diff options
Diffstat (limited to 'arch/powerpc/kernel')
69 files changed, 3225 insertions, 1991 deletions
diff --git a/arch/powerpc/kernel/.gitignore b/arch/powerpc/kernel/.gitignore new file mode 100644 index 00000000000..c5f676c3c22 --- /dev/null +++ b/arch/powerpc/kernel/.gitignore @@ -0,0 +1 @@ +vmlinux.lds diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 946daea780f..1308a86e907 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -12,11 +12,12 @@ CFLAGS_prom_init.o += -fPIC CFLAGS_btext.o += -fPIC endif -ifdef CONFIG_FTRACE +ifdef CONFIG_FUNCTION_TRACER # Do not trace early boot code CFLAGS_REMOVE_cputable.o = -pg -mno-sched-epilog CFLAGS_REMOVE_prom_init.o = -pg -mno-sched-epilog CFLAGS_REMOVE_btext.o = -pg -mno-sched-epilog +CFLAGS_REMOVE_prom.o = -pg -mno-sched-epilog ifdef CONFIG_DYNAMIC_FTRACE # dynamic ftrace setup. @@ -28,13 +29,14 @@ endif obj-y := cputable.o ptrace.o syscalls.o \ irq.o align.o signal_32.o pmc.o vdso.o \ init_task.o process.o systbl.o idle.o \ - signal.o + signal.o sysfs.o obj-y += vdso32/ obj-$(CONFIG_PPC64) += setup_64.o sys_ppc32.o \ signal_64.o ptrace32.o \ paca.o cpu_setup_ppc970.o \ cpu_setup_pa6t.o \ - firmware.o sysfs.o nvram_64.o + firmware.o nvram_64.o +obj64-$(CONFIG_RELOCATABLE) += reloc_64.o obj-$(CONFIG_PPC64) += vdso64/ obj-$(CONFIG_ALTIVEC) += vecemu.o vector.o obj-$(CONFIG_PPC_970_NAP) += idle_power4.o @@ -69,10 +71,10 @@ extra-$(CONFIG_8xx) := head_8xx.o extra-y += vmlinux.lds obj-y += time.o prom.o traps.o setup-common.o \ - udbg.o misc.o io.o \ + udbg.o misc.o io.o dma.o \ misc_$(CONFIG_WORD_SIZE).o obj-$(CONFIG_PPC32) += entry_32.o setup_32.o -obj-$(CONFIG_PPC64) += dma_64.o iommu.o +obj-$(CONFIG_PPC64) += dma-iommu.o iommu.o obj-$(CONFIG_KGDB) += kgdb.o obj-$(CONFIG_PPC_MULTIPLATFORM) += prom_init.o obj-$(CONFIG_MODULES) += ppc_ksyms.o @@ -101,6 +103,10 @@ endif obj-$(CONFIG_PPC64) += $(obj64-y) +ifneq ($(CONFIG_XMON)$(CONFIG_KEXEC),) +obj-y += ppc_save_regs.o +endif + extra-$(CONFIG_PPC_FPU) += fpu.o extra-$(CONFIG_PPC64) += entry_64.o diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 92768d3006f..661d07d2146 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -60,6 +60,7 @@ int main(void) { DEFINE(THREAD, offsetof(struct task_struct, thread)); DEFINE(MM, offsetof(struct task_struct, mm)); + DEFINE(MMCONTEXTID, offsetof(struct mm_struct, context.id)); #ifdef CONFIG_PPC64 DEFINE(AUDITCONTEXT, offsetof(struct task_struct, audit_context)); #else @@ -122,6 +123,8 @@ int main(void) DEFINE(PACASTABRR, offsetof(struct paca_struct, stab_rr)); DEFINE(PACAR1, offsetof(struct paca_struct, saved_r1)); DEFINE(PACATOC, offsetof(struct paca_struct, kernel_toc)); + DEFINE(PACAKBASE, offsetof(struct paca_struct, kernelbase)); + DEFINE(PACAKMSR, offsetof(struct paca_struct, kernel_msr)); DEFINE(PACASOFTIRQEN, offsetof(struct paca_struct, soft_enabled)); DEFINE(PACAHARDIRQEN, offsetof(struct paca_struct, hard_enabled)); DEFINE(PACASLBCACHE, offsetof(struct paca_struct, slb_cache)); @@ -304,6 +307,7 @@ int main(void) DEFINE(CFG_SYSCALL_MAP32, offsetof(struct vdso_data, syscall_map_32)); DEFINE(WTOM_CLOCK_SEC, offsetof(struct vdso_data, wtom_clock_sec)); DEFINE(WTOM_CLOCK_NSEC, offsetof(struct vdso_data, wtom_clock_nsec)); + DEFINE(STAMP_XTIME, offsetof(struct vdso_data, stamp_xtime)); DEFINE(CFG_ICACHE_BLOCKSZ, offsetof(struct vdso_data, icache_block_size)); DEFINE(CFG_DCACHE_BLOCKSZ, offsetof(struct vdso_data, dcache_block_size)); DEFINE(CFG_ICACHE_LOGBLOCKSZ, offsetof(struct vdso_data, icache_log_block_size)); @@ -350,14 +354,15 @@ int main(void) #endif DEFINE(PGD_TABLE_SIZE, PGD_TABLE_SIZE); + DEFINE(PTE_SIZE, sizeof(pte_t)); #ifdef CONFIG_KVM DEFINE(TLBE_BYTES, sizeof(struct tlbe)); DEFINE(VCPU_HOST_STACK, offsetof(struct kvm_vcpu, arch.host_stack)); DEFINE(VCPU_HOST_PID, offsetof(struct kvm_vcpu, arch.host_pid)); - DEFINE(VCPU_HOST_TLB, offsetof(struct kvm_vcpu, arch.host_tlb)); DEFINE(VCPU_SHADOW_TLB, offsetof(struct kvm_vcpu, arch.shadow_tlb)); + DEFINE(VCPU_SHADOW_MOD, offsetof(struct kvm_vcpu, arch.shadow_tlb_mod)); DEFINE(VCPU_GPRS, offsetof(struct kvm_vcpu, arch.gpr)); DEFINE(VCPU_LR, offsetof(struct kvm_vcpu, arch.lr)); DEFINE(VCPU_CR, offsetof(struct kvm_vcpu, arch.cr)); @@ -369,12 +374,16 @@ int main(void) DEFINE(VCPU_SPRG5, offsetof(struct kvm_vcpu, arch.sprg5)); DEFINE(VCPU_SPRG6, offsetof(struct kvm_vcpu, arch.sprg6)); DEFINE(VCPU_SPRG7, offsetof(struct kvm_vcpu, arch.sprg7)); - DEFINE(VCPU_PID, offsetof(struct kvm_vcpu, arch.pid)); + DEFINE(VCPU_SHADOW_PID, offsetof(struct kvm_vcpu, arch.shadow_pid)); DEFINE(VCPU_LAST_INST, offsetof(struct kvm_vcpu, arch.last_inst)); DEFINE(VCPU_FAULT_DEAR, offsetof(struct kvm_vcpu, arch.fault_dear)); DEFINE(VCPU_FAULT_ESR, offsetof(struct kvm_vcpu, arch.fault_esr)); #endif +#ifdef CONFIG_44x + DEFINE(PGD_T_LOG2, PGD_T_LOG2); + DEFINE(PTE_T_LOG2, PTE_T_LOG2); +#endif return 0; } diff --git a/arch/powerpc/kernel/btext.c b/arch/powerpc/kernel/btext.c index d8f0329b134..26e58630ed7 100644 --- a/arch/powerpc/kernel/btext.c +++ b/arch/powerpc/kernel/btext.c @@ -442,28 +442,26 @@ void btext_drawtext(const char *c, unsigned int len) void btext_drawhex(unsigned long v) { - char *hex_table = "0123456789abcdef"; - if (!boot_text_mapped) return; #ifdef CONFIG_PPC64 - btext_drawchar(hex_table[(v >> 60) & 0x0000000FUL]); - btext_drawchar(hex_table[(v >> 56) & 0x0000000FUL]); - btext_drawchar(hex_table[(v >> 52) & 0x0000000FUL]); - btext_drawchar(hex_table[(v >> 48) & 0x0000000FUL]); - btext_drawchar(hex_table[(v >> 44) & 0x0000000FUL]); - btext_drawchar(hex_table[(v >> 40) & 0x0000000FUL]); - btext_drawchar(hex_table[(v >> 36) & 0x0000000FUL]); - btext_drawchar(hex_table[(v >> 32) & 0x0000000FUL]); + btext_drawchar(hex_asc_hi(v >> 56)); + btext_drawchar(hex_asc_lo(v >> 56)); + btext_drawchar(hex_asc_hi(v >> 48)); + btext_drawchar(hex_asc_lo(v >> 48)); + btext_drawchar(hex_asc_hi(v >> 40)); + btext_drawchar(hex_asc_lo(v >> 40)); + btext_drawchar(hex_asc_hi(v >> 32)); + btext_drawchar(hex_asc_lo(v >> 32)); #endif - btext_drawchar(hex_table[(v >> 28) & 0x0000000FUL]); - btext_drawchar(hex_table[(v >> 24) & 0x0000000FUL]); - btext_drawchar(hex_table[(v >> 20) & 0x0000000FUL]); - btext_drawchar(hex_table[(v >> 16) & 0x0000000FUL]); - btext_drawchar(hex_table[(v >> 12) & 0x0000000FUL]); - btext_drawchar(hex_table[(v >> 8) & 0x0000000FUL]); - btext_drawchar(hex_table[(v >> 4) & 0x0000000FUL]); - btext_drawchar(hex_table[(v >> 0) & 0x0000000FUL]); + btext_drawchar(hex_asc_hi(v >> 24)); + btext_drawchar(hex_asc_lo(v >> 24)); + btext_drawchar(hex_asc_hi(v >> 16)); + btext_drawchar(hex_asc_lo(v >> 16)); + btext_drawchar(hex_asc_hi(v >> 8)); + btext_drawchar(hex_asc_lo(v >> 8)); + btext_drawchar(hex_asc_hi(v)); + btext_drawchar(hex_asc_lo(v)); btext_drawchar(' '); } diff --git a/arch/powerpc/kernel/cpu_setup_44x.S b/arch/powerpc/kernel/cpu_setup_44x.S index 80cac984d85..10b4ab1008a 100644 --- a/arch/powerpc/kernel/cpu_setup_44x.S +++ b/arch/powerpc/kernel/cpu_setup_44x.S @@ -34,7 +34,13 @@ _GLOBAL(__setup_cpu_440grx) blr _GLOBAL(__setup_cpu_460ex) _GLOBAL(__setup_cpu_460gt) - b __init_fpu_44x + mflr r4 + bl __init_fpu_44x + bl __fixup_440A_mcheck + mtlr r4 + blr + +_GLOBAL(__setup_cpu_440x5) _GLOBAL(__setup_cpu_440gx) _GLOBAL(__setup_cpu_440spe) b __fixup_440A_mcheck diff --git a/arch/powerpc/kernel/cpu_setup_ppc970.S b/arch/powerpc/kernel/cpu_setup_ppc970.S index bf118c38575..27f2507279d 100644 --- a/arch/powerpc/kernel/cpu_setup_ppc970.S +++ b/arch/powerpc/kernel/cpu_setup_ppc970.S @@ -110,7 +110,7 @@ load_hids: isync /* Save away cpu state */ - LOAD_REG_IMMEDIATE(r5,cpu_state_storage) + LOAD_REG_ADDR(r5,cpu_state_storage) /* Save HID0,1,4 and 5 */ mfspr r3,SPRN_HID0 @@ -134,7 +134,7 @@ _GLOBAL(__restore_cpu_ppc970) rldicl. r0,r0,4,63 beqlr - LOAD_REG_IMMEDIATE(r5,cpu_state_storage) + LOAD_REG_ADDR(r5,cpu_state_storage) /* Before accessing memory, we make sure rm_ci is clear */ li r0,0 mfspr r3,SPRN_HID4 diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 25c273c761d..923f87aff20 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -19,6 +19,7 @@ #include <asm/oprofile_impl.h> #include <asm/cputable.h> #include <asm/prom.h> /* for PTRRELOC on ARCH=ppc */ +#include <asm/mmu.h> struct cpu_spec* cur_cpu_spec = NULL; EXPORT_SYMBOL(cur_cpu_spec); @@ -39,6 +40,7 @@ extern void __setup_cpu_440epx(unsigned long offset, struct cpu_spec* spec); extern void __setup_cpu_440gx(unsigned long offset, struct cpu_spec* spec); extern void __setup_cpu_440grx(unsigned long offset, struct cpu_spec* spec); extern void __setup_cpu_440spe(unsigned long offset, struct cpu_spec* spec); +extern void __setup_cpu_440x5(unsigned long offset, struct cpu_spec* spec); extern void __setup_cpu_460ex(unsigned long offset, struct cpu_spec* spec); extern void __setup_cpu_460gt(unsigned long offset, struct cpu_spec* spec); extern void __setup_cpu_603(unsigned long offset, struct cpu_spec* spec); @@ -93,6 +95,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "POWER3 (630)", .cpu_features = CPU_FTRS_POWER3, .cpu_user_features = COMMON_USER_PPC64|PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, @@ -108,6 +111,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "POWER3 (630+)", .cpu_features = CPU_FTRS_POWER3, .cpu_user_features = COMMON_USER_PPC64|PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, @@ -123,6 +127,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "RS64-II (northstar)", .cpu_features = CPU_FTRS_RS64, .cpu_user_features = COMMON_USER_PPC64, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, @@ -138,6 +143,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "RS64-III (pulsar)", .cpu_features = CPU_FTRS_RS64, .cpu_user_features = COMMON_USER_PPC64, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, @@ -153,6 +159,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "RS64-III (icestar)", .cpu_features = CPU_FTRS_RS64, .cpu_user_features = COMMON_USER_PPC64, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, @@ -168,6 +175,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "RS64-IV (sstar)", .cpu_features = CPU_FTRS_RS64, .cpu_user_features = COMMON_USER_PPC64, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, @@ -183,6 +191,7 @@ 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, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, @@ -198,6 +207,7 @@ 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, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, @@ -214,6 +224,7 @@ 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, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, @@ -232,6 +243,7 @@ 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, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, @@ -250,6 +262,7 @@ 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, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, @@ -268,6 +281,7 @@ 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, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, @@ -286,6 +300,7 @@ 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, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, @@ -302,6 +317,7 @@ 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, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 6, @@ -322,6 +338,7 @@ 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, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 6, @@ -338,6 +355,7 @@ 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, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 6, @@ -355,6 +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, .icache_bsize = 128, .dcache_bsize = 128, .machine_check = machine_check_generic, @@ -368,6 +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, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 6, @@ -387,6 +407,7 @@ 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, .icache_bsize = 128, .dcache_bsize = 128, .machine_check = machine_check_generic, @@ -399,6 +420,7 @@ 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, .icache_bsize = 128, .dcache_bsize = 128, .machine_check = machine_check_generic, @@ -411,6 +433,7 @@ 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, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 6, @@ -433,6 +456,7 @@ 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, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 4, @@ -448,6 +472,7 @@ 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, .icache_bsize = 64, .dcache_bsize = 64, .num_pmcs = 6, @@ -465,6 +490,7 @@ 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, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 6, @@ -482,6 +508,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_PPC601, .cpu_user_features = COMMON_USER | PPC_FEATURE_601_INSTR | PPC_FEATURE_UNIFIED_CACHE | PPC_FEATURE_NO_TB, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_generic, @@ -493,6 +520,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "603", .cpu_features = CPU_FTRS_603, .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = 0, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_603, @@ -505,6 +533,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "603e", .cpu_features = CPU_FTRS_603, .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = 0, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_603, @@ -517,6 +546,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "603ev", .cpu_features = CPU_FTRS_603, .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = 0, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_603, @@ -529,6 +559,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "604", .cpu_features = CPU_FTRS_604, .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 2, @@ -542,6 +573,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "604e", .cpu_features = CPU_FTRS_604, .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -555,6 +587,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "604r", .cpu_features = CPU_FTRS_604, .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -568,6 +601,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "604ev", .cpu_features = CPU_FTRS_604, .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -581,6 +615,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "740/750", .cpu_features = CPU_FTRS_740_NOTAU, .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -594,6 +629,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "750CX", .cpu_features = CPU_FTRS_750, .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -607,9 +643,11 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "750CX", .cpu_features = CPU_FTRS_750, .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, + .pmc_type = PPC_PMC_IBM, .cpu_setup = __setup_cpu_750cx, .machine_check = machine_check_generic, .platform = "ppc750", @@ -620,9 +658,11 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "750CXe", .cpu_features = CPU_FTRS_750, .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, + .pmc_type = PPC_PMC_IBM, .cpu_setup = __setup_cpu_750cx, .machine_check = machine_check_generic, .platform = "ppc750", @@ -633,9 +673,11 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "750CXe", .cpu_features = CPU_FTRS_750, .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, + .pmc_type = PPC_PMC_IBM, .cpu_setup = __setup_cpu_750cx, .machine_check = machine_check_generic, .platform = "ppc750", @@ -646,9 +688,11 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "750CL", .cpu_features = CPU_FTRS_750CL, .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, + .pmc_type = PPC_PMC_IBM, .cpu_setup = __setup_cpu_750, .machine_check = machine_check_generic, .platform = "ppc750", @@ -659,9 +703,11 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "745/755", .cpu_features = CPU_FTRS_750, .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, + .pmc_type = PPC_PMC_IBM, .cpu_setup = __setup_cpu_750, .machine_check = machine_check_generic, .platform = "ppc750", @@ -672,9 +718,11 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "750FX", .cpu_features = CPU_FTRS_750FX1, .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, + .pmc_type = PPC_PMC_IBM, .cpu_setup = __setup_cpu_750, .machine_check = machine_check_generic, .platform = "ppc750", @@ -685,9 +733,11 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "750FX", .cpu_features = CPU_FTRS_750FX2, .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, + .pmc_type = PPC_PMC_IBM, .cpu_setup = __setup_cpu_750, .machine_check = machine_check_generic, .platform = "ppc750", @@ -698,9 +748,11 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "750FX", .cpu_features = CPU_FTRS_750FX, .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, + .pmc_type = PPC_PMC_IBM, .cpu_setup = __setup_cpu_750fx, .machine_check = machine_check_generic, .platform = "ppc750", @@ -711,9 +763,11 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "750GX", .cpu_features = CPU_FTRS_750GX, .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, + .pmc_type = PPC_PMC_IBM, .cpu_setup = __setup_cpu_750fx, .machine_check = machine_check_generic, .platform = "ppc750", @@ -724,9 +778,11 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "740/750", .cpu_features = CPU_FTRS_740, .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, + .pmc_type = PPC_PMC_IBM, .cpu_setup = __setup_cpu_750, .machine_check = machine_check_generic, .platform = "ppc750", @@ -738,9 +794,11 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_7400_NOTAU, .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, + .pmc_type = PPC_PMC_G4, .cpu_setup = __setup_cpu_7400, .machine_check = machine_check_generic, .platform = "ppc7400", @@ -752,9 +810,11 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_7400, .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, + .pmc_type = PPC_PMC_G4, .cpu_setup = __setup_cpu_7400, .machine_check = machine_check_generic, .platform = "ppc7400", @@ -766,9 +826,11 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_7400, .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, + .pmc_type = PPC_PMC_G4, .cpu_setup = __setup_cpu_7410, .machine_check = machine_check_generic, .platform = "ppc7400", @@ -780,9 +842,11 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_7450_20, .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 6, + .pmc_type = PPC_PMC_G4, .cpu_setup = __setup_cpu_745x, .oprofile_cpu_type = "ppc/7450", .oprofile_type = PPC_OPROFILE_G4, @@ -796,9 +860,11 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_7450_21, .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 6, + .pmc_type = PPC_PMC_G4, .cpu_setup = __setup_cpu_745x, .oprofile_cpu_type = "ppc/7450", .oprofile_type = PPC_OPROFILE_G4, @@ -812,9 +878,11 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_7450_23, .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 6, + .pmc_type = PPC_PMC_G4, .cpu_setup = __setup_cpu_745x, .oprofile_cpu_type = "ppc/7450", .oprofile_type = PPC_OPROFILE_G4, @@ -828,9 +896,11 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_7455_1, .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 6, + .pmc_type = PPC_PMC_G4, .cpu_setup = __setup_cpu_745x, .oprofile_cpu_type = "ppc/7450", .oprofile_type = PPC_OPROFILE_G4, @@ -844,9 +914,11 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_7455_20, .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 6, + .pmc_type = PPC_PMC_G4, .cpu_setup = __setup_cpu_745x, .oprofile_cpu_type = "ppc/7450", .oprofile_type = PPC_OPROFILE_G4, @@ -860,9 +932,11 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_7455, .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 6, + .pmc_type = PPC_PMC_G4, .cpu_setup = __setup_cpu_745x, .oprofile_cpu_type = "ppc/7450", .oprofile_type = PPC_OPROFILE_G4, @@ -876,9 +950,11 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_7447_10, .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 6, + .pmc_type = PPC_PMC_G4, .cpu_setup = __setup_cpu_745x, .oprofile_cpu_type = "ppc/7450", .oprofile_type = PPC_OPROFILE_G4, @@ -892,9 +968,11 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_7447_10, .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 6, + .pmc_type = PPC_PMC_G4, .cpu_setup = __setup_cpu_745x, .oprofile_cpu_type = "ppc/7450", .oprofile_type = PPC_OPROFILE_G4, @@ -907,9 +985,11 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "7447/7457", .cpu_features = CPU_FTRS_7447, .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 6, + .pmc_type = PPC_PMC_G4, .cpu_setup = __setup_cpu_745x, .oprofile_cpu_type = "ppc/7450", .oprofile_type = PPC_OPROFILE_G4, @@ -923,9 +1003,11 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_7447A, .