diff options
Diffstat (limited to 'arch/powerpc/kernel')
43 files changed, 1657 insertions, 570 deletions
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 3bb2a3e6a33..e8b981897d4 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -38,11 +38,14 @@ obj-$(CONFIG_PPC64) += setup_64.o sys_ppc32.o \ paca.o nvram_64.o firmware.o obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_ppc970.o cpu_setup_pa6t.o +obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_power7.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 +obj-$(CONFIG_PPC_P7_NAP) += idle_power7.o obj-$(CONFIG_PPC_OF) += of_platform.o prom_parse.o obj-$(CONFIG_PPC_CLOCK) += clock.o procfs-y := proc_powerpc.o @@ -75,7 +78,6 @@ obj-$(CONFIG_PPC_FSL_BOOK3E) += cpu_setup_fsl_booke.o dbell.o obj-$(CONFIG_PPC_BOOK3E_64) += dbell.o extra-y := head_$(CONFIG_WORD_SIZE).o -extra-$(CONFIG_PPC_BOOK3E_32) := head_new_booke.o extra-$(CONFIG_40x) := head_40x.o extra-$(CONFIG_44x) := head_44x.o extra-$(CONFIG_FSL_BOOKE) := head_fsl_booke.o @@ -103,8 +105,11 @@ obj-$(CONFIG_KEXEC) += machine_kexec.o crash.o \ obj-$(CONFIG_AUDIT) += audit.o obj64-$(CONFIG_AUDIT) += compat_audit.o +obj-$(CONFIG_PPC_IO_WORKAROUNDS) += io-workarounds.o + obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o +obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o obj-$(CONFIG_PERF_EVENTS) += perf_callchain.o obj-$(CONFIG_PPC_PERF_CTRS) += perf_event.o diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 23e6a93145a..36e1c8a29be 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -74,6 +74,7 @@ int main(void) DEFINE(AUDITCONTEXT, offsetof(struct task_struct, audit_context)); DEFINE(SIGSEGV, SIGSEGV); DEFINE(NMI_MASK, NMI_MASK); + DEFINE(THREAD_DSCR, offsetof(struct thread_struct, dscr)); #else DEFINE(THREAD_INFO, offsetof(struct task_struct, stack)); #endif /* CONFIG_PPC64 */ @@ -395,6 +396,7 @@ int main(void) DEFINE(VCPU_HOST_STACK, offsetof(struct kvm_vcpu, arch.host_stack)); DEFINE(VCPU_HOST_PID, offsetof(struct kvm_vcpu, arch.host_pid)); DEFINE(VCPU_GPRS, offsetof(struct kvm_vcpu, arch.gpr)); + DEFINE(VCPU_VRSAVE, offsetof(struct kvm_vcpu, arch.vrsave)); DEFINE(VCPU_SPRG4, offsetof(struct kvm_vcpu, arch.sprg4)); DEFINE(VCPU_SPRG5, offsetof(struct kvm_vcpu, arch.sprg5)); DEFINE(VCPU_SPRG6, offsetof(struct kvm_vcpu, arch.sprg6)); diff --git a/arch/powerpc/kernel/cpu_setup_a2.S b/arch/powerpc/kernel/cpu_setup_a2.S new file mode 100644 index 00000000000..7f818feaa7a --- /dev/null +++ b/arch/powerpc/kernel/cpu_setup_a2.S @@ -0,0 +1,114 @@ +/* + * 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_WSP_COPRO + /* Make sure ACOP starts out as zero */ + li r3,0 + mtspr SPRN_ACOP,r3 + + /* 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 +#endif /* CONFIG_PPC_WSP_COPRO */ + + /* 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(0,0,0) +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 913611105c1..8053db02b85 100644 --- a/arch/powerpc/kernel/cpu_setup_fsl_booke.S +++ b/arch/powerpc/kernel/cpu_setup_fsl_booke.S @@ -88,6 +88,9 @@ _GLOBAL(__setup_cpu_e5500) bl __e500_dcache_setup #ifdef CONFIG_PPC_BOOK3E_64 bl .__setup_base_ivors + bl .setup_perfmon_ivor + bl .setup_doorbell_ivors + bl .setup_ehv_ivors #else bl __setup_e500mc_ivors #endif diff --git a/arch/powerpc/kernel/cpu_setup_power7.S b/arch/powerpc/kernel/cpu_setup_power7.S new file mode 100644 index 00000000000..4f9a93fcfe0 --- /dev/null +++ b/arch/powerpc/kernel/cpu_setup_power7.S @@ -0,0 +1,91 @@ +/* + * This file contains low level CPU setup functions. + * Copyright (C) 2003 Benjamin Herrenschmidt (benh@kernel.crashing.org) + * + * 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/processor.h> +#include <asm/page.h> +#include <asm/cputable.h> +#include <asm/ppc_asm.h> +#include <asm/asm-offsets.h> +#include <asm/cache.h> + +/* Entry: r3 = crap, r4 = ptr to cputable entry + * + * Note that we can be called twice for pseudo-PVRs + */ +_GLOBAL(__setup_cpu_power7) + mflr r11 + bl __init_hvmode_206 + mtlr r11 + beqlr + li r0,0 + mtspr SPRN_LPID,r0 + bl __init_LPCR + bl __init_TLB + mtlr r11 + blr + +_GLOBAL(__restore_cpu_power7) + mflr r11 + mfmsr r3 + rldicl. r0,r3,4,63 + beqlr + li r0,0 + mtspr SPRN_LPID,r0 + bl __init_LPCR + bl __init_TLB + mtlr r11 + blr + +__init_hvmode_206: + /* Disable CPU_FTR_HVMODE_206 and exit if MSR:HV is not set */ + mfmsr r3 + rldicl. r0,r3,4,63 + bnelr + ld r5,CPU_SPEC_FEATURES(r4) + LOAD_REG_IMMEDIATE(r6,CPU_FTR_HVMODE_206) + xor r5,r5,r6 + std r5,CPU_SPEC_FEATURES(r4) + blr + +__init_LPCR: + /* Setup a sane LPCR: + * + * LPES = 0b01 (HSRR0/1 used for 0x500) + * PECE = 0b111 + * DPFD = 4 + * + * Other bits untouched for now + */ + mfspr r3,SPRN_LPCR + ori r3,r3,(LPCR_LPES0|LPCR_LPES1) + xori r3,r3, LPCR_LPES0 + ori r3,r3,(LPCR_PECE0|LPCR_PECE1|LPCR_PECE2) + li r5,7 + sldi r5,r5,LPCR_DPFD_SH + andc r3,r3,r5 + li r5,4 + sldi r5,r5,LPCR_DPFD_SH + or r3,r3,r5 + mtspr SPRN_LPCR,r3 + isync + blr + +__init_TLB: + /* Clear the TLB */ + li r6,128 + mtctr r6 + li r7,0xc00 /* IS field = 0b11 */ + ptesync +2: tlbiel r7 + addi r7,r7,0x1000 + bdnz 2b + ptesync +1: blr diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index b9602ee06de..9fb933248ab 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -62,10 +62,12 @@ extern void __setup_cpu_745x(unsigned long offset, struct cpu_spec* spec); extern void __setup_cpu_ppc970(unsigned long offset, struct cpu_spec* spec); extern void __setup_cpu_ppc970MP(unsigned long offset, struct cpu_spec* spec); extern void __setup_cpu_pa6t(unsigned long offset, struct cpu_spec* spec); +extern void __setup_cpu_a2(unsigned long offset, struct cpu_spec* spec); extern void __restore_cpu_pa6t(void); extern void __restore_cpu_ppc970(void); extern void __setup_cpu_power7(unsigned long offset, struct cpu_spec* spec); extern void __restore_cpu_power7(void); +extern void __restore_cpu_a2(void); #endif /* CONFIG_PPC64 */ #if defined(CONFIG_E500) extern void __setup_cpu_e5500(unsigned long offset, struct cpu_spec* spec); @@ -199,7 +201,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "POWER4 (gp)", .cpu_features = CPU_FTRS_POWER4, .cpu_user_features = COMMON_USER_POWER4, - .mmu_features = MMU_FTR_HPTE_TABLE, + .mmu_features = MMU_FTRS_POWER4, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, @@ -214,7 +216,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "POWER4+ (gq)", .cpu_features = CPU_FTRS_POWER4, .cpu_user_features = COMMON_USER_POWER4, - .mmu_features = MMU_FTR_HPTE_TABLE, + .mmu_features = MMU_FTRS_POWER4, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, @@ -230,7 +232,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_PPC970, .cpu_user_features = COMMON_USER_POWER4 | PPC_FEATURE_HAS_ALTIVEC_COMP, - .mmu_features = MMU_FTR_HPTE_TABLE, + .mmu_features = MMU_FTRS_PPC970, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, @@ -248,7 +250,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_PPC970, .cpu_user_features = COMMON_USER_POWER4 | PPC_FEATURE_HAS_ALTIVEC_COMP, - .mmu_features = MMU_FTR_HPTE_TABLE, + .mmu_features = MMU_FTRS_PPC970, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, @@ -284,7 +286,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_PPC970, .cpu_user_features = COMMON_USER_POWER4 | PPC_FEATURE_HAS_ALTIVEC_COMP, - .mmu_features = MMU_FTR_HPTE_TABLE, + .mmu_features = MMU_FTRS_PPC970, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, @@ -302,7 +304,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_PPC970, .cpu_user_features = COMMON_USER_POWER4 | PPC_FEATURE_HAS_ALTIVEC_COMP, - .mmu_features = MMU_FTR_HPTE_TABLE, + .mmu_features = MMU_FTRS_PPC970, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, @@ -318,7 +320,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "POWER5 (gr)", .cpu_features = CPU_FTRS_POWER5, .cpu_user_features = COMMON_USER_POWER5, - .mmu_features = MMU_FTR_HPTE_TABLE, + .mmu_features = MMU_FTRS_POWER5, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 6, @@ -338,7 +340,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "POWER5+ (gs)", .cpu_features = CPU_FTRS_POWER5, .cpu_user_features = COMMON_USER_POWER5_PLUS, - .mmu_features = MMU_FTR_HPTE_TABLE, + .mmu_features = MMU_FTRS_POWER5, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 6, @@ -354,7 +356,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "POWER5+ (gs)", .cpu_features = CPU_FTRS_POWER5, .cpu_user_features = COMMON_USER_POWER5_PLUS, - .mmu_features = MMU_FTR_HPTE_TABLE, + .mmu_features = MMU_FTRS_POWER5, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 6, @@ -371,7 +373,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "POWER5+", .cpu_features = CPU_FTRS_POWER5, .cpu_user_features = COMMON_USER_POWER5_PLUS, - .mmu_features = MMU_FTR_HPTE_TABLE, + .mmu_features = MMU_FTRS_POWER5, .icache_bsize = 128, .dcache_bsize = 128, .oprofile_cpu_type = "ppc64/ibm-compat-v1", @@ -385,7 +387,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_POWER6, .cpu_user_features = COMMON_USER_POWER6 | PPC_FEATURE_POWER6_EXT, - .mmu_features = MMU_FTR_HPTE_TABLE, + .mmu_features = MMU_FTRS_POWER6, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 6, @@ -404,7 +406,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "POWER6 (architected)", .cpu_features = CPU_FTRS_POWER6, .cpu_user_features = COMMON_USER_POWER6, - .mmu_features = MMU_FTR_HPTE_TABLE, + .mmu_features = MMU_FTRS_POWER6, .icache_bsize = 128, .dcache_bsize = 128, .oprofile_cpu_type = "ppc64/ibm-compat-v1", @@ -417,12 +419,13 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "POWER7 (architected)", .cpu_features = CPU_FTRS_POWER7, .cpu_user_features = COMMON_USER_POWER7, - .mmu_features = MMU_FTR_HPTE_TABLE | - MMU_FTR_TLBIE_206, + .mmu_features = MMU_FTRS_POWER7, .icache_bsize = 128, .dcache_bsize = 128, .oprofile_type = PPC_OPROFILE_POWER4, .oprofile_cpu_type = "ppc64/ibm-compat-v1", + .cpu_setup = __setup_cpu_power7, + .cpu_restore = __restore_cpu_power7, .platform = "power7", }, { /* Power7 */ @@ -431,14 +434,15 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "POWER7 (raw)", .cpu_features = CPU_FTRS_POWER7, .cpu_user_features = COMMON_USER_POWER7, - .mmu_features = MMU_FTR_HPTE_TABLE | - MMU_FTR_TLBIE_206, + .mmu_features = MMU_FTRS_POWER7, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 6, .pmc_type = PPC_PMC_IBM, .oprofile_cpu_type = "ppc64/power7", .oprofile_type = PPC_OPROFILE_POWER4, + .cpu_setup = __setup_cpu_power7, + .cpu_restore = __restore_cpu_power7, .platform = "power7", }, { /* Power7+ */ @@ -447,14 +451,15 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "POWER7+ (raw)", .cpu_features = CPU_FTRS_POWER7, .cpu_user_features = COMMON_USER_POWER7, - .mmu_features = MMU_FTR_HPTE_TABLE | - MMU_FTR_TLBIE_206, + .mmu_features = MMU_FTRS_POWER7, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 6, .pmc_type = PPC_PMC_IBM, .oprofile_cpu_type = "ppc64/power7", .oprofile_type = PPC_OPROFILE_POWER4, + .cpu_setup = __setup_cpu_power7, + .cpu_restore = __restore_cpu_power7, .platform = "power7+", }, { /* Cell Broadband Engine */ @@ -465,7 +470,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_user_features = COMMON_USER_PPC64 | PPC_FEATURE_CELL | PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_SMT, - .mmu_features = MMU_FTR_HPTE_TABLE, + .mmu_features = MMU_FTRS_CELL, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 4, @@ -480,7 +485,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "PA6T", .cpu_features = CPU_FTRS_PA6T, .cpu_user_features = COMMON_USER_PA6T, - .mmu_features = MMU_FTR_HPTE_TABLE, + .mmu_features = MMU_FTRS_PA6T, .icache_bsize = 64, .dcache_bsize = 64, .num_pmcs = 6, @@ -497,7 +502,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "POWER4 (compatible)", .cpu_features = CPU_FTRS_COMPATIBLE, .cpu_user_features = COMMON_USER_PPC64, - .mmu_features = MMU_FTR_HPTE_TABLE, + .mmu_features = MMU_FTRS_DEFAULT_HPTE_ARCH_V2, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 6, @@ -1974,7 +1979,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .pvr_value = 0x80240000, .cpu_name = "e5500", .cpu_features = CPU_FTRS_E5500, - .cpu_user_features = COMMON_USER_BOOKE, + .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, .mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS | MMU_FTR_USE_TLBILX, .icache_bsize = 64, @@ -2005,7 +2010,22 @@ static struct cpu_spec __initdata cpu_specs[] = { #endif /* CONFIG_PPC32 */ #endif /* CONFIG_E500 */ -#ifdef CONFIG_PPC_BOOK3E_64 +#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 */ @@ -2026,7 +2046,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .machine_check = machine_check_generic, .platform = "power6", }, -#endif +#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 5b5e1f002a8..4e6ee944495 100644 --- a/arch/powerpc/kernel/crash.c +++ b/arch/powerpc/kernel/crash.c @@ -64,9 +64,9 @@ void crash_ipi_callback(struct pt_regs *regs) return; hard_irq_disable(); - if (!cpu_isset(cpu, cpus_in_crash)) + if (!cpumask_test_cpu(cpu, &cpus_in_crash)) crash_save_cpu(regs, cpu); - cpu_set(cpu, cpus_in_crash); + cpumask_set_cpu(cpu, &cpus_in_crash); /* * Entered via soft-reset - could be the kdump @@ -77,8 +77,8 @@ void crash_ipi_callback(struct pt_regs *regs) * Tell the kexec CPU that entered via soft-reset and ready * to go down. */ - if (cpu_isset(cpu, cpus_in_sr)) { - cpu_clear(cpu, cpus_in_sr); + if (cpumask_test_cpu(cpu, &cpus_in_sr)) { + cpumask_clear_cpu(cpu, &cpus_in_sr); atomic_inc(&enter_on_soft_reset); } @@ -87,7 +87,7 @@ void crash_ipi_callback(struct pt_regs *regs) * This barrier is needed to make sure that all CPUs are stopped. * If not, soft-reset will be invoked to bring other CPUs. */ - while (!cpu_isset(crashing_cpu, cpus_in_crash)) + while (!cpumask_test_cpu(crashing_cpu, &cpus_in_crash)) cpu_relax(); if (ppc_md.kexec_cpu_down) @@ -109,7 +109,7 @@ static void crash_soft_reset_check(int cpu) { unsigned int ncpus = num_online_cpus() - 1;/* Excluding the panic cpu */ - cpu_clear(cpu, cpus_in_sr); + cpumask_clear_cpu(cpu, &cpus_in_sr); while (atomic_read(&enter_on_soft_reset) != ncpus) cpu_relax(); } @@ -132,7 +132,7 @@ static void crash_kexec_prepare_cpus(int cpu) */ printk(KERN_EMERG "Sending IPI to other cpus...