diff options
Diffstat (limited to 'arch/powerpc/kernel')
76 files changed, 2399 insertions, 1774 deletions
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index fcc9a89a469..670c312d914 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -2,6 +2,7 @@ # Makefile for the linux kernel. # +CFLAGS_prom.o = -I$(src)/../../../scripts/dtc/libfdt CFLAGS_ptrace.o += -DUTS_MACHINE='"$(UTS_MACHINE)"' subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror @@ -42,7 +43,6 @@ obj-$(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 obj-$(CONFIG_PPC64) += vdso64/ obj-$(CONFIG_ALTIVEC) += vecemu.o obj-$(CONFIG_PPC_970_NAP) += idle_power4.o diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c index de91f3ae631..34f55524d45 100644 --- a/arch/powerpc/kernel/align.c +++ b/arch/powerpc/kernel/align.c @@ -25,14 +25,13 @@ #include <asm/cputable.h> #include <asm/emulated_ops.h> #include <asm/switch_to.h> +#include <asm/disassemble.h> struct aligninfo { unsigned char len; unsigned char flags; }; -#define IS_XFORM(inst) (((inst) >> 26) == 31) -#define IS_DSFORM(inst) (((inst) >> 26) >= 56) #define INVALID { 0, 0 } @@ -73,7 +72,7 @@ static struct aligninfo aligninfo[128] = { { 8, LD+F }, /* 00 0 1001: lfd */ { 4, ST+F+S }, /* 00 0 1010: stfs */ { 8, ST+F }, /* 00 0 1011: stfd */ - INVALID, /* 00 0 1100 */ + { 16, LD }, /* 00 0 1100: lq */ { 8, LD }, /* 00 0 1101: ld/ldu/lwa */ INVALID, /* 00 0 1110 */ { 8, ST }, /* 00 0 1111: std/stdu */ @@ -140,7 +139,7 @@ static struct aligninfo aligninfo[128] = { { 2, LD+SW }, /* 10 0 1100: lhbrx */ { 4, LD+SE }, /* 10 0 1101 lwa */ { 2, ST+SW }, /* 10 0 1110: sthbrx */ - INVALID, /* 10 0 1111 */ + { 16, ST }, /* 10 0 1111: stq */ INVALID, /* 10 1 0000 */ INVALID, /* 10 1 0001 */ INVALID, /* 10 1 0010 */ @@ -192,37 +191,6 @@ static struct aligninfo aligninfo[128] = { }; /* - * Create a DSISR value from the instruction - */ -static inline unsigned make_dsisr(unsigned instr) -{ - unsigned dsisr; - - - /* bits 6:15 --> 22:31 */ - dsisr = (instr & 0x03ff0000) >> 16; - - if (IS_XFORM(instr)) { - /* bits 29:30 --> 15:16 */ - dsisr |= (instr & 0x00000006) << 14; - /* bit 25 --> 17 */ - dsisr |= (instr & 0x00000040) << 8; - /* bits 21:24 --> 18:21 */ - dsisr |= (instr & 0x00000780) << 3; - } else { - /* bit 5 --> 17 */ - dsisr |= (instr & 0x04000000) >> 12; - /* bits 1: 4 --> 18:21 */ - dsisr |= (instr & 0x78000000) >> 17; - /* bits 30:31 --> 12:13 */ - if (IS_DSFORM(instr)) - dsisr |= (instr & 0x00000003) << 18; - } - - return dsisr; -} - -/* * The dcbz (data cache block zero) instruction * gives an alignment fault if used on non-cacheable * memory. We handle the fault mainly for the @@ -385,8 +353,6 @@ static int emulate_fp_pair(unsigned char __user *addr, unsigned int reg, char *ptr1 = (char *) ¤t->thread.TS_FPR(reg+1); int i, ret, sw = 0; - if (!(flags & F)) - return 0; if (reg & 1) return 0; /* invalid form: FRS/FRT must be even */ if (flags & SW) @@ -406,6 +372,34 @@ static int emulate_fp_pair(unsigned char __user *addr, unsigned int reg, return 1; /* exception handled and fixed up */ } +#ifdef CONFIG_PPC64 +static int emulate_lq_stq(struct pt_regs *regs, unsigned char __user *addr, + unsigned int reg, unsigned int flags) +{ + char *ptr0 = (char *)®s->gpr[reg]; + char *ptr1 = (char *)®s->gpr[reg+1]; + int i, ret, sw = 0; + + if (reg & 1) + return 0; /* invalid form: GPR must be even */ + if (flags & SW) + sw = 7; + ret = 0; + for (i = 0; i < 8; ++i) { + if (!(flags & ST)) { + ret |= __get_user(ptr0[i^sw], addr + i); + ret |= __get_user(ptr1[i^sw], addr + i + 8); + } else { + ret |= __put_user(ptr0[i^sw], addr + i); + ret |= __put_user(ptr1[i^sw], addr + i + 8); + } + } + if (ret) + return -EFAULT; + return 1; /* exception handled and fixed up */ +} +#endif /* CONFIG_PPC64 */ + #ifdef CONFIG_SPE static struct aligninfo spe_aligninfo[32] = { @@ -914,10 +908,20 @@ int fix_alignment(struct pt_regs *regs) flush_fp_to_thread(current); } - /* Special case for 16-byte FP loads and stores */ - if (nb == 16) { - PPC_WARN_ALIGNMENT(fp_pair, regs); - return emulate_fp_pair(addr, reg, flags); + if ((nb == 16)) { + if (flags & F) { + /* Special case for 16-byte FP loads and stores */ + PPC_WARN_ALIGNMENT(fp_pair, regs); + return emulate_fp_pair(addr, reg, flags); + } else { +#ifdef CONFIG_PPC64 + /* Special case for 16-byte loads and stores */ + PPC_WARN_ALIGNMENT(lq_stq, regs); + return emulate_lq_stq(regs, addr, reg, flags); +#else + return 0; +#endif + } } PPC_WARN_ALIGNMENT(unaligned, regs); diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index b5aacf72ae6..f5995a91221 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -54,6 +54,7 @@ #endif #if defined(CONFIG_KVM) && defined(CONFIG_PPC_BOOK3S) #include <asm/kvm_book3s.h> +#include <asm/kvm_ppc.h> #endif #ifdef CONFIG_PPC32 @@ -247,13 +248,14 @@ int main(void) #endif DEFINE(PACAHWCPUID, offsetof(struct paca_struct, hw_cpu_id)); DEFINE(PACAKEXECSTATE, offsetof(struct paca_struct, kexec_state)); + DEFINE(PACA_DSCR, offsetof(struct paca_struct, dscr_default)); DEFINE(PACA_STARTTIME, offsetof(struct paca_struct, starttime)); DEFINE(PACA_STARTTIME_USER, offsetof(struct paca_struct, starttime_user)); DEFINE(PACA_USER_TIME, offsetof(struct paca_struct, user_time)); DEFINE(PACA_SYSTEM_TIME, offsetof(struct paca_struct, system_time)); DEFINE(PACA_TRAP_SAVE, offsetof(struct paca_struct, trap_save)); DEFINE(PACA_NAPSTATELOST, offsetof(struct paca_struct, nap_state_lost)); - DEFINE(PACA_SPRG3, offsetof(struct paca_struct, sprg3)); + DEFINE(PACA_SPRG_VDSO, offsetof(struct paca_struct, sprg_vdso)); #endif /* CONFIG_PPC64 */ /* RTAS */ @@ -445,7 +447,9 @@ int main(void) DEFINE(VCPU_XER, offsetof(struct kvm_vcpu, arch.xer)); DEFINE(VCPU_CTR, offsetof(struct kvm_vcpu, arch.ctr)); DEFINE(VCPU_LR, offsetof(struct kvm_vcpu, arch.lr)); +#ifdef CONFIG_PPC_BOOK3S DEFINE(VCPU_TAR, offsetof(struct kvm_vcpu, arch.tar)); +#endif DEFINE(VCPU_CR, offsetof(struct kvm_vcpu, arch.cr)); DEFINE(VCPU_PC, offsetof(struct kvm_vcpu, arch.pc)); #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE @@ -467,6 +471,9 @@ int main(void) DEFINE(VCPU_SHARED, offsetof(struct kvm_vcpu, arch.shared)); DEFINE(VCPU_SHARED_MSR, offsetof(struct kvm_vcpu_arch_shared, msr)); DEFINE(VCPU_SHADOW_MSR, offsetof(struct kvm_vcpu, arch.shadow_msr)); +#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_KVM_BOOK3S_PR_POSSIBLE) + DEFINE(VCPU_SHAREDBE, offsetof(struct kvm_vcpu, arch.shared_big_endian)); +#endif DEFINE(VCPU_SHARED_MAS0, offsetof(struct kvm_vcpu_arch_shared, mas0)); DEFINE(VCPU_SHARED_MAS1, offsetof(struct kvm_vcpu_arch_shared, mas1)); @@ -493,7 +500,6 @@ int main(void) DEFINE(VCPU_DAR, offsetof(struct kvm_vcpu, arch.shregs.dar)); DEFINE(VCPU_VPA, offsetof(struct kvm_vcpu, arch.vpa.pinned_addr)); DEFINE(VCPU_VPA_DIRTY, offsetof(struct kvm_vcpu, arch.vpa.dirty)); - DEFINE(VCPU_INTR_MSR, offsetof(struct kvm_vcpu, arch.intr_msr)); #endif #ifdef CONFIG_PPC_BOOK3S DEFINE(VCPU_VCPUID, offsetof(struct kvm_vcpu, vcpu_id)); @@ -528,11 +534,13 @@ int main(void) DEFINE(VCPU_SLB_NR, offsetof(struct kvm_vcpu, arch.slb_nr)); DEFINE(VCPU_FAULT_DSISR, offsetof(struct kvm_vcpu, arch.fault_dsisr)); DEFINE(VCPU_FAULT_DAR, offsetof(struct kvm_vcpu, arch.fault_dar)); + DEFINE(VCPU_INTR_MSR, offsetof(struct kvm_vcpu, arch.intr_msr)); DEFINE(VCPU_LAST_INST, offsetof(struct kvm_vcpu, arch.last_inst)); DEFINE(VCPU_TRAP, offsetof(struct kvm_vcpu, arch.trap)); DEFINE(VCPU_CFAR, offsetof(struct kvm_vcpu, arch.cfar)); DEFINE(VCPU_PPR, offsetof(struct kvm_vcpu, arch.ppr)); DEFINE(VCPU_FSCR, offsetof(struct kvm_vcpu, arch.fscr)); + DEFINE(VCPU_SHADOW_FSCR, offsetof(struct kvm_vcpu, arch.shadow_fscr)); DEFINE(VCPU_PSPB, offsetof(struct kvm_vcpu, arch.pspb)); DEFINE(VCPU_EBBHR, offsetof(struct kvm_vcpu, arch.ebbhr)); DEFINE(VCPU_EBBRR, offsetof(struct kvm_vcpu, arch.ebbrr)); @@ -614,6 +622,7 @@ int main(void) #ifdef CONFIG_PPC64 SVCPU_FIELD(SVCPU_SLB, slb); SVCPU_FIELD(SVCPU_SLB_MAX, slb_max); + SVCPU_FIELD(SVCPU_SHADOW_FSCR, shadow_fscr); #endif HSTATE_FIELD(HSTATE_HOST_R1, host_r1); @@ -649,6 +658,7 @@ int main(void) #ifdef CONFIG_PPC_BOOK3S_64 HSTATE_FIELD(HSTATE_CFAR, cfar); HSTATE_FIELD(HSTATE_PPR, ppr); + HSTATE_FIELD(HSTATE_HOST_FSCR, host_fscr); #endif /* CONFIG_PPC_BOOK3S_64 */ #else /* CONFIG_PPC_BOOK3S */ diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c index 2912b8787aa..40198d50b4c 100644 --- a/arch/powerpc/kernel/cacheinfo.c +++ b/arch/powerpc/kernel/cacheinfo.c @@ -756,7 +756,10 @@ void cacheinfo_cpu_online(unsigned int cpu_id) cacheinfo_sysfs_populate(cpu_id, cache); } -#ifdef CONFIG_HOTPLUG_CPU /* functions needed for cpu offline */ +/* functions needed to remove cache entry for cpu offline or suspend/resume */ + +#if (defined(CONFIG_PPC_PSERIES) && defined(CONFIG_SUSPEND)) || \ + defined(CONFIG_HOTPLUG_CPU) static struct cache *cache_lookup_by_cpu(unsigned int cpu_id) { @@ -843,4 +846,4 @@ void cacheinfo_cpu_offline(unsigned int cpu_id) if (cache) cache_cpu_clear(cache, cpu_id); } -#endif /* CONFIG_HOTPLUG_CPU */ +#endif /* (CONFIG_PPC_PSERIES && CONFIG_SUSPEND) || CONFIG_HOTPLUG_CPU */ diff --git a/arch/powerpc/kernel/cpu_setup_a2.S b/arch/powerpc/kernel/cpu_setup_a2.S deleted file mode 100644 index 61f079e05b6..00000000000 --- a/arch/powerpc/kernel/cpu_setup_a2.S +++ /dev/null @@ -1,120 +0,0 @@ -/* - * A2 specific assembly support code - * - * Copyright 2009 Ben Herrenschmidt, IBM Corp. - * - * 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. - */ - -#include <asm/asm-offsets.h> -#include <asm/ppc_asm.h> -#include <asm/ppc-opcode.h> -#include <asm/processor.h> -#include <asm/reg_a2.h> -#include <asm/reg.h> -#include <asm/thread_info.h> - -/* - * Disable thdid and class fields in ERATs to bump PID to full 14 bits capacity. - * This also prevents external LPID accesses but that isn't a problem when not a - * guest. Under PV, this setting will be ignored and MMUCR will return the right - * number of PID bits we can use. - */ -#define MMUCR1_EXTEND_PID \ - (MMUCR1_ICTID | MMUCR1_ITTID | MMUCR1_DCTID | \ - MMUCR1_DTTID | MMUCR1_DCCD) - -/* - * Use extended PIDs if enabled. - * Don't clear the ERATs on context sync events and enable I & D LRU. - * Enable ERAT back invalidate when tlbwe overwrites an entry. - */ -#define INITIAL_MMUCR1 \ - (MMUCR1_EXTEND_PID | MMUCR1_CSINV_NEVER | MMUCR1_IRRE | \ - MMUCR1_DRRE | MMUCR1_TLBWE_BINV) - -_GLOBAL(__setup_cpu_a2) - /* Some of these are actually thread local and some are - * core local but doing it always won't hurt - */ - -#ifdef CONFIG_PPC_ICSWX - /* Make sure ACOP starts out as zero */ - li r3,0 - mtspr SPRN_ACOP,r3 - - /* Skip the following if we are in Guest mode */ - mfmsr r3 - andis. r0,r3,MSR_GS@h - bne _icswx_skip_guest - - /* Enable icswx instruction */ - mfspr r3,SPRN_A2_CCR2 - ori r3,r3,A2_CCR2_ENABLE_ICSWX - mtspr SPRN_A2_CCR2,r3 - - /* Unmask all CTs in HACOP */ - li r3,-1 - mtspr SPRN_HACOP,r3 -_icswx_skip_guest: -#endif /* CONFIG_PPC_ICSWX */ - - /* Enable doorbell */ - mfspr r3,SPRN_A2_CCR2 - oris r3,r3,A2_CCR2_ENABLE_PC@h - mtspr SPRN_A2_CCR2,r3 - isync - - /* Setup CCR0 to disable power saving for now as it's busted - * in the current implementations. Setup CCR1 to wake on - * interrupts normally (we write the default value but who - * knows what FW may have clobbered...) - */ - li r3,0 - mtspr SPRN_A2_CCR0, r3 - LOAD_REG_IMMEDIATE(r3,0x0f0f0f0f) - mtspr SPRN_A2_CCR1, r3 - - /* Initialise MMUCR1 */ - lis r3,INITIAL_MMUCR1@h - ori r3,r3,INITIAL_MMUCR1@l - mtspr SPRN_MMUCR1,r3 - - /* Set MMUCR2 to enable 4K, 64K, 1M, 16M and 1G pages */ - LOAD_REG_IMMEDIATE(r3, 0x000a7531) - mtspr SPRN_MMUCR2,r3 - - /* Set MMUCR3 to write all thids bit to the TLB */ - LOAD_REG_IMMEDIATE(r3, 0x0000000f) - mtspr SPRN_MMUCR3,r3 - - /* Don't do ERAT stuff if running guest mode */ - mfmsr r3 - andis. r0,r3,MSR_GS@h - bne 1f - - /* Now set the I-ERAT watermark to 15 */ - lis r4,(MMUCR0_TLBSEL_I|MMUCR0_ECL)@h - mtspr SPRN_MMUCR0, r4 - li r4,A2_IERAT_SIZE-1 - PPC_ERATWE(R4,R4,3) - - /* Now set the D-ERAT watermark to 31 */ - lis r4,(MMUCR0_TLBSEL_D|MMUCR0_ECL)@h - mtspr SPRN_MMUCR0, r4 - li r4,A2_DERAT_SIZE-1 - PPC_ERATWE(R4,R4,3) - - /* And invalidate the beast just in case. That won't get rid of - * a bolted entry though it will be in LRU and so will go away eventually - * but let's not bother for now - */ - PPC_ERATILX(0,0,R0) -1: - blr - -_GLOBAL(__restore_cpu_a2) - b __setup_cpu_a2 diff --git a/arch/powerpc/kernel/cpu_setup_fsl_booke.S b/arch/powerpc/kernel/cpu_setup_fsl_booke.S index cc2d8962e09..4f1393d2007 100644 --- a/arch/powerpc/kernel/cpu_setup_fsl_booke.S +++ b/arch/powerpc/kernel/cpu_setup_fsl_booke.S @@ -94,12 +94,12 @@ _GLOBAL(setup_altivec_idle) _GLOBAL(__setup_cpu_e6500) mflr r6 #ifdef CONFIG_PPC64 - bl .setup_altivec_ivors + 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 + bl setup_lrat_ivor 1: #endif bl setup_pw20_idle @@ -164,15 +164,15 @@ _GLOBAL(__setup_cpu_e5500) #ifdef CONFIG_PPC_BOOK3E_64 _GLOBAL(__restore_cpu_e6500) mflr r5 - bl .setup_altivec_ivors + 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 + bl setup_lrat_ivor 1: - bl .setup_pw20_idle - bl .setup_altivec_idle + bl setup_pw20_idle + bl setup_altivec_idle bl __restore_cpu_e5500 mtlr r5 blr @@ -181,9 +181,9 @@ _GLOBAL(__restore_cpu_e5500) mflr r4 bl __e500_icache_setup bl __e500_dcache_setup - bl .__setup_base_ivors - bl .setup_perfmon_ivor - bl .setup_doorbell_ivors + bl __setup_base_ivors + bl setup_perfmon_ivor + bl setup_doorbell_ivors /* * We only want to touch IVOR38-41 if we're running on hardware * that supports category E.HV. The architectural way to determine @@ -192,7 +192,7 @@ _GLOBAL(__restore_cpu_e5500) mfspr r10,SPRN_MMUCFG rlwinm. r10,r10,0,MMUCFG_LPIDSIZE beq 1f - bl .setup_ehv_ivors + bl setup_ehv_ivors 1: mtlr r4 blr @@ -201,9 +201,9 @@ _GLOBAL(__setup_cpu_e5500) mflr r5 bl __e500_icache_setup bl __e500_dcache_setup - bl .__setup_base_ivors - bl .setup_perfmon_ivor - bl .setup_doorbell_ivors + bl __setup_base_ivors + bl setup_perfmon_ivor + bl setup_doorbell_ivors /* * We only want to touch IVOR38-41 if we're running on hardware * that supports category E.HV. The architectural way to determine @@ -212,7 +212,7 @@ _GLOBAL(__setup_cpu_e5500) mfspr r10,SPRN_MMUCFG rlwinm. r10,r10,0,MMUCFG_LPIDSIZE beq 1f - bl .setup_ehv_ivors + bl setup_ehv_ivors b 2f 1: ld r10,CPU_SPEC_FEATURES(r4) diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S index 37d1bb002aa..46733535cc0 100644 --- a/arch/powerpc/kernel/cpu_setup_power.S +++ b/arch/powerpc/kernel/cpu_setup_power.S @@ -56,7 +56,7 @@ _GLOBAL(__setup_cpu_power8) li r0,0 mtspr SPRN_LPID,r0 mfspr r3,SPRN_LPCR - oris r3, r3, LPCR_AIL_3@h + ori r3, r3, LPCR_PECEDH bl __init_LPCR bl __init_HFSCR bl __init_tlb_power8 @@ -75,7 +75,7 @@ _GLOBAL(__restore_cpu_power8) li r0,0 mtspr SPRN_LPID,r0 mfspr r3,SPRN_LPCR - oris r3, r3, LPCR_AIL_3@h + ori r3, r3, LPCR_PECEDH bl __init_LPCR bl __init_HFSCR bl __init_tlb_power8 diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 6c8dd5da4de..0c157642c2a 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -109,7 +109,8 @@ extern void __restore_cpu_e6500(void); PPC_FEATURE_PSERIES_PERFMON_COMPAT) #define COMMON_USER2_POWER8 (PPC_FEATURE2_ARCH_2_07 | \ PPC_FEATURE2_HTM_COMP | PPC_FEATURE2_DSCR | \ - PPC_FEATURE2_ISEL | PPC_FEATURE2_TAR) + PPC_FEATURE2_ISEL | PPC_FEATURE2_TAR | \ + PPC_FEATURE2_VEC_CRYPTO) #define COMMON_USER_PA6T (COMMON_USER_PPC64 | PPC_FEATURE_PA6T |\ PPC_FEATURE_TRUE_LE | \ PPC_FEATURE_HAS_ALTIVEC_COMP) @@ -510,7 +511,27 @@ static struct cpu_spec __initdata cpu_specs[] = { .pvr_mask = 0xffff0000, .pvr_value = 0x004b0000, .cpu_name = "POWER8E (raw)", - .cpu_features = CPU_FTRS_POWER8, + .cpu_features = CPU_FTRS_POWER8E, + .cpu_user_features = COMMON_USER_POWER8, + .cpu_user_features2 = COMMON_USER2_POWER8, + .mmu_features = MMU_FTRS_POWER8, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .pmc_type = PPC_PMC_IBM, + .oprofile_cpu_type = "ppc64/power8", + .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 DD1: Does not support doorbell IPIs */ + .pvr_mask = 0xffffff00, + .pvr_value = 0x004d0100, + .cpu_name = "POWER8 (raw)", + .cpu_features = CPU_FTRS_POWER8_DD1, .cpu_user_features = COMMON_USER_POWER8, .cpu_user_features2 = COMMON_USER2_POWER8, .mmu_features = MMU_FTRS_POWER8, @@ -2148,44 +2169,6 @@ static struct cpu_spec __initdata cpu_specs[] = { } #endif /* CONFIG_PPC32 */ #endif /* CONFIG_E500 */ - -#ifdef CONFIG_PPC_A2 - { /* Standard A2 (>= DD2) + FPU core */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x00480000, - .cpu_name = "A2 (>= DD2)", - .cpu_features = CPU_FTRS_A2, - .cpu_user_features = COMMON_USER_PPC64, - .mmu_features = MMU_FTRS_A2, - .icache_bsize = 64, - .dcache_bsize = 64, - .num_pmcs = 0, - .cpu_setup = __setup_cpu_a2, - .cpu_restore = __restore_cpu_a2, - .machine_check = machine_check_generic, - .platform = "ppca2", - }, - { /* This is a default entry to get going, to be replaced by - * a real one at some stage - */ -#define CPU_FTRS_BASE_BOOK3E (CPU_FTR_USE_TB | \ - CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_SMT | \ - CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE) - .pvr_mask = 0x00000000, - .pvr_value = 0x00000000, - .cpu_name = "Book3E", - .cpu_features = CPU_FTRS_BASE_BOOK3E, - .cpu_user_features = COMMON_USER_PPC64, - .mmu_features = MMU_FTR_TYPE_3E | MMU_FTR_USE_TLBILX | - MMU_FTR_USE_TLBIVAX_BCAST | - MMU_FTR_LOCK_BCAST_INVAL, - .icache_bsize = 64, - .dcache_bsize = 64, - .num_pmcs = 0, - .machine_check = machine_check_generic, - .platform = "power6", - }, -#endif /* CONFIG_PPC_A2 */ }; static struct cpu_spec the_cpu_spec; diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c index 18d7c80ddeb..51dbace3269 100644 --- a/arch/powerpc/kernel/crash.c +++ b/arch/powerpc/kernel/crash.c @@ -81,7 +81,7 @@ void crash_ipi_callback(struct pt_regs *regs) } atomic_inc(&cpus_in_crash); - smp_mb__after_atomic_inc(); + smp_mb__after_atomic(); /* * Starting the kdump boot. diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c index 11c1d069d92..7a13f378ca2 100644 --- a/arch/powerpc/kernel/crash_dump.c +++ b/arch/powerpc/kernel/crash_dump.c @@ -98,17 +98,19 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf, size_t csize, unsigned long offset, int userbuf) { void *vaddr; + phys_addr_t paddr; if (!csize) return 0; csize = min_t(size_t, csize, PAGE_SIZE); + paddr = pfn << PAGE_SHIFT; - if ((min_low_pfn < pfn) && (pfn < max_pfn)) { - vaddr = __va(pfn << PAGE_SHIFT); + if (memblock_is_region_memory(paddr, csize)) { + vaddr = __va(paddr); csize = copy_oldmem_vaddr(vaddr, buf, csize, offset, userbuf); } else { - vaddr = __ioremap(pfn << PAGE_SHIFT, PAGE_SIZE, 0); + vaddr = __ioremap(paddr, PAGE_SIZE, 0); csize = copy_oldmem_vaddr(vaddr, buf, csize, offset, userbuf); iounmap(vaddr); } diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c index 8032b97ccdc..ee78f6e49d6 100644 --- a/arch/powerpc/kernel/dma.c +++ b/arch/powerpc/kernel/dma.c @@ -191,12 +191,10 @@ EXPORT_SYMBOL(dma_direct_ops); #define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16) -int dma_set_mask(struct device *dev, u64 dma_mask) +int __dma_set_mask(struct device *dev, u64 dma_mask) { struct dma_map_ops *dma_ops = get_dma_ops(dev); - if (ppc_md.dma_set_mask) - return ppc_md.dma_set_mask(dev, dma_mask); if ((dma_ops != NULL) && (dma_ops->set_dma_mask != NULL)) return dma_ops->set_dma_mask(dev, dma_mask); if (!dev->dma_mask || !dma_supported(dev, dma_mask)) @@ -204,6 +202,12 @@ int dma_set_mask(struct device *dev, u64 dma_mask) *dev->dma_mask = dma_mask; return 0; } +int dma_set_mask(struct device *dev, u64 dma_mask) +{ + if (ppc_md.dma_set_mask) + return ppc_md.dma_set_mask(dev, dma_mask); + return __dma_set_mask(dev, dma_mask); +} EXPORT_SYMBOL(dma_set_mask); u64 dma_get_required_mask(struct device *dev) diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 148db72a8c4..86e25702aac 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -22,18 +22,21 @@ */ #include <linux/delay.h> +#include <linux/debugfs.h> #include <linux/sched.h> #include <linux/init.h> #include <linux/list.h> #include <linux/pci.h> #include <linux/proc_fs.h> #include <linux/rbtree.h> +#include <linux/reboot.h> #include <linux/seq_file.h> #include <linux/spinlock.h> #include <linux/export.h> #include <linux/of.h> #include <linux/atomic.h> +#include <asm/debug.h> #include <asm/eeh.h> #include <asm/eeh_event.h> #include <asm/io.h> @@ -86,22 +89,21 @@ /* Time to wait for a PCI slot to report status, in milliseconds */ #define PCI_BUS_RESET_WAIT_MSEC (5*60*1000) -/* Platform dependent EEH operations */ -struct eeh_ops *eeh_ops = NULL; - -int eeh_subsystem_enabled; -EXPORT_SYMBOL(eeh_subsystem_enabled); - /* - * EEH probe mode support. The intention is to support multiple - * platforms for EEH. Some platforms like pSeries do PCI emunation - * based on device tree. However, other platforms like powernv probe - * PCI devices from hardware. The flag is used to distinguish that. - * In addition, struct eeh_ops::probe would be invoked for particular - * OF node or PCI device so that the corresponding PE would be created - * there. + * EEH probe mode support, which is part of the flags, + * is to support multiple platforms for EEH. Some platforms + * like pSeries do PCI emunation based on device tree. + * However, other platforms like powernv probe PCI devices + * from hardware. The flag is used to distinguish that. + * In addition, struct eeh_ops::probe would be invoked for + * particular OF node or PCI device so that the corresponding + * PE would be created there. */ -int eeh_probe_mode; +int eeh_subsystem_flags; +EXPORT_SYMBOL(eeh_subsystem_flags); + +/* Platform dependent EEH operations */ +struct eeh_ops *eeh_ops = NULL; /* Lock to avoid races due to multiple reports of an error */ DEFINE_RAW_SPINLOCK(confirm_error_lock); @@ -132,6 +134,15 @@ static struct eeh_stats eeh_stats; #define IS_BRIDGE(class_code) (((class_code)<<16) == PCI_BASE_CLASS_BRIDGE) +static int __init eeh_setup(char *str) +{ + if (!strcmp(str, "off")) + eeh_subsystem_flags |= EEH_FORCE_DISABLED; + + return 1; +} +__setup("eeh=", eeh_setup); + /** * eeh_gather_pci_data - Copy assorted PCI config space registers to buff * @edev: device to report data for @@ -144,73 +155,67 @@ static struct eeh_stats eeh_stats; static size_t eeh_gather_pci_data(struct eeh_dev *edev, char * buf, size_t len) { struct device_node *dn = eeh_dev_to_of_node(edev); - struct pci_dev *dev = eeh_dev_to_pci_dev(edev); u32 cfg; int cap, i; int n = 0; n += scnprintf(buf+n, len-n, "%s\n", dn->full_name); - printk(KERN_WARNING "EEH: of node=%s\n", dn->full_name); + pr_warn("EEH: of node=%s\n", dn->full_name); eeh_ops->read_config(dn, PCI_VENDOR_ID, 4, &cfg); n += scnprintf(buf+n, len-n, "dev/vend:%08x\n", cfg); - printk(KERN_WARNING "EEH: PCI device/vendor: %08x\n", cfg); + pr_warn("EEH: PCI device/vendor: %08x\n", cfg); eeh_ops->read_config(dn, PCI_COMMAND, 4, &cfg); n += scnprintf(buf+n, len-n, "cmd/stat:%x\n", cfg); - printk(KERN_WARNING "EEH: PCI cmd/status register: %08x\n", cfg); - - if (!dev) { - printk(KERN_WARNING "EEH: no PCI device for this of node\n"); - return n; - } + pr_warn("EEH: PCI cmd/status register: %08x\n", cfg); /* Gather bridge-specific registers */ - if (dev->class >> 16 == PCI_BASE_CLASS_BRIDGE) { + if (edev->mode & EEH_DEV_BRIDGE) { eeh_ops->read_config(dn, PCI_SEC_STATUS, 2, &cfg); n += scnprintf(buf+n, len-n, "sec stat:%x\n", cfg); - printk(KERN_WARNING "EEH: Bridge secondary status: %04x\n", cfg); + pr_warn("EEH: Bridge secondary status: %04x\n", cfg); eeh_ops->read_config(dn, PCI_BRIDGE_CONTROL, 2, &cfg); n += scnprintf(buf+n, len-n, "brdg ctl:%x\n", cfg); - printk(KERN_WARNING "EEH: Bridge control: %04x\n", cfg); + pr_warn("EEH: Bridge control: %04x\n", cfg); } /* Dump out the PCI-X command and status regs */ - cap = pci_find_capability(dev, PCI_CAP_ID_PCIX); + cap = edev->pcix_cap; if (cap) { eeh_ops->read_config(dn, cap, 4, &cfg); n += scnprintf(buf+n, len-n, "pcix-cmd:%x\n", cfg); - printk(KERN_WARNING "EEH: PCI-X cmd: %08x\n", cfg); + pr_warn("EEH: PCI-X cmd: %08x\n", cfg); eeh_ops->read_config(dn, cap+4, 4, &cfg); n += scnprintf(buf+n, len-n, "pcix-stat:%x\n", cfg); - printk(KERN_WARNING "EEH: PCI-X status: %08x\n", cfg); + pr_warn("EEH: PCI-X status: %08x\n", cfg); } - /* If PCI-E capable, dump PCI-E cap 10, and the AER */ - if (pci_is_pcie(dev)) { + /* If PCI-E capable, dump PCI-E cap 10 */ + cap = edev->pcie_cap; + if (cap) { n += scnprintf(buf+n, len-n, "pci-e cap10:\n"); - printk(KERN_WARNING - "EEH: PCI-E capabilities and status follow:\n"); + pr_warn("EEH: PCI-E capabilities and status follow:\n"); for (i=0; i<=8; i++) { - eeh_ops->read_config(dn, dev->pcie_cap+4*i, 4, &cfg); + eeh_ops->read_config(dn, cap+4*i, 4, &cfg); n += scnprintf(buf+n, len-n, "%02x:%x\n", 4*i, cfg); - printk(KERN_WARNING "EEH: PCI-E %02x: %08x\n", i, cfg); + pr_warn("EEH: PCI-E %02x: %08x\n", i, cfg); } + } + + /* If AER capable, dump it */ + cap = edev->aer_cap; + if (cap) { + n += scnprintf(buf+n, len-n, "pci-e AER:\n"); + pr_warn("EEH: PCI-E AER capability register set follows:\n"); - cap = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR); - if (cap) { - n += scnprintf(buf+n, len-n, "pci-e AER:\n"); - printk(KERN_WARNING - "EEH: PCI-E AER capability register set follows:\n"); - - for (i=0; i<14; i++) { - eeh_ops->read_config(dn, cap+4*i, 4, &cfg); - n += scnprintf(buf+n, len-n, "%02x:%x\n", 4*i, cfg); - printk(KERN_WARNING "EEH: PCI-E AER %02x: %08x\n", i, cfg); - } + for (i=0; i<14; i++) { + eeh_ops->read_config(dn, cap+4*i, 4, &cfg); + n += scnprintf(buf+n, len-n, "%02x:%x\n", 4*i, cfg); + pr_warn("EEH: PCI-E AER %02x: %08x\n", i, cfg); } } @@ -231,21 +236,19 @@ void eeh_slot_error_detail(struct eeh_pe *pe, int severity) { size_t loglen = 0; struct eeh_dev *edev, *tmp; - bool valid_cfg_log = true; /* * When the PHB is fenced or dead, it's pointless to collect * the data from PCI config space because it should return * 0xFF's. For ER, we still retrieve the data from the PCI * config space. + * + * For pHyp, we have to enable IO for log retrieval. Otherwise, + * 0xFF's is always returned from PCI config space. */ - if (eeh_probe_mode_dev() && - (pe->type & EEH_PE_PHB) && - (pe->state & (EEH_PE_ISOLATED | EEH_PE_PHB_DEAD))) - valid_cfg_log = false; - - if (valid_cfg_log) { - eeh_pci_enable(pe, EEH_OPT_THAW_MMIO); + if (!