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 6, + .pmc_type = PPC_PMC_G4, .cpu_setup = __setup_cpu_745x, .oprofile_cpu_type = "ppc/7450", .oprofile_type = PPC_OPROFILE_G4, @@ -939,9 +1021,11 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_7448, .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 6, + .pmc_type = PPC_PMC_G4, .cpu_setup = __setup_cpu_745x, .oprofile_cpu_type = "ppc/7450", .oprofile_type = PPC_OPROFILE_G4, @@ -954,6 +1038,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "82xx", .cpu_features = CPU_FTRS_82XX, .cpu_user_features = COMMON_USER, + .mmu_features = 0, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_603, @@ -966,6 +1051,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "G2_LE", .cpu_features = CPU_FTRS_G2_LE, .cpu_user_features = COMMON_USER, + .mmu_features = MMU_FTR_USE_HIGH_BATS, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_603, @@ -978,6 +1064,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "e300c1", .cpu_features = CPU_FTRS_E300, .cpu_user_features = COMMON_USER, + .mmu_features = MMU_FTR_USE_HIGH_BATS, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_603, @@ -990,6 +1077,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "e300c2", .cpu_features = CPU_FTRS_E300C2, .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU, + .mmu_features = MMU_FTR_USE_HIGH_BATS, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_603, @@ -1002,6 +1090,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "e300c3", .cpu_features = CPU_FTRS_E300, .cpu_user_features = COMMON_USER, + .mmu_features = MMU_FTR_USE_HIGH_BATS, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_603, @@ -1016,6 +1105,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "e300c4", .cpu_features = CPU_FTRS_E300, .cpu_user_features = COMMON_USER, + .mmu_features = MMU_FTR_USE_HIGH_BATS, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_603, @@ -1031,6 +1121,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "(generic PPC)", .cpu_features = CPU_FTRS_CLASSIC32, .cpu_user_features = COMMON_USER, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_generic, @@ -1046,6 +1137,7 @@ static struct cpu_spec __initdata cpu_specs[] = { * if the 8xx code is there.... */ .cpu_features = CPU_FTRS_8XX, .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU, + .mmu_features = MMU_FTR_TYPE_8xx, .icache_bsize = 16, .dcache_bsize = 16, .platform = "ppc823", @@ -1058,6 +1150,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "403GC", .cpu_features = CPU_FTRS_40X, .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU, + .mmu_features = MMU_FTR_TYPE_40x, .icache_bsize = 16, .dcache_bsize = 16, .machine_check = machine_check_4xx, @@ -1070,6 +1163,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_40X, .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | PPC_FEATURE_NO_TB, + .mmu_features = MMU_FTR_TYPE_40x, .icache_bsize = 16, .dcache_bsize = 16, .machine_check = machine_check_4xx, @@ -1081,6 +1175,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "403G ??", .cpu_features = CPU_FTRS_40X, .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU, + .mmu_features = MMU_FTR_TYPE_40x, .icache_bsize = 16, .dcache_bsize = 16, .machine_check = machine_check_4xx, @@ -1093,6 +1188,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_40X, .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_4xx, @@ -1105,6 +1201,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_40X, .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_4xx, @@ -1117,6 +1214,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_40X, .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_4xx, @@ -1129,6 +1227,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_40X, .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_4xx, @@ -1141,6 +1240,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_40X, .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_4xx, @@ -1153,6 +1253,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_40X, .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_4xx, @@ -1165,6 +1266,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_40X, .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_4xx, @@ -1177,6 +1279,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_40X, .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_4xx, @@ -1188,6 +1291,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "405LP", .cpu_features = CPU_FTRS_40X, .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU, + .mmu_features = MMU_FTR_TYPE_40x, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_4xx, @@ -1200,6 +1304,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_40X, .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_4xx, @@ -1212,6 +1317,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_40X, .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_4xx, @@ -1224,6 +1330,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_40X, .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_4xx, @@ -1236,6 +1343,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_40X, .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_4xx, @@ -1248,6 +1356,21 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_40X, .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, + .icache_bsize = 32, + .dcache_bsize = 32, + .machine_check = machine_check_4xx, + .platform = "ppc405", + }, + { + /* 405EZ */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x41510000, + .cpu_name = "405EZ", + .cpu_features = CPU_FTRS_40X, + .cpu_user_features = PPC_FEATURE_32 | + PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_4xx, @@ -1260,6 +1383,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_40X, .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_4xx, @@ -1274,6 +1398,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "440GR Rev. A", .cpu_features = CPU_FTRS_44X, .cpu_user_features = COMMON_USER_BOOKE, + .mmu_features = MMU_FTR_TYPE_44x, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_4xx, @@ -1285,6 +1410,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "440EP Rev. A", .cpu_features = CPU_FTRS_44X, .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, + .mmu_features = MMU_FTR_TYPE_44x, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_440ep, @@ -1297,6 +1423,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "440GR Rev. B", .cpu_features = CPU_FTRS_44X, .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, + .mmu_features = MMU_FTR_TYPE_44x, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_4xx, @@ -1308,6 +1435,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "440EP Rev. C", .cpu_features = CPU_FTRS_44X, .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, + .mmu_features = MMU_FTR_TYPE_44x, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_440ep, @@ -1320,6 +1448,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "440EP Rev. B", .cpu_features = CPU_FTRS_44X, .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, + .mmu_features = MMU_FTR_TYPE_44x, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_440ep, @@ -1332,6 +1461,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "440GRX", .cpu_features = CPU_FTRS_44X, .cpu_user_features = COMMON_USER_BOOKE, + .mmu_features = MMU_FTR_TYPE_44x, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_440grx, @@ -1344,6 +1474,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "440EPX", .cpu_features = CPU_FTRS_44X, .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, + .mmu_features = MMU_FTR_TYPE_44x, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_440epx, @@ -1356,6 +1487,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "440GP Rev. B", .cpu_features = CPU_FTRS_44X, .cpu_user_features = COMMON_USER_BOOKE, + .mmu_features = MMU_FTR_TYPE_44x, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_4xx, @@ -1367,6 +1499,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "440GP Rev. C", .cpu_features = CPU_FTRS_44X, .cpu_user_features = COMMON_USER_BOOKE, + .mmu_features = MMU_FTR_TYPE_44x, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_4xx, @@ -1378,6 +1511,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "440GX Rev. A", .cpu_features = CPU_FTRS_44X, .cpu_user_features = COMMON_USER_BOOKE, + .mmu_features = MMU_FTR_TYPE_44x, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_440gx, @@ -1390,6 +1524,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "440GX Rev. B", .cpu_features = CPU_FTRS_44X, .cpu_user_features = COMMON_USER_BOOKE, + .mmu_features = MMU_FTR_TYPE_44x, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_440gx, @@ -1402,6 +1537,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "440GX Rev. C", .cpu_features = CPU_FTRS_44X, .cpu_user_features = COMMON_USER_BOOKE, + .mmu_features = MMU_FTR_TYPE_44x, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_440gx, @@ -1414,6 +1550,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "440GX Rev. F", .cpu_features = CPU_FTRS_44X, .cpu_user_features = COMMON_USER_BOOKE, + .mmu_features = MMU_FTR_TYPE_44x, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_440gx, @@ -1426,6 +1563,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "440SP Rev. A", .cpu_features = CPU_FTRS_44X, .cpu_user_features = COMMON_USER_BOOKE, + .mmu_features = MMU_FTR_TYPE_44x, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_4xx, @@ -1437,6 +1575,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "440SPe Rev. A", .cpu_features = CPU_FTRS_44X, .cpu_user_features = COMMON_USER_BOOKE, + .mmu_features = MMU_FTR_TYPE_44x, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_440spe, @@ -1449,6 +1588,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "440SPe Rev. B", .cpu_features = CPU_FTRS_44X, .cpu_user_features = COMMON_USER_BOOKE, + .mmu_features = MMU_FTR_TYPE_44x, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_440spe, @@ -1461,16 +1601,20 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "440 in Virtex-5 FXT", .cpu_features = CPU_FTRS_44X, .cpu_user_features = COMMON_USER_BOOKE, + .mmu_features = MMU_FTR_TYPE_44x, .icache_bsize = 32, .dcache_bsize = 32, + .cpu_setup = __setup_cpu_440x5, + .machine_check = machine_check_440A, .platform = "ppc440", }, { /* 460EX */ .pvr_mask = 0xffff0002, .pvr_value = 0x13020002, .cpu_name = "460EX", - .cpu_features = CPU_FTRS_44X, + .cpu_features = CPU_FTRS_440x6, .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, + .mmu_features = MMU_FTR_TYPE_44x, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_460ex, @@ -1481,8 +1625,9 @@ static struct cpu_spec __initdata cpu_specs[] = { .pvr_mask = 0xffff0002, .pvr_value = 0x13020000, .cpu_name = "460GT", - .cpu_features = CPU_FTRS_44X, + .cpu_features = CPU_FTRS_440x6, .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, + .mmu_features = MMU_FTR_TYPE_44x, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_460gt, @@ -1495,6 +1640,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "(generic 44x PPC)", .cpu_features = CPU_FTRS_44X, .cpu_user_features = COMMON_USER_BOOKE, + .mmu_features = MMU_FTR_TYPE_44x, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_4xx, @@ -1511,6 +1657,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_EFP_SINGLE | PPC_FEATURE_UNIFIED_CACHE, + .mmu_features = MMU_FTR_TYPE_FSL_E, .dcache_bsize = 32, .machine_check = machine_check_e200, .platform = "ppc5554", @@ -1525,6 +1672,7 @@ static struct cpu_spec __initdata cpu_specs[] = { PPC_FEATURE_HAS_SPE_COMP | PPC_FEATURE_HAS_EFP_SINGLE_COMP | PPC_FEATURE_UNIFIED_CACHE, + .mmu_features = MMU_FTR_TYPE_FSL_E, .dcache_bsize = 32, .machine_check = machine_check_e200, .platform = "ppc5554", @@ -1537,6 +1685,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_EFP_SINGLE | PPC_FEATURE_UNIFIED_CACHE, + .mmu_features = MMU_FTR_TYPE_FSL_E, .dcache_bsize = 32, .machine_check = machine_check_e200, .platform = "ppc5554", @@ -1551,6 +1700,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_SPE_COMP | PPC_FEATURE_HAS_EFP_SINGLE_COMP, + .mmu_features = MMU_FTR_TYPE_FSL_E, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -1568,6 +1718,7 @@ static struct cpu_spec __initdata cpu_specs[] = { PPC_FEATURE_HAS_SPE_COMP | PPC_FEATURE_HAS_EFP_SINGLE_COMP | PPC_FEATURE_HAS_EFP_DOUBLE_COMP, + .mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -1582,6 +1733,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "e500mc", .cpu_features = CPU_FTRS_E500MC, .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, + .mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS, .icache_bsize = 64, .dcache_bsize = 64, .num_pmcs = 4, @@ -1598,6 +1750,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_SPE_COMP | PPC_FEATURE_HAS_EFP_SINGLE_COMP, + .mmu_features = MMU_FTR_TYPE_FSL_E, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_e500, diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c index a323c9b32ee..19671aca659 100644 --- a/arch/powerpc/kernel/crash_dump.c +++ b/arch/powerpc/kernel/crash_dump.c @@ -27,6 +27,10 @@ #define DBG(fmt...) #endif +/* Stores the physical address of elf header of crash image. */ +unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX; + +#ifndef CONFIG_RELOCATABLE void __init reserve_kdump_trampoline(void) { lmb_reserve(0, KDUMP_RESERVE_LIMIT); @@ -65,8 +69,13 @@ void __init setup_kdump_trampoline(void) DBG(" <- setup_kdump_trampoline()\n"); } +#endif /* CONFIG_RELOCATABLE */ -#ifdef CONFIG_PROC_VMCORE +/* + * Note: elfcorehdr_addr is not just limited to vmcore. It is also used by + * is_kdump_kernel() to determine if we are booting after a panic. Hence + * ifdef it under CONFIG_CRASH_DUMP and not CONFIG_PROC_VMCORE. + */ static int __init parse_elfcorehdr(char *p) { if (p) @@ -75,7 +84,6 @@ static int __init parse_elfcorehdr(char *p) return 1; } __setup("elfcorehdr=", parse_elfcorehdr); -#endif static int __init parse_savemaxmem(char *p) { diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c new file mode 100644 index 00000000000..14183af1b3f --- /dev/null +++ b/arch/powerpc/kernel/dma-iommu.c @@ -0,0 +1,101 @@ +/* + * Copyright (C) 2006 Benjamin Herrenschmidt, IBM Corporation + * + * Provide default implementations of the DMA mapping callbacks for + * busses using the iommu infrastructure + */ + +#include <asm/iommu.h> + +/* + * Generic iommu implementation + */ + +/* Allocates a contiguous real buffer and creates mappings over it. + * Returns the virtual address of the buffer and sets dma_handle + * to the dma address (mapping) of the first page. + */ +static void *dma_iommu_alloc_coherent(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t flag) +{ + return iommu_alloc_coherent(dev, dev->archdata.dma_data, size, + dma_handle, device_to_mask(dev), flag, + dev_to_node(dev)); +} + +static void dma_iommu_free_coherent(struct device *dev, size_t size, + void *vaddr, dma_addr_t dma_handle) +{ + iommu_free_coherent(dev->archdata.dma_data, size, vaddr, dma_handle); +} + +/* Creates TCEs for a user provided buffer. The user buffer must be + * contiguous real kernel storage (not vmalloc). The address passed here + * comprises a page address and offset into that page. The dma_addr_t + * returned will point to the same byte within the page as was passed in. + */ +static dma_addr_t dma_iommu_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, + enum dma_data_direction direction, + struct dma_attrs *attrs) +{ + return iommu_map_page(dev, dev->archdata.dma_data, page, offset, size, + device_to_mask(dev), direction, attrs); +} + + +static void dma_iommu_unmap_page(struct device *dev, dma_addr_t dma_handle, + size_t size, enum dma_data_direction direction, + struct dma_attrs *attrs) +{ + iommu_unmap_page(dev->archdata.dma_data, dma_handle, size, direction, + attrs); +} + + +static int dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist, + int nelems, enum dma_data_direction direction, + struct dma_attrs *attrs) +{ + return iommu_map_sg(dev, dev->archdata.dma_data, sglist, nelems, + device_to_mask(dev), direction, attrs); +} + +static void dma_iommu_unmap_sg(struct device *dev, struct scatterlist *sglist, + int nelems, enum dma_data_direction direction, + struct dma_attrs *attrs) +{ + iommu_unmap_sg(dev->archdata.dma_data, sglist, nelems, direction, + attrs); +} + +/* We support DMA to/from any memory page via the iommu */ +static int dma_iommu_dma_supported(struct device *dev, u64 mask) +{ + struct iommu_table *tbl = dev->archdata.dma_data; + + if (!tbl || tbl->it_offset > mask) { + printk(KERN_INFO + "Warning: IOMMU offset too big for device mask\n"); + if (tbl) + printk(KERN_INFO + "mask: 0x%08lx, table offset: 0x%08lx\n", + mask, tbl->it_offset); + else + printk(KERN_INFO "mask: 0x%08lx, table unavailable\n", + mask); + return 0; + } else + return 1; +} + +struct dma_mapping_ops dma_iommu_ops = { + .alloc_coherent = dma_iommu_alloc_coherent, + .free_coherent = dma_iommu_free_coherent, + .map_sg = dma_iommu_map_sg, + .unmap_sg = dma_iommu_unmap_sg, + .dma_supported = dma_iommu_dma_supported, + .map_page = dma_iommu_map_page, + .unmap_page = dma_iommu_unmap_page, +}; +EXPORT_SYMBOL(dma_iommu_ops); diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c new file mode 100644 index 00000000000..1c5c8a6fc12 --- /dev/null +++ b/arch/powerpc/kernel/dma.c @@ -0,0 +1,158 @@ +/* + * Copyright (C) 2006 Benjamin Herrenschmidt, IBM Corporation + * + * Provide default implementations of the DMA mapping callbacks for + * directly mapped busses. + */ + +#include <linux/device.h> +#include <linux/dma-mapping.h> +#include <asm/bug.h> +#include <asm/abs_addr.h> + +/* + * Generic direct DMA implementation + * + * This implementation supports a per-device offset that can be applied if + * the address at which memory is visible to devices is not 0. Platform code + * can set archdata.dma_data to an unsigned long holding the offset. By + * default the offset is PCI_DRAM_OFFSET. + */ + +static unsigned long get_dma_direct_offset(struct device *dev) +{ + if (dev) + return (unsigned long)dev->archdata.dma_data; + + return PCI_DRAM_OFFSET; +} + +void *dma_direct_alloc_coherent(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t flag) +{ + void *ret; +#ifdef CONFIG_NOT_COHERENT_CACHE + ret = __dma_alloc_coherent(size, dma_handle, flag); + if (ret == NULL) + return NULL; + *dma_handle += get_dma_direct_offset(dev); + return ret; +#else + struct page *page; + int node = dev_to_node(dev); + + /* ignore region specifiers */ + flag &= ~(__GFP_HIGHMEM); + + page = alloc_pages_node(node, flag, get_order(size)); + if (page == NULL) + return NULL; + ret = page_address(page); + memset(ret, 0, size); + *dma_handle = virt_to_abs(ret) + get_dma_direct_offset(dev); + + return ret; +#endif +} + +void dma_direct_free_coherent(struct device *dev, size_t size, + void *vaddr, dma_addr_t dma_handle) +{ +#ifdef CONFIG_NOT_COHERENT_CACHE + __dma_free_coherent(size, vaddr); +#else + free_pages((unsigned long)vaddr, get_order(size)); +#endif +} + +static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, + int nents, enum dma_data_direction direction, + struct dma_attrs *attrs) +{ + struct scatterlist *sg; + int i; + + for_each_sg(sgl, sg, nents, i) { + sg->dma_address = sg_phys(sg) + get_dma_direct_offset(dev); + sg->dma_length = sg->length; + __dma_sync_page(sg_page(sg), sg->offset, sg->length, direction); + } + + return nents; +} + +static void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sg, + int nents, enum dma_data_direction direction, + struct dma_attrs *attrs) +{ +} + +static int dma_direct_dma_supported(struct device *dev, u64 mask) +{ +#ifdef CONFIG_PPC64 + /* Could be improved to check for memory though it better be + * done via some global so platforms can set the limit in case + * they have limited DMA windows + */ + return mask >= DMA_32BIT_MASK; +#else + return 1; +#endif +} + +static inline dma_addr_t dma_direct_map_page(struct device *dev, + struct page *page, + unsigned long offset, + size_t size, + enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + BUG_ON(dir == DMA_NONE); + __dma_sync_page(page, offset, size, dir); + return page_to_phys(page) + offset + get_dma_direct_offset(dev); +} + +static inline void dma_direct_unmap_page(struct device *dev, + dma_addr_t dma_address, + size_t size, + enum dma_data_direction direction, + struct dma_attrs *attrs) +{ +} + +#ifdef CONFIG_NOT_COHERENT_CACHE +static inline void dma_direct_sync_sg(struct