\n"); msecs = 10000; - while ((cpus_weight(cpus_in_crash) < ncpus) && (--msecs > 0)) { + while ((cpumask_weight(&cpus_in_crash) < ncpus) && (--msecs > 0)) { cpu_relax(); mdelay(1); } @@ -144,52 +144,24 @@ static void crash_kexec_prepare_cpus(int cpu) * user to do soft reset such that we get all. * Soft-reset will be used until better mechanism is implemented. */ - if (cpus_weight(cpus_in_crash) < ncpus) { + if (cpumask_weight(&cpus_in_crash) < ncpus) { printk(KERN_EMERG "done waiting: %d cpu(s) not responding\n", - ncpus - cpus_weight(cpus_in_crash)); + ncpus - cpumask_weight(&cpus_in_crash)); printk(KERN_EMERG "Activate soft-reset to stop other cpu(s)\n"); - cpus_in_sr = CPU_MASK_NONE; + cpumask_clear(&cpus_in_sr); atomic_set(&enter_on_soft_reset, 0); - while (cpus_weight(cpus_in_crash) < ncpus) + while (cpumask_weight(&cpus_in_crash) < ncpus) cpu_relax(); } /* * Make sure all CPUs are entered via soft-reset if the kdump is * invoked using soft-reset. */ - if (cpu_isset(cpu, cpus_in_sr)) + if (cpumask_test_cpu(cpu, &cpus_in_sr)) crash_soft_reset_check(cpu); /* Leave the IPI callback set */ } -/* wait for all the CPUs to hit real mode but timeout if they don't come in */ -#ifdef CONFIG_PPC_STD_MMU_64 -static void crash_kexec_wait_realmode(int cpu) -{ - unsigned int msecs; - int i; - - msecs = 10000; - for (i=0; i < NR_CPUS && msecs > 0; i++) { - if (i == cpu) - continue; - - while (paca[i].kexec_state < KEXEC_STATE_REAL_MODE) { - barrier(); - if (!cpu_possible(i)) { - break; - } - if (!cpu_online(i)) { - break; - } - msecs--; - mdelay(1); - } - } - mb(); -} -#endif /* CONFIG_PPC_STD_MMU_64 */ - /* * This function will be called by secondary cpus or by kexec cpu * if soft-reset is activated to stop some CPUs. @@ -210,7 +182,7 @@ void crash_kexec_secondary(struct pt_regs *regs) * exited using 'x'(exit and recover) or * kexec_should_crash() failed for all running tasks. */ - cpu_clear(cpu, cpus_in_sr); + cpumask_clear_cpu(cpu, &cpus_in_sr); local_irq_restore(flags); return; } @@ -224,7 +196,7 @@ void crash_kexec_secondary(struct pt_regs *regs) * then start kexec boot. */ crash_soft_reset_check(cpu); - cpu_set(crashing_cpu, cpus_in_crash); + cpumask_set_cpu(crashing_cpu, &cpus_in_crash); if (ppc_md.kexec_cpu_down) ppc_md.kexec_cpu_down(1, 0); machine_kexec(kexec_crash_image); @@ -234,7 +206,6 @@ void crash_kexec_secondary(struct pt_regs *regs) } #else /* ! CONFIG_SMP */ -static inline void crash_kexec_wait_realmode(int cpu) {} static void crash_kexec_prepare_cpus(int cpu) { @@ -253,10 +224,40 @@ static void crash_kexec_prepare_cpus(int cpu) void crash_kexec_secondary(struct pt_regs *regs) { - cpus_in_sr = CPU_MASK_NONE; + cpumask_clear(&cpus_in_sr); } #endif /* CONFIG_SMP */ +/* wait for all the CPUs to hit real mode but timeout if they don't come in */ +#if defined(CONFIG_SMP) && defined(CONFIG_PPC_STD_MMU_64) +static void crash_kexec_wait_realmode(int cpu) +{ + unsigned int msecs; + int i; + + msecs = 10000; + for (i=0; i < nr_cpu_ids && msecs > 0; i++) { + if (i == cpu) + continue; + + while (paca[i].kexec_state < KEXEC_STATE_REAL_MODE) { + barrier(); + if (!cpu_possible(i)) { + break; + } + if (!cpu_online(i)) { + break; + } + msecs--; + mdelay(1); + } + } + mb(); +} +#else +static inline void crash_kexec_wait_realmode(int cpu) {} +#endif /* CONFIG_SMP && CONFIG_PPC_STD_MMU_64 */ + /* * Register a function to be called on shutdown. Only use this if you * can't reset your device in the second kernel. @@ -345,7 +346,7 @@ void default_machine_crash_shutdown(struct pt_regs *regs) crashing_cpu = smp_processor_id(); crash_save_cpu(regs, crashing_cpu); crash_kexec_prepare_cpus(crashing_cpu); - cpu_set(crashing_cpu, cpus_in_crash); + cpumask_set_cpu(crashing_cpu, &cpus_in_crash); crash_kexec_wait_realmode(crashing_cpu); machine_kexec_mask_interrupts(); diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c index 3307a52d797..2cc451aaaca 100644 --- a/arch/powerpc/kernel/dbell.c +++ b/arch/powerpc/kernel/dbell.c @@ -13,84 +13,35 @@ #include <linux/kernel.h> #include <linux/smp.h> #include <linux/threads.h> -#include <linux/percpu.h> +#include <linux/hardirq.h> #include <asm/dbell.h> #include <asm/irq_regs.h> #ifdef CONFIG_SMP -struct doorbell_cpu_info { - unsigned long messages; /* current messages bits */ - unsigned int tag; /* tag value */ -}; - -static DEFINE_PER_CPU(struct doorbell_cpu_info, doorbell_cpu_info); - void doorbell_setup_this_cpu(void) { - struct doorbell_cpu_info *info = &__get_cpu_var(doorbell_cpu_info); + unsigned long tag = mfspr(SPRN_PIR) & 0x3fff; - info->messages = 0; - info->tag = mfspr(SPRN_PIR) & 0x3fff; + smp_muxed_ipi_set_data(smp_processor_id(), tag); } -void doorbell_message_pass(int target, int msg) +void doorbell_cause_ipi(int cpu, unsigned long data) { - struct doorbell_cpu_info *info; - int i; - - if (target < NR_CPUS) { - info = &per_cpu(doorbell_cpu_info, target); - set_bit(msg, &info->messages); - ppc_msgsnd(PPC_DBELL, 0, info->tag); - } - else if (target == MSG_ALL_BUT_SELF) { - for_each_online_cpu(i) { - if (i == smp_processor_id()) - continue; - info = &per_cpu(doorbell_cpu_info, i); - set_bit(msg, &info->messages); - ppc_msgsnd(PPC_DBELL, 0, info->tag); - } - } - else { /* target == MSG_ALL */ - for_each_online_cpu(i) { - info = &per_cpu(doorbell_cpu_info, i); - set_bit(msg, &info->messages); - } - ppc_msgsnd(PPC_DBELL, PPC_DBELL_MSG_BRDCAST, 0); - } + ppc_msgsnd(PPC_DBELL, 0, data); } void doorbell_exception(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); - struct doorbell_cpu_info *info = &__get_cpu_var(doorbell_cpu_info); - int msg; - /* Warning: regs can be NULL when called from irq enable */ + irq_enter(); - if (!info->messages || (num_online_cpus() < 2)) - goto out; + smp_ipi_demux(); - for (msg = 0; msg < 4; msg++) - if (test_and_clear_bit(msg, &info->messages)) - smp_message_recv(msg); - -out: + irq_exit(); set_irq_regs(old_regs); } - -void doorbell_check_self(void) -{ - struct doorbell_cpu_info *info = &__get_cpu_var(doorbell_cpu_info); - - if (!info->messages) - return; - - ppc_msgsnd(PPC_DBELL, 0, info->tag); -} - #else /* CONFIG_SMP */ void doorbell_exception(struct pt_regs *regs) { diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index d82878c4daa..d834425186a 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -421,6 +421,12 @@ 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 @@ -462,10 +468,10 @@ BEGIN_FTR_SECTION FTR_SECTION_ELSE_NESTED(95) clrrdi r6,r8,40 /* get its 1T ESID */ clrrdi r9,r1,40 /* get current sp 1T ESID */ - ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_1T_SEGMENT, 95) + ALT_MMU_FTR_SECTION_END_NESTED_IFCLR(MMU_FTR_1T_SEGMENT, 95) FTR_SECTION_ELSE b 2f -ALT_FTR_SECTION_END_IFSET(CPU_FTR_SLB) +ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_SLB) clrldi. r0,r6,2 /* is new ESID c00000000? */ cmpd cr1,r6,r9 /* or is new ESID the same as current ESID? */ cror eq,4*cr1+eq,eq @@ -479,7 +485,7 @@ BEGIN_FTR_SECTION li r9,MMU_SEGSIZE_1T /* insert B field */ oris r6,r6,(MMU_SEGSIZE_1T << SLBIE_SSIZE_SHIFT)@h rldimi r7,r9,SLB_VSID_SSIZE_SHIFT,0 -END_FTR_SECTION_IFSET(CPU_FTR_1T_SEGMENT) +END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) /* Update the last bolted SLB. No write barriers are needed * here, provided we only update the current CPU's SLB shadow @@ -491,7 +497,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_1T_SEGMENT) std r7,SLBSHADOW_STACKVSID(r9) /* Save VSID */ std r0,SLBSHADOW_STACKESID(r9) /* Save ESID */ - /* No need to check for CPU_FTR_NO_SLBIE_B here, since when + /* No need to check for MMU_FTR_NO_SLBIE_B here, since when * we have 1TB segments, the only CPUs known to have the errata * only support less than 1TB of system memory and we'll never * actually hit this code path. @@ -522,6 +528,15 @@ BEGIN_FTR_SECTION mtspr SPRN_VRSAVE,r0 /* if G4, restore VRSAVE reg */ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) #endif /* CONFIG_ALTIVEC */ +#ifdef CONFIG_PPC64 +BEGIN_FTR_SECTION + ld r0,THREAD_DSCR(r4) + cmpd r0,r25 + beq 1f + mtspr SPRN_DSCR,r0 +1: +END_FTR_SECTION_IFSET(CPU_FTR_DSCR) +#endif /* r3-r13 are destroyed -- Cort */ REST_8GPRS(14, r1) @@ -838,7 +853,7 @@ _GLOBAL(enter_rtas) _STATIC(rtas_return_loc) /* relocation is off at this point */ - mfspr r4,SPRN_SPRG_PACA /* Get PACA */ + GET_PACA(r4) clrldi r4,r4,2 /* convert to realmode address */ bcl 20,31,$+4 @@ -869,7 +884,7 @@ _STATIC(rtas_restore_regs) REST_8GPRS(14, r1) /* Restore the non-volatiles */ REST_10GPRS(22, r1) /* ditto */ - mfspr r13,SPRN_SPRG_PACA + GET_PACA(r13) ld r4,_CCR(r1) mtcr r4 diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index 9651acc3504..d24d4400cc7 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -17,6 +17,7 @@ #include <asm/cputable.h> #include <asm/setup.h> #include <asm/thread_info.h> +#include <asm/reg_a2.h> #include <asm/exception-64e.h> #include <asm/bug.h> #include <asm/irqflags.h> @@ -252,9 +253,6 @@ exception_marker: .balign 0x1000 .globl interrupt_base_book3e interrupt_base_book3e: /* fake trap */ - /* Note: If real debug exceptions are supported by the HW, the vector - * below will have to be patched up to point to an appropriate handler - */ EXCEPTION_STUB(0x000, machine_check) /* 0x0200 */ EXCEPTION_STUB(0x020, critical_input) /* 0x0580 */ EXCEPTION_STUB(0x040, debug_crit) /* 0x0d00 */ @@ -271,8 +269,13 @@ interrupt_base_book3e: /* fake trap */ EXCEPTION_STUB(0x1a0, watchdog) /* 0x09f0 */ EXCEPTION_STUB(0x1c0, data_tlb_miss) EXCEPTION_STUB(0x1e0, instruction_tlb_miss) + EXCEPTION_STUB(0x260, perfmon) EXCEPTION_STUB(0x280, doorbell) EXCEPTION_STUB(0x2a0, doorbell_crit) + EXCEPTION_STUB(0x2c0, guest_doorbell) + EXCEPTION_STUB(0x2e0, guest_doorbell_crit) + EXCEPTION_STUB(0x300, hypercall) + EXCEPTION_STUB(0x320, ehpriv) .globl interrupt_end_book3e interrupt_end_book3e: @@ -454,6 +457,70 @@ interrupt_end_book3e: kernel_dbg_exc: b . /* NYI */ +/* Debug exception as a debug interrupt*/ + START_EXCEPTION(debug_debug); + DBG_EXCEPTION_PROLOG(0xd00, PROLOG_ADDITION_2REGS) + + /* + * If there is a single step or branch-taken exception in an + * exception entry sequence, it was probably meant to apply to + * the code where the exception occurred (since exception entry + * doesn't turn off DE automatically). We simulate the effect + * of turning off DE on entry to an exception handler by turning + * off DE in the DSRR1 value and clearing the debug status. + */ + + mfspr r14,SPRN_DBSR /* check single-step/branch taken */ + andis. r15,r14,DBSR_IC@h + beq+ 1f + + LOAD_REG_IMMEDIATE(r14,interrupt_base_book3e) + LOAD_REG_IMMEDIATE(r15,interrupt_end_book3e) + cmpld cr0,r10,r14 + cmpld cr1,r10,r15 + blt+ cr0,1f + bge+ cr1,1f + + /* here it looks like we got an inappropriate debug exception. */ + lis r14,DBSR_IC@h /* clear the IC event */ + rlwinm r11,r11,0,~MSR_DE /* clear DE in the DSRR1 value */ + mtspr SPRN_DBSR,r14 + mtspr SPRN_DSRR1,r11 + lwz r10,PACA_EXDBG+EX_CR(r13) /* restore registers */ + ld r1,PACA_EXDBG+EX_R1(r13) + ld r14,PACA_EXDBG+EX_R14(r13) + ld r15,PACA_EXDBG+EX_R15(r13) + mtcr r10 + ld r10,PACA_EXDBG+EX_R10(r13) /* restore registers */ + ld r11,PACA_EXDBG+EX_R11(r13) + mfspr r13,SPRN_SPRG_DBG_SCRATCH + rfdi + + /* Normal debug exception */ + /* XXX We only handle coming from userspace for now since we can't + * quite save properly an interrupted kernel state yet + */ +1: andi. r14,r11,MSR_PR; /* check for userspace again */ + beq kernel_dbg_exc; /* if from kernel mode */ + + /* 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(0xd00, PACA_EXDBG, INTS_DISABLE_ALL) + 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 + + MASKABLE_EXCEPTION(0x260, perfmon, .performance_monitor_exception, ACK_NONE) + /* Doorbell interrupt */ MASKABLE_EXCEPTION(0x2070, doorbell, .doorbell_exception, ACK_NONE) @@ -468,6 +535,11 @@ kernel_dbg_exc: // b ret_from_crit_except b . + MASKABLE_EXCEPTION(0x2c0, guest_doorbell, .unknown_exception, ACK_NONE) + MASKABLE_EXCEPTION(0x2e0, guest_doorbell_crit, .unknown_exception, ACK_NONE) + MASKABLE_EXCEPTION(0x310, hypercall, .unknown_exception, ACK_NONE) + MASKABLE_EXCEPTION(0x320, ehpriv, .unknown_exception, ACK_NONE) + /* * An interrupt came in while soft-disabled; clear EE in SRR1, @@ -587,7 +659,12 @@ fast_exception_return: BAD_STACK_TRAMPOLINE(0x000) BAD_STACK_TRAMPOLINE(0x100) BAD_STACK_TRAMPOLINE(0x200) +BAD_STACK_TRAMPOLINE(0x260) +BAD_STACK_TRAMPOLINE(0x2c0) +BAD_STACK_TRAMPOLINE(0x2e0) BAD_STACK_TRAMPOLINE(0x300) +BAD_STACK_TRAMPOLINE(0x310) +BAD_STACK_TRAMPOLINE(0x320) BAD_STACK_TRAMPOLINE(0x400) BAD_STACK_TRAMPOLINE(0x500) BAD_STACK_TRAMPOLINE(0x600) @@ -864,8 +941,23 @@ have_hes: * that will have to be made dependent on whether we are running under * a hypervisor I suppose. */ - ori r3,r3,MAS0_HES | MAS0_WQ_ALLWAYS - mtspr SPRN_MAS0,r3 + + /* BEWARE, MAGIC + * This code is called as an ordinary function on the boot CPU. But to + * avoid duplication, this code is also used in SCOM bringup of + * secondary CPUs. We read the code between the initial_tlb_code_start + * and initial_tlb_code_end labels one instruction at a time and RAM it + * into the new core via SCOM. That doesn't process branches, so there + * must be none between those two labels. It also means if this code + * ever takes any parameters, the SCOM code must also be updated to + * provide them. + */ + .globl a2_tlbinit_code_start +a2_tlbinit_code_start: + + ori r11,r3,MAS0_WQ_ALLWAYS + oris r11,r11,MAS0_ESEL(3)@h /* Use way 3: workaround A2 erratum 376 */ + mtspr SPRN_MAS0,r11 lis r3,(MAS1_VALID | MAS1_IPROT)@h ori r3,r3,BOOK3E_PAGESZ_1GB << MAS1_TSIZE_SHIFT mtspr SPRN_MAS1,r3 @@ -879,18 +971,86 @@ have_hes: /* Write the TLB entry */ tlbwe + .globl a2_tlbinit_after_linear_map +a2_tlbinit_after_linear_map: + /* Now we branch the new virtual address mapped by this entry */ LOAD_REG_IMMEDIATE(r3,1f) mtctr r3 bctr 1: /* We are now running at PAGE_OFFSET, clean the TLB of everything - * else (XXX we should scan for bolted crap from the firmware too) + * else (including IPROTed things left by firmware) + * r4 = TLBnCFG + * r3 = current address (more or less) */ + + li r5,0 + mtspr SPRN_MAS6,r5 + tlbsx 0,r3 + + rlwinm r9,r4,0,TLBnCFG_N_ENTRY + rlwinm r10,r4,8,0xff + addi r10,r10,-1 /* Get inner loop mask */ + + li r3,1 + + mfspr r5,SPRN_MAS1 + rlwinm r5,r5,0,(~(MAS1_VALID|MAS1_IPROT)) + + mfspr r6,SPRN_MAS2 + rldicr r6,r6,0,51 /* Extract EPN */ + + mfspr r7,SPRN_MAS0 + rlwinm r7,r7,0,0xffff0fff /* Clear HES and WQ */ + + rlwinm r8,r7,16,0xfff /* Extract ESEL */ + +2: add r4,r3,r8 + and r4,r4,r10 + + rlwimi r7,r4,16,MAS0_ESEL_MASK + + mtspr SPRN_MAS0,r7 + mtspr SPRN_MAS1,r5 + mtspr SPRN_MAS2,r6 + tlbwe + + addi r3,r3,1 + and. r4,r3,r10 + + bne 3f + addis r6,r6,(1<<30)@h +3: + cmpw r3,r9 + blt 2b + + .