(pe->type & EEH_PE_PHB)) { + if (eeh_probe_mode_devtree()) + eeh_pci_enable(pe, EEH_OPT_THAW_MMIO); eeh_ops->configure_bridge(pe); eeh_pe_restore_bars(pe); @@ -308,7 +311,7 @@ static int eeh_phb_check_failure(struct eeh_pe *pe) /* If the PHB has been in problematic state */ eeh_serialize_lock(&flags); - if (phb_pe->state & (EEH_PE_ISOLATED | EEH_PE_PHB_DEAD)) { + if (phb_pe->state & EEH_PE_ISOLATED) { ret = 0; goto out; } @@ -327,8 +330,8 @@ static int eeh_phb_check_failure(struct eeh_pe *pe) eeh_pe_state_mark(phb_pe, EEH_PE_ISOLATED); eeh_serialize_unlock(flags); - pr_err("EEH: PHB#%x failure detected\n", - phb_pe->phb->global_number); + pr_err("EEH: PHB#%x failure detected, location: %s\n", + phb_pe->phb->global_number, eeh_pe_loc_get(phb_pe)); dump_stack(); eeh_send_failure_event(phb_pe); @@ -355,16 +358,17 @@ out: int eeh_dev_check_failure(struct eeh_dev *edev) { int ret; + int active_flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE); unsigned long flags; struct device_node *dn; struct pci_dev *dev; - struct eeh_pe *pe; + struct eeh_pe *pe, *parent_pe, *phb_pe; int rc = 0; const char *location; eeh_stats.total_mmio_ffs++; - if (!eeh_subsystem_enabled) + if (!eeh_enabled()) return 0; if (!edev) { @@ -436,14 +440,34 @@ int eeh_dev_check_failure(struct eeh_dev *edev) */ if ((ret < 0) || (ret == EEH_STATE_NOT_SUPPORT) || - (ret & (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) == - (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) { + ((ret & active_flags) == active_flags)) { eeh_stats.false_positives++; pe->false_positives++; rc = 0; goto dn_unlock; } + /* + * It should be corner case that the parent PE has been + * put into frozen state as well. We should take care + * that at first. + */ + parent_pe = pe->parent; + while (parent_pe) { + /* Hit the ceiling ? */ + if (parent_pe->type & EEH_PE_PHB) + break; + + /* Frozen parent PE ? */ + ret = eeh_ops->get_state(parent_pe, NULL); + if (ret > 0 && + (ret & active_flags) != active_flags) + pe = parent_pe; + + /* Next parent level */ + parent_pe = parent_pe->parent; + } + eeh_stats.slot_resets++; /* Avoid repeated reports of this failure, including problems @@ -457,8 +481,11 @@ int eeh_dev_check_failure(struct eeh_dev *edev) * a stack trace will help the device-driver authors figure * out what happened. So print that out. */ - pr_err("EEH: Frozen PE#%x detected on PHB#%x\n", - pe->addr, pe->phb->global_number); + phb_pe = eeh_phb_pe_get(pe->phb); + pr_err("EEH: Frozen PHB#%x-PE#%x detected\n", + pe->phb->global_number, pe->addr); + pr_err("EEH: PE location: %s, PHB location: %s\n", + eeh_pe_loc_get(pe), eeh_pe_loc_get(phb_pe)); dump_stack(); eeh_send_failure_event(pe); @@ -514,16 +541,42 @@ EXPORT_SYMBOL(eeh_check_failure); */ int eeh_pci_enable(struct eeh_pe *pe, int function) { - int rc; + int rc, flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE); + + /* + * pHyp doesn't allow to enable IO or DMA on unfrozen PE. + * Also, it's pointless to enable them on unfrozen PE. So + * we have the check here. + */ + if (function == EEH_OPT_THAW_MMIO || + function == EEH_OPT_THAW_DMA) { + rc = eeh_ops->get_state(pe, NULL); + if (rc < 0) + return rc; + + /* Needn't to enable or already enabled */ + if ((rc == EEH_STATE_NOT_SUPPORT) || + ((rc & flags) == flags)) + return 0; + } rc = eeh_ops->set_option(pe, function); if (rc) - pr_warning("%s: Unexpected state change %d on PHB#%d-PE#%x, err=%d\n", - __func__, function, pe->phb->global_number, pe->addr, rc); + pr_warn("%s: Unexpected state change %d on " + "PHB#%d-PE#%x, err=%d\n", + __func__, function, pe->phb->global_number, + pe->addr, rc); rc = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC); - if (rc > 0 && (rc & EEH_STATE_MMIO_ENABLED) && - (function == EEH_OPT_THAW_MMIO)) + if (rc <= 0) + return rc; + + if ((function == EEH_OPT_THAW_MMIO) && + (rc & EEH_STATE_MMIO_ENABLED)) + return 0; + + if ((function == EEH_OPT_THAW_DMA) && + (rc & EEH_STATE_DMA_ENABLED)) return 0; return rc; @@ -611,26 +664,7 @@ static void eeh_reset_pe_once(struct eeh_pe *pe) else eeh_ops->reset(pe, EEH_RESET_HOT); - /* The PCI bus requires that the reset be held high for at least - * a 100 milliseconds. We wait a bit longer 'just in case'. - */ -#define PCI_BUS_RST_HOLD_TIME_MSEC 250 - msleep(PCI_BUS_RST_HOLD_TIME_MSEC); - - /* We might get hit with another EEH freeze as soon as the - * pci slot reset line is dropped. Make sure we don't miss - * these, and clear the flag now. - */ - eeh_pe_state_clear(pe, EEH_PE_ISOLATED); - eeh_ops->reset(pe, EEH_RESET_DEACTIVATE); - - /* After a PCI slot has been reset, the PCI Express spec requires - * a 1.5 second idle time for the bus to stabilize, before starting - * up traffic. - */ -#define PCI_BUS_SETTLE_TIME_MSEC 1800 - msleep(PCI_BUS_SETTLE_TIME_MSEC); } /** @@ -650,6 +684,10 @@ int eeh_reset_pe(struct eeh_pe *pe) for (i=0; i<3; i++) { eeh_reset_pe_once(pe); + /* + * EEH_PE_ISOLATED is expected to be removed after + * BAR restore. + */ rc = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC); if ((rc & flags) == flags) return 0; @@ -747,6 +785,17 @@ int __exit eeh_ops_unregister(const char *name) return -EEXIST; } +static int eeh_reboot_notifier(struct notifier_block *nb, + unsigned long action, void *unused) +{ + eeh_set_enable(false); + return NOTIFY_DONE; +} + +static struct notifier_block eeh_reboot_nb = { + .notifier_call = eeh_reboot_notifier, +}; + /** * eeh_init - EEH initialization * @@ -778,6 +827,14 @@ int eeh_init(void) if (machine_is(powernv) && cnt++ <= 0) return ret; + /* Register reboot notifier */ + ret = register_reboot_notifier(&eeh_reboot_nb); + if (ret) { + pr_warn("%s: Failed to register notifier (%d)\n", + __func__, ret); + return ret; + } + /* call platform initialization function */ if (!eeh_ops) { pr_warning("%s: Platform EEH operation not found\n", @@ -806,8 +863,8 @@ int eeh_init(void) &hose_list, list_node) pci_walk_bus(hose->bus, eeh_ops->dev_probe, NULL); } else { - pr_warning("%s: Invalid probe mode %d\n", - __func__, eeh_probe_mode); + pr_warn("%s: Invalid probe mode %x", + __func__, eeh_subsystem_flags); return -EINVAL; } @@ -822,7 +879,7 @@ int eeh_init(void) return ret; } - if (eeh_subsystem_enabled) + if (eeh_enabled()) pr_info("EEH: PCI Enhanced I/O Error Handling Enabled\n"); else pr_warning("EEH: No capable adapters found\n"); @@ -897,7 +954,7 @@ void eeh_add_device_late(struct pci_dev *dev) struct device_node *dn; struct eeh_dev *edev; - if (!dev || !eeh_subsystem_enabled) + if (!dev || !eeh_enabled()) return; pr_debug("EEH: Adding device %s\n", pci_name(dev)); @@ -1005,7 +1062,7 @@ void eeh_remove_device(struct pci_dev *dev) { struct eeh_dev *edev; - if (!dev || !eeh_subsystem_enabled) + if (!dev || !eeh_enabled()) return; edev = pci_dev_to_eeh_dev(dev); @@ -1045,7 +1102,7 @@ void eeh_remove_device(struct pci_dev *dev) static int proc_eeh_show(struct seq_file *m, void *v) { - if (0 == eeh_subsystem_enabled) { + if (!eeh_enabled()) { seq_printf(m, "EEH Subsystem is globally disabled\n"); seq_printf(m, "eeh_total_mmio_ffs=%llu\n", eeh_stats.total_mmio_ffs); } else { @@ -1082,10 +1139,45 @@ static const struct file_operations proc_eeh_operations = { .release = single_release, }; +#ifdef CONFIG_DEBUG_FS +static int eeh_enable_dbgfs_set(void *data, u64 val) +{ + if (val) + eeh_subsystem_flags &= ~EEH_FORCE_DISABLED; + else + eeh_subsystem_flags |= EEH_FORCE_DISABLED; + + /* Notify the backend */ + if (eeh_ops->post_init) + eeh_ops->post_init(); + + return 0; +} + +static int eeh_enable_dbgfs_get(void *data, u64 *val) +{ + if (eeh_enabled()) + *val = 0x1ul; + else + *val = 0x0ul; + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(eeh_enable_dbgfs_ops, eeh_enable_dbgfs_get, + eeh_enable_dbgfs_set, "0x%llx\n"); +#endif + static int __init eeh_init_proc(void) { - if (machine_is(pseries) || machine_is(powernv)) + if (machine_is(pseries) || machine_is(powernv)) { proc_create("powerpc/eeh", 0, NULL, &proc_eeh_operations); +#ifdef CONFIG_DEBUG_FS + debugfs_create_file("eeh_enable", 0600, + powerpc_debugfs_root, NULL, + &eeh_enable_dbgfs_ops); +#endif + } + return 0; } __initcall(eeh_init_proc); diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 7bb30dca4e1..420da61d4ce 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -143,17 +143,43 @@ static void eeh_disable_irq(struct pci_dev *dev) static void eeh_enable_irq(struct pci_dev *dev) { struct eeh_dev *edev = pci_dev_to_eeh_dev(dev); - struct irq_desc *desc; if ((edev->mode) & EEH_DEV_IRQ_DISABLED) { edev->mode &= ~EEH_DEV_IRQ_DISABLED; - - desc = irq_to_desc(dev->irq); - if (desc && desc->depth > 0) + /* + * FIXME !!!!! + * + * This is just ass backwards. This maze has + * unbalanced irq_enable/disable calls. So instead of + * finding the root cause it works around the warning + * in the irq_enable code by conditionally calling + * into it. + * + * That's just wrong.The warning in the core code is + * there to tell people to fix their assymetries in + * their own code, not by abusing the core information + * to avoid it. + * + * I so wish that the assymetry would be the other way + * round and a few more irq_disable calls render that + * shit unusable forever. + * + * tglx + */ + if (irqd_irq_disabled(irq_get_irq_data(dev->irq))) enable_irq(dev->irq); } } +static bool eeh_dev_removed(struct eeh_dev *edev) +{ + /* EEH device removed ? */ + if (!edev || (edev->mode & EEH_DEV_REMOVED)) + return true; + + return false; +} + /** * eeh_report_error - Report pci error to each device driver * @data: eeh device @@ -170,10 +196,8 @@ static void *eeh_report_error(void *data, void *userdata) enum pci_ers_result rc, *res = userdata; struct pci_driver *driver; - /* We might not have the associated PCI device, - * then we should continue for next one. - */ - if (!dev) return NULL; + if (!dev || eeh_dev_removed(edev)) + return NULL; dev->error_state = pci_channel_io_frozen; driver = eeh_pcid_get(dev); @@ -213,6 +237,9 @@ 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)) + return NULL; + driver = eeh_pcid_get(dev); if (!driver) return NULL; @@ -250,7 +277,8 @@ static void *eeh_report_reset(void *data, void *userdata) enum pci_ers_result rc, *res = userdata; struct pci_driver *driver; - if (!dev) return NULL; + if (!dev || eeh_dev_removed(edev)) + return NULL; dev->error_state = pci_channel_io_normal; driver = eeh_pcid_get(dev); @@ -290,7 +318,8 @@ static void *eeh_report_resume(void *data, void *userdata) struct pci_dev *dev = eeh_dev_to_pci_dev(edev); struct pci_driver *driver; - if (!dev) return NULL; + if (!dev || eeh_dev_removed(edev)) + return NULL; dev->error_state = pci_channel_io_normal; driver = eeh_pcid_get(dev); @@ -326,7 +355,8 @@ 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) return NULL; + if (!dev || eeh_dev_removed(edev)) + return NULL; dev->error_state = pci_channel_io_perm_failure; driver = eeh_pcid_get(dev); @@ -362,10 +392,24 @@ static void *eeh_rmv_device(void *data, void *userdata) */ if (!dev || (dev->hdr_type & PCI_HEADER_TYPE_BRIDGE)) return NULL; - driver = eeh_pcid_get(dev); - if (driver && driver->err_handler) + + /* + * We rely on count-based pcibios_release_device() to + * detach permanently offlined PEs. Unfortunately, that's + * not reliable enough. We might have the permanently + * offlined PEs attached, but we needn't take care of + * them and their child devices. + */ + if (eeh_dev_removed(edev)) return NULL; + driver = eeh_pcid_get(dev); + if (driver) { + eeh_pcid_put(dev); + if (driver->err_handler) + return NULL; + } + /* Remove it from PCI subsystem */ pr_debug("EEH: Removing %s without EEH sensitive driver\n", pci_name(dev)); @@ -396,6 +440,48 @@ static void *eeh_pe_detach_dev(void *data, void *userdata) return NULL; } +/* + * Explicitly clear PE's frozen state for PowerNV where + * we have frozen PE until BAR restore is completed. It's + * harmless to clear it for pSeries. To be consistent with + * PE reset (for 3 times), we try to clear the frozen state + * for 3 times as well. + */ +static void *__eeh_clear_pe_frozen_state(void *data, void *flag) +{ + struct eeh_pe *pe = (struct eeh_pe *)data; + int i, rc; + + for (i = 0; i < 3; i++) { + rc = eeh_pci_enable(pe, EEH_OPT_THAW_MMIO); + if (rc) + continue; + rc = eeh_pci_enable(pe, EEH_OPT_THAW_DMA); + if (!rc) + break; + } + + /* The PE has been isolated, clear it */ + if (rc) { + pr_warn("%s: Can't clear frozen PHB#%x-PE#%x (%d)\n", + __func__, pe->phb->global_number, pe->addr, rc); + return (void *)pe; + } + + return NULL; +} + +static int eeh_clear_pe_frozen_state(struct eeh_pe *pe) +{ + void *rc; + + rc = eeh_pe_traverse(pe, __eeh_clear_pe_frozen_state, NULL); + if (!rc) + eeh_pe_state_clear(pe, EEH_PE_ISOLATED); + + return rc ? -EIO : 0; +} + /** * eeh_reset_device - Perform actual reset of a pci slot * @pe: EEH PE @@ -430,19 +516,33 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus) eeh_pe_dev_traverse(pe, eeh_rmv_device, &removed); } - /* Reset the pci controller. (Asserts RST#; resets config space). + /* + * Reset the pci controller. (Asserts RST#; resets config space). * Reconfigure bridges and devices. Don't try to bring the system * up if the reset failed for some reason. + * + * During the reset, it's very dangerous to have uncontrolled PCI + * config accesses. So we prefer to block them. However, controlled + * PCI config accesses initiated from EEH itself are allowed. */ + eeh_pe_state_mark(pe, EEH_PE_RESET); rc = eeh_reset_pe(pe); - if (rc) + if (rc) { + eeh_pe_state_clear(pe, EEH_PE_RESET); return rc; + } pci_lock_rescan_remove(); /* Restore PE */ eeh_ops->configure_bridge(pe); eeh_pe_restore_bars(pe); + eeh_pe_state_clear(pe, EEH_PE_RESET); + + /* Clear frozen state */ + rc = eeh_clear_pe_frozen_state(pe); + if (rc) + return rc; /* Give the system 5 seconds to finish running the user-space * hotplug shutdown scripts, e.g. ifdown for ethernet. Yes, @@ -552,7 +652,6 @@ static void eeh_handle_normal_event(struct eeh_pe *pe) result = PCI_ERS_RESULT_NEED_RESET; } else { pr_info("EEH: Notify device drivers to resume I/O\n"); - result = PCI_ERS_RESULT_NONE; eeh_pe_dev_traverse(pe, eeh_report_mmio_enabled, &result); } } @@ -564,10 +663,17 @@ static void eeh_handle_normal_event(struct eeh_pe *pe) if (rc < 0) goto hard_fail; - if (rc) + if (rc) { result = PCI_ERS_RESULT_NEED_RESET; - else + } else { + /* + * We didn't do PE reset for the case. The PE + * is still in frozen state. Clear it before + * resuming the PE. + */ + eeh_pe_state_clear(pe, EEH_PE_ISOLATED); result = PCI_ERS_RESULT_RECOVERED; + } } /* If any device has a hard failure, then shut off everything. */ @@ -629,8 +735,17 @@ perm_error: /* Notify all devices that they're about to go down. */ eeh_pe_dev_traverse(pe, eeh_report_failure, NULL); - /* Shut down the device drivers for good. */ + /* Mark the PE to be removed permanently */ + pe->freeze_count = EEH_MAX_ALLOWED_FREEZES + 1; + + /* + * Shut down the device drivers for good. We mark + * all removed devices correctly to avoid access + * the their PCI config any more. + */ if (frozen_bus) { + eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED); + pci_lock_rescan_remove(); pcibios_remove_pci_devices(frozen_bus); pci_unlock_rescan_remove(); @@ -655,14 +770,13 @@ static void eeh_handle_special_event(void) eeh_serialize_lock(&flags); /* Purge all events */ - eeh_remove_event(NULL); + eeh_remove_event(NULL, true); 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_pe_state_mark(phb_pe, EEH_PE_ISOLATED); } eeh_serialize_unlock(flags); @@ -675,11 +789,10 @@ static void eeh_handle_special_event(void) eeh_serialize_lock(&flags); /* Purge all events of the PHB */ - eeh_remove_event(pe); + eeh_remove_event(pe, true); if (rc == EEH_NEXT_ERR_DEAD_PHB) - eeh_pe_state_mark(pe, - EEH_PE_ISOLATED | EEH_PE_PHB_DEAD); + eeh_pe_state_mark(pe, EEH_PE_ISOLATED); else eeh_pe_state_mark(pe, EEH_PE_ISOLATED | EEH_PE_RECOVERING); @@ -703,12 +816,14 @@ static void eeh_handle_special_event(void) if (rc == EEH_NEXT_ERR_FROZEN_PE || rc == EEH_NEXT_ERR_FENCED_PHB) { eeh_handle_normal_event(pe); + eeh_pe_state_clear(pe, EEH_PE_RECOVERING); } 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)) + !(phb_pe->state & EEH_PE_ISOLATED) || + (phb_pe->state & EEH_PE_RECOVERING)) continue; /* Notify all devices to be down */ diff --git a/arch/powerpc/kernel/eeh_event.c b/arch/powerpc/kernel/eeh_event.c index 72d748b56c8..4eefb6e34db 100644 --- a/arch/powerpc/kernel/eeh_event.c +++ b/arch/powerpc/kernel/eeh_event.c @@ -152,24 +152,33 @@ int eeh_send_failure_event(struct eeh_pe *pe) /** * eeh_remove_event - Remove EEH event from the queue * @pe: Event binding to the PE + * @force: Event will be removed unconditionally * * On PowerNV platform, we might have subsequent coming events * is part of the former one. For that case, those subsequent * coming events are totally duplicated and unnecessary, thus * they should be removed. */ -void eeh_remove_event(struct eeh_pe *pe) +void eeh_remove_event(struct eeh_pe *pe, bool force) { unsigned long flags; struct eeh_event *event, *tmp; + /* + * If we have NULL PE passed in, we have dead IOC + * or we're sure we can report all existing errors + * by the caller. + * + * With "force", the event with associated PE that + * have been isolated, the event won't be removed + * to avoid event lost. + */ spin_lock_irqsave(&eeh_eventlist_lock, flags); list_for_each_entry_safe(event, tmp, &eeh_eventlist, list) { - /* - * If we don't have valid PE passed in, that means - * we already have event corresponding to dead IOC - * and all events should be purged. - */ + if (!force && event->pe && + (event->pe->state & EEH_PE_ISOLATED)) + continue; + if (!pe) { list_del(&event->list); kfree(event); diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index f0c353fa655..fbd01eba447 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -503,13 +503,17 @@ static void *__eeh_pe_state_mark(void *data, void *flag) struct eeh_dev *edev, *tmp; struct pci_dev *pdev; - /* - * Mark the PE with the indicated state. Also, - * the associated PCI device will be put into - * I/O frozen state to avoid I/O accesses from - * the PCI device driver. - */ + /* Keep the state of permanently removed PE intact */ + if ((pe->freeze_count > EEH_MAX_ALLOWED_FREEZES) && + (state & (EEH_PE_ISOLATED | EEH_PE_RECOVERING))) + return NULL; + pe->state |= state; + + /* Offline PCI devices if applicable */ + if (state != EEH_PE_ISOLATED) + return NULL; + eeh_pe_for_each_dev(pe, edev, tmp) { pdev = eeh_dev_to_pci_dev(edev); if (pdev) @@ -532,6 +536,27 @@ void eeh_pe_state_mark(struct eeh_pe *pe, int state) eeh_pe_traverse(pe, __eeh_pe_state_mark, &state); } +static void *__eeh_pe_dev_mode_mark(void *data, void *flag) +{ + struct eeh_dev *edev = data; + int mode = *((int *)flag); + + edev->mode |= mode; + + return NULL; +} + +/** + * eeh_pe_dev_state_mark - Mark state for all device under the PE + * @pe: EEH PE + * + * Mark specific state for all child devices of the PE. + */ +void eeh_pe_dev_mode_mark(struct eeh_pe *pe, int mode) +{ + eeh_pe_dev_traverse(pe, __eeh_pe_dev_mode_mark, &mode); +} + /** * __eeh_pe_state_clear - Clear state for the PE * @data: EEH PE @@ -546,8 +571,16 @@ static void *__eeh_pe_state_clear(void *data, void *flag) struct eeh_pe *pe = (struct eeh_pe *)data; int state = *((int *)flag); + /* Keep the state of permanently removed PE intact */ + if ((pe->freeze_count > EEH_MAX_ALLOWED_FREEZES) && + (state & EEH_PE_ISOLATED)) + return NULL; + pe->state &= ~state; - pe->check_count = 0; + + /* Clear check count since last isolation */ + if (state & EEH_PE_ISOLATED) + pe->check_count = 0; return NULL; } @@ -759,6 +792,66 @@ void eeh_pe_restore_bars(struct eeh_pe *pe) } /** + * eeh_pe_loc_get - Retrieve location code binding to the given PE + * @pe: EEH PE + * + * Retrieve the location code of the given PE. If the primary PE bus + * is root bus, we will grab location code from PHB device tree node + * or root port. Otherwise, the upstream bridge's device tree node + * of the primary PE bus will be checked for the location code. + */ +const char *eeh_pe_loc_get(struct eeh_pe *pe) +{ + struct pci_controller *hose; + struct pci_bus *bus = eeh_pe_bus_get(pe); + struct pci_dev *pdev; + struct device_node *dn; + const char *loc; + + if (!bus) + return "N/A"; + + /* PHB PE or root PE ? */ + if (pci_is_root_bus(bus)) { + hose = pci_bus_to_host(bus); + loc = of_get_property(hose->dn, + "ibm,loc-code", NULL); + if (loc) + return loc; + loc = of_get_property(hose->dn, + "ibm,io-base-loc-code", NULL); + if (loc) + return loc; + + pdev = pci_get_slot(bus, 0x0); + } else { + pdev = bus->self; + } + + if (!pdev) { + loc = "N/A"; + goto out; + } + + dn = pci_device_to_OF_node(pdev); + if (!dn) { + loc = "N/A"; + goto out; + } + + loc = of_get_property(dn, "ibm,loc-code", NULL); + if (!loc) + loc = of_get_property(dn, "ibm,slot-location-code", NULL); + if (!loc) + loc = "N/A"; + +out: + if (pci_is_root_bus(bus) && pdev) + pci_dev_put(pdev); + return loc; +} + +/** * eeh_pe_bus_get - Retrieve PCI bus according to the given PE * @pe: EEH PE * diff --git a/arch/powerpc/kernel/eeh_sysfs.c b/arch/powerpc/kernel/eeh_sysfs.c index 5d753d4f2c7..e2595ba4b72 100644 --- a/arch/powerpc/kernel/eeh_sysfs.c +++ b/arch/powerpc/kernel/eeh_sysfs.c @@ -59,6 +59,9 @@ void eeh_sysfs_add_device(struct pci_dev *pdev) struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev); int rc=0; + if (!eeh_enabled()) + return; + if (edev && (edev->mode & EEH_DEV_SYSFS)) return; diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 662c6dd9807..6528c5e2cc4 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -39,8 +39,8 @@ * System calls. */ .section ".toc","aw" -.SYS_CALL_TABLE: - .tc .sys_call_table[TC],.sys_call_table +SYS_CALL_TABLE: + .tc sys_call_table[TC],sys_call_table /* This value is used to mark exception frames on the stack. */ exception_marker: @@ -106,7 +106,7 @@ BEGIN_FW_FTR_SECTION LDX_BE r10,0,r10 /* get log write index */ cmpd cr1,r11,r10 beq+ cr1,33f - bl .accumulate_stolen_time + bl accumulate_stolen_time REST_GPR(0,r1) REST_4GPRS(3,r1) REST_2GPRS(7,r1) @@ -143,7 +143,7 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR) std r10,SOFTE(r1) #ifdef SHOW_SYSCALLS - bl .do_show_syscall + bl do_show_syscall REST_GPR(0,r1) REST_4GPRS(3,r1) REST_2GPRS(7,r1) @@ -162,7 +162,7 @@ system_call: /* label this so stack traces look sane */ * Need to vector to 32 Bit or default sys_call_table here, * based on caller's run-mode / personality. */ - ld r11,.SYS_CALL_TABLE@toc(2) + ld r11,SYS_CALL_TABLE@toc(2) andi. r10,r10,_TIF_32BIT beq 15f addi r11,r11,8 /* use 32-bit syscall entries */ @@ -174,14 +174,14 @@ system_call: /* label this so stack traces look sane */ clrldi r8,r8,32 15: slwi r0,r0,4 - ldx r10,r11,r0 /* Fetch system call handler [ptr] */ - mtctr r10 + ldx r12,r11,r0 /* Fetch system call handler [ptr] */ + mtctr r12 bctrl /* Call handler */ syscall_exit: std r3,RESULT(r1) #ifdef SHOW_SYSCALLS - bl .do_show_syscall_exit + bl do_show_syscall_exit ld r3,RESULT(r1) #endif CURRENT_THREAD_INFO(r12, r1) @@ -248,9 +248,9 @@ syscall_error: /* Traced system call support */ syscall_dotrace: - bl .save_nvgprs + bl save_nvgprs addi r3,r1,STACK_FRAME_OVERHEAD - bl .do_syscall_trace_enter + bl do_syscall_trace_enter /* * Restore argument registers possibly just changed. * We use the return value of do_syscall_trace_enter @@ -308,7 +308,7 @@ syscall_exit_work: 4: /* Anything else left to do? */ SET_DEFAULT_THREAD_PPR(r3, r10) /* Set thread.ppr = 3 */ andi. r0,r9,(_TIF_SYSCALL_T_OR_A|_TIF_SINGLESTEP) - beq .ret_from_except_lite + beq ret_from_except_lite /* Re-enable interrupts */ #ifdef CONFIG_PPC_BOOK3E @@ -319,10 +319,10 @@ syscall_exit_work: mtmsrd r10,1 #endif /* CONFIG_PPC_BOOK3E */ - bl .save_nvgprs + bl save_nvgprs addi r3,r1,STACK_FRAME_OVERHEAD - bl .do_syscall_trace_leave - b .ret_from_except + bl do_syscall_trace_leave + b ret_from_except /* Save non-volatile GPRs, if not already saved. */ _GLOBAL(save_nvgprs) @@ -345,52 +345,48 @@ _GLOBAL(save_nvgprs) */ _GLOBAL(ppc_fork) - bl .save_nvgprs - bl .sys_fork + bl save_nvgprs + bl sys_fork b syscall_exit _GLOBAL(ppc_vfork) - bl .save_nvgprs - bl .sys_vfork + bl save_nvgprs + bl sys_vfork b syscall_exit _GLOBAL(ppc_clone) - bl .save_nvgprs - bl .sys_clone + bl save_nvgprs + bl sys_clone b syscall_exit _GLOBAL(ppc32_swapcontext) - bl .save_nvgprs - bl .compat_sys_swapcontext + bl save_nvgprs + bl compat_sys_swapcontext b syscall_exit _GLOBAL(ppc64_swapcontext) - bl .save_nvgprs - bl .sys_swapcontext + bl save_nvgprs + bl sys_swapcontext b syscall_exit _GLOBAL(ret_from_fork) - bl .schedule_tail + bl schedule_tail REST_NVGPRS(r1) li r3,0 b syscall_exit _GLOBAL(ret_from_kernel_thread) - bl .schedule_tail + bl schedule_tail REST_NVGPRS(r1) - ld r14, 0(r14) mtlr r14 mr r3,r15 +#if defined(_CALL_ELF) && _CALL_ELF == 2 + mr r12,r14 +#endif blrl li r3,0 b syscall_exit - .section ".toc","aw" -DSCR_DEFAULT: - .tc dscr_default[TC],dscr_default - - .section ".text" - /* * This routine switches between two different tasks. The process * state of one is saved on its kernel stack. Then the state @@ -432,12 +428,6 @@ BEGIN_FTR_SECTION std r24,THREAD_VRSAVE(r3) END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) #endif /* CONFIG_ALTIVEC */ -#ifdef CONFIG_PPC64 -BEGIN_FTR_SECTION - mfspr r25,SPRN_DSCR - std r25,THREAD_DSCR(r3) -END_FTR_SECTION_IFSET(CPU_FTR_DSCR) -#endif and. r0,r0,r22 beq+ 1f andc r22,r22,r0 @@ -575,11 +565,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) #ifdef CONFIG_PPC64 BEGIN_FTR_SECTION lwz r6,THREAD_DSCR_INHERIT(r4) - ld r7,DSCR_DEFAULT@toc(2) ld r0,THREAD_DSCR(r4) cmpwi r6,0 bne 1f - ld r0,0(r7) + ld r0,PACA_DSCR(r13) 1: BEGIN_FTR_SECTION_NESTED(70) mfspr r8, SPRN_FSCR @@ -611,7 +600,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_DSCR) _GLOBAL(ret_from_except) ld r11,_TRAP(r1) andi. r0,r11,1 - bne .ret_from_except_lite + bne ret_from_except_lite REST_NVGPRS(r1) _GLOBAL(ret_from_except_lite) @@ -661,23 +650,23 @@ _GLOBAL(ret_from_except_lite) #endif 1: andi. r0,r4,_TIF_NEED_RESCHED beq 2f - bl .restore_interrupts + bl restore_interrupts SCHEDULE_USER - b .ret_from_except_lite + b ret_from_except_lite 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 + bl restore_tm_state b restore 3: #endif - bl .save_nvgprs - bl .restore_interrupts + bl save_nvgprs + bl restore_interrupts addi r3,r1,STACK_FRAME_OVERHEAD - bl .do_notify_resume - b .ret_from_except + bl do_notify_resume + b ret_from_except resume_kernel: /* check current_thread_info, _TIF_EMULATE_STACK_STORE */ @@ -730,7 +719,7 @@ resume_kernel: * sure we are soft-disabled first and reconcile irq state. */ RECONCILE_IRQ_STATE(r3,r4) -1: bl .preempt_schedule_irq +1: bl preempt_schedule_irq /* Re-test flags and eventually loop */ CURRENT_THREAD_INFO(r9, r1) @@ -792,7 +781,7 @@ restore_no_replay: */ do_restore: #ifdef CONFIG_PPC_BOOK3E - b .exception_return_book3e + b exception_return_book3e #else /* * Clear the reservation. If we know the CPU tracks the address of @@ -907,7 +896,7 @@ restore_check_irq_replay: * * Still, this might be useful for things like hash_page */ - bl .__check_irq_replay + bl __check_irq_replay cmpwi cr0,r3,0 beq restore_no_replay @@ -928,13 +917,13 @@ restore_check_irq_replay: cmpwi cr0,r3,0x500 bne 1f addi r3,r1,STACK_FRAME_OVERHEAD; - bl .do_IRQ - b .ret_from_except + bl do_IRQ + b ret_from_except 1: cmpwi cr0,r3,0x900 bne 1f addi r3,r1,STACK_FRAME_OVERHEAD; - bl .timer_interrupt - b .ret_from_except + bl timer_interrupt + b ret_from_except #ifdef CONFIG_PPC_DOORBELL 1: #ifdef CONFIG_PPC_BOOK3E @@ -948,14 +937,14 @@ restore_check_irq_replay: #endif /* CONFIG_PPC_BOOK3E */ bne 1f addi r3,r1,STACK_FRAME_OVERHEAD; - bl .doorbell_exception - b .ret_from_except + bl doorbell_exception + b ret_from_except #endif /* CONFIG_PPC_DOORBELL */ -1: b .ret_from_except /* What else to do here ? */ +1: b ret_from_except /* What else to do here ? */ unrecov_restore: addi r3,r1,STACK_FRAME_OVERHEAD - bl .unrecoverable_exception + bl unrecoverable_exception b unrecov_restore #ifdef CONFIG_PPC_RTAS @@ -1021,7 +1010,7 @@ _GLOBAL(enter_rtas) std r6,PACASAVEDMSR(r13) /* Setup our real return addr */ - LOAD_REG_ADDR(r4,.rtas_return_loc) + LOAD_REG_ADDR(r4,rtas_return_loc) clrldi r4,r4,2 /* convert to realmode address */ mtlr r4 @@ -1045,7 +1034,7 @@ _GLOBAL(enter_rtas) rfid b . /* prevent speculative execution */ -_STATIC(rtas_return_loc) +rtas_return_loc: FIXUP_ENDIAN /* relocation is off at this point */ @@ -1054,7 +1043,7 @@ _STATIC(rtas_return_loc) bcl 20,31,$+4 0: mflr r3 - ld r3,(1f-0b)(r3) /* get &.rtas_restore_regs */ + ld r3,(1f-0b)(r3) /* get &rtas_restore_regs */ mfmsr r6 li r0,MSR_RI @@ -1071,9 +1060,9 @@ _STATIC(rtas_return_loc) b . /* prevent speculative execution */ .align 3 -1: .llong .rtas_restore_regs +1: .llong rtas_restore_regs -_STATIC(rtas_restore_regs) +rtas_restore_regs: /* relocation is on at this point */ REST_GPR(2, r1) /* Restore the TOC */ REST_GPR(13, r1) /* Restore paca */ @@ -1173,7 +1162,7 @@ _GLOBAL(mcount) _GLOBAL(_mcount) blr -_GLOBAL(ftrace_caller) +_GLOBAL_TOC(ftrace_caller) /* Taken from output of objdump from lib64/glibc */ mflr r3 ld r11, 0(r1) @@ -1197,10 +1186,7 @@ _GLOBAL(ftrace_graph_stub) _GLOBAL(ftrace_stub) blr #else -_GLOBAL(mcount) - blr - -_GLOBAL(_mcount) +_GLOBAL_TOC(_mcount) /* Taken from output of objdump from lib64/glibc */ mflr r3 ld r11, 0(r1) @@ -1238,7 +1224,7 @@ _GLOBAL(ftrace_graph_caller) ld r11, 112(r1) addi r3, r11, 16 - bl .prepare_ftrace_return + bl prepare_ftrace_return nop ld r0, 128(r1) @@ -1254,7 +1240,7 @@ _GLOBAL(return_to_handler) mr r31, r1 stdu r1, -112(r1) - bl .ftrace_return_to_handler + bl ftrace_return_to_handler nop /* return value has real return address */ @@ -1284,7 +1270,7 @@ _GLOBAL(mod_return_to_handler) */ ld r2, PACATOC(r13) - bl .ftrace_return_to_handler + bl ftrace_return_to_handler nop /* return value has real return address */ diff --git a/arch/powerpc/kernel/epapr_paravirt.c b/arch/powerpc/kernel/epapr_paravirt.c index 7898be90f2d..59e4ba74975 100644 --- a/arch/powerpc/kernel/epapr_paravirt.c +++ b/arch/powerpc/kernel/epapr_paravirt.c @@ -30,13 +30,14 @@ extern u32 epapr_ev_idle_start[]; #endif bool epapr_paravirt_enabled; +static bool __maybe_unused epapr_has_idle; static int __init early_init_dt_scan_epapr(unsigned long node, const char *uname, int depth, void *data) { const u32 *insts; - unsigned long len; + int len; int i; insts = of_get_flat_dt_prop(node, "hcall-instructions", &len); @@ -47,15 +48,16 @@ static int __init early_init_dt_scan_epapr(unsigned long node, return -1; for (i = 0; i < (len / 4); i++) { - patch_instruction(epapr_hypercall_start + i, insts[i]); + u32 inst = be32_to_cpu(insts[i]); + patch_instruction(epapr_hypercall_start + i, inst); #if !defined(CONFIG_64BIT) || defined(CONFIG_PPC_BOOK3E_64) - patch_instruction(epapr_ev_idle_start + i, insts[i]); + patch_instruction(epapr_ev_idle_start + i, inst); #endif } #if !defined(CONFIG_64BIT) || defined(CONFIG_PPC_BOOK3E_64) if (of_get_flat_dt_prop(node, "has-idle", NULL)) - ppc_md.power_save = epapr_ev_idle; + epapr_has_idle = true; #endif epapr_paravirt_enabled = true; @@ -70,3 +72,14 @@ int __init epapr_paravirt_early_init(void) return 0; } +static int __init epapr_idle_init(void) +{ +#if !defined(CONFIG_64BIT) || defined(CONFIG_PPC_BOOK3E_64) + if (epapr_has_idle) + ppc_md.power_save = epapr_ev_idle; +#endif + + return 0; +} + +postcore_initcall(epapr_idle_init); diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index 063b65dd4f2..bb9cac6c805 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -34,7 +34,250 @@ * special interrupts from within a non-standard level will probably * blow you up */ -#define SPECIAL_EXC_FRAME_SIZE INT_FRAME_SIZE +#define SPECIAL_EXC_SRR0 0 +#define SPECIAL_EXC_SRR1 1 +#define SPECIAL_EXC_SPRG_GEN 2 +#define SPECIAL_EXC_SPRG_TLB 3 +#define SPECIAL_EXC_MAS0 4 +#define SPECIAL_EXC_MAS1 5 +#define SPECIAL_EXC_MAS2 6 +#define SPECIAL_EXC_MAS3 7 +#define SPECIAL_EXC_MAS6 8 +#define SPECIAL_EXC_MAS7 9 +#define SPECIAL_EXC_MAS5 10 /* E.HV only */ +#define SPECIAL_EXC_MAS8 11 /* E.HV only */ +#define SPECIAL_EXC_IRQHAPPENED 12 +#define SPECIAL_EXC_DEAR 13 +#define SPECIAL_EXC_ESR 14 +#define SPECIAL_EXC_SOFTE 15 +#define SPECIAL_EXC_CSRR0 16 +#define SPECIAL_EXC_CSRR1 17 +/* must be even to keep 16-byte stack alignment */ +#define SPECIAL_EXC_END 18 + +#define SPECIAL_EXC_FRAME_SIZE (INT_FRAME_SIZE + SPECIAL_EXC_END * 8) +#define SPECIAL_EXC_FRAME_OFFS (INT_FRAME_SIZE - 288) + +#define SPECIAL_EXC_STORE(reg, name) \ + std