device *dev, + struct scatterlist *sgl, int nents, + enum dma_data_direction direction) +{ + struct scatterlist *sg; + int i; + + for_each_sg(sgl, sg, nents, i) + __dma_sync_page(sg_page(sg), sg->offset, sg->length, direction); +} + +static inline void dma_direct_sync_single_range(struct device *dev, + dma_addr_t dma_handle, unsigned long offset, size_t size, + enum dma_data_direction direction) +{ + __dma_sync(bus_to_virt(dma_handle+offset), size, direction); +} +#endif + +struct dma_mapping_ops dma_direct_ops = { + .alloc_coherent = dma_direct_alloc_coherent, + .free_coherent = dma_direct_free_coherent, + .map_sg = dma_direct_map_sg, + .unmap_sg = dma_direct_unmap_sg, + .dma_supported = dma_direct_dma_supported, + .map_page = dma_direct_map_page, + .unmap_page = dma_direct_unmap_page, +#ifdef CONFIG_NOT_COHERENT_CACHE + .sync_single_range_for_cpu = dma_direct_sync_single_range, + .sync_single_range_for_device = dma_direct_sync_single_range, + .sync_sg_for_cpu = dma_direct_sync_sg, + .sync_sg_for_device = dma_direct_sync_sg, +#endif +}; +EXPORT_SYMBOL(dma_direct_ops); diff --git a/arch/powerpc/kernel/dma_64.c b/arch/powerpc/kernel/dma_64.c deleted file mode 100644 index ae5708e3a31..00000000000 --- a/arch/powerpc/kernel/dma_64.c +++ /dev/null @@ -1,200 +0,0 @@ -/* - * Copyright (C) 2006 Benjamin Herrenschmidt, IBM Corporation - * - * Provide default implementations of the DMA mapping callbacks for - * directly mapped busses and busses using the iommu infrastructure - */ - -#include <linux/device.h> -#include <linux/dma-mapping.h> -#include <asm/bug.h> -#include <asm/iommu.h> -#include <asm/abs_addr.h> - -/* - * Generic iommu implementation - */ - -/* Allocates a contiguous real buffer and creates mappings over it. - * Returns the virtual address of the buffer and sets dma_handle - * to the dma address (mapping) of the first page. - */ -static void *dma_iommu_alloc_coherent(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t flag) -{ - return iommu_alloc_coherent(dev, dev->archdata.dma_data, size, - dma_handle, device_to_mask(dev), flag, - dev->archdata.numa_node); -} - -static void dma_iommu_free_coherent(struct device *dev, size_t size, - void *vaddr, dma_addr_t dma_handle) -{ - iommu_free_coherent(dev->archdata.dma_data, size, vaddr, dma_handle); -} - -/* Creates TCEs for a user provided buffer. The user buffer must be - * contiguous real kernel storage (not vmalloc). The address of the buffer - * passed here is the kernel (virtual) address of the buffer. The buffer - * need not be page aligned, the dma_addr_t returned will point to the same - * byte within the page as vaddr. - */ -static dma_addr_t dma_iommu_map_single(struct device *dev, void *vaddr, - size_t size, - enum dma_data_direction direction, - struct dma_attrs *attrs) -{ - return iommu_map_single(dev, dev->archdata.dma_data, vaddr, size, - device_to_mask(dev), direction, attrs); -} - - -static void dma_iommu_unmap_single(struct device *dev, dma_addr_t dma_handle, - size_t size, - enum dma_data_direction direction, - struct dma_attrs *attrs) -{ - iommu_unmap_single(dev->archdata.dma_data, dma_handle, size, direction, - attrs); -} - - -static int dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist, - int nelems, enum dma_data_direction direction, - struct dma_attrs *attrs) -{ - return iommu_map_sg(dev, dev->archdata.dma_data, sglist, nelems, - device_to_mask(dev), direction, attrs); -} - -static void dma_iommu_unmap_sg(struct device *dev, struct scatterlist *sglist, - int nelems, enum dma_data_direction direction, - struct dma_attrs *attrs) -{ - iommu_unmap_sg(dev->archdata.dma_data, sglist, nelems, direction, - attrs); -} - -/* We support DMA to/from any memory page via the iommu */ -static int dma_iommu_dma_supported(struct device *dev, u64 mask) -{ - struct iommu_table *tbl = dev->archdata.dma_data; - - if (!tbl || tbl->it_offset > mask) { - printk(KERN_INFO - "Warning: IOMMU offset too big for device mask\n"); - if (tbl) - printk(KERN_INFO - "mask: 0x%08lx, table offset: 0x%08lx\n", - mask, tbl->it_offset); - else - printk(KERN_INFO "mask: 0x%08lx, table unavailable\n", - mask); - return 0; - } else - return 1; -} - -struct dma_mapping_ops dma_iommu_ops = { - .alloc_coherent = dma_iommu_alloc_coherent, - .free_coherent = dma_iommu_free_coherent, - .map_single = dma_iommu_map_single, - .unmap_single = dma_iommu_unmap_single, - .map_sg = dma_iommu_map_sg, - .unmap_sg = dma_iommu_unmap_sg, - .dma_supported = dma_iommu_dma_supported, -}; -EXPORT_SYMBOL(dma_iommu_ops); - -/* - * Generic direct DMA implementation - * - * This implementation supports a per-device offset that can be applied if - * the address at which memory is visible to devices is not 0. Platform code - * can set archdata.dma_data to an unsigned long holding the offset. By - * default the offset is zero. - */ - -static unsigned long get_dma_direct_offset(struct device *dev) -{ - return (unsigned long)dev->archdata.dma_data; -} - -static void *dma_direct_alloc_coherent(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t flag) -{ - struct page *page; - void *ret; - int node = dev->archdata.numa_node; - - page = alloc_pages_node(node, flag, get_order(size)); - if (page == NULL) - return NULL; - ret = page_address(page); - memset(ret, 0, size); - *dma_handle = virt_to_abs(ret) + get_dma_direct_offset(dev); - - return ret; -} - -static void dma_direct_free_coherent(struct device *dev, size_t size, - void *vaddr, dma_addr_t dma_handle) -{ - free_pages((unsigned long)vaddr, get_order(size)); -} - -static dma_addr_t dma_direct_map_single(struct device *dev, void *ptr, - size_t size, - enum dma_data_direction direction, - struct dma_attrs *attrs) -{ - return virt_to_abs(ptr) + get_dma_direct_offset(dev); -} - -static void dma_direct_unmap_single(struct device *dev, dma_addr_t dma_addr, - size_t size, - enum dma_data_direction direction, - struct dma_attrs *attrs) -{ -} - -static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, - int nents, enum dma_data_direction direction, - struct dma_attrs *attrs) -{ - struct scatterlist *sg; - int i; - - for_each_sg(sgl, sg, nents, i) { - sg->dma_address = sg_phys(sg) + get_dma_direct_offset(dev); - sg->dma_length = sg->length; - } - - return nents; -} - -static void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sg, - int nents, enum dma_data_direction direction, - struct dma_attrs *attrs) -{ -} - -static int dma_direct_dma_supported(struct device *dev, u64 mask) -{ - /* Could be improved to check for memory though it better be - * done via some global so platforms can set the limit in case - * they have limited DMA windows - */ - return mask >= DMA_32BIT_MASK; -} - -struct dma_mapping_ops dma_direct_ops = { - .alloc_coherent = dma_direct_alloc_coherent, - .free_coherent = dma_direct_free_coherent, - .map_single = dma_direct_map_single, - .unmap_single = dma_direct_unmap_single, - .map_sg = dma_direct_map_sg, - .unmap_sg = dma_direct_unmap_sg, - .dma_supported = dma_direct_dma_supported, -}; -EXPORT_SYMBOL(dma_direct_ops); diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 1cbbf703364..6f7eb7e00c7 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -1158,43 +1158,21 @@ machine_check_in_rtas: #endif /* CONFIG_PPC_RTAS */ -#ifdef CONFIG_FTRACE +#ifdef CONFIG_FUNCTION_TRACER #ifdef CONFIG_DYNAMIC_FTRACE _GLOBAL(mcount) _GLOBAL(_mcount) - stwu r1,-48(r1) - stw r3, 12(r1) - stw r4, 16(r1) - stw r5, 20(r1) - stw r6, 24(r1) - mflr r3 - stw r7, 28(r1) - mfcr r5 - stw r8, 32(r1) - stw r9, 36(r1) - stw r10,40(r1) - stw r3, 44(r1) - stw r5, 8(r1) - subi r3, r3, MCOUNT_INSN_SIZE - .globl mcount_call -mcount_call: - bl ftrace_stub - nop - lwz r6, 8(r1) - lwz r0, 44(r1) - lwz r3, 12(r1) + /* + * It is required that _mcount on PPC32 must preserve the + * link register. But we have r0 to play with. We use r0 + * to push the return address back to the caller of mcount + * into the ctr register, restore the link register and + * then jump back using the ctr register. + */ + mflr r0 mtctr r0 - lwz r4, 16(r1) - mtcr r6 - lwz r5, 20(r1) - lwz r6, 24(r1) - lwz r0, 52(r1) - lwz r7, 28(r1) - lwz r8, 32(r1) + lwz r0, 4(r1) mtlr r0 - lwz r9, 36(r1) - lwz r10,40(r1) - addi r1, r1, 48 bctr _GLOBAL(ftrace_caller) diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 2d802e97097..383ed6eb008 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -57,12 +57,18 @@ system_call_common: beq- 1f ld r1,PACAKSAVE(r13) 1: std r10,0(r1) - crclr so std r11,_NIP(r1) std r12,_MSR(r1) std r0,GPR0(r1) std r10,GPR1(r1) ACCOUNT_CPU_USER_ENTRY(r10, r11) + /* + * This "crclr so" clears CR0.SO, which is the error indication on + * return from this system call. There must be no cmp instruction + * between it and the "mfcr r9" below, otherwise if XER.SO is set, + * CR0.SO will get set, causing all system calls to appear to fail. + */ + crclr so std r2,GPR2(r1) std r3,GPR3(r1) std r4,GPR4(r1) @@ -512,31 +518,12 @@ _GLOBAL(ret_from_except_lite) #endif restore: - ld r5,SOFTE(r1) -#ifdef CONFIG_PPC_ISERIES BEGIN_FW_FTR_SECTION - cmpdi 0,r5,0 - beq 4f - /* Check for pending interrupts (iSeries) */ - ld r3,PACALPPACAPTR(r13) - ld r3,LPPACAANYINT(r3) - cmpdi r3,0 - beq+ 4f /* skip do_IRQ if no interrupts */ - - li r3,0 - stb r3,PACASOFTIRQEN(r13) /* ensure we are soft-disabled */ -#ifdef CONFIG_TRACE_IRQFLAGS - bl .trace_hardirqs_off - mfmsr r10 -#endif - ori r10,r10,MSR_EE - mtmsrd r10 /* hard-enable again */ - addi r3,r1,STACK_FRAME_OVERHEAD - bl .do_IRQ - b .ret_from_except_lite /* loop back and handle more */ -4: -END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES) -#endif + ld r5,SOFTE(r1) +FW_FTR_SECTION_ELSE + b iseries_check_pending_irqs +ALT_FW_FTR_SECTION_END_IFCLR(FW_FEATURE_ISERIES) +2: TRACE_AND_RESTORE_IRQ(r5); /* extract EE bit and use it to restore paca->hard_enabled */ @@ -592,6 +579,30 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES) rfid b . /* prevent speculative execution */ +iseries_check_pending_irqs: +#ifdef CONFIG_PPC_ISERIES + ld r5,SOFTE(r1) + cmpdi 0,r5,0 + beq 2b + /* Check for pending interrupts (iSeries) */ + ld r3,PACALPPACAPTR(r13) + ld r3,LPPACAANYINT(r3) + cmpdi r3,0 + beq+ 2b /* skip do_IRQ if no interrupts */ + + li r3,0 + stb r3,PACASOFTIRQEN(r13) /* ensure we are soft-disabled */ +#ifdef CONFIG_TRACE_IRQFLAGS + bl .trace_hardirqs_off + mfmsr r10 +#endif + ori r10,r10,MSR_EE + mtmsrd r10 /* hard-enable again */ + addi r3,r1,STACK_FRAME_OVERHEAD + bl .do_IRQ + b .ret_from_except_lite /* loop back and handle more */ +#endif + do_work: #ifdef CONFIG_PREEMPT andi. r0,r3,MSR_PR /* Returning to user mode? */ @@ -685,10 +696,6 @@ _GLOBAL(enter_rtas) std r7,_DAR(r1) mfdsisr r8 std r8,_DSISR(r1) - mfsrr0 r9 - std r9,_SRR0(r1) - mfsrr1 r10 - std r10,_SRR1(r1) /* Temporary workaround to clear CR until RTAS can be modified to * ignore all bits. @@ -749,6 +756,10 @@ _STATIC(rtas_return_loc) mfspr r4,SPRN_SPRG3 /* Get PACA */ clrldi r4,r4,2 /* convert to realmode address */ + bcl 20,31,$+4 +0: mflr r3 + ld r3,(1f-0b)(r3) /* get &.rtas_restore_regs */ + mfmsr r6 li r0,MSR_RI andc r6,r6,r0 @@ -756,7 +767,6 @@ _STATIC(rtas_return_loc) mtmsrd r6 ld r1,PACAR1(r4) /* Restore our SP */ - LOAD_REG_IMMEDIATE(r3,.rtas_restore_regs) ld r4,PACASAVEDMSR(r4) /* Restore our MSR */ mtspr SPRN_SRR0,r3 @@ -764,6 +774,9 @@ _STATIC(rtas_return_loc) rfid b . /* prevent speculative execution */ + .align 3 +1: .llong .rtas_restore_regs + _STATIC(rtas_restore_regs) /* relocation is on at this point */ REST_GPR(2, r1) /* Restore the TOC */ @@ -783,10 +796,6 @@ _STATIC(rtas_restore_regs) mtdar r7 ld r8,_DSISR(r1) mtdsisr r8 - ld r9,_SRR0(r1) - mtsrr0 r9 - ld r10,_SRR1(r1) - mtsrr1 r10 addi r1,r1,RTAS_FRAME_SIZE /* Unstack our frame */ ld r0,16(r1) /* get return address */ @@ -881,22 +890,10 @@ _GLOBAL(enter_prom) mtlr r0 blr -#ifdef CONFIG_FTRACE +#ifdef CONFIG_FUNCTION_TRACER #ifdef CONFIG_DYNAMIC_FTRACE _GLOBAL(mcount) _GLOBAL(_mcount) - /* Taken from output of objdump from lib64/glibc */ - mflr r3 - stdu r1, -112(r1) - std r3, 128(r1) - subi r3, r3, MCOUNT_INSN_SIZE - .globl mcount_call -mcount_call: - bl ftrace_stub - nop - ld r0, 128(r1) - mtlr r0 - addi r1, r1, 112 blr _GLOBAL(ftrace_caller) diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c index 3855ceb937b..5355244c99f 100644 --- a/arch/powerpc/kernel/ftrace.c +++ b/arch/powerpc/kernel/ftrace.c @@ -9,36 +9,44 @@ #include <linux/spinlock.h> #include <linux/hardirq.h> +#include <linux/uaccess.h> +#include <linux/module.h> #include <linux/ftrace.h> #include <linux/percpu.h> #include <linux/init.h> #include <linux/list.h> #include <asm/cacheflush.h> +#include <asm/code-patching.h> #include <asm/ftrace.h> +#if 0 +#define DEBUGP printk +#else +#define DEBUGP(fmt , ...) do { } while (0) +#endif -static unsigned int ftrace_nop = 0x60000000; +static unsigned int ftrace_nop = PPC_NOP_INSTR; #ifdef CONFIG_PPC32 # define GET_ADDR(addr) addr #else /* PowerPC64's functions are data that points to the functions */ -# define GET_ADDR(addr) *(unsigned long *)addr +# define GET_ADDR(addr) (*(unsigned long *)addr) #endif -static unsigned int notrace ftrace_calc_offset(long ip, long addr) +static unsigned int ftrace_calc_offset(long ip, long addr) { return (int)(addr - ip); } -notrace unsigned char *ftrace_nop_replace(void) +static unsigned char *ftrace_nop_replace(void) { return (char *)&ftrace_nop; } -notrace unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr) +static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr) { static unsigned int op; @@ -68,87 +76,443 @@ notrace unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr) # define _ASM_PTR " .long " #endif -notrace int +static int ftrace_modify_code(unsigned long ip, unsigned char *old_code, unsigned char *new_code) { - unsigned replaced; - unsigned old = *(unsigned *)old_code; - unsigned new = *(unsigned *)new_code; - int faulted = 0; + unsigned char replaced[MCOUNT_INSN_SIZE]; /* * Note: Due to modules and __init, code can * disappear and change, we need to protect against faulting - * as well as code changing. + * as well as code changing. We do this by using the + * probe_kernel_* functions. * * No real locking needed, this code is run through - * kstop_machine. + * kstop_machine, or before SMP starts. */ - asm volatile ( - "1: lwz %1, 0(%2)\n" - " cmpw %1, %5\n" - " bne 2f\n" - " stwu %3, 0(%2)\n" - "2:\n" - ".section .fixup, \"ax\"\n" - "3: li %0, 1\n" - " b 2b\n" - ".previous\n" - ".section __ex_table,\"a\"\n" - _ASM_ALIGN "\n" - _ASM_PTR "1b, 3b\n" - ".previous" - : "=r"(faulted), "=r"(replaced) - : "r"(ip), "r"(new), - "0"(faulted), "r"(old) - : "memory"); - - if (replaced != old && replaced != new) - faulted = 2; - - if (!faulted) - flush_icache_range(ip, ip + 8); - - return faulted; + + /* read the text we want to modify */ + if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE)) + return -EFAULT; + + /* Make sure it is what we expect it to be */ + if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0) + return -EINVAL; + + /* replace the text with the new text */ + if (probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE)) + return -EPERM; + + flush_icache_range(ip, ip + 8); + + return 0; } -notrace int ftrace_update_ftrace_func(ftrace_func_t func) +/* + * Helper functions that are the same for both PPC64 and PPC32. + */ +static int test_24bit_addr(unsigned long ip, unsigned long addr) { - unsigned long ip = (unsigned long)(&ftrace_call); - unsigned char old[MCOUNT_INSN_SIZE], *new; - int ret; - memcpy(old, &ftrace_call, MCOUNT_INSN_SIZE); - new = ftrace_call_replace(ip, (unsigned long)func); - ret = ftrace_modify_code(ip, old, new); + /* use the create_branch to verify that this offset can be branched */ + return create_branch((unsigned int *)ip, addr, 0); +} - return ret; +static int is_bl_op(unsigned int op) +{ + return (op & 0xfc000003) == 0x48000001; } -notrace int ftrace_mcount_set(unsigned long *data) +static unsigned long find_bl_target(unsigned long ip, unsigned int op) { - unsigned long ip = (long)(&mcount_call); - unsigned long *addr = data; - unsigned char old[MCOUNT_INSN_SIZE], *new; + static int offset; + + offset = (op & 0x03fffffc); + /* make it signed */ + if (offset & 0x02000000) + offset |= 0xfe000000; + + return ip + (long)offset; +} + +#ifdef CONFIG_PPC64 +static int +__ftrace_make_nop(struct module *mod, + struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned int op; + unsigned int jmp[5]; + unsigned long ptr; + unsigned long ip = rec->ip; + unsigned long tramp; + int offset; + + /* read where this goes */ + if (probe_kernel_read(&op, (void *)ip, sizeof(int))) + return -EFAULT; + + /* Make sure that that this is still a 24bit jump */ + if (!is_bl_op(op)) { + printk(KERN_ERR "Not expected bl: opcode is %x\n", op); + return -EINVAL; + } + + /* lets find where the pointer goes */ + tramp = find_bl_target(ip, op); + + /* + * On PPC64 the trampoline looks like: + * 0x3d, 0x82, 0x00, 0x00, addis r12,r2, <high> + * 0x39, 0x8c, 0x00, 0x00, addi r12,r12, <low> + * Where the bytes 2,3,6 and 7 make up the 32bit offset + * to the TOC that holds the pointer. + * to jump to. + * 0xf8, 0x41, 0x00, 0x28, std r2,40(r1) + * 0xe9, 0x6c, 0x00, 0x20, ld r11,32(r12) + * The actually address is 32 bytes from the offset + * into the TOC. + * 0xe8, 0x4c, 0x00, 0x28, ld r2,40(r12) + */ + + DEBUGP("ip:%lx jumps to %lx r2: %lx", ip, tramp, mod->arch.toc); + + /* Find where the trampoline jumps to */ + if (probe_kernel_read(jmp, (void *)tramp, sizeof(jmp))) { + printk(KERN_ERR "Failed to read %lx\n", tramp); + return -EFAULT; + } + + DEBUGP(" %08x %08x", jmp[0], jmp[1]); + + /* verify that this is what we expect it to be */ + if (((jmp[0] & 0xffff0000) != 0x3d820000) || + ((jmp[1] & 0xffff0000) != 0x398c0000) || + (jmp[2] != 0xf8410028) || + (jmp[3] != 0xe96c0020) || + (jmp[4] != 0xe84c0028)) { + printk(KERN_ERR "Not a trampoline\n"); + return -EINVAL; + } + + offset = (unsigned)((unsigned short)jmp[0]) << 16 | + (unsigned)((unsigned short)jmp[1]); + + DEBUGP(" %x ", offset); + + /* get the address this jumps too */ + tramp = mod->arch.toc + offset + 32; + DEBUGP("toc: %lx", tramp); + + if (probe_kernel_read(jmp, (void *)tramp, 8)) { + printk(KERN_ERR "Failed to read %lx\n", tramp); + return -EFAULT; + } + + DEBUGP(" %08x %08x\n", jmp[0], jmp[1]); + + ptr = ((unsigned long)jmp[0] << 32) + jmp[1]; + + /* This should match what was called */ + if (ptr != GET_ADDR(addr)) { + printk(KERN_ERR "addr does not match %lx\n", ptr); + return -EINVAL; + } /* - * Replace the mcount stub with a pointer to the - * ip recorder function. + * We want to nop the line, but the next line is + * 0xe8, 0x41, 0x00, 0x28 ld r2,40(r1) + * This needs to be turned to a nop too. */ - memcpy(old, &mcount_call, MCOUNT_INSN_SIZE); - new = ftrace_call_replace(ip, *addr); - *addr = ftrace_modify_code(ip, old, new); + if (probe_kernel_read(&op, (void *)(ip+4), MCOUNT_INSN_SIZE)) + return -EFAULT; + + if (op != 0xe8410028) { + printk(KERN_ERR "Next line is not ld! (%08x)\n", op); + return -EINVAL; + } + + /* + * Milton Miller pointed out that we can not blindly do nops. + * If a task was preempted when calling a trace function, + * the nops will remove the way to restore the TOC in r2 + * and the r2 TOC will get corrupted. + */ + + /* + * Replace: + * bl <tramp> <==== will be replaced with "b 1f" + * ld r2,40(r1) + * 1: + */ + op = 0x48000008; /* b +8 */ + + if (probe_kernel_write((void *)ip, &op, MCOUNT_INSN_SIZE)) + return -EPERM; + + + flush_icache_range(ip, ip + 8); return 0; } -int __init ftrace_dyn_arch_init(void *data) +#else /* !PPC64 */ +static int +__ftrace_make_nop(struct module *mod, + struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned int op; + unsigned int jmp[4]; + unsigned long ip = rec->ip; + unsigned long tramp; + + if (probe_kernel_read(&op, (void *)ip, MCOUNT_INSN_SIZE)) + return -EFAULT; + + /* Make sure that that this is still a 24bit jump */ + if (!is_bl_op(op)) { + printk(KERN_ERR "Not expected bl: opcode is %x\n", op); + return -EINVAL; + } + + /* lets find where the pointer goes */ + tramp = find_bl_target(ip, op); + + /* + * On PPC32 the trampoline looks like: + * 0x3d, 0x60, 0x00, 0x00 lis r11,sym@ha + * 0x39, 0x6b, 0x00, 0x00 addi r11,r11,sym@l + * 0x7d, 0x69, 0x03, 0xa6 mtctr r11 + * 0x4e, 0x80, 0x04, 0x20 bctr + */ + + DEBUGP("ip:%lx jumps to %lx", ip, tramp); + + /* Find where the trampoline jumps to */ + if (probe_kernel_read(jmp, (void *)tramp, sizeof(jmp))) { + printk(KERN_ERR "Failed to read %lx\n", tramp); + return -EFAULT; + } + + DEBUGP(" %08x %08x ", jmp[0], jmp[1]); + + /* verify that this is what we expect it to be */ + if (((jmp[0] & 0xffff0000) != 0x3d600000) || + ((jmp[1] & 0xffff0000) != 0x396b0000) || + (jmp[2] != 0x7d6903a6) || + (jmp[3] != 0x4e800420)) { + printk(KERN_ERR "Not a trampoline\n"); + return -EINVAL; + } + + tramp = (jmp[1] & 0xffff) | + ((jmp[0] & 0xffff) << 16); + if (tramp & 0x8000) + tramp -= 0x10000; + + DEBUGP(" %x ", tramp); + + if (tramp != addr) { + printk(KERN_ERR + "Trampoline location %08lx does not match addr\n", + tramp); + return -EINVAL; + } + + op = PPC_NOP_INSTR; + + if (probe_kernel_write((void *)ip, &op, MCOUNT_INSN_SIZE)) + return -EPERM; + + flush_icache_range(ip, ip + 8); + + return 0; +} +#endif /* PPC64 */ + +int ftrace_make_nop(struct module *mod, + struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned char *old, *new; + unsigned long ip = rec->ip; + + /* + * If the calling address is more that 24 bits away, + * then we had to use a trampoline to make the call. + * Otherwise just update the call site. + */ + if (test_24bit_addr(ip, addr)) { + /* within range */ + old = ftrace_call_replace(ip, addr); + new = ftrace_nop_replace(); + return ftrace_modify_code(ip, old, new); + } + + /* + * Out of range jumps are called from modules. + * We should either already have a pointer to the module + * or it has been passed in. + */ + if (!rec->arch.mod) { + if (!mod) { + printk(KERN_ERR "No module loaded addr=%lx\n", + addr); + return -EFAULT; + } + rec->arch.mod = mod; + } else if (mod) { + if (mod != rec->arch.mod) { + printk(KERN_ERR + "Record mod %p not equal to passed in mod %p\n", + rec->arch.mod, mod); + return -EINVAL; + } + /* nothing to do if mod == rec->arch.mod */ + } else + mod = rec->arch.mod; + + return __ftrace_make_nop(mod, rec, addr); + +} + +#ifdef CONFIG_PPC64 +static int +__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned int op[2]; + unsigned long ip = rec->ip; + + /* read where this goes */ + if (probe_kernel_read(op, (void *)ip, MCOUNT_INSN_SIZE * 2)) + return -EFAULT; + + /* + * It should be pointing to two nops or + * b +8; ld r2,40(r1) + */ + if (((op[0] != 0x48000008) || (op[1] != 0xe8410028)) && + ((op[0] != PPC_NOP_INSTR) || (op[1] != PPC_NOP_INSTR))) { + printk(KERN_ERR "Expected NOPs but have %x %x\n", op[0], op[1]); + return -EINVAL; + } + + /* If we never set up a trampoline to ftrace_caller, then bail */ + if (!rec->arch.mod->arch.tramp) { + printk(KERN_ERR "No ftrace trampoline\n"); + return -EINVAL; + } + + /* create the branch to the trampoline */ + op[0] = create_branch((unsigned int *)ip, + rec->arch.mod->arch.tramp, BRANCH_SET_LINK); + if (!op[0]) { + printk(KERN_ERR "REL24 out of range!