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(0,0,0) sync isync + .globl a2_tlbinit_code_end +a2_tlbinit_code_end: + /* We translate LR and return */ mflr r3 tovirt(r3,r3) @@ -1040,3 +1200,33 @@ _GLOBAL(__setup_base_ivors) sync blr + +_GLOBAL(setup_perfmon_ivor) + SET_IVOR(35, 0x260) /* Performance Monitor */ + blr + +_GLOBAL(setup_doorbell_ivors) + SET_IVOR(36, 0x280) /* Processor Doorbell */ + SET_IVOR(37, 0x2a0) /* Processor Doorbell Crit */ + + /* Check MMUCFG[LPIDSIZE] to determine if we have category E.HV */ + mfspr r10,SPRN_MMUCFG + rlwinm. r10,r10,0,MMUCFG_LPIDSIZE + beqlr + + SET_IVOR(38, 0x2c0) /* Guest Processor Doorbell */ + SET_IVOR(39, 0x2e0) /* Guest Processor Doorbell Crit/MC */ + blr + +_GLOBAL(setup_ehv_ivors) + /* + * We may be running as a guest and lack E.HV even on a chip + * that normally has it. + */ + mfspr r10,SPRN_MMUCFG + rlwinm. r10,r10,0,MMUCFG_LPIDSIZE + beqlr + + SET_IVOR(40, 0x300) /* Embedded Hypervisor System Call */ + SET_IVOR(41, 0x320) /* Embedded Hypervisor Privilege */ + blr diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index aeb739e1876..a85f4874cba 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -37,23 +37,51 @@ .globl __start_interrupts __start_interrupts: - STD_EXCEPTION_PSERIES(0x100, system_reset) + .globl system_reset_pSeries; +system_reset_pSeries: + HMT_MEDIUM; + DO_KVM 0x100; + SET_SCRATCH0(r13) +#ifdef CONFIG_PPC_P7_NAP +BEGIN_FTR_SECTION + /* Running native on arch 2.06 or later, check if we are + * waking up from nap. We only handle no state loss and + * supervisor state loss. We do -not- handle hypervisor + * state loss at this time. + */ + mfspr r13,SPRN_SRR1 + rlwinm r13,r13,47-31,30,31 + cmpwi cr0,r13,1 + bne 1f + b .power7_wakeup_noloss +1: cmpwi cr0,r13,2 + bne 1f + b .power7_wakeup_loss + /* 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 + */ +1: cmpwi cr0,r13,3 + beq . +END_FTR_SECTION_IFSET(CPU_FTR_HVMODE_206) +#endif /* CONFIG_PPC_P7_NAP */ + EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD) . = 0x200 _machine_check_pSeries: HMT_MEDIUM DO_KVM 0x200 - mtspr SPRN_SPRG_SCRATCH0,r13 /* save r13 */ - EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common) + SET_SCRATCH0(r13) + EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common, EXC_STD) . = 0x300 .globl data_access_pSeries data_access_pSeries: HMT_MEDIUM DO_KVM 0x300 - mtspr SPRN_SPRG_SCRATCH0,r13 + SET_SCRATCH0(r13) BEGIN_FTR_SECTION - mfspr r13,SPRN_SPRG_PACA + GET_PACA(r13) std r9,PACA_EXSLB+EX_R9(r13) std r10,PACA_EXSLB+EX_R10(r13) mfspr r10,SPRN_DAR @@ -67,22 +95,22 @@ BEGIN_FTR_SECTION std r11,PACA_EXGEN+EX_R11(r13) ld r11,PACA_EXSLB+EX_R9(r13) std r12,PACA_EXGEN+EX_R12(r13) - mfspr r12,SPRN_SPRG_SCRATCH0 + GET_SCRATCH0(r12) std r10,PACA_EXGEN+EX_R10(r13) std r11,PACA_EXGEN+EX_R9(r13) std r12,PACA_EXGEN+EX_R13(r13) - EXCEPTION_PROLOG_PSERIES_1(data_access_common) + EXCEPTION_PROLOG_PSERIES_1(data_access_common, EXC_STD) FTR_SECTION_ELSE - EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, data_access_common) -ALT_FTR_SECTION_END_IFCLR(CPU_FTR_SLB) + EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, data_access_common, EXC_STD) +ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_SLB) . = 0x380 .globl data_access_slb_pSeries data_access_slb_pSeries: HMT_MEDIUM DO_KVM 0x380 - mtspr SPRN_SPRG_SCRATCH0,r13 - mfspr r13,SPRN_SPRG_PACA /* get paca address into r13 */ + SET_SCRATCH0(r13) + GET_PACA(r13) std r3,PACA_EXSLB+EX_R3(r13) mfspr r3,SPRN_DAR std r9,PACA_EXSLB+EX_R9(r13) /* save r9 - r12 */ @@ -95,7 +123,7 @@ data_access_slb_pSeries: std r10,PACA_EXSLB+EX_R10(r13) std r11,PACA_EXSLB+EX_R11(r13) std r12,PACA_EXSLB+EX_R12(r13) - mfspr r10,SPRN_SPRG_SCRATCH0 + GET_SCRATCH0(r10) std r10,PACA_EXSLB+EX_R13(r13) mfspr r12,SPRN_SRR1 /* and SRR1 */ #ifndef CONFIG_RELOCATABLE @@ -113,15 +141,15 @@ data_access_slb_pSeries: bctr #endif - STD_EXCEPTION_PSERIES(0x400, instruction_access) + STD_EXCEPTION_PSERIES(0x400, 0x400, instruction_access) . = 0x480 .globl instruction_access_slb_pSeries instruction_access_slb_pSeries: HMT_MEDIUM DO_KVM 0x480 - mtspr SPRN_SPRG_SCRATCH0,r13 - mfspr r13,SPRN_SPRG_PACA /* get paca address into r13 */ + SET_SCRATCH0(r13) + GET_PACA(r13) std r3,PACA_EXSLB+EX_R3(r13) mfspr r3,SPRN_SRR0 /* SRR0 is faulting address */ std r9,PACA_EXSLB+EX_R9(r13) /* save r9 - r12 */ @@ -134,7 +162,7 @@ instruction_access_slb_pSeries: std r10,PACA_EXSLB+EX_R10(r13) std r11,PACA_EXSLB+EX_R11(r13) std r12,PACA_EXSLB+EX_R12(r13) - mfspr r10,SPRN_SPRG_SCRATCH0 + GET_SCRATCH0(r10) std r10,PACA_EXSLB+EX_R13(r13) mfspr r12,SPRN_SRR1 /* and SRR1 */ #ifndef CONFIG_RELOCATABLE @@ -147,13 +175,29 @@ instruction_access_slb_pSeries: bctr #endif - MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt) - STD_EXCEPTION_PSERIES(0x600, alignment) - STD_EXCEPTION_PSERIES(0x700, program_check) - STD_EXCEPTION_PSERIES(0x800, fp_unavailable) - MASKABLE_EXCEPTION_PSERIES(0x900, decrementer) - STD_EXCEPTION_PSERIES(0xa00, trap_0a) - STD_EXCEPTION_PSERIES(0xb00, trap_0b) + /* We open code these as we can't have a ". = x" (even with + * x = "." within a feature section + */ + . = 0x500; + .globl hardware_interrupt_pSeries; + .globl hardware_interrupt_hv; +hardware_interrupt_pSeries: +hardware_interrupt_hv: + BEGIN_FTR_SECTION + _MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt, EXC_STD) + FTR_SECTION_ELSE + _MASKABLE_EXCEPTION_PSERIES(0x502, hardware_interrupt, EXC_HV) + ALT_FTR_SECTION_END_IFCLR(CPU_FTR_HVMODE_206) + + STD_EXCEPTION_PSERIES(0x600, 0x600, alignment) + STD_EXCEPTION_PSERIES(0x700, 0x700, program_check) + STD_EXCEPTION_PSERIES(0x800, 0x800, fp_unavailable) + + MASKABLE_EXCEPTION_PSERIES(0x900, 0x900, decrementer) + MASKABLE_EXCEPTION_HV(0x980, 0x980, decrementer) + + STD_EXCEPTION_PSERIES(0xa00, 0xa00, trap_0a) + STD_EXCEPTION_PSERIES(0xb00, 0xb00, trap_0b) . = 0xc00 .globl system_call_pSeries @@ -165,13 +209,13 @@ BEGIN_FTR_SECTION beq- 1f END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE) mr r9,r13 - mfspr r13,SPRN_SPRG_PACA + GET_PACA(r13) mfspr r11,SPRN_SRR0 - ld r12,PACAKBASE(r13) - ld r10,PACAKMSR(r13) - LOAD_HANDLER(r12, system_call_entry) - mtspr SPRN_SRR0,r12 mfspr r12,SPRN_SRR1 + ld r10,PACAKBASE(r13) + LOAD_HANDLER(r10, system_call_entry) + mtspr SPRN_SRR0,r10 + ld r10,PACAKMSR(r13) mtspr SPRN_SRR1,r10 rfid b . /* prevent speculative execution */ @@ -183,8 +227,21 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE) rfid /* return to userspace */ b . - STD_EXCEPTION_PSERIES(0xd00, single_step) - STD_EXCEPTION_PSERIES(0xe00, trap_0e) + STD_EXCEPTION_PSERIES(0xd00, 0xd00, single_step) + + /* At 0xe??? we have a bunch of hypervisor exceptions, we branch + * out of line to handle them + */ + . = 0xe00 + b h_data_storage_hv + . = 0xe20 + b h_instr_storage_hv + . = 0xe40 + b emulation_assist_hv + . = 0xe50 + b hmi_exception_hv + . = 0xe60 + b hmi_exception_hv /* We need to deal with the Altivec unavailable exception * here which is at 0xf20, thus in the middle of the @@ -193,39 +250,42 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE) */ performance_monitor_pSeries_1: . = 0xf00 - DO_KVM 0xf00 b performance_monitor_pSeries altivec_unavailable_pSeries_1: . = 0xf20 - DO_KVM 0xf20 b altivec_unavailable_pSeries vsx_unavailable_pSeries_1: . = 0xf40 - DO_KVM 0xf40 b vsx_unavailable_pSeries #ifdef CONFIG_CBE_RAS - HSTD_EXCEPTION_PSERIES(0x1200, cbe_system_error) + STD_EXCEPTION_HV(0x1200, 0x1202, cbe_system_error) #endif /* CONFIG_CBE_RAS */ - STD_EXCEPTION_PSERIES(0x1300, instruction_breakpoint) + STD_EXCEPTION_PSERIES(0x1300, 0x1300, instruction_breakpoint) #ifdef CONFIG_CBE_RAS - HSTD_EXCEPTION_PSERIES(0x1600, cbe_maintenance) + STD_EXCEPTION_HV(0x1600, 0x1602, cbe_maintenance) #endif /* CONFIG_CBE_RAS */ - STD_EXCEPTION_PSERIES(0x1700, altivec_assist) + STD_EXCEPTION_PSERIES(0x1700, 0x1700, altivec_assist) #ifdef CONFIG_CBE_RAS - HSTD_EXCEPTION_PSERIES(0x1800, cbe_thermal) + STD_EXCEPTION_HV(0x1800, 0x1802, cbe_thermal) #endif /* CONFIG_CBE_RAS */ . = 0x3000 -/*** pSeries interrupt support ***/ +/*** Out of line interrupts support ***/ + + /* moved from 0xe00 */ + STD_EXCEPTION_HV(., 0xe00, h_data_storage) + STD_EXCEPTION_HV(., 0xe20, h_instr_storage) + STD_EXCEPTION_HV(., 0xe40, emulation_assist) + STD_EXCEPTION_HV(., 0xe60, hmi_exception) /* need to flush cache ? */ /* moved from 0xf00 */ - STD_EXCEPTION_PSERIES(., performance_monitor) - STD_EXCEPTION_PSERIES(., altivec_unavailable) - STD_EXCEPTION_PSERIES(., vsx_unavailable) + STD_EXCEPTION_PSERIES(., 0xf00, performance_monitor) + STD_EXCEPTION_PSERIES(., 0xf20, altivec_unavailable) + STD_EXCEPTION_PSERIES(., 0xf40, vsx_unavailable) /* * An interrupt came in while soft-disabled; clear EE in SRR1, @@ -240,17 +300,30 @@ masked_interrupt: rotldi r10,r10,16 mtspr SPRN_SRR1,r10 ld r10,PACA_EXGEN+EX_R10(r13) - mfspr r13,SPRN_SPRG_SCRATCH0 + GET_SCRATCH0(r13) rfid b . +masked_Hinterrupt: + stb r10,PACAHARDIRQEN(r13) + mtcrf 0x80,r9 + ld r9,PACA_EXGEN+EX_R9(r13) + mfspr r10,SPRN_HSRR1 + rldicl r10,r10,48,1 /* clear MSR_EE */ + rotldi r10,r10,16 + mtspr SPRN_HSRR1,r10 + ld r10,PACA_EXGEN+EX_R10(r13) + GET_SCRATCH0(r13) + hrfid + b . + .align 7 do_stab_bolted_pSeries: std r11,PACA_EXSLB+EX_R11(r13) std r12,PACA_EXSLB+EX_R12(r13) - mfspr r10,SPRN_SPRG_SCRATCH0 + GET_SCRATCH0(r10) std r10,PACA_EXSLB+EX_R13(r13) - EXCEPTION_PROLOG_PSERIES_1(.do_stab_bolted) + EXCEPTION_PROLOG_PSERIES_1(.do_stab_bolted, EXC_STD) #ifdef CONFIG_PPC_PSERIES /* @@ -260,15 +333,15 @@ do_stab_bolted_pSeries: .align 7 system_reset_fwnmi: HMT_MEDIUM - mtspr SPRN_SPRG_SCRATCH0,r13 /* save r13 */ - EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common) + SET_SCRATCH0(r13) /* save r13 */ + EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD) .globl machine_check_fwnmi .align 7 machine_check_fwnmi: HMT_MEDIUM - mtspr SPRN_SPRG_SCRATCH0,r13 /* save r13 */ - EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common) + SET_SCRATCH0(r13) /* save r13 */ + EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common, EXC_STD) #endif /* CONFIG_PPC_PSERIES */ @@ -282,7 +355,7 @@ slb_miss_user_pseries: std r10,PACA_EXGEN+EX_R10(r13) std r11,PACA_EXGEN+EX_R11(r13) std r12,PACA_EXGEN+EX_R12(r13) - mfspr r10,SPRG_SCRATCH0 + GET_SCRATCH0(r10) ld r11,PACA_EXSLB+EX_R9(r13) ld r12,PACA_EXSLB+EX_R3(r13) std r10,PACA_EXGEN+EX_R13(r13) @@ -342,6 +415,8 @@ machine_check_common: 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, .program_check_exception) + STD_EXCEPTION_COMMON(0xe60, hmi_exception, .unknown_exception) STD_EXCEPTION_COMMON_IDLE(0xf00, performance_monitor, .performance_monitor_exception) STD_EXCEPTION_COMMON(0x1300, instruction_breakpoint, .instruction_breakpoint_exception) #ifdef CONFIG_ALTIVEC @@ -386,9 +461,24 @@ bad_stack: std r12,_XER(r1) SAVE_GPR(0,r1) SAVE_GPR(2,r1) - SAVE_4GPRS(3,r1) - SAVE_2GPRS(7,r1) - SAVE_10GPRS(12,r1) + ld r10,EX_R3(r3) + std r10,GPR3(r1) + SAVE_GPR(4,r1) + SAVE_4GPRS(5,r1) + ld r9,EX_R9(r3) + ld r10,EX_R10(r3) + SAVE_2GPRS(9,r1) + ld r9,EX_R11(r3) + ld r10,EX_R12(r3) + ld r11,EX_R13(r3) + std r9,GPR11(r1) + std r10,GPR12(r1) + std r11,GPR13(r1) +BEGIN_FTR_SECTION + ld r10,EX_CFAR(r3) + std r10,ORIG_GPR3(r1) +END_FTR_SECTION_IFSET(CPU_FTR_CFAR) + SAVE_8GPRS(14,r1) SAVE_10GPRS(22,r1) lhz r12,PACA_TRAP_SAVE(r13) std r12,_TRAP(r1) @@ -397,6 +487,9 @@ bad_stack: li r12,0 std r12,0(r11) ld r2,PACATOC(r13) + ld r11,exception_marker@toc(r2) + std r12,RESULT(r1) + std r11,STACK_FRAME_OVERHEAD-16(r1) 1: addi r3,r1,STACK_FRAME_OVERHEAD bl .kernel_bad_stack b 1b @@ -419,6 +512,19 @@ data_access_common: li r5,0x300 b .do_hash_page /* Try to handle as hpte fault */ + .align 7 + .globl h_data_storage_common +h_data_storage_common: + mfspr r10,SPRN_HDAR + std r10,PACA_EXGEN+EX_DAR(r13) + mfspr r10,SPRN_HDSISR + stw r10,PACA_EXGEN+EX_DSISR(r13) + EXCEPTION_PROLOG_COMMON(0xe00, PACA_EXGEN) + bl .save_nvgprs + addi r3,r1,STACK_FRAME_OVERHEAD + bl .unknown_exception + b .ret_from_except + .align 7 .globl instruction_access_common instruction_access_common: @@ -428,6 +534,8 @@ instruction_access_common: li r5,0x400 b .do_hash_page /* Try to handle as hpte fault */ + STD_EXCEPTION_COMMON(0xe20, h_instr_storage, .unknown_exception) + /* * Here is the common SLB miss user that is used when going to virtual * mode for SLB misses, that is currently not used @@ -750,7 +858,7 @@ _STATIC(do_hash_page) BEGIN_FTR_SECTION andis. r0,r4,0x0020 /* Is it a segment table fault? */ bne- do_ste_alloc /* If so handle it */ -END_FTR_SECTION_IFCLR(CPU_FTR_SLB) +END_MMU_FTR_SECTION_IFCLR(MMU_FTR_SLB) clrrdi r11,r1,THREAD_SHIFT lwz r0,TI_PREEMPT(r11) /* If we're in an "NMI" */ diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c