reg, (SPECIAL_EXC_##name * 8 + SPECIAL_EXC_FRAME_OFFS)(r1) + +#define SPECIAL_EXC_LOAD(reg, name) \ + ld reg, (SPECIAL_EXC_##name * 8 + SPECIAL_EXC_FRAME_OFFS)(r1) + +special_reg_save: + lbz r9,PACAIRQHAPPENED(r13) + RECONCILE_IRQ_STATE(r3,r4) + + /* + * We only need (or have stack space) to save this stuff if + * we interrupted the kernel. + */ + ld r3,_MSR(r1) + andi. r3,r3,MSR_PR + bnelr + + /* Copy info into temporary exception thread info */ + ld r11,PACAKSAVE(r13) + CURRENT_THREAD_INFO(r11, r11) + CURRENT_THREAD_INFO(r12, r1) + ld r10,TI_FLAGS(r11) + std r10,TI_FLAGS(r12) + ld r10,TI_PREEMPT(r11) + std r10,TI_PREEMPT(r12) + ld r10,TI_TASK(r11) + std r10,TI_TASK(r12) + + /* + * Advance to the next TLB exception frame for handler + * types that don't do it automatically. + */ + LOAD_REG_ADDR(r11,extlb_level_exc) + lwz r12,0(r11) + mfspr r10,SPRN_SPRG_TLB_EXFRAME + add r10,r10,r12 + mtspr SPRN_SPRG_TLB_EXFRAME,r10 + + /* + * Save registers needed to allow nesting of certain exceptions + * (such as TLB misses) inside special exception levels + */ + mfspr r10,SPRN_SRR0 + SPECIAL_EXC_STORE(r10,SRR0) + mfspr r10,SPRN_SRR1 + SPECIAL_EXC_STORE(r10,SRR1) + mfspr r10,SPRN_SPRG_GEN_SCRATCH + SPECIAL_EXC_STORE(r10,SPRG_GEN) + mfspr r10,SPRN_SPRG_TLB_SCRATCH + SPECIAL_EXC_STORE(r10,SPRG_TLB) + mfspr r10,SPRN_MAS0 + SPECIAL_EXC_STORE(r10,MAS0) + mfspr r10,SPRN_MAS1 + SPECIAL_EXC_STORE(r10,MAS1) + mfspr r10,SPRN_MAS2 + SPECIAL_EXC_STORE(r10,MAS2) + mfspr r10,SPRN_MAS3 + SPECIAL_EXC_STORE(r10,MAS3) + mfspr r10,SPRN_MAS6 + SPECIAL_EXC_STORE(r10,MAS6) + mfspr r10,SPRN_MAS7 + SPECIAL_EXC_STORE(r10,MAS7) +BEGIN_FTR_SECTION + mfspr r10,SPRN_MAS5 + SPECIAL_EXC_STORE(r10,MAS5) + mfspr r10,SPRN_MAS8 + SPECIAL_EXC_STORE(r10,MAS8) + + /* MAS5/8 could have inappropriate values if we interrupted KVM code */ + li r10,0 + mtspr SPRN_MAS5,r10 + mtspr SPRN_MAS8,r10 +END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV) + SPECIAL_EXC_STORE(r9,IRQHAPPENED) + + mfspr r10,SPRN_DEAR + SPECIAL_EXC_STORE(r10,DEAR) + mfspr r10,SPRN_ESR + SPECIAL_EXC_STORE(r10,ESR) + + lbz r10,PACASOFTIRQEN(r13) + SPECIAL_EXC_STORE(r10,SOFTE) + ld r10,_NIP(r1) + SPECIAL_EXC_STORE(r10,CSRR0) + ld r10,_MSR(r1) + SPECIAL_EXC_STORE(r10,CSRR1) + + blr + +ret_from_level_except: + ld r3,_MSR(r1) + andi. r3,r3,MSR_PR + beq 1f + b ret_from_except +1: + + LOAD_REG_ADDR(r11,extlb_level_exc) + lwz r12,0(r11) + mfspr r10,SPRN_SPRG_TLB_EXFRAME + sub r10,r10,r12 + mtspr SPRN_SPRG_TLB_EXFRAME,r10 + + /* + * It's possible that the special level exception interrupted a + * TLB miss handler, and inserted the same entry that the + * interrupted handler was about to insert. On CPUs without TLB + * write conditional, this can result in a duplicate TLB entry. + * Wipe all non-bolted entries to be safe. + * + * Note that this doesn't protect against any TLB misses + * we may take accessing the stack from here to the end of + * the special level exception. It's not clear how we can + * reasonably protect against that, but only CPUs with + * neither TLB write conditional nor bolted kernel memory + * are affected. Do any such CPUs even exist? + */ + PPC_TLBILX_ALL(0,R0) + + REST_NVGPRS(r1) + + SPECIAL_EXC_LOAD(r10,SRR0) + mtspr SPRN_SRR0,r10 + SPECIAL_EXC_LOAD(r10,SRR1) + mtspr SPRN_SRR1,r10 + SPECIAL_EXC_LOAD(r10,SPRG_GEN) + mtspr SPRN_SPRG_GEN_SCRATCH,r10 + SPECIAL_EXC_LOAD(r10,SPRG_TLB) + mtspr SPRN_SPRG_TLB_SCRATCH,r10 + SPECIAL_EXC_LOAD(r10,MAS0) + mtspr SPRN_MAS0,r10 + SPECIAL_EXC_LOAD(r10,MAS1) + mtspr SPRN_MAS1,r10 + SPECIAL_EXC_LOAD(r10,MAS2) + mtspr SPRN_MAS2,r10 + SPECIAL_EXC_LOAD(r10,MAS3) + mtspr SPRN_MAS3,r10 + SPECIAL_EXC_LOAD(r10,MAS6) + mtspr SPRN_MAS6,r10 + SPECIAL_EXC_LOAD(r10,MAS7) + mtspr SPRN_MAS7,r10 +BEGIN_FTR_SECTION + SPECIAL_EXC_LOAD(r10,MAS5) + mtspr SPRN_MAS5,r10 + SPECIAL_EXC_LOAD(r10,MAS8) + mtspr SPRN_MAS8,r10 +END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV) + + lbz r6,PACASOFTIRQEN(r13) + ld r5,SOFTE(r1) + + /* Interrupts had better not already be enabled... */ + twnei r6,0 + + cmpwi cr0,r5,0 + beq 1f + + TRACE_ENABLE_INTS + stb r5,PACASOFTIRQEN(r13) +1: + /* + * Restore PACAIRQHAPPENED rather than setting it based on + * the return MSR[EE], since we could have interrupted + * __check_irq_replay() or other inconsistent transitory + * states that must remain that way. + */ + SPECIAL_EXC_LOAD(r10,IRQHAPPENED) + stb r10,PACAIRQHAPPENED(r13) + + SPECIAL_EXC_LOAD(r10,DEAR) + mtspr SPRN_DEAR,r10 + SPECIAL_EXC_LOAD(r10,ESR) + mtspr SPRN_ESR,r10 + + stdcx. r0,0,r1 /* to clear the reservation */ + + REST_4GPRS(2, r1) + REST_4GPRS(6, r1) + + ld r10,_CTR(r1) + ld r11,_XER(r1) + mtctr r10 + mtxer r11 + + blr + +.macro ret_from_level srr0 srr1 paca_ex scratch + bl ret_from_level_except + + ld r10,_LINK(r1) + ld r11,_CCR(r1) + ld r0,GPR13(r1) + mtlr r10 + mtcr r11 + + ld r10,GPR10(r1) + ld r11,GPR11(r1) + ld r12,GPR12(r1) + mtspr \scratch,r0 + + std r10,\paca_ex+EX_R10(r13); + std r11,\paca_ex+EX_R11(r13); + ld r10,_NIP(r1) + ld r11,_MSR(r1) + ld r0,GPR0(r1) + ld r1,GPR1(r1) + mtspr \srr0,r10 + mtspr \srr1,r11 + ld r10,\paca_ex+EX_R10(r13) + ld r11,\paca_ex+EX_R11(r13) + mfspr r13,\scratch +.endm + +ret_from_crit_except: + ret_from_level SPRN_CSRR0 SPRN_CSRR1 PACA_EXCRIT SPRN_SPRG_CRIT_SCRATCH + rfci + +ret_from_mc_except: + ret_from_level SPRN_MCSRR0 SPRN_MCSRR1 PACA_EXMC SPRN_SPRG_MC_SCRATCH + rfmci /* Exception prolog code for all exceptions */ #define EXCEPTION_PROLOG(n, intnum, type, addition) \ @@ -42,7 +285,6 @@ mfspr r13,SPRN_SPRG_PACA; /* get PACA */ \ std r10,PACA_EX##type+EX_R10(r13); \ std r11,PACA_EX##type+EX_R11(r13); \ - PROLOG_STORE_RESTORE_SCRATCH_##type; \ mfcr r10; /* save CR */ \ mfspr r11,SPRN_##type##_SRR1;/* what are we coming from */ \ DO_KVM intnum,SPRN_##type##_SRR1; /* KVM hook */ \ @@ -69,19 +311,19 @@ #define CRIT_SET_KSTACK \ ld r1,PACA_CRIT_STACK(r13); \ - subi r1,r1,SPECIAL_EXC_FRAME_SIZE; + subi r1,r1,SPECIAL_EXC_FRAME_SIZE #define SPRN_CRIT_SRR0 SPRN_CSRR0 #define SPRN_CRIT_SRR1 SPRN_CSRR1 #define DBG_SET_KSTACK \ ld r1,PACA_DBG_STACK(r13); \ - subi r1,r1,SPECIAL_EXC_FRAME_SIZE; + subi r1,r1,SPECIAL_EXC_FRAME_SIZE #define SPRN_DBG_SRR0 SPRN_DSRR0 #define SPRN_DBG_SRR1 SPRN_DSRR1 #define MC_SET_KSTACK \ ld r1,PACA_MC_STACK(r13); \ - subi r1,r1,SPECIAL_EXC_FRAME_SIZE; + subi r1,r1,SPECIAL_EXC_FRAME_SIZE #define SPRN_MC_SRR0 SPRN_MCSRR0 #define SPRN_MC_SRR1 SPRN_MCSRR1 @@ -100,20 +342,6 @@ #define GDBELL_EXCEPTION_PROLOG(n, intnum, addition) \ EXCEPTION_PROLOG(n, intnum, GDBELL, addition##_GDBELL(n)) -/* - * Store user-visible scratch in PACA exception slots and restore proper value - */ -#define PROLOG_STORE_RESTORE_SCRATCH_GEN -#define PROLOG_STORE_RESTORE_SCRATCH_GDBELL -#define PROLOG_STORE_RESTORE_SCRATCH_DBG -#define PROLOG_STORE_RESTORE_SCRATCH_MC - -#define PROLOG_STORE_RESTORE_SCRATCH_CRIT \ - mfspr r10,SPRN_SPRG_CRIT_SCRATCH; /* get r13 */ \ - std r10,PACA_EXCRIT+EX_R13(r13); \ - ld r11,PACA_SPRG3(r13); \ - mtspr SPRN_SPRG_CRIT_SCRATCH,r11; - /* Variants of the "addition" argument for the prolog */ #define PROLOG_ADDITION_NONE_GEN(n) @@ -147,10 +375,8 @@ std r15,PACA_EXMC+EX_R15(r13) -/* Core exception code for all exceptions except TLB misses. - * XXX: Needs to make SPRN_SPRG_GEN depend on exception type - */ -#define EXCEPTION_COMMON(n, excf, ints) \ +/* Core exception code for all exceptions except TLB misses. */ +#define EXCEPTION_COMMON_LVL(n, scratch, excf) \ exc_##n##_common: \ std r0,GPR0(r1); /* save r0 in stackframe */ \ std r2,GPR2(r1); /* save r2 in stackframe */ \ @@ -163,7 +389,7 @@ exc_##n##_common: \ ACCOUNT_CPU_USER_ENTRY(r10,r11);/* accounting (uses cr0+eq) */ \ 2: ld r3,excf+EX_R10(r13); /* get back r10 */ \ ld r4,excf+EX_R11(r13); /* get back r11 */ \ - mfspr r5,SPRN_SPRG_GEN_SCRATCH;/* get back r13 */ \ + mfspr r5,scratch; /* get back r13 */ \ std r12,GPR12(r1); /* save r12 in stackframe */ \ ld r2,PACATOC(r13); /* get kernel TOC into r2 */ \ mflr r6; /* save LR in stackframe */ \ @@ -187,24 +413,29 @@ exc_##n##_common: \ std r11,SOFTE(r1); /* and save it to stackframe */ \ std r12,STACK_FRAME_OVERHEAD-16(r1); /* mark the frame */ \ std r3,_TRAP(r1); /* set trap number */ \ - std r0,RESULT(r1); /* clear regs->result */ \ - ints; + std r0,RESULT(r1); /* clear regs->result */ -/* Variants for the "ints" argument. This one does nothing when we want - * to keep interrupts in their original state - */ -#define INTS_KEEP +#define EXCEPTION_COMMON(n) \ + EXCEPTION_COMMON_LVL(n, SPRN_SPRG_GEN_SCRATCH, PACA_EXGEN) +#define EXCEPTION_COMMON_CRIT(n) \ + EXCEPTION_COMMON_LVL(n, SPRN_SPRG_CRIT_SCRATCH, PACA_EXCRIT) +#define EXCEPTION_COMMON_MC(n) \ + EXCEPTION_COMMON_LVL(n, SPRN_SPRG_MC_SCRATCH, PACA_EXMC) +#define EXCEPTION_COMMON_DBG(n) \ + EXCEPTION_COMMON_LVL(n, SPRN_SPRG_DBG_SCRATCH, PACA_EXDBG) -/* This second version is meant for exceptions that don't immediately - * hard-enable. We set a bit in paca->irq_happened to ensure that - * a subsequent call to arch_local_irq_restore() will properly - * hard-enable and avoid the fast-path, and then reconcile irq state. +/* + * This is meant for exceptions that don't immediately hard-enable. We + * set a bit in paca->irq_happened to ensure that a subsequent call to + * arch_local_irq_restore() will properly hard-enable and avoid the + * fast-path, and then reconcile irq state. */ #define INTS_DISABLE RECONCILE_IRQ_STATE(r3,r4) -/* This is called by exceptions that used INTS_KEEP (that did not touch - * irq indicators in the PACA). This will restore MSR:EE to it's previous - * value +/* + * This is called by exceptions that don't use INTS_DISABLE (that did not + * touch irq indicators in the PACA). This will restore MSR:EE to it's + * previous value * * XXX In the long run, we may want to open-code it in order to separate the * load from the wrtee, thus limiting the latency caused by the dependency @@ -262,12 +493,13 @@ exc_##n##_bad_stack: \ #define MASKABLE_EXCEPTION(trapnum, intnum, label, hdlr, ack) \ START_EXCEPTION(label); \ NORMAL_EXCEPTION_PROLOG(trapnum, intnum, PROLOG_ADDITION_MASKABLE)\ - EXCEPTION_COMMON(trapnum, PACA_EXGEN, INTS_DISABLE) \ + EXCEPTION_COMMON(trapnum) \ + INTS_DISABLE; \ ack(r8); \ CHECK_NAPPING(); \ addi r3,r1,STACK_FRAME_OVERHEAD; \ bl hdlr; \ - b .ret_from_except_lite; + b ret_from_except_lite; /* This value is used to mark exception frames on the stack. */ .section ".toc","aw" @@ -283,8 +515,8 @@ exception_marker: .balign 0x1000 .globl interrupt_base_book3e interrupt_base_book3e: /* fake trap */ - EXCEPTION_STUB(0x000, machine_check) /* 0x0200 */ - EXCEPTION_STUB(0x020, critical_input) /* 0x0580 */ + EXCEPTION_STUB(0x000, machine_check) + EXCEPTION_STUB(0x020, critical_input) /* 0x0100 */ EXCEPTION_STUB(0x040, debug_crit) /* 0x0d00 */ EXCEPTION_STUB(0x060, data_storage) /* 0x0300 */ EXCEPTION_STUB(0x080, instruction_storage) /* 0x0400 */ @@ -299,8 +531,8 @@ interrupt_base_book3e: /* fake trap */ EXCEPTION_STUB(0x1a0, watchdog) /* 0x09f0 */ EXCEPTION_STUB(0x1c0, data_tlb_miss) EXCEPTION_STUB(0x1e0, instruction_tlb_miss) - EXCEPTION_STUB(0x200, altivec_unavailable) /* 0x0f20 */ - EXCEPTION_STUB(0x220, altivec_assist) /* 0x1700 */ + EXCEPTION_STUB(0x200, altivec_unavailable) + EXCEPTION_STUB(0x220, altivec_assist) EXCEPTION_STUB(0x260, perfmon) EXCEPTION_STUB(0x280, doorbell) EXCEPTION_STUB(0x2a0, doorbell_crit) @@ -317,25 +549,25 @@ interrupt_end_book3e: START_EXCEPTION(critical_input); CRIT_EXCEPTION_PROLOG(0x100, BOOKE_INTERRUPT_CRITICAL, PROLOG_ADDITION_NONE) -// EXCEPTION_COMMON(0x100, PACA_EXCRIT, INTS_DISABLE) -// bl special_reg_save_crit -// CHECK_NAPPING(); -// addi r3,r1,STACK_FRAME_OVERHEAD -// bl .critical_exception -// b ret_from_crit_except - b . + EXCEPTION_COMMON_CRIT(0x100) + bl save_nvgprs + bl special_reg_save + CHECK_NAPPING(); + addi r3,r1,STACK_FRAME_OVERHEAD + bl unknown_exception + b ret_from_crit_except /* Machine Check Interrupt */ START_EXCEPTION(machine_check); - MC_EXCEPTION_PROLOG(0x200, BOOKE_INTERRUPT_MACHINE_CHECK, + MC_EXCEPTION_PROLOG(0x000, BOOKE_INTERRUPT_MACHINE_CHECK, PROLOG_ADDITION_NONE) -// EXCEPTION_COMMON(0x200, PACA_EXMC, INTS_DISABLE) -// bl special_reg_save_mc -// addi r3,r1,STACK_FRAME_OVERHEAD -// CHECK_NAPPING(); -// bl .machine_check_exception -// b ret_from_mc_except - b . + EXCEPTION_COMMON_MC(0x000) + bl save_nvgprs + bl special_reg_save + CHECK_NAPPING(); + addi r3,r1,STACK_FRAME_OVERHEAD + bl machine_check_exception + b ret_from_mc_except /* Data Storage Interrupt */ START_EXCEPTION(data_storage) @@ -343,7 +575,8 @@ interrupt_end_book3e: PROLOG_ADDITION_2REGS) mfspr r14,SPRN_DEAR mfspr r15,SPRN_ESR - EXCEPTION_COMMON(0x300, PACA_EXGEN, INTS_DISABLE) + EXCEPTION_COMMON(0x300) + INTS_DISABLE b storage_fault_common /* Instruction Storage Interrupt */ @@ -352,12 +585,13 @@ interrupt_end_book3e: PROLOG_ADDITION_2REGS) li r15,0 mr r14,r10 - EXCEPTION_COMMON(0x400, PACA_EXGEN, INTS_DISABLE) + EXCEPTION_COMMON(0x400) + INTS_DISABLE b storage_fault_common /* External Input Interrupt */ MASKABLE_EXCEPTION(0x500, BOOKE_INTERRUPT_EXTERNAL, - external_input, .do_IRQ, ACK_NONE) + external_input, do_IRQ, ACK_NONE) /* Alignment */ START_EXCEPTION(alignment); @@ -365,7 +599,7 @@ interrupt_end_book3e: PROLOG_ADDITION_2REGS) mfspr r14,SPRN_DEAR mfspr r15,SPRN_ESR - EXCEPTION_COMMON(0x600, PACA_EXGEN, INTS_KEEP) + EXCEPTION_COMMON(0x600) b alignment_more /* no room, go out of line */ /* Program Interrupt */ @@ -373,90 +607,96 @@ interrupt_end_book3e: NORMAL_EXCEPTION_PROLOG(0x700, BOOKE_INTERRUPT_PROGRAM, PROLOG_ADDITION_1REG) mfspr r14,SPRN_ESR - EXCEPTION_COMMON(0x700, PACA_EXGEN, INTS_DISABLE) + EXCEPTION_COMMON(0x700) + INTS_DISABLE std r14,_DSISR(r1) addi r3,r1,STACK_FRAME_OVERHEAD ld r14,PACA_EXGEN+EX_R14(r13) - bl .save_nvgprs - bl .program_check_exception - b .ret_from_except + bl save_nvgprs + bl program_check_exception + b ret_from_except /* Floating Point Unavailable Interrupt */ START_EXCEPTION(fp_unavailable); NORMAL_EXCEPTION_PROLOG(0x800, BOOKE_INTERRUPT_FP_UNAVAIL, PROLOG_ADDITION_NONE) /* we can probably do a shorter exception entry for that one... */ - EXCEPTION_COMMON(0x800, PACA_EXGEN, INTS_KEEP) + EXCEPTION_COMMON(0x800) ld r12,_MSR(r1) andi. r0,r12,MSR_PR; beq- 1f - bl .load_up_fpu + bl load_up_fpu b fast_exception_return 1: INTS_DISABLE - bl .save_nvgprs + bl save_nvgprs addi r3,r1,STACK_FRAME_OVERHEAD - bl .kernel_fp_unavailable_exception - b .ret_from_except + bl kernel_fp_unavailable_exception + b ret_from_except /* Altivec Unavailable Interrupt */ START_EXCEPTION(altivec_unavailable); NORMAL_EXCEPTION_PROLOG(0x200, BOOKE_INTERRUPT_SPE_ALTIVEC_UNAVAIL, PROLOG_ADDITION_NONE) /* we can probably do a shorter exception entry for that one... */ - EXCEPTION_COMMON(0x200, PACA_EXGEN, INTS_KEEP) + EXCEPTION_COMMON(0x200) #ifdef CONFIG_ALTIVEC BEGIN_FTR_SECTION ld r12,_MSR(r1) andi. r0,r12,MSR_PR; beq- 1f - bl .load_up_altivec + bl load_up_altivec b fast_exception_return 1: END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) #endif INTS_DISABLE - bl .save_nvgprs + bl save_nvgprs addi r3,r1,STACK_FRAME_OVERHEAD - bl .altivec_unavailable_exception - b .ret_from_except + bl altivec_unavailable_exception + b ret_from_except /* AltiVec Assist */ START_EXCEPTION(altivec_assist); NORMAL_EXCEPTION_PROLOG(0x220, BOOKE_INTERRUPT_SPE_FP_DATA_ALTIVEC_ASSIST, PROLOG_ADDITION_NONE) - EXCEPTION_COMMON(0x220, PACA_EXGEN, INTS_DISABLE) - bl .save_nvgprs + EXCEPTION_COMMON(0x220) + INTS_DISABLE + bl save_nvgprs addi r3,r1,STACK_FRAME_OVERHEAD #ifdef CONFIG_ALTIVEC BEGIN_FTR_SECTION - bl .altivec_assist_exception + bl altivec_assist_exception END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) #else - bl .unknown_exception + bl unknown_exception #endif - b .ret_from_except + b ret_from_except /* Decrementer Interrupt */ MASKABLE_EXCEPTION(0x900, BOOKE_INTERRUPT_DECREMENTER, - decrementer, .timer_interrupt, ACK_DEC) + decrementer, timer_interrupt, ACK_DEC) /* Fixed Interval Timer Interrupt */ MASKABLE_EXCEPTION(0x980, BOOKE_INTERRUPT_FIT, - fixed_interval, .unknown_exception, ACK_FIT) + fixed_interval, unknown_exception, ACK_FIT) /* Watchdog Timer Interrupt */ START_EXCEPTION(watchdog); CRIT_EXCEPTION_PROLOG(0x9f0, BOOKE_INTERRUPT_WATCHDOG, PROLOG_ADDITION_NONE) -// EXCEPTION_COMMON(0x9f0, PACA_EXCRIT, INTS_DISABLE) -// bl special_reg_save_crit -// CHECK_NAPPING(); -// addi r3,r1,STACK_FRAME_OVERHEAD -// bl .unknown_exception -// b ret_from_crit_except - b . + EXCEPTION_COMMON_CRIT(0x9f0) + bl save_nvgprs + bl special_reg_save + CHECK_NAPPING(); + addi r3,r1,STACK_FRAME_OVERHEAD +#ifdef CONFIG_BOOKE_WDT + bl WatchdogException +#else + bl unknown_exception +#endif + b ret_from_crit_except /* System Call Interrupt */ START_EXCEPTION(system_call) @@ -470,11 +710,12 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) START_EXCEPTION(ap_unavailable); NORMAL_EXCEPTION_PROLOG(0xf20, BOOKE_INTERRUPT_AP_UNAVAIL, PROLOG_ADDITION_NONE) - EXCEPTION_COMMON(0xf20, PACA_EXGEN, INTS_DISABLE) - bl .save_nvgprs + EXCEPTION_COMMON(0xf20) + INTS_DISABLE + bl save_nvgprs addi r3,r1,STACK_FRAME_OVERHEAD - bl .unknown_exception - b .ret_from_except + bl unknown_exception + b ret_from_except /* Debug exception as a critical interrupt*/ START_EXCEPTION(debug_crit); @@ -513,7 +754,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) mtcr r10 ld r10,PACA_EXCRIT+EX_R10(r13) /* restore registers */ ld r11,PACA_EXCRIT+EX_R11(r13) - ld r13,PACA_EXCRIT+EX_R13(r13) + mfspr r13,SPRN_SPRG_CRIT_SCRATCH rfci /* Normal debug exception */ @@ -526,18 +767,16 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) /* Now we mash up things to make it look like we are coming on a * normal exception */ - ld r15,PACA_EXCRIT+EX_R13(r13) - mtspr SPRN_SPRG_GEN_SCRATCH,r15 mfspr r14,SPRN_DBSR - EXCEPTION_COMMON(0xd00, PACA_EXCRIT, INTS_DISABLE) + EXCEPTION_COMMON_CRIT(0xd00) std r14,_DSISR(r1) addi r3,r1,STACK_FRAME_OVERHEAD mr r4,r14 ld r14,PACA_EXCRIT+EX_R14(r13) ld r15,PACA_EXCRIT+EX_R15(r13) - bl .save_nvgprs - bl .DebugException - b .ret_from_except + bl save_nvgprs + bl DebugException + b ret_from_except kernel_dbg_exc: b . /* NYI */ @@ -592,43 +831,43 @@ kernel_dbg_exc: /* Now we mash up things to make it look like we are coming on a * normal exception */ - mfspr r15,SPRN_SPRG_DBG_SCRATCH - mtspr SPRN_SPRG_GEN_SCRATCH,r15 mfspr r14,SPRN_DBSR - EXCEPTION_COMMON(0xd08, PACA_EXDBG, INTS_DISABLE) + EXCEPTION_COMMON_DBG(0xd08) + INTS_DISABLE std r14,_DSISR(r1) addi r3,r1,STACK_FRAME_OVERHEAD mr r4,r14 ld r14,PACA_EXDBG+EX_R14(r13) ld r15,PACA_EXDBG+EX_R15(r13) - bl .save_nvgprs - bl .DebugException - b .ret_from_except + bl save_nvgprs + bl DebugException + b ret_from_except START_EXCEPTION(perfmon); NORMAL_EXCEPTION_PROLOG(0x260, BOOKE_INTERRUPT_PERFORMANCE_MONITOR, PROLOG_ADDITION_NONE) - EXCEPTION_COMMON(0x260, PACA_EXGEN, INTS_DISABLE) + EXCEPTION_COMMON(0x260) + INTS_DISABLE CHECK_NAPPING() addi r3,r1,STACK_FRAME_OVERHEAD - bl .performance_monitor_exception - b .ret_from_except_lite + bl performance_monitor_exception + b ret_from_except_lite /* Doorbell interrupt */ MASKABLE_EXCEPTION(0x280, BOOKE_INTERRUPT_DOORBELL, - doorbell, .doorbell_exception, ACK_NONE) + doorbell, doorbell_exception, ACK_NONE) /* Doorbell critical Interrupt */ START_EXCEPTION(doorbell_crit); CRIT_EXCEPTION_PROLOG(0x2a0, BOOKE_INTERRUPT_DOORBELL_CRITICAL, PROLOG_ADDITION_NONE) -// EXCEPTION_COMMON(0x2a0, PACA_EXCRIT, INTS_DISABLE) -// bl special_reg_save_crit -// CHECK_NAPPING(); -// addi r3,r1,STACK_FRAME_OVERHEAD -// bl .doorbell_critical_exception -// b ret_from_crit_except - b . + EXCEPTION_COMMON_CRIT(0x2a0) + bl save_nvgprs + bl special_reg_save + CHECK_NAPPING(); + addi r3,r1,STACK_FRAME_OVERHEAD + bl unknown_exception + b ret_from_crit_except /* * Guest doorbell interrupt @@ -637,52 +876,52 @@ kernel_dbg_exc: START_EXCEPTION(guest_doorbell); GDBELL_EXCEPTION_PROLOG(0x2c0, BOOKE_INTERRUPT_GUEST_DBELL, PROLOG_ADDITION_NONE) - EXCEPTION_COMMON(0x2c0, PACA_EXGEN, INTS_KEEP) + EXCEPTION_COMMON(0x2c0) addi r3,r1,STACK_FRAME_OVERHEAD - bl .save_nvgprs + bl save_nvgprs INTS_RESTORE_HARD - bl .unknown_exception - b .ret_from_except + bl unknown_exception + b ret_from_except /* Guest Doorbell critical Interrupt */ START_EXCEPTION(guest_doorbell_crit); CRIT_EXCEPTION_PROLOG(0x2e0, BOOKE_INTERRUPT_GUEST_DBELL_CRIT, PROLOG_ADDITION_NONE) -// EXCEPTION_COMMON(0x2e0, PACA_EXCRIT, INTS_DISABLE) -// bl special_reg_save_crit -// CHECK_NAPPING(); -// addi r3,r1,STACK_FRAME_OVERHEAD -// bl .guest_doorbell_critical_exception -// b ret_from_crit_except - b . + EXCEPTION_COMMON_CRIT(0x2e0) + bl save_nvgprs + bl special_reg_save + CHECK_NAPPING(); + addi r3,r1,STACK_FRAME_OVERHEAD + bl unknown_exception + b ret_from_crit_except /* Hypervisor call */ START_EXCEPTION(hypercall); NORMAL_EXCEPTION_PROLOG(0x310, BOOKE_INTERRUPT_HV_SYSCALL, PROLOG_ADDITION_NONE) - EXCEPTION_COMMON(0x310, PACA_EXGEN, INTS_KEEP) + EXCEPTION_COMMON(0x310) addi r3,r1,STACK_FRAME_OVERHEAD - bl .save_nvgprs + bl save_nvgprs INTS_RESTORE_HARD - bl .unknown_exception - b .ret_from_except + bl unknown_exception + b ret_from_except /* Embedded Hypervisor priviledged */ START_EXCEPTION(ehpriv); NORMAL_EXCEPTION_PROLOG(0x320, BOOKE_INTERRUPT_HV_PRIV, PROLOG_ADDITION_NONE) - EXCEPTION_COMMON(0x320, PACA_EXGEN, INTS_KEEP) + EXCEPTION_COMMON(0x320) addi r3,r1,STACK_FRAME_OVERHEAD - bl .save_nvgprs + bl save_nvgprs INTS_RESTORE_HARD - bl .unknown_exception - b .ret_from_except + 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) + EXCEPTION_COMMON(0x340) addi r3,r1,STACK_FRAME_OVERHEAD bl .save_nvgprs INTS_RESTORE_HARD @@ -775,16 +1014,16 @@ storage_fault_common: mr r5,r15 ld r14,PACA_EXGEN+EX_R14(r13) ld r15,PACA_EXGEN+EX_R15(r13) - bl .do_page_fault + bl do_page_fault cmpdi r3,0 bne- 1f - b .ret_from_except_lite -1: bl .save_nvgprs + b ret_from_except_lite +1: bl save_nvgprs mr r5,r3 addi r3,r1,STACK_FRAME_OVERHEAD ld r4,_DAR(r1) - bl .bad_page_fault - b .ret_from_except + bl bad_page_fault + b ret_from_except /* * Alignment exception doesn't fit entirely in the 0x100 bytes so it @@ -796,10 +1035,10 @@ alignment_more: addi r3,r1,STACK_FRAME_OVERHEAD ld r14,PACA_EXGEN+EX_R14(r13) ld r15,PACA_EXGEN+EX_R15(r13) - bl .save_nvgprs + bl save_nvgprs INTS_RESTORE_HARD - bl .alignment_exception - b .ret_from_except + bl alignment_exception + b ret_from_except /* * We branch here from entry_64.S for the last stage of the exception @@ -933,7 +1172,7 @@ bad_stack_book3e: std r12,0(r11) ld r2,PACATOC(r13) 1: addi r3,r1,STACK_FRAME_OVERHEAD - bl .kernel_bad_stack + bl kernel_bad_stack b 1b /* @@ -1228,22 +1467,6 @@ a2_tlbinit_after_linear_map: .globl a2_tlbinit_after_iprot_flush a2_tlbinit_after_iprot_flush: -#ifdef CONFIG_PPC_EARLY_DEBUG_WSP - /* Now establish early debug mappings if applicable */ - /* Restore the MAS0 we used for linear mapping load */ - mtspr SPRN_MAS0,r11 - - lis r3,(MAS1_VALID | MAS1_IPROT)@h - ori r3,r3,(BOOK3E_PAGESZ_4K << MAS1_TSIZE_SHIFT) - mtspr SPRN_MAS1,r3 - LOAD_REG_IMMEDIATE(r3, WSP_UART_VIRT | MAS2_I | MAS2_G) - mtspr SPRN_MAS2,r3 - LOAD_REG_IMMEDIATE(r3, WSP_UART_PHYS | MAS3_SR | MAS3_SW) - mtspr SPRN_MAS7_MAS3,r3 - /* re-use the MAS8 value from the linear mapping */ - tlbwe -#endif /* CONFIG_PPC_EARLY_DEBUG_WSP */ - PPC_TLBILX(0,0,R0) sync isync @@ -1282,13 +1505,13 @@ _GLOBAL(start_initialization_book3e) * and always use AS 0, so we just set it up to match our link * address and never use 0 based addresses. */ - bl .initial_tlb_book3e + bl initial_tlb_book3e /* Init global core bits */ - bl .init_core_book3e + bl init_core_book3e /* Init per-thread bits */ - bl .init_thread_book3e + bl init_thread_book3e /* Return to common init code */ tovirt(r28,r28) @@ -1309,7 +1532,7 @@ _GLOBAL(start_initialization_book3e) */ _GLOBAL(book3e_secondary_core_init_tlb_set) li r4,1 - b .generic_secondary_smp_init + b generic_secondary_smp_init _GLOBAL(book3e_secondary_core_init) mflr r28 @@ -1319,18 +1542,18 @@ _GLOBAL(book3e_secondary_core_init) bne 2f /* Setup TLB for this core */ - bl .initial_tlb_book3e + bl initial_tlb_book3e /* We can return from the above running at a different * address, so recalculate r2 (TOC) */ - bl .relative_toc + bl relative_toc /* Init global core bits */ -2: bl .init_core_book3e +2: bl init_core_book3e /* Init per-thread bits */ -3: bl .init_thread_book3e +3: bl init_thread_book3e /* Return to common init code at proper virtual address. * @@ -1357,14 +1580,14 @@ _GLOBAL(book3e_secondary_thread_init) mflr r28 b 3b -_STATIC(init_core_book3e) +init_core_book3e: /* Establish the interrupt vector base */ LOAD_REG_IMMEDIATE(r3, interrupt_base_book3e) mtspr SPRN_IVPR,r3 sync blr -_STATIC(init_thread_book3e) +init_thread_book3e: lis r3,(SPRN_EPCR_ICM | SPRN_EPCR_GICM)@h mtspr SPRN_EPCR,r3 diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 38d507306a1..a7d36b19221 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -54,14 +54,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE) \ xori r12,r12,MSR_LE ; \ mtspr SPRN_SRR1,r12 ; \ rfid ; /* return to userspace */ \ - b . ; \ -2: mfspr r12,SPRN_SRR1 ; \ - andi. r12,r12,MSR_PR ; \ - bne 0b ; \ - mtspr SPRN_SRR0,r3 ; \ - mtspr SPRN_SRR1,r4 ; \ - mtspr SPRN_SDR1,r5 ; \ - rfid ; \ b . ; /* prevent speculative execution */ #if defined(CONFIG_RELOCATABLE) @@ -121,9 +113,10 @@ BEGIN_FTR_SECTION cmpwi cr1,r13,2 /* Total loss of HV state is fatal, we could try to use the * PIR to locate a PACA, then use an emergency stack etc... - * but for now, let's just stay stuck here + * OPAL v3 based powernv platforms have new idle states + * which fall in this catagory. */ - bgt cr1,. + bgt cr1,8f GET_PACA(r13) #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE @@ -139,8 +132,13 @@ BEGIN_FTR_SECTION #endif beq cr1,2f - b .power7_wakeup_noloss -2: b .power7_wakeup_loss + b power7_wakeup_noloss +2: b power7_wakeup_loss + + /* Fast Sleep wakeup on PowerNV */ +8: GET_PACA(r13) + b power7_wakeup_tb_loss + 9: END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) #endif /* CONFIG_PPC_P7_NAP */ @@ -164,13 +162,18 @@ BEGIN_FTR_SECTION */ mfspr r13,SPRN_SRR1 rlwinm. r13,r13,47-31,30,31 + OPT_GET_SPR(r13, SPRN_CFAR, CPU_FTR_CFAR) beq 9f + mfspr r13,SPRN_SRR1 + rlwinm. r13,r13,47-31,30,31 /* waking up from powersave (nap) state */ cmpwi cr1,r13,2 /* Total loss of HV state is fatal. let's just stay stuck here */ + OPT_GET_SPR(r13, SPRN_CFAR, CPU_FTR_CFAR) bgt cr1,. 