paca(&boot_paca); fixup_boot_paca(); - /* Initialize lockdep early or else spinlocks will blow */ - lockdep_init(); - /* -------- printk is now safe to use ------- */ /* Enable early debugging if any specified (see udbg.h) */ diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index cf8c7e4e0..cb64d6feb 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -1,7 +1,7 @@ /* * Common signal handling code for both 32 and 64 bits * - * Copyright (c) 2007 Benjamin Herrenschmidt, IBM Coproration + * Copyright (c) 2007 Benjamin Herrenschmidt, IBM Corporation * Extracted from signal_32.c and signal_64.c * * This file is subject to the terms and conditions of the GNU General @@ -178,7 +178,7 @@ unsigned long get_tm_stackpointer(struct pt_regs *regs) * need to use the stack pointer from the checkpointed state, rather * than the speculated state. This ensures that the signal context * (written tm suspended) will be written below the stack required for - * the rollback. The transaction is aborted becuase of the treclaim, + * the rollback. The transaction is aborted because of the treclaim, * so any memory written between the tbegin and the signal will be * rolled back anyway. * diff --git a/arch/powerpc/kernel/signal.h b/arch/powerpc/kernel/signal.h index 51b274199..be305c858 100644 --- a/arch/powerpc/kernel/signal.h +++ b/arch/powerpc/kernel/signal.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2007 Benjamin Herrenschmidt, IBM Coproration + * Copyright (c) 2007 Benjamin Herrenschmidt, IBM Corporation * Extracted from signal_32.c and signal_64.c * * This file is subject to the terms and conditions of the GNU General diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index ec9ec2058..8cac1eb41 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -206,7 +206,7 @@ int smp_request_message_ipi(int virq, int msg) #ifdef CONFIG_PPC_SMP_MUXED_IPI struct cpu_messages { - int messages; /* current messages */ + long messages; /* current messages */ unsigned long data; /* data for cause ipi */ }; static DEFINE_PER_CPU_SHARED_ALIGNED(struct cpu_messages, ipi_message); @@ -218,7 +218,7 @@ void smp_muxed_ipi_set_data(int cpu, unsigned long data) info->data = data; } -void smp_muxed_ipi_message_pass(int cpu, int msg) +void smp_muxed_ipi_set_message(int cpu, int msg) { struct cpu_messages *info = &per_cpu(ipi_message, cpu); char *message = (char *)&info->messages; @@ -228,6 +228,13 @@ void smp_muxed_ipi_message_pass(int cpu, int msg) */ smp_mb(); message[msg] = 1; +} + +void smp_muxed_ipi_message_pass(int cpu, int msg) +{ + struct cpu_messages *info = &per_cpu(ipi_message, cpu); + + smp_muxed_ipi_set_message(cpu, msg); /* * cause_ipi functions are required to include a full barrier * before doing whatever causes the IPI. @@ -236,20 +243,31 @@ void smp_muxed_ipi_message_pass(int cpu, int msg) } #ifdef __BIG_ENDIAN__ -#define IPI_MESSAGE(A) (1 << (24 - 8 * (A))) +#define IPI_MESSAGE(A) (1uL << ((BITS_PER_LONG - 8) - 8 * (A))) #else -#define IPI_MESSAGE(A) (1 << (8 * (A))) +#define IPI_MESSAGE(A) (1uL << (8 * (A))) #endif irqreturn_t smp_ipi_demux(void) { struct cpu_messages *info = this_cpu_ptr(&ipi_message); - unsigned int all; + unsigned long all; mb(); /* order any irq clear */ do { all = xchg(&info->messages, 0); +#if defined(CONFIG_KVM_XICS) && defined(CONFIG_KVM_BOOK3S_HV_POSSIBLE) + /* + * Must check for PPC_MSG_RM_HOST_ACTION messages + * before PPC_MSG_CALL_FUNCTION messages because when + * a VM is destroyed, we call kick_all_cpus_sync() + * to ensure that any pending PPC_MSG_RM_HOST_ACTION + * messages have completed before we free any VCPUs. + */ + if (all & IPI_MESSAGE(PPC_MSG_RM_HOST_ACTION)) + kvmppc_xics_ipi_action(); +#endif if (all & IPI_MESSAGE(PPC_MSG_CALL_FUNCTION)) generic_smp_call_function_interrupt(); if (all & IPI_MESSAGE(PPC_MSG_RESCHEDULE)) @@ -427,7 +445,7 @@ void generic_cpu_die(unsigned int cpu) for (i = 0; i < 100; i++) { smp_rmb(); - if (per_cpu(cpu_state, cpu) == CPU_DEAD) + if (is_cpu_dead(cpu)) return; msleep(100); } @@ -454,6 +472,11 @@ int generic_check_cpu_restart(unsigned int cpu) return per_cpu(cpu_state, cpu) == CPU_UP_PREPARE; } +int is_cpu_dead(unsigned int cpu) +{ + return