index ce1f3e44c24..bf99cfa6bbf 100644 --- a/arch/powerpc/kernel/ftrace.c +++ b/arch/powerpc/kernel/ftrace.c @@ -22,6 +22,7 @@ #include <asm/cacheflush.h> #include <asm/code-patching.h> #include <asm/ftrace.h> +#include <asm/syscall.h> #ifdef CONFIG_DYNAMIC_FTRACE @@ -600,3 +601,10 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) } } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ + +#if defined(CONFIG_FTRACE_SYSCALLS) && defined(CONFIG_PPC64) +unsigned long __init arch_syscall_addr(int nr) +{ + return sys_call_table[nr*2]; +} +#endif /* CONFIG_FTRACE_SYSCALLS && CONFIG_PPC64 */ diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index c5c24beb838..ba250d505e0 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -805,19 +805,6 @@ _ENTRY(copy_and_flush) blr #ifdef CONFIG_SMP -#ifdef CONFIG_GEMINI - .globl __secondary_start_gemini -__secondary_start_gemini: - mfspr r4,SPRN_HID0 - ori r4,r4,HID0_ICFI - li r3,0 - ori r3,r3,HID0_ICE - andc r4,r4,r3 - mtspr SPRN_HID0,r4 - sync - b __secondary_start -#endif /* CONFIG_GEMINI */ - .globl __secondary_start_mpc86xx __secondary_start_mpc86xx: mfspr r3, SPRN_PIR @@ -890,15 +877,6 @@ __secondary_start: mtspr SPRN_SRR1,r4 SYNC RFI - -_GLOBAL(start_secondary_resume) - /* Reset stack */ - rlwinm r1,r1,0,0,(31-THREAD_SHIFT) /* current_thread_info() */ - addi r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD - li r3,0 - std r3,0(r1) /* Zero the stack frame pointer */ - bl start_secondary - b . #endif /* CONFIG_SMP */ #ifdef CONFIG_KVM_BOOK3S_HANDLER diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 3a319f9c9d3..ba504099844 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -147,6 +147,8 @@ __secondary_hold: mtctr r4 mr r3,r24 li r4,0 + /* Make sure that patched code is visible */ + isync bctr #else BUG_OPCODE @@ -216,19 +218,25 @@ generic_secondary_common_init: */ LOAD_REG_ADDR(r13, paca) /* Load paca pointer */ 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 */ +#else + LOAD_REG_ADDR(r7, nr_cpu_ids) /* Load nr_cpu_ids address */ + lwz r7,0(r7) /* also the max paca allocated */ li r5,0 /* logical cpu id */ 1: lhz r6,PACAHWCPUID(r13) /* Load HW procid from paca */ cmpw r6,r24 /* Compare to our id */ beq 2f addi r13,r13,PACA_SIZE /* Loop to next PACA on miss */ addi r5,r5,1 - cmpwi r5,NR_CPUS + cmpw r5,r7 /* Check if more pacas exist */ blt 1b mr r3,r24 /* not found, copy phys to r3 */ b .kexec_wait /* next kernel might do better */ -2: mtspr SPRN_SPRG_PACA,r13 /* Save vaddr of paca in an SPRG */ +2: SET_PACA(r13) #ifdef CONFIG_PPC_BOOK3E addi r12,r13,PACA_EXTLB /* and TLB exc frame in another */ mtspr SPRN_SPRG_TLB_EXFRAME,r12 @@ -236,34 +244,39 @@ generic_secondary_common_init: /* From now on, r24 is expected to be logical cpuid */ mr r24,r5 -3: HMT_LOW - lbz r23,PACAPROCSTART(r13) /* Test if this processor should */ - /* start. */ - -#ifndef CONFIG_SMP - b 3b /* Never go on non-SMP */ -#else - cmpwi 0,r23,0 - beq 3b /* Loop until told to go */ - - sync /* order paca.run and cur_cpu_spec */ /* 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 - beq 4f + beq 3f ld r23,0(r23) mtctr r23 bctrl -4: /* Create a temp kernel stack for use before relocation is on. */ +3: LOAD_REG_ADDR(r3, boot_cpu_count) /* Decrement boot_cpu_count */ + lwarx r4,0,r3 + subi r4,r4,1 + stwcx. r4,0,r3 + bne 3b + isync + +4: HMT_LOW + lbz r23,PACAPROCSTART(r13) /* Test if this processor should */ + /* start. */ + cmpwi 0,r23,0 + beq 4b /* Loop until told to go */ + + sync /* order paca.run and cur_cpu_spec */ + isync /* In case code patching happened */ + + /* Create a temp kernel stack for use before relocation is on. */ ld r1,PACAEMERGSP(r13) subi r1,r1,STACK_FRAME_OVERHEAD b __secondary_start -#endif +#endif /* SMP */ /* * Turn the MMU off. @@ -534,7 +547,7 @@ _GLOBAL(pmac_secondary_start) ld r4,0(r4) /* Get base vaddr of paca array */ mulli r13,r24,PACA_SIZE /* Calculate vaddr of right paca */ add r13,r13,r4 /* for this processor. */ - mtspr SPRN_SPRG_PACA,r13 /* Save vaddr of paca in an SPRG*/ + SET_PACA(r13) /* Save vaddr of paca in an SPRG*/ /* Mark interrupts soft and hard disabled (they might be enabled * in the PACA when doing hotplug) @@ -645,7 +658,7 @@ _GLOBAL(enable_64b_mode) oris r11,r11,0x8000 /* CM bit set, we'll set ICM later */ mtmsr r11 #else /* CONFIG_PPC_BOOK3E */ - li r12,(MSR_SF | MSR_ISF)@highest + li r12,(MSR_64BIT | MSR_ISF)@highest sldi r12,r12,48 or r11,r11,r12 mtmsrd r11 diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S new file mode 100644 index 00000000000..f8f0bc7f1d4 --- /dev/null +++ b/arch/powerpc/kernel/idle_power7.S @@ -0,0 +1,97 @@ +/* + * This file contains the power_save function for 970-family CPUs. + * + * 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 <linux/threads.h> +#include <asm/processor.h> +#include <asm/page.h> +#include <asm/cputable.h> +#include <asm/thread_info.h> +#include <asm/ppc_asm.h> +#include <asm/asm-offsets.h> +#include <asm/ppc-opcode.h> + +#undef DEBUG + + .text + +_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 + + /* 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 + * need to save PC, some CR bits and the NV GPRs, + * but for now an interrupt frame will do. + */ + mflr r0 + std r0,16(r1) + stdu r1,-INT_FRAME_SIZE(r1) + std r0,_LINK(r1) + std r0,_NIP(r1) + +#ifndef CONFIG_SMP + /* Make sure FPU, VSX etc... are flushed as we may lose + * state when going to nap mode + */ + bl .discard_lazy_cpu_state +#endif /* CONFIG_SMP */ + + /* Hard disable interrupts */ + mfmsr r9 + rldicl r9,r9,48,1 + rotldi r9,r9,16 + mtmsrd r9,1 /* hard-disable interrupts */ + li r0,0 + stb r0,PACASOFTIRQEN(r13) /* we'll hard-enable shortly */ + stb r0,PACAHARDIRQEN(r13) + + /* Continue saving state */ + SAVE_GPR(2, r1) + SAVE_NVGPRS(r1) + mfcr r3 + std r3,_CCR(r1) + std r9,_MSR(r1) + std r1,PACAR1(r13) + + /* 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_wakeup_loss) + GET_PACA(r13) + ld r1,PACAR1(r13) + 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 + mtspr SPRN_SRR1,r4 + mtspr SPRN_SRR0,r5 + rfid + +_GLOBAL(power7_wakeup_noloss) + GET_PACA(r13) + ld r1,PACAR1(r13) + ld r4,_MSR(r1) + ld r5,_NIP(r1) + addi r1,r1,INT_FRAME_SIZE + mtspr SPRN_SRR1,r4 + mtspr SPRN_SRR0,r5 + rfid diff --git a/arch/powerpc/kernel/io-workarounds.c b/arch/powerpc/kernel/io-workarounds.c new file mode 100644 index 00000000000..ffafaea3d26 --- /dev/null +++ b/arch/powerpc/kernel/io-workarounds.c @@ -0,0 +1,188 @@ +/* + * Support PCI IO workaround + * + * Copyright (C) 2006 Benjamin Herrenschmidt <benh@kernel.crashing.org> + * IBM, Corp. + * (C) Copyright 2007-2008 TOSHIBA CORPORATION + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#undef DEBUG + +#include <linux/kernel.h> + +#include <asm/io.h> +#include <asm/machdep.h> +#include <asm/pgtable.h> +#include <asm/ppc-pci.h> +#include <asm/io-workarounds.h> + +#define IOWA_MAX_BUS 8 + +static struct iowa_bus iowa_busses[IOWA_MAX_BUS]; +static unsigned int iowa_bus_count; + +static struct iowa_bus *iowa_pci_find(unsigned long vaddr, unsigned long paddr) +{ + int i, j; + struct resource *res; + unsigned long vstart, vend; + + for (i = 0; i < iowa_bus_count; i++) { + struct iowa_bus *bus = &iowa_busses[i]; + struct pci_controller *phb = bus->phb; + + if (vaddr) { + vstart = (unsigned long)phb->io_base_virt; + vend = vstart + phb->pci_io_size - 1; + if ((vaddr >= vstart) && (vaddr <= vend)) + return bus; + } + + if (paddr) + for (j = 0; j < 3; j++) { + res = &phb->mem_resources[j]; + if (paddr >= res->start && paddr <= res->end) + return bus; + } + } + + return NULL; +} + +struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR addr) +{ + struct iowa_bus *bus; + int token; + + token = PCI_GET_ADDR_TOKEN(addr); + + if (token && token <= iowa_bus_count) + bus = &iowa_busses[token - 1]; + else { + unsigned long vaddr, paddr; + pte_t *ptep; + + vaddr = (unsigned long)PCI_FIX_ADDR(addr); + if (vaddr < PHB_IO_BASE || vaddr >= PHB_IO_END) + return NULL; + + ptep = find_linux_pte(init_mm.pgd, vaddr); + if (ptep == NULL) + paddr = 0; + else + paddr = pte_pfn(*ptep) << PAGE_SHIFT; + bus = iowa_pci_find(vaddr, paddr); + + if (bus == NULL) + return NULL; + } + + return bus; +} + +struct iowa_bus *iowa_pio_find_bus(unsigned long port) +{ + unsigned long vaddr = (unsigned long)pci_io_base + port; + return iowa_pci_find(vaddr, 0); +} + + +#define DEF_PCI_AC_RET(name, ret, at, al, space, aa) \ +static ret iowa_##name at \ +{ \ + struct iowa_bus *bus; \ + bus = iowa_##space##_find_bus(aa); \ + if (bus && bus->ops && bus->ops->name) \ + return bus->ops->name al; \ + return __do_##name al; \ +} + +#define DEF_PCI_AC_NORET(name, at, al, space, aa) \ +static void iowa_##name at \ +{ \ + struct iowa_bus *bus; \ + bus = iowa_##space##_find_bus(aa); \ + if (bus && bus->ops && bus->ops->name) { \ + bus->ops->name al; \ + return; \ + } \ + __do_##name al; \ +} + +#include <asm/io-defs.h> + +#undef DEF_PCI_AC_RET +#undef DEF_PCI_AC_NORET + +static const struct ppc_pci_io __devinitconst iowa_pci_io = { + +#define DEF_PCI_AC_RET(name, ret, at, al, space, aa) .name = iowa_##name, +#define DEF_PCI_AC_NORET(name, at, al, space, aa) .name = iowa_##name, + +#include <asm/io-defs.h> + +#undef DEF_PCI_AC_RET +#undef DEF_PCI_AC_NORET + +}; + +static void __iomem *iowa_ioremap(phys_addr_t addr, unsigned long size, + unsigned long flags, void *caller) +{ + struct iowa_bus *bus; + void __iomem *res = __ioremap_caller(addr, size, flags, caller); + int busno; + + bus = iowa_pci_find(0, (unsigned long)addr); + if (bus != NULL) { + busno = bus - iowa_busses; + PCI_SET_ADDR_TOKEN(res, busno + 1); + } + return res; +} + +/* Enable IO workaround */ +static void __devinit io_workaround_init(void) +{ + static int io_workaround_inited; + + if (io_workaround_inited) + return; + ppc_pci_io = iowa_pci_io; + ppc_md.ioremap = iowa_ioremap; + io_workaround_inited = 1; +} + +/* Register new bus to support workaround */ +void __devinit iowa_register_bus(struct pci_controller *phb, + struct ppc_pci_io *ops, + int (*initfunc)(struct iowa_bus *, void *), void *data) +{ + struct iowa_bus *bus; + struct device_node *np = phb->dn; + + io_workaround_init(); + + if (iowa_bus_count >= IOWA_MAX_BUS) { + pr_err("IOWA:Too many pci bridges, " + "workarounds disabled for %s\n", np->full_name); + return; + } + + bus = &iowa_busses[iowa_bus_count]; + bus->phb = phb; + bus->ops = ops; + bus->private = data; + + if (initfunc) + if ((*initfunc)(bus, data)) + return; + + iowa_bus_count++; + + pr_debug("IOWA:[%d]Add bus, %s.\n", iowa_bus_count-1, np->full_name); +} + diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index f621b7d2d86..5b428e30866 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -66,7 +66,6 @@ #include <asm/ptrace.h> #include <asm/machdep.h> #include <asm/udbg.h> -#include <asm/dbell.h> #include <asm/smp.h> #ifdef CONFIG_PPC64 @@ -160,7 +159,8 @@ notrace void arch_local_irq_restore(unsigned long en) #if defined(CONFIG_BOOKE) && defined(CONFIG_SMP) /* Check for pending doorbell interrupts and resend to ourself */ - doorbell_check_self(); + if (cpu_has_feature(CPU_FTR_DBELL)) + smp_muxed_ipi_resend(); #endif /* @@ -295,17 +295,20 @@ static inline void handle_one_irq(unsigned int irq) unsigned long saved_sp_limit; struct irq_desc *desc; + desc = irq_to_desc(irq); + if (!desc) + return; + /* Switch to the irq stack to handle this */ curtp = current_thread_info(); irqtp = hardirq_ctx[smp_processor_id()]; if (curtp == irqtp) { /* We're already on the irq stack, just handle it */ - generic_handle_irq(irq); + desc->handle_irq(irq, desc); return; } - desc = irq_to_desc(irq); saved_sp_limit = current->thread.ksp_limit; irqtp->task = curtp->task; @@ -397,24 +400,28 @@ struct thread_info *mcheckirq_ctx[NR_CPUS] __read_mostly; void exc_lvl_ctx_init(void) { struct thread_info *tp; - int i, hw_cpu; + int i, cpu_nr; for_each_possible_cpu(i) { - hw_cpu = get_hard_smp_processor_id(i); - memset((void *)critirq_ctx[hw_cpu], 0, THREAD_SIZE); - tp = critirq_ctx[hw_cpu]; - tp->cpu = i; +#ifdef CONFIG_PPC64 + cpu_nr = i; +#else + cpu_nr = get_hard_smp_processor_id(i); +#endif + memset((void *)critirq_ctx[cpu_nr], 0, THREAD_SIZE); + tp = critirq_ctx[cpu_nr]; + tp->cpu = cpu_nr; tp->preempt_count = 0; #ifdef CONFIG_BOOKE - memset((void *)dbgirq_ctx[hw_cpu], 0, THREAD_SIZE); - tp = dbgirq_ctx[hw_cpu]; - tp->cpu = i; + memset((void *)dbgirq_ctx[cpu_nr], 0, THREAD_SIZE); + tp = dbgirq_ctx[cpu_nr]; + tp->cpu = cpu_nr; tp->preempt_count = 0; - memset((void *)mcheckirq_ctx[hw_cpu], 0, THREAD_SIZE); - tp = mcheckirq_ctx[hw_cpu]; - tp->cpu = i; + memset((void *)mcheckirq_ctx[cpu_nr], 0, THREAD_SIZE); + tp = mcheckirq_ctx[cpu_nr]; + tp->cpu = cpu_nr; tp->preempt_count = HARDIRQ_OFFSET; #endif } @@ -477,20 +484,41 @@ void do_softirq(void) * IRQ controller and virtual interrupts */ +/* The main irq map itself is an array of NR_IRQ entries containing the + * associate host and irq number. An entry with a host of NULL is free. + * An entry can be allocated if it's free, the allocator always then sets + * hwirq first to the host's invalid irq number and then fills ops. + */ +struct irq_map_entry { + irq_hw_number_t hwirq; + struct irq_host *host; +}; + static LIST_HEAD(irq_hosts); static DEFINE_RAW_SPINLOCK(irq_big_lock); -static unsigned int revmap_trees_allocated; static DEFINE_MUTEX(revmap_trees_mutex); -struct irq_map_entry irq_map[NR_IRQS]; +static struct irq_map_entry irq_map[NR_IRQS]; static unsigned int irq_virq_count = NR_IRQS; static struct irq_host *irq_default_host; +irq_hw_number_t irqd_to_hwirq(struct irq_data *d) +{ + return irq_map[d->irq].hwirq; +} +EXPORT_SYMBOL_GPL(irqd_to_hwirq); + irq_hw_number_t virq_to_hw(unsigned int virq) { return irq_map[virq].hwirq; } EXPORT_SYMBOL_GPL(virq_to_hw); +bool virq_is_host(unsigned int virq, struct irq_host *host) +{ + return irq_map[virq].host == host; +} +EXPORT_SYMBOL_GPL(virq_is_host); + static int default_irq_host_match(struct irq_host *h, struct device_node *np) { return h->of_node != NULL && h->of_node == np; @@ -511,7 +539,7 @@ struct irq_host *irq_alloc_host(struct device_node *of_node, /* Allocate structure and revmap table if using linear mapping */ if (revmap_type == IRQ_HOST_MAP_LINEAR) size += revmap_arg * sizeof(unsigned int); - host = zalloc_maybe_bootmem(size, GFP_KERNEL); + host = kzalloc(size, GFP_KERNEL); if (host == NULL) return NULL; @@ -532,15 +560,8 @@ struct irq_host *irq_alloc_host(struct device_node *of_node, if (revmap_type == IRQ_HOST_MAP_LEGACY) { if (irq_map[0].host != NULL) { raw_spin_unlock_irqrestore(&irq_big_lock, flags); - /* If we are early boot, we can't free the structure, - * too bad... - * this will be fixed once slab is made available early - * instead of the current cruft - */ - if (mem_init_done) { - of_node_put(host->of_node); - kfree(host); - } + of_node_put(host->of_node); + kfree(host); return NULL; } irq_map[0].host = host; @@ -561,14 +582,14 @@ struct irq_host *irq_alloc_host(struct device_node *of_node, irq_map[i].host = host; smp_wmb(); - /* Clear norequest flags */ - irq_clear_status_flags(i, IRQ_NOREQUEST); - /* Legacy flags are left to default at this point, * one can then use irq_create_mapping() to * explicitly change them */ ops->map(host, i, i); + + /* Clear norequest flags */ + irq_clear_status_flags(i, IRQ_NOREQUEST); } break; case IRQ_HOST_MAP_LINEAR: @@ -579,6 +600,9 @@ struct irq_host *irq_alloc_host(struct device_node *of_node, smp_wmb(); host->revmap_data.linear.revmap = rmap; break; + case IRQ_HOST_MAP_TREE: + INIT_RADIX_TREE(&host->revmap_data.tree, GFP_KERNEL); + break; default: break; } @@ -636,8 +660,6 @@ static int irq_setup_virq(struct irq_host *host, unsigned int virq, goto error; } - irq_clear_status_flags(virq, IRQ_NOREQUEST); - /* map it */ smp_wmb(); irq_map[virq].hwirq = hwirq; @@ -648,6 +670,8 @@ static int irq_setup_virq(struct irq_host *host, unsigned int virq, goto errdesc; } + irq_clear_status_flags(virq, IRQ_NOREQUEST); + return 0; errdesc: @@ -699,13 +723,9 @@ unsigned int irq_create_mapping(struct irq_host *host, } pr_debug("irq: -> using host @%p\n", host); - /* Check if mapping already exist, if it does, call - * host->ops->map() to update the flags - */ + /* Check if mapping already exists */ virq = irq_find_mapping(host, hwirq); if (virq != NO_IRQ) { - if (host->ops->remap) - host->ops->remap(host, virq, hwirq); pr_debug("irq: -> existing mapping on virq %d\n", virq); return virq; } @@ -786,14 +806,15 @@ void irq_dispose_mapping(unsigned int virq) return; host = irq_map[virq].host; - WARN_ON (host == NULL); - if (host == NULL) + if (WARN_ON(host == NULL)) return; /* Never unmap legacy interrupts */ if (host->revmap_type == IRQ_HOST_MAP_LEGACY) return; + irq_set_status_flags(virq, IRQ_NOREQUEST); + /* remove chip and handler */ irq_set_chip_and_handler(virq, NULL, NULL); @@ -813,13 +834,6 @@ void irq_dispose_mapping(unsigned int virq) host->revmap_data.linear.revmap[hwirq] = NO_IRQ; break; case IRQ_HOST_MAP_TREE: - /* - * Check if radix tree allocated yet, if not then nothing to - * remove. - */ - smp_rmb(); - if (revmap_trees_allocated < 1) - break; mutex_lock(&revmap_trees_mutex); radix_tree_delete(&host->revmap_data.tree, hwirq); mutex_unlock(&revmap_trees_mutex); @@ -830,8 +844,6 @@ void irq_dispose_mapping(unsigned int virq) smp_mb(); irq_map[virq].hwirq = host->inval_irq; - irq_set_status_flags(virq, IRQ_NOREQUEST); - irq_free_descs(virq, 1); /* Free it */ irq_free_virt(virq, 1); @@ -877,21 +889,17 @@ unsigned int irq_radix_revmap_lookup(struct irq_host *host, struct irq_map_entry *ptr; unsigned int virq; - WARN_ON(host->revmap_type != IRQ_HOST_MAP_TREE); - - /* - * Check if the radix tree exists and has bee initialized. - * If not, we fallback to slow mode - */ - if (revmap_trees_allocated < 2) + if (WARN_ON_ONCE(host->revmap_type != IRQ_HOST_MAP_TREE)) return irq_find_mapping(host, hwirq); - /* Now try to resolve */ /* - * No rcu_read_lock(ing) needed, the ptr returned can't go under us - * as it's referencing an entry in the static irq_map table. + * The ptr returned references the static global irq_map. + * but freeing an irq can delete nodes along the path to + * do the lookup via call_rcu. */ + rcu_read_lock(); ptr = radix_tree_lookup(&host->revmap_data.tree, hwirq); + rcu_read_unlock(); /* * If found in radix tree, then fine. @@ -909,16 +917,7 @@ unsigned int irq_radix_revmap_lookup(struct irq_host *host, void irq_radix_revmap_insert(struct irq_host *host, unsigned int virq, irq_hw_number_t hwirq) { - - WARN_ON(host->revmap_type != IRQ_HOST_MAP_TREE); - - /* - * Check if the radix tree exists yet. - * If not, then the irq will be inserted into the tree when it gets - * initialized. - */ - smp_rmb(); - if (revmap_trees_allocated < 1) + if (WARN_ON(host->revmap_type != IRQ_HOST_MAP_TREE)) return; if (virq != NO_IRQ) { @@ -934,7 +933,8 @@ unsigned int irq_linear_revmap(struct irq_host *host, { unsigned int *revmap; - WARN_ON(host->revmap_type != IRQ_HOST_MAP_LINEAR); + if (WARN_ON_ONCE(host->revmap_type != IRQ_HOST_MAP_LINEAR)) + return irq_find_mapping(host, hwirq); /* Check revmap bounds */ if (unlikely(hwirq >= host->revmap_data.linear.size)) @@ -1007,14 +1007,23 @@ void irq_free_virt(unsigned int virq, unsigned int count) WARN_ON (virq < NUM_ISA_INTERRUPTS); WARN_ON (count == 0 || (virq + count) > irq_virq_count); + if (virq < NUM_ISA_INTERRUPTS) { + if (virq + count < NUM_ISA_INTERRUPTS) + return; + count =- NUM_ISA_INTERRUPTS - virq; + virq = NUM_ISA_INTERRUPTS; + } + + if (count > irq_virq_count || virq > irq_virq_count - count) { + if (virq > irq_virq_count) + return; + count = irq_virq_count - virq; + } + raw_spin_lock_irqsave(&irq_big_lock, flags); for (i = virq; i < (virq + count); i++) { struct irq_host *host; - if (i < NUM_ISA_INTERRUPTS || - (virq + count) > irq_virq_count) - continue; - host = irq_map[i].host; irq_map[i].hwirq = host->inval_irq; smp_wmb(); @@ -1028,53 +1037,6 @@ int arch_early_irq_init(void) return 0; } -/* We need to create the radix trees late */ -static int irq_late_init(void) -{ - struct irq_host *h; - unsigned int i; - - /* - * No mutual exclusion with respect to accessors of the tree is needed - * here as the synchronization is done via the state variable - * revmap_trees_allocated. - */ - list_for_each_entry(h, &irq_hosts, link) { - if (h->revmap_type == IRQ_HOST_MAP_TREE) - INIT_RADIX_TREE(&h->revmap_data.tree, GFP_KERNEL); - } - - /* - * Make sure the radix trees inits are visible before setting - * the flag - */ - smp_wmb(); - revmap_trees_allocated = 1; - - /* - * Insert the reverse mapping for those interrupts already present - * in irq_map[]. - */ - mutex_lock(&revmap_trees_mutex); - for (i = 0; i < irq_virq_count; i++) { - if (irq_map[i].host && - (irq_map[i].host->revmap_type == IRQ_HOST_MAP_TREE)) - radix_tree_insert(&irq_map[i].host->revmap_data.tree, - irq_map[i].hwirq, &irq_map[i]); - } - mutex_unlock(&revmap_trees_mutex); - - /* - * Make sure the radix trees insertions are visible before setting - * the flag - */ - smp_wmb(); - revmap_trees_allocated = 2; - - return 0; -} -arch_initcall(irq_late_init); - #ifdef CONFIG_VIRQ_DEBUG static int virq_debug_show(struct seq_file *m, void *private) { @@ -1082,10 +1044,11 @@ static int virq_debug_show(struct seq_file *m, void *private) struct irq_desc *desc; const char *p; static const char none[] = "none"; + void *data; int i; - seq_printf(m, "%-5s %-7s %-15s %s\n", "virq", "hwirq", - "chip name", "host name"); + seq_printf(m, "%-5s %-7s %-15s %-18s %s\n", "virq", "hwirq", + "chip name", "chip data", "host name"); for (i = 1; i < nr_irqs; i++) { desc = irq_to_desc(i); @@ -1098,7 +1061,7 @@ static int virq_debug_show(struct seq_file *m, void *private) struct irq_chip *chip; seq_printf(m, "%5d ", i); - seq_printf(m, "0x%05lx ", virq_to_hw(i)); + seq_printf(m, "0x%05lx ", irq_map[i].hwirq); chip = irq_desc_get_chip(desc); if (chip && chip->name) @@ -1107,6 +1070,9 @@ static int virq_debug_show(struct seq_file *m, void *private) p = none; seq_printf(m, "%-15s ", p); + data = irq_desc_get_chip_data(desc); + seq_printf(m, "0x%16p ", data); + if (irq_map[i].host && irq_map[i].host->of_node) p = irq_map[i].host->of_node->full_name; else diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c index 42850ee00ad..76a6e40a6f7 100644 --- a/arch/powerpc/kernel/kgdb.c +++ b/arch/powerpc/kernel/kgdb.c @@ -109,7 +109,7 @@ static int kgdb_call_nmi_hook(struct pt_regs *regs) #ifdef CONFIG_SMP void kgdb_roundup_cpus(unsigned long flags) { - smp_send_debugger_break(MSG_ALL_BUT_SELF); + smp_send_debugger_break(); } #endif @@ -142,7 +142,7 @@ static int kgdb_singlestep(struct pt_regs *regs) return 0; /* - * On Book E and perhaps other processsors, singlestep is handled on + * On Book E and perhaps other processors, singlestep is handled on * the critical exception stack. This causes current_thread_info() * to fail, since it it locates the thread_info by masking off * the low bits of the current stack pointer. We work around diff --git a/arch/powerpc/kernel/lparcfg.c b/arch/powerpc/kernel/lparcfg.c index 301db65f05a..84daabe2fcb 100644 --- a/arch/powerpc/kernel/lparcfg.c +++ b/arch/powerpc/kernel/lparcfg.c @@ -132,34 +132,6 @@ static int iseries_lparcfg_data(struct seq_file *m, void *v) /* * Methods used to fetch LPAR data when running on a pSeries platform. */ -/** - * h_get_mpp - * H_GET_MPP hcall returns info in 7 parms - */ -int h_get_mpp(struct hvcall_mpp_data *mpp_data) -{ - int rc; - unsigned long retbuf[PLPAR_HCALL9_BUFSIZE]; - - rc = plpar_hcall9(H_GET_MPP, retbuf); - - mpp_data->entitled_mem = retbuf[0]; - mpp_data->mapped_mem = retbuf[1]; - - mpp_data->group_num = (retbuf[2] >> 2 * 8) & 0xffff; - mpp_data->pool_num = retbuf[2] & 0xffff; - - mpp_data->mem_weight = (retbuf[3] >> 7 * 8) & 0xff; - mpp_data->unallocated_mem_weight = (retbuf[3] >> 6 * 8) & 0xff; - mpp_data->unallocated_entitlement = retbuf[3] & 0xffffffffffff; - - mpp_data->pool_size = retbuf[4]; - mpp_data->loan_request = retbuf[5]; - mpp_data->backing_mem = retbuf[6]; - - return rc; -} -EXPORT_SYMBOL(h_get_mpp); struct hvcall_ppp_data { u64 entitlement; @@ -345,6 +317,30 @@ static void parse_mpp_data(struct seq_file *m) seq_printf(m, "backing_memory=%ld bytes\n", mpp_data.backing_mem); } +/** + * parse_mpp_x_data + * Parse out data returned from h_get_mpp_x + */ +static void parse_mpp_x_data(struct seq_file *m) +{ + struct hvcall_mpp_x_data mpp_x_data; + + if (!firmware_has_feature(FW_FEATURE_XCMO)) + return; + if (h_get_mpp_x(&mpp_x_data)) + return; + + seq_printf(m, "coalesced_bytes=%ld\n", mpp_x_data.coalesced_bytes); + + if (mpp_x_data.pool_coalesced_bytes) + seq_printf(m, "pool_coalesced_bytes=%ld\n", + mpp_x_data.pool_coalesced_bytes); + if (mpp_x_data.pool_purr_cycles) + seq_printf(m, "coalesce_pool_purr=%ld\n", mpp_x_data.pool_purr_cycles); + if (mpp_x_data.pool_spurr_cycles) + seq_printf(m, "coalesce_pool_spurr=%ld\n", mpp_x_data.pool_spurr_cycles); +} + #define SPLPAR_CHARACTERISTICS_TOKEN 20 #define SPLPAR_MAXLENGTH 1026*(sizeof(char)) @@ -520,6 +516,7 @@ static int pseries_lparcfg_data(struct seq_file *m, void *v) parse_system_parameter_string(m); parse_ppp_data(m); parse_mpp_data(m); + parse_mpp_x_data(m); pseries_cmo_data(m); splpar_dispatch_data(m); diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index 094bd9821ad..998a1002860 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -694,6 +694,17 @@ _GLOBAL(kernel_thread) addi r1,r1,16 blr +#ifdef CONFIG_SMP +_GLOBAL(start_secondary_resume) + /* Reset stack */ + rlwinm r1,r1,0,0,(31-THREAD_SHIFT) /* current_thread_info() */ + addi r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD + li r3,0 + stw r3,0(r1) /* Zero the stack frame pointer */ + bl start_secondary + b . +#endif /* CONFIG_SMP */ + /* * This routine is just here to keep GCC happy - sigh... */ diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index 206a321a71d..e89df59cdc5 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -462,7 +462,8 @@ _GLOBAL(disable_kernel_fp) * wait for the flag to change, indicating this kernel is going away but * the slave code for the next one is at addresses 0 to 100. * - * This is used by all slaves. + * This is used by all slaves, even those that did not find a matching + * paca in the secondary startup code. * * Physical (hardware) cpu id should be in r3. */ @@ -471,10 +472,6 @@ _GLOBAL(kexec_wait) 1: mflr r5 addi r5,r5,kexec_flag-1b - li r4,KEXEC_STATE_REAL_MODE - stb r4,PACAKEXECSTATE(r13) - SYNC - 99: HMT_LOW #ifdef CONFIG_KEXEC /* use no memory without kexec */ lwz r4,0(r5) @@ -499,11 +496,17 @@ kexec_flag: * * get phys id from paca * switch to real mode + * mark the paca as no longer used * join other cpus in kexec_wait(phys_id) */ _GLOBAL(kexec_smp_wait) lhz r3,PACAHWCPUID(r13) bl real_mode + + li r4,KEXEC_STATE_REAL_MODE + stb r4,PACAKEXECSTATE(r13) + SYNC + b .kexec_wait /* diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index 10f0aadee95..efeb8818418 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -7,7 +7,7 @@ * 2 of the License, or (at your option) any later version. */ -#include <linux/threads.h> +#include <linux/smp.h> #include <linux/module.h> #include <linux/memblock.h> @@ -156,18 +156,29 @@ void __init initialise_paca(struct paca_struct *new_paca, int cpu) /* Put the paca pointer into r13 and SPRG_PACA */ void setup_paca(struct paca_struct *new_paca) { + /* Setup r13 */ local_paca = new_paca; - mtspr(SPRN_SPRG_PACA, local_paca); + #ifdef CONFIG_PPC_BOOK3E + /* On Book3E, initialize the TLB miss exception frames */ mtspr(SPRN_SPRG_TLB_EXFRAME, local_paca->extlb); +#else + /* In HV mode, we setup both HPACA and PACA to avoid problems + * if we do a GET_PACA() before the feature fixups have