9: + OPT_SET_SPR(r13, SPRN_CFAR, CPU_FTR_CFAR) END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) #endif /* CONFIG_PPC_P7_NAP */ EXCEPTION_PROLOG_0(PACA_EXMC) @@ -208,16 +211,16 @@ data_access_slb_pSeries: #endif /* __DISABLED__ */ mfspr r12,SPRN_SRR1 #ifndef CONFIG_RELOCATABLE - b .slb_miss_realmode + b slb_miss_realmode #else /* - * We can't just use a direct branch to .slb_miss_realmode + * We can't just use a direct branch to slb_miss_realmode * because the distance from here to there depends on where * the kernel ends up being put. */ mfctr r11 ld r10,PACAKBASE(r13) - LOAD_HANDLER(r10, .slb_miss_realmode) + LOAD_HANDLER(r10, slb_miss_realmode) mtctr r10 bctr #endif @@ -240,11 +243,11 @@ instruction_access_slb_pSeries: #endif /* __DISABLED__ */ mfspr r12,SPRN_SRR1 #ifndef CONFIG_RELOCATABLE - b .slb_miss_realmode + b slb_miss_realmode #else mfctr r11 ld r10,PACAKBASE(r13) - LOAD_HANDLER(r10, .slb_miss_realmode) + LOAD_HANDLER(r10, slb_miss_realmode) mtctr r10 bctr #endif @@ -436,9 +439,9 @@ BEGIN_FTR_SECTION * 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 + * Switch to mc_emergency stack and handle re-entrancy (we limit + * the nested MCE upto level 4 to avoid stack 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 @@ -461,6 +464,9 @@ BEGIN_FTR_SECTION 0: subi r1,r1,INT_FRAME_SIZE /* alloc stack frame */ addi r10,r10,1 /* increment paca->in_mce */ sth r10,PACA_IN_MCE(r13) + /* Limit nested MCE to level 4 to avoid stack overflow */ + cmpwi r10,4 + bgt 2f /* Check if we hit limit of 4 */ std r11,GPR1(r1) /* Save r1 on the stack. */ std r11,0(r1) /* make stack chain pointer */ mfspr r11,SPRN_SRR0 /* Save SRR0 */ @@ -479,10 +485,23 @@ BEGIN_FTR_SECTION 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 +1: mtspr SPRN_SRR0,r12 mtspr SPRN_SRR1,r11 rfid b . /* prevent speculative execution */ +2: + /* Stack overflow. Stay on emergency stack and panic. + * Keep the ME bit off while panic-ing, so that if we hit + * another machine check we checkstop. + */ + addi r1,r1,INT_FRAME_SIZE /* go back to previous stack frame */ + ld r11,PACAKMSR(r13) + ld r12,PACAKBASE(r13) + LOAD_HANDLER(r12, unrecover_mce) + li r10,MSR_ME + andc r11,r11,r10 /* Turn off MSR_ME */ + b 1b + b . /* prevent speculative execution */ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) machine_check_pSeries: @@ -521,7 +540,7 @@ do_stab_bolted_pSeries: std r12,PACA_EXSLB+EX_R12(r13) GET_SCRATCH0(r10) std r10,PACA_EXSLB+EX_R13(r13) - EXCEPTION_PROLOG_PSERIES_1(.do_stab_bolted, EXC_STD) + EXCEPTION_PROLOG_PSERIES_1(do_stab_bolted, EXC_STD) KVM_HANDLER_SKIP(PACA_EXGEN, EXC_STD, 0x300) KVM_HANDLER_SKIP(PACA_EXSLB, EXC_STD, 0x380) @@ -766,38 +785,38 @@ kvmppc_skip_Hinterrupt: /*** Common interrupt handlers ***/ - STD_EXCEPTION_COMMON(0x100, system_reset, .system_reset_exception) + STD_EXCEPTION_COMMON(0x100, system_reset, system_reset_exception) STD_EXCEPTION_COMMON_ASYNC(0x500, hardware_interrupt, do_IRQ) - STD_EXCEPTION_COMMON_ASYNC(0x900, decrementer, .timer_interrupt) - STD_EXCEPTION_COMMON(0x980, hdecrementer, .hdec_interrupt) + STD_EXCEPTION_COMMON_ASYNC(0x900, decrementer, timer_interrupt) + STD_EXCEPTION_COMMON(0x980, hdecrementer, hdec_interrupt) #ifdef CONFIG_PPC_DOORBELL - STD_EXCEPTION_COMMON_ASYNC(0xa00, doorbell_super, .doorbell_exception) + STD_EXCEPTION_COMMON_ASYNC(0xa00, doorbell_super, doorbell_exception) #else - STD_EXCEPTION_COMMON_ASYNC(0xa00, doorbell_super, .unknown_exception) + STD_EXCEPTION_COMMON_ASYNC(0xa00, doorbell_super, unknown_exception) #endif - STD_EXCEPTION_COMMON(0xb00, trap_0b, .unknown_exception) - STD_EXCEPTION_COMMON(0xd00, single_step, .single_step_exception) - STD_EXCEPTION_COMMON(0xe00, trap_0e, .unknown_exception) - STD_EXCEPTION_COMMON(0xe40, emulation_assist, .emulation_assist_interrupt) - STD_EXCEPTION_COMMON(0xe60, hmi_exception, .unknown_exception) + STD_EXCEPTION_COMMON(0xb00, trap_0b, unknown_exception) + STD_EXCEPTION_COMMON(0xd00, single_step, single_step_exception) + STD_EXCEPTION_COMMON(0xe00, trap_0e, unknown_exception) + STD_EXCEPTION_COMMON(0xe40, emulation_assist, emulation_assist_interrupt) + STD_EXCEPTION_COMMON(0xe60, hmi_exception, unknown_exception) #ifdef CONFIG_PPC_DOORBELL - STD_EXCEPTION_COMMON_ASYNC(0xe80, h_doorbell, .doorbell_exception) + STD_EXCEPTION_COMMON_ASYNC(0xe80, h_doorbell, doorbell_exception) #else - STD_EXCEPTION_COMMON_ASYNC(0xe80, h_doorbell, .unknown_exception) + STD_EXCEPTION_COMMON_ASYNC(0xe80, h_doorbell, unknown_exception) #endif - STD_EXCEPTION_COMMON_ASYNC(0xf00, performance_monitor, .performance_monitor_exception) - STD_EXCEPTION_COMMON(0x1300, instruction_breakpoint, .instruction_breakpoint_exception) - STD_EXCEPTION_COMMON(0x1502, denorm, .unknown_exception) + STD_EXCEPTION_COMMON_ASYNC(0xf00, performance_monitor, performance_monitor_exception) + STD_EXCEPTION_COMMON(0x1300, instruction_breakpoint, instruction_breakpoint_exception) + STD_EXCEPTION_COMMON(0x1502, denorm, unknown_exception) #ifdef CONFIG_ALTIVEC - STD_EXCEPTION_COMMON(0x1700, altivec_assist, .altivec_assist_exception) + STD_EXCEPTION_COMMON(0x1700, altivec_assist, altivec_assist_exception) #else - STD_EXCEPTION_COMMON(0x1700, altivec_assist, .unknown_exception) + STD_EXCEPTION_COMMON(0x1700, altivec_assist, unknown_exception) #endif #ifdef CONFIG_CBE_RAS - STD_EXCEPTION_COMMON(0x1200, cbe_system_error, .cbe_system_error_exception) - STD_EXCEPTION_COMMON(0x1600, cbe_maintenance, .cbe_maintenance_exception) - STD_EXCEPTION_COMMON(0x1800, cbe_thermal, .cbe_thermal_exception) + STD_EXCEPTION_COMMON(0x1200, cbe_system_error, cbe_system_error_exception) + STD_EXCEPTION_COMMON(0x1600, cbe_maintenance, cbe_maintenance_exception) + STD_EXCEPTION_COMMON(0x1800, cbe_thermal, cbe_thermal_exception) #endif /* CONFIG_CBE_RAS */ /* @@ -826,16 +845,16 @@ data_access_slb_relon_pSeries: mfspr r3,SPRN_DAR mfspr r12,SPRN_SRR1 #ifndef CONFIG_RELOCATABLE - b .slb_miss_realmode + b slb_miss_realmode #else /* - * We can't just use a direct branch to .slb_miss_realmode + * We can't just use a direct branch to slb_miss_realmode * because the distance from here to there depends on where * the kernel ends up being put. */ mfctr r11 ld r10,PACAKBASE(r13) - LOAD_HANDLER(r10, .slb_miss_realmode) + LOAD_HANDLER(r10, slb_miss_realmode) mtctr r10 bctr #endif @@ -851,11 +870,11 @@ instruction_access_slb_relon_pSeries: mfspr r3,SPRN_SRR0 /* SRR0 is faulting address */ mfspr r12,SPRN_SRR1 #ifndef CONFIG_RELOCATABLE - b .slb_miss_realmode + b slb_miss_realmode #else mfctr r11 ld r10,PACAKBASE(r13) - LOAD_HANDLER(r10, .slb_miss_realmode) + LOAD_HANDLER(r10, slb_miss_realmode) mtctr r10 bctr #endif @@ -963,7 +982,7 @@ system_call_entry: b system_call_common ppc64_runlatch_on_trampoline: - b .__ppc64_runlatch_on + b __ppc64_runlatch_on /* * Here we have detected that the kernel stack pointer is bad. @@ -1022,7 +1041,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR) std r12,RESULT(r1) std r11,STACK_FRAME_OVERHEAD-16(r1) 1: addi r3,r1,STACK_FRAME_OVERHEAD - bl .kernel_bad_stack + bl kernel_bad_stack b 1b /* @@ -1043,7 +1062,7 @@ data_access_common: ld r3,PACA_EXGEN+EX_DAR(r13) lwz r4,PACA_EXGEN+EX_DSISR(r13) li r5,0x300 - b .do_hash_page /* Try to handle as hpte fault */ + b do_hash_page /* Try to handle as hpte fault */ .align 7 .globl h_data_storage_common @@ -1053,11 +1072,11 @@ h_data_storage_common: mfspr r10,SPRN_HDSISR stw r10,PACA_EXGEN+EX_DSISR(r13) EXCEPTION_PROLOG_COMMON(0xe00, PACA_EXGEN) - bl .save_nvgprs + bl save_nvgprs DISABLE_INTS addi r3,r1,STACK_FRAME_OVERHEAD - bl .unknown_exception - b .ret_from_except + bl unknown_exception + b ret_from_except .align 7 .globl instruction_access_common @@ -1068,9 +1087,9 @@ instruction_access_common: ld r3,_NIP(r1) andis. r4,r12,0x5820 li r5,0x400 - b .do_hash_page /* Try to handle as hpte fault */ + b do_hash_page /* Try to handle as hpte fault */ - STD_EXCEPTION_COMMON(0xe20, h_instr_storage, .unknown_exception) + STD_EXCEPTION_COMMON(0xe20, h_instr_storage, unknown_exception) /* * Here is the common SLB miss user that is used when going to virtual @@ -1085,7 +1104,7 @@ slb_miss_user_common: stw r9,PACA_EXGEN+EX_CCR(r13) std r10,PACA_EXGEN+EX_LR(r13) std r11,PACA_EXGEN+EX_SRR0(r13) - bl .slb_allocate_user + bl slb_allocate_user ld r10,PACA_EXGEN+EX_LR(r13) ld r3,PACA_EXGEN+EX_R3(r13) @@ -1128,9 +1147,9 @@ slb_miss_fault: unrecov_user_slb: EXCEPTION_PROLOG_COMMON(0x4200, PACA_EXGEN) DISABLE_INTS - bl .save_nvgprs + bl save_nvgprs 1: addi r3,r1,STACK_FRAME_OVERHEAD - bl .unrecoverable_exception + bl unrecoverable_exception b 1b #endif /* __DISABLED__ */ @@ -1155,10 +1174,10 @@ machine_check_common: lwz r4,PACA_EXGEN+EX_DSISR(r13) std r3,_DAR(r1) std r4,_DSISR(r1) - bl .save_nvgprs + bl save_nvgprs addi r3,r1,STACK_FRAME_OVERHEAD - bl .machine_check_exception - b .ret_from_except + bl machine_check_exception + b ret_from_except .align 7 .globl alignment_common @@ -1172,31 +1191,31 @@ alignment_common: lwz r4,PACA_EXGEN+EX_DSISR(r13) std r3,_DAR(r1) std r4,_DSISR(r1) - bl .save_nvgprs + bl save_nvgprs DISABLE_INTS addi r3,r1,STACK_FRAME_OVERHEAD - bl .alignment_exception - b .ret_from_except + bl alignment_exception + b ret_from_except .align 7 .globl program_check_common program_check_common: EXCEPTION_PROLOG_COMMON(0x700, PACA_EXGEN) - bl .save_nvgprs + bl save_nvgprs DISABLE_INTS addi r3,r1,STACK_FRAME_OVERHEAD - bl .program_check_exception - b .ret_from_except + bl program_check_exception + b ret_from_except .align 7 .globl fp_unavailable_common fp_unavailable_common: EXCEPTION_PROLOG_COMMON(0x800, PACA_EXGEN) bne 1f /* if from user, just load it up */ - bl .save_nvgprs + bl save_nvgprs DISABLE_INTS addi r3,r1,STACK_FRAME_OVERHEAD - bl .kernel_fp_unavailable_exception + bl kernel_fp_unavailable_exception BUG_OPCODE 1: #ifdef CONFIG_PPC_TRANSACTIONAL_MEM @@ -1208,15 +1227,15 @@ BEGIN_FTR_SECTION bne- 2f END_FTR_SECTION_IFSET(CPU_FTR_TM) #endif - bl .load_up_fpu + bl load_up_fpu b fast_exception_return #ifdef CONFIG_PPC_TRANSACTIONAL_MEM 2: /* User process was in a transaction */ - bl .save_nvgprs + bl save_nvgprs DISABLE_INTS addi r3,r1,STACK_FRAME_OVERHEAD - bl .fp_unavailable_tm - b .ret_from_except + bl fp_unavailable_tm + b ret_from_except #endif .align 7 .globl altivec_unavailable_common @@ -1234,24 +1253,24 @@ BEGIN_FTR_SECTION bne- 2f END_FTR_SECTION_NESTED(CPU_FTR_TM, CPU_FTR_TM, 69) #endif - bl .load_up_altivec + bl load_up_altivec b fast_exception_return #ifdef CONFIG_PPC_TRANSACTIONAL_MEM 2: /* User process was in a transaction */ - bl .save_nvgprs + bl save_nvgprs DISABLE_INTS addi r3,r1,STACK_FRAME_OVERHEAD - bl .altivec_unavailable_tm - b .ret_from_except + bl altivec_unavailable_tm + b ret_from_except #endif 1: END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) #endif - bl .save_nvgprs + bl save_nvgprs DISABLE_INTS addi r3,r1,STACK_FRAME_OVERHEAD - bl .altivec_unavailable_exception - b .ret_from_except + bl altivec_unavailable_exception + b ret_from_except .align 7 .globl vsx_unavailable_common @@ -1269,26 +1288,26 @@ BEGIN_FTR_SECTION bne- 2f END_FTR_SECTION_NESTED(CPU_FTR_TM, CPU_FTR_TM, 69) #endif - b .load_up_vsx + b load_up_vsx #ifdef CONFIG_PPC_TRANSACTIONAL_MEM 2: /* User process was in a transaction */ - bl .save_nvgprs + bl save_nvgprs DISABLE_INTS addi r3,r1,STACK_FRAME_OVERHEAD - bl .vsx_unavailable_tm - b .ret_from_except + bl vsx_unavailable_tm + b ret_from_except #endif 1: END_FTR_SECTION_IFSET(CPU_FTR_VSX) #endif - bl .save_nvgprs + bl save_nvgprs DISABLE_INTS addi r3,r1,STACK_FRAME_OVERHEAD - bl .vsx_unavailable_exception - b .ret_from_except + bl vsx_unavailable_exception + b ret_from_except - STD_EXCEPTION_COMMON(0xf60, facility_unavailable, .facility_unavailable_exception) - STD_EXCEPTION_COMMON(0xf80, hv_facility_unavailable, .facility_unavailable_exception) + STD_EXCEPTION_COMMON(0xf60, facility_unavailable, facility_unavailable_exception) + STD_EXCEPTION_COMMON(0xf80, hv_facility_unavailable, facility_unavailable_exception) .align 7 .globl __end_handlers @@ -1383,9 +1402,10 @@ _GLOBAL(opal_mc_secondary_handler) machine_check_handle_early: std r0,GPR0(r1) /* Save r0 */ EXCEPTION_PROLOG_COMMON_3(0x200) - bl .save_nvgprs + bl save_nvgprs addi r3,r1,STACK_FRAME_OVERHEAD - bl .machine_check_early + bl machine_check_early + std r3,RESULT(r1) /* Save result */ ld r12,_MSR(r1) #ifdef CONFIG_PPC_P7_NAP /* @@ -1405,11 +1425,11 @@ machine_check_handle_early: /* Supervisor state loss */ li r0,1 stb r0,PACA_NAPSTATELOST(r13) -3: bl .machine_check_queue_event +3: bl machine_check_queue_event MACHINE_CHECK_HANDLER_WINDUP GET_PACA(r13) ld r1,PACAR1(r13) - b .power7_enter_nap_mode + b power7_enter_nap_mode 4: #endif /* @@ -1440,16 +1460,38 @@ machine_check_handle_early: */ andi. r11,r12,MSR_RI bne 2f -1: addi r3,r1,STACK_FRAME_OVERHEAD - bl .unrecoverable_exception - b 1b +1: mfspr r11,SPRN_SRR0 + ld r10,PACAKBASE(r13) + LOAD_HANDLER(r10,unrecover_mce) + mtspr SPRN_SRR0,r10 + ld r10,PACAKMSR(r13) + /* + * We are going down. But there are chances that we might get hit by + * another MCE during panic path and we may run into unstable state + * with no way out. Hence, turn ME bit off while going down, so that + * when another MCE is hit during panic path, system will checkstop + * and hypervisor will get restarted cleanly by SP. + */ + li r3,MSR_ME + andc r10,r10,r3 /* Turn off MSR_ME */ + mtspr SPRN_SRR1,r10 + rfid + b . 2: /* + * Check if we have successfully handled/recovered from error, if not + * then stay on emergency stack and panic. + */ + ld r3,RESULT(r1) /* Load result */ + cmpdi r3,0 /* see if we handled MCE successfully */ + + beq 1b /* if !handled then panic */ + /* * 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 + bl machine_check_queue_event MACHINE_CHECK_HANDLER_WINDUP rfid 9: @@ -1457,6 +1499,17 @@ machine_check_handle_early: MACHINE_CHECK_HANDLER_WINDUP b machine_check_pSeries +unrecover_mce: + /* Invoke machine_check_exception to print MCE event and panic. */ + addi r3,r1,STACK_FRAME_OVERHEAD + bl machine_check_exception + /* + * We will not reach here. Even if we did, there is no way out. Call + * unrecoverable_exception and die. + */ +1: addi r3,r1,STACK_FRAME_OVERHEAD + bl unrecoverable_exception + b 1b /* * r13 points to the PACA, r9 contains the saved CR, * r12 contain the saved SRR1, SRR0 is still ready for return @@ -1465,7 +1518,7 @@ machine_check_handle_early: * r3 is saved in paca->slb_r3 * We assume we aren't going to take any exceptions during this procedure. */ -_GLOBAL(slb_miss_realmode) +slb_miss_realmode: mflr r10 #ifdef CONFIG_RELOCATABLE mtctr r11 @@ -1474,7 +1527,7 @@ _GLOBAL(slb_miss_realmode) stw r9,PACA_EXSLB+EX_CCR(r13) /* save CR in exc. frame */ std r10,PACA_EXSLB+EX_LR(r13) /* save LR */ - bl .slb_allocate_realmode + bl slb_allocate_realmode /* All done -- return from exception. */ @@ -1514,9 +1567,9 @@ _GLOBAL(slb_miss_realmode) unrecov_slb: EXCEPTION_PROLOG_COMMON(0x4100, PACA_EXSLB) DISABLE_INTS - bl .save_nvgprs + bl save_nvgprs 1: addi r3,r1,STACK_FRAME_OVERHEAD - bl .unrecoverable_exception + bl unrecoverable_exception b 1b @@ -1533,7 +1586,7 @@ power4_fixup_nap: * Hash table stuff */ .align 7 -_STATIC(do_hash_page) +do_hash_page: std r3,_DAR(r1) std r4,_DSISR(r1) @@ -1570,7 +1623,7 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_SLB) * * at return r3 = 0 for success, 1 for page fault, negative for error */ - bl .hash_page /* build HPTE if possible */ + bl hash_page /* build HPTE if possible */ cmpdi r3,0 /* see if hash_page succeeded */ /* Success */ @@ -1584,35 +1637,35 @@ handle_page_fault: 11: ld r4,_DAR(r1) ld r5,_DSISR(r1) addi r3,r1,STACK_FRAME_OVERHEAD - bl .do_page_fault + bl do_page_fault cmpdi r3,0 beq+ 12f - bl .save_nvgprs + bl save_nvgprs mr r5,r3 addi r3,r1,STACK_FRAME_OVERHEAD lwz r4,_DAR(r1) - bl .bad_page_fault - b .ret_from_except + bl bad_page_fault + b ret_from_except /* We have a data breakpoint exception - handle it */ handle_dabr_fault: - bl .save_nvgprs + bl save_nvgprs ld r4,_DAR(r1) ld r5,_DSISR(r1) addi r3,r1,STACK_FRAME_OVERHEAD - bl .do_break -12: b .ret_from_except_lite + bl do_break +12: b ret_from_except_lite /* We have a page fault that hash_page could handle but HV refused * the PTE insertion */ -13: bl .save_nvgprs +13: bl save_nvgprs mr r5,r3 addi r3,r1,STACK_FRAME_OVERHEAD ld r4,_DAR(r1) - bl .low_hash_fault - b .ret_from_except + bl low_hash_fault + b ret_from_except /* * We come here as a result of a DSI at a point where we don't want @@ -1621,16 +1674,16 @@ handle_dabr_fault: * were soft-disabled. We want to invoke the exception handler for * the access, or panic if there isn't a handler. */ -77: bl .save_nvgprs +77: bl save_nvgprs mr r4,r3 addi r3,r1,STACK_FRAME_OVERHEAD li r5,SIGSEGV - bl .bad_page_fault - b .ret_from_except + bl bad_page_fault + b ret_from_except /* here we have a segment miss */ do_ste_alloc: - bl .ste_allocate /* try to insert stab entry */ + bl ste_allocate /* try to insert stab entry */ cmpdi r3,0 bne- handle_page_fault b fast_exception_return @@ -1643,7 +1696,7 @@ do_ste_alloc: * We assume (DAR >> 60) == 0xc. */ .align 7 -_GLOBAL(do_stab_bolted) +do_stab_bolted: stw r9,PACA_EXSLB+EX_CCR(r13) /* save CR in exc. frame */ std r11,PACA_EXSLB+EX_SRR0(r13) /* save SRR0 in exc. frame */ mfspr r11,SPRN_DAR /* ea */ diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index 2230fd0ca3e..742694c1d85 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -55,9 +55,9 @@ int crash_mem_ranges; int __init early_init_dt_scan_fw_dump(unsigned long node, const char *uname, int depth, void *data) { - __be32 *sections; + const __be32 *sections; int i, num_sections; - unsigned long size; + int size; const int *token; if (depth != 1 || strcmp(uname, "rtas") != 0) @@ -69,7 +69,7 @@ int __init early_init_dt_scan_fw_dump(unsigned long node, */ token = of_get_flat_dt_prop(node, "ibm,configure-kernel-dump", NULL); if (!token) - return 0; + return 1; fw_dump.fadump_supported = 1; fw_dump.ibm_configure_kernel_dump = *token; @@ -92,7 +92,7 @@ int __init early_init_dt_scan_fw_dump(unsigned long node, &size); if (!sections) - return 0; + return 1; num_sections = size / (3 * sizeof(u32)); @@ -110,6 +110,7 @@ int __init early_init_dt_scan_fw_dump(unsigned long node, break; } } + return 1; } @@ -645,7 +646,7 @@ static int __init fadump_build_cpu_notes(const struct fadump_mem_struct *fdm) } /* Lower 4 bytes of reg_value contains logical cpu id */ cpu = reg_entry->reg_value & FADUMP_CPU_ID_MASK; - if (!cpumask_test_cpu(cpu, &fdh->cpu_online_mask)) { + if (fdh && !cpumask_test_cpu(cpu, &fdh->cpu_online_mask)) { SKIP_TO_NEXT_CPU(reg_entry); continue; } @@ -662,9 +663,11 @@ static int __init fadump_build_cpu_notes(const struct fadump_mem_struct *fdm) } fadump_final_note(note_buf); - pr_debug("Updating elfcore header (%llx) with cpu notes\n", + if (fdh) { + pr_debug("Updating elfcore header (%llx) with cpu notes\n", fdh->elfcorehdr_addr); - fadump_update_elfcore_header((char *)__va(fdh->elfcorehdr_addr)); + fadump_update_elfcore_header((char *)__va(fdh->elfcorehdr_addr)); + } return 0; error_out: diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c index 9b27b293a92..d178834fe50 100644 --- a/arch/powerpc/kernel/ftrace.c +++ b/arch/powerpc/kernel/ftrace.c @@ -10,6 +10,8 @@ * */ +#define pr_fmt(fmt) "ftrace-powerpc: " fmt + #include <linux/spinlock.h> #include <linux/hardirq.h> #include <linux/uaccess.h> @@ -74,6 +76,7 @@ ftrace_modify_code(unsigned long ip, unsigned int old, unsigned int new) */ static int test_24bit_addr(unsigned long ip, unsigned long addr) { + addr = ppc_function_entry((void *)addr); /* use the create_branch to verify that this offset can be branched */ return create_branch((unsigned int *)ip, addr, 0); @@ -104,11 +107,9 @@ __ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr) { unsigned int op; - unsigned int jmp[5]; - unsigned long ptr; + unsigned long entry, ptr; unsigned long ip = rec->ip; - unsigned long tramp; - int offset; + void *tramp; /* read where this goes */ if (probe_kernel_read(&op, (void *)ip, sizeof(int))) @@ -116,101 +117,46 @@ __ftrace_make_nop(struct module *mod, /* Make sure that that this is still a 24bit jump */ if (!is_bl_op(op)) { - printk(KERN_ERR "Not expected bl: opcode is %x\n", op); + pr_err("Not expected bl: opcode is %x\n", op); return -EINVAL; } /* lets find where the pointer goes */ - tramp = find_bl_target(ip, op); - - /* - * On PPC64 the trampoline looks like: - * 0x3d, 0x82, 0x00, 0x00, addis r12,r2, <high> - * 0x39, 0x8c, 0x00, 0x00, addi r12,r12, <low> - * Where the bytes 2,3,6 and 7 make up the 32bit offset - * to the TOC that holds the pointer. - * to jump to. - * 0xf8, 0x41, 0x00, 0x28, std r2,40(r1) - * 0xe9, 0x6c, 0x00, 0x20, ld r11,32(r12) - * The actually address is 32 bytes from the offset - * into the TOC. - * 0xe8, 0x4c, 0x00, 0x28, ld r2,40(r12) - */ - - pr_devel("ip:%lx jumps to %lx r2: %lx", ip, tramp, mod->arch.toc); - - /* Find where the trampoline jumps to */ - if (probe_kernel_read(jmp, (void *)tramp, sizeof(jmp))) { - printk(KERN_ERR "Failed to read %lx\n", tramp); - return -EFAULT; - } + tramp = (void *)find_bl_target(ip, op); - pr_devel(" %08x %08x", jmp[0], jmp[1]); + pr_devel("ip:%lx jumps to %p", ip, tramp); - /* verify that this is what we expect it to be */ - if (((jmp[0] & 0xffff0000) != 0x3d820000) || - ((jmp[1] & 0xffff0000) != 0x398c0000) || - (jmp[2] != 0xf8410028) || - (jmp[3] != 0xe96c0020) || - (jmp[4] != 0xe84c0028)) { - printk(KERN_ERR "Not a trampoline\n"); + if (!is_module_trampoline(tramp)) { + pr_err("Not a trampoline\n"); return -EINVAL; } - /* The bottom half is signed extended */ - offset = ((unsigned)((unsigned short)jmp[0]) << 16) + - (int)((short)jmp[1]); - - pr_devel(" %x ", offset); - - /* get the address this jumps too */ - tramp = mod->arch.toc + offset + 32; - pr_devel("toc: %lx", tramp); - - if (probe_kernel_read(jmp, (void *)tramp, 8)) { - printk(KERN_ERR "Failed to read %lx\n", tramp); + if (module_trampoline_target(mod, tramp, &ptr)) { + pr_err("Failed to get trampoline target\n"); return -EFAULT; } - pr_devel(" %08x %08x\n", jmp[0], jmp[1]); - -#ifdef __LITTLE_ENDIAN__ - ptr = ((unsigned long)jmp[1] << 32) + jmp[0]; -#else - ptr = ((unsigned long)jmp[0] << 32) + jmp[1]; -#endif + pr_devel("trampoline target %lx", ptr); + entry = ppc_global_function_entry((void *)addr); /* This should match what was called */ - if (ptr != ppc_function_entry((void *)addr)) { - printk(KERN_ERR "addr does not match %lx\n", ptr); + if (ptr != entry) { + pr_err("addr %lx does not match expected %lx\n", ptr, entry); return -EINVAL; } /* - * We want to nop the line, but the next line is - * 0xe8, 0x41, 0x00, 0x28 ld r2,40(r1) - * This needs to be turned to a nop too. - */ - if (probe_kernel_read(&op, (void *)(ip+4), MCOUNT_INSN_SIZE)) - return -EFAULT; - - if (op != 0xe8410028) { - printk(KERN_ERR "Next line is not ld! (%08x)\n", op); - return -EINVAL; - } - - /* - * Milton Miller pointed out that we can not blindly do nops. - * If a task was preempted when calling a trace function, - * the nops will remove the way to restore the TOC in r2 - * and the r2 TOC will get corrupted. - */ - - /* - * Replace: - * bl <tramp> <==== will be replaced with "b 1f" - * ld r2,40(r1) - * 1: + * Our original call site looks like: + * + * bl <tramp> + * ld r2,XX(r1) + * + * Milton Miller pointed out that we can not simply nop the branch. + * If a task was preempted when calling a trace function, the nops + * will remove the way to restore the TOC in r2 and the r2 TOC will + * get corrupted. + * + * Use a b +8 to jump over the load. */ op = 0x48000008; /* b +8 */ @@ -235,7 +181,7 @@ __ftrace_make_nop(struct module *mod, /* Make sure that that this is still a 24bit jump */ if (!is_bl_op(op)) { - printk(KERN_ERR "Not expected bl: opcode is %x\n", op); + pr_err("Not expected bl: opcode is %x\n", op); return -EINVAL; } @@ -254,7 +200,7 @@ __ftrace_make_nop(struct module *mod, /* Find where the trampoline jumps to */ if (probe_kernel_read(jmp, (void *)tramp, sizeof(jmp))) { - printk(KERN_ERR "Failed to read %lx\n", tramp); + pr_err("Failed to read %lx\n", tramp); return -EFAULT; } @@ -265,7 +211,7 @@ __ftrace_make_nop(struct module *mod, ((jmp[1] & 0xffff0000) != 0x398c0000) || (jmp[2] != 0x7d8903a6) || (jmp[3] != 0x4e800420)) { - printk(KERN_ERR "Not a trampoline\n"); + pr_err("Not a trampoline\n"); return -EINVAL; } @@ -277,8 +223,7 @@ __ftrace_make_nop(struct module *mod, pr_devel(" %lx ", tramp); if (tramp != addr) { - printk(KERN_ERR - "Trampoline location %08lx does not match addr\n", + pr_err("Trampoline location %08lx does not match addr\n", tramp); return -EINVAL; } @@ -319,15 +264,13 @@ int ftrace_make_nop(struct module *mod, */ if (!rec->arch.mod) { if (!mod) { - printk(KERN_ERR "No module loaded addr=%lx\n", - addr); + pr_err("No module loaded addr=%lx\n", addr); return -EFAULT; } rec->arch.mod = mod; } else if (mod) { if (mod != rec->arch.mod) { - printk(KERN_ERR - "Record mod %p not equal to passed in mod %p\n", + pr_err("Record mod %p not equal to passed in mod %p\n", rec->arch.mod, mod); return -EINVAL; } @@ -348,45 +291,42 @@ static int __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) { unsigned int op[2]; - unsigned long ip = rec->ip; + void *ip = (void *)rec->ip; /* read where this goes */ - if (probe_kernel_read(op, (void *)ip, MCOUNT_INSN_SIZE * 2)) + if (probe_kernel_read(op, ip, sizeof(op))) return -EFAULT; /* - * It should be pointing to two nops or - * b +8; ld r2,40(r1) + * We expect to see: + * + * b +8 + * ld r2,XX(r1) + * + * 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] != 0xe8410028)) && - ((op[0] != PPC_INST_NOP) || (op[1] != PPC_INST_NOP))) { - printk(KERN_ERR "Expected NOPs but have %x %x\n", op[0], op[1]); + if ((op[0] != 0x48000008) || ((op[1] & 0xffff0000) != 0xe8410000)) { + pr_err("Unexpected call sequence: %x %x\n", op[0], op[1]); return -EINVAL; } /* If we never set up a trampoline to ftrace_caller, then bail */ if (!rec->arch.mod->arch.tramp) { - printk(KERN_ERR "No ftrace trampoline\n"); + pr_err("No ftrace trampoline\n"); return -EINVAL; } - /* create the branch to the trampoline */ - op[0] = create_branch((unsigned int *)ip, - rec->arch.mod->arch.tramp, BRANCH_SET_LINK); - if (!op[0]) { - printk(KERN_ERR "REL24 out of range!\n"); + /* Ensure branch is within 24 bits */ + if (!create_branch(ip, rec->arch.mod->arch.tramp, BRANCH_SET_LINK)) { + pr_err("Branch out of range\n"); return -EINVAL; } - /* ld r2,40(r1) */ - op[1] = 0xe8410028; - - pr_devel("write to %lx\n", rec->ip); - - if (probe_kernel_write((void *)ip, op, MCOUNT_INSN_SIZE * 2)) - return -EPERM; - - flush_icache_range(ip, ip + 8); + if (patch_branch(ip, rec->arch.mod->arch.tramp, BRANCH_SET_LINK)) { + pr_err("REL24 out of range!\n"); + return -EINVAL; + } return 0; } @@ -403,13 +343,13 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) /* It should be pointing to a nop */ if (op != PPC_INST_NOP) { - printk(KERN_ERR "Expected NOP but have %x\n", op); + pr_err("Expected NOP but have %x\n", op); return -EINVAL; } /* If we never set up a trampoline to ftrace_caller, then bail */ if (!rec->arch.mod->arch.tramp) { - printk(KERN_ERR "No ftrace trampoline\n"); + pr_err("No ftrace trampoline\n"); return -EINVAL; } @@ -417,7 +357,7 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) op = create_branch((unsigned int *)ip, rec->arch.mod->arch.tramp, BRANCH_SET_LINK); if (!op) { - printk(KERN_ERR "REL24 out of range!\n"); + pr_err("REL24 out of range!\n"); return -EINVAL; } @@ -455,7 +395,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) * already have a module defined. */ if (!rec->arch.mod) { - printk(KERN_ERR "No module loaded\n"); + pr_err("No module loaded\n"); return -EINVAL; } @@ -531,13 +471,8 @@ void arch_ftrace_update_code(int command) ftrace_disable_ftrace_graph_caller(); } -int __init ftrace_dyn_arch_init(void *data) +int __init ftrace_dyn_arch_init(void) { - /* caller expects data to be zero */ - unsigned long *p = data; - - *p = 0; - return 0; } #endif /* CONFIG_DYNAMIC_FTRACE */ diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S index 67ee0d6c107..7d7d8635227 100644 --- a/arch/powerpc/kernel/head_40x.S +++ b/arch/powerpc/kernel/head_40x.S @@ -930,25 +930,6 @@ initial_mmu: tlbwe r4,r0,TLB_DATA /* Load the data portion of the entry */ tlbwe r3,r0,TLB_TAG /* Load the tag portion of the entry */ -#if defined(CONFIG_SERIAL_TEXT_DEBUG) && defined(SERIAL_DEBUG_IO_BASE) - - /* Load a TLB entry for the UART, so that ppc4xx_progress() can use - * the UARTs nice and early. We use a 4k real==virtual mapping. */ - - lis r3,SERIAL_DEBUG_IO_BASE@h - ori r3,r3,SERIAL_DEBUG_IO_BASE@l - mr r4,r3 - clrrwi r4,r4,12 - ori r4,r4,(TLB_WR|TLB_I|TLB_M|TLB_G) - - clrrwi r3,r3,12 - ori r3,r3,(TLB_VALID | TLB_PAGESZ(PAGESZ_4K)) - - li r0,0 /* TLB slot 0 */ - tlbwe r4,r0,TLB_DATA - tlbwe r3,r0,TLB_TAG -#endif /* CONFIG_SERIAL_DEBUG_TEXT && SERIAL_DEBUG_IO_BASE */ - isync /* Establish the exception vector base diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index b7363bd4245..a95145d7f61 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -70,16 +70,15 @@ _GLOBAL(__start) /* NOP this out unconditionally */ BEGIN_FTR_SECTION FIXUP_ENDIAN - b .__start_initialization_multiplatform + b __start_initialization_multiplatform END_FTR_SECTION(0, 1) /* Catch branch to 0 in real mode */ trap - /* Secondary processors spin on this value until it becomes nonzero. - * When it does it contains the real address of the descriptor - * of the function that the cpu should jump to to continue - * initialization. + /* Secondary processors spin on this value until it becomes non-zero. + * When non-zero, it contains the real address of the function the cpu + * should jump to. */ .balign 8 .globl __secondary_hold_spinloop @@ -140,16 +139,15 @@ __secondary_hold: tovirt(r26,r26) #endif /* All secondary cpus wait here until told to start. */ -100: ld r4,__secondary_hold_spinloop-_stext(r26) - cmpdi 0,r4,0 +100: ld r12,__secondary_hold_spinloop-_stext(r26) + cmpdi 0,r12,0 beq 100b #if defined(CONFIG_SMP) || defined(CONFIG_KEXEC) #ifdef CONFIG_PPC_BOOK3E - tovirt(r4,r4) + tovirt(r12,r12) #endif - ld r4,0(r4) /* deref function descriptor */ - mtctr r4 + mtctr r12 mr r3,r24 /* * it may be the case that other platforms have r4 right to @@ -186,16 +184,16 @@ _GLOBAL(generic_secondary_thread_init) mr r24,r3 /* turn on 64-bit mode */ - bl .enable_64b_mode + bl enable_64b_mode /* get a valid TOC pointer, wherever we're mapped at */ - bl .relative_toc + bl relative_toc tovirt(r2,r2) #ifdef CONFIG_PPC_BOOK3E /* Book3E initialization */ mr r3,r24 - bl .book3e_secondary_thread_init + bl book3e_secondary_thread_init #endif b generic_secondary_common_init @@ -214,17 +212,17 @@ _GLOBAL(generic_secondary_smp_init) mr r25,r4 /* turn on 64-bit mode */ - bl .enable_64b_mode + bl enable_64b_mode /* get a valid TOC pointer, wherever we're mapped at */ - bl .relative_toc + bl relative_toc tovirt(r2,r2) #ifdef CONFIG_PPC_BOOK3E /* Book3E initialization */ mr r3,r24 mr r4,r25 - bl .book3e_secondary_core_init + bl book3e_secondary_core_init #endif generic_secondary_common_init: @@ -236,7 +234,7 @@ generic_secondary_common_init: ld r13,0(r13) /* Get base vaddr of paca array */ #ifndef CONFIG_SMP addi r13,r13,PACA_SIZE /* know r13 if used accidentally */ - b .kexec_wait /* wait for next kernel if !SMP */ + b kexec_wait /* wait for next kernel if !SMP */ #else LOAD_REG_ADDR(r7, nr_cpu_ids) /* Load nr_cpu_ids address */ lwz r7,0(r7) /* also the max paca allocated */ @@ -250,7 +248,7 @@ generic_secondary_common_init: blt 1b mr r3,r24 /* not found, copy phys to r3 */ - b .kexec_wait /* next kernel might do better */ + b kexec_wait /* next kernel might do better */ 2: SET_PACA(r13) #ifdef CONFIG_PPC_BOOK3E @@ -264,11 +262,13 @@ generic_secondary_common_init: /* See if we need to call a cpu state restore handler */ LOAD_REG_ADDR(r23, cur_cpu_spec) ld r23,0(r23) - ld r23,CPU_SPEC_RESTORE(r23) - cmpdi 0,r23,0 + ld r12,CPU_SPEC_RESTORE(r23) + cmpdi 0,r12,0 beq 3f - ld r23,0(r23) - mtctr r23 +#if !defined(_CALL_ELF) || _CALL_ELF != 2 + ld r12,0(r12) +#endif + mtctr r12 bctrl 3: LOAD_REG_ADDR(r3, spinning_secondaries) /* Decrement spinning_secondaries */ @@ -299,7 +299,7 @@ generic_secondary_common_init: * Assumes we're mapped EA == RA if the MMU is on. */ #ifdef CONFIG_PPC_BOOK3S -_STATIC(__mmu_off) +__mmu_off: mfmsr r3 andi. r0,r3,MSR_IR|MSR_DR beqlr @@ -324,12 +324,12 @@ _STATIC(__mmu_off) * DT block, r4 is a physical pointer to the kernel itself * */ -_GLOBAL(__start_initialization_multiplatform) +__start_initialization_multiplatform: /* Make sure we are running in 64 bits mode */ - bl .enable_64b_mode + bl enable_64b_mode /* Get TOC pointer (current runtime address) */ - bl .relative_toc + bl relative_toc /* find out where we are now */ bcl 20,31,$+4 @@ -342,7 +342,7 @@ _GLOBAL(__start_initialization_multiplatform) */ cmpldi cr0,r5,0 beq 1f - b .