per_cpu(cpu_state, cpu) == CPU_DEAD; +} + static bool secondaries_inhibited(void) { return kvm_hv_mode_active(); @@ -727,7 +750,7 @@ void start_secondary(void *unused) local_irq_enable(); - cpu_startup_entry(CPUHP_ONLINE); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); BUG(); } diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index b6becc795..9229ba63c 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -203,9 +203,8 @@ static int __kprobes __die(const char *str, struct pt_regs *regs, long err) #ifdef CONFIG_SMP printk("SMP NR_CPUS=%d ", NR_CPUS); #endif -#ifdef CONFIG_DEBUG_PAGEALLOC - printk("DEBUG_PAGEALLOC "); -#endif + if (debug_pagealloc_enabled()) + printk("DEBUG_PAGEALLOC "); #ifdef CONFIG_NUMA printk("NUMA "); #endif @@ -1148,6 +1147,7 @@ void __kprobes program_check_exception(struct pt_regs *regs) goto bail; } if (reason & REASON_TRAP) { + unsigned long bugaddr; /* Debugger is first in line to stop recursive faults in * rcu_lock, notify_die, or atomic_notifier_call_chain */ if (debugger_bpt(regs)) @@ -1158,8 +1158,15 @@ void __kprobes program_check_exception(struct pt_regs *regs) == NOTIFY_STOP) goto bail; + bugaddr = regs->nip; + /* + * Fixup bugaddr for BUG_ON() in real mode + */ + if (!is_kernel_addr(bugaddr) && !(regs->msr & MSR_IR)) + bugaddr += PAGE_OFFSET; + if (!(regs->msr & MSR_PR) && /* not user-mode */ - report_bug(regs->nip, regs) == BUG_TRAP_TYPE_WARN) { + report_bug(bugaddr, regs) == BUG_TRAP_TYPE_WARN) { regs->nip += 4; goto bail; } @@ -1394,7 +1401,7 @@ void facility_unavailable_exception(struct pt_regs *regs) * is a read DSCR attempt through a mfspr instruction, we * just emulate the instruction instead. This code path will * always emulate all the mfspr instructions till the user - * has attempted atleast one mtspr instruction. This way it + * has attempted at least one mtspr instruction. This way it * preserves the same behaviour when the user is accessing * the DSCR through privilege level only SPR number (0x11) * which is emulated through illegal instruction exception. diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S index 162d0f714..1c2e7a343 100644 --- a/arch/powerpc/kernel/vector.S +++ b/arch/powerpc/kernel/vector.S @@ -91,6 +91,10 @@ _GLOBAL(load_up_altivec) oris r12,r12,MSR_VEC@h std r12,_MSR(r1) #endif + /* Don't care if r4 overflows, this is desired behaviour */ + lbz r4,THREAD_LOAD_VEC(r5) + addi r4,r4,1 + stb r4,THREAD_LOAD_VEC(r5) addi r6,r5,THREAD_VRSTATE li r4,1 li r10,VRSTATE_VSCR @@ -102,36 +106,20 @@ _GLOBAL(load_up_altivec) blr /* - * __giveup_altivec(tsk) - * Disable VMX for the task given as the argument, - * and save the vector registers in its thread_struct. + * save_altivec(tsk) + * Save the vector registers to its thread_struct */ -_GLOBAL(__giveup_altivec) +_GLOBAL(save_altivec) addi r3,r3,THREAD /* want THREAD of task */ PPC_LL r7,THREAD_VRSAVEAREA(r3) PPC_LL r5,PT_REGS(r3) PPC_LCMPI 0,r7,0 bne 2f addi r7,r3,THREAD_VRSTATE -2: PPC_LCMPI 0,r5,0 - SAVE_32VRS(0,r4,r7) +2: SAVE_32VRS(0,r4,r7) mfvscr v0 li r4,VRSTATE_VSCR stvx v0,r4,r7 - beq 1f - PPC_LL r4,_MSR-STACK_FRAME_OVERHEAD(r5) -#ifdef CONFIG_VSX -BEGIN_FTR_SECTION - lis r3,(MSR_VEC|MSR_VSX)@h -FTR_SECTION_ELSE - lis r3,MSR_VEC@h -ALT_FTR_SECTION_END_IFSET(CPU_FTR_VSX) -#else - lis r3,MSR_VEC@h -#endif - andc r4,r4,r3 /* disable FP for previous task */ - PPC_STL r4,_MSR-STACK_FRAME_OVERHEAD(r5) -1: blr #ifdef CONFIG_VSX @@ -163,23 +151,6 @@ _GLOBAL(load_up_vsx) std r12,_MSR(r1) b fast_exception_return -/* - * __giveup_vsx(tsk) - * Disable VSX for the task given as the argument. - * Does NOT save vsx registers. - */ -_GLOBAL(__giveup_vsx) - addi r3,r3,THREAD /* want THREAD of task */ - ld r5,PT_REGS(r3) - cmpdi 0,r5,0 - beq 1f - ld r4,_MSR-STACK_FRAME_OVERHEAD(r5) - lis r3,MSR_VSX@h - andc r4,r4,r3 /* disable VSX for previous task */ - std r4,_MSR-STACK_FRAME_OVERHEAD(r5) -1: - blr - #endif /* CONFIG_VSX */ diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index d41fd0af8..2dd91f79d 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -55,6 +55,7 @@ SECTIONS LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT + SOFTIRQENTRY_TEXT #ifdef CONFIG_PPC32 *(.got1) |