been + * applied + */ + if (cpu_has_feature(CPU_FTR_HVMODE_206)) + mtspr(SPRN_SPRG_HPACA, local_paca); #endif + mtspr(SPRN_SPRG_PACA, local_paca); + } static int __initdata paca_size; void __init allocate_pacas(void) { - int nr_cpus, cpu, limit; + int cpu, limit; /* * We can't take SLB misses on the paca, and we want to access them @@ -179,23 +190,18 @@ void __init allocate_pacas(void) if (firmware_has_feature(FW_FEATURE_ISERIES)) limit = min(limit, HvPagesToMap * HVPAGESIZE); - nr_cpus = NR_CPUS; - /* On iSeries we know we can never have more than 64 cpus */ - if (firmware_has_feature(FW_FEATURE_ISERIES)) - nr_cpus = min(64, nr_cpus); - - paca_size = PAGE_ALIGN(sizeof(struct paca_struct) * nr_cpus); + paca_size = PAGE_ALIGN(sizeof(struct paca_struct) * nr_cpu_ids); paca = __va(memblock_alloc_base(paca_size, PAGE_SIZE, limit)); memset(paca, 0, paca_size); printk(KERN_DEBUG "Allocated %u bytes for %d pacas at %p\n", - paca_size, nr_cpus, paca); + paca_size, nr_cpu_ids, paca); - allocate_lppacas(nr_cpus, limit); + allocate_lppacas(nr_cpu_ids, limit); /* Can't use for_each_*_cpu, as they aren't functional yet */ - for (cpu = 0; cpu < nr_cpus; cpu++) + for (cpu = 0; cpu < nr_cpu_ids; cpu++) initialise_paca(&paca[cpu], cpu); } diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c index d225d99fe39..6baabc13306 100644 --- a/arch/powerpc/kernel/pci_dn.c +++ b/arch/powerpc/kernel/pci_dn.c @@ -43,10 +43,9 @@ void * __devinit update_dn_pci_info(struct device_node *dn, void *data) const u32 *regs; struct pci_dn *pdn; - pdn = alloc_maybe_bootmem(sizeof(*pdn), GFP_KERNEL); + pdn = zalloc_maybe_bootmem(sizeof(*pdn), GFP_KERNEL); if (pdn == NULL) return NULL; - memset(pdn, 0, sizeof(*pdn)); dn->data = pdn; pdn->node = dn; pdn->phb = phb; diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c index ef3ef566235..7d28f540200 100644 --- a/arch/powerpc/kernel/ppc_ksyms.c +++ b/arch/powerpc/kernel/ppc_ksyms.c @@ -54,7 +54,6 @@ extern void single_step_exception(struct pt_regs *regs); extern int sys_sigreturn(struct pt_regs *regs); EXPORT_SYMBOL(clear_pages); -EXPORT_SYMBOL(copy_page); EXPORT_SYMBOL(ISA_DMA_THRESHOLD); EXPORT_SYMBOL(DMA_MODE_READ); EXPORT_SYMBOL(DMA_MODE_WRITE); @@ -88,9 +87,7 @@ EXPORT_SYMBOL(__copy_tofrom_user); EXPORT_SYMBOL(__clear_user); EXPORT_SYMBOL(__strncpy_from_user); EXPORT_SYMBOL(__strnlen_user); -#ifdef CONFIG_PPC64 -EXPORT_SYMBOL(copy_4K_page); -#endif +EXPORT_SYMBOL(copy_page); #if defined(CONFIG_PCI) && defined(CONFIG_PPC32) EXPORT_SYMBOL(isa_io_base); diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index f74f355a961..91e52df3d81 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -395,6 +395,9 @@ struct task_struct *__switch_to(struct task_struct *prev, struct thread_struct *new_thread, *old_thread; unsigned long flags; struct task_struct *last; +#ifdef CONFIG_PPC_BOOK3S_64 + struct ppc64_tlb_batch *batch; +#endif #ifdef CONFIG_SMP /* avoid complexity of lazy save/restore of fpu @@ -513,7 +516,17 @@ struct task_struct *__switch_to(struct task_struct *prev, old_thread->accum_tb += (current_tb - start_tb); new_thread->start_tb = current_tb; } -#endif +#endif /* CONFIG_PPC64 */ + +#ifdef CONFIG_PPC_BOOK3S_64 + batch = &__get_cpu_var(ppc64_tlb_batch); + if (batch->active) { + current_thread_info()->local_flags |= _TLF_LAZY_MMU; + if (batch->index) + __flush_tlb_pending(batch); + batch->active = 0; + } +#endif /* CONFIG_PPC_BOOK3S_64 */ local_irq_save(flags); @@ -528,6 +541,14 @@ struct task_struct *__switch_to(struct task_struct *prev, hard_irq_disable(); last = _switch(old_thread, new_thread); +#ifdef CONFIG_PPC_BOOK3S_64 + if (current_thread_info()->local_flags & _TLF_LAZY_MMU) { + current_thread_info()->local_flags &= ~_TLF_LAZY_MMU; + batch = &__get_cpu_var(ppc64_tlb_batch); + batch->active = 1; + } +#endif /* CONFIG_PPC_BOOK3S_64 */ + local_irq_restore(flags); return last; @@ -702,6 +723,8 @@ void prepare_to_copy(struct task_struct *tsk) /* * Copy a thread.. */ +extern unsigned long dscr_default; /* defined in arch/powerpc/kernel/sysfs.c */ + int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long unused, struct task_struct *p, struct pt_regs *regs) @@ -755,11 +778,11 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, _ALIGN_UP(sizeof(struct thread_info), 16); #ifdef CONFIG_PPC_STD_MMU_64 - if (cpu_has_feature(CPU_FTR_SLB)) { + if (mmu_has_feature(MMU_FTR_SLB)) { unsigned long sp_vsid; unsigned long llp = mmu_psize_defs[mmu_linear_psize].sllp; - if (cpu_has_feature(CPU_FTR_1T_SEGMENT)) + if (mmu_has_feature(MMU_FTR_1T_SEGMENT)) sp_vsid = get_kernel_vsid(sp, MMU_SEGSIZE_1T) << SLB_VSID_SHIFT_1T; else @@ -769,6 +792,20 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, p->thread.ksp_vsid = sp_vsid; } #endif /* CONFIG_PPC_STD_MMU_64 */ +#ifdef CONFIG_PPC64 + if (cpu_has_feature(CPU_FTR_DSCR)) { + if (current->thread.dscr_inherit) { + p->thread.dscr_inherit = 1; + p->thread.dscr = current->thread.dscr; + } else if (0 != dscr_default) { + p->thread.dscr_inherit = 1; + p->thread.dscr = dscr_default; + } else { + p->thread.dscr_inherit = 0; + p->thread.dscr = 0; + } + } +#endif /* * The PPC64 ABI makes use of a TOC to contain function diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index e74fa12afc8..8c3112a57cf 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -68,6 +68,7 @@ int __initdata iommu_force_on; unsigned long tce_alloc_start, tce_alloc_end; u64 ppc64_rma_size; #endif +static phys_addr_t first_memblock_size; static int __init early_parse_mem(char *p) { @@ -81,11 +82,29 @@ static int __init early_parse_mem(char *p) } early_param("mem", early_parse_mem); +/* + * overlaps_initrd - check for overlap with page aligned extension of + * initrd. + */ +static inline int overlaps_initrd(unsigned long start, unsigned long size) +{ +#ifdef CONFIG_BLK_DEV_INITRD + if (!initrd_start) + return 0; + + return (start + size) > _ALIGN_DOWN(initrd_start, PAGE_SIZE) && + start <= _ALIGN_UP(initrd_end, PAGE_SIZE); +#else + return 0; +#endif +} + /** * move_device_tree - move tree to an unused area, if needed. * * The device tree may be allocated beyond our memory limit, or inside the - * crash kernel region for kdump. If so, move it out of the way. + * crash kernel region for kdump, or within the page aligned range of initrd. + * If so, move it out of the way. */ static void __init move_device_tree(void) { @@ -98,7 +117,8 @@ static void __init move_device_tree(void) size = be32_to_cpu(initial_boot_params->totalsize); if ((memory_limit && (start + size) > PHYSICAL_START + memory_limit) || - overlaps_crashkernel(start, size)) { + 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; @@ -123,18 +143,19 @@ static void __init move_device_tree(void) */ static struct ibm_pa_feature { unsigned long cpu_features; /* CPU_FTR_xxx bit */ + unsigned long mmu_features; /* MMU_FTR_xxx bit */ unsigned int cpu_user_ftrs; /* PPC_FEATURE_xxx bit */ unsigned char pabyte; /* byte number in ibm,pa-features */ unsigned char pabit; /* bit number (big-endian) */ unsigned char invert; /* if 1, pa bit set => clear feature */ } ibm_pa_features[] __initdata = { - {0, PPC_FEATURE_HAS_MMU, 0, 0, 0}, - {0, PPC_FEATURE_HAS_FPU, 0, 1, 0}, - {CPU_FTR_SLB, 0, 0, 2, 0}, - {CPU_FTR_CTRL, 0, 0, 3, 0}, - {CPU_FTR_NOEXECUTE, 0, 0, 6, 0}, - {CPU_FTR_NODSISRALIGN, 0, 1, 1, 1}, - {CPU_FTR_CI_LARGE_PAGE, 0, 1, 2, 0}, + {0, 0, PPC_FEATURE_HAS_MMU, 0, 0, 0}, + {0, 0, PPC_FEATURE_HAS_FPU, 0, 1, 0}, + {0, MMU_FTR_SLB, 0, 0, 2, 0}, + {CPU_FTR_CTRL, 0, 0, 0, 3, 0}, + {CPU_FTR_NOEXECUTE, 0, 0, 0, 6, 0}, + {CPU_FTR_NODSISRALIGN, 0, 0, 1, 1, 1}, + {0, MMU_FTR_CI_LARGE_PAGE, 0, 1, 2, 0}, {CPU_FTR_REAL_LE, PPC_FEATURE_TRUE_LE, 5, 0, 0}, }; @@ -166,9 +187,11 @@ static void __init scan_features(unsigned long node, unsigned char *ftrs, if (bit ^ fp->invert) { cur_cpu_spec->cpu_features |= fp->cpu_features; cur_cpu_spec->cpu_user_features |= fp->cpu_user_ftrs; + cur_cpu_spec->mmu_features |= fp->mmu_features; } else { cur_cpu_spec->cpu_features &= ~fp->cpu_features; cur_cpu_spec->cpu_user_features &= ~fp->cpu_user_ftrs; + cur_cpu_spec->mmu_features &= ~fp->mmu_features; } } } @@ -268,13 +291,13 @@ static int __init early_init_dt_scan_cpus(unsigned long node, const char *uname, int depth, void *data) { - static int logical_cpuid = 0; char *type = of_get_flat_dt_prop(node, "device_type", NULL); const u32 *prop; const u32 *intserv; int i, nthreads; unsigned long len; - int found = 0; + int found = -1; + int found_thread = 0; /* We are scanning "cpu" nodes only */ if (type == NULL || strcmp(type, "cpu") != 0) @@ -298,11 +321,10 @@ 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 (initial_boot_params && initial_boot_params->version >= 2) { - if (intserv[i] == - initial_boot_params->boot_cpuid_phys) { - found = 1; - break; + if (initial_boot_params->version >= 2) { + if (intserv[i] == initial_boot_params->boot_cpuid_phys) { + found = boot_cpu_count; + found_thread = i; } } else { /* @@ -311,23 +333,20 @@ static int __init early_init_dt_scan_cpus(unsigned long node, * off secondary threads. */ if (of_get_flat_dt_prop(node, - "linux,boot-cpu", NULL) != NULL) { - found = 1; - break; - } + "linux,boot-cpu", NULL) != NULL) + found = boot_cpu_count; } - #ifdef CONFIG_SMP /* logical cpu id is always 0 on UP kernels */ - logical_cpuid++; + boot_cpu_count++; #endif } - if (found) { - DBG("boot cpu: logical %d physical %d\n", logical_cpuid, - intserv[i]); - boot_cpuid = logical_cpuid; - set_hard_smp_processor_id(boot_cpuid, intserv[i]); + if (found >= 0) { + DBG("boot cpu: logical %d physical %d\n", found, + intserv[found_thread]); + boot_cpuid = found; + set_hard_smp_processor_id(found, intserv[found_thread]); /* * PAPR defines "logical" PVR values for cpus that @@ -509,11 +528,14 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size) size = 0x80000000ul - base; } #endif - - /* First MEMBLOCK added, do some special initializations */ - if (memstart_addr == ~(phys_addr_t)0) - setup_initial_memory_limit(base, size); - memstart_addr = min((u64)memstart_addr, base); + /* Keep track of the beginning of memory -and- the size of + * the very first block in the device-tree as it represents + * the RMA on ppc64 server + */ + if (base < memstart_addr) { + memstart_addr = base; + first_memblock_size = size; + } /* Add the chunk to the MEMBLOCK list */ memblock_add(base, size); @@ -552,7 +574,9 @@ static void __init early_reserve_mem(void) #ifdef CONFIG_BLK_DEV_INITRD /* then reserve the initrd, if any */ if (initrd_start && (initrd_end > initrd_start)) - memblock_reserve(__pa(initrd_start), initrd_end - initrd_start); + memblock_reserve(_ALIGN_DOWN(__pa(initrd_start), PAGE_SIZE), + _ALIGN_UP(initrd_end, PAGE_SIZE) - + _ALIGN_DOWN(initrd_start, PAGE_SIZE)); #endif /* CONFIG_BLK_DEV_INITRD */ #ifdef CONFIG_PPC32 @@ -691,13 +715,14 @@ void __init early_init_devtree(void *params) * device-tree, including the platform type, initrd location and * size, TCE reserve, and more ... */ - of_scan_flat_dt(early_init_dt_scan_chosen_ppc, NULL); + of_scan_flat_dt(early_init_dt_scan_chosen_ppc, cmd_line); /* Scan memory nodes and rebuild MEMBLOCKs */ memblock_init(); of_scan_flat_dt(early_init_dt_scan_root, NULL); of_scan_flat_dt(early_init_dt_scan_memory_ppc, NULL); + setup_initial_memory_limit(memstart_addr, first_memblock_size); /* Save command line for /proc/cmdline and then parse parameters */ strlcpy(boot_command_line, cmd_line, COMMAND_LINE_SIZE); diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 941ff4dbc56..c016033ba78 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -335,6 +335,7 @@ static void __init prom_printf(const char *format, ...) const char *p, *q, *s; va_list args; unsigned long v; + long vs; struct prom_t *_prom = &RELOC(prom); va_start(args, format); @@ -368,12 +369,35 @@ static void __init prom_printf(const char *format, ...) v = va_arg(args, unsigned long); prom_print_hex(v); break; + case 'd': + ++q; + vs = va_arg(args, int); + if (vs < 0) { + prom_print(RELOC("-")); + vs = -vs; + } + prom_print_dec(vs); + break; case 'l': ++q; - if (*q == 'u') { /* '%lu' */ + if (*q == 0) + break; + else if (*q == 'x') { + ++q; + v = va_arg(args, unsigned long); + prom_print_hex(v); + } else if (*q == 'u') { /* '%lu' */ ++q; v = va_arg(args, unsigned long); prom_print_dec(v); + } else if (*q == 'd') { /* %ld */ + ++q; + vs = va_arg(args, long); + if (vs < 0) { + prom_print(RELOC("-")); + vs = -vs; + } + prom_print_dec(vs); } break; } @@ -676,8 +700,10 @@ static void __init early_cmdline_parse(void) #endif /* CONFIG_PCI_MSI */ #ifdef CONFIG_PPC_SMLPAR #define OV5_CMO 0x80 /* Cooperative Memory Overcommitment */ +#define OV5_XCMO 0x40 /* Page Coalescing */ #else #define OV5_CMO 0x00 +#define OV5_XCMO 0x00 #endif #define OV5_TYPE1_AFFINITY 0x80 /* Type 1 NUMA affinity */ @@ -732,7 +758,7 @@ static unsigned char ibm_architecture_vec[] = { OV5_LPAR | OV5_SPLPAR | OV5_LARGE_PAGES | OV5_DRCONF_MEMORY | OV5_DONATE_DEDICATE_CPU | OV5_MSI, 0, - OV5_CMO, + OV5_CMO | OV5_XCMO, OV5_TYPE1_AFFINITY, 0, 0, diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index a6ae1cfad86..cb22024f2b4 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -29,6 +29,7 @@ #include <linux/signal.h> #include <linux/seccomp.h> #include <linux/audit.h> +#include <trace/syscall.h> #ifdef CONFIG_PPC32 #include <linux/module.h> #endif @@ -40,6 +41,9 @@ #include <asm/pgtable.h> #include <asm/system.h> +#define CREATE_TRACE_POINTS +#include <trace/events/syscalls.h> + /* * The parameter save area on the stack is used to store arguments being passed * to callee function and is located at fixed offset from stack pointer. @@ -1710,6 +1714,9 @@ long do_syscall_trace_enter(struct pt_regs *regs) */ ret = -1L; + if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) + trace_sys_enter(regs, regs->gpr[0]); + if (unlikely(current->audit_context)) { #ifdef CONFIG_PPC64 