__boot_from_prom /* yes -> prom */ + b __boot_from_prom /* yes -> prom */ 1: /* Save parameters */ mr r31,r3 @@ -354,8 +354,8 @@ _GLOBAL(__start_initialization_multiplatform) #endif #ifdef CONFIG_PPC_BOOK3E - bl .start_initialization_book3e - b .__after_prom_start + bl start_initialization_book3e + b __after_prom_start #else /* Setup some critical 970 SPRs before switching MMU off */ mfspr r0,SPRN_PVR @@ -368,15 +368,15 @@ _GLOBAL(__start_initialization_multiplatform) beq 1f cmpwi r0,0x45 /* 970GX */ bne 2f -1: bl .__cpu_preinit_ppc970 +1: bl __cpu_preinit_ppc970 2: /* Switch off MMU if not already off */ - bl .__mmu_off - b .__after_prom_start + bl __mmu_off + b __after_prom_start #endif /* CONFIG_PPC_BOOK3E */ -_INIT_STATIC(__boot_from_prom) +__boot_from_prom: #ifdef CONFIG_PPC_OF_BOOT_TRAMPOLINE /* Save parameters */ mr r31,r3 @@ -395,7 +395,7 @@ _INIT_STATIC(__boot_from_prom) #ifdef CONFIG_RELOCATABLE /* Relocate code for where we are now */ mr r3,r26 - bl .relocate + bl relocate #endif /* Restore parameters */ @@ -407,14 +407,14 @@ _INIT_STATIC(__boot_from_prom) /* Do all of the interaction with OF client interface */ mr r8,r26 - bl .prom_init + bl prom_init #endif /* #CONFIG_PPC_OF_BOOT_TRAMPOLINE */ /* We never return. We also hit that trap if trying to boot * from OF while CONFIG_PPC_OF_BOOT_TRAMPOLINE isn't selected */ trap -_STATIC(__after_prom_start) +__after_prom_start: #ifdef CONFIG_RELOCATABLE /* process relocations for the final address of the kernel */ lis r25,PAGE_OFFSET@highest /* compute virtual base of kernel */ @@ -424,7 +424,7 @@ _STATIC(__after_prom_start) bne 1f add r25,r25,r26 1: mr r3,r25 - bl .relocate + bl relocate #endif /* @@ -464,12 +464,12 @@ _STATIC(__after_prom_start) lis r5,(copy_to_here - _stext)@ha addi r5,r5,(copy_to_here - _stext)@l /* # bytes of memory to copy */ - bl .copy_and_flush /* copy the first n bytes */ + bl copy_and_flush /* copy the first n bytes */ /* this includes the code being */ /* executed here. */ addis r8,r3,(4f - _stext)@ha /* Jump to the copy of this code */ - addi r8,r8,(4f - _stext)@l /* that we just made */ - mtctr r8 + addi r12,r8,(4f - _stext)@l /* that we just made */ + mtctr r12 bctr .balign 8 @@ -478,9 +478,9 @@ p_end: .llong _end - _stext 4: /* Now copy the rest of the kernel up to _end */ addis r5,r26,(p_end - _stext)@ha ld r5,(p_end - _stext)@l(r5) /* get _end */ -5: bl .copy_and_flush /* copy the rest */ +5: bl copy_and_flush /* copy the rest */ -9: b .start_here_multiplatform +9: b start_here_multiplatform /* * Copy routine used to copy the kernel to start at physical address 0 @@ -544,7 +544,7 @@ __secondary_start_pmac_0: _GLOBAL(pmac_secondary_start) /* turn on 64-bit mode */ - bl .enable_64b_mode + bl enable_64b_mode li r0,0 mfspr r3,SPRN_HID4 @@ -556,11 +556,11 @@ _GLOBAL(pmac_secondary_start) slbia /* get TOC pointer (real address) */ - bl .relative_toc + bl relative_toc tovirt(r2,r2) /* Copy some CPU settings from CPU 0 */ - bl .__restore_cpu_ppc970 + bl __restore_cpu_ppc970 /* pSeries do that early though I don't think we really need it */ mfmsr r3 @@ -619,7 +619,7 @@ __secondary_start: std r14,PACAKSAVE(r13) /* Do early setup for that CPU (stab, slb, hash table pointer) */ - bl .early_setup_secondary + bl early_setup_secondary /* * setup the new stack pointer, but *don't* use this until @@ -639,7 +639,7 @@ __secondary_start: stb r0,PACAIRQHAPPENED(r13) /* enable MMU and jump to start_secondary */ - LOAD_REG_ADDR(r3, .start_secondary_prolog) + LOAD_REG_ADDR(r3, start_secondary_prolog) LOAD_REG_IMMEDIATE(r4, MSR_KERNEL) mtspr SPRN_SRR0,r3 @@ -652,11 +652,11 @@ __secondary_start: * zero the stack back-chain pointer and get the TOC virtual address * before going into C code. */ -_GLOBAL(start_secondary_prolog) +start_secondary_prolog: ld r2,PACATOC(r13) li r3,0 std r3,0(r1) /* Zero the stack frame pointer */ - bl .start_secondary + bl start_secondary b . /* * Reset stack pointer and call start_secondary @@ -667,14 +667,14 @@ _GLOBAL(start_secondary_resume) ld r1,PACAKSAVE(r13) /* Reload kernel stack pointer */ li r3,0 std r3,0(r1) /* Zero the stack frame pointer */ - bl .start_secondary + bl start_secondary b . #endif /* * This subroutine clobbers r11 and r12 */ -_GLOBAL(enable_64b_mode) +enable_64b_mode: mfmsr r11 /* grab the current MSR */ #ifdef CONFIG_PPC_BOOK3E oris r11,r11,0x8000 /* CM bit set, we'll set ICM later */ @@ -715,9 +715,9 @@ p_toc: .llong __toc_start + 0x8000 - 0b /* * This is where the main kernel code starts. */ -_INIT_STATIC(start_here_multiplatform) +start_here_multiplatform: /* set up the TOC */ - bl .relative_toc + bl relative_toc tovirt(r2,r2) /* Clear out the BSS. It may have been done in prom_init, @@ -776,9 +776,9 @@ _INIT_STATIC(start_here_multiplatform) /* Restore parameters passed from prom_init/kexec */ mr r3,r31 - bl .early_setup /* also sets r13 and SPRG_PACA */ + bl early_setup /* also sets r13 and SPRG_PACA */ - LOAD_REG_ADDR(r3, .start_here_common) + LOAD_REG_ADDR(r3, start_here_common) ld r4,PACAKMSR(r13) mtspr SPRN_SRR0,r3 mtspr SPRN_SRR1,r4 @@ -786,7 +786,8 @@ _INIT_STATIC(start_here_multiplatform) b . /* prevent speculative execution */ /* This is where all platforms converge execution */ -_INIT_GLOBAL(start_here_common) + +start_here_common: /* relocation is on at this point */ std r1,PACAKSAVE(r13) @@ -794,7 +795,7 @@ _INIT_GLOBAL(start_here_common) ld r2,PACATOC(r13) /* Do more system initializations in virtual mode */ - bl .setup_system + bl setup_system /* Mark interrupts soft and hard disabled (they might be enabled * in the PACA when doing hotplug) @@ -805,7 +806,7 @@ _INIT_GLOBAL(start_here_common) stb r0,PACAIRQHAPPENED(r13) /* Generic kernel entry */ - bl .start_kernel + bl start_kernel /* Not reached */ BUG_OPCODE diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index b0a1792279b..0bb5918faaa 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -72,7 +72,7 @@ int arch_install_hw_breakpoint(struct perf_event *bp) * If so, DABR will be populated in single_step_dabr_instruction(). */ if (current->thread.last_hit_ubp != bp) - set_breakpoint(info); + __set_breakpoint(info); return 0; } @@ -198,7 +198,7 @@ void thread_change_pc(struct task_struct *tsk, struct pt_regs *regs) info = counter_arch_bp(tsk->thread.last_hit_ubp); regs->msr &= ~MSR_SE; - set_breakpoint(info); + __set_breakpoint(info); tsk->thread.last_hit_ubp = NULL; } @@ -284,7 +284,7 @@ int __kprobes hw_breakpoint_handler(struct die_args *args) if (!(info->type & HW_BRK_TYPE_EXTRANEOUS_IRQ)) perf_bp_event(bp, regs); - set_breakpoint(info); + __set_breakpoint(info); out: rcu_read_unlock(); return rc; @@ -316,7 +316,7 @@ int __kprobes single_step_dabr_instruction(struct die_args *args) if (!(info->type & HW_BRK_TYPE_EXTRANEOUS_IRQ)) perf_bp_event(bp, regs); - set_breakpoint(info); + __set_breakpoint(info); current->thread.last_hit_ubp = NULL; /* diff --git a/arch/powerpc/kernel/idle_book3e.S b/arch/powerpc/kernel/idle_book3e.S index bfb73cc209c..48c21acef91 100644 --- a/arch/powerpc/kernel/idle_book3e.S +++ b/arch/powerpc/kernel/idle_book3e.S @@ -43,7 +43,7 @@ _GLOBAL(\name) */ #ifdef CONFIG_TRACE_IRQFLAGS stdu r1,-128(r1) - bl .trace_hardirqs_on + bl trace_hardirqs_on addi r1,r1,128 #endif li r0,1 diff --git a/arch/powerpc/kernel/idle_power4.S b/arch/powerpc/kernel/idle_power4.S index e3edaa18991..f57a19348bd 100644 --- a/arch/powerpc/kernel/idle_power4.S +++ b/arch/powerpc/kernel/idle_power4.S @@ -46,7 +46,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_CAN_NAP) mflr r0 std r0,16(r1) stdu r1,-128(r1) - bl .trace_hardirqs_on + bl trace_hardirqs_on addi r1,r1,128 ld r0,16(r1) mtlr r0 diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S index 3fdef0f0c67..5cf3d367190 100644 --- a/arch/powerpc/kernel/idle_power7.S +++ b/arch/powerpc/kernel/idle_power7.S @@ -17,20 +17,35 @@ #include <asm/ppc-opcode.h> #include <asm/hw_irq.h> #include <asm/kvm_book3s_asm.h> +#include <asm/opal.h> #undef DEBUG - .text +/* Idle state entry routines */ -_GLOBAL(power7_idle) - /* Now check if user or arch enabled NAP mode */ - LOAD_REG_ADDRBASE(r3,powersave_nap) - lwz r4,ADDROFF(powersave_nap)(r3) - cmpwi 0,r4,0 - beqlr - /* fall through */ +#define IDLE_STATE_ENTER_SEQ(IDLE_INST) \ + /* Magic NAP/SLEEP/WINKLE mode enter sequence */ \ + std r0,0(r1); \ + ptesync; \ + ld r0,0(r1); \ +1: cmp cr0,r0,r0; \ + bne 1b; \ + IDLE_INST; \ + b . -_GLOBAL(power7_nap) + .text + +/* + * Pass requested state in r3: + * 0 - nap + * 1 - sleep + * + * To check IRQ_HAPPENED in r4 + * 0 - don't check + * 1 - check + */ +_GLOBAL(power7_powersave_common) + /* Use r3 to pass state nap/sleep/winkle */ /* NAP is a state loss, we create a regs frame on the * stack, fill it up with the state we care about and * stick a pointer to it in PACAR1. We really only @@ -47,7 +62,7 @@ _GLOBAL(power7_nap) /* Make sure FPU, VSX etc... are flushed as we may lose * state when going to nap mode */ - bl .discard_lazy_cpu_state + bl discard_lazy_cpu_state #endif /* CONFIG_SMP */ /* Hard disable interrupts */ @@ -60,6 +75,8 @@ _GLOBAL(power7_nap) lbz r0,PACAIRQHAPPENED(r13) cmpwi cr0,r0,0 beq 1f + cmpwi cr0,r4,0 + beq 1f addi r1,r1,INT_FRAME_SIZE ld r0,16(r1) mtlr r0 @@ -79,8 +96,8 @@ _GLOBAL(power7_nap) /* Continue saving state */ SAVE_GPR(2, r1) SAVE_NVGPRS(r1) - mfcr r3 - std r3,_CCR(r1) + mfcr r4 + std r4,_CCR(r1) std r9,_MSR(r1) std r1,PACAR1(r13) @@ -90,15 +107,59 @@ _GLOBAL(power7_enter_nap_mode) li r4,KVM_HWTHREAD_IN_NAP stb r4,HSTATE_HWTHREAD_STATE(r13) #endif + cmpwi cr0,r3,1 + beq 2f + IDLE_STATE_ENTER_SEQ(PPC_NAP) + /* No return */ +2: IDLE_STATE_ENTER_SEQ(PPC_SLEEP) + /* No return */ - /* Magic NAP mode enter sequence */ - std r0,0(r1) - ptesync - ld r0,0(r1) -1: cmp cr0,r0,r0 - bne 1b - PPC_NAP - b . +_GLOBAL(power7_idle) + /* Now check if user or arch enabled NAP mode */ + LOAD_REG_ADDRBASE(r3,powersave_nap) + lwz r4,ADDROFF(powersave_nap)(r3) + cmpwi 0,r4,0 + beqlr + li r3, 1 + /* fall through */ + +_GLOBAL(power7_nap) + mr r4,r3 + li r3,0 + b power7_powersave_common + /* No return */ + +_GLOBAL(power7_sleep) + li r3,1 + li r4,1 + b power7_powersave_common + /* No return */ + +_GLOBAL(power7_wakeup_tb_loss) + ld r2,PACATOC(r13); + ld r1,PACAR1(r13) + + /* Time base re-sync */ + li r0,OPAL_RESYNC_TIMEBASE + LOAD_REG_ADDR(r11,opal); + ld r12,8(r11); + ld r2,0(r11); + mtctr r12 + bctrl + + /* TODO: Check r3 for failure */ + + REST_NVGPRS(r1) + REST_GPR(2, r1) + ld r3,_CCR(r1) + ld r4,_MSR(r1) + ld r5,_NIP(r1) + addi r1,r1,INT_FRAME_SIZE + mtcr r3 + mfspr r3,SPRN_SRR1 /* Return SRR1 */ + mtspr SPRN_SRR1,r4 + mtspr SPRN_SRR0,r5 + rfid _GLOBAL(power7_wakeup_loss) ld r1,PACAR1(r13) @@ -116,7 +177,7 @@ _GLOBAL(power7_wakeup_loss) _GLOBAL(power7_wakeup_noloss) lbz r0,PACA_NAPSTATELOST(r13) cmpwi r0,0 - bne .power7_wakeup_loss + bne power7_wakeup_loss ld r1,PACAR1(r13) ld r4,_MSR(r1) ld r5,_NIP(r1) diff --git a/arch/powerpc/kernel/iomap.c b/arch/powerpc/kernel/iomap.c index b82227e7e21..12e48d56f77 100644 --- a/arch/powerpc/kernel/iomap.c +++ b/arch/powerpc/kernel/iomap.c @@ -23,7 +23,7 @@ unsigned int ioread16(void __iomem *addr) } unsigned int ioread16be(void __iomem *addr) { - return in_be16(addr); + return readw_be(addr); } unsigned int ioread32(void __iomem *addr) { @@ -31,7 +31,7 @@ unsigned int ioread32(void __iomem *addr) } unsigned int ioread32be(void __iomem *addr) { - return in_be32(addr); + return readl_be(addr); } EXPORT_SYMBOL(ioread8); EXPORT_SYMBOL(ioread16); @@ -49,7 +49,7 @@ void iowrite16(u16 val, void __iomem *addr) } void iowrite16be(u16 val, void __iomem *addr) { - out_be16(addr, val); + writew_be(val, addr); } void iowrite32(u32 val, void __iomem *addr) { @@ -57,7 +57,7 @@ void iowrite32(u32 val, void __iomem *addr) } void iowrite32be(u32 val, void __iomem *addr) { - out_be32(addr, val); + writel_be(val, addr); } EXPORT_SYMBOL(iowrite8); EXPORT_SYMBOL(iowrite16); @@ -75,15 +75,15 @@ EXPORT_SYMBOL(iowrite32be); */ void ioread8_rep(void __iomem *addr, void *dst, unsigned long count) { - _insb((u8 __iomem *) addr, dst, count); + readsb(addr, dst, count); } void ioread16_rep(void __iomem *addr, void *dst, unsigned long count) { - _insw_ns((u16 __iomem *) addr, dst, count); + readsw(addr, dst, count); } void ioread32_rep(void __iomem *addr, void *dst, unsigned long count) { - _insl_ns((u32 __iomem *) addr, dst, count); + readsl(addr, dst, count); } EXPORT_SYMBOL(ioread8_rep); EXPORT_SYMBOL(ioread16_rep); @@ -91,15 +91,15 @@ EXPORT_SYMBOL(ioread32_rep); void iowrite8_rep(void __iomem *addr, const void *src, unsigned long count) { - _outsb((u8 __iomem *) addr, src, count); + writesb(addr, src, count); } void iowrite16_rep(void __iomem *addr, const void *src, unsigned long count) { - _outsw_ns((u16 __iomem *) addr, src, count); + writesw(addr, src, count); } void iowrite32_rep(void __iomem *addr, const void *src, unsigned long count) { - _outsl_ns((u32 __iomem *) addr, src, count); + writesl(addr, src, count); } EXPORT_SYMBOL(iowrite8_rep); EXPORT_SYMBOL(iowrite16_rep); diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index d773dd440a4..88e3ec6e1d9 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -1088,6 +1088,14 @@ int iommu_take_ownership(struct iommu_table *tbl) memset(tbl->it_map, 0xff, sz); iommu_clear_tces_and_put_pages(tbl, tbl->it_offset, tbl->it_size); + /* + * Disable iommu bypass, otherwise the user can DMA to all of + * our physical memory via the bypass window instead of just + * the pages that has been explicitly mapped into the iommu + */ + if (tbl->set_bypass) + tbl->set_bypass(tbl, false); + return 0; } EXPORT_SYMBOL_GPL(iommu_take_ownership); @@ -1102,6 +1110,10 @@ void iommu_release_ownership(struct iommu_table *tbl) /* Restore bit#0 set by iommu_init_table() */ if (tbl->it_offset == 0) set_bit(0, tbl->it_map); + + /* The kernel owns the device now, we can restore the iommu bypass */ + if (tbl->set_bypass) + tbl->set_bypass(tbl, true); } EXPORT_SYMBOL_GPL(iommu_release_ownership); diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 9729b23bfb0..248ee7e5beb 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -304,7 +304,7 @@ void notrace restore_interrupts(void) * being re-enabled and generally sanitized the lazy irq state, * and in the latter case it will leave with interrupts hard * disabled and marked as such, so the local_irq_enable() call - * in cpu_idle() will properly re-enable everything. + * in arch_cpu_idle() will properly re-enable everything. */ bool prep_irq_for_idle(void) { @@ -465,7 +465,6 @@ static inline void check_stack_overflow(void) void __do_irq(struct pt_regs *regs) { - struct irq_desc *desc; unsigned int irq; irq_enter(); @@ -487,11 +486,8 @@ void __do_irq(struct pt_regs *regs) /* And finally process it */ if (unlikely(irq == NO_IRQ)) __get_cpu_var(irq_stat).spurious_irqs++; - else { - desc = irq_to_desc(irq); - if (likely(desc)) - desc->handle_irq(irq, desc); - } + else + generic_handle_irq(irq); trace_irq_exit(regs); @@ -559,8 +555,13 @@ void exc_lvl_ctx_init(void) #ifdef CONFIG_PPC64 cpu_nr = i; #else +#ifdef CONFIG_SMP cpu_nr = get_hard_smp_processor_id(i); +#else + cpu_nr = 0; +#endif #endif + memset((void *)critirq_ctx[cpu_nr], 0, THREAD_SIZE); tp = critirq_ctx[cpu_nr]; tp->cpu = cpu_nr; diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index 90fab64d911..2f72af82513 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -32,6 +32,7 @@ #include <linux/module.h> #include <linux/kdebug.h> #include <linux/slab.h> +#include <asm/code-patching.h> #include <asm/cacheflush.h> #include <asm/sstep.h> #include <asm/uaccess.h> @@ -491,12 +492,10 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self, return ret; } -#ifdef CONFIG_PPC64 unsigned long arch_deref_entry_point(void *entry) { - return ((func_descr_t *)entry)->entry; + return ppc_global_function_entry(entry); } -#endif int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) { @@ -508,8 +507,12 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) /* setup return addr to the jprobe handler routine */ regs->nip = arch_deref_entry_point(jp->entry); #ifdef CONFIG_PPC64 +#if defined(_CALL_ELF) && _CALL_ELF == 2 + regs->gpr[12] = (unsigned long)jp->entry; +#else regs->gpr[2] = (unsigned long)(((func_descr_t *)jp->entry)->toc); #endif +#endif return 1; } diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c index 6a0175297b0..33aa4ddf597 100644 --- a/arch/powerpc/kernel/kvm.c +++ b/arch/powerpc/kernel/kvm.c @@ -74,7 +74,7 @@ #define KVM_INST_MTSRIN 0x7c0001e4 static bool kvm_patching_worked = true; -static char kvm_tmp[1024 * 1024]; +char kvm_tmp[1024 * 1024]; static int kvm_tmp_index; static inline void kvm_patch_ins(u32 *inst, u32 new_inst) @@ -417,7 +417,7 @@ static void kvm_map_magic_page(void *data) ulong out[8]; in[0] = KVM_MAGIC_PAGE; - in[1] = KVM_MAGIC_PAGE; + in[1] = KVM_MAGIC_PAGE | MAGIC_PAGE_FLAG_NOT_MAPPED_NX; epapr_hypercall(in, out, KVM_HCALL_TOKEN(KVM_HC_PPC_MAP_MAGIC_PAGE)); diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c index 40bd7bd4e19..936258881c9 100644 --- a/arch/powerpc/kernel/legacy_serial.c +++ b/arch/powerpc/kernel/legacy_serial.c @@ -48,6 +48,9 @@ static struct of_device_id legacy_serial_parents[] __initdata = { static unsigned int legacy_serial_count; static int legacy_serial_console = -1; +static const upf_t legacy_port_flags = UPF_BOOT_AUTOCONF | UPF_SKIP_TEST | + UPF_SHARE_IRQ | UPF_FIXED_PORT; + static unsigned int tsi_serial_in(struct uart_port *p, int offset) { unsigned int tmp; @@ -71,8 +74,9 @@ static int __init add_legacy_port(struct device_node *np, int want_index, phys_addr_t taddr, unsigned long irq, upf_t flags, int irq_check_parent) { - const __be32 *clk, *spd; + const __be32 *clk, *spd, *rs; u32 clock = BASE_BAUD * 16; + u32 shift = 0; int index; /* get clock freq. if present */ @@ -83,6 +87,11 @@ static int __init add_legacy_port(struct device_node *np, int want_index, /* get default speed if present */ spd = of_get_property(np, "current-speed", NULL); + /* get register shift if present */ + rs = of_get_property(np, "reg-shift", NULL); + if (rs && *rs) + shift = be32_to_cpup(rs); + /* If we have a location index, then try to use it */ if (want_index >= 0 && want_index < MAX_LEGACY_SERIAL_PORTS) index = want_index; @@ -126,6 +135,7 @@ static int __init add_legacy_port(struct device_node *np, int want_index, legacy_serial_ports[index].uartclk = clock; legacy_serial_ports[index].irq = irq; legacy_serial_ports[index].flags = flags; + legacy_serial_ports[index].regshift = shift; legacy_serial_infos[index].taddr = taddr; legacy_serial_infos[index].np = of_node_get(np); legacy_serial_infos[index].clock = clock; @@ -153,8 +163,6 @@ static int __init add_legacy_soc_port(struct device_node *np, { u64 addr; const __be32 *addrp; - upf_t flags = UPF_BOOT_AUTOCONF | UPF_SKIP_TEST | UPF_SHARE_IRQ - | UPF_FIXED_PORT; struct device_node *tsi = of_get_parent(np); /* We only support ports that have a clock frequency properly @@ -163,9 +171,8 @@ static int __init add_legacy_soc_port(struct device_node *np, if (of_get_property(np, "clock-frequency", NULL) == NULL) return -1; - /* if reg-shift or offset, don't try to use it */ - if ((of_get_property(np, "reg-shift", NULL) != NULL) || - (of_get_property(np, "reg-offset", NULL) != NULL)) + /* if reg-offset don't try to use it */ + if ((of_get_property(np, "reg-offset", NULL) != NULL)) return -1; /* if rtas uses this device, don't try to use it as well */ @@ -185,9 +192,11 @@ static int __init add_legacy_soc_port(struct device_node *np, * IO port value. It will be fixed up later along with the irq */ if (tsi && !strcmp(tsi->type, "tsi-bridge")) - return add_legacy_port(np, -1, UPIO_TSI, addr, addr, NO_IRQ, flags, 0); + return add_legacy_port(np, -1, UPIO_TSI, addr, addr, + NO_IRQ, legacy_port_flags, 0); else - return add_legacy_port(np, -1, UPIO_MEM, addr, addr, NO_IRQ, flags, 0); + return add_legacy_port(np, -1, UPIO_MEM, addr, addr, + NO_IRQ, legacy_port_flags, 0); } static int __init add_legacy_isa_port(struct device_node *np, @@ -233,7 +242,7 @@ static int __init add_legacy_isa_port(struct device_node *np, /* Add port, irq will be dealt with later */ return add_legacy_port(np, index, UPIO_PORT, be32_to_cpu(reg[1]), - taddr, NO_IRQ, UPF_BOOT_AUTOCONF, 0); + taddr, NO_IRQ, legacy_port_flags, 0); } @@ -306,7 +315,7 @@ static int __init add_legacy_pci_port(struct device_node *np, * IO port value. It will be fixed up later along with the irq */ return add_legacy_port(np, index, iotype, base, addr, NO_IRQ, - UPF_BOOT_AUTOCONF, np != pci_dev); + legacy_port_flags, np != pci_dev); } #endif @@ -315,17 +324,20 @@ static void __init setup_legacy_serial_console(int console) struct legacy_serial_info *info = &legacy_serial_infos[console]; struct plat_serial8250_port *port = &legacy_serial_ports[console]; void __iomem *addr; + unsigned int stride; + + stride = 1 << port->regshift; /* Check if a translated MMIO address has been found */ if (info->taddr) { addr = ioremap(info->taddr, 0x1000); if (addr == NULL) return; - udbg_uart_init_mmio(addr, 1); + udbg_uart_init_mmio(addr, stride); } else { /* Check if it's PIO and we support untranslated PIO */ if (port->iotype == UPIO_PORT && isa_io_special) - udbg_uart_init_pio(port->iobase, 1); + udbg_uart_init_pio(port->iobase, stride); else return; } diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c index 75d4f7340da..015ae55c186 100644 --- a/arch/powerpc/kernel/machine_kexec.c +++ b/arch/powerpc/kernel/machine_kexec.c @@ -196,7 +196,9 @@ int overlaps_crashkernel(unsigned long start, unsigned long size) /* Values we need to export to the second kernel via the device tree. */ static phys_addr_t kernel_end; +static phys_addr_t crashk_base; static phys_addr_t crashk_size; +static unsigned long long mem_limit; static struct property kernel_end_prop = { .name = "linux,kernel-end", @@ -207,7 +209,7 @@ static struct property kernel_end_prop = { static struct property crashk_base_prop = { .name = "linux,crashkernel-base", .length = sizeof(phys_addr_t), - .value = &crashk_res.start, + .value = &crashk_base }; static struct property crashk_size_prop = { @@ -219,9 +221,11 @@ static struct property crashk_size_prop = { static struct property memory_limit_prop = { .name = "linux,memory-limit", .length = sizeof(unsigned long long), - .value = &memory_limit, + .value = &mem_limit, }; +#define cpu_to_be_ulong __PASTE(cpu_to_be, BITS_PER_LONG) + static void __init export_crashk_values(struct device_node *node) { struct property *prop; @@ -237,8 +241,9 @@ static void __init export_crashk_values(struct device_node *node) of_remove_property(node, prop); if (crashk_res.start != 0) { + crashk_base = cpu_to_be_ulong(crashk_res.start), of_add_property(node, &crashk_base_prop); - crashk_size = resource_size(&crashk_res); + crashk_size = cpu_to_be_ulong(resource_size(&crashk_res)); of_add_property(node, &crashk_size_prop); } @@ -246,6 +251,7 @@ static void __init export_crashk_values(struct device_node *node) * memory_limit is required by the kexec-tools to limit the * crash regions to the actual memory used. */ + mem_limit = cpu_to_be_ulong(memory_limit); of_update_property(node, &memory_limit_prop); } @@ -264,7 +270,7 @@ static int __init kexec_setup(void) of_remove_property(node, prop); /* information needed by userspace when using default_machine_kexec */ - kernel_end = __pa(_end); + kernel_end = cpu_to_be_ulong(__pa(_end)); of_add_property(node, &kernel_end_prop); export_crashk_values(node); diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c index be4e6d648f6..879b3aacac3 100644 --- a/arch/powerpc/kernel/machine_kexec_64.c +++ b/arch/powerpc/kernel/machine_kexec_64.c @@ -237,7 +237,7 @@ static void wake_offline_cpus(void) if (!cpu_online(cpu)) { printk(KERN_INFO "kexec: Waking offline cpu %d.\n", cpu); - cpu_up(cpu); + WARN_ON(cpu_up(cpu)); } } } @@ -369,6 +369,7 @@ void default_machine_kexec(struct kimage *image) /* Values we need to export to the second kernel via the device tree. */ static unsigned long htab_base; +static unsigned long htab_size; static struct property htab_base_prop = { .name = "linux,htab-base", @@ -379,7 +380,7 @@ static struct property htab_base_prop = { static struct property htab_size_prop = { .name = "linux,htab-size", .length = sizeof(unsigned long), - .value = &htab_size_bytes, + .value = &htab_size, }; static int __init export_htab_values(void) @@ -403,8 +404,9 @@ static int __init export_htab_values(void) if (prop) of_remove_property(node, prop); - htab_base = __pa(htab_address); + htab_base = cpu_to_be64(__pa(htab_address)); of_add_property(node, &htab_base_prop); + htab_size = cpu_to_be64(htab_size_bytes); of_add_property(node, &htab_size_prop); of_node_put(node); diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c index cadef7e64e4..a7fd4cb78b7 100644 --- a/arch/powerpc/kernel/mce.c +++ b/arch/powerpc/kernel/mce.c @@ -70,7 +70,7 @@ static void mce_set_error_info(struct machine_check_event *mce, */ void save_mce_event(struct pt_regs *regs, long handled, struct mce_error_info *mce_err, - uint64_t addr) + uint64_t nip, uint64_t addr) { uint64_t srr1; int index = __get_cpu_var(mce_nest_count)++; @@ -86,7 +86,7 @@ void save_mce_event(struct pt_regs *regs, long handled, /* Populate generic machine check info */ mce->version = MCE_V1; - mce->srr0 = regs->nip; + mce->srr0 = nip; mce->srr1 = regs->msr; mce->gpr3 = regs->gpr[3]; mce->in_use = 1; diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c index 27c93f41166..aa9aff3d6ad 100644 --- a/arch/powerpc/kernel/mce_power.c +++ b/arch/powerpc/kernel/mce_power.c @@ -26,6 +26,7 @@ #include <linux/ptrace.h> #include <asm/mmu.h> #include <asm/mce.h> +#include <asm/machdep.h> /* flush SLBs and reload */ static void flush_and_reload_slb(void) @@ -197,13 +198,32 @@ static void mce_get_derror_p7(struct mce_error_info *mce_err, uint64_t dsisr) } } +static long mce_handle_ue_error(struct pt_regs *regs) +{ + long handled = 0; + + /* + * On specific SCOM read via MMIO we may get a machine check + * exception with SRR0 pointing inside opal. If that is the + * case OPAL may have recovery address to re-read SCOM data in + * different way and hence we can recover from this MC. + */ + + if (ppc_md.mce_check_early_recovery) { + if (ppc_md.mce_check_early_recovery(regs)) + handled = 1; + } + return handled; +} + long __machine_check_early_realmode_p7(struct pt_regs *regs) { - uint64_t srr1, addr; + uint64_t srr1, nip, addr; long handled = 1; struct mce_error_info mce_error_info = { 0 }; srr1 = regs->msr; + nip = regs->nip; /* * Handle memory errors depending whether this was a load/store or @@ -221,7 +241,11 @@ long __machine_check_early_realmode_p7(struct pt_regs *regs) addr = regs->nip; } - save_mce_event(regs, handled, &mce_error_info, addr); + /* Handle UE error. */ + if (mce_error_info.error_type == MCE_ERROR_TYPE_UE) + handled = mce_handle_ue_error(regs); + + save_mce_event(regs, handled, &mce_error_info, nip, addr); return handled; } @@ -263,11 +287,12 @@ static long mce_handle_derror_p8(uint64_t dsisr) long __machine_check_early_realmode_p8(struct pt_regs *regs) { - uint64_t srr1, addr; + uint64_t srr1, nip, addr; long handled = 1; struct mce_error_info mce_error_info = { 0 }; srr1 = regs->msr; + nip = regs->nip; if (P7_SRR1_MC_LOADSTORE(srr1)) { handled = mce_handle_derror_p8(regs->dsisr); @@ -279,6 +304,10 @@ long __machine_check_early_realmode_p8(struct pt_regs *regs) addr = regs->nip; } - save_mce_event(regs, handled, &mce_error_info, addr); + /* Handle UE error. */ + if (mce_error_info.error_type == MCE_ERROR_TYPE_UE) + handled = mce_handle_ue_error(regs); + + save_mce_event(regs, handled, &mce_error_info, nip, addr); return handled; } diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index 879f09620f8..7c6bb4b17b4 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -57,11 +57,14 @@ _GLOBAL(call_do_softirq) mtlr r0 blr +/* + * void call_do_irq(struct pt_regs *regs, struct thread_info *irqtp); + */ _GLOBAL(call_do_irq) mflr r0 stw r0,4(r1) lwz r10,THREAD+KSP_LIMIT(r2) - addi r11,r3,THREAD_INFO_GAP + addi r11,r4,THREAD_INFO_GAP stwu r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r4) mr r1,r4 stw r10,8(r1) diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index 3d0249599d5..4e314b90c75 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -34,7 +34,7 @@ _GLOBAL(call_do_softirq) std r0,16(r1) stdu r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r3) mr r1,r3 - bl .__do_softirq + bl __do_softirq ld r1,0(r1) ld r0,16(r1) mtlr r0 @@ -45,7 +45,7 @@ _GLOBAL(call_do_irq) std r0,16(r1) stdu r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r4) mr r1,r4 - bl .