\n"); + return -EINVAL; + } + + /* ld r2,40(r1) */ + op[1] = 0xe8410028; + + DEBUGP("write to %lx\n", rec->ip); + + if (probe_kernel_write((void *)ip, op, MCOUNT_INSN_SIZE * 2)) + return -EPERM; + + flush_icache_range(ip, ip + 8); + + return 0; +} +#else +static int +__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) { - /* This is running in kstop_machine */ + unsigned int op; + unsigned long ip = rec->ip; - ftrace_mcount_set(data); + /* read where this goes */ + if (probe_kernel_read(&op, (void *)ip, MCOUNT_INSN_SIZE)) + return -EFAULT; + + /* It should be pointing to a nop */ + if (op != PPC_NOP_INSTR) { + printk(KERN_ERR "Expected NOP but have %x\n", op); + return -EINVAL; + } + + /* If we never set up a trampoline to ftrace_caller, then bail */ + if (!rec->arch.mod->arch.tramp) { + printk(KERN_ERR "No ftrace trampoline\n"); + return -EINVAL; + } + + /* create the branch to the trampoline */ + op = create_branch((unsigned int *)ip, + rec->arch.mod->arch.tramp, BRANCH_SET_LINK); + if (!op) { + printk(KERN_ERR "REL24 out of range!\n"); + return -EINVAL; + } + + DEBUGP("write to %lx\n", rec->ip); + + if (probe_kernel_write((void *)ip, &op, MCOUNT_INSN_SIZE)) + return -EPERM; + + flush_icache_range(ip, ip + 8); return 0; } +#endif /* CONFIG_PPC64 */ + +int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned char *old, *new; + unsigned long ip = rec->ip; + + /* + * If the calling address is more that 24 bits away, + * then we had to use a trampoline to make the call. + * Otherwise just update the call site. + */ + if (test_24bit_addr(ip, addr)) { + /* within range */ + old = ftrace_nop_replace(); + new = ftrace_call_replace(ip, addr); + return ftrace_modify_code(ip, old, new); + } + + /* + * Out of range jumps are called from modules. + * Being that we are converting from nop, it had better + * already have a module defined. + */ + if (!rec->arch.mod) { + printk(KERN_ERR "No module loaded\n"); + return -EINVAL; + } + + return __ftrace_make_call(rec, addr); +} + +int ftrace_update_ftrace_func(ftrace_func_t func) +{ + unsigned long ip = (unsigned long)(&ftrace_call); + unsigned char old[MCOUNT_INSN_SIZE], *new; + int ret; + + memcpy(old, &ftrace_call, MCOUNT_INSN_SIZE); + new = ftrace_call_replace(ip, (unsigned long)func); + ret = ftrace_modify_code(ip, old, new); + + return ret; +} + +int __init ftrace_dyn_arch_init(void *data) +{ + /* caller expects data to be zero */ + unsigned long *p = data; + + *p = 0; + return 0; +} diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index 8bb65751929..a1c4cfd25de 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -31,6 +31,7 @@ #include <asm/ppc_asm.h> #include <asm/asm-offsets.h> #include <asm/ptrace.h> +#include <asm/bug.h> /* 601 only have IBAT; cr0.eq is set on 601 when using this macro */ #define LOAD_BAT(n, reg, RA, RB) \ @@ -110,6 +111,12 @@ __start: #ifdef CONFIG_PPC_MULTIPLATFORM cmpwi 0,r5,0 beq 1f + + /* find out where we are now */ + bcl 20,31,$+4 +0: mflr r8 /* r8 = runtime addr here */ + addis r8,r8,(_stext - 0b)@ha + addi r8,r8,(_stext - 0b)@l /* current runtime base addr */ bl prom_init trap #endif @@ -176,7 +183,8 @@ __after_mmu_off: bl reloc_offset mr r26,r3 addis r4,r3,KERNELBASE@h /* current address of _start */ - cmpwi 0,r4,0 /* are we already running at 0? */ + lis r5,PHYSICAL_START@h + cmplw 0,r4,r5 /* already running at PHYSICAL_START? */ bne relocate_kernel /* * we now have the 1st 16M of ram mapped with the bats. @@ -369,13 +377,13 @@ i##n: \ DataAccess: EXCEPTION_PROLOG mfspr r10,SPRN_DSISR + stw r10,_DSISR(r11) andis. r0,r10,0xa470 /* weird error? */ bne 1f /* if not, try to put a PTE */ mfspr r4,SPRN_DAR /* into the hash table */ rlwinm r3,r10,32-15,21,21 /* DSISR_STORE -> _PAGE_RW */ bl hash_page -1: stw r10,_DSISR(r11) - mr r5,r10 +1: lwz r5,_DSISR(r11) /* get DSISR value */ mfspr r4,SPRN_DAR EXC_XFER_EE_LITE(0x300, handle_page_fault) @@ -804,13 +812,13 @@ giveup_altivec: /* * This code is jumped to from the startup code to copy - * the kernel image to physical address 0. + * the kernel image to physical address PHYSICAL_START. */ relocate_kernel: addis r9,r26,klimit@ha /* fetch klimit */ lwz r25,klimit@l(r9) addis r25,r25,-KERNELBASE@h - li r3,0 /* Destination base address */ + lis r3,PHYSICAL_START@h /* Destination base address */ li r6,0 /* Destination offset */ li r5,0x4000 /* # bytes of memory to copy */ bl copy_and_flush /* copy the first 0x4000 bytes */ @@ -983,12 +991,12 @@ load_up_mmu: LOAD_BAT(1,r3,r4,r5) LOAD_BAT(2,r3,r4,r5) LOAD_BAT(3,r3,r4,r5) -BEGIN_FTR_SECTION +BEGIN_MMU_FTR_SECTION LOAD_BAT(4,r3,r4,r5) LOAD_BAT(5,r3,r4,r5) LOAD_BAT(6,r3,r4,r5) LOAD_BAT(7,r3,r4,r5) -END_FTR_SECTION_IFSET(CPU_FTR_HAS_HIGH_BATS) +END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS) blr /* @@ -1064,9 +1072,14 @@ start_here: RFI /* + * void switch_mmu_context(struct mm_struct *prev, struct mm_struct *next); + * * Set up the segment registers for a new context. */ -_ENTRY(set_context) +_ENTRY(switch_mmu_context) + lwz r3,MMCONTEXTID(r4) + cmpwi cr0,r3,0 + blt- 4f mulli r3,r3,897 /* multiply context by skew factor */ rlwinm r3,r3,4,8,27 /* VSID = (context & 0xfffff) << 4 */ addis r3,r3,0x6000 /* Set Ks, Ku bits */ @@ -1077,6 +1090,7 @@ _ENTRY(set_context) /* Context switch the PTE pointer for the Abatron BDI2000. * The PGDIR is passed as second argument. */ + lwz r4,MM_PGD(r4) lis r5, KERNELBASE@h lwz r5, 0xf0(r5) stw r4, 0x4(r5) @@ -1092,6 +1106,9 @@ _ENTRY(set_context) sync isync blr +4: trap + EMIT_BUG_ENTRY 4b,__FILE__,__LINE__,0 + blr /* * An undocumented "feature" of 604e requires that the v bit @@ -1125,7 +1142,7 @@ clear_bats: mtspr SPRN_IBAT2L,r10 mtspr SPRN_IBAT3U,r10 mtspr SPRN_IBAT3L,r10 -BEGIN_FTR_SECTION +BEGIN_MMU_FTR_SECTION /* Here's a tweak: at this point, CPU setup have * not been called yet, so HIGH_BAT_EN may not be * set in HID0 for the 745x processors. However, it @@ -1148,7 +1165,7 @@ BEGIN_FTR_SECTION mtspr SPRN_IBAT6L,r10 mtspr SPRN_IBAT7U,r10 mtspr SPRN_IBAT7L,r10 -END_FTR_SECTION_IFSET(CPU_FTR_HAS_HIGH_BATS) +END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS) blr flush_tlbs: @@ -1172,11 +1189,11 @@ mmu_off: /* * Use the first pair of BAT registers to map the 1st 16MB - * of RAM to KERNELBASE. From this point on we can't safely + * of RAM to PAGE_OFFSET. From this point on we can't safely * call OF any more. */ initial_bats: - lis r11,KERNELBASE@h + lis r11,PAGE_OFFSET@h mfspr r9,SPRN_PVR rlwinm r9,r9,16,16,31 /* r9 = 1 for 601, 4 for 604 */ cmpwi 0,r9,1 diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S index f3a1ea9d7fe..b56fecc93a1 100644 --- a/arch/powerpc/kernel/head_44x.S +++ b/arch/powerpc/kernel/head_44x.S @@ -69,6 +69,17 @@ _ENTRY(_start); li r24,0 /* CPU number */ /* + * In case the firmware didn't do it, we apply some workarounds + * that are good for all 440 core variants here + */ + mfspr r3,SPRN_CCR0 + rlwinm r3,r3,0,0,27 /* disable icache prefetch */ + isync + mtspr SPRN_CCR0,r3 + isync + sync + +/* * Set up the initial MMU state * * We are still executing code at the virtual address @@ -391,12 +402,14 @@ interrupt_base: rlwimi r13,r12,10,30,30 /* Load the PTE */ - rlwinm r12, r10, 13, 19, 29 /* Compute pgdir/pmd offset */ + /* Compute pgdir/pmd offset */ + rlwinm r12, r10, PPC44x_PGD_OFF_SHIFT, PPC44x_PGD_OFF_MASK_BIT, 29 lwzx r11, r12, r11 /* Get pgd/pmd entry */ rlwinm. r12, r11, 0, 0, 20 /* Extract pt base address */ beq 2f /* Bail if no table */ - rlwimi r12, r10, 23, 20, 28 /* Compute pte address */ + /* Compute pte address */ + rlwimi r12, r10, PPC44x_PTE_ADD_SHIFT, PPC44x_PTE_ADD_MASK_BIT, 28 lwz r11, 0(r12) /* Get high word of pte entry */ lwz r12, 4(r12) /* Get low word of pte entry */ @@ -485,12 +498,14 @@ tlb_44x_patch_hwater_D: /* Make up the required permissions */ li r13,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_HWEXEC - rlwinm r12, r10, 13, 19, 29 /* Compute pgdir/pmd offset */ + /* Compute pgdir/pmd offset */ + rlwinm r12, r10, PPC44x_PGD_OFF_SHIFT, PPC44x_PGD_OFF_MASK_BIT, 29 lwzx r11, r12, r11 /* Get pgd/pmd entry */ rlwinm. r12, r11, 0, 0, 20 /* Extract pt base address */ beq 2f /* Bail if no table */ - rlwimi r12, r10, 23, 20, 28 /* Compute pte address */ + /* Compute pte address */ + rlwimi r12, r10, PPC44x_PTE_ADD_SHIFT, PPC44x_PTE_ADD_MASK_BIT, 28 lwz r11, 0(r12) /* Get high word of pte entry */ lwz r12, 4(r12) /* Get low word of pte entry */ @@ -554,15 +569,16 @@ tlb_44x_patch_hwater_I: */ finish_tlb_load: /* Combine RPN & ERPN an write WS 0 */ - rlwimi r11,r12,0,0,19 + rlwimi r11,r12,0,0,31-PAGE_SHIFT tlbwe r11,r13,PPC44x_TLB_XLAT /* * Create WS1. This is the faulting address (EPN), * page size, and valid flag. */ - li r11,PPC44x_TLB_VALID | PPC44x_TLB_4K - rlwimi r10,r11,0,20,31 /* Insert valid and page size*/ + li r11,PPC44x_TLB_VALID | PPC44x_TLBE_SIZE + /* Insert valid and page size */ + rlwimi r10,r11,0,PPC44x_PTE_ADD_MASK_BIT,31 tlbwe r10,r13,PPC44x_TLB_PAGEID /* Write PAGEID */ /* And WS 2 */ @@ -634,12 +650,12 @@ _GLOBAL(set_context) * goes at the beginning of the data segment, which is page-aligned. */ .data - .align 12 + .align PAGE_SHIFT .globl sdata sdata: .globl empty_zero_page empty_zero_page: - .space 4096 + .space PAGE_SIZE /* * To support >32-bit physical addresses, we use an 8KB pgdir. diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index cc8fb474d52..b4bcf5a930f 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -82,7 +82,11 @@ END_FTR_SECTION(0, 1) /* Catch branch to 0 in real mode */ trap - /* Secondary processors spin on this value until it goes to 1. */ + /* Secondary processors spin on this value until it becomes nonzero. + * When it does it contains the real address of the descriptor + * of the function that the cpu should jump to to continue + * initialization. + */ .globl __secondary_hold_spinloop __secondary_hold_spinloop: .llong 0x0 @@ -102,6 +106,20 @@ __secondary_hold_acknowledge: .llong hvReleaseData-KERNELBASE #endif /* CONFIG_PPC_ISERIES */ +#ifdef CONFIG_CRASH_DUMP + /* This flag is set to 1 by a loader if the kernel should run + * at the loaded address instead of the linked address. This + * is used by kexec-tools to keep the the kdump kernel in the + * crash_kernel region. The loader is responsible for + * observing the alignment requirement. + */ + /* Do not move this variable as kexec-tools knows about it. */ + . = 0x5c + .globl __run_at_load +__run_at_load: + .long 0x72756e30 /* "run0" -- relocate to 0 by default */ +#endif + . = 0x60 /* * The following code is used to hold secondary processors @@ -109,8 +127,11 @@ __secondary_hold_acknowledge: * before the bulk of the kernel has been relocated. This code * is relocated to physical address 0x60 before prom_init is run. * All of it must fit below the first exception vector at 0x100. + * Use .globl here not _GLOBAL because we want __secondary_hold + * to be the actual text address, not a descriptor. */ -_GLOBAL(__secondary_hold) + .globl __secondary_hold +__secondary_hold: mfmsr r24 ori r24,r24,MSR_RI mtmsrd r24 /* RI on */ @@ -121,16 +142,16 @@ _GLOBAL(__secondary_hold) /* Tell the master cpu we're here */ /* Relocation is off & we are located at an address less */ /* than 0x100, so only need to grab low order offset. */ - std r24,__secondary_hold_acknowledge@l(0) + std r24,__secondary_hold_acknowledge-_stext(0) sync /* All secondary cpus wait here until told to start. */ -100: ld r4,__secondary_hold_spinloop@l(0) - cmpdi 0,r4,1 - bne 100b +100: ld r4,__secondary_hold_spinloop-_stext(0) + cmpdi 0,r4,0 + beq 100b #if defined(CONFIG_SMP) || defined(CONFIG_KEXEC) - LOAD_REG_IMMEDIATE(r4, .generic_secondary_smp_init) + ld r4,0(r4) /* deref function descriptor */ mtctr r4 mr r3,r24 bctr @@ -147,6 +168,10 @@ exception_marker: /* * This is the start of the interrupt handlers for pSeries * This code runs with relocation off. + * Code from here to __end_interrupts gets copied down to real + * address 0x100 when we are running a relocatable kernel. + * Therefore any relative branches in this section must only + * branch to labels in this section. */ . = 0x100 .globl __start_interrupts @@ -200,7 +225,20 @@ data_access_slb_pSeries: mfspr r10,SPRN_SPRG1 std r10,PACA_EXSLB+EX_R13(r13) mfspr r12,SPRN_SRR1 /* and SRR1 */ - b .slb_miss_realmode /* Rel. branch works in real mode */ +#ifndef CONFIG_RELOCATABLE + b .slb_miss_realmode +#else + /* + * We can't just use a direct branch to .slb_miss_realmode + * because the distance from here to there depends on where + * the kernel ends up being put. + */ + mfctr r11 + ld r10,PACAKBASE(r13) + LOAD_HANDLER(r10, .slb_miss_realmode) + mtctr r10 + bctr +#endif STD_EXCEPTION_PSERIES(0x400, instruction_access) @@ -225,7 +263,15 @@ instruction_access_slb_pSeries: mfspr r10,SPRN_SPRG1 std r10,PACA_EXSLB+EX_R13(r13) mfspr r12,SPRN_SRR1 /* and SRR1 */ - b .slb_miss_realmode /* Rel. branch works in real mode */ +#ifndef CONFIG_RELOCATABLE + b .slb_miss_realmode +#else + mfctr r11 + ld r10,PACAKBASE(r13) + LOAD_HANDLER(r10, .slb_miss_realmode) + mtctr r10 + bctr +#endif MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt) STD_EXCEPTION_PSERIES(0x600, alignment) @@ -244,14 +290,12 @@ BEGIN_FTR_SECTION beq- 1f END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE) mr r9,r13 - mfmsr r10 mfspr r13,SPRN_SPRG3 mfspr r11,SPRN_SRR0 - clrrdi r12,r13,32 - oris r12,r12,system_call_common@h - ori r12,r12,system_call_common@l + ld r12,PACAKBASE(r13) + ld r10,PACAKMSR(r13) + LOAD_HANDLER(r12, system_call_entry) mtspr SPRN_SRR0,r12 - ori r10,r10,MSR_IR|MSR_DR|MSR_RI mfspr r12,SPRN_SRR1 mtspr SPRN_SRR1,r10 rfid @@ -325,16 +369,32 @@ do_stab_bolted_pSeries: mfspr r12,SPRN_SPRG2 EXCEPTION_PROLOG_PSERIES(PACA_EXSLB, .do_stab_bolted) +#ifdef CONFIG_PPC_PSERIES +/* + * Vectors for the FWNMI option. Share common code. + */ + .globl system_reset_fwnmi + .align 7 +system_reset_fwnmi: + HMT_MEDIUM + mtspr SPRN_SPRG1,r13 /* save r13 */ + EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common) + + .globl machine_check_fwnmi + .align 7 +machine_check_fwnmi: + HMT_MEDIUM + mtspr SPRN_SPRG1,r13 /* save r13 */ + EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common) + +#endif /* CONFIG_PPC_PSERIES */ + +#ifdef __DISABLED__ /* - * We have some room here we use that to put - * the peries slb miss user trampoline code so it's reasonably - * away from slb_miss_user_common to avoid problems with rfid - * * This is used for when the SLB miss handler has to go virtual, * which doesn't happen for now anymore but will once we re-implement * dynamic VSIDs for shared page tables */ -#ifdef __DISABLED__ slb_miss_user_pseries: std r10,PACA_EXGEN+EX_R10(r13) std r11,PACA_EXGEN+EX_R11(r13) @@ -357,25 +417,17 @@ slb_miss_user_pseries: b . /* prevent spec. execution */ #endif /* __DISABLED__ */ -#ifdef CONFIG_PPC_PSERIES + .align 7 + .globl __end_interrupts +__end_interrupts: + /* - * Vectors for the FWNMI option. Share common code. + * Code from here down to __end_handlers is invoked from the + * exception prologs above. Because the prologs assemble the + * addresses of these handlers using the LOAD_HANDLER macro, + * which uses an addi instruction, these handlers must be in + * the first 32k of the kernel image. */ - .globl system_reset_fwnmi - .align 7 -system_reset_fwnmi: - HMT_MEDIUM - mtspr SPRN_SPRG1,r13 /* save r13 */ - EXCEPTION_PROLOG_PSERIES_FORCE_64BIT(PACA_EXGEN, system_reset_common) - - .globl machine_check_fwnmi - .align 7 -machine_check_fwnmi: - HMT_MEDIUM - mtspr SPRN_SPRG1,r13 /* save r13 */ - EXCEPTION_PROLOG_PSERIES_FORCE_64BIT(PACA_EXMC, machine_check_common) - -#endif /* CONFIG_PPC_PSERIES */ /*** Common interrupt handlers ***/ @@ -414,6 +466,10 @@ machine_check_common: STD_EXCEPTION_COMMON(0x1800, cbe_thermal, .cbe_thermal_exception) #endif /* CONFIG_CBE_RAS */ + .align 7 +system_call_entry: + b system_call_common + /* * Here we have detected that the kernel stack pointer is bad. * R9 contains the saved CR, r13 points to the paca, @@ -457,65 +513,6 @@ bad_stack: b 1b /* - * Return from an exception with minimal checks. - * The caller is assumed to have done EXCEPTION_PROLOG_COMMON. - * If interrupts have been enabled, or anything has been - * done that might have changed the scheduling status of - * any task or sent any task a signal, you should use - * ret_from_except or ret_from_except_lite instead of this. - */ -fast_exc_return_irq: /* restores irq state too */ - ld r3,SOFTE(r1) - TRACE_AND_RESTORE_IRQ(r3); - ld r12,_MSR(r1) - rldicl r4,r12,49,63 /* get MSR_EE to LSB */ - stb r4,PACAHARDIRQEN(r13) /* restore paca->hard_enabled */ - b 1f - - .globl fast_exception_return -fast_exception_return: - ld r12,_MSR(r1) -1: ld r11,_NIP(r1) - andi. r3,r12,MSR_RI /* check if RI is set */ - beq- unrecov_fer - -#ifdef CONFIG_VIRT_CPU_ACCOUNTING - andi. r3,r12,MSR_PR - beq 2f - ACCOUNT_CPU_USER_EXIT(r3, r4) -2: -#endif - - ld r3,_CCR(r1) - ld r4,_LINK(r1) - ld r5,_CTR(r1) - ld r6,_XER(r1) - mtcr r3 - mtlr r4 - mtctr r5 - mtxer r6 - REST_GPR(0, r1) - REST_8GPRS(2, r1) - - mfmsr r10 - rldicl r10,r10,48,1 /* clear EE */ - rldicr r10,r10,16,61 /* clear RI (LE is 0 already) */ - mtmsrd r10,1 - - mtspr SPRN_SRR1,r12 - mtspr SPRN_SRR0,r11 - REST_4GPRS(10, r1) - ld r1,GPR1(r1) - rfid - b . /* prevent speculative execution */ - -unrecov_fer: - bl .save_nvgprs -1: addi r3,r1,STACK_FRAME_OVERHEAD - bl .unrecoverable_exception - b 1b - -/* * Here r13 points to the paca, r9 contains the saved CR, * SRR0 and SRR1 are saved in r11 and r12, * r9 - r13 are saved in paca->exgen. @@ -616,6 +613,9 @@ unrecov_user_slb: */ _GLOBAL(slb_miss_realmode) mflr r10 +#ifdef CONFIG_RELOCATABLE + mtctr r11 +#endif stw r9,PACA_EXSLB+EX_CCR(r13) /* save CR in exc. frame */ std r10,PACA_EXSLB+EX_LR(r13) /* save LR */ @@ -666,11 +666,10 @@ BEGIN_FW_FTR_SECTION END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES) #endif /* CONFIG_PPC_ISERIES */ mfspr r11,SPRN_SRR0 - clrrdi r10,r13,32 + ld r10,PACAKBASE(r13) LOAD_HANDLER(r10,unrecov_slb) mtspr SPRN_SRR0,r10 - mfmsr r10 - ori r10,r10,MSR_IR|MSR_DR|MSR_RI + ld r10,PACAKMSR(r13) mtspr SPRN_SRR1,r10 rfid b . @@ -766,6 +765,85 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) bl .altivec_unavailable_exception b .ret_from_except + .align 7 + .globl vsx_unavailable_common +vsx_unavailable_common: + EXCEPTION_PROLOG_COMMON(0xf40, PACA_EXGEN) +#ifdef CONFIG_VSX +BEGIN_FTR_SECTION + bne .load_up_vsx +1: +END_FTR_SECTION_IFSET(CPU_FTR_VSX) +#endif + bl .save_nvgprs + addi r3,r1,STACK_FRAME_OVERHEAD + ENABLE_INTS + bl .vsx_unavailable_exception + b .ret_from_except + + .align 7 + .globl __end_handlers +__end_handlers: + +/* + * Return from an exception with minimal checks. + * The caller is assumed to have done EXCEPTION_PROLOG_COMMON. + * If interrupts have been enabled, or anything has been + * done that might have changed the scheduling status of + * any task or sent any task a signal, you should use + * ret_from_except or ret_from_except_lite instead of this. + */ +fast_exc_return_irq: /* restores irq state too */ + ld r3,SOFTE(r1) + TRACE_AND_RESTORE_IRQ(r3); + ld r12,_MSR(r1) + rldicl r4,r12,49,63 /* get MSR_EE to LSB */ + stb r4,PACAHARDIRQEN(r13) /* restore paca->hard_enabled */ + b 1f + + .globl fast_exception_return +fast_exception_return: + ld r12,_MSR(r1) +1: ld r11,_NIP(r1) + andi. r3,r12,MSR_RI /* check if RI is set */ + beq- unrecov_fer + +#ifdef CONFIG_VIRT_CPU_ACCOUNTING + andi. r3,r12,MSR_PR + beq 2f + ACCOUNT_CPU_USER_EXIT(r3, r4) +2: +#endif + + ld r3,_CCR(r1) + ld r4,_LINK(r1) + ld r5,_CTR(r1) + ld r6,_XER(r1) + mtcr r3 + mtlr r4 + mtctr r5 + mtxer r6 + REST_GPR(0, r1) + REST_8GPRS(2, r1) + + mfmsr r10 + rldicl r10,r10,48,1 /* clear EE */ + rldicr r10,r10,16,61 /* clear RI (LE is 0 already) */ + mtmsrd r10,1 + + mtspr SPRN_SRR1,r12 + mtspr SPRN_SRR0,r11 + REST_4GPRS(10, r1) + ld r1,GPR1(r1) + rfid + b . /* prevent speculative execution */ + +unrecov_fer: + bl .save_nvgprs +1: addi r3,r1,STACK_FRAME_OVERHEAD + bl .unrecoverable_exception + b 1b + #ifdef CONFIG_ALTIVEC /* * load_up_altivec(unused, unused, tsk) @@ -840,22 +918,6 @@ _STATIC(load_up_altivec) blr #endif /* CONFIG_ALTIVEC */ - .align 7 - .globl vsx_unavailable_common -vsx_unavailable_common: - EXCEPTION_PROLOG_COMMON(0xf40, PACA_EXGEN) -#ifdef CONFIG_VSX -BEGIN_FTR_SECTION - bne .load_up_vsx -1: -END_FTR_SECTION_IFSET(CPU_FTR_VSX) -#endif - bl .save_nvgprs - addi r3,r1,STACK_FRAME_OVERHEAD - ENABLE_INTS - bl .vsx_unavailable_exception - b .ret_from_except - #ifdef CONFIG_VSX /* * load_up_vsx(unused, unused, tsk) @@ -1175,11 +1237,14 @@ _GLOBAL(generic_secondary_smp_init) /* turn on 64-bit mode */ bl .enable_64b_mode + /* get the TOC pointer (real address) */ + bl .relative_toc + /* Set up a paca value for this processor. Since we have the * physical cpu id in r24, we need to search the pacas to find * which logical id maps to our physical one. */ - LOAD_REG_IMMEDIATE(r13, paca) /* Get base vaddr of paca array */ + LOAD_REG_ADDR(r13, paca) /* Get base vaddr of paca array */ li r5,0 /* logical cpu id */ 1: lhz r6,PACAHWCPUID(r13) /* Load HW procid from paca */ cmpw r6,r24 /* Compare to our id */ @@ -1208,7 +1273,7 @@ _GLOBAL(generic_secondary_smp_init) sync /* order paca.run and cur_cpu_spec */ /* See if we need to call a cpu state restore handler */ - LOAD_REG_IMMEDIATE(r23, cur_cpu_spec) + LOAD_REG_ADDR(r23, cur_cpu_spec) ld r23,0(r23) ld r23,CPU_SPEC_RESTORE(r23) cmpdi 0,r23,0 @@ -1224,10 +1289,15 @@ _GLOBAL(generic_secondary_smp_init) b __secondary_start #endif +/* + * Turn the MMU off. + * Assumes we're mapped EA == RA if the MMU is on. + */ _STATIC(__mmu_off) mfmsr r3 andi. r0,r3,MSR_IR|MSR_DR beqlr + mflr r4 andc r3,r3,r0 mtspr SPRN_SRR0,r4 mtspr SPRN_SRR1,r3 @@ -1248,6 +1318,18 @@ _STATIC(__mmu_off) * */ _GLOBAL(__start_initialization_multiplatform) + /* Make sure we are running in 64 bits mode */ + bl .enable_64b_mode + + /* Get TOC pointer (current runtime address) */ + bl .relative_toc + + /* find out where we are now */ + bcl 20,31,$+4 +0: mflr r26 /* r26 = runtime addr here */ + addis r26,r26,(_stext - 0b)@ha + addi r26,r26,(_stext - 0b)@l /* current runtime base addr */ + /* * Are we booted from a PROM Of-type client-interface ? */ @@ -1259,9 +1341,6 @@ _GLOBAL(__start_initialization_multiplatform) mr r31,r3 mr r30,r4 - /* Make sure we are running in 64 bits mode */ - bl .enable_64b_mode - /* Setup some critical 970 SPRs before switching MMU off */ mfspr r0,SPRN_PVR srwi r0,r0,16 @@ -1276,9 +1355,7 @@ _GLOBAL(__start_initialization_multiplatform) 1: bl .__cpu_preinit_ppc970 2: - /* Switch off MMU if not already */ - LOAD_REG_IMMEDIATE(r4, .__after_prom_start - KERNELBASE) - add r4,r4,r30 + /* Switch off MMU if not already off */ bl .__mmu_off b .__after_prom_start @@ -1293,22 +1370,15 @@ _INIT_STATIC(__boot_from_prom) /* * Align the stack to 16-byte boundary * Depending on the size and layout of the ELF sections in the initial - * boot binary, the stack pointer will be unalignet on PowerMac + * boot binary, the stack pointer may be unaligned on PowerMac */ rldicr r1,r1,0,59 - /* Make sure we are running in 64 bits mode */ - bl .enable_64b_mode - - /* put a relocation offset into r3 */ - bl .reloc_offset - - LOAD_REG_IMMEDIATE(r2,__toc_start) - addi r2,r2,0x4000 - addi r2,r2,0x4000 - - /* Relocate the TOC from a virt addr to a real addr */ - add r2,r2,r3 +#ifdef CONFIG_RELOCATABLE + /* Relocate code for where we are now */ + mr r3,r26 + bl .relocate +#endif /* Restore parameters */ mr r3,r31 @@ -1318,60 +1388,72 @@ _INIT_STATIC(__boot_from_prom) mr r7,r27 /* Do all of the interaction with OF client interface */ + mr r8,r26 bl .prom_init /* We never return */ trap _STATIC(__after_prom_start) +#ifdef CONFIG_RELOCATABLE + /* process relocations for the final address of the kernel */ + lis r25,PAGE_OFFSET@highest /* compute virtual base of kernel */ + sldi r25,r25,32 +#ifdef CONFIG_CRASH_DUMP + lwz r7,__run_at_load-_stext(r26) + cmplwi cr0,r7,1 /* kdump kernel ? - stay where we are */ + bne 1f + add r25,r25,r26 +#endif +1: mr r3,r25 + bl .relocate +#endif /* - * We need to run with __start at physical address PHYSICAL_START. + * We need to run with _stext at physical address PHYSICAL_START. * This will leave some code in the first 256B of * real memory, which are reserved for software use. - * The remainder of the first page is loaded with the fixed - * interrupt vectors. The next two pages are filled with - * unknown exception placeholders. * * Note: This process overwrites the OF exception vectors. - * r26 == relocation offset - * r27 == KERNELBASE */ - bl .reloc_offset - mr r26,r3 - LOAD_REG_IMMEDIATE(r27, KERNELBASE) - - LOAD_REG_IMMEDIATE(r3, PHYSICAL_START) /* target addr */ - - // XXX FIXME: Use phys returned by OF (r30) - add r4,r27,r26 /* source addr */ - /* current address of _start */ - /* i.e. where we are running */ - /* the source addr */ - - cmpdi r4,0 /* In some cases the loader may */ - bne 1f - b .start_here_multiplatform /* have already put us at zero */ - /* so we can skip the copy. */ -1: LOAD_REG_IMMEDIATE(r5,copy_to_here) /* # bytes of memory to copy */ - sub r5,r5,r27 - + li r3,0 /* target addr */ + mr. r4,r26 /* In some cases the loader may */ + beq 9f /* have already put us at zero */ li r6,0x100 /* Start offset, the first 0x100 */ /* bytes were copied earlier. */ +#ifdef CONFIG_CRASH_DUMP +/* + * Check if the kernel has to be running as relocatable kernel based on the + * variable __run_at_load, if it is set the kernel is treated as relocatable + * kernel, otherwise it will be moved to PHYSICAL_START + */ + lwz r7,__run_at_load-_stext(r26) + cmplwi cr0,r7,1 + bne 3f + + li r5,__end_interrupts - _stext /* just copy interrupts */ + b 5f +3: +#endif + lis r5,(copy_to_here - _stext)@ha + addi r5,r5,(copy_to_here - _stext)@l /* # bytes of memory to copy */ + bl .copy_and_flush /* copy the first n bytes */ /* this includes the code being */ /* executed here. */ - - LOAD_REG_IMMEDIATE(r0, 4f) /* Jump to the copy of this code */ - mtctr r0 /* that we just made/relocated */ + addis r8,r3,(4f - _stext)@ha /* Jump to the copy of this code */ + addi r8,r8,(4f - _stext)@l /* that we just made */ + mtctr r8 bctr -4: LOAD_REG_IMMEDIATE(r5,klimit) - add r5,r5,r26 - ld r5,0(r5) /* get the value of klimit */ - sub r5,r5,r27 - bl .copy_and_flush /* copy the rest */ - b .start_here_multiplatform +p_end: .llong _end - _stext + +4: /* Now copy the rest of the kernel up to _end */ + addis r5,r26,(p_end - _stext)@ha + ld r5,(p_end - _stext)@l(r5) /* get _end */ +5: bl .copy_and_flush /* copy the rest */ + +9: b .start_here_multiplatform /* * Copy routine used to copy the kernel to start at physical address 0 @@ -1436,6 +1518,9 @@ _GLOBAL(pmac_secondary_start) /* turn on 64-bit mode */ bl .enable_64b_mode + /* get TOC pointer (real address) */ + bl .relative_toc + /* Copy some CPU settings from CPU 0 */ bl .__restore_cpu_ppc970 @@ -1445,10 +1530,10 @@ _GLOBAL(pmac_secondary_start) mtmsrd r3 /* RI on */ /* Set up a paca value for this processor. */ - LOAD_REG_IMMEDIATE(r4, paca) /* Get base vaddr of paca array */ - mulli r13,r24,PACA_SIZE /* Calculate vaddr of right paca */ + LOAD_REG_ADDR(r4,paca) /* 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_SPRG3,r13 /* Save vaddr of paca in SPRG3 */ + mtspr SPRN_SPRG3,r13 /* Save vaddr of paca in SPRG3 */ /* Create a temp kernel stack for use before relocation is on. */ ld r1,PACAEMERGSP(r13) @@ -1476,9 +1561,6 @@ __secondary_start: /* Set thread priority to MEDIUM */ HMT_MEDIUM - /* Load TOC */ - ld r2,PACATOC(r13) - /* Do early setup for that CPU (stab, slb, hash table pointer) */ bl .early_setup_secondary @@ -1515,9 +1597,11 @@ END_FW_FTR_SECTION_IFCLR(FW_FEATURE_ISERIES) /* * Running with relocation on at this point. All we want to do is - * zero the stack back-chain pointer before going into C code. + * zero the stack back-chain pointer and get the TOC virtual address + * before going into C code. */ _GLOBAL(start_secondary_prolog) + ld r2,PACATOC(r13) li r3,0 std r3,0(r1) /* Zero the stack frame pointer */ bl .start_secondary @@ -1529,34 +1613,46 @@ _GLOBAL(start_secondary_prolog) */ _GLOBAL(enable_64b_mode) mfmsr r11 /* grab the current MSR */ - li r12,1 - rldicr r12,r12,MSR_SF_LG,(63-MSR_SF_LG) - or r11,r11,r12 - li r12,1 - rldicr r12,r12,MSR_ISF_LG,(63-MSR_ISF_LG) + li r12,(MSR_SF | MSR_ISF)@highest + sldi r12,r12,48 or r11,r11,r12 mtmsrd r11 isync blr /* + * This puts the TOC pointer into r2, offset by 0x8000 (as expected + * by the toolchain). It computes the correct value for wherever we + * are running at the moment, using position-independent code. + */ +_GLOBAL(relative_toc) + mflr r0 + bcl 20,31,$+4 +0: mflr r9 + ld r2,(p_toc - 0b)(r9) + add r2,r2,r9 + mtlr r0 + blr + +p_toc: .llong __toc_start + 0x8000 - 0b + +/* * This is where the main kernel code starts. */ _INIT_STATIC(start_here_multiplatform) - /* get a new offset, now that the kernel has moved. */ - bl .reloc_offset - mr r26,r3 + /* set up the TOC (real address) */ + bl .relative_toc /* Clear out the BSS. It may have been done in prom_init, * already but that's irrelevant since prom_init will soon * be detached from the kernel completely. Besides, we need * to clear it now for kexec-style entry. */ - LOAD_REG_IMMEDIATE(r11,__bss_stop) - LOAD_REG_IMMEDIATE(r8,__bss_start) + LOAD_REG_ADDR(r11,__bss_stop) + LOAD_REG_ADDR(r8,__bss_start) sub r11,r11,r8 /* bss size */ addi r11,r11,7 /* round up to an even double word */ - rldicl. r11,r11,61,3 /* shift right by 3 */ + srdi. r11,r11,3 /* shift right by 3 */ beq 4f addi r8,r8,-8 li r0,0 @@ -1569,35 +1665,35 @@ _INIT_STATIC(start_here_multiplatform) ori r6,r6,MSR_RI mtmsrd r6 /* RI on */ - /* The following gets the stack and TOC set up with the regs */ +#ifdef CONFIG_RELOCATABLE + /* Save the physical address we're running at in kernstart_addr */ + LOAD_REG_ADDR(r4, kernstart_addr) + clrldi r0,r25,2 + std r0,0(r4) +#endif + + /* The following gets the stack set up with the regs */ /* pointing to the real addr of the kernel stack. This is */ /* all done to support the C function call below which sets */ /* up the htab. This is done because we have relocated the */ /* kernel but are still running in real mode. */ - LOAD_REG_IMMEDIATE(r3,init_thread_union) - add r3,r3,r26 + LOAD_REG_ADDR(r3,init_thread_union) - /* set up a stack pointer (physical address) */ + /* set up a stack pointer */ addi r1,r3,THREAD_SIZE li r0,0 stdu r0,-STACK_FRAME_OVERHEAD(r1) - /* set up the TOC (physical address) */ - LOAD_REG_IMMEDIATE(r2,__toc_start) - addi r2,r2,0x4000 - addi r2,r2,0x4000 - add r2,r2,r26 - /* Do very early kernel initializations, including initial hash table, * stab and slb setup before we turn on relocation. */ /* Restore parameters passed from prom_init/kexec */ mr r3,r31 - bl .early_setup + bl .early_setup /* also sets r13 and SPRG3 */ - LOAD_REG_IMMEDIATE(r3, .start_here_common) - LOAD_REG_IMMEDIATE(r4, MSR_KERNEL) + LOAD_REG_ADDR(r3, .start_here_common) + ld r4,PACAKMSR(r13) mtspr SPRN_SRR0,r3 mtspr SPRN_SRR1,r4 rfid @@ -1606,20 +1702,10 @@ _INIT_STATIC(start_here_multiplatform) /* This is where all platforms converge execution */ _INIT_GLOBAL(start_here_common) /* relocation is on at this point */ + std r1,PACAKSAVE(r13) - /* The following code sets up the SP and TOC now that we are */ - /* running with translation enabled. */ - - LOAD_REG_IMMEDIATE(r3,init_thread_union) - - /* set up the stack */ - addi r1,r3,THREAD_SIZE - li r0,0 - stdu r0,-STACK_FRAME_OVERHEAD(r1) - - /* Load the TOC */ + /* Load the TOC (virtual address) */ ld r2,PACATOC(r13) - std r1,PACAKSAVE(r13) bl .setup_system diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S index 3cb52fa0eda..11b549acc03 100644 --- a/arch/powerpc/kernel/head_fsl_booke.S +++ b/arch/powerpc/kernel/head_fsl_booke.S @@ -92,6 +92,7 @@ _ENTRY(_start); * if needed */ +_ENTRY(__early_start) /* 1. Find the index of the entry we're executing in */ bl invstr /* Find our address */ invstr: mflr r6 /* Make it accessible */ @@ -235,36 +236,40 @@ skpinv: addi r6,r6,1 /* Increment */ tlbivax 0,r9 TLBSYNC +/* The mapping only needs to be cache-coherent on SMP */ +#ifdef CONFIG_SMP +#define M_IF_SMP MAS2_M +#else +#define M_IF_SMP 0 +#endif + /* 6. Setup KERNELBASE mapping in TLB1[0] */ lis r6,0x1000 /* Set MAS0(TLBSEL) = TLB1(1), ESEL = 0 */ mtspr SPRN_MAS0,r6 lis r6,(MAS1_VALID|MAS1_IPROT)@h ori r6,r6,(MAS1_TSIZE(BOOKE_PAGESZ_64M))@l mtspr SPRN_MAS1,r6 - li r7,0 - lis r6,PAGE_OFFSET@h - ori r6,r6,PAGE_OFFSET@l - rlwimi r6,r7,0,20,31 + lis r6,MAS2_VAL(PAGE_OFFSET, BOOKE_PAGESZ_64M, M_IF_SMP)@h + ori r6,r6,MAS2_VAL(PAGE_OFFSET, BOOKE_PAGESZ_64M, M_IF_SMP)@l mtspr SPRN_MAS2,r6 mtspr SPRN_MAS3,r8 tlbwe /* 7. Jump to KERNELBASE mapping */ - lis r6,KERNELBASE@h - ori r6,r6,KERNELBASE@l - rlwimi r6,r7,0,20,31 + lis r6,(KERNELBASE & ~0xfff)@h + ori r6,r6,(KERNELBASE & ~0xfff)@l lis r7,MSR_KERNEL@h ori r7,r7,MSR_KERNEL@l bl 1f /* Find our address */ 1: mflr r9 rlwimi r6,r9,0,20,31 - addi r6,r6,24 + addi r6,r6,(2f - 1b) mtspr SPRN_SRR0,r6 mtspr SPRN_SRR1,r7 rfi /* start execution out of TLB1[0] entry */ /* 8. Clear out the temp mapping */ - lis r7,0x1000 /* Set MAS0(TLBSEL) = 1 */ +2: lis r7,0x1000 /* Set MAS0(TLBSEL) = 1 */ rlwimi r7,r5,16,4,15 /* Setup MAS0 = TLBSEL | ESEL(r5) */ mtspr SPRN_MAS0,r7 tlbre @@ -344,6 +349,15 @@ skpinv: addi r6,r6,1 /* Increment */ mtspr SPRN_DBSR,r2 #endif +#ifdef CONFIG_SMP + /* Check to see if we're the second processor, and jump + * to the secondary_start code if so + */ + mfspr r24,SPRN_PIR + cmpwi r24,0 + bne __secondary_start +#endif + /* * This is where the main kernel code starts. */ @@ -422,7 +436,6 @@ skpinv: addi r6,r6,1 /* Increment */ * r12 is pointer to the pte */ #ifdef CONFIG_PTE_64BIT -#define PTE_FLAGS_OFFSET 4 #define FIND_PTE \ rlwinm r12, r10, 13, 19, 29; /* Compute pgdir/pmd offset */ \ lwzx r11, r12, r11; /* Get pgd/pmd entry */ \ @@ -431,7 +444,6 @@ skpinv: addi r6,r6,1 /* Increment */ rlwimi r12, r10, 23, 20, 28; /* Compute pte address */ \ lwz r11, 4(r12); /* Get pte entry */ #else -#define PTE_FLAGS_OFFSET 0 #define FIND_PTE \ rlwimi r11, r10, 12, 20, 29; /* Create L1 (pgdir/pmd) address */ \ lwz r11, 0(r11); /* Get L1 entry */ \ @@ -579,13 +591,19 @@ interrupt_base: FIND_PTE andc. r13,r13,r11 /* Check permission */ - bne 2f /* Bail if permission mismach */ #ifdef CONFIG_PTE_64BIT - lwz r13, 0(r12) +#ifdef CONFIG_SMP + subf r10,r11,r12 /* create false data dep */ + lwzx r13,r11,r10 /* Get upper pte bits */ +#else + lwz r13,0(r12) /* Get upper pte bits */ +#endif #endif - /* Jump to common tlb load */ + bne 2f /* Bail if permission/valid mismach */ + + /* Jump to common tlb load */ b finish_tlb_load 2: /* The bailout. Restore registers to pre-exception conditions @@ -640,12 +658,18 @@ interrupt_base: FIND_PTE andc. r13,r13,r11 /* Check permission */ - bne 2f /* Bail if permission mismach */ #ifdef CONFIG_PTE_64BIT - lwz r13, 0(r12) +#ifdef CONFIG_SMP + subf r10,r11,r12 /* create false data dep */ + lwzx r13,r11,r10 /* Get upper pte bits */ +#else + lwz r13,0(r12) /* Get upper pte bits */ +#endif #endif + bne 2f /* Bail if permission mismach */ + /* Jump to common TLB load point */ b finish_tlb_load @@ -675,12 +699,13 @@ interrupt_base: /* SPE Floating Point Data */ #ifdef CONFIG_SPE EXCEPTION(0x2030, SPEFloatingPointData, SPEFloatingPointException, EXC_XFER_EE); -#else - EXCEPTION(0x2040, SPEFloatingPointData, unknown_exception, EXC_XFER_EE) -#endif /* CONFIG_SPE */ /* SPE Floating Point Round */ + EXCEPTION(0x2050, SPEFloatingPointRound, SPEFloatingPointRoundException, EXC_XFER_EE) +#else + EXCEPTION(0x2040, SPEFloatingPointData, unknown_exception, EXC_XFER_EE) EXCEPTION(0x2050, SPEFloatingPointRound, unknown_exception, EXC_XFER_EE) +#endif /* CONFIG_SPE */ /* Performance Monitor */ EXCEPTION(0x2060, PerformanceMonitor, performance_monitor_exception, EXC_XFER_STD) @@ -702,7 +727,7 @@ interrupt_base: /* * Both the instruction and data TLB miss get to this * point to load the TLB. - * r10 - EA of fault + * r10 - available to use * r11 - TLB (info from Linux PTE) * r12 - available to use * r13 - upper bits of PTE (if PTE_64BIT) or available to use @@ -725,6 +750,9 @@ finish_tlb_load: #else rlwimi r12, r11, 26, 27, 31 /* extract WIMGE from pte */ #endif +#ifdef CONFIG_SMP + ori r12, r12, MAS2_M +#endif mtspr SPRN_MAS2, r12 li r10, (_PAGE_HWEXEC | _PAGE_PRESENT) @@ -736,15 +764,15 @@ finish_tlb_load: iseleq r12, r12, r10 #ifdef CONFIG_PTE_64BIT -2: rlwimi r12, r13, 24, 0, 7 /* grab RPN[32:39] */ + rlwimi r12, r13, 24, 0, 7 /* grab RPN[32:39] */ rlwimi r12, r11, 24, 8, 19 /* grab RPN[40:51] */ mtspr SPRN_MAS3, r12 -BEGIN_FTR_SECTION +BEGIN_MMU_FTR_SECTION srwi r10, r13, 8 /* grab RPN[8:31] */ mtspr SPRN_MAS7, r10 -END_FTR_SECTION_IFSET(CPU_FTR_BIG_PHYS) +END_MMU_FTR_SECTION_IFSET(MMU_FTR_BIG_PHYS) #else -2: rlwimi r11, r12, 0, 20, 31 /* Extract RPN from PTE and merge with perms */ + rlwimi r11, r12, 0, 20, 31 /* Extract RPN from PTE and merge with perms */ mtspr SPRN_MAS3, r11 #endif #ifdef CONFIG_E200 @@ -1027,6 +1055,63 @@ _GLOBAL(flush_dcache_L1) blr +#ifdef CONFIG_SMP +/* When we get here, r24 needs to hold the CPU # */ + .globl __secondary_start +__secondary_start: + lis r3,__secondary_hold_acknowledge@h + ori r3,r3,__secondary_hold_acknowledge@l + stw r24,0(r3) + + li r3,0 + mr r4,r24 /* Why? */ + bl call_setup_cpu + + lis r3,tlbcam_index@ha + lwz r3,tlbcam_index@l(r3) + mtctr r3 + li r26,0 /* r26 safe? */ + + /* Load each CAM entry */ +1: mr r3,r26 + bl loadcam_entry + addi r26,r26,1 + bdnz 1b + + /* get current_thread_info and current */ + lis r1,secondary_ti@ha + lwz r1,secondary_ti@l(r1) + lwz r2,TI_TASK(r1) + + /* stack */ + addi r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD + li r0,0 + stw r0,0(r1) + + /* ptr to current thread */ + addi r4,r2,THREAD /* address of our thread_struct */ + mtspr SPRN_SPRG3,r4 + + /* Setup the defaults for TLB entries */ + li r4,(MAS4_TSIZED(BOOKE_PAGESZ_4K))@l + mtspr SPRN_MAS4,r4 + + /* Jump to start_secondary */ + lis r4,MSR_KERNEL@h + ori r4,r4,MSR_KERNEL@l + lis r3,start_secondary@h + ori r3,r3,start_secondary@l + mtspr SPRN_SRR0,r3 + mtspr SPRN_SRR1,r4 + sync + rfi + sync + + .globl __secondary_hold_acknowledge +__secondary_hold_acknowledge: + .long -1 +#endif + /* * We put a few things here that have to be page-aligned. This stuff * goes at the beginning of the data segment, which is page-aligned. diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c index a06362223f8..6e3f6249365 100644 --- a/arch/powerpc/kernel/ibmebus.c +++ b/arch/powerpc/kernel/ibmebus.c @@ -47,7 +47,7 @@ #include <asm/abs_addr.h> static struct device ibmebus_bus_device = { /* fake "parent" device */ - .bus_id = "ibmebus", + .init_name = "ibmebus", }; struct bus_type ibmebus_bus_type; @@ -79,20 +79,21 @@ static void ibmebus_free_coherent(struct device *dev, kfree(vaddr); } -static dma_addr_t ibmebus_map_single(struct device *dev, - void *ptr, - size_t size, - enum dma_data_direction direction, - struct dma_attrs *attrs) +static dma_addr_t ibmebus_map_page(struct device *dev, + struct page *page, + unsigned long offset, + size_t size, + enum dma_data_direction direction, + struct dma_attrs *attrs) { - return (dma_addr_t)(ptr); + return (dma_addr_t)(page_address(page) + offset); } -static void ibmebus_unmap_single(struct device *dev, - dma_addr_t dma_addr, - size_t size, - enum dma_data_direction direction, - struct dma_attrs *attrs) +static void ibmebus_unmap_page(struct device *dev, + dma_addr_t dma_addr, + size_t size, + enum dma_data_direction direction, + struct dma_attrs *attrs) { return; } @@ -129,11 +130,11 @@ static int ibmebus_dma_supported(struct device *dev, u64 mask) static struct dma_mapping_ops ibmebus_dma_ops = { .alloc_coherent = ibmebus_alloc_coherent, .free_coherent = ibmebus_free_coherent, - .map_single = ibmebus_map_single, - .unmap_single = ibmebus_unmap_single, .map_sg = ibmebus_map_sg, .unmap_sg = ibmebus_unmap_sg, .dma_supported = ibmebus_dma_supported, + .map_page = ibmebus_map_page, + .unmap_page = ibmebus_unmap_page, }; static int ibmebus_match_path(struct device *dev, void *data) @@ -230,6 +231,7 @@ void ibmebus_free_irq(u32 ist, void *dev_id) unsigned int irq = irq_find_mapping(NULL, ist); free_irq(irq, dev_id); + irq_dispose_mapping(irq); } EXPORT_SYMBOL(ibmebus_free_irq); diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c index 31982d05d81..88d9c1d5e5f 100644 --- a/arch/powerpc/kernel/idle.c +++ b/arch/powerpc/kernel/idle.c @@ -69,10 +69,15 @@ void cpu_idle(void) smp_mb(); local_irq_disable(); + /* Don't trace irqs off for idle */ + stop_critical_timings(); + /* check again after disabling irqs */ if (!need_resched() && !cpu_should_die()) ppc_md.power_save(); + start_critical_timings(); + local_irq_enable(); set_thread_flag(TIF_POLLING_NRFLAG); diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 550a19399bf..1bfa706b96e 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -32,6 +32,7 @@ #include <linux/dma-mapping.h> #include <linux/bitops.h> #include <linux/iommu-helper.h> +#include <linux/crash_dump.h> #include <asm/io.h> #include <asm/prom.h> #include <asm/iommu.h> @@ -51,17 +52,6 @@ static int protect4gb = 1; static void __iommu_free(struct iommu_table *, dma_addr_t, unsigned int); -static inline unsigned long iommu_num_pages(unsigned long vaddr, - unsigned long slen) -{ - unsigned long npages; - - npages = IOMMU_PAGE_ALIGN(vaddr + slen) - (vaddr & IOMMU_PAGE_MASK); - npages >>= IOMMU_PAGE_SHIFT; - - return npages; -} - static int __init setup_protect4gb(char *str) { if (strcmp(str, "on") == 0) @@ -325,7 +315,7 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl, } /* Allocate iommu entries for that segment */ vaddr = (unsigned long) sg_virt(s); - npages = iommu_num_pages(vaddr, slen); + npages = iommu_num_pages(vaddr, slen, IOMMU_PAGE_SIZE); align = 0; if (IOMMU_PAGE_SHIFT < PAGE_SHIFT && slen >= PAGE_SIZE && (vaddr & ~PAGE_MASK) == 0) @@ -418,7 +408,8 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl, unsigned long vaddr, npages; vaddr = s->dma_address & IOMMU_PAGE_MASK; - npages = iommu_num_pages(s->dma_address, s->dma_length); + npages = iommu_num_pages(s->dma_address, s->dma_length, + IOMMU_PAGE_SIZE); __iommu_free(tbl, vaddr, npages); s->dma_address = DMA_ERROR_CODE; s->dma_length = 0; @@ -452,7 +443,8 @@ void iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist, if (sg->dma_length == 0) break; - npages = iommu_num_pages(dma_handle, sg->dma_length); + npages = iommu_num_pages(dma_handle, sg->dma_length, + IOMMU_PAGE_SIZE); __iommu_free(tbl, dma_handle, npages); sg = sg_next(sg); } @@ -467,6 +459,42 @@ void iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist, spin_unlock_irqrestore(&(tbl->it_lock), flags); } +static void iommu_table_clear(struct iommu_table *tbl) +{ + if (!is_kdump_kernel()) { + /* Clear the table in case firmware left allocations in it */ + ppc_md.tce_free(tbl, tbl->it_offset, tbl->it_size); + return; + } + +#ifdef CONFIG_CRASH_DUMP + if (ppc_md.tce_get) { + unsigned long index, tceval, tcecount = 0; + + /* Reserve the existing mappings left by the first kernel. */ + for (index = 0; index < tbl->it_size; index++) { + tceval = ppc_md.tce_get(tbl, index + tbl->it_offset); + /* + * Freed TCE entry contains 0x7fffffffffffffff on JS20 + */ + if (tceval && (tceval != 0x7fffffffffffffffUL)) { + __set_bit(index, tbl->it_map); + tcecount++; + } + } + + if ((tbl->it_size - tcecount) < KDUMP_MIN_TCE_ENTRIES) { + printk(KERN_WARNING "TCE table is full; freeing "); + printk(KERN_WARNING "%d entries for the kdump boot\n", + KDUMP_MIN_TCE_ENTRIES); + for (index = tbl->it_size - KDUMP_MIN_TCE_ENTRIES; + index < tbl->it_size; index++) + __clear_bit(index, tbl->it_map); + } + } +#endif +} + /* * Build a iommu_table structure. This contains a bit map which * is used to manage allocation of the tce space. @@ -493,38 +521,7 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid) tbl->it_largehint = tbl->it_halfpoint; spin_lock_init(&tbl->it_lock); -#ifdef CONFIG_CRASH_DUMP - if (ppc_md.tce_get) { - unsigned long index; - unsigned long tceval; - unsigned long tcecount = 0; - - /* - * Reserve the existing mappings left by the first kernel. - */ - for (index = 0; index < tbl->it_size; index++) { - tceval = ppc_md.tce_get(tbl, index + tbl->it_offset); - /* - * Freed TCE entry contains 0x7fffffffffffffff on JS20 - */ - if (tceval && (tceval != 0x7fffffffffffffffUL)) { - __set_bit(index, tbl->it_map); - tcecount++; - } - } - if ((tbl->it_size - tcecount) < KDUMP_MIN_TCE_ENTRIES) { - printk(KERN_WARNING "TCE table is full; "); - printk(KERN_WARNING "freeing %d entries for the kdump boot\n", - KDUMP_MIN_TCE_ENTRIES); - for (index = tbl->it_size - KDUMP_MIN_TCE_ENTRIES; - index < tbl->it_size; index++) - __clear_bit(index, tbl->it_map); - } - } -#else - /* Clear the hardware table in case firmware left allocations in it */ - ppc_md.tce_free(tbl, tbl->it_offset, tbl->it_size); -#endif + iommu_table_clear(tbl); if (!welcomed) { printk(KERN_INFO "IOMMU table initialized, virtual merging %s\n", @@ -568,23 +565,25 @@ void iommu_free_table(struct iommu_table *tbl, const char *node_name) } /* Creates TCEs for a user provided buffer. The user buffer must be - * contiguous real kernel storage (not vmalloc). The address of the buffer - * passed here is the kernel (virtual) address of the buffer. The buffer - * need not be page aligned, the dma_addr_t returned will point to the same - * byte within the page as vaddr. + * contiguous real kernel storage (not vmalloc). The address passed here + * comprises a page address and offset into that page. The dma_addr_t + * returned will point to the same byte within the page as was passed in. */ -dma_addr_t iommu_map_single(struct device *dev, struct iommu_table *tbl, - void *vaddr, size_t size, unsigned long mask, - enum dma_data_direction direction, struct dma_attrs *attrs) +dma_addr_t iommu_map_page(struct device *dev, struct iommu_table *tbl, + struct page *page, unsigned long offset, size_t size, + unsigned long mask, enum dma_data_direction direction, + struct dma_attrs *attrs) { dma_addr_t dma_handle = DMA_ERROR_CODE; + void *vaddr; unsigned long uaddr; unsigned int npages, align; BUG_ON(direction == DMA_NONE); + vaddr = page_address(page) + offset; uaddr = (unsigned long)vaddr; - npages = iommu_num_pages(uaddr, size); + npages = iommu_num_pages(uaddr, size, IOMMU_PAGE_SIZE); if (tbl) { align = 0; @@ -608,16 +607,16 @@ dma_addr_t iommu_map_single(struct device *dev, struct iommu_table *tbl, return dma_handle; } -void iommu_unmap_single(struct iommu_table *tbl, dma_addr_t dma_handle, - size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs) +void iommu_unmap_page(struct iommu_table *tbl, dma_addr_t dma_handle, + size_t size, enum dma_data_direction direction, + struct dma_attrs *attrs) { unsigned int npages; BUG_ON(direction == DMA_NONE); if (tbl) { - npages = iommu_num_pages(dma_handle, size); + npages = iommu_num_pages(dma_handle, size, IOMMU_PAGE_SIZE); iommu_free(tbl, dma_handle, npages); } } diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index d972decf032..ac222d0ab12 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -439,8 +439,8 @@ void do_softirq(void) static LIST_HEAD(irq_hosts); static DEFINE_SPINLOCK(irq_big_lock); -static DEFINE_PER_CPU(unsigned int, irq_radix_reader); -static unsigned int irq_radix_writer; +static unsigned int revmap_trees_allocated; +static DEFINE_MUTEX(revmap_trees_mutex); struct irq_map_entry irq_map[NR_IRQS]; static unsigned int irq_virq_count = NR_IRQS; static struct irq_host *irq_default_host; @@ -583,57 +583,6 @@ void irq_set_virq_count(unsigned int count) irq_virq_count = count; } -/* radix tree not lockless safe ! we use a brlock-type mecanism - * for now, until we can use a lockless radix tree - */ -static void irq_radix_wrlock(unsigned long *flags) -{ - unsigned int cpu, ok; - - spin_lock_irqsave(&irq_big_lock, *flags); - irq_radix_writer = 1; - smp_mb(); - do { - barrier(); - ok = 1; - for_each_possible_cpu(cpu) { - if (per_cpu(irq_radix_reader, cpu)) { - ok = 0; - break; - } - } - if (!ok) - cpu_relax(); - } while(!ok); -} - -static void irq_radix_wrunlock(unsigned long flags) -{ - smp_wmb(); - irq_radix_writer = 0; - spin_unlock_irqrestore(&irq_big_lock, flags); -} - -static void irq_radix_rdlock(unsigned long *flags) -{ - local_irq_save(*flags); - __get_cpu_var(irq_radix_reader) = 1; - smp_mb(); - if (likely(irq_radix_writer == 0)) - return; - __get_cpu_var(irq_radix_reader) = 0; - smp_wmb(); - spin_lock(&irq_big_lock); - __get_cpu_var(irq_radix_reader) = 1; - spin_unlock(&irq_big_lock); -} - -static void irq_radix_rdunlock(unsigned long flags) -{ - __get_cpu_var(irq_radix_reader) = 0; - local_irq_restore(flags); -} - static int irq_setup_virq(struct irq_host *host, unsigned int virq, irq_hw_number_t hwirq) { @@ -788,7 +737,6 @@ void irq_dispose_mapping(unsigned int virq) { struct irq_host *host; irq_hw_number_t hwirq; - unsigned long flags; if (virq == NO_IRQ) return; @@ -821,12 +769,16 @@ 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 (host->revmap_data.tree.gfp_mask == 0) + /* + * Check if radix tree allocated yet, if not then nothing to + * remove. + */ + smp_rmb(); + if (revmap_trees_allocated < 1) break; - irq_radix_wrlock(&flags); + mutex_lock(&revmap_trees_mutex); radix_tree_delete(&host->revmap_data.tree, hwirq); - irq_radix_wrunlock(flags); + mutex_unlock(&revmap_trees_mutex); break; } @@ -875,43 +827,62 @@ unsigned int irq_find_mapping(struct irq_host *host, EXPORT_SYMBOL_GPL(irq_find_mapping); -unsigned int irq_radix_revmap(struct irq_host *host, - irq_hw_number_t hwirq) +unsigned int irq_radix_revmap_lookup(struct irq_host *host, + irq_hw_number_t hwirq) { - struct radix_tree_root *tree; struct irq_map_entry *ptr; unsigned int virq; - unsigned long flags; WARN_ON(host->revmap_type != IRQ_HOST_MAP_TREE); - /* Check if the radix tree exist yet. We test the value of - * the gfp_mask for that. Sneaky but saves another int in the - * structure. If not, we fallback to slow mode + /* + * Check if the radix tree exists and has bee initialized. + * If not, we fallback to slow mode */ - tree = &host->revmap_data.tree; - if (tree->gfp_mask == 0) + if (revmap_trees_allocated < 2) return irq_find_mapping(host, hwirq); /* Now try to resolve */ - irq_radix_rdlock(&flags); - ptr = radix_tree_lookup(tree, hwirq); - irq_radix_rdunlock(flags); + /* + * 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. + */ + ptr = radix_tree_lookup(&host->revmap_data.tree, hwirq); - /* Found it, return */ - if (ptr) { + /* + * If found in radix tree, then fine. + * Else fallback to linear lookup - this should not happen in practice + * as it means that we failed to insert the node in the radix tree. + */ + if (ptr) virq = ptr - irq_map; - return virq; - } + else + virq = irq_find_mapping(host, hwirq); + + return virq; +} + +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) + return; - /* If not there, try to insert it */ - virq = irq_find_mapping(host, hwirq); if (virq != NO_IRQ) { - irq_radix_wrlock(&flags); - radix_tree_insert(tree, hwirq, &irq_map[virq]); - irq_radix_wrunlock(flags); + mutex_lock(&revmap_trees_mutex); + radix_tree_insert(&host->revmap_data.tree, hwirq, + &irq_map[virq]); + mutex_unlock(&revmap_trees_mutex); } - return virq; } unsigned int irq_linear_revmap(struct irq_host *host, @@ -1020,14 +991,44 @@ void irq_early_init(void) static int irq_late_init(void) { struct irq_host *h; - unsigned long flags; + unsigned int i; - irq_radix_wrlock(&flags); + /* + * 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_ATOMIC); + 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]); } - irq_radix_wrunlock(flags); + 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; } diff --git a/arch/powerpc/kernel/lparcfg.c b/arch/powerpc/kernel/lparcfg.c index b3eef30b513..d051e8cbcd0 100644 --- a/arch/powerpc/kernel/lparcfg.c +++ b/arch/powerpc/kernel/lparcfg.c @@ -510,10 +510,10 @@ static ssize_t update_ppp(u64 *entitlement, u8 *weight) return -EINVAL; pr_debug("%s: current_entitled = %lu, current_weight = %u\n", - __FUNCTION__, ppp_data.entitlement, ppp_data.weight); + __func__, ppp_data.entitlement, ppp_data.weight); pr_debug("%s: new_entitled = %lu, new_weight = %u\n", - __FUNCTION__, new_entitled, new_weight); + __func__, new_entitled, new_weight); retval = plpar_hcall_norets(H_SET_PPP, new_entitled, new_weight); return retval; @@ -556,10 +556,10 @@ static ssize_t update_mpp(u64 *entitlement, u8 *weight) return -EINVAL; pr_debug("%s: current_entitled = %lu, current_weight = %u\n", - __FUNCTION__, mpp_data.entitled_mem, mpp_data.mem_weight); + __func__, mpp_data.entitled_mem, mpp_data.mem_weight); pr_debug("%s: new_entitled = %lu, new_weight = %u\n", - __FUNCTION__, new_entitled, new_weight); + __func__, new_entitled, new_weight); rc = plpar_hcall_norets(H_SET_MPP, new_entitled, new_weight); return rc; diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c index aab76887a84..b3abebb7ee6 100644 --- a/arch/powerpc/kernel/machine_kexec.c +++ b/arch/powerpc/kernel/machine_kexec.c @@ -13,13 +13,17 @@ #include <linux/reboot.h> #include <linux/threads.h> #include <linux/lmb.h> +#include <linux/of.h> #include <asm/machdep.h> #include <asm/prom.h> +#include <asm/sections.h> void machine_crash_shutdown(struct pt_regs *regs) { if (ppc_md.machine_crash_shutdown) ppc_md.machine_crash_shutdown(regs); + else + default_machine_crash_shutdown(regs); } /* @@ -31,11 +35,8 @@ int machine_kexec_prepare(struct kimage *image) { if (ppc_md.machine_kexec_prepare) return ppc_md.machine_kexec_prepare(image); - /* - * Fail if platform doesn't provide its own machine_kexec_prepare - * implementation. - */ - return -ENOSYS; + else + return default_machine_kexec_prepare(image); } void machine_kexec_cleanup(struct kimage *image) @@ -52,13 +53,11 @@ void machine_kexec(struct kimage *image) { if (ppc_md.machine_kexec) ppc_md.machine_kexec(image); - else { - /* - * Fall back to normal restart if platform doesn't provide - * its own kexec function, and user insist to kexec... - */ - machine_restart(NULL); - } + else + default_machine_kexec(image); + + /* Fall back to normal restart if we're still alive. */ + machine_restart(NULL); for(;;); } @@ -88,11 +87,13 @@ void __init reserve_crashkernel(void) crash_size = crashk_res.end - crashk_res.start + 1; +#ifndef CONFIG_RELOCATABLE if (crashk_res.start != KDUMP_KERNELBASE) printk("Crash kernel location must be 0x%x\n", KDUMP_KERNELBASE); crashk_res.start = KDUMP_KERNELBASE; +#endif crash_size = PAGE_ALIGN(crash_size); crashk_res.end = crashk_res.start + crash_size - 1; @@ -116,3 +117,71 @@ int overlaps_crashkernel(unsigned long start, unsigned long size) { return (start + size) > crashk_res.start && start <= crashk_res.end; } + +/* Values we need to export to the second kernel via the device tree. */ +static unsigned long kernel_end; +static unsigned long crashk_size; + +static struct property kernel_end_prop = { + .name = "linux,kernel-end", + .length = sizeof(unsigned long), + .value = &kernel_end, +}; + +static struct property crashk_base_prop = { + .name = "linux,crashkernel-base", + .length = sizeof(unsigned long), + .value = &crashk_res.start, +}; + +static struct property crashk_size_prop = { + .name = "linux,crashkernel-size", + .length = sizeof(unsigned long), + .value = &crashk_size, +}; + +static void __init export_crashk_values(struct device_node *node) +{ + struct property *prop; + + /* There might be existing crash kernel properties, but we can't + * be sure what's in them, so remove them. */ + prop = of_find_property(node, "linux,crashkernel-base", NULL); + if (prop) + prom_remove_property(node, prop); + + prop = of_find_property(node, "linux,crashkernel-size", NULL); + if (prop) + prom_remove_property(node, prop); + + if (crashk_res.start != 0) { + prom_add_property(node, &crashk_base_prop); + crashk_size = crashk_res.end - crashk_res.start + 1; + prom_add_property(node, &crashk_size_prop); + } +} + +static int __init kexec_setup(void) +{ + struct device_node *node; + struct property *prop; + + node = of_find_node_by_path("/chosen"); + if (!node) + return -ENOENT; + + /* remove any stale properties so ours can be found */ + prop = of_find_property(node, kernel_end_prop.name, NULL); + if (prop) + prom_remove_property(node, prop); + + /* information needed by userspace when using default_machine_kexec */ + kernel_end = __pa(_end); + prom_add_property(node, &kernel_end_prop); + + export_crashk_values(node); + + of_node_put(node); + return 0; +} +late_initcall(kexec_setup); diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c index a168514d860..49e705fcee6 100644 --- a/arch/powerpc/kernel/machine_kexec_64.c +++ b/arch/powerpc/kernel/machine_kexec_64.c @@ -270,8 +270,8 @@ void default_machine_kexec(struct kimage *image) * using debugger IPI. */ - if (crashing_cpu == -1) - kexec_prepare_cpus(); + if (crashing_cpu == -1) + kexec_prepare_cpus(); /* switch to a staticly allocated stack. Based on irq stack code. * XXX: the task struct will likely be invalid once we do the copy! @@ -289,7 +289,7 @@ void default_machine_kexec(struct kimage *image) } /* Values we need to export to the second kernel via the device tree. */ -static unsigned long htab_base, kernel_end; +static unsigned long htab_base; static struct property htab_base_prop = { .name = "linux,htab-base", @@ -303,81 +303,32 @@ static struct property htab_size_prop = { .value = &htab_size_bytes, }; -static struct property kernel_end_prop = { - .name = "linux,kernel-end", - .length = sizeof(unsigned long), - .value = &kernel_end, -}; - -static void __init export_htab_values(void) +static int __init export_htab_values(void) { struct device_node *node; - - node = of_find_node_by_path("/chosen"); - if (!node) - return; - - kernel_end = __pa(_end); - prom_add_property(node, &kernel_end_prop); + struct property *prop; /* On machines with no htab htab_address is NULL */ - if (NULL == htab_address) - goto out; - - htab_base = __pa(htab_address); - prom_add_property(node, &htab_base_prop); - prom_add_property(node, &htab_size_prop); - - out: - of_node_put(node); -} - -static struct property crashk_base_prop = { - .name = "linux,crashkernel-base", - .length = sizeof(unsigned long), - .value = &crashk_res.start, -}; - -static unsigned long crashk_size; - -static struct property crashk_size_prop = { - .name = "linux,crashkernel-size", - .length = sizeof(unsigned long), - .value = &crashk_size, -}; - -static void __init export_crashk_values(void) -{ - struct device_node *node; - struct property *prop; + if (!htab_address) + return -ENODEV; node = of_find_node_by_path("/chosen"); if (!node) - return; + return -ENODEV; - /* There might be existing crash kernel properties, but we can't - * be sure what's in them, so remove them. */ - prop = of_find_property(node, "linux,crashkernel-base", NULL); + /* remove any stale propertys so ours can be found */ + prop = of_find_property(node, htab_base_prop.name, NULL); if (prop) prom_remove_property(node, prop); - - prop = of_find_property(node, "linux,crashkernel-size", NULL); + prop = of_find_property(node, htab_size_prop.name, NULL); if (prop) prom_remove_property(node, prop); - if (crashk_res.start != 0) { - prom_add_property(node, &crashk_base_prop); - crashk_size = crashk_res.end - crashk_res.start + 1; - prom_add_property(node, &crashk_size_prop); - } + htab_base = __pa(htab_address); + prom_add_property(node, &htab_base_prop); + prom_add_property(node, &htab_size_prop); of_node_put(node); -} - -static int __init kexec_setup(void) -{ - export_htab_values(); - export_crashk_values(); return 0; } -__initcall(kexec_setup); +late_initcall(export_htab_values); diff --git a/arch/powerpc/kernel/misc.S b/arch/powerpc/kernel/misc.S index 85cb6f34084..2d29752cbe1 100644 --- a/arch/powerpc/kernel/misc.S +++ b/arch/powerpc/kernel/misc.S @@ -31,11 +31,14 @@ _GLOBAL(reloc_offset) mflr r0 bl 1f 1: mflr r3 - LOAD_REG_IMMEDIATE(r4,1b) + PPC_LL r4,(2f-1b)(r3) subf r3,r4,r3 mtlr r0 blr + .align 3 +2: PPC_LONG 1b + /* * add_reloc_offset(x) returns x + reloc_offset(). */ @@ -43,12 +46,15 @@ _GLOBAL(add_reloc_offset) mflr r0 bl 1f 1: mflr r5 - LOAD_REG_IMMEDIATE(r4,1b) + PPC_LL r4,(2f-1b)(r5) subf r5,r4,r5 add r3,r3,r5 mtlr r0 blr + .align 3 +2: PPC_LONG 1b + _GLOBAL(kernel_execve) li r0,__NR_execve sc diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index 7a6dfbca768..15f28e0de78 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -29,6 +29,7 @@ #include <asm/asm-offsets.h> #include <asm/processor.h> #include <asm/kexec.h> +#include <asm/bug.h> .text @@ -271,170 +272,6 @@ _GLOBAL(real_writeb) #endif /* CONFIG_40x */ -/* - * Flush MMU TLB - */ -_GLOBAL(_tlbia) -#if defined(CONFIG_40x) - sync /* Flush to memory before changing mapping */ - tlbia - isync /* Flush shadow TLB */ -#elif defined(CONFIG_44x) - li r3,0 - sync - - /* Load high watermark */ - lis r4,tlb_44x_hwater@ha - lwz r5,tlb_44x_hwater@l(r4) - -1: tlbwe r3,r3,PPC44x_TLB_PAGEID - addi r3,r3,1 - cmpw 0,r3,r5 - ble 1b - - isync -#elif defined(CONFIG_FSL_BOOKE) - /* Invalidate all entries in TLB0 */ - li r3, 0x04 - tlbivax 0,3 - /* Invalidate all entries in TLB1 */ - li r3, 0x0c - tlbivax 0,3 - msync -#ifdef CONFIG_SMP - tlbsync -#endif /* CONFIG_SMP */ -#else /* !