if (!is_32bit_task()) @@ -1738,6 +1745,9 @@ void do_syscall_trace_leave(struct pt_regs *regs) audit_syscall_exit((regs->ccr&0x10000000)?AUDITSC_FAILURE:AUDITSC_SUCCESS, regs->result); + if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) + trace_sys_exit(regs, regs->result); + step = test_thread_flag(TIF_SINGLESTEP); if (step || test_thread_flag(TIF_SYSCALL_TRACE)) tracehook_report_syscall_exit(regs, step); diff --git a/arch/powerpc/kernel/rtas-rtc.c b/arch/powerpc/kernel/rtas-rtc.c index 77578c093dd..c57c19358a2 100644 --- a/arch/powerpc/kernel/rtas-rtc.c +++ b/arch/powerpc/kernel/rtas-rtc.c @@ -4,6 +4,7 @@ #include <linux/init.h> #include <linux/rtc.h> #include <linux/delay.h> +#include <linux/ratelimit.h> #include <asm/prom.h> #include <asm/rtas.h> #include <asm/time.h> @@ -29,9 +30,10 @@ unsigned long __init rtas_get_boot_time(void) } } while (wait_time && (get_tb() < max_wait_tb)); - if (error != 0 && printk_ratelimit()) { - printk(KERN_WARNING "error: reading the clock failed (%d)\n", - error); + if (error != 0) { + printk_ratelimited(KERN_WARNING + "error: reading the clock failed (%d)\n", + error); return 0; } @@ -55,19 +57,21 @@ void rtas_get_rtc_time(struct rtc_time *rtc_tm) wait_time = rtas_busy_delay_time(error); if (wait_time) { - if (in_interrupt() && printk_ratelimit()) { + if (in_interrupt()) { memset(rtc_tm, 0, sizeof(struct rtc_time)); - printk(KERN_WARNING "error: reading clock" - " would delay interrupt\n"); + printk_ratelimited(KERN_WARNING + "error: reading clock " + "would delay interrupt\n"); return; /* delay not allowed */ } msleep(wait_time); } } while (wait_time && (get_tb() < max_wait_tb)); - if (error != 0 && printk_ratelimit()) { - printk(KERN_WARNING "error: reading the clock failed (%d)\n", - error); + if (error != 0) { + printk_ratelimited(KERN_WARNING + "error: reading the clock failed (%d)\n", + error); return; } @@ -99,9 +103,10 @@ int rtas_set_rtc_time(struct rtc_time *tm) } } while (wait_time && (get_tb() < max_wait_tb)); - if (error != 0 && printk_ratelimit()) - printk(KERN_WARNING "error: setting the clock failed (%d)\n", - error); + if (error != 0) + printk_ratelimited(KERN_WARNING + "error: setting the clock failed (%d)\n", + error); return 0; } diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 2097f2b3cba..271ff6318ed 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -42,6 +42,7 @@ #include <asm/time.h> #include <asm/mmu.h> #include <asm/topology.h> +#include <asm/pSeries_reconfig.h> struct rtas_t rtas = { .lock = __ARCH_SPIN_LOCK_UNLOCKED @@ -494,7 +495,7 @@ unsigned int rtas_busy_delay(int status) might_sleep(); ms = rtas_busy_delay_time(status); - if (ms) + if (ms && need_resched()) msleep(ms); return ms; @@ -731,6 +732,7 @@ static int __rtas_suspend_last_cpu(struct rtas_suspend_me_data *data, int wake_w atomic_set(&data->error, rc); start_topology_update(); + pSeries_coalesce_init(); if (wake_when_done) { atomic_set(&data->done, 1); diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 21f30cb6807..79fca2651b6 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -381,7 +381,7 @@ static void __init cpu_init_thread_core_maps(int tpc) int i; threads_per_core = tpc; - threads_core_mask = CPU_MASK_NONE; + cpumask_clear(&threads_core_mask); /* This implementation only supports power of 2 number of threads * for simplicity and performance @@ -390,7 +390,7 @@ static void __init cpu_init_thread_core_maps(int tpc) BUG_ON(tpc != (1 << threads_shift)); for (i = 0; i < tpc; i++) - cpu_set(i, threads_core_mask); + cpumask_set_cpu(i, &threads_core_mask); printk(KERN_INFO "CPU maps initialized for %d thread%s per core\n", tpc, tpc > 1 ? "s" : ""); @@ -404,7 +404,7 @@ static void __init cpu_init_thread_core_maps(int tpc) * cpu_present_mask * * Having the possible map set up early allows us to restrict allocations - * of things like irqstacks to num_possible_cpus() rather than NR_CPUS. + * of things like irqstacks to nr_cpu_ids rather than NR_CPUS. * * We do not initialize the online map here; cpus set their own bits in * cpu_online_mask as they come up. @@ -424,7 +424,7 @@ void __init smp_setup_cpu_maps(void) DBG("smp_setup_cpu_maps()\n"); - while ((dn = of_find_node_by_type(dn, "cpu")) && cpu < NR_CPUS) { + while ((dn = of_find_node_by_type(dn, "cpu")) && cpu < nr_cpu_ids) { const int *intserv; int j, len; @@ -443,7 +443,7 @@ void __init smp_setup_cpu_maps(void) intserv = &cpu; /* assume logical == phys */ } - for (j = 0; j < nthreads && cpu < NR_CPUS; j++) { + for (j = 0; j < nthreads && cpu < nr_cpu_ids; j++) { DBG(" thread %d -> cpu %d (hard id %d)\n", j, cpu, intserv[j]); set_cpu_present(cpu, true); @@ -483,12 +483,12 @@ void __init smp_setup_cpu_maps(void) if (cpu_has_feature(CPU_FTR_SMT)) maxcpus *= nthreads; - if (maxcpus > NR_CPUS) { + if (maxcpus > nr_cpu_ids) { printk(KERN_WARNING "Partition configured for %d cpus, " "operating system maximum is %d.\n", - maxcpus, NR_CPUS); - maxcpus = NR_CPUS; + maxcpus, nr_cpu_ids); + maxcpus = nr_cpu_ids; } else printk(KERN_INFO "Partition configured for %d cpus.\n", maxcpus); @@ -510,7 +510,7 @@ void __init smp_setup_cpu_maps(void) cpu_init_thread_core_maps(nthreads); /* Now that possible cpus are set, set nr_cpu_ids for later use */ - nr_cpu_ids = find_last_bit(cpumask_bits(cpu_possible_mask),NR_CPUS) + 1; + setup_nr_cpu_ids(); free_unused_pacas(); } @@ -602,6 +602,10 @@ int check_legacy_ioport(unsigned long base_port) * name instead */ if (!np) np = of_find_node_by_name(NULL, "8042"); + if (np) { + of_i8042_kbd_irq = 1; + of_i8042_aux_irq = 12; + } break; case FDC_BASE: /* FDC1 */ np = of_find_node_by_type(NULL, "fdc"); diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index 1d2fbc90530..620d792b52e 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -48,6 +48,7 @@ extern void bootx_init(unsigned long r4, unsigned long phys); int boot_cpuid = -1; EXPORT_SYMBOL_GPL(boot_cpuid); +int __initdata boot_cpu_count; int boot_cpuid_phys; int smp_hw_index[NR_CPUS]; diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 5a0401fcaeb..a88bf2713d4 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -62,6 +62,7 @@ #include <asm/udbg.h> #include <asm/kexec.h> #include <asm/mmu_context.h> +#include <asm/code-patching.h> #include "setup.h" @@ -72,6 +73,7 @@ #endif int boot_cpuid = 0; +int __initdata boot_cpu_count; u64 ppc64_pft_size; /* Pick defaults since we might want to patch instructions @@ -233,6 +235,7 @@ void early_setup_secondary(void) void smp_release_cpus(void) { unsigned long *ptr; + int i; DBG(" -> smp_release_cpus()\n"); @@ -245,7 +248,16 @@ void smp_release_cpus(void) ptr = (unsigned long *)((unsigned long)&__secondary_hold_spinloop - PHYSICAL_START); *ptr = __pa(generic_secondary_smp_init); - mb(); + + /* And wait a bit for them to catch up */ + for (i = 0; i < 100000; i++) { + mb(); + HMT_low(); + if (boot_cpu_count == 0) + break; + udelay(1); + } + DBG("boot_cpu_count = %d\n", boot_cpu_count); DBG(" <- smp_release_cpus()\n"); } @@ -423,17 +435,30 @@ void __init setup_system(void) DBG(" <- setup_system()\n"); } -static u64 slb0_limit(void) +/* This returns the limit below which memory accesses to the linear + * mapping are guarnateed not to cause a TLB or SLB miss. This is + * used to allocate interrupt or emergency stacks for which our + * exception entry path doesn't deal with being interrupted. + */ +static u64 safe_stack_limit(void) { - if (cpu_has_feature(CPU_FTR_1T_SEGMENT)) { +#ifdef CONFIG_PPC_BOOK3E + /* Freescale BookE bolts the entire linear mapping */ + if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) + return linear_map_top; + /* Other BookE, we assume the first GB is bolted */ + return 1ul << 30; +#else + /* BookS, the first segment is bolted */ + if (mmu_has_feature(MMU_FTR_1T_SEGMENT)) return 1UL << SID_SHIFT_1T; - } return 1UL << SID_SHIFT; +#endif } static void __init irqstack_early_init(void) { - u64 limit = slb0_limit(); + u64 limit = safe_stack_limit(); unsigned int i; /* @@ -453,6 +478,9 @@ static void __init irqstack_early_init(void) #ifdef CONFIG_PPC_BOOK3E static void __init exc_lvl_early_init(void) { + extern unsigned int interrupt_base_book3e; + extern unsigned int exc_debug_debug_book3e; + unsigned int i; for_each_possible_cpu(i) { @@ -463,6 +491,10 @@ static void __init exc_lvl_early_init(void) mcheckirq_ctx[i] = (struct thread_info *) __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE)); } + + if (cpu_has_feature(CPU_FTR_DEBUG_LVL_EXC)) + patch_branch(&interrupt_base_book3e + (0x040 / 4) + 1, + (unsigned long)&exc_debug_debug_book3e, 0); } #else #define exc_lvl_early_init() @@ -486,7 +518,7 @@ static void __init emergency_stack_init(void) * bringup, we need to get at them in real mode. This means they * must also be within the RMO region. */ - limit = min(slb0_limit(), ppc64_rma_size); + limit = min(safe_stack_limit(), ppc64_rma_size); for_each_possible_cpu(i) { unsigned long sp; diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index b96a3a010c2..78b76dc54df 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -25,6 +25,7 @@ #include <linux/errno.h> #include <linux/elf.h> #include <linux/ptrace.h> +#include <linux/ratelimit.h> #ifdef CONFIG_PPC64 #include <linux/syscalls.h> #include <linux/compat.h> @@ -892,11 +893,12 @@ badframe: printk("badframe in handle_rt_signal, regs=%p frame=%p newsp=%lx\n", regs, frame, newsp); #endif - if (show_unhandled_signals && printk_ratelimit()) - printk(KERN_INFO "%s[%d]: bad frame in handle_rt_signal32: " - "%p nip %08lx lr %08lx\n", - current->comm, current->pid, - addr, regs->nip, regs->link); + if (show_unhandled_signals) + printk_ratelimited(KERN_INFO + "%s[%d]: bad frame in handle_rt_signal32: " + "%p nip %08lx lr %08lx\n", + current->comm, current->pid, + addr, regs->nip, regs->link); force_sigsegv(sig, current); return 0; @@ -1058,11 +1060,12 @@ long sys_rt_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8, return 0; bad: - if (show_unhandled_signals && printk_ratelimit()) - printk(KERN_INFO "%s[%d]: bad frame in sys_rt_sigreturn: " - "%p nip %08lx lr %08lx\n", - current->comm, current->pid, - rt_sf, regs->nip, regs->link); + if (show_unhandled_signals) + printk_ratelimited(KERN_INFO + "%s[%d]: bad frame in sys_rt_sigreturn: " + "%p nip %08lx lr %08lx\n", + current->comm, current->pid, + rt_sf, regs->nip, regs->link); force_sig(SIGSEGV, current); return 0; @@ -1149,12 +1152,12 @@ int sys_debug_setcontext(struct ucontext __user *ctx, * We kill the task with a SIGSEGV in this situation. */ if (do_setcontext(ctx, regs, 1)) { - if (show_unhandled_signals && printk_ratelimit()) - printk(KERN_INFO "%s[%d]: bad frame in " - "sys_debug_setcontext: %p nip %08lx " - "lr %08lx\n", - current->comm, current->pid, - ctx, regs->nip, regs->link); + if (show_unhandled_signals) + printk_ratelimited(KERN_INFO "%s[%d]: bad frame in " + "sys_debug_setcontext: %p nip %08lx " + "lr %08lx\n", + current->comm, current->pid, + ctx, regs->nip, regs->link); force_sig(SIGSEGV, current); goto out; @@ -1236,11 +1239,12 @@ badframe: printk("badframe in handle_signal, regs=%p frame=%p newsp=%lx\n", regs, frame, newsp); #endif - if (show_unhandled_signals && printk_ratelimit()) - printk(KERN_INFO "%s[%d]: bad frame in handle_signal32: " - "%p nip %08lx lr %08lx\n", - current->comm, current->pid, - frame, regs->nip, regs->link); + if (show_unhandled_signals) + printk_ratelimited(KERN_INFO + "%s[%d]: bad frame in handle_signal32: " + "%p nip %08lx lr %08lx\n", + current->comm, current->pid, + frame, regs->nip, regs->link); force_sigsegv(sig, current); return 0; @@ -1288,11 +1292,12 @@ long sys_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8, return 0; badframe: - if (show_unhandled_signals && printk_ratelimit()) - printk(KERN_INFO "%s[%d]: bad frame in sys_sigreturn: " - "%p nip %08lx lr %08lx\n", - current->comm, current->pid, - addr, regs->nip, regs->link); + if (show_unhandled_signals) + printk_ratelimited(KERN_INFO + "%s[%d]: bad frame in sys_sigreturn: " + "%p nip %08lx lr %08lx\n", + current->comm, current->pid, + addr, regs->nip, regs->link); force_sig(SIGSEGV, current); return 0; diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 27c4a4584f8..e91c736cc84 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -24,6 +24,7 @@ #include <linux/elf.h> #include <linux/ptrace.h> #include <linux/module.h> +#include <linux/ratelimit.h> #include <asm/sigcontext.h> #include <asm/ucontext.h> @@ -380,10 +381,10 @@ badframe: 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_ratelimit()) - printk(regs->msr & MSR_SF ? fmt64 : fmt32, - current->comm, current->pid, "rt_sigreturn", - (long)uc, regs->nip, regs->link); + if (show_unhandled_signals) + printk_ratelimited(regs->msr & MSR_64BIT ? fmt64 : fmt32, + current->comm, current->pid, "rt_sigreturn", + (long)uc, regs->nip, regs->link); force_sig(SIGSEGV, current); return 0; @@ -468,10 +469,10 @@ badframe: printk("badframe in setup_rt_frame, regs=%p frame=%p newsp=%lx\n", regs, frame, newsp); #endif - if (show_unhandled_signals && printk_ratelimit()) - printk(regs->msr & MSR_SF ? fmt64 : fmt32, - current->comm, current->pid, "setup_rt_frame", - (long)frame, regs->nip, regs->link); + if (show_unhandled_signals) + printk_ratelimited(regs->msr & MSR_64BIT ? fmt64 : fmt32, + current->comm, current->pid, "setup_rt_frame", + (long)frame, regs->nip, regs->link); force_sigsegv(signr, current); return 0; diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index cbdbb14be4b..8ebc6700b98 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -95,7 +95,7 @@ int smt_enabled_at_boot = 1; static void (*crash_ipi_function_ptr)(struct pt_regs *) = NULL; #ifdef CONFIG_PPC64 -void __devinit smp_generic_kick_cpu(int nr) +int __devinit smp_generic_kick_cpu(int nr) { BUG_ON(nr < 0 || nr >= NR_CPUS); @@ -106,37 +106,10 @@ void __devinit smp_generic_kick_cpu(int nr) */ paca[nr].cpu_start = 1; smp_mb(); -} -#endif -void smp_message_recv(int msg) -{ - switch(msg) { - case PPC_MSG_CALL_FUNCTION: - generic_smp_call_function_interrupt(); - break; - case PPC_MSG_RESCHEDULE: - /* we notice need_resched on exit */ - break; - case PPC_MSG_CALL_FUNC_SINGLE: - generic_smp_call_function_single_interrupt(); - break; - case PPC_MSG_DEBUGGER_BREAK: - if (crash_ipi_function_ptr) { - crash_ipi_function_ptr(get_irq_regs()); - break; - } -#ifdef CONFIG_DEBUGGER - debugger_ipi(get_irq_regs()); - break; -#endif /* CONFIG_DEBUGGER */ - /* FALLTHROUGH */ - default: - printk("SMP %d: smp_message_recv(): unknown msg %d\n", - smp_processor_id(), msg); - break; - } + return 0; } +#endif static irqreturn_t call_function_action(int irq, void *data) { @@ -146,7 +119,7 @@ static irqreturn_t call_function_action(int irq, void *data) static irqreturn_t reschedule_action(int irq, void *data) { - /* we just need the return path side effect of checking need_resched */ + scheduler_ipi(); return IRQ_HANDLED; } @@ -158,7 +131,15 @@ static irqreturn_t call_function_single_action(int irq, void *data) static irqreturn_t debug_ipi_action(int irq, void *data) { - smp_message_recv(PPC_MSG_DEBUGGER_BREAK); + if (crash_ipi_function_ptr) { + crash_ipi_function_ptr(get_irq_regs()); + return IRQ_HANDLED; + } + +#ifdef CONFIG_DEBUGGER + debugger_ipi(get_irq_regs()); +#endif /* CONFIG_DEBUGGER */ + return IRQ_HANDLED; } @@ -197,6 +178,66 @@ int smp_request_message_ipi(int virq, int msg) return err; } +#ifdef CONFIG_PPC_SMP_MUXED_IPI +struct cpu_messages { + int messages; /* current messages */ + unsigned long data; /* data for cause ipi */ +}; +static DEFINE_PER_CPU_SHARED_ALIGNED(struct cpu_messages, ipi_message); + +void smp_muxed_ipi_set_data(int cpu, unsigned long data) +{ + struct cpu_messages *info = &per_cpu(ipi_message, cpu); + + info->data = data; +} + +void smp_muxed_ipi_message_pass(int cpu, int msg) +{ + struct cpu_messages *info = &per_cpu(ipi_message, cpu); + char *message = (char *)&info->messages; + + message[msg] = 1; + mb(); + smp_ops->cause_ipi(cpu, info->data); +} + +void smp_muxed_ipi_resend(void) +{ + struct cpu_messages *info = &__get_cpu_var(ipi_message); + + if (info->messages) + smp_ops->cause_ipi(smp_processor_id(), info->data); +} + +irqreturn_t smp_ipi_demux(void) +{ + struct cpu_messages *info = &__get_cpu_var(ipi_message); + unsigned int all; + + mb(); /* order any irq clear */ + + do { + all = xchg_local(&info->messages, 0); + +#ifdef __BIG_ENDIAN + if (all & (1 << (24 - 8 * PPC_MSG_CALL_FUNCTION))) + generic_smp_call_function_interrupt(); + if (all & (1 << (24 - 8 * PPC_MSG_RESCHEDULE))) + scheduler_ipi(); + if (all & (1 << (24 - 8 * PPC_MSG_CALL_FUNC_SINGLE))) + generic_smp_call_function_single_interrupt(); + if (all & (1 << (24 - 8 * PPC_MSG_DEBUGGER_BREAK))) + debug_ipi_action(0, NULL); +#else +#error Unsupported ENDIAN +#endif + } while (info->messages); + + return IRQ_HANDLED; +} +#endif /* CONFIG_PPC_SMP_MUXED_IPI */ + void smp_send_reschedule(int cpu) { if (likely(smp_ops)) @@ -216,11 +257,18 @@ void arch_send_call_function_ipi_mask(const struct cpumask *mask) smp_ops->message_pass(cpu, PPC_MSG_CALL_FUNCTION); } -#ifdef CONFIG_DEBUGGER -void smp_send_debugger_break(int cpu) +#if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC) +void smp_send_debugger_break(void) { - if (likely(smp_ops)) - smp_ops->message_pass(cpu, PPC_MSG_DEBUGGER_BREAK); + int cpu; + int me = raw_smp_processor_id(); + + if (unlikely(!smp_ops)) + return; + + for_each_online_cpu(cpu) + if (cpu != me) + smp_ops->message_pass(cpu, PPC_MSG_DEBUGGER_BREAK); } #endif @@ -228,9 +276,9 @@ void smp_send_debugger_break(int cpu) void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *)) { crash_ipi_function_ptr = crash_ipi_callback; - if (crash_ipi_callback && smp_ops) { + if (crash_ipi_callback) { mb(); - smp_ops->message_pass(MSG_ALL_BUT_SELF, PPC_MSG_DEBUGGER_BREAK); + smp_send_debugger_break(); } } #endif @@ -410,8 +458,6 @@ int __cpuinit __cpu_up(unsigned int cpu) { int rc, c; - secondary_ti = current_set[cpu]; - if (smp_ops == NULL || (smp_ops->cpu_bootable && !smp_ops->cpu_bootable(cpu))) return -EINVAL; @@ -421,6 +467,8 @@ int __cpuinit __cpu_up(unsigned int cpu) if (rc) return rc; + secondary_ti = current_set[cpu]; + /* Make sure callin-map entry is 0 (can be leftover a CPU * hotplug */ @@ -434,7 +482,11 @@ int __cpuinit __cpu_up(unsigned int cpu) /* wake up cpus */ DBG("smp: kicking cpu %d\n", cpu); - smp_ops->kick_cpu(cpu); + rc = smp_ops->kick_cpu(cpu); + if (rc) { + pr_err("smp: failed starting cpu %d (rc %d)\n", cpu, rc); + return rc; + } /* * wait to see if the cpu made a callin (is actually up). @@ -507,7 +559,7 @@ int cpu_first_thread_of_core(int core) } EXPORT_SYMBOL_GPL(cpu_first_thread_of_core); -/* Must be called when no change can occur to cpu_present_map, +/* Must be called when no change can occur to cpu_present_mask, * i.e. during cpu online or offline. */ static struct device_node *cpu_to_l2cache(int cpu) @@ -608,7 +660,7 @@ void __init smp_cpus_done(unsigned int max_cpus) * se we pin us down to CPU 0 for a short while */ alloc_cpumask_var(&old_mask, GFP_NOWAIT); - cpumask_copy(old_mask, ¤t->cpus_allowed); + cpumask_copy(old_mask, tsk_cpus_allowed(current)); set_cpus_allowed_ptr(current, cpumask_of(boot_cpuid)); if (smp_ops && smp_ops->setup_cpu) diff --git a/arch/powerpc/kernel/swsusp.c b/arch/powerpc/kernel/swsusp.c index 560c9611950..aa17b76dd42 100644 --- a/arch/powerpc/kernel/swsusp.c +++ b/arch/powerpc/kernel/swsusp.c @@ -10,7 +10,6 @@ */ #include <linux/sched.h> -#include <asm/suspend.h> #include <asm/system.h> #include <asm/current.h> #include <asm/mmu_context.h> diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index c0d8c2006bf..f0f2199e64e 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -182,6 +182,41 @@ static SYSDEV_ATTR(mmcra, 0600, show_mmcra, store_mmcra); static SYSDEV_ATTR(spurr, 0600, show_spurr, NULL); static SYSDEV_ATTR(dscr, 0600, show_dscr, store_dscr); static SYSDEV_ATTR(purr, 0600, show_purr, store_purr); + +unsigned long dscr_default = 0; +EXPORT_SYMBOL(dscr_default); + +static ssize_t show_dscr_default(struct sysdev_class *class, + struct sysdev_class_attribute *attr, char *buf) +{ + return sprintf(buf, "%lx\n", dscr_default); +} + +static ssize_t __used store_dscr_default(struct sysdev_class *class, + struct sysdev_class_attribute *attr, const char *buf, + size_t count) +{ + unsigned long val; + int ret = 0; + + ret = sscanf(buf, "%lx", &val); + if (ret != 1) + return -EINVAL; + dscr_default = val; + + return count; +} + +static SYSDEV_CLASS_ATTR(dscr_default, 0600, + show_dscr_default, store_dscr_default); + +static void sysfs_create_dscr_default(void) +{ + int err = 0; + if (cpu_has_feature(CPU_FTR_DSCR)) + err = sysfs_create_file(&cpu_sysdev_class.kset.kobj, + &attr_dscr_default.attr); +} #endif /* CONFIG_PPC64 */ #ifdef HAS_PPC_PMC_PA6T @@ -617,6 +652,9 @@ static int __init topology_init(void) if (cpu_online(cpu)) register_cpu_online(cpu); } +#ifdef CONFIG_PPC64 + sysfs_create_dscr_default(); +#endif /* CONFIG_PPC64 */ return 0; } diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 5ddb801bc15..1a0141426cd 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -34,6 +34,7 @@ #include <linux/bug.h> #include <linux/kdebug.h> #include <linux/debugfs.h> +#include <linux/ratelimit.h> #include <asm/emulated_ops.h> #include <asm/pgtable.h> @@ -55,6 +56,7 @@ #endif #include <asm/kexec.h> #include <asm/ppc-opcode.h> +#include <asm/rio.h> #if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC) int (*__debugger)(struct pt_regs *regs) __read_mostly; @@ -143,7 +145,6 @@ int die(const char *str, struct pt_regs *regs, long err) #endif printk("%s\n", ppc_md.name ? ppc_md.name : ""); - sysfs_printk_last_file(); if (notify_die(DIE_OOPS, str, regs, err, 255, SIGSEGV) == NOTIFY_STOP) return 1; @@ -197,12 +198,11 @@ void _exception(int signr, struct pt_regs *regs, int code, unsigned long addr) if (die("Exception in kernel mode", regs, signr)) return; } else if (show_unhandled_signals && - unhandled_signal(current, signr) && - printk_ratelimit()) { - printk(regs->msr & MSR_SF ? fmt64 : fmt32, - current->comm, current->pid, signr, - addr, regs->nip, regs->link, code); - } + unhandled_signal(current, signr)) { + printk_ratelimited(regs->msr & MSR_64BIT ? fmt64 : fmt32, + current->comm, current->pid, signr, + addr, regs->nip, regs->link, code); + } memset(&info, 0, sizeof(info)); info.si_signo = signr; @@ -221,7 +221,7 @@ void system_reset_exception(struct pt_regs *regs) } #ifdef CONFIG_KEXEC - cpu_set(smp_processor_id(), cpus_in_sr); + cpumask_set_cpu(smp_processor_id(), &cpus_in_sr); #endif die("System Reset", regs, SIGABRT); @@ -425,6 +425,12 @@ int machine_check_e500mc(struct pt_regs *regs) unsigned long reason = mcsr; int recoverable = 1; + if (reason & MCSR_LD) { + recoverable = fsl_rio_mcheck_exception(regs); + if (recoverable == 1) + goto silent_out; + } + printk("Machine check in kernel mode.\n"); printk("Caused by (from MCSR=%lx): ", reason); @@ -500,6 +506,7 @@ int machine_check_e500mc(struct pt_regs *regs) reason & MCSR_MEA ? "Effective" : "Physical", addr); } +silent_out: mtspr(SPRN_MCSR, mcsr); return mfspr(SPRN_MCSR) == 0 && recoverable; } @@ -508,6 +515,11 @@ int machine_check_e500(struct pt_regs *regs) { unsigned long reason = get_mc_reason(regs); + if (reason & MCSR_BUS_RBERR) { + if (fsl_rio_mcheck_exception(regs)) + return 1; + } + printk("Machine check in kernel mode.\n"); printk("Caused by (from MCSR=%lx): ", reason); @@ -909,6 +921,26 @@ static int emulate_instruction(struct pt_regs *regs) return emulate_isel(regs, instword); } +#ifdef CONFIG_PPC64 + /* Emulate the mfspr rD, DSCR. */ + if (((instword & PPC_INST_MFSPR_DSCR_MASK) == PPC_INST_MFSPR_DSCR) && + cpu_has_feature(CPU_FTR_DSCR)) { + PPC_WARN_EMULATED(mfdscr, regs); + rd = (instword >> 21) & 0x1f; + regs->gpr[rd] = mfspr(SPRN_DSCR); + return 0; + } + /* Emulate the mtspr DSCR, rD. */ + if (((instword & PPC_INST_MTSPR_DSCR_MASK) == PPC_INST_MTSPR_DSCR) && + cpu_has_feature(CPU_FTR_DSCR)) { + PPC_WARN_EMULATED(mtdscr, regs); + rd = (instword >> 21) & 0x1f; + mtspr(SPRN_DSCR, regs->gpr[rd]); + current->thread.dscr_inherit = 1; + return 0; + } +#endif + return -EINVAL; } @@ -1310,9 +1342,8 @@ void altivec_assist_exception(struct pt_regs *regs) } else { /* didn't recognize the instruction */ /* XXX quick hack for now: set the non-Java bit in the VSCR */ - if (printk_ratelimit()) - printk(KERN_ERR "Unrecognized altivec instruction " - "in %s at %lx\n", current->comm, regs->nip); + printk_ratelimited(KERN_ERR "Unrecognized altivec instruction " + "in %s at %lx\n", current->comm, regs->nip); current->thread.vscr.u[3] |= 0x10000; } } @@ -1506,15 +1537,18 @@ struct ppc_emulated ppc_emulated = { #ifdef CONFIG_VSX WARN_EMULATED_SETUP(vsx), #endif +#ifdef CONFIG_PPC64 + WARN_EMULATED_SETUP(mfdscr), + WARN_EMULATED_SETUP(mtdscr), +#endif }; u32 ppc_warn_emulated; void ppc_warn_emulated_print(const char *type) { - if (printk_ratelimit()) - pr_warning("%s used emulated %s instruction\n", current->comm, - type); + pr_warn_ratelimited("%s used emulated %s instruction\n", current->comm, + type); } static int __init ppc_warn_emulated_init(void) diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c index e39cad83c88..23d65abbedc 100644 --- a/arch/powerpc/kernel/udbg.c +++ b/arch/powerpc/kernel/udbg.c @@ -62,6 +62,8 @@ 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(); #endif #ifdef CONFIG_PPC_EARLY_DEBUG diff --git a/arch/powerpc/kernel/udbg_16550.c b/arch/powerpc/kernel/udbg_16550.c index baa33a7517b..6837f839ab7 100644 --- a/arch/powerpc/kernel/udbg_16550.c +++ b/arch/powerpc/kernel/udbg_16550.c @@ -11,6 +11,7 @@ #include <linux/types.h> #include <asm/udbg.h> #include <asm/io.h> +#include <asm/reg_a2.h> extern u8 real_readb(volatile u8 __iomem *addr); extern void real_writeb(u8 data, volatile u8 __iomem *addr); @@ -298,3 +299,53 @@ void __init udbg_init_40x_realmode(void) udbg_getc_poll = NULL; } #endif /* CONFIG_PPC_EARLY_DEBUG_40x */ + +#ifdef CONFIG_PPC_EARLY_DEBUG_WSP +static void udbg_wsp_flush(void) +{ + if (udbg_comport) { + while ((readb(&udbg_comport->lsr) & LSR_THRE) == 0) + /* wait for idle */; + } +} + +static void udbg_wsp_putc(char c) +{ + if (udbg_comport) { + if (c == '\n') + udbg_wsp_putc('\r'); + udbg_wsp_flush(); + writeb(c, &udbg_comport->thr); eieio(); + } +} + +static int udbg_wsp_getc(void) +{ + if (udbg_comport) { + while ((readb(&udbg_comport->lsr) & LSR_DR) == 0) + ; /* wait for char */ + return readb(&udbg_comport->rbr); + } + return -1; +} + +static int udbg_wsp_getc_poll(void) +{ + if (udbg_comport) + if (readb(&udbg_comport->lsr) & LSR_DR) + return readb(&udbg_comport->rbr); + return -1; +} + +void __init udbg_init_wsp(void) +{ + udbg_comport = (struct NS16550 __iomem *)WSP_UART_VIRT; + + udbg_init_uart(udbg_comport, 57600, 50000000); + + udbg_putc = udbg_wsp_putc; + udbg_flush = udbg_wsp_flush; + udbg_getc = udbg_wsp_getc; + udbg_getc_poll = udbg_wsp_getc_poll; +} +#endif /* CONFIG_PPC_EARLY_DEBUG_WSP */ diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S index 9de6f396cf8..4d5a3edff49 100644 --- a/arch/powerpc/kernel/vector.S +++ b/arch/powerpc/kernel/vector.S @@ -102,7 +102,7 @@ _GLOBAL(giveup_altivec) MTMSRD(r5) /* enable use of VMX now */ isync PPC_LCMPI 0,r3,0 - beqlr- /* if no previous owner, done */ + beqlr /* if no previous owner, done */ addi r3,r3,THREAD /* want THREAD of task */ PPC_LL r5,PT_REGS(r3) PPC_LCMPI 0,r5,0 diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index b9150f07d26..920276c0f6a 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -160,7 +160,7 @@ SECTIONS INIT_RAM_FS } - PERCPU(L1_CACHE_BYTES, PAGE_SIZE) + PERCPU_SECTION(L1_CACHE_BYTES) . = ALIGN(8); .machine.desc : AT(ADDR(.machine.desc) - LOAD_OFFSET) { |