__do_irq + bl __do_irq ld r1,0(r1) ld r0,16(r1) mtlr r0 @@ -506,7 +506,7 @@ _GLOBAL(kexec_smp_wait) stb r4,PACAKEXECSTATE(r13) SYNC - b .kexec_wait + b kexec_wait /* * switch to real mode (turn mmu off) @@ -576,7 +576,7 @@ _GLOBAL(kexec_sequence) /* copy dest pages, flush whole dest image */ mr r3,r29 - bl .kexec_copy_flush /* (image) */ + bl kexec_copy_flush /* (image) */ /* turn off mmu */ bl real_mode @@ -586,7 +586,7 @@ _GLOBAL(kexec_sequence) mr r4,r30 /* start, aka phys mem offset */ li r5,0x100 li r6,0 - bl .copy_and_flush /* (dest, src, copy limit, start offset) */ + bl copy_and_flush /* (dest, src, copy limit, start offset) */ 1: /* assume normal blr return */ /* release other cpus to the new kernel secondary start at 0x60 */ @@ -595,8 +595,12 @@ _GLOBAL(kexec_sequence) stw r6,kexec_flag-1b(5) /* clear out hardware hash page table and tlb */ - ld r5,0(r27) /* deref function descriptor */ - mtctr r5 +#if !defined(_CALL_ELF) || _CALL_ELF != 2 + ld r12,0(r27) /* deref function descriptor */ +#else + mr r12,r27 +#endif + mtctr r12 bctrl /* ppc_md.hpte_clear_all(void); */ /* @@ -630,3 +634,31 @@ _GLOBAL(kexec_sequence) li r5,0 blr /* image->start(physid, image->start, 0); */ #endif /* CONFIG_KEXEC */ + +#ifdef CONFIG_MODULES +#if defined(_CALL_ELF) && _CALL_ELF == 2 + +#ifdef CONFIG_MODVERSIONS +.weak __crc_TOC. +.section "___kcrctab+TOC.","a" +.globl __kcrctab_TOC. +__kcrctab_TOC.: + .llong __crc_TOC. +#endif + +/* + * Export a fake .TOC. since both modpost and depmod will complain otherwise. + * Both modpost and depmod strip the leading . so we do the same here. + */ +.section "__ksymtab_strings","a" +__kstrtab_TOC.: + .asciz "TOC." + +.section "___ksymtab+TOC.","a" +/* This symbol name is important: it's used by modpost to find exported syms */ +.globl __ksymtab_TOC. +__ksymtab_TOC.: + .llong 0 /* .value */ + .llong __kstrtab_TOC. +#endif /* ELFv2 */ +#endif /* MODULES */ diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 12664c130d7..d807ee626af 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -22,6 +22,7 @@ #include <linux/vmalloc.h> #include <linux/ftrace.h> #include <linux/bug.h> +#include <linux/uaccess.h> #include <asm/module.h> #include <asm/firmware.h> #include <asm/code-patching.h> @@ -41,46 +42,170 @@ #define DEBUGP(fmt , ...) #endif +#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; + +static func_desc_t func_desc(unsigned long addr) +{ + return addr; +} +static unsigned long func_addr(unsigned long addr) +{ + return addr; +} +static unsigned long stub_func_addr(func_desc_t func) +{ + return func; +} + +/* PowerPC64 specific values for the Elf64_Sym st_other field. */ +#define STO_PPC64_LOCAL_BIT 5 +#define STO_PPC64_LOCAL_MASK (7 << STO_PPC64_LOCAL_BIT) +#define PPC64_LOCAL_ENTRY_OFFSET(other) \ + (((1 << (((other) & STO_PPC64_LOCAL_MASK) >> STO_PPC64_LOCAL_BIT)) >> 2) << 2) + +static unsigned int local_entry_offset(const Elf64_Sym *sym) +{ + /* sym->st_other indicates offset to local entry point + * (otherwise it will assume r12 is the address of the start + * of function and try to derive r2 from it). */ + 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; + +static func_desc_t func_desc(unsigned long addr) +{ + return *(struct ppc64_opd_entry *)addr; +} +static unsigned long func_addr(unsigned long addr) +{ + return func_desc(addr).funcaddr; +} +static unsigned long stub_func_addr(func_desc_t func) +{ + return func.funcaddr; +} +static unsigned int local_entry_offset(const Elf64_Sym *sym) +{ + return 0; +} +#endif + /* 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). */ struct ppc64_stub_entry { - /* 28 byte jump instruction sequence (7 instructions) */ - unsigned char jump[28]; - unsigned char unused[4]; + /* 28 byte jump instruction sequence (7 instructions). We only + * 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; /* Data for the above code */ - struct ppc64_opd_entry opd; + func_desc_t funcdata; }; -/* We use a stub to fix up r2 (TOC ptr) and to jump to the (external) - function which may be more than 24-bits away. We could simply - patch the new r2 value and function pointer into the stub, but it's - significantly shorter to put these values at the end of the stub - code, and patch the stub address (32-bits relative to the TOC ptr, - r2) into the stub. */ -static struct ppc64_stub_entry ppc64_stub = -{ .jump = { -#ifdef __LITTLE_ENDIAN__ - 0x00, 0x00, 0x82, 0x3d, /* addis r12,r2, <high> */ - 0x00, 0x00, 0x8c, 0x39, /* addi r12,r12, <low> */ +/* + * PPC64 uses 24 bit jumps, but we need to jump into other modules or + * the kernel which may be further. So we jump to a stub. + * + * For ELFv1 we need to use this to set up the new r2 value (aka TOC + * pointer). For ELFv2 it's the callee's responsibility to set up the + * new r2, but for both we need to save the old r2. + * + * We could simply patch the new r2 value and function pointer into + * the stub, but it's significantly shorter to put these values at the + * end of the stub code, and patch the stub address (32-bits relative + * to the TOC ptr, r2) into the stub. + */ + +static u32 ppc64_stub_insns[] = { + 0x3d620000, /* addis r11,r2, <high> */ + 0x396b0000, /* addi r11,r11, <low> */ /* Save current r2 value in magic place on the stack. */ - 0x28, 0x00, 0x41, 0xf8, /* std r2,40(r1) */ - 0x20, 0x00, 0x6c, 0xe9, /* ld r11,32(r12) */ - 0x28, 0x00, 0x4c, 0xe8, /* ld r2,40(r12) */ - 0xa6, 0x03, 0x69, 0x7d, /* mtctr r11 */ - 0x20, 0x04, 0x80, 0x4e /* bctr */ -#else - 0x3d, 0x82, 0x00, 0x00, /* addis r12,r2, <high> */ - 0x39, 0x8c, 0x00, 0x00, /* addi r12,r12, <low> */ - /* Save current r2 value in magic place on the stack. */ - 0xf8, 0x41, 0x00, 0x28, /* std r2,40(r1) */ - 0xe9, 0x6c, 0x00, 0x20, /* ld r11,32(r12) */ - 0xe8, 0x4c, 0x00, 0x28, /* ld r2,40(r12) */ - 0x7d, 0x69, 0x03, 0xa6, /* mtctr r11 */ - 0x4e, 0x80, 0x04, 0x20 /* bctr */ + 0xf8410000|R2_STACK_OFFSET, /* std r2,R2_STACK_OFFSET(r1) */ + 0xe98b0020, /* ld r12,32(r11) */ +#if !defined(_CALL_ELF) || _CALL_ELF != 2 + /* Set up new r2 from function descriptor */ + 0xe84b0028, /* ld r2,40(r11) */ +#endif + 0x7d8903a6, /* mtctr r12 */ + 0x4e800420 /* bctr */ +}; + +#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) +{ + unsigned int i; + u32 insns[ARRAY_SIZE(ppc64_stub_insns)]; + + BUILD_BUG_ON(sizeof(ppc64_stub_insns) != sizeof(ppc64_stub_mask)); + + if (probe_kernel_read(insns, p, sizeof(insns))) + 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; + + if (probe_kernel_read(buf, trampoline, sizeof(buf))) + return -EFAULT; + + upper = buf[0] & 0xffff; + lower = buf[1] & 0xffff; + + /* perform the addis/addi, both signed */ + offset = ((short)upper << 16) + (short)lower; + + /* + * 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(target, toc_entry, sizeof(*target))) + return -EFAULT; + + return 0; +} + #endif -} }; /* Count how many different 24-bit relocations (different symbol, different addend) */ @@ -183,17 +308,27 @@ static unsigned long get_stubs_size(const Elf64_Ehdr *hdr, return relocs * sizeof(struct ppc64_stub_entry); } +/* Still needed for ELFv2, for .TOC. */ static void dedotify_versions(struct modversion_info *vers, unsigned long size) { struct modversion_info *end; for (end = (void *)vers + size; vers < end; vers++) - if (vers->name[0] == '.') + if (vers->name[0] == '.') { memmove(vers->name, vers->name+1, strlen(vers->name)); +#ifdef ARCH_RELOCATES_KCRCTAB + /* The TOC symbol has no CRC computed. To avoid CRC + * check failing, we must force it to the expected + * value (see CRC check in module.c). + */ + if (!strcmp(vers->name, "TOC.")) + vers->crc = -(unsigned long)reloc_start; +#endif + } } -/* Undefined symbols which refer to .funcname, hack to funcname */ +/* Undefined symbols which refer to .funcname, hack to funcname (or .TOC.) */ static void dedotify(Elf64_Sym *syms, unsigned int numsyms, char *strtab) { unsigned int i; @@ -207,6 +342,24 @@ static void dedotify(Elf64_Sym *syms, unsigned int numsyms, char *strtab) } } +static Elf64_Sym *find_dot_toc(Elf64_Shdr *sechdrs, + const char *strtab, + unsigned int symindex) +{ + unsigned int i, numsyms; + Elf64_Sym *syms; + + syms = (Elf64_Sym *)sechdrs[symindex].sh_addr; + numsyms = sechdrs[symindex].sh_size / sizeof(Elf64_Sym); + + for (i = 1; i < numsyms; i++) { + if (syms[i].st_shndx == SHN_UNDEF + && strcmp(strtab + syms[i].st_name, "TOC.") == 0) + return &syms[i]; + } + return NULL; +} + int module_frob_arch_sections(Elf64_Ehdr *hdr, Elf64_Shdr *sechdrs, char *secstrings, @@ -271,21 +424,12 @@ static inline unsigned long my_r2(Elf64_Shdr *sechdrs, struct module *me) /* Patch stub to reference function and correct r2 value. */ static inline int create_stub(Elf64_Shdr *sechdrs, struct ppc64_stub_entry *entry, - struct ppc64_opd_entry *opd, + unsigned long addr, struct module *me) { - Elf64_Half *loc1, *loc2; long reladdr; - *entry = ppc64_stub; - -#ifdef __LITTLE_ENDIAN__ - loc1 = (Elf64_Half *)&entry->jump[0]; - loc2 = (Elf64_Half *)&entry->jump[4]; -#else - loc1 = (Elf64_Half *)&entry->jump[2]; - loc2 = (Elf64_Half *)&entry->jump[6]; -#endif + memcpy(entry->jump, ppc64_stub_insns, sizeof(ppc64_stub_insns)); /* Stub uses address relative to r2. */ reladdr = (unsigned long)entry - my_r2(sechdrs, me); @@ -296,35 +440,33 @@ static inline int create_stub(Elf64_Shdr *sechdrs, } DEBUGP("Stub %p get data from reladdr %li\n", entry, reladdr); - *loc1 = PPC_HA(reladdr); - *loc2 = PPC_LO(reladdr); - entry->opd.funcaddr = opd->funcaddr; - entry->opd.r2 = opd->r2; + entry->jump[0] |= PPC_HA(reladdr); + entry->jump[1] |= PPC_LO(reladdr); + entry->funcdata = func_desc(addr); return 1; } -/* Create stub to jump to function described in this OPD: we need the +/* 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, - unsigned long opdaddr, + unsigned long addr, struct module *me) { struct ppc64_stub_entry *stubs; - struct ppc64_opd_entry *opd = (void *)opdaddr; unsigned int i, num_stubs; num_stubs = sechdrs[me->arch.stubs_section].sh_size / sizeof(*stubs); /* Find this stub, or if that fails, the next avail. entry */ stubs = (void *)sechdrs[me->arch.stubs_section].sh_addr; - for (i = 0; stubs[i].opd.funcaddr; i++) { + for (i = 0; stub_func_addr(stubs[i].funcdata); i++) { BUG_ON(i >= num_stubs); - if (stubs[i].opd.funcaddr == opd->funcaddr) + if (stub_func_addr(stubs[i].funcdata) == func_addr(addr)) return (unsigned long)&stubs[i]; } - if (!create_stub(sechdrs, &stubs[i], opd, me)) + if (!create_stub(sechdrs, &stubs[i], addr, me)) return 0; return (unsigned long)&stubs[i]; @@ -339,7 +481,8 @@ static int restore_r2(u32 *instruction, struct module *me) me->name, *instruction); return 0; } - *instruction = 0xe8410028; /* ld r2,40(r1) */ + /* ld r2,R2_STACK_OFFSET(r1) */ + *instruction = 0xe8410000 | R2_STACK_OFFSET; return 1; } @@ -357,6 +500,17 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, DEBUGP("Applying ADD relocate section %u to %u\n", relsec, sechdrs[relsec].sh_info); + + /* First time we're called, we can fix up .TOC. */ + if (!me->arch.toc_fixed) { + sym = find_dot_toc(sechdrs, strtab, symindex); + /* It's theoretically possible that a module doesn't want a + * .TOC. so don't fail it just for that. */ + if (sym) + sym->st_value = my_r2(sechdrs, me); + me->arch.toc_fixed = true; + } + for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rela); i++) { /* This is where to make the change */ location = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr @@ -453,7 +607,8 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, return -ENOENT; if (!restore_r2((u32 *)location + 1, me)) return -ENOEXEC; - } + } else + value += local_entry_offset(sym); /* Convert value to relative */ value -= (unsigned long)location; @@ -474,6 +629,31 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, *location = value - (unsigned long)location; break; + case R_PPC64_TOCSAVE: + /* + * Marker reloc indicates we don't have to save r2. + * That would only save us one instruction, so ignore + * it. + */ + break; + + case R_PPC64_REL16_HA: + /* Subtract location pointer */ + value -= (unsigned long)location; + value = ((value + 0x8000) >> 16); + *((uint16_t *) location) + = (*((uint16_t *) location) & ~0xffff) + | (value & 0xffff); + break; + + case R_PPC64_REL16_LO: + /* Subtract location pointer */ + value -= (unsigned long)location; + *((uint16_t *) location) + = (*((uint16_t *) location) & ~0xffff) + | (value & 0xffff); + break; + default: printk("%s: Unknown ADD relocation: %lu\n", me->name, diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index bf0aada02fe..d6e195e8cd4 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -98,6 +98,9 @@ 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. + * + * If you make the number of persistent SLB entries dynamic, please also + * update PR KVM to flush and restore them accordingly. */ static struct slb_shadow *slb_shadow; @@ -152,7 +155,8 @@ void __init initialise_paca(struct paca_struct *new_paca, int cpu) new_paca->paca_index = cpu; new_paca->kernel_toc = kernel_toc; new_paca->kernelbase = (unsigned long) _stext; - new_paca->kernel_msr = MSR_KERNEL; + /* Only set MSR:IR/DR when MMU is initialized */ + new_paca->kernel_msr = MSR_KERNEL & ~(MSR_IR | MSR_DR); new_paca->hw_cpu_id = 0xffff; new_paca->kexec_state = KEXEC_STATE_NONE; new_paca->__current = &init_task; diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index d9476c1fc95..b49c72fd7f1 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -21,6 +21,7 @@ #include <linux/string.h> #include <linux/init.h> #include <linux/bootmem.h> +#include <linux/delay.h> #include <linux/export.h> #include <linux/of_address.h> #include <linux/of_pci.h> @@ -120,6 +121,25 @@ resource_size_t pcibios_window_alignment(struct pci_bus *bus, return 1; } +void pcibios_reset_secondary_bus(struct pci_dev *dev) +{ + u16 ctrl; + + if (ppc_md.pcibios_reset_secondary_bus) { + ppc_md.pcibios_reset_secondary_bus(dev); + return; + } + + pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &ctrl); + ctrl |= PCI_BRIDGE_CTL_BUS_RESET; + pci_write_config_word(dev, PCI_BRIDGE_CONTROL, ctrl); + msleep(2); + + ctrl &= ~PCI_BRIDGE_CTL_BUS_RESET; + pci_write_config_word(dev, PCI_BRIDGE_CONTROL, ctrl); + ssleep(1); +} + static resource_size_t pcibios_io_size(const struct pci_controller *hose) { #ifdef CONFIG_PPC64 @@ -201,26 +221,6 @@ struct pci_controller* pci_find_hose_for_OF_device(struct device_node* node) return NULL; } -static ssize_t pci_show_devspec(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct pci_dev *pdev; - struct device_node *np; - - pdev = to_pci_dev (dev); - np = pci_device_to_OF_node(pdev); - if (np == NULL || np->full_name == NULL) - return 0; - return sprintf(buf, "%s", np->full_name); -} -static DEVICE_ATTR(devspec, S_IRUGO, pci_show_devspec, NULL); - -/* Add sysfs properties */ -int pcibios_add_platform_entries(struct pci_dev *pdev) -{ - return device_create_file(&pdev->dev, &dev_attr_devspec); -} - /* * Reads the interrupt pin to determine if interrupt is use by card. * If the interrupt is used, then gets the interrupt line from the @@ -666,60 +666,36 @@ void pci_resource_to_user(const struct pci_dev *dev, int bar, void pci_process_bridge_OF_ranges(struct pci_controller *hose, struct device_node *dev, int primary) { - const __be32 *ranges; - int rlen; - int pna = of_n_addr_cells(dev); - int np = pna + 5; int memno = 0; - u32 pci_space; - unsigned long long pci_addr, cpu_addr, pci_next, cpu_next, size; struct resource *res; + struct of_pci_range range; + struct of_pci_range_parser parser; printk(KERN_INFO "PCI host bridge %s %s ranges:\n", dev->full_name, primary ? "(primary)" : ""); - /* Get ranges property */ - ranges = of_get_property(dev, "ranges", &rlen); - if (ranges == NULL) + /* Check for ranges property */ + if (of_pci_range_parser_init(&parser, dev)) return; /* Parse it */ - while ((rlen -= np * 4) >= 0) { - /* Read next ranges element */ - pci_space = of_read_number(ranges, 1); - pci_addr = of_read_number(ranges + 1, 2); - cpu_addr = of_translate_address(dev, ranges + 3); - size = of_read_number(ranges + pna + 3, 2); - ranges += np; - + for_each_of_pci_range(&parser, &range) { /* If we failed translation or got a zero-sized region * (some FW try to feed us with non sensical zero sized regions * such as power3 which look like some kind of attempt at exposing * the VGA memory hole) */ - if (cpu_addr == OF_BAD_ADDR || size == 0) + if (range.cpu_addr == OF_BAD_ADDR || range.size == 0) continue; - /* Now consume following elements while they are contiguous */ - for (; rlen >= np * sizeof(u32); - ranges += np, rlen -= np * 4) { - if (of_read_number(ranges, 1) != pci_space) - break; - pci_next = of_read_number(ranges + 1, 2); - cpu_next = of_translate_address(dev, ranges + 3); - if (pci_next != pci_addr + size || - cpu_next != cpu_addr + size) - break; - size += of_read_number(ranges + pna + 3, 2); - } - /* Act based on address space type */ res = NULL; - switch ((pci_space >> 24) & 0x3) { - case 1: /* PCI IO space */ + switch (range.flags & IORESOURCE_TYPE_BITS) { + case IORESOURCE_IO: printk(KERN_INFO " IO 0x%016llx..0x%016llx -> 0x%016llx\n", - cpu_addr, cpu_addr + size - 1, pci_addr); + range.cpu_addr, range.cpu_addr + range.size - 1, + range.pci_addr); /* We support only one IO range */ if (hose->pci_io_size) { @@ -729,11 +705,12 @@ void pci_process_bridge_OF_ranges(struct pci_controller *hose, } #ifdef CONFIG_PPC32 /* On 32 bits, limit I/O space to 16MB */ - if (size > 0x01000000) - size = 0x01000000; + if (range.size > 0x01000000) + range.size = 0x01000000; /* 32 bits needs to map IOs here */ - hose->io_base_virt = ioremap(cpu_addr, size); + hose->io_base_virt = ioremap(range.cpu_addr, + range.size); /* Expect trouble if pci_addr is not 0 */ if (primary) @@ -743,20 +720,20 @@ void pci_process_bridge_OF_ranges(struct pci_controller *hose, /* pci_io_size and io_base_phys always represent IO * space starting at 0 so we factor in pci_addr */ - hose->pci_io_size = pci_addr + size; - hose->io_base_phys = cpu_addr - pci_addr; + hose->pci_io_size = range.pci_addr + range.size; + hose->io_base_phys = range.cpu_addr - range.pci_addr; /* Build resource */ res = &hose->io_resource; - res->flags = IORESOURCE_IO; - res->start = pci_addr; + range.cpu_addr = range.pci_addr; break; - case 2: /* PCI Memory space */ - case 3: /* PCI 64 bits Memory space */ + case IORESOURCE_MEM: printk(KERN_INFO " MEM 0x%016llx..0x%016llx -> 0x%016llx %s\n", - cpu_addr, cpu_addr + size - 1, pci_addr, - (pci_space & 0x40000000) ? "Prefetch" : ""); + range.cpu_addr, range.cpu_addr + range.size - 1, + range.pci_addr, + (range.pci_space & 0x40000000) ? + "Prefetch" : ""); /* We support only 3 memory ranges */ if (memno >= 3) { @@ -765,28 +742,21 @@ void pci_process_bridge_OF_ranges(struct pci_controller *hose, continue; } /* Handles ISA memory hole space here */ - if (pci_addr == 0) { + if (range.pci_addr == 0) { if (primary || isa_mem_base == 0) - isa_mem_base = cpu_addr; - hose->isa_mem_phys = cpu_addr; - hose->isa_mem_size = size; + isa_mem_base = range.cpu_addr; + hose->isa_mem_phys = range.cpu_addr; + hose->isa_mem_size = range.size; } /* Build resource */ - hose->mem_offset[memno] = cpu_addr - pci_addr; + hose->mem_offset[memno] = range.cpu_addr - + range.pci_addr; res = &hose->mem_resources[memno++]; - res->flags = IORESOURCE_MEM; - if (pci_space & 0x40000000) - res->flags |= IORESOURCE_PREFETCH; - res->start = cpu_addr; break; } if (res != NULL) { - res->name = dev->full_name; - res->end = res->start + size - 1; - res->parent = NULL; - res->sibling = NULL; - res->child = NULL; + of_pci_range_to_resource(&range, dev, res); } } } diff --git a/arch/powerpc/kernel/pci-hotplug.c b/arch/powerpc/kernel/pci-hotplug.c index c1e17ae68a0..5b789177aa2 100644 --- a/arch/powerpc/kernel/pci-hotplug.c +++ b/arch/powerpc/kernel/pci-hotplug.c @@ -98,8 +98,7 @@ void pcibios_add_pci_devices(struct pci_bus * bus) max = bus->busn_res.start; for (pass = 0; pass < 2; pass++) { list_for_each_entry(dev, &bus->devices, bus_list) { - if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE || - dev->hdr_type == PCI_HEADER_TYPE_CARDBUS) + if (pci_is_bridge(dev)) max = pci_scan_bridge(bus, dev, max, pass); } diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index a9e311f7a9d..155013da27e 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -208,8 +208,7 @@ long sys_pciconfig_iobase(long which, unsigned long in_bus, unsigned long in_devfn) { struct pci_controller* hose; - struct list_head *ln; - struct pci_bus *bus = NULL; + struct pci_bus *tmp_bus, *bus = NULL; struct device_node *hose_node; /* Argh ! Please forgive me for that hack, but that's the @@ -230,11 +229,12 @@ long sys_pciconfig_iobase(long which, unsigned long in_bus, * used on pre-domains setup. We return the first match */ - for (ln = pci_root_buses.next; ln != &pci_root_buses; ln = ln->next) { - bus = pci_bus_b(ln); - if (in_bus >= bus->number && in_bus <= bus->busn_res.end) + list_for_each_entry(tmp_bus, &pci_root_buses, node) { + if (in_bus >= tmp_bus->number && + in_bus <= tmp_bus->busn_res.end) { + bus = tmp_bus; break; - bus = NULL; + } } if (bus == NULL || bus->dev.of_node == NULL) return -ENODEV; diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c index 83c26d82999..44562aa97f1 100644 --- a/arch/powerpc/kernel/pci_of_scan.c +++ b/arch/powerpc/kernel/pci_of_scan.c @@ -304,6 +304,9 @@ static struct pci_dev *of_scan_pci_dev(struct pci_bus *bus, struct pci_dev *dev = NULL; const __be32 *reg; int reglen, devfn; +#ifdef CONFIG_EEH + struct eeh_dev *edev = of_node_to_eeh_dev(dn); +#endif pr_debug(" * %s\n", dn->full_name); if (!of_device_is_available(dn)) @@ -321,6 +324,12 @@ static struct pci_dev *of_scan_pci_dev(struct pci_bus *bus, return dev; } + /* Device removed permanently ? */ +#ifdef CONFIG_EEH + if (edev && (edev->mode & EEH_DEV_REMOVED)) + return NULL; +#endif + /* create a new pci_dev for this device */ dev = of_create_pci_dev(dn, bus, devfn); if (!dev) @@ -362,8 +371,7 @@ static void __of_scan_bus(struct device_node *node, struct pci_bus *bus, /* Now scan child busses */ list_for_each_entry(dev, &bus->devices, bus_list) { - if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE || - dev->hdr_type == PCI_HEADER_TYPE_CARDBUS) { + if (pci_is_bridge(dev)) { of_scan_pci_bridge(dev); } } diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c index 3bd77edd761..48d17d6fca5 100644 --- a/arch/powerpc/kernel/ppc_ksyms.c +++ b/arch/powerpc/kernel/ppc_ksyms.c @@ -120,6 +120,7 @@ EXPORT_SYMBOL(giveup_spe); EXPORT_SYMBOL(flush_instruction_cache); #endif EXPORT_SYMBOL(flush_dcache_range); +EXPORT_SYMBOL(flush_icache_range); #ifdef CONFIG_SMP #ifdef CONFIG_PPC32 @@ -154,9 +155,7 @@ EXPORT_SYMBOL(__cmpdi2); #endif long long __bswapdi2(long long); EXPORT_SYMBOL(__bswapdi2); -#ifdef __BIG_ENDIAN__ EXPORT_SYMBOL(memcpy); -#endif EXPORT_SYMBOL(memset); EXPORT_SYMBOL(memmove); EXPORT_SYMBOL(memcmp); diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 8d4c247f173..be99774d3f4 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -54,6 +54,7 @@ #ifdef CONFIG_PPC64 #include <asm/firmware.h> #endif +#include <asm/code-patching.h> #include <linux/kprobes.h> #include <linux/kdebug.h> @@ -495,14 +496,21 @@ static inline int set_dawr(struct arch_hw_breakpoint *brk) return 0; } -int set_breakpoint(struct arch_hw_breakpoint *brk) +void __set_breakpoint(struct arch_hw_breakpoint *brk) { __get_cpu_var(current_brk) = *brk; if (cpu_has_feature(CPU_FTR_DAWR)) - return set_dawr(brk); + set_dawr(brk); + else + set_dabr(brk); +} - return set_dabr(brk); +void set_breakpoint(struct arch_hw_breakpoint *brk) +{ + preempt_disable(); + __set_breakpoint(brk); + preempt_enable(); } #ifdef CONFIG_PPC64 @@ -610,6 +618,31 @@ out_and_saveregs: tm_save_sprs(thr); } +extern void __tm_recheckpoint(struct thread_struct *thread, + unsigned long orig_msr); + +void tm_recheckpoint(struct thread_struct *thread, + unsigned long orig_msr) +{ + unsigned long flags; + + /* We really can't be interrupted here as the TEXASR registers can't + * change and later in the trecheckpoint code, we have a userspace R1. + * So let's hard disable over this region. + */ + local_irq_save(flags); + hard_irq_disable(); + + /* The TM SPRs are restored here, so that TEXASR.FS can be set + * before the trecheckpoint and no explosion occurs. + */ + tm_restore_sprs(thread); + + __tm_recheckpoint(thread, orig_msr); + + local_irq_restore(flags); +} + static inline void tm_recheckpoint_new_task(struct task_struct *new) { unsigned long msr; @@ -628,13 +661,10 @@ static inline void tm_recheckpoint_new_task(struct task_struct *new) if (!new->thread.regs) return; - /* The TM SPRs are restored here, so that TEXASR.FS can be set - * before the trecheckpoint and no explosion occurs. - */ - tm_restore_sprs(&new->thread); - - if (!MSR_TM_ACTIVE(new->thread.regs->msr)) + if (!MSR_TM_ACTIVE(new->thread.regs->msr)){ + tm_restore_sprs(&new->thread); return; + } msr = new->thread.tm_orig_msr; /* Recheckpoint to restore original checkpointed register state. */ TM_DEBUG("*** tm_recheckpoint of pid %d " @@ -725,15 +755,15 @@ struct task_struct *__switch_to(struct task_struct *prev, WARN_ON(!irqs_disabled()); - /* Back up the TAR across context switches. + /* Back up the TAR and DSCR across context switches. * Note that the TAR is not available for use in the kernel. (To * provide this, the TAR should be backed up/restored on exception * entry/exit instead, and be in pt_regs. FIXME, this should be in * pt_regs anyway (for debug).) - * Save the TAR here before we do treclaim/trecheckpoint as these - * will change the TAR. + * Save the TAR and DSCR here before we do treclaim/trecheckpoint as + * these will change them. */ - save_tar(&prev->thread); + save_early_sprs(&prev->thread); __switch_to_tm(prev); @@ -812,7 +842,7 @@ struct task_struct *__switch_to(struct task_struct *prev, */ #ifndef CONFIG_HAVE_HW_BREAKPOINT if (unlikely(!hw_brk_match(&__get_cpu_var(current_brk), &new->thread.hw_brk))) - set_breakpoint(&new->thread.hw_brk); + __set_breakpoint(&new->thread.hw_brk); #endif /* CONFIG_HAVE_HW_BREAKPOINT */ #endif @@ -1048,6 +1078,15 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) flush_altivec_to_thread(src); flush_vsx_to_thread(src); flush_spe_to_thread(src); + /* + * Flush TM state out so we can copy it. __switch_to_tm() does this + * flush but it removes the checkpointed state from the current CPU and + * transitions the CPU out of TM mode. Hence we need to call + * tm_recheckpoint_new_task() (on the same task) to restore the + * checkpointed state back and the TM mode. + */ + __switch_to_tm(src); + tm_recheckpoint_new_task(src); *dst = *src; @@ -1077,7 +1116,9 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, struct thread_info *ti = (void *)task_stack_page(p); memset(childregs, 0, sizeof(struct pt_regs)); childregs->gpr[1] = sp + sizeof(struct pt_regs); - childregs->gpr[14] = usp; /* function */ + /* function */ + if (usp) + childregs->gpr[14] = ppc_function_entry((void *)usp); #ifdef CONFIG_PPC64 clear_tsk_thread_flag(p, TIF_32BIT); childregs->softe = 1; @@ -1156,17 +1197,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, if (cpu_has_feature(CPU_FTR_HAS_PPR)) p->thread.ppr = INIT_PPR; #endif - /* - * The PPC64 ABI makes use of a TOC to contain function - * pointers. The function (ret_from_except) is actually a pointer - * to the TOC entry. The first entry is a pointer to the actual - * function. - */ -#ifdef CONFIG_PPC64 - kregs->nip = *((unsigned long *)f); -#else - kregs->nip = (unsigned long)f; -#endif + kregs->nip = ppc_function_entry(f); return 0; } diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index f58c0d3aaeb..b694b073097 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -29,10 +29,11 @@ #include <linux/bitops.h> #include <linux/export.h> #include <linux/kexec.h> -#include <linux/debugfs.h> #include <linux/irq.h> #include <linux/memblock.h> #include <linux/of.h> +#include <linux/of_fdt.h> +#include <linux/libfdt.h> #include <asm/prom.h> #include <asm/rtas.h> @@ -117,14 +118,14 @@ static void __init move_device_tree(void) DBG("-> move_device_tree\n"); start = __pa(initial_boot_params); - size = be32_to_cpu(initial_boot_params->totalsize); + size = fdt_totalsize(initial_boot_params); if ((memory_limit && (start + size) > PHYSICAL_START + memory_limit) || overlaps_crashkernel(start, size) || overlaps_initrd(start, size)) { p = __va(memblock_alloc(size, PAGE_SIZE)); memcpy(p, initial_boot_params, size); - initial_boot_params = (struct boot_param_header *)p; + initial_boot_params = p; DBG("Moved device tree to 0x%p\n", p); } @@ -162,7 +163,7 @@ static struct ibm_pa_feature { {CPU_FTR_REAL_LE, PPC_FEATURE_TRUE_LE, 5, 0, 0}, }; -static void __init scan_features(unsigned long node, unsigned char *ftrs, +static void __init scan_features(unsigned long node, const unsigned char *ftrs, unsigned long tablelen, struct ibm_pa_feature *fp, unsigned long ft_size) @@ -201,8 +202,8 @@ static void __init scan_features(unsigned long node, unsigned char *ftrs, static void __init check_cpu_pa_features(unsigned long node) { - unsigned char *pa_ftrs; - unsigned long tablelen; + const unsigned char *pa_ftrs; + int tablelen; pa_ftrs = of_get_flat_dt_prop(node, "ibm,pa-features", &tablelen); if (pa_ftrs == NULL) @@ -215,7 +216,7 @@ static void __init check_cpu_pa_features(unsigned long node) #ifdef CONFIG_PPC_STD_MMU_64 static void __init check_cpu_slb_size(unsigned long node) { - __be32 *slb_size_ptr; + const __be32 *slb_size_ptr; slb_size_ptr = of_get_flat_dt_prop(node, "slb-size", NULL); if (slb_size_ptr != NULL) { @@ -256,7 +257,7 @@ static struct feature_property { static inline void identical_pvr_fixup(unsigned long node) { unsigned int pvr; - char *model = of_get_flat_dt_prop(node, "model", NULL); + const char *model = of_get_flat_dt_prop(node, "model", NULL); /* * Since 440GR(x)/440EP(x) processors have the same pvr, @@ -294,11 +295,11 @@ static int __init early_init_dt_scan_cpus(unsigned long node, const char *uname, int