(CONFIG_40x || CONFIG_44x || CONFIG_FSL_BOOKE) */ -#if defined(CONFIG_SMP) - rlwinm r8,r1,0,0,(31-THREAD_SHIFT) - lwz r8,TI_CPU(r8) - oris r8,r8,10 - mfmsr r10 - SYNC - rlwinm r0,r10,0,17,15 /* clear bit 16 (MSR_EE) */ - rlwinm r0,r0,0,28,26 /* clear DR */ - mtmsr r0 - SYNC_601 - isync - lis r9,mmu_hash_lock@h - ori r9,r9,mmu_hash_lock@l - tophys(r9,r9) -10: lwarx r7,0,r9 - cmpwi 0,r7,0 - bne- 10b - stwcx. r8,0,r9 - bne- 10b - sync - tlbia - sync - TLBSYNC - li r0,0 - stw r0,0(r9) /* clear mmu_hash_lock */ - mtmsr r10 - SYNC_601 - isync -#else /* CONFIG_SMP */ - sync - tlbia - sync -#endif /* CONFIG_SMP */ -#endif /* ! defined(CONFIG_40x) */ - blr - -/* - * Flush MMU TLB for a particular address - */ -_GLOBAL(_tlbie) -#if defined(CONFIG_40x) - /* We run the search with interrupts disabled because we have to change - * the PID and I don't want to preempt when that happens. - */ - mfmsr r5 - mfspr r6,SPRN_PID - wrteei 0 - mtspr SPRN_PID,r4 - tlbsx. r3, 0, r3 - mtspr SPRN_PID,r6 - wrtee r5 - bne 10f - sync - /* There are only 64 TLB entries, so r3 < 64, which means bit 25 is clear. - * Since 25 is the V bit in the TLB_TAG, loading this value will invalidate - * the TLB entry. */ - tlbwe r3, r3, TLB_TAG - isync -10: - -#elif defined(CONFIG_44x) - mfspr r5,SPRN_MMUCR - rlwimi r5,r4,0,24,31 /* Set TID */ - - /* We have to run the search with interrupts disabled, even critical - * and debug interrupts (in fact the only critical exceptions we have - * are debug and machine check). Otherwise an interrupt which causes - * a TLB miss can clobber the MMUCR between the mtspr and the tlbsx. */ - mfmsr r4 - lis r6,(MSR_EE|MSR_CE|MSR_ME|MSR_DE)@ha - addi r6,r6,(MSR_EE|MSR_CE|MSR_ME|MSR_DE)@l - andc r6,r4,r6 - mtmsr r6 - mtspr SPRN_MMUCR,r5 - tlbsx. r3, 0, r3 - mtmsr r4 - bne 10f - sync - /* There are only 64 TLB entries, so r3 < 64, - * which means bit 22, is clear. Since 22 is - * the V bit in the TLB_PAGEID, loading this - * value will invalidate the TLB entry. - */ - tlbwe r3, r3, PPC44x_TLB_PAGEID - isync -10: -#elif defined(CONFIG_FSL_BOOKE) - rlwinm r4, r3, 0, 0, 19 - ori r5, r4, 0x08 /* TLBSEL = 1 */ - tlbivax 0, r4 - tlbivax 0, r5 - msync -#if defined(CONFIG_SMP) - tlbsync -#endif /* CONFIG_SMP */ -#else /* !(CONFIG_40x || CONFIG_44x || CONFIG_FSL_BOOKE) */ -#if defined(CONFIG_SMP) - rlwinm r8,r1,0,0,(31-THREAD_SHIFT) - lwz r8,TI_CPU(r8) - oris r8,r8,11 - mfmsr r10 - SYNC - rlwinm r0,r10,0,17,15 /* clear bit 16 (MSR_EE) */ - rlwinm r0,r0,0,28,26 /* clear DR */ - mtmsr r0 - SYNC_601 - isync - lis r9,mmu_hash_lock@h - ori r9,r9,mmu_hash_lock@l - tophys(r9,r9) -10: lwarx r7,0,r9 - cmpwi 0,r7,0 - bne- 10b - stwcx. r8,0,r9 - bne- 10b - eieio - tlbie r3 - sync - TLBSYNC - li r0,0 - stw r0,0(r9) /* clear mmu_hash_lock */ - mtmsr r10 - SYNC_601 - isync -#else /* CONFIG_SMP */ - tlbie r3 - sync -#endif /* CONFIG_SMP */ -#endif /* ! CONFIG_40x */ - blr /* * Flush instruction cache. @@ -589,8 +426,8 @@ _GLOBAL(__flush_dcache_icache) BEGIN_FTR_SECTION blr END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) - rlwinm r3,r3,0,0,19 /* Get page base address */ - li r4,4096/L1_CACHE_BYTES /* Number of lines in a page */ + rlwinm r3,r3,0,0,31-PAGE_SHIFT /* Get page base address */ + li r4,PAGE_SIZE/L1_CACHE_BYTES /* Number of lines in a page */ mtctr r4 mr r6,r3 0: dcbst 0,r3 /* Write line to ram */ @@ -630,8 +467,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) rlwinm r0,r10,0,28,26 /* clear DR */ mtmsr r0 isync - rlwinm r3,r3,0,0,19 /* Get page base address */ - li r4,4096/L1_CACHE_BYTES /* Number of lines in a page */ + rlwinm r3,r3,0,0,31-PAGE_SHIFT /* Get page base address */ + li r4,PAGE_SIZE/L1_CACHE_BYTES /* Number of lines in a page */ mtctr r4 mr r6,r3 0: dcbst 0,r3 /* Write line to ram */ @@ -655,7 +492,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) * void clear_pages(void *page, int order) ; */ _GLOBAL(clear_pages) - li r0,4096/L1_CACHE_BYTES + li r0,PAGE_SIZE/L1_CACHE_BYTES slw r0,r0,r4 mtctr r0 #ifdef CONFIG_8xx @@ -713,7 +550,7 @@ _GLOBAL(copy_page) dcbt r5,r4 li r11,L1_CACHE_BYTES+4 #endif /* MAX_COPY_PREFETCH */ - li r0,4096/L1_CACHE_BYTES - MAX_COPY_PREFETCH + li r0,PAGE_SIZE/L1_CACHE_BYTES - MAX_COPY_PREFETCH crclr 4*cr0+eq 2: mtctr r0 @@ -846,8 +683,10 @@ _GLOBAL(kernel_thread) li r4,0 /* new sp (unused) */ li r0,__NR_clone sc - cmpwi 0,r3,0 /* parent or child? */ - bne 1f /* return if parent */ + bns+ 1f /* did system call indicate error? */ + neg r3,r3 /* if so, make return code negative */ +1: cmpwi 0,r3,0 /* parent or child? */ + bne 2f /* return if parent */ li r0,0 /* make top-level stack frame */ stwu r0,-16(r1) mtlr r30 /* fn addr in lr */ @@ -857,7 +696,7 @@ _GLOBAL(kernel_thread) li r0,__NR_exit /* exit if function returns */ li r3,0 sc -1: lwz r30,8(r1) +2: lwz r30,8(r1) lwz r31,12(r1) addi r1,r1,16 blr diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index 4dd70cf7bb4..3053fe5c62f 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -426,8 +426,10 @@ _GLOBAL(kernel_thread) li r4,0 /* new sp (unused) */ li r0,__NR_clone sc - cmpdi 0,r3,0 /* parent or child? */ - bne 1f /* return if parent */ + bns+ 1f /* did system call indicate error? */ + neg r3,r3 /* if so, make return code negative */ +1: cmpdi 0,r3,0 /* parent or child? */ + bne 2f /* return if parent */ li r0,0 stdu r0,-STACK_FRAME_OVERHEAD(r1) ld r2,8(r29) @@ -438,7 +440,7 @@ _GLOBAL(kernel_thread) li r0,__NR_exit /* exit after child exits */ li r3,0 sc -1: addi r1,r1,STACK_FRAME_OVERHEAD +2: addi r1,r1,STACK_FRAME_OVERHEAD ld r29,-24(r1) ld r30,-16(r1) blr diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c index 7ff29247526..43e7e3a7f13 100644 --- a/arch/powerpc/kernel/module.c +++ b/arch/powerpc/kernel/module.c @@ -78,6 +78,12 @@ int module_finalize(const Elf_Ehdr *hdr, (void *)sect->sh_addr, (void *)sect->sh_addr + sect->sh_size); + sect = find_section(hdr, sechdrs, "__mmu_ftr_fixup"); + if (sect != NULL) + do_feature_fixups(cur_cpu_spec->mmu_features, + (void *)sect->sh_addr, + (void *)sect->sh_addr + sect->sh_size); + #ifdef CONFIG_PPC64 sect = find_section(hdr, sechdrs, "__fw_ftr_fixup"); if (sect != NULL) diff --git a/arch/powerpc/kernel/module_32.c b/arch/powerpc/kernel/module_32.c index 2df91a03462..f832773fc28 100644 --- a/arch/powerpc/kernel/module_32.c +++ b/arch/powerpc/kernel/module_32.c @@ -22,6 +22,7 @@ #include <linux/fs.h> #include <linux/string.h> #include <linux/kernel.h> +#include <linux/ftrace.h> #include <linux/cache.h> #include <linux/bug.h> #include <linux/sort.h> @@ -53,6 +54,9 @@ static unsigned int count_relocs(const Elf32_Rela *rela, unsigned int num) r_addend = rela[i].r_addend; } +#ifdef CONFIG_DYNAMIC_FTRACE + _count_relocs++; /* add one for ftrace_caller */ +#endif return _count_relocs; } @@ -306,5 +310,11 @@ int apply_relocate_add(Elf32_Shdr *sechdrs, return -ENOEXEC; } } +#ifdef CONFIG_DYNAMIC_FTRACE + module->arch.tramp = + do_plt_call(module->module_core, + (unsigned long)ftrace_caller, + sechdrs, module); +#endif return 0; } diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 1af2377e499..8992b031a7b 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -20,6 +20,7 @@ #include <linux/moduleloader.h> #include <linux/err.h> #include <linux/vmalloc.h> +#include <linux/ftrace.h> #include <linux/bug.h> #include <asm/module.h> #include <asm/firmware.h> @@ -163,6 +164,11 @@ static unsigned long get_stubs_size(const Elf64_Ehdr *hdr, } } +#ifdef CONFIG_DYNAMIC_FTRACE + /* make the trampoline to the ftrace_caller */ + relocs++; +#endif + DEBUGP("Looks like a total of %lu stubs, max\n", relocs); return relocs * sizeof(struct ppc64_stub_entry); } @@ -441,5 +447,12 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, } } +#ifdef CONFIG_DYNAMIC_FTRACE + me->arch.toc = my_r2(sechdrs, me); + me->arch.tramp = stub_for_addr(sechdrs, + (unsigned long)ftrace_caller, + me); +#endif + return 0; } diff --git a/arch/powerpc/kernel/of_device.c b/arch/powerpc/kernel/of_device.c index e9be908f199..fa983a59c4c 100644 --- a/arch/powerpc/kernel/of_device.c +++ b/arch/powerpc/kernel/of_device.c @@ -14,7 +14,6 @@ static void of_device_make_bus_id(struct of_device *dev) { static atomic_t bus_no_reg_magic; struct device_node *node = dev->node; - char *name = dev->dev.bus_id; const u32 *reg; u64 addr; int magic; @@ -27,14 +26,12 @@ static void of_device_make_bus_id(struct of_device *dev) reg = of_get_property(node, "dcr-reg", NULL); if (reg) { #ifdef CONFIG_PPC_DCR_NATIVE - snprintf(name, BUS_ID_SIZE, "d%x.%s", - *reg, node->name); + dev_set_name(&dev->dev, "d%x.%s", *reg, node->name); #else /* CONFIG_PPC_DCR_NATIVE */ addr = of_translate_dcr_address(node, *reg, NULL); if (addr != OF_BAD_ADDR) { - snprintf(name, BUS_ID_SIZE, - "D%llx.%s", (unsigned long long)addr, - node->name); + dev_set_name(&dev->dev, "D%llx.%s", + (unsigned long long)addr, node->name); return; } #endif /* !CONFIG_PPC_DCR_NATIVE */ @@ -48,9 +45,8 @@ static void of_device_make_bus_id(struct of_device *dev) if (reg) { addr = of_translate_address(node, reg); if (addr != OF_BAD_ADDR) { - snprintf(name, BUS_ID_SIZE, - "%llx.%s", (unsigned long long)addr, - node->name); + dev_set_name(&dev->dev, "%llx.%s", + (unsigned long long)addr, node->name); return; } } @@ -60,7 +56,7 @@ static void of_device_make_bus_id(struct of_device *dev) * counter (and pray...) */ magic = atomic_add_return(1, &bus_no_reg_magic); - snprintf(name, BUS_ID_SIZE, "%s.%d", node->name, magic - 1); + dev_set_name(&dev->dev, "%s.%d", node->name, magic - 1); } struct of_device *of_device_alloc(struct device_node *np, @@ -78,10 +74,9 @@ struct of_device *of_device_alloc(struct device_node *np, dev->dev.parent = parent; dev->dev.release = of_release_dev; dev->dev.archdata.of_node = np; - dev->dev.archdata.numa_node = of_node_to_nid(np); if (bus_id) - strlcpy(dev->dev.bus_id, bus_id, BUS_ID_SIZE); + dev_set_name(&dev->dev, bus_id); else of_device_make_bus_id(dev); diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index c9bf17eec31..c744b327bca 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -12,6 +12,7 @@ #include <asm/lppaca.h> #include <asm/paca.h> +#include <asm/sections.h> /* This symbol is provided by the linker - let it fill in the paca * field correctly */ @@ -36,6 +37,7 @@ struct lppaca lppaca[] = { .end_of_quantum = 0xfffffffffffffffful, .slb_count = 64, .vmxregs_in_use = 0, + .page_ins = 0, }, }; @@ -79,6 +81,8 @@ void __init initialise_pacas(void) new_paca->lock_token = 0x8000; new_paca->paca_index = cpu; new_paca->kernel_toc = kernel_toc; + new_paca->kernelbase = (unsigned long) _stext; + new_paca->kernel_msr = MSR_KERNEL; new_paca->hw_cpu_id = 0xffff; new_paca->slb_shadow_ptr = &slb_shadow[cpu]; new_paca->__current = &init_task; diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index ea0c61e09b7..2538030954d 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -37,13 +37,7 @@ #include <asm/machdep.h> #include <asm/ppc-pci.h> #include <asm/firmware.h> - -#ifdef DEBUG -#include <asm/udbg.h> -#define DBG(fmt...) printk(fmt) -#else -#define DBG(fmt...) -#endif +#include <asm/eeh.h> static DEFINE_SPINLOCK(hose_spinlock); @@ -53,8 +47,37 @@ static int global_phb_number; /* Global phb counter */ /* ISA Memory physical address */ resource_size_t isa_mem_base; -/* Default PCI flags is 0 */ -unsigned int ppc_pci_flags; +/* Default PCI flags is 0 on ppc32, modified at boot on ppc64 */ +unsigned int ppc_pci_flags = 0; + + +static struct dma_mapping_ops *pci_dma_ops; + +void set_pci_dma_ops(struct dma_mapping_ops *dma_ops) +{ + pci_dma_ops = dma_ops; +} + +struct dma_mapping_ops *get_pci_dma_ops(void) +{ + return pci_dma_ops; +} +EXPORT_SYMBOL(get_pci_dma_ops); + +int pci_set_dma_mask(struct pci_dev *dev, u64 mask) +{ + return dma_set_mask(&dev->dev, mask); +} + +int pci_set_consistent_dma_mask(struct pci_dev *dev, u64 mask) +{ + int rc; + + rc = dma_set_mask(&dev->dev, mask); + dev->dev.coherent_dma_mask = dev->dma_mask; + + return rc; +} struct pci_controller *pcibios_alloc_controller(struct device_node *dev) { @@ -137,8 +160,6 @@ EXPORT_SYMBOL(pci_domain_nr); */ struct pci_controller* pci_find_hose_for_OF_device(struct device_node* node) { - if (!have_of) - return NULL; while(node) { struct pci_controller *hose, *tmp; list_for_each_entry_safe(hose, tmp, &hose_list, list_node) @@ -204,7 +225,7 @@ int pci_read_irq_line(struct pci_dev *pci_dev) return -1; #endif - DBG("Try to map irq for %s...\n", pci_name(pci_dev)); + pr_debug("PCI: Try to map irq for %s...\n", pci_name(pci_dev)); #ifdef DEBUG memset(&oirq, 0xff, sizeof(oirq)); @@ -228,26 +249,26 @@ int pci_read_irq_line(struct pci_dev *pci_dev) line == 0xff || line == 0) { return -1; } - DBG(" -> no map ! Using line %d (pin %d) from PCI config\n", - line, pin); + pr_debug(" No map ! Using line %d (pin %d) from PCI config\n", + line, pin); virq = irq_create_mapping(NULL, line); if (virq != NO_IRQ) set_irq_type(virq, IRQ_TYPE_LEVEL_LOW); } else { - DBG(" -> got one, spec %d cells (0x%08x 0x%08x...) on %s\n", - oirq.size, oirq.specifier[0], oirq.specifier[1], + pr_debug(" Got one, spec %d cells (0x%08x 0x%08x...) on %s\n", + oirq.size, oirq.specifier[0], oirq.specifier[1], oirq.controller->full_name); virq = irq_create_of_mapping(oirq.controller, oirq.specifier, oirq.size); } if(virq == NO_IRQ) { - DBG(" -> failed to map !\n"); + pr_debug(" Failed to map !\n"); return -1; } - DBG(" -> mapped to linux irq %d\n", virq); + pr_debug(" Mapped to linux irq %d\n", virq); pci_dev->irq = virq; @@ -349,13 +370,10 @@ static pgprot_t __pci_mmap_set_pgprot(struct pci_dev *dev, struct resource *rp, } /* XXX would be nice to have a way to ask for write-through */ - prot |= _PAGE_NO_CACHE; if (write_combine) - prot &= ~_PAGE_GUARDED; + return pgprot_noncached_wc(prot); else - prot |= _PAGE_GUARDED; - - return __pgprot(prot); + return pgprot_noncached(prot); } /* @@ -366,19 +384,17 @@ static pgprot_t __pci_mmap_set_pgprot(struct pci_dev *dev, struct resource *rp, pgprot_t pci_phys_mem_access_prot(struct file *file, unsigned long pfn, unsigned long size, - pgprot_t protection) + pgprot_t prot) { struct pci_dev *pdev = NULL; struct resource *found = NULL; - unsigned long prot = pgprot_val(protection); - unsigned long offset = pfn << PAGE_SHIFT; + resource_size_t offset = ((resource_size_t)pfn) << PAGE_SHIFT; int i; if (page_is_ram(pfn)) - return __pgprot(prot); - - prot |= _PAGE_NO_CACHE | _PAGE_GUARDED; + return prot; + prot = pgprot_noncached(prot); for_each_pci_dev(pdev) { for (i = 0; i <= PCI_ROM_RESOURCE; i++) { struct resource *rp = &pdev->resource[i]; @@ -399,13 +415,14 @@ pgprot_t pci_phys_mem_access_prot(struct file *file, } if (found) { if (found->flags & IORESOURCE_PREFETCH) - prot &= ~_PAGE_GUARDED; + prot = pgprot_noncached_wc(prot); pci_dev_put(pdev); } - DBG("non-PCI map for %lx, prot: %lx\n", offset, prot); + pr_debug("PCI: Non-PCI map for %llx, prot: %lx\n", + (unsigned long long)offset, pgprot_val(prot)); - return __pgprot(prot); + return prot; } @@ -422,7 +439,8 @@ pgprot_t pci_phys_mem_access_prot(struct file *file, int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, enum pci_mmap_state mmap_state, int write_combine) { - resource_size_t offset = vma->vm_pgoff << PAGE_SHIFT; + resource_size_t offset = + ((resource_size_t)vma->vm_pgoff) << PAGE_SHIFT; struct resource *rp; int ret; @@ -441,6 +459,131 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, return ret; } +/* This provides legacy IO read access on a bus */ +int pci_legacy_read(struct pci_bus *bus, loff_t port, u32 *val, size_t size) +{ + unsigned long offset; + struct pci_controller *hose = pci_bus_to_host(bus); + struct resource *rp = &hose->io_resource; + void __iomem *addr; + + /* Check if port can be supported by that bus. We only check + * the ranges of the PHB though, not the bus itself as the rules + * for forwarding legacy cycles down bridges are not our problem + * here. So if the host bridge supports it, we do it. + */ + offset = (unsigned long)hose->io_base_virt - _IO_BASE; + offset += port; + + if (!(rp->flags & IORESOURCE_IO)) + return -ENXIO; + if (offset < rp->start || (offset + size) > rp->end) + return -ENXIO; + addr = hose->io_base_virt + port; + + switch(size) { + case 1: + *((u8 *)val) = in_8(addr); + return 1; + case 2: + if (port & 1) + return -EINVAL; + *((u16 *)val) = in_le16(addr); + return 2; + case 4: + if (port & 3) + return -EINVAL; + *((u32 *)val) = in_le32(addr); + return 4; + } + return -EINVAL; +} + +/* This provides legacy IO write access on a bus */ +int pci_legacy_write(struct pci_bus *bus, loff_t port, u32 val, size_t size) +{ + unsigned long offset; + struct pci_controller *hose = pci_bus_to_host(bus); + struct resource *rp = &hose->io_resource; + void __iomem *addr; + + /* Check if port can be supported by that bus. We only check + * the ranges of the PHB though, not the bus itself as the rules + * for forwarding legacy cycles down bridges are not our problem + * here. So if the host bridge supports it, we do it. + */ + offset = (unsigned long)hose->io_base_virt - _IO_BASE; + offset += port; + + if (!(rp->flags & IORESOURCE_IO)) + return -ENXIO; + if (offset < rp->start || (offset + size) > rp->end) + return -ENXIO; + addr = hose->io_base_virt + port; + + /* WARNING: The generic code is idiotic. It gets passed a pointer + * to what can be a 1, 2 or 4 byte quantity and always reads that + * as a u32, which means that we have to correct the location of + * the data read within those 32 bits for size 1 and 2 + */ + switch(size) { + case 1: + out_8(addr, val >> 24); + return 1; + case 2: + if (port & 1) + return -EINVAL; + out_le16(addr, val >> 16); + return 2; + case 4: + if (port & 3) + return -EINVAL; + out_le32(addr, val); + return 4; + } + return -EINVAL; +} + +/* This provides legacy IO or memory mmap access on a bus */ +int pci_mmap_legacy_page_range(struct pci_bus *bus, + struct vm_area_struct *vma, + enum pci_mmap_state mmap_state) +{ + struct pci_controller *hose = pci_bus_to_host(bus); + resource_size_t offset = + ((resource_size_t)vma->vm_pgoff) << PAGE_SHIFT; + resource_size_t size = vma->vm_end - vma->vm_start; + struct resource *rp; + + pr_debug("pci_mmap_legacy_page_range(%04x:%02x, %s @%llx..