depth, void *data) { - char *type = of_get_flat_dt_prop(node, "device_type", NULL); + const char *type = of_get_flat_dt_prop(node, "device_type", NULL); const __be32 *prop; const __be32 *intserv; int i, nthreads; - unsigned long len; + int len; int found = -1; int found_thread = 0; @@ -324,9 +325,9 @@ static int __init early_init_dt_scan_cpus(unsigned long node, * version 2 of the kexec param format adds the phys cpuid of * booted proc. */ - if (be32_to_cpu(initial_boot_params->version) >= 2) { + if (fdt_version(initial_boot_params) >= 2) { if (be32_to_cpu(intserv[i]) == - be32_to_cpu(initial_boot_params->boot_cpuid_phys)) { + fdt_boot_cpuid_phys(initial_boot_params)) { found = boot_cpu_count; found_thread = i; } @@ -346,52 +347,52 @@ static int __init early_init_dt_scan_cpus(unsigned long node, #endif } - if (found >= 0) { - DBG("boot cpu: logical %d physical %d\n", found, - be32_to_cpu(intserv[found_thread])); - boot_cpuid = found; - set_hard_smp_processor_id(found, - be32_to_cpu(intserv[found_thread])); + /* Not the boot CPU */ + if (found < 0) + return 0; - /* - * PAPR defines "logical" PVR values for cpus that - * meet various levels of the architecture: - * 0x0f000001 Architecture version 2.04 - * 0x0f000002 Architecture version 2.05 - * If the cpu-version property in the cpu node contains - * such a value, we call identify_cpu again with the - * logical PVR value in order to use the cpu feature - * bits appropriate for the architecture level. - * - * A POWER6 partition in "POWER6 architected" mode - * uses the 0x0f000002 PVR value; in POWER5+ mode - * it uses 0x0f000001. - */ - prop = of_get_flat_dt_prop(node, "cpu-version", NULL); - if (prop && (be32_to_cpup(prop) & 0xff000000) == 0x0f000000) - identify_cpu(0, be32_to_cpup(prop)); + DBG("boot cpu: logical %d physical %d\n", found, + be32_to_cpu(intserv[found_thread])); + boot_cpuid = found; + set_hard_smp_processor_id(found, be32_to_cpu(intserv[found_thread])); - identical_pvr_fixup(node); - } + /* + * PAPR defines "logical" PVR values for cpus that + * meet various levels of the architecture: + * 0x0f000001 Architecture version 2.04 + * 0x0f000002 Architecture version 2.05 + * If the cpu-version property in the cpu node contains + * such a value, we call identify_cpu again with the + * logical PVR value in order to use the cpu feature + * bits appropriate for the architecture level. + * + * A POWER6 partition in "POWER6 architected" mode + * uses the 0x0f000002 PVR value; in POWER5+ mode + * it uses 0x0f000001. + */ + prop = of_get_flat_dt_prop(node, "cpu-version", NULL); + if (prop && (be32_to_cpup(prop) & 0xff000000) == 0x0f000000) + identify_cpu(0, be32_to_cpup(prop)); + + identical_pvr_fixup(node); check_cpu_feature_properties(node); check_cpu_pa_features(node); check_cpu_slb_size(node); -#ifdef CONFIG_PPC_PSERIES +#ifdef CONFIG_PPC64 if (nthreads > 1) cur_cpu_spec->cpu_features |= CPU_FTR_SMT; else cur_cpu_spec->cpu_features &= ~CPU_FTR_SMT; #endif - return 0; } int __init early_init_dt_scan_chosen_ppc(unsigned long node, const char *uname, int depth, void *data) { - unsigned long *lprop; /* All these set by kernel, so no need to convert endian */ + const unsigned long *lprop; /* All these set by kernel, so no need to convert endian */ /* Use common scan routine to determine if this is the chosen node */ if (early_init_dt_scan_chosen(node, uname, depth, data) == 0) @@ -442,8 +443,9 @@ int __init early_init_dt_scan_chosen_ppc(unsigned long node, const char *uname, */ static int __init early_init_dt_scan_drconf_memory(unsigned long node) { - __be32 *dm, *ls, *usm; - unsigned long l, n, flags; + const __be32 *dm, *ls, *usm; + int l; + unsigned long n, flags; u64 base, size, memblock_size; unsigned int is_kexec_kdump = 0, rngs; @@ -563,9 +565,12 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size) static void __init early_reserve_mem_dt(void) { - unsigned long i, len, dt_root; + unsigned long i, dt_root; + int len; const __be32 *prop; + early_init_fdt_scan_reserved_mem(); + dt_root = of_get_flat_dt_root(); prop = of_get_flat_dt_prop(dt_root, "reserved-ranges", &len); @@ -592,18 +597,10 @@ static void __init early_reserve_mem_dt(void) static void __init early_reserve_mem(void) { - u64 base, size; __be64 *reserve_map; - unsigned long self_base; - unsigned long self_size; reserve_map = (__be64 *)(((unsigned long)initial_boot_params) + - be32_to_cpu(initial_boot_params->off_mem_rsvmap)); - - /* before we do anything, lets reserve the dt blob */ - self_base = __pa((unsigned long)initial_boot_params); - self_size = be32_to_cpu(initial_boot_params->totalsize); - memblock_reserve(self_base, self_size); + fdt_off_mem_rsvmap(initial_boot_params)); /* Look for the new "reserved-regions" property in the DT */ early_reserve_mem_dt(); @@ -633,26 +630,12 @@ static void __init early_reserve_mem(void) size_32 = be32_to_cpup(reserve_map_32++); if (size_32 == 0) break; - /* skip if the reservation is for the blob */ - if (base_32 == self_base && size_32 == self_size) - continue; DBG("reserving: %x -> %x\n", base_32, size_32); memblock_reserve(base_32, size_32); } return; } #endif - DBG("Processing reserve map\n"); - - /* Handle the reserve map in the fdt blob if it exists */ - while (1) { - base = be64_to_cpup(reserve_map++); - size = be64_to_cpup(reserve_map++); - if (size == 0) - break; - DBG("reserving: %llx -> %llx\n", base, size); - memblock_reserve(base, size); - } } void __init early_init_devtree(void *params) @@ -679,13 +662,6 @@ void __init early_init_devtree(void *params) of_scan_flat_dt(early_init_dt_scan_fw_dump, NULL); #endif - /* Pre-initialize the cmd_line with the content of boot_commmand_line, - * which will be empty except when the content of the variable has - * been overriden by a bootloading mechanism. This happens typically - * with HAL takeover - */ - strlcpy(cmd_line, boot_command_line, COMMAND_LINE_SIZE); - /* Retrieve various informations from the /chosen node of the * device-tree, including the platform type, initrd location and * size, TCE reserve, and more ... @@ -744,6 +720,10 @@ void __init early_init_devtree(void *params) * (altivec support, boot CPU ID, ...) */ of_scan_flat_dt(early_init_dt_scan_cpus, NULL); + if (boot_cpuid < 0) { + printk("Failed to indentify boot CPU !\n"); + BUG(); + } #if defined(CONFIG_SMP) && defined(CONFIG_PPC64) /* We'll later wait for secondaries to check in; there are @@ -752,6 +732,11 @@ void __init early_init_devtree(void *params) spinning_secondaries = boot_cpu_count - 1; #endif +#ifdef CONFIG_PPC_POWERNV + /* Scan and build the list of machine check recoverable ranges */ + of_scan_flat_dt(early_init_dt_scan_recoverable_ranges, NULL); +#endif + DBG(" <- early_init_devtree()\n"); } @@ -910,23 +895,3 @@ bool arch_match_cpu_phys_id(int cpu, u64 phys_id) { return (int)phys_id == get_hard_smp_processor_id(cpu); } - -#if defined(CONFIG_DEBUG_FS) && defined(DEBUG) -static struct debugfs_blob_wrapper flat_dt_blob; - -static int __init export_flat_device_tree(void) -{ - struct dentry *d; - - flat_dt_blob.data = initial_boot_params; - flat_dt_blob.size = be32_to_cpu(initial_boot_params->totalsize); - - d = debugfs_create_blob("flat-device-tree", S_IFREG | S_IRUSR, - powerpc_debugfs_root, &flat_dt_blob); - if (!d) - return 1; - - return 0; -} -__initcall(export_flat_device_tree); -#endif diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 078145acf7f..1a85d8f9673 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -1268,201 +1268,6 @@ static u64 __initdata prom_opal_base; static u64 __initdata prom_opal_entry; #endif -#ifdef __BIG_ENDIAN__ -/* XXX Don't change this structure without updating opal-takeover.S */ -static struct opal_secondary_data { - s64 ack; /* 0 */ - u64 go; /* 8 */ - struct opal_takeover_args args; /* 16 */ -} opal_secondary_data; - -static u64 __initdata prom_opal_align; -static u64 __initdata prom_opal_size; -static int __initdata prom_rtas_start_cpu; -static u64 __initdata prom_rtas_data; -static u64 __initdata prom_rtas_entry; - -extern char opal_secondary_entry; - -static void __init prom_query_opal(void) -{ - long rc; - - /* We must not query for OPAL presence on a machine that - * supports TNK takeover (970 blades), as this uses the same - * h-call with different arguments and will crash - */ - if (PHANDLE_VALID(call_prom("finddevice", 1, 1, - ADDR("/tnk-memory-map")))) { - prom_printf("TNK takeover detected, skipping OPAL check\n"); - return; - } - - prom_printf("Querying for OPAL presence... "); - - rc = opal_query_takeover(&prom_opal_size, - &prom_opal_align); - prom_debug("(rc = %ld) ", rc); - if (rc != 0) { - prom_printf("not there.\n"); - return; - } - of_platform = PLATFORM_OPAL; - prom_printf(" there !\n"); - prom_debug(" opal_size = 0x%lx\n", prom_opal_size); - prom_debug(" opal_align = 0x%lx\n", prom_opal_align); - if (prom_opal_align < 0x10000) - prom_opal_align = 0x10000; -} - -static int __init prom_rtas_call(int token, int nargs, int nret, - int *outputs, ...) -{ - struct rtas_args rtas_args; - va_list list; - int i; - - rtas_args.token = token; - rtas_args.nargs = nargs; - rtas_args.nret = nret; - rtas_args.rets = (rtas_arg_t *)&(rtas_args.args[nargs]); - va_start(list, outputs); - for (i = 0; i < nargs; ++i) - rtas_args.args[i] = va_arg(list, rtas_arg_t); - va_end(list); - - for (i = 0; i < nret; ++i) - rtas_args.rets[i] = 0; - - opal_enter_rtas(&rtas_args, prom_rtas_data, - prom_rtas_entry); - - if (nret > 1 && outputs != NULL) - for (i = 0; i < nret-1; ++i) - outputs[i] = rtas_args.rets[i+1]; - return (nret > 0)? rtas_args.rets[0]: 0; -} - -static void __init prom_opal_hold_cpus(void) -{ - int i, cnt, cpu, rc; - long j; - phandle node; - char type[64]; - u32 servers[8]; - void *entry = (unsigned long *)&opal_secondary_entry; - struct opal_secondary_data *data = &opal_secondary_data; - - prom_debug("prom_opal_hold_cpus: start...\n"); - prom_debug(" - entry = 0x%x\n", entry); - prom_debug(" - data = 0x%x\n", data); - - data->ack = -1; - data->go = 0; - - /* look for cpus */ - for (node = 0; prom_next_node(&node); ) { - type[0] = 0; - prom_getprop(node, "device_type", type, sizeof(type)); - if (strcmp(type, "cpu") != 0) - continue; - - /* Skip non-configured cpus. */ - if (prom_getprop(node, "status", type, sizeof(type)) > 0) - if (strcmp(type, "okay") != 0) - continue; - - cnt = prom_getprop(node, "ibm,ppc-interrupt-server#s", servers, - sizeof(servers)); - if (cnt == PROM_ERROR) - break; - cnt >>= 2; - for (i = 0; i < cnt; i++) { - cpu = servers[i]; - prom_debug("CPU %d ... ", cpu); - if (cpu == prom.cpu) { - prom_debug("booted !\n"); - continue; - } - prom_debug("starting ... "); - - /* Init the acknowledge var which will be reset by - * the secondary cpu when it awakens from its OF - * spinloop. - */ - data->ack = -1; - rc = prom_rtas_call(prom_rtas_start_cpu, 3, 1, - NULL, cpu, entry, data); - prom_debug("rtas rc=%d ...", rc); - - for (j = 0; j < 100000000 && data->ack == -1; j++) { - HMT_low(); - mb(); - } - HMT_medium(); - if (data->ack != -1) - prom_debug("done, PIR=0x%x\n", data->ack); - else - prom_debug("timeout !\n"); - } - } - prom_debug("prom_opal_hold_cpus: end...\n"); -} - -static void __init prom_opal_takeover(void) -{ - struct opal_secondary_data *data = &opal_secondary_data; - struct opal_takeover_args *args = &data->args; - u64 align = prom_opal_align; - u64 top_addr, opal_addr; - - args->k_image = (u64)_stext; - args->k_size = _end - _stext; - args->k_entry = 0; - args->k_entry2 = 0x60; - - top_addr = _ALIGN_UP(args->k_size, align); - - if (prom_initrd_start != 0) { - args->rd_image = prom_initrd_start; - args->rd_size = prom_initrd_end - args->rd_image; - args->rd_loc = top_addr; - top_addr = _ALIGN_UP(args->rd_loc + args->rd_size, align); - } - - /* Pickup an address for the HAL. We want to go really high - * up to avoid problem with future kexecs. On the other hand - * we don't want to be all over the TCEs on P5IOC2 machines - * which are going to be up there too. We assume the machine - * has plenty of memory, and we ask for the HAL for now to - * be just below the 1G point, or above the initrd - */ - opal_addr = _ALIGN_DOWN(0x40000000 - prom_opal_size, align); - if (opal_addr < top_addr) - opal_addr = top_addr; - args->hal_addr = opal_addr; - - /* Copy the command line to the kernel image */ - strlcpy(boot_command_line, prom_cmd_line, - COMMAND_LINE_SIZE); - - prom_debug(" k_image = 0x%lx\n", args->k_image); - prom_debug(" k_size = 0x%lx\n", args->k_size); - prom_debug(" k_entry = 0x%lx\n", args->k_entry); - prom_debug(" k_entry2 = 0x%lx\n", args->k_entry2); - prom_debug(" hal_addr = 0x%lx\n", args->hal_addr); - prom_debug(" rd_image = 0x%lx\n", args->rd_image); - prom_debug(" rd_size = 0x%lx\n", args->rd_size); - prom_debug(" rd_loc = 0x%lx\n", args->rd_loc); - prom_printf("Performing OPAL takeover,this can take a few minutes..\n"); - prom_close_stdin(); - mb(); - data->go = 1; - for (;;) - opal_do_takeover(args); -} -#endif /* __BIG_ENDIAN__ */ - /* * Allocate room for and instantiate OPAL */ @@ -1597,12 +1402,6 @@ static void __init prom_instantiate_rtas(void) &val, sizeof(val)) != PROM_ERROR) rtas_has_query_cpu_stopped = true; -#if defined(CONFIG_PPC_POWERNV) && defined(__BIG_ENDIAN__) - /* PowerVN takeover hack */ - prom_rtas_data = base; - prom_rtas_entry = entry; - prom_getprop(rtas_node, "start-cpu", &prom_rtas_start_cpu, 4); -#endif prom_debug("rtas base = 0x%x\n", base); prom_debug("rtas entry = 0x%x\n", entry); prom_debug("rtas size = 0x%x\n", (long)size); @@ -3027,16 +2826,6 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4, prom_instantiate_rtas(); #ifdef CONFIG_PPC_POWERNV -#ifdef __BIG_ENDIAN__ - /* Detect HAL and try instanciating it & doing takeover */ - if (of_platform == PLATFORM_PSERIES_LPAR) { - prom_query_opal(); - if (of_platform == PLATFORM_OPAL) { - prom_opal_hold_cpus(); - prom_opal_takeover(); - } - } else -#endif /* __BIG_ENDIAN__ */ if (of_platform == PLATFORM_OPAL) prom_instantiate_opal(); #endif /* CONFIG_PPC_POWERNV */ diff --git a/arch/powerpc/kernel/prom_init_check.sh b/arch/powerpc/kernel/prom_init_check.sh index b0c263da219..fe8e54b9ef7 100644 --- a/arch/powerpc/kernel/prom_init_check.sh +++ b/arch/powerpc/kernel/prom_init_check.sh @@ -21,9 +21,7 @@ _end enter_prom memcpy memset reloc_offset __secondary_hold __secondary_hold_acknowledge __secondary_hold_spinloop __start strcmp strcpy strlcpy strlen strncmp strstr logo_linux_clut224 reloc_got2 kernstart_addr memstart_addr linux_banner _stext -opal_query_takeover opal_do_takeover opal_enter_rtas opal_secondary_entry -boot_command_line __prom_init_toc_start __prom_init_toc_end -btext_setup_display" +__prom_init_toc_start __prom_init_toc_end btext_setup_display TOC." NM="$1" OBJ="$2" diff --git a/arch/powerpc/kernel/reloc_64.S b/arch/powerpc/kernel/reloc_64.S index b47a0e1ab00..d88736fbece 100644 --- a/arch/powerpc/kernel/reloc_64.S +++ b/arch/powerpc/kernel/reloc_64.S @@ -69,8 +69,8 @@ _GLOBAL(relocate) * R_PPC64_RELATIVE ones. */ mtctr r8 -5: lwz r0,12(9) /* ELF64_R_TYPE(reloc->r_info) */ - cmpwi r0,R_PPC64_RELATIVE +5: ld r0,8(9) /* ELF64_R_TYPE(reloc->r_info) */ + cmpdi r0,R_PPC64_RELATIVE bne 6f ld r6,0(r9) /* reloc->r_offset */ ld r0,16(r9) /* reloc->r_addend */ @@ -81,6 +81,7 @@ _GLOBAL(relocate) 6: blr +.balign 8 p_dyn: .llong __dynamic_start - 0b p_rela: .llong __rela_dyn_start - 0b p_st: .llong _stext - 0b diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 4cf674d7d5a..8b4c857c142 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -993,32 +993,36 @@ struct pseries_errorlog *get_pseries_errorlog(struct rtas_error_log *log, (struct rtas_ext_event_log_v6 *)log->buffer; struct pseries_errorlog *sect; unsigned char *p, *log_end; + uint32_t ext_log_length = rtas_error_extended_log_length(log); + uint8_t log_format = rtas_ext_event_log_format(ext_log); + uint32_t company_id = rtas_ext_event_company_id(ext_log); /* Check that we understand the format */ - if (log->extended_log_length < sizeof(struct rtas_ext_event_log_v6) || - ext_log->log_format != RTAS_V6EXT_LOG_FORMAT_EVENT_LOG || - ext_log->company_id != RTAS_V6EXT_COMPANY_ID_IBM) + if (ext_log_length < sizeof(struct rtas_ext_event_log_v6) || + log_format != RTAS_V6EXT_LOG_FORMAT_EVENT_LOG || + company_id != RTAS_V6EXT_COMPANY_ID_IBM) return NULL; - log_end = log->buffer + log->extended_log_length; + log_end = log->buffer + ext_log_length; p = ext_log->vendor_log; while (p < log_end) { sect = (struct pseries_errorlog *)p; - if (sect->id == section_id) + if (pseries_errorlog_id(sect) == section_id) return sect; - p += sect->length; + p += pseries_errorlog_length(sect); } return NULL; } +/* We assume to be passed big endian arguments */ asmlinkage int ppc_rtas(struct rtas_args __user *uargs) { struct rtas_args args; unsigned long flags; char *buff_copy, *errbuf = NULL; - int nargs; + int nargs, nret, token; int rc; if (!capable(CAP_SYS_ADMIN)) @@ -1027,10 +1031,13 @@ asmlinkage int ppc_rtas(struct rtas_args __user *uargs) if (copy_from_user(&args, uargs, 3 * sizeof(u32)) != 0) return -EFAULT; - nargs = args.nargs; + nargs = be32_to_cpu(args.nargs); + nret = be32_to_cpu(args.nret); + token = be32_to_cpu(args.token); + if (nargs > ARRAY_SIZE(args.args) - || args.nret > ARRAY_SIZE(args.args) - || nargs + args.nret > ARRAY_SIZE(args.args)) + || nret > ARRAY_SIZE(args.args) + || nargs + nret > ARRAY_SIZE(args.args)) return -EINVAL; /* Copy in args. */ @@ -1038,14 +1045,14 @@ asmlinkage int ppc_rtas(struct rtas_args __user *uargs) nargs * sizeof(rtas_arg_t)) != 0) return -EFAULT; - if (args.token == RTAS_UNKNOWN_SERVICE) + if (token == RTAS_UNKNOWN_SERVICE) return -EINVAL; args.rets = &args.args[nargs]; - memset(args.rets, 0, args.nret * sizeof(rtas_arg_t)); + memset(args.rets, 0, nret * sizeof(rtas_arg_t)); /* Need to handle ibm,suspend_me call specially */ - if (args.token == ibm_suspend_me_token) { + if (token == ibm_suspend_me_token) { rc = rtas_ibm_suspend_me(&args); if (rc) return rc; @@ -1062,7 +1069,7 @@ asmlinkage int ppc_rtas(struct rtas_args __user *uargs) /* A -1 return code indicates that the last command couldn't be completed due to a hardware error. */ - if (args.rets[0] == -1) + if (be32_to_cpu(args.rets[0]) == -1) errbuf = __fetch_rtas_last_error(buff_copy); unlock_rtas(flags); @@ -1077,7 +1084,7 @@ asmlinkage int ppc_rtas(struct rtas_args __user *uargs) /* Copy out args. */ if (copy_to_user(uargs->args + nargs, args.args + nargs, - args.nret * sizeof(rtas_arg_t)) != 0) + nret * sizeof(rtas_arg_t)) != 0) return -EFAULT; return 0; @@ -1135,7 +1142,7 @@ void __init rtas_initialize(void) int __init early_init_dt_scan_rtas(unsigned long node, const char *uname, int depth, void *data) { - u32 *basep, *entryp, *sizep; + const u32 *basep, *entryp, *sizep; if (depth != 1 || strcmp(uname, "rtas") != 0) return 0; diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c index 2f3cdb01506..db2b482af65 100644 --- a/arch/powerpc/kernel/rtas_flash.c +++ b/arch/powerpc/kernel/rtas_flash.c @@ -611,17 +611,19 @@ static void rtas_flash_firmware(int reboot_type) for (f = flist; f; f = next) { /* Translate data addrs to absolute */ for (i = 0; i < f->num_blocks; i++) { - f->blocks[i].data = (char *)__pa(f->blocks[i].data); + f->blocks[i].data = (char *)cpu_to_be64(__pa(f->blocks[i].data)); image_size += f->blocks[i].length; + f->blocks[i].length = cpu_to_be64(f->blocks[i].length); } next = f->next; /* Don't translate NULL pointer for last entry */ if (f->next) - f->next = (struct flash_block_list *)__pa(f->next); + f->next = (struct flash_block_list *)cpu_to_be64(__pa(f->next)); else f->next = NULL; /* make num_blocks into the version/length field */ f->num_blocks = (FLASH_BLOCK_LIST_VERSION << 56) | ((f->num_blocks+1)*16); + f->num_blocks = cpu_to_be64(f->num_blocks); } printk(KERN_ALERT "FLASH: flash image is %ld bytes\n", image_size); @@ -705,7 +707,7 @@ static int __init rtas_flash_init(void) if (rtas_token("ibm,update-flash-64-and-reboot") == RTAS_UNKNOWN_SERVICE) { pr_info("rtas_flash: no firmware flash support\n"); - return 1; + return -EINVAL; } rtas_validate_flash_data.buf = kzalloc(VALIDATE_BUF_SIZE, GFP_KERNEL); diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c index 7d4c7172f38..c168337aef9 100644 --- a/arch/powerpc/kernel/rtas_pci.c +++ b/arch/powerpc/kernel/rtas_pci.c @@ -80,10 +80,6 @@ int rtas_read_config(struct pci_dn *pdn, int where, int size, u32 *val) if (ret) return PCIBIOS_DEVICE_NOT_FOUND; - if (returnval == EEH_IO_ERROR_VALUE(size) && - eeh_dev_check_failure(of_node_to_eeh_dev(pdn->node))) - return PCIBIOS_DEVICE_NOT_FOUND; - return PCIBIOS_SUCCESSFUL; } @@ -92,18 +88,39 @@ static int rtas_pci_read_config(struct pci_bus *bus, int where, int size, u32 *val) { struct device_node *busdn, *dn; - - busdn = pci_bus_to_OF_node(bus); + struct pci_dn *pdn; + bool found = false; +#ifdef CONFIG_EEH + struct eeh_dev *edev; +#endif + int ret; /* Search only direct children of the bus */ + *val = 0xFFFFFFFF; + busdn = pci_bus_to_OF_node(bus); for (dn = busdn->child; dn; dn = dn->sibling) { - struct pci_dn *pdn = PCI_DN(dn); + pdn = PCI_DN(dn); if (pdn && pdn->devfn == devfn - && of_device_is_available(dn)) - return rtas_read_config(pdn, where, size, val); + && of_device_is_available(dn)) { + found = true; + break; + } } - return PCIBIOS_DEVICE_NOT_FOUND; + if (!found) + return PCIBIOS_DEVICE_NOT_FOUND; +#ifdef CONFIG_EEH + edev = of_node_to_eeh_dev(dn); + if (edev && edev->pe && edev->pe->state & EEH_PE_RESET) + return PCIBIOS_DEVICE_NOT_FOUND; +#endif + + ret = rtas_read_config(pdn, where, size, val); + if (*val == EEH_IO_ERROR_VALUE(size) && + eeh_dev_check_failure(of_node_to_eeh_dev(dn))) + return PCIBIOS_DEVICE_NOT_FOUND; + + return ret; } int rtas_write_config(struct pci_dn *pdn, int where, int size, u32 val) @@ -136,17 +153,34 @@ static int rtas_pci_write_config(struct pci_bus *bus, int where, int size, u32 val) { struct device_node *busdn, *dn; - - busdn = pci_bus_to_OF_node(bus); + struct pci_dn *pdn; + bool found = false; +#ifdef CONFIG_EEH + struct eeh_dev *edev; +#endif + int ret; /* Search only direct children of the bus */ + busdn = pci_bus_to_OF_node(bus); for (dn = busdn->child; dn; dn = dn->sibling) { - struct pci_dn *pdn = PCI_DN(dn); + pdn = PCI_DN(dn); if (pdn && pdn->devfn == devfn - && of_device_is_available(dn)) - return rtas_write_config(pdn, where, size, val); + && of_device_is_available(dn)) { + found = true; + break; + } } - return PCIBIOS_DEVICE_NOT_FOUND; + + if (!found) + return PCIBIOS_DEVICE_NOT_FOUND; +#ifdef CONFIG_EEH + edev = of_node_to_eeh_dev(dn); + if (edev && edev->pe && (edev->pe->state & EEH_PE_RESET)) + return PCIBIOS_DEVICE_NOT_FOUND; +#endif + ret = rtas_write_config(pdn, where, size, val); + + return ret; } static struct pci_ops rtas_pci_ops = { diff --git a/arch/powerpc/kernel/rtasd.c b/arch/powerpc/kernel/rtasd.c index 1130c53ad65..e736387fee6 100644 --- a/arch/powerpc/kernel/rtasd.c +++ b/arch/powerpc/kernel/rtasd.c @@ -150,8 +150,8 @@ static void printk_log_rtas(char *buf, int len) struct rtas_error_log *errlog = (struct rtas_error_log *)buf; printk(RTAS_DEBUG "event: %d, Type: %s, Severity: %d\n", - error_log_cnt, rtas_event_type(errlog->type), - errlog->severity); + error_log_cnt, rtas_event_type(rtas_error_type(errlog)), + rtas_error_severity(errlog)); } } @@ -159,14 +159,16 @@ static int log_rtas_len(char * buf) { int len; struct rtas_error_log *err; + uint32_t extended_log_length; /* rtas fixed header */ len = 8; err = (struct rtas_error_log *)buf; - if (err->extended && err->extended_log_length) { + extended_log_length = rtas_error_extended_log_length(err); + if (rtas_error_extended(err) && extended_log_length) { /* extended header */ - len += err->extended_log_length; + len += extended_log_length; } if (rtas_error_log_max == 0) @@ -293,15 +295,13 @@ void prrn_schedule_update(u32 scope) static void handle_rtas_event(const struct rtas_error_log *log) { - if (log->type == RTAS_TYPE_PRRN) { - /* For PRRN Events the extended log length is used to denote - * the scope for calling rtas update-nodes. - */ - if (prrn_is_enabled()) - prrn_schedule_update(log->extended_log_length); - } + if (rtas_error_type(log) != RTAS_TYPE_PRRN || !prrn_is_enabled()) + return; - return; + /* For PRRN Events the extended log length is used to denote + * the scope for calling rtas update-nodes. + */ + prrn_schedule_update(rtas_error_extended_log_length(log)); } #else diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index bc76cc6b419..e5b022c55cc 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -76,6 +76,9 @@ EXPORT_SYMBOL(ppc_md); struct machdep_calls *machine_id; EXPORT_SYMBOL(machine_id); +int boot_cpuid = -1; +EXPORT_SYMBOL_GPL(boot_cpuid); + unsigned long klimit = (unsigned long) _end; char cmd_line[COMMAND_LINE_SIZE]; @@ -209,6 +212,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) { unsigned long cpu_id = (unsigned long)v - 1; unsigned int pvr; + unsigned long proc_freq; unsigned short maj; unsigned short min; @@ -260,12 +264,19 @@ static int show_cpuinfo(struct seq_file *m, void *v) #endif /* CONFIG_TAU */ /* - * Assume here that all clock rates are the same in a - * smp system. -- Cort + * Platforms that have variable clock rates, should implement + * the method ppc_md.get_proc_freq() that reports the clock + * rate of a given cpu. The rest can use ppc_proc_freq to + * report the clock rate that is same across all cpus. */ - if (ppc_proc_freq) + if (ppc_md.get_proc_freq) + proc_freq = ppc_md.get_proc_freq(cpu_id); + else + proc_freq = ppc_proc_freq; + + if (proc_freq) seq_printf(m, "clock\t\t: %lu.%06luMHz\n", - ppc_proc_freq / 1000000, ppc_proc_freq % 1000000); + proc_freq / 1000000, proc_freq % 1000000); if (ppc_md.show_percpuinfo != NULL) ppc_md.show_percpuinfo(m, cpu_id); @@ -379,9 +390,10 @@ void __init check_for_initrd(void) #ifdef CONFIG_SMP -int threads_per_core, threads_shift; +int threads_per_core, threads_per_subcore, threads_shift; cpumask_t threads_core_mask; EXPORT_SYMBOL_GPL(threads_per_core); +EXPORT_SYMBOL_GPL(threads_per_subcore); EXPORT_SYMBOL_GPL(threads_shift); EXPORT_SYMBOL_GPL(threads_core_mask); @@ -390,6 +402,7 @@ static void __init cpu_init_thread_core_maps(int tpc) int i; threads_per_core = tpc; + threads_per_subcore = tpc; cpumask_clear(&threads_core_mask); /* This implementation only supports power of 2 number of threads @@ -456,9 +469,17 @@ void __init smp_setup_cpu_maps(void) } for (j = 0; j < nthreads && cpu < nr_cpu_ids; j++) { + bool avail; + DBG(" thread %d -> cpu %d (hard id %d)\n", j, cpu, be32_to_cpu(intserv[j])); - set_cpu_present(cpu, true); + + avail = of_device_is_available(dn); + if (!avail) + avail = !of_property_match_string(dn, + "enable-method", "spin-table"); + + set_cpu_present(cpu, avail); set_hard_smp_processor_id(cpu, be32_to_cpu(intserv[j])); set_cpu_possible(cpu, true); cpu++; @@ -715,33 +736,6 @@ static int powerpc_debugfs_init(void) arch_initcall(powerpc_debugfs_init); #endif -#ifdef CONFIG_BOOKE_WDT -extern u32 booke_wdt_enabled; -extern u32 booke_wdt_period; - -/* Checks wdt=x and wdt_period=xx command-line option */ -notrace int __init early_parse_wdt(char *p) -{ - if (p && strncmp(p, "0", 1) != 0) - booke_wdt_enabled = 1; - - return 0; -} -early_param("wdt", early_parse_wdt); - -int __init early_parse_wdt_period(char *p) -{ - unsigned long ret; - if (p) { - if (!kstrtol(p, 0, &ret)) - booke_wdt_period = ret; - } - - return 0; -} -early_param("wdt_period", early_parse_wdt_period); -#endif /* CONFIG_BOOKE_WDT */ - void ppc_printk_progress(char *s, unsigned short hex) { pr_info("%s\n", s); diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index 2b0da27eaee..ea4fda60e57 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -44,8 +44,6 @@ extern void bootx_init(unsigned long r4, unsigned long phys); -int boot_cpuid = -1; -EXPORT_SYMBOL_GPL(boot_cpuid); int boot_cpuid_phys; EXPORT_SYMBOL_GPL(boot_cpuid_phys); @@ -247,7 +245,12 @@ static void __init exc_lvl_early_init(void) /* interrupt stacks must be in lowmem, we get that for free on ppc32 * as the memblock is limited to lowmem by MEMBLOCK_REAL_LIMIT */ for_each_possible_cpu(i) { +#ifdef CONFIG_SMP hw_cpu = get_hard_smp_processor_id(i); +#else + hw_cpu = 0; +#endif + critirq_ctx[hw_cpu] = (struct thread_info *) __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE)); #ifdef CONFIG_BOOKE diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index f5f11a7d30e..ee082d77117 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -36,6 +36,7 @@ #include <linux/lockdep.h> #include <linux/memblock.h> #include <linux/hugetlb.h> +#include <linux/memory.h> #include <asm/io.h> #include <asm/kdump.h> @@ -74,7 +75,6 @@ #define DBG(fmt...) #endif -int boot_cpuid = 0; int spinning_secondaries; u64 ppc64_pft_size; @@ -102,6 +102,8 @@ static void setup_tlb_core_data(void) { int cpu; + BUILD_BUG_ON(offsetof(struct tlb_core_data, lock) != 0); + for_each_possible_cpu(cpu) { int first = cpu_first_thread_sibling(cpu); @@ -194,6 +196,19 @@ static void fixup_boot_paca(void) get_paca()->data_offset = 0; } +static void cpu_ready_for_interrupts(void) +{ + /* Set IR and DR in PACA MSR */ + get_paca()->kernel_msr = MSR_KERNEL; + + /* Enable AIL if supported */ + if (cpu_has_feature(CPU_FTR_HVMODE) && + cpu_has_feature(CPU_FTR_ARCH_207S)) { + unsigned long lpcr = mfspr(SPRN_LPCR); + mtspr(SPRN_LPCR, lpcr | LPCR_AIL_3); + } +} + /* * Early initialization entry point. This is called by head.S * with MMU translation disabled. We rely on the "feature" of @@ -260,6 +275,14 @@ void __init early_setup(unsigned long dt_ptr) /* Initialize the hash table or TLB handling */ early_init_mmu(); + /* + * At this point, we can let interrupts switch to virtual mode + * (the MMU has been setup), so adjust the MSR in the PACA to + * have IR and DR set and enable AIL if it exists + */ + cpu_ready_for_interrupts(); + + /* Reserve large chunks of memory for use by CMA for KVM */ kvm_cma_reserve(); /* @@ -292,6 +315,13 @@ void early_setup_secondary(void) /* Initialize the hash table or TLB handling */ early_init_mmu_secondary(); + + /* + * At this point, we can let interrupts switch to virtual mode + * (the MMU has been setup), so adjust the MSR in the PACA to + * have IR and DR set. + */ + cpu_ready_for_interrupts(); } #endif /* CONFIG_SMP */ @@ -312,7 +342,7 @@ void smp_release_cpus(void) ptr = (unsigned long *)((unsigned long)&__secondary_hold_spinloop - PHYSICAL_START); - *ptr = __pa(generic_secondary_smp_init); + *ptr = ppc_function_entry(generic_secondary_smp_init); /* And wait a bit for them to catch up */ for (i = 0; i < 100000; i++) { @@ -552,14 +582,20 @@ static void __init irqstack_early_init(void) static void __init exc_lvl_early_init(void) { unsigned int i; + unsigned long sp; for_each_possible_cpu(i) { - critirq_ctx[i] = (struct thread_info *) - __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE)); - dbgirq_ctx[i] = (struct thread_info *) - __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE)); - mcheckirq_ctx[i] = (struct thread_info *) - __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE)); + sp = memblock_alloc(THREAD_SIZE, THREAD_SIZE); + critirq_ctx[i] = (struct thread_info *)__va(sp); + paca[i].crit_kstack = __va(sp + THREAD_SIZE); + + sp = memblock_alloc(THREAD_SIZE, THREAD_SIZE); + dbgirq_ctx[i] = (struct thread_info *)__va(sp); + paca[i].dbg_kstack = __va(sp + THREAD_SIZE); + + sp = memblock_alloc(THREAD_SIZE, THREAD_SIZE); + mcheckirq_ctx[i] = (struct thread_info *)__va(sp); + paca[i].mc_kstack = __va(sp + THREAD_SIZE); } if (cpu_has_feature(CPU_FTR_DEBUG_LVL_EXC)) @@ -745,6 +781,15 @@ void __init setup_per_cpu_areas(void) } #endif +#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE +unsigned long memory_block_size_bytes(void) +{ + if (ppc_md.memory_block_size) + return ppc_md.memory_block_size(); + + return MIN_MEMORY_BLOCK_SIZE; +} +#endif #if defined(CONFIG_PPC_INDIRECT_PIO) || defined(CONFIG_PPC_INDIRECT_MMIO) struct ppc_pci_io ppc_pci_io; diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index 8fc4177ed65..1c794cef288 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -134,7 +134,7 @@ static int do_signal(struct pt_regs *regs) */ if (current->thread.hw_brk.address && current->thread.hw_brk.type) - set_breakpoint(¤t->thread.hw_brk); + __set_breakpoint(¤t->thread.hw_brk); #endif /* Re-enable the breakpoints for the signal stack */ thread_change_pc(current, regs); diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index a67e00aa3ca..1bc5a1755ed 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -54,7 +54,6 @@ #include "signal.h" -#undef DEBUG_SIG #ifdef CONFIG_PPC64 #define sys_rt_sigreturn compat_sys_rt_sigreturn @@ -881,6 +880,8 @@ static long restore_tm_user_regs(struct pt_regs *regs, * transactional versions should be loaded. */ tm_enable(); + /* Make sure the transaction is marked as failed */ + current->thread.tm_texasr |= TEXASR_FS; /* This loads the checkpointed FP/VEC state, if used */ tm_recheckpoint(¤t->thread, msr); /* Get the top half of the MSR */ @@ -1061,10 +1062,6 @@ int handle_rt_signal32(unsigned long sig, struct k_sigaction *ka, return 1; badframe: -#ifdef DEBUG_SIG - printk("badframe in handle_rt_signal, regs=%p frame=%p newsp=%lx\n", - regs, frame, newsp); -#endif if (show_unhandled_signals) printk_ratelimited(KERN_INFO "%s[%d]: bad frame in handle_rt_signal32: " @@ -1482,10 +1479,6 @@ int handle_signal32(unsigned long sig, struct k_sigaction *ka, return 1; badframe: -#ifdef DEBUG_SIG - printk("badframe in handle_signal, regs=%p frame=%p newsp=%lx\n", - regs, frame, newsp); -#endif if (show_unhandled_signals) printk_ratelimited(KERN_INFO "%s[%d]: bad frame in handle_signal32: " diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index e35bf773df7..97c1e4b683f 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -38,7 +38,6 @@ #include "signal.h" -#define DEBUG_SIG 0 #define GP_REGS_SIZE min(sizeof(elf_gregset_t), sizeof(struct pt_regs)) #define FP_REGS_SIZE sizeof(elf_fpregset_t) @@ -65,8 +64,8 @@ struct rt_sigframe { struct siginfo __user *pinfo; void __user *puc; struct siginfo info; - /* 64 bit ABI allows for 288 bytes below sp before decrementing it. */ - char abigap[288]; + /* New 64 bit little-endian ABI allows redzone of 512 bytes below sp */ + char abigap[USER_REDZONE_SIZE]; } __attribute__ ((aligned (16))); static const char fmt32[] = KERN_INFO \ @@ -527,6 +526,8 @@ static long restore_tm_sigcontexts(struct pt_regs *regs, } #endif tm_enable(); + /* Make sure the transaction is marked as failed */ + current->thread.tm_texasr |= TEXASR_FS; /* This loads the checkpointed FP/VEC state, if used */ tm_recheckpoint(¤t->thread, msr); @@ -698,10 +699,6 @@ int sys_rt_sigreturn(unsigned long r3, unsigned long r4, unsigned long r5, return 0; badframe: -#if DEBUG_SIG - printk("badframe in sys_rt_sigreturn, regs=%p uc=%p &uc->uc_mcontext=%p\n", - regs, uc, &uc->uc_mcontext); -#endif if (show_unhandled_signals) printk_ratelimited(regs->msr & MSR_64BIT ? fmt64 : fmt32, current->comm, current->pid, "rt_sigreturn", @@ -807,10 +804,6 @@ int handle_rt_signal64(int signr, struct k_sigaction *ka, siginfo_t *info, return 1; badframe: -#if DEBUG_SIG - printk("badframe in setup_rt_frame, regs=%p frame=%p newsp=%lx\n", - regs, frame, newsp); -#endif if (show_unhandled_signals) printk_ratelimited(regs->msr & MSR_64BIT ? fmt64 : fmt32, current->comm, current->pid, "setup_rt_frame", diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index ac2621af315..1007fb802e6 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -35,6 +35,8 @@ #include <asm/ptrace.h> #include <linux/atomic.h> #include <asm/irq.h> +#include <asm/hw_irq.h> +#include <asm/kvm_ppc.h> #include <asm/page.h> #include <asm/pgtable.h> #include <asm/prom.h> @@ -145,9 +147,9 @@ static irqreturn_t reschedule_action(int irq, void *data) return IRQ_HANDLED; } -static irqreturn_t call_function_single_action(int irq, void *data) +static irqreturn_t tick_broadcast_ipi_action(int irq, void *data) { - generic_smp_call_function_single_interrupt(); + tick_broadcast_ipi_handler(); return IRQ_HANDLED; } @@ -168,14 +170,14 @@ static irqreturn_t debug_ipi_action(int irq, void *data) static irq_handler_t smp_ipi_action[] = { [PPC_MSG_CALL_FUNCTION] = call_function_action, [PPC_MSG_RESCHEDULE] = reschedule_action, - [PPC_MSG_CALL_FUNC_SINGLE] = call_function_single_action, + [PPC_MSG_TICK_BROADCAST] = tick_broadcast_ipi_action, [PPC_MSG_DEBUGGER_BREAK] = debug_ipi_action, }; const char *smp_ipi_name[] = { [PPC_MSG_CALL_FUNCTION] = "ipi call function", [PPC_MSG_RESCHEDULE] = "ipi reschedule", - [PPC_MSG_CALL_FUNC_SINGLE] = "ipi call function single", + [PPC_MSG_TICK_BROADCAST] = "ipi tick-broadcast", [PPC_MSG_DEBUGGER_BREAK] = "ipi debugger", }; @@ -251,8 +253,8 @@ irqreturn_t smp_ipi_demux(void) generic_smp_call_function_interrupt(); if (all & IPI_MESSAGE(PPC_MSG_RESCHEDULE)) scheduler_ipi(); - if (all & IPI_MESSAGE(PPC_MSG_CALL_FUNC_SINGLE)) - generic_smp_call_function_single_interrupt(); + if (all & IPI_MESSAGE(PPC_MSG_TICK_BROADCAST)) + tick_broadcast_ipi_handler(); if (all & IPI_MESSAGE(PPC_MSG_DEBUGGER_BREAK)) debug_ipi_action(0, NULL); } while (info->messages); @@ -280,7 +282,7 @@ EXPORT_SYMBOL_GPL(smp_send_reschedule); void arch_send_call_function_single_ipi(int cpu) { - do_message_pass(cpu, PPC_MSG_CALL_FUNC_SINGLE); + do_message_pass(cpu, PPC_MSG_CALL_FUNCTION); } void arch_send_call_function_ipi_mask(const struct cpumask *mask) @@ -291,6 +293,16 @@ void arch_send_call_function_ipi_mask(const struct cpumask *mask) do_message_pass(cpu, PPC_MSG_CALL_FUNCTION); } +#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST +void tick_broadcast(const struct cpumask *mask) +{ + unsigned int cpu; + + for_each_cpu(cpu, mask) + do_message_pass(cpu, PPC_MSG_TICK_BROADCAST); +} +#endif + #if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC) void smp_send_debugger_break(void) { @@ -379,6 +391,7 @@ void smp_prepare_boot_cpu(void) #ifdef CONFIG_PPC64 paca[boot_cpuid].__current = current; #endif + set_numa_node(numa_cpu_lookup_table[boot_cpuid]); current_set[boot_cpuid] = task_thread_info(current); } @@ -446,38 +459,9 @@ int generic_check_cpu_restart(unsigned int cpu) return per_cpu(cpu_state, cpu) == CPU_UP_PREPARE; } -static atomic_t secondary_inhibit_count; - -/* - * Don't allow secondary CPU threads to come online - */ -void inhibit_secondary_onlining(void) -{ - /* - * This makes secondary_inhibit_count stable during cpu - * online/offline operations. - */ - get_online_cpus(); - - atomic_inc(&secondary_inhibit_count); - put_online_cpus(); -} -EXPORT_SYMBOL_GPL(inhibit_secondary_onlining); - -/* - * Allow secondary CPU threads to come online again - */ -void uninhibit_secondary_onlining(void) -{ - get_online_cpus(); - atomic_dec(&secondary_inhibit_count); - put_online_cpus(); -} -EXPORT_SYMBOL_GPL(uninhibit_secondary_onlining); - -static int secondaries_inhibited(void) +static bool secondaries_inhibited(void) { - return atomic_read(&secondary_inhibit_count); + return kvm_hv_mode_active(); } #else /* HOTPLUG_CPU */ @@ -506,7 +490,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle) * Don't allow secondary threads to come online if inhibited */ if (threads_per_core > 1 && secondaries_inhibited() && - cpu % threads_per_core != 0) + cpu_thread_in_subcore(cpu)) return -EBUSY; if (smp_ops == NULL || @@ -739,6 +723,12 @@ void start_secondary(void *unused) } traverse_core_siblings(cpu, true); + /* + * numa_node_id() works after this. + */ + set_numa_node(numa_cpu_lookup_table[cpu]); + set_numa_mem(local_memory_node(numa_cpu_lookup_table[cpu])); + smp_wmb(); notify_cpu_starting(cpu); set_cpu_online(cpu, true); @@ -755,6 +745,28 @@ int setup_profiling_timer(unsigned int multiplier) return 0; } +#ifdef CONFIG_SCHED_SMT +/* cpumask of CPUs with asymetric SMT dependancy */ +static int powerpc_smt_flags(void) +{ + int flags = SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES; + + if (cpu_has_feature(CPU_FTR_ASYM_SMT)) { + printk_once(KERN_INFO "Enabling Asymmetric SMT scheduling\n"); + flags |= SD_ASYM_PACKING; + } + return flags; +} +#endif + +static struct sched_domain_topology_level powerpc_topology[] = { +#ifdef CONFIG_SCHED_SMT + { cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) }, +#endif + { cpu_cpu_mask, SD_INIT_NAME(DIE) }, + { NULL, }, +}; + void __init smp_cpus_done(unsigned int max_cpus) { cpumask_var_t old_mask; @@ -779,15 +791,8 @@ void __init smp_cpus_done(unsigned int max_cpus) dump_numa_cpu_topology(); -} + set_sched_topology(powerpc_topology); -int arch_sd_sibling_asym_packing(void) -{ - if (cpu_has_feature(CPU_FTR_ASYM_SMT)) { - printk_once(KERN_INFO "Enabling Asymmetric SMT scheduling\n"); - return SD_ASYM_PACKING; - } - return 0; } #ifdef CONFIG_HOTPLUG_CPU diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index 97e1dc91768..67fd2fd2620 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -404,7 +404,7 @@ void ppc_enable_pmcs(void) } EXPORT_SYMBOL(ppc_enable_pmcs); -#define __SYSFS_SPRSETUP(NAME, ADDRESS, EXTRA) \ +#define __SYSFS_SPRSETUP_READ_WRITE(NAME, ADDRESS, EXTRA) \ static void read_##NAME(void *val) \ { \ *(unsigned long *)val = mfspr(ADDRESS); \ @@ -413,7 +413,9 @@ static void write_##NAME(void *val) \ { \ EXTRA; \ mtspr(ADDRESS, *(unsigned long *)val); \ -} \ +} + +#define __SYSFS_SPRSETUP_SHOW_STORE(NAME) \ static ssize_t show_##NAME(struct device *dev, \ struct device_attribute *attr, \ char *buf) \ @@ -436,10 +438,15 @@ 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, ) +#define SYSFS_PMCSETUP(NAME, ADDRESS) \ + __SYSFS_SPRSETUP_READ_WRITE(NAME, ADDRESS, ppc_enable_pmcs()) \ + __SYSFS_SPRSETUP_SHOW_STORE(NAME) +#define SYSFS_SPRSETUP(NAME, ADDRESS) \ + __SYSFS_SPRSETUP_READ_WRITE(NAME, ADDRESS, ) \ + __SYSFS_SPRSETUP_SHOW_STORE(NAME) + +#define SYSFS_SPRSETUP_SHOW_STORE(NAME) \ + __SYSFS_SPRSETUP_SHOW_STORE(NAME) /* Let's define all possible registers, we'll only hook up the ones * that are implemented on the current processor @@ -477,7 +484,6 @@ SYSFS_PMCSETUP(pmc8, SPRN_PMC8); SYSFS_PMCSETUP(mmcra, SPRN_MMCRA); SYSFS_SPRSETUP(purr, SPRN_PURR); SYSFS_SPRSETUP(spurr, SPRN_SPURR); -SYSFS_SPRSETUP(dscr, SPRN_DSCR); SYSFS_SPRSETUP(pir, SPRN_PIR); /* @@ -487,12 +493,27 @@ SYSFS_SPRSETUP(pir, SPRN_PIR); */ static DEVICE_ATTR(mmcra, 0600, show_mmcra, store_mmcra); static DEVICE_ATTR(spurr, 0400, show_spurr, NULL); -static DEVICE_ATTR(dscr, 0600, show_dscr, store_dscr); static DEVICE_ATTR(purr, 0400, show_purr, store_purr); static DEVICE_ATTR(pir, 0400, show_pir, NULL); -unsigned long dscr_default = 0; -EXPORT_SYMBOL(dscr_default); +static unsigned long dscr_default; + +static void read_dscr(void *val) +{ + *(unsigned long *)val = get_paca()->dscr_default; +} + +static void write_dscr(void *val) +{ + get_paca()->dscr_default = *(unsigned long *)val; + if (!current->thread.dscr_inherit) { + current->thread.dscr = *(unsigned long *)val; + mtspr(SPRN_DSCR, *(unsigned long *)val); + } +} + +SYSFS_SPRSETUP_SHOW_STORE(dscr); +static DEVICE_ATTR(dscr, 0600, show_dscr, store_dscr); static void add_write_permission_dev_attr(struct device_attribute *attr) { @@ -505,14 +526,6 @@ static ssize_t show_dscr_default(struct device *dev, return sprintf(buf, "%lx\n", dscr_default); } -static void update_dscr(void *dummy) -{ - if (!current->thread.dscr_inherit) { - current->thread.dscr = dscr_default; - mtspr(SPRN_DSCR, dscr_default); - } -} - static ssize_t __used store_dscr_default(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) @@ -525,7 +538,7 @@ static ssize_t __used store_dscr_default(struct device *dev, return -EINVAL; dscr_default = val; - on_each_cpu(update_dscr, NULL, 1); + on_each_cpu(write_dscr, &val, 1); return count; } @@ -975,7 +988,8 @@ static int __init topology_init(void) int cpu; register_nodes(); - register_cpu_notifier(&sysfs_cpu_nb); + + cpu_notifier_register_begin(); for_each_possible_cpu(cpu) { struct cpu *c = &per_cpu(cpu_devices, cpu); @@ -999,6 +1013,11 @@ static int __init topology_init(void) if (cpu_online(cpu)) register_cpu_online(cpu); } + + __register_cpu_notifier(&sysfs_cpu_nb); + + cpu_notifier_register_done(); + #ifdef CONFIG_PPC64 sysfs_create_dscr_default(); #endif /* CONFIG_PPC64 */ diff --git a/arch/powerpc/kernel/systbl.S b/arch/powerpc/kernel/systbl.S index 93219c34af3..895c50ca943 100644 --- a/arch/powerpc/kernel/systbl.S +++ b/arch/powerpc/kernel/systbl.S @@ -17,12 +17,12 @@ #include <asm/ppc_asm.h> #ifdef CONFIG_PPC64 -#define SYSCALL(func) .llong .sys_##func,.sys_##func -#define COMPAT_SYS(func) .llong .sys_##func,.compat_sys_##func -#define PPC_SYS(func) .llong .ppc_##func,.ppc_##func -#define OLDSYS(func) .llong .sys_ni_syscall,.sys_ni_syscall -#define SYS32ONLY(func) .llong .sys_ni_syscall,.compat_sys_##func -#define SYSX(f, f3264, f32) .llong .f,.f3264 +#define SYSCALL(func) .llong DOTSYM(sys_##func),DOTSYM(sys_##func) +#define COMPAT_SYS(func) .llong DOTSYM(sys_##func),DOTSYM(compat_sys_##func) +#define PPC_SYS(func) .llong DOTSYM(ppc_##func),DOTSYM(ppc_##func) +#define OLDSYS(func) .llong DOTSYM(sys_ni_syscall),DOTSYM(sys_ni_syscall) +#define SYS32ONLY(func) .llong DOTSYM(sys_ni_syscall),DOTSYM(compat_sys_##func) +#define SYSX(f, f3264, f32) .llong DOTSYM(f),DOTSYM(f3264) #else #define SYSCALL(func) .long sys_##func #define COMPAT_SYS(func) .long sys_##func @@ -36,6 +36,8 @@ #define PPC_SYS_SPU(func) PPC_SYS(func) #define SYSX_SPU(f, f3264, f32) SYSX(f, f3264, f32) +.section .rodata,"a" + #ifdef CONFIG_PPC64 #define sys_sigpending sys_ni_syscall #define sys_old_getrlimit sys_ni_syscall @@ -43,5 +45,7 @@ .p2align 3 #endif -_GLOBAL(sys_call_table) +.globl sys_call_table +sys_call_table: + #include <asm/systbl.h> diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index b3dab20acf3..9fff9cdcc51 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -42,6 +42,7 @@ #include <linux/timex.h> #include <linux/kernel_stat.h> #include <linux/time.h> +#include <linux/clockchips.h> #include <linux/init.h> #include <linux/profile.h> #include <linux/cpu.h> @@ -106,7 +107,7 @@ struct clock_event_device decrementer_clockevent = { .irq = 0, .set_next_event = decrementer_set_next_event, .set_mode = decrementer_set_mode, - .features = CLOCK_EVT_FEAT_ONESHOT, + .features = CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_C3STOP, }; EXPORT_SYMBOL(decrementer_clockevent); @@ -478,47 +479,13 @@ void arch_irq_work_raise(void) #endif /* CONFIG_IRQ_WORK */ -/* - * timer_interrupt - gets called when the decrementer overflows, - * with interrupts disabled. - */ -void timer_interrupt(struct pt_regs * regs) +void __timer_interrupt(void) { - struct pt_regs *old_regs; + struct pt_regs *regs = get_irq_regs(); u64 *next_tb = &__get_cpu_var(decrementers_next_tb); struct clock_event_device *evt = &__get_cpu_var(decrementers); u64 now; - /* Ensure a positive value is written to the decrementer, or else - * some CPUs will continue to take decrementer exceptions. - */ - set_dec(DECREMENTER_MAX); - - /* Some implementations of hotplug will get timer interrupts while - * offline, just ignore these and we also need to set - * decrementers_next_tb as MAX to make sure __check_irq_replay - * don't replay timer interrupt when return, otherwise we'll trap - * here infinitely :( - */ - if (!cpu_online(smp_processor_id())) { - *next_tb = ~(u64)0; - return; - } - - /* Conditionally hard-enable interrupts now that the DEC has been - * bumped to its maximum value - */ - may_hard_irq_enable(); - - -#if defined(CONFIG_PPC32) && defined(CONFIG_PMAC) - if (atomic_read(&ppc_n_lost_interrupts) != 0) - do_IRQ(regs); -#endif - - old_regs = set_irq_regs(regs); - irq_enter(); - trace_timer_interrupt_entry(regs); if (test_irq_work_pending()) { @@ -551,7 +518,48 @@ void timer_interrupt(struct pt_regs * regs) #endif trace_timer_interrupt_exit(regs); +} + +/* + * timer_interrupt - gets called when the decrementer overflows, + * with interrupts disabled. + */ +void timer_interrupt(struct pt_regs * regs) +{ + struct pt_regs *old_regs; + u64 *next_tb = &__get_cpu_var(decrementers_next_tb); + + /* Ensure a positive value is written to the decrementer, or else + * some CPUs will continue to take decrementer exceptions. + */ + set_dec(DECREMENTER_MAX); + + /* Some implementations of hotplug will get timer interrupts while + * offline, just ignore these and we also need to set + * decrementers_next_tb as MAX to make sure __check_irq_replay + * don't replay timer interrupt when return, otherwise we'll trap + * here infinitely :( + */ + if (!cpu_online(smp_processor_id())) { + *next_tb = ~(u64)0; + return; + } + /* Conditionally hard-enable interrupts now that the DEC has been + * bumped to its maximum value + */ + may_hard_irq_enable(); + + +#if defined(CONFIG_PPC32) && defined(CONFIG_PPC_PMAC) + if (atomic_read(&ppc_n_lost_interrupts) != 0) + do_IRQ(regs); +#endif + + old_regs = set_irq_regs(regs); + irq_enter(); + + __timer_interrupt(); irq_exit(); set_irq_regs(old_regs); } @@ -805,9 +813,6 @@ 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); @@ -825,6 +830,15 @@ static void decrementer_set_mode(enum clock_event_mode mode, decrementer_set_next_event(DECREMENTER_MAX, dev); } +/* Interrupt handler for the timer broadcast IPI */ +void tick_broadcast_ipi_handler(void) +{ + u64 *next_tb = &__get_cpu_var(decrementers_next_tb); + + *next_tb = get_tb_or_rtc(); + __timer_interrupt(); +} + static void register_decrementer_clockevent(int cpu) { struct clock_event_device *dec = &per_cpu(decrementers, cpu); @@ -928,6 +942,7 @@ void __init time_init(void) clocksource_init(); init_decrementer_clockevent(); + tick_setup_hrtimer_broadcast(); } diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S index ef47bcbd435..2a324f4cb1b 100644 --- a/arch/powerpc/kernel/tm.S +++ b/arch/powerpc/kernel/tm.S @@ -10,6 +10,7 @@ #include <asm/ppc-opcode.h> #include <asm/ptrace.h> #include <asm/reg.h> +#include <asm/bug.h> #ifdef CONFIG_VSX /* See fpu.S, this is borrowed from there */ @@ -41,7 +42,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX); \ /* Stack frame offsets for local variables. */ #define TM_FRAME_L0 TM_FRAME_SIZE-16 #define TM_FRAME_L1 TM_FRAME_SIZE-8 -#define STACK_PARAM(x) (48+((x)*8)) /* In order to access the TM SPRs, TM must be enabled. So, do so: */ @@ -78,12 +78,6 @@ _GLOBAL(tm_abort) TABORT(R3) blr - .section ".toc","aw" -DSCR_DEFAULT: - .tc dscr_default[TC],dscr_default - - .section ".text" - /* void tm_reclaim(struct thread_struct *thread, * unsigned long orig_msr, * uint8_t cause) @@ -108,12 +102,12 @@ _GLOBAL(tm_reclaim) mflr r0 stw r6, 8(r1) std r0, 16(r1) - std r2, 40(r1) + std r2, STK_GOT(r1) stdu r1, -TM_FRAME_SIZE(r1) /* We've a struct pt_regs at [r1+STACK_FRAME_OVERHEAD]. */ - std r3, STACK_PARAM(0)(r1) + std r3, STK_PARAM(R3)(r1) SAVE_NVGPRS(r1) /* We need to setup MSR for VSX register save instructions. Here we @@ -175,6 +169,13 @@ dont_backup_vec: stfd fr0,FPSTATE_FPSCR(r7) dont_backup_fp: + /* Do sanity check on MSR to make sure we are suspended */ + li r7, (MSR_TS_S)@higher + srdi r6, r14, 32 + and r6, r6, r7 +1: tdeqi r6, 0 + EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0 + /* The moment we treclaim, ALL of our GPRs will switch * to user register state. (FPRs, CCR etc. also!) * Use an sprg and a tm_scratch in the PACA to shuffle. @@ -202,7 +203,7 @@ dont_backup_fp: /* Now get some more GPRS free */ std r7, GPR7(r1) /* Temporary stash */ std r12, GPR12(r1) /* '' '' '' */ - ld r12, STACK_PARAM(0)(r1) /* Param 0, thread_struct * */ + ld r12, STK_PARAM(R3)(r1) /* Param 0, thread_struct * */ std r11, THREAD_TM_PPR(r12) /* Store PPR and free r11 */ @@ -289,11 +290,10 @@ dont_backup_fp: ld r0, 16(r1) mtcr r4 mtlr r0 - ld r2, 40(r1) + ld r2, STK_GOT(r1) - /* Load system default DSCR */ - ld r4, DSCR_DEFAULT@toc(r2) - ld r0, 0(r4) + /* Load CPU's default DSCR */ + ld r0, PACA_DSCR(r13) mtspr SPRN_DSCR, r0 blr @@ -307,12 +307,12 @@ dont_backup_fp: * Call with IRQs off, stacks get all out of sync for * some periods in here! */ -_GLOBAL(tm_recheckpoint) +_GLOBAL(__tm_recheckpoint) mfcr r5 mflr r0 stw r5, 8(r1) std r0, 16(r1) - std r2, 40(r1) + std r2, STK_GOT(r1) stdu r1, -TM_FRAME_SIZE(r1) /* We've a struct pt_regs at [r1+STACK_FRAME_OVERHEAD]. @@ -320,8 +320,6 @@ _GLOBAL(tm_recheckpoint) */ SAVE_NVGPRS(r1) - std r1, PACAR1(r13) - /* Load complete register state from ts_ckpt* registers */ addi r7, r3, PT_CKPT_REGS /* Thread's ckpt_regs */ @@ -385,12 +383,10 @@ restore_gprs: /* ******************** CR,LR,CCR,MSR ********** */ ld r4, _CTR(r7) ld r5, _LINK(r7) - ld r6, _CCR(r7) ld r8, _XER(r7) mtctr r4 mtlr r5 - mtcr r6 mtxer r8 /* ******************** TAR ******************** */ @@ -406,7 +402,8 @@ restore_gprs: li r4, 0 mtmsrd r4, 1 - REST_4GPRS(0, r7) /* GPR0-3 */ + REST_GPR(0, r7) /* GPR0 */ + REST_2GPRS(2, r7) /* GPR2-3 */ REST_GPR(4, r7) /* GPR4 */ REST_4GPRS(8, r7) /* GPR8-11 */ REST_2GPRS(12, r7) /* GPR12-13 */ @@ -418,6 +415,31 @@ restore_gprs: mtspr SPRN_DSCR, r5 mtspr SPRN_PPR, r6 + /* Do final sanity check on TEXASR to make sure FS is set. Do this + * here before we load up the userspace r1 so any bugs we hit will get + * a call chain */ + mfspr r5, SPRN_TEXASR + srdi r5, r5, 16 + li r6, (TEXASR_FS)@h + and r6, r6, r5 +1: tdeqi r6, 0 + EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0 + + /* Do final sanity check on MSR to make sure we are not transactional + * or suspended + */ + mfmsr r6 + li r5, (MSR_TS_MASK)@higher + srdi r6, r6, 32 + and r6, r6, r5 +1: tdnei r6, 0 + EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0 + + /* Restore CR */ + ld r6, _CCR(r7) + mtcr r6 + + REST_GPR(1, r7) /* GPR1 */ REST_GPR(5, r7) /* GPR5-7 */ REST_GPR(6, r7) ld r7, GPR7(r7) @@ -448,11 +470,10 @@ restore_gprs: ld r0, 16(r1) mtcr r4 mtlr r0 - ld r2, 40(r1) + ld r2, STK_GOT(r1) - /* Load system default DSCR */ - ld r4, DSCR_DEFAULT@toc(r2) - ld r0, 0(r4) + /* Load CPU's default DSCR */ + ld r0, PACA_DSCR(r13) mtspr SPRN_DSCR, r0 blr diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 33cd7a0b8e7..239f1cde3ff 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -295,6 +295,8 @@ long machine_check_early(struct pt_regs *regs) { long handled = 0; + __get_cpu_var(irq_stat).mce_exceptions++; + if (cur_cpu_spec && cur_cpu_spec->machine_check_early) handled = cur_cpu_spec->machine_check_early(regs); return handled; @@ -1379,8 +1381,9 @@ void facility_unavailable_exception(struct pt_regs *regs) if (!arch_irq_disabled_regs(regs)) local_irq_enable(); - pr_err("%sFacility '%s' unavailable, exception at 0x%lx, MSR=%lx\n", - hv ? "Hypervisor " : "", facility, regs->nip, regs->msr); + pr_err_ratelimited( + "%sFacility '%s' unavailable, exception at 0x%lx, MSR=%lx\n", + hv ? "Hypervisor " : "", facility, regs->nip, regs->msr); if (user_mode(regs)) { _exception(SIGILL, regs, ILL_ILLOPC, regs->nip); @@ -1867,6 +1870,7 @@ struct ppc_emulated ppc_emulated = { #ifdef CONFIG_PPC64 WARN_EMULATED_SETUP(mfdscr), WARN_EMULATED_SETUP(mtdscr), + WARN_EMULATED_SETUP(lq_stq), #endif }; diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c index a15837519dc..b7aa07279a6 100644 --- a/arch/powerpc/kernel/udbg.c +++ b/arch/powerpc/kernel/udbg.c @@ -62,8 +62,6 @@ void __init udbg_early_init(void) udbg_init_cpm(); #elif defined(CONFIG_PPC_EARLY_DEBUG_USBGECKO) udbg_init_usbgecko(); -#elif defined(CONFIG_PPC_EARLY_DEBUG_WSP) - udbg_init_wsp(); #elif defined(CONFIG_PPC_EARLY_DEBUG_MEMCONS) /* In memory console */ udbg_init_memcons(); diff --git a/arch/powerpc/kernel/udbg_16550.c b/arch/powerpc/kernel/udbg_16550.c index 75702e207b2..6e7c4923b5e 100644 --- a/arch/powerpc/kernel/udbg_16550.c +++ b/arch/powerpc/kernel/udbg_16550.c @@ -296,14 +296,3 @@ void __init udbg_init_40x_realmode(void) } #endif /* CONFIG_PPC_EARLY_DEBUG_40x */ - - -#ifdef CONFIG_PPC_EARLY_DEBUG_WSP - -void __init udbg_init_wsp(void) -{ - udbg_uart_init_mmio((void *)WSP_UART_VIRT, 1); - udbg_uart_setup(57600, 50000000); -} - -#endif /* CONFIG_PPC_EARLY_DEBUG_WSP */ diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index 094e45c16a1..ce74c335a6a 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -715,8 +715,8 @@ int vdso_getcpu_init(void) unsigned long cpu, node, val; /* - * SPRG3 contains the CPU in the bottom 16 bits and the NUMA node in - * the next 16 bits. The VDSO uses this to implement getcpu(). + * SPRG_VDSO contains the CPU in the bottom 16 bits and the NUMA node + * in the next 16 bits. The VDSO uses this to implement getcpu(). */ cpu = get_cpu(); WARN_ON_ONCE(cpu > 0xffff); @@ -725,8 +725,8 @@ int vdso_getcpu_init(void) WARN_ON_ONCE(node > 0xffff); val = (cpu & 0xfff) | ((node & 0xffff) << 16); - mtspr(SPRN_SPRG3, val); - get_paca()->sprg3 = val; + mtspr(SPRN_SPRG_VDSO_WRITE, val); + get_paca()->sprg_vdso = val; put_cpu(); diff --git a/arch/powerpc/kernel/vdso32/getcpu.S b/arch/powerpc/kernel/vdso32/getcpu.S index 47afd08c90f..23eb9a9441b 100644 --- a/arch/powerpc/kernel/vdso32/getcpu.S +++ b/arch/powerpc/kernel/vdso32/getcpu.S @@ -29,7 +29,7 @@ */ V_FUNCTION_BEGIN(__kernel_getcpu) .cfi_startproc - mfspr r5,SPRN_USPRG3 + mfspr r5,SPRN_SPRG_VDSO_READ cmpdi cr0,r3,0 cmpdi cr1,r4,0 clrlwi r6,r5,16 diff --git a/arch/powerpc/kernel/vdso32/vdso32_wrapper.S b/arch/powerpc/kernel/vdso32/vdso32_wrapper.S index 79683d0393f..6ac107ac402 100644 --- a/arch/powerpc/kernel/vdso32/vdso32_wrapper.S +++ b/arch/powerpc/kernel/vdso32/vdso32_wrapper.S @@ -6,7 +6,7 @@ .globl vdso32_start, vdso32_end .balign PAGE_SIZE vdso32_start: - .incbin "arch/powerpc/kernel/vdso32/vdso32.so" + .incbin "arch/powerpc/kernel/vdso32/vdso32.so.dbg" .balign PAGE_SIZE vdso32_end: diff --git a/arch/powerpc/kernel/vdso64/getcpu.S b/arch/powerpc/kernel/vdso64/getcpu.S index 47afd08c90f..23eb9a9441b 100644 --- a/arch/powerpc/kernel/vdso64/getcpu.S +++ b/arch/powerpc/kernel/vdso64/getcpu.S @@ -29,7 +29,7 @@ */ V_FUNCTION_BEGIN(__kernel_getcpu) .cfi_startproc - mfspr r5,SPRN_USPRG3 + mfspr r5,SPRN_SPRG_VDSO_READ cmpdi cr0,r3,0 cmpdi cr1,r4,0 clrlwi r6,r5,16 diff --git a/arch/powerpc/kernel/vdso64/vdso64_wrapper.S b/arch/powerpc/kernel/vdso64/vdso64_wrapper.S index 8df9e246300..df60fca6a13 100644 --- a/arch/powerpc/kernel/vdso64/vdso64_wrapper.S +++ b/arch/powerpc/kernel/vdso64/vdso64_wrapper.S @@ -6,7 +6,7 @@ .globl vdso64_start, vdso64_end .balign PAGE_SIZE vdso64_start: - .incbin "arch/powerpc/kernel/vdso64/vdso64.so" + .incbin "arch/powerpc/kernel/vdso64/vdso64.so.dbg" .balign PAGE_SIZE vdso64_end: diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c index 826d8bd9e52..904c66128fa 100644 --- a/arch/powerpc/kernel/vio.c +++ b/arch/powerpc/kernel/vio.c @@ -1432,7 +1432,8 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node) /* needed to ensure proper operation of coherent allocations * later, in case driver doesn't set it explicitly */ - dma_coerce_mask_and_coherent(&viodev->dev, DMA_BIT_MASK(64)); + viodev->dev.coherent_dma_mask = DMA_BIT_MASK(64); + viodev->dev.dma_mask = &viodev->dev.coherent_dma_mask; } /* register with generic device framework */ |