%llx)\n", + pci_domain_nr(bus), bus->number, + mmap_state == pci_mmap_mem ? "MEM" : "IO", + (unsigned long long)offset, + (unsigned long long)(offset + size - 1)); + + if (mmap_state == pci_mmap_mem) { + if ((offset + size) > hose->isa_mem_size) + return -ENXIO; + offset += hose->isa_mem_phys; + } else { + unsigned long io_offset = (unsigned long)hose->io_base_virt - _IO_BASE; + unsigned long roffset = offset + io_offset; + rp = &hose->io_resource; + if (!(rp->flags & IORESOURCE_IO)) + return -ENXIO; + if (roffset < rp->start || (roffset + size) > rp->end) + return -ENXIO; + offset += hose->io_base_phys; + } + pr_debug(" -> mapping phys %llx\n", (unsigned long long)offset); + + vma->vm_pgoff = offset >> PAGE_SHIFT; + vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); + return remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff, + vma->vm_end - vma->vm_start, + vma->vm_page_prot); +} + void pci_resource_to_user(const struct pci_dev *dev, int bar, const struct resource *rsrc, resource_size_t *start, resource_size_t *end) @@ -543,6 +686,12 @@ void __devinit pci_process_bridge_OF_ranges(struct pci_controller *hose, cpu_addr = of_translate_address(dev, ranges + 3); size = of_read_number(ranges + pna + 3, 2); ranges += np; + + /* If we failed translation or got a zero-sized region + * (some FW try to feed us with non sensical zero sized regions + * such as power3 which look like some kind of attempt at exposing + * the VGA memory hole) + */ if (cpu_addr == OF_BAD_ADDR || size == 0) continue; @@ -616,6 +765,8 @@ void __devinit pci_process_bridge_OF_ranges(struct pci_controller *hose, isa_hole = memno; if (primary || isa_mem_base == 0) isa_mem_base = cpu_addr; + hose->isa_mem_phys = cpu_addr; + hose->isa_mem_size = size; } /* We get the PCI/Mem offset from the first range or @@ -669,15 +820,12 @@ void __devinit pci_process_bridge_OF_ranges(struct pci_controller *hose, int pci_proc_domain(struct pci_bus *bus) { struct pci_controller *hose = pci_bus_to_host(bus); -#ifdef CONFIG_PPC64 - return hose->buid != 0; -#else + if (!(ppc_pci_flags & PPC_PCI_ENABLE_PROC_DOMAINS)) return 0; if (ppc_pci_flags & PPC_PCI_COMPAT_DOMAIN_0) return hose->global_number != 0; return 1; -#endif } void pcibios_resource_to_bus(struct pci_dev *dev, struct pci_bus_region *region, @@ -731,11 +879,6 @@ static void __devinit fixup_resource(struct resource *res, struct pci_dev *dev) res->start = (res->start + offset) & mask; res->end = (res->end + offset) & mask; - - pr_debug("PCI:%s %016llx-%016llx\n", - pci_name(dev), - (unsigned long long)res->start, - (unsigned long long)res->end); } @@ -781,6 +924,11 @@ static void __devinit pcibios_fixup_resources(struct pci_dev *dev) (unsigned int)res->flags); fixup_resource(res, dev); + + pr_debug("PCI:%s %016llx-%016llx\n", + pci_name(dev), + (unsigned long long)res->start, + (unsigned long long)res->end); } /* Call machine specific resource fixup */ @@ -789,68 +937,160 @@ static void __devinit pcibios_fixup_resources(struct pci_dev *dev) } DECLARE_PCI_FIXUP_HEADER(PCI_ANY_ID, PCI_ANY_ID, pcibios_fixup_resources); -static void __devinit __pcibios_fixup_bus(struct pci_bus *bus) +/* This function tries to figure out if a bridge resource has been initialized + * by the firmware or not. It doesn't have to be absolutely bullet proof, but + * things go more smoothly when it gets it right. It should covers cases such + * as Apple "closed" bridge resources and bare-metal pSeries unassigned bridges + */ +static int __devinit pcibios_uninitialized_bridge_resource(struct pci_bus *bus, + struct resource *res) { struct pci_controller *hose = pci_bus_to_host(bus); struct pci_dev *dev = bus->self; + resource_size_t offset; + u16 command; + int i; - pr_debug("PCI: Fixup bus %d (%s)\n", bus->number, dev ? pci_name(dev) : "PHB"); + /* We don't do anything if PCI_PROBE_ONLY is set */ + if (ppc_pci_flags & PPC_PCI_PROBE_ONLY) + return 0; - /* Fixup PCI<->PCI bridges. Host bridges are handled separately, for - * now differently between 32 and 64 bits. - */ - if (dev != NULL) { - struct resource *res; - int i; + /* Job is a bit different between memory and IO */ + if (res->flags & IORESOURCE_MEM) { + /* If the BAR is non-0 (res != pci_mem_offset) then it's probably been + * initialized by somebody + */ + if (res->start != hose->pci_mem_offset) + return 0; - for (i = 0; i < PCI_BUS_NUM_RESOURCES; ++i) { - if ((res = bus->resource[i]) == NULL) - continue; - if (!res->flags) - continue; - if (i >= 3 && bus->self->transparent) - continue; - /* On PowerMac, Apple leaves bridge windows open over - * an inaccessible region of memory space (0...fffff) - * which is somewhat bogus, but that's what they think - * means disabled... - * - * We clear those to force them to be reallocated later - * - * We detect such regions by the fact that the base is - * equal to the pci_mem_offset of the host bridge and - * their size is smaller than 1M. - */ - if (res->flags & IORESOURCE_MEM && - res->start == hose->pci_mem_offset && - res->end < 0x100000) { - printk(KERN_INFO - "PCI: Closing bogus Apple Firmware" - " region %d on bus 0x%02x\n", - i, bus->number); - res->flags = 0; - continue; - } + /* The BAR is 0, let's check if memory decoding is enabled on + * the bridge. If not, we consider it unassigned + */ + pci_read_config_word(dev, PCI_COMMAND, &command); + if ((command & PCI_COMMAND_MEMORY) == 0) + return 1; - pr_debug("PCI:%s Bus rsrc %d %016llx-%016llx [%x] fixup...\n", - pci_name(dev), i, - (unsigned long long)res->start,\ - (unsigned long long)res->end, - (unsigned int)res->flags); + /* Memory decoding is enabled and the BAR is 0. If any of the bridge + * resources covers that starting address (0 then it's good enough for + * us for memory + */ + for (i = 0; i < 3; i++) { + if ((hose->mem_resources[i].flags & IORESOURCE_MEM) && + hose->mem_resources[i].start == hose->pci_mem_offset) + return 0; + } + + /* Well, it starts at 0 and we know it will collide so we may as + * well consider it as unassigned. That covers the Apple case. + */ + return 1; + } else { + /* If the BAR is non-0, then we consider it assigned */ + offset = (unsigned long)hose->io_base_virt - _IO_BASE; + if (((res->start - offset) & 0xfffffffful) != 0) + return 0; + + /* Here, we are a bit different than memory as typically IO space + * starting at low addresses -is- valid. What we do instead if that + * we consider as unassigned anything that doesn't have IO enabled + * in the PCI command register, and that's it. + */ + pci_read_config_word(dev, PCI_COMMAND, &command); + if (command & PCI_COMMAND_IO) + return 0; + + /* It's starting at 0 and IO is disabled in the bridge, consider + * it unassigned + */ + return 1; + } +} - fixup_resource(res, dev); +/* Fixup resources of a PCI<->PCI bridge */ +static void __devinit pcibios_fixup_bridge(struct pci_bus *bus) +{ + struct resource *res; + int i; + + struct pci_dev *dev = bus->self; + + for (i = 0; i < PCI_BUS_NUM_RESOURCES; ++i) { + if ((res = bus->resource[i]) == NULL) + continue; + if (!res->flags) + continue; + if (i >= 3 && bus->self->transparent) + continue; + + pr_debug("PCI:%s Bus rsrc %d %016llx-%016llx [%x] fixup...\n", + pci_name(dev), i, + (unsigned long long)res->start,\ + (unsigned long long)res->end, + (unsigned int)res->flags); + + /* Perform fixup */ + fixup_resource(res, dev); + + /* Try to detect uninitialized P2P bridge resources, + * and clear them out so they get re-assigned later + */ + if (pcibios_uninitialized_bridge_resource(bus, res)) { + res->flags = 0; + pr_debug("PCI:%s (unassigned)\n", pci_name(dev)); + } else { + + pr_debug("PCI:%s %016llx-%016llx\n", + pci_name(dev), + (unsigned long long)res->start, + (unsigned long long)res->end); } } +} - /* Additional setup that is different between 32 and 64 bits for now */ - pcibios_do_bus_setup(bus); +void __devinit pcibios_setup_bus_self(struct pci_bus *bus) +{ + /* Fix up the bus resources for P2P bridges */ + if (bus->self != NULL) + pcibios_fixup_bridge(bus); - /* Platform specific bus fixups */ + /* Platform specific bus fixups. This is currently only used + * by fsl_pci and I'm hoping to get rid of it at some point + */ if (ppc_md.pcibios_fixup_bus) ppc_md.pcibios_fixup_bus(bus); - /* Read default IRQs and fixup if necessary */ + /* Setup bus DMA mappings */ + if (ppc_md.pci_dma_bus_setup) + ppc_md.pci_dma_bus_setup(bus); +} + +void __devinit pcibios_setup_bus_devices(struct pci_bus *bus) +{ + struct pci_dev *dev; + + pr_debug("PCI: Fixup bus devices %d (%s)\n", + bus->number, bus->self ? pci_name(bus->self) : "PHB"); + list_for_each_entry(dev, &bus->devices, bus_list) { + struct dev_archdata *sd = &dev->dev.archdata; + + /* Setup OF node pointer in archdata */ + sd->of_node = pci_device_to_OF_node(dev); + + /* Fixup NUMA node as it may not be setup yet by the generic + * code and is needed by the DMA init + */ + set_dev_node(&dev->dev, pcibus_to_node(dev->bus)); + + /* Hook up default DMA ops */ + sd->dma_ops = pci_dma_ops; + sd->dma_data = (void *)PCI_DRAM_OFFSET; + + /* Additional platform DMA/iommu setup */ + if (ppc_md.pci_dma_dev_setup) + ppc_md.pci_dma_dev_setup(dev); + + /* Read default IRQs and fixup if necessary */ pci_read_irq_line(dev); if (ppc_md.pci_irq_fixup) ppc_md.pci_irq_fixup(dev); @@ -860,22 +1100,19 @@ static void __devinit __pcibios_fixup_bus(struct pci_bus *bus) void __devinit pcibios_fixup_bus(struct pci_bus *bus) { /* When called from the generic PCI probe, read PCI<->PCI bridge - * bases before proceeding + * bases. This is -not- called when generating the PCI tree from + * the OF device-tree. */ if (bus->self != NULL) pci_read_bridge_bases(bus); - __pcibios_fixup_bus(bus); -} -EXPORT_SYMBOL(pcibios_fixup_bus); -/* When building a bus from the OF tree rather than probing, we need a - * slightly different version of the fixup which doesn't read the - * bridge bases using config space accesses - */ -void __devinit pcibios_fixup_of_probed_bus(struct pci_bus *bus) -{ - __pcibios_fixup_bus(bus); + /* Now fixup the bus bus */ + pcibios_setup_bus_self(bus); + + /* Now fixup devices on that bus */ + pcibios_setup_bus_devices(bus); } +EXPORT_SYMBOL(pcibios_fixup_bus); static int skip_isa_ioresource_align(struct pci_dev *dev) { @@ -945,10 +1182,10 @@ static int __init reparent_resources(struct resource *parent, *pp = NULL; for (p = res->child; p != NULL; p = p->sibling) { p->parent = res; - DBG(KERN_INFO "PCI: reparented %s [%llx..%llx] under %s\n", - p->name, - (unsigned long long)p->start, - (unsigned long long)p->end, res->name); + pr_debug("PCI: Reparented %s [%llx..%llx] under %s\n", + p->name, + (unsigned long long)p->start, + (unsigned long long)p->end, res->name); } return 0; } @@ -986,80 +1223,80 @@ static int __init reparent_resources(struct resource *parent, * as well. */ -static void __init pcibios_allocate_bus_resources(struct list_head *bus_list) +void pcibios_allocate_bus_resources(struct pci_bus *bus) { - struct pci_bus *bus; + struct pci_bus *b; int i; struct resource *res, *pr; - /* Depth-First Search on bus tree */ - list_for_each_entry(bus, bus_list, node) { - for (i = 0; i < PCI_BUS_NUM_RESOURCES; ++i) { - if ((res = bus->resource[i]) == NULL || !res->flags - || res->start > res->end) - continue; - if (bus->parent == NULL) - pr = (res->flags & IORESOURCE_IO) ? - &ioport_resource : &iomem_resource; - else { - /* Don't bother with non-root busses when - * re-assigning all resources. We clear the - * resource flags as if they were colliding - * and as such ensure proper re-allocation - * later. - */ - if (ppc_pci_flags & PPC_PCI_REASSIGN_ALL_RSRC) - goto clear_resource; - pr = pci_find_parent_resource(bus->self, res); - if (pr == res) { - /* this happens when the generic PCI - * code (wrongly) decides that this - * bridge is transparent -- paulus - */ - continue; - } - } + pr_debug("PCI: Allocating bus resources for %04x:%02x...\n", + pci_domain_nr(bus), bus->number); - DBG("PCI: %s (bus %d) bridge rsrc %d: %016llx-%016llx " - "[0x%x], parent %p (%s)\n", - bus->self ? pci_name(bus->self) : "PHB", - bus->number, i, - (unsigned long long)res->start, - (unsigned long long)res->end, - (unsigned int)res->flags, - pr, (pr && pr->name) ? pr->name : "nil"); - - if (pr && !(pr->flags & IORESOURCE_UNSET)) { - if (request_resource(pr, res) == 0) - continue; - /* - * Must be a conflict with an existing entry. - * Move that entry (or entries) under the - * bridge resource and try again. + for (i = 0; i < PCI_BUS_NUM_RESOURCES; ++i) { + if ((res = bus->resource[i]) == NULL || !res->flags + || res->start > res->end || res->parent) + continue; + if (bus->parent == NULL) + pr = (res->flags & IORESOURCE_IO) ? + &ioport_resource : &iomem_resource; + else { + /* Don't bother with non-root busses when + * re-assigning all resources. We clear the + * resource flags as if they were colliding + * and as such ensure proper re-allocation + * later. + */ + if (ppc_pci_flags & PPC_PCI_REASSIGN_ALL_RSRC) + goto clear_resource; + pr = pci_find_parent_resource(bus->self, res); + if (pr == res) { + /* this happens when the generic PCI + * code (wrongly) decides that this + * bridge is transparent -- paulus */ - if (reparent_resources(pr, res) == 0) - continue; + continue; } - printk(KERN_WARNING - "PCI: Cannot allocate resource region " - "%d of PCI bridge %d, will remap\n", - i, bus->number); -clear_resource: - res->flags = 0; } - pcibios_allocate_bus_resources(&bus->children); + + pr_debug("PCI: %s (bus %d) bridge rsrc %d: %016llx-%016llx " + "[0x%x], parent %p (%s)\n", + bus->self ? pci_name(bus->self) : "PHB", + bus->number, i, + (unsigned long long)res->start, + (unsigned long long)res->end, + (unsigned int)res->flags, + pr, (pr && pr->name) ? pr->name : "nil"); + + if (pr && !(pr->flags & IORESOURCE_UNSET)) { + if (request_resource(pr, res) == 0) + continue; + /* + * Must be a conflict with an existing entry. + * Move that entry (or entries) under the + * bridge resource and try again. + */ + if (reparent_resources(pr, res) == 0) + continue; + } + printk(KERN_WARNING "PCI: Cannot allocate resource region " + "%d of PCI bridge %d, will remap\n", i, bus->number); +clear_resource: + res->flags = 0; } + + list_for_each_entry(b, &bus->children, node) + pcibios_allocate_bus_resources(b); } static inline void __devinit alloc_resource(struct pci_dev *dev, int idx) { struct resource *pr, *r = &dev->resource[idx]; - DBG("PCI: Allocating %s: Resource %d: %016llx..%016llx [%x]\n", - pci_name(dev), idx, - (unsigned long long)r->start, - (unsigned long long)r->end, - (unsigned int)r->flags); + pr_debug("PCI: Allocating %s: Resource %d: %016llx..%016llx [%x]\n", + pci_name(dev), idx, + (unsigned long long)r->start, + (unsigned long long)r->end, + (unsigned int)r->flags); pr = pci_find_parent_resource(dev, r); if (!pr || (pr->flags & IORESOURCE_UNSET) || @@ -1067,10 +1304,11 @@ static inline void __devinit alloc_resource(struct pci_dev *dev, int idx) printk(KERN_WARNING "PCI: Cannot allocate resource region %d" " of device %s, will remap\n", idx, pci_name(dev)); if (pr) - DBG("PCI: parent is %p: %016llx-%016llx [%x]\n", pr, - (unsigned long long)pr->start, - (unsigned long long)pr->end, - (unsigned int)pr->flags); + pr_debug("PCI: parent is %p: %016llx-%016llx [%x]\n", + pr, + (unsigned long long)pr->start, + (unsigned long long)pr->end, + (unsigned int)pr->flags); /* We'll assign a new address later */ r->flags |= IORESOURCE_UNSET; r->end -= r->start; @@ -1108,7 +1346,8 @@ static void __init pcibios_allocate_resources(int pass) * but keep it unregistered. */ u32 reg; - DBG("PCI: Switching off ROM of %s\n", pci_name(dev)); + pr_debug("PCI: Switching off ROM of %s\n", + pci_name(dev)); r->flags &= ~IORESOURCE_ROM_ENABLE; pci_read_config_dword(dev, dev->rom_base_reg, ®); pci_write_config_dword(dev, dev->rom_base_reg, @@ -1119,10 +1358,13 @@ static void __init pcibios_allocate_resources(int pass) void __init pcibios_resource_survey(void) { + struct pci_bus *b; + /* Allocate and assign resources. If we re-assign everything, then * we skip the allocate phase */ - pcibios_allocate_bus_resources(&pci_root_buses); + list_for_each_entry(b, &pci_root_buses, node) + pcibios_allocate_bus_resources(b); if (!(ppc_pci_flags & PPC_PCI_REASSIGN_ALL_RSRC)) { pcibios_allocate_resources(0); @@ -1130,7 +1372,7 @@ void __init pcibios_resource_survey(void) } if (!(ppc_pci_flags & PPC_PCI_PROBE_ONLY)) { - DBG("PCI: Assigning unassigned resouces...\n"); + pr_debug("PCI: Assigning unassigned resouces...\n"); pci_assign_unassigned_resources(); } @@ -1140,9 +1382,11 @@ void __init pcibios_resource_survey(void) } #ifdef CONFIG_HOTPLUG -/* This is used by the pSeries hotplug driver to allocate resource + +/* This is used by the PCI hotplug driver to allocate resource * of newly plugged busses. We can try to consolidate with the - * rest of the code later, for now, keep it as-is + * rest of the code later, for now, keep it as-is as our main + * resource allocation function doesn't deal with sub-trees yet. */ void __devinit pcibios_claim_one_bus(struct pci_bus *bus) { @@ -1157,6 +1401,14 @@ void __devinit pcibios_claim_one_bus(struct pci_bus *bus) if (r->parent || !r->start || !r->flags) continue; + + pr_debug("PCI: Claiming %s: " + "Resource %d: %016llx..%016llx [%x]\n", + pci_name(dev), i, + (unsigned long long)r->start, + (unsigned long long)r->end, + (unsigned int)r->flags); + pci_claim_resource(dev, i); } } @@ -1165,6 +1417,31 @@ void __devinit pcibios_claim_one_bus(struct pci_bus *bus) pcibios_claim_one_bus(child_bus); } EXPORT_SYMBOL_GPL(pcibios_claim_one_bus); + + +/* pcibios_finish_adding_to_bus + * + * This is to be called by the hotplug code after devices have been + * added to a bus, this include calling it for a PHB that is just + * being added + */ +void pcibios_finish_adding_to_bus(struct pci_bus *bus) +{ + pr_debug("PCI: Finishing adding to hotplug bus %04x:%02x\n", + pci_domain_nr(bus), bus->number); + + /* Allocate bus and devices resources */ + pcibios_allocate_bus_resources(bus); + pcibios_claim_one_bus(bus); + + /* Add new devices to global lists. Register in proc, sysfs. */ + pci_bus_add_devices(bus); + + /* Fixup EEH */ + eeh_add_device_tree_late(bus); +} +EXPORT_SYMBOL_GPL(pcibios_finish_adding_to_bus); + #endif /* CONFIG_HOTPLUG */ int pcibios_enable_device(struct pci_dev *dev, int mask) @@ -1175,3 +1452,61 @@ int pcibios_enable_device(struct pci_dev *dev, int mask) return pci_enable_resources(dev, mask); } + +void __devinit pcibios_setup_phb_resources(struct pci_controller *hose) +{ + struct pci_bus *bus = hose->bus; + struct resource *res; + int i; + + /* Hookup PHB IO resource */ + bus->resource[0] = res = &hose->io_resource; + + if (!res->flags) { + printk(KERN_WARNING "PCI: I/O resource not set for host" + " bridge %s (domain %d)\n", + hose->dn->full_name, hose->global_number); +#ifdef CONFIG_PPC32 + /* Workaround for lack of IO resource only on 32-bit */ + res->start = (unsigned long)hose->io_base_virt - isa_io_base; + res->end = res->start + IO_SPACE_LIMIT; + res->flags = IORESOURCE_IO; +#endif /* CONFIG_PPC32 */ + } + + pr_debug("PCI: PHB IO resource = %016llx-%016llx [%lx]\n", + (unsigned long long)res->start, + (unsigned long long)res->end, + (unsigned long)res->flags); + + /* Hookup PHB Memory resources */ + for (i = 0; i < 3; ++i) { + res = &hose->mem_resources[i]; + if (!res->flags) { + if (i > 0) + continue; + printk(KERN_ERR "PCI: Memory resource 0 not set for " + "host bridge %s (domain %d)\n", + hose->dn->full_name, hose->global_number); +#ifdef CONFIG_PPC32 + /* Workaround for lack of MEM resource only on 32-bit */ + res->start = hose->pci_mem_offset; + res->end = (resource_size_t)-1LL; + res->flags = IORESOURCE_MEM; +#endif /* CONFIG_PPC32 */ + } + bus->resource[i+1] = res; + + pr_debug("PCI: PHB MEM resource %d = %016llx-%016llx [%lx]\n", i, + (unsigned long long)res->start, + (unsigned long long)res->end, + (unsigned long)res->flags); + } + + pr_debug("PCI: PHB MEM offset = %016llx\n", + (unsigned long long)hose->pci_mem_offset); + pr_debug("PCI: PHB IO offset = %08lx\n", + (unsigned long)hose->io_base_virt - _IO_BASE); + +} + diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c index 88db4ffaf11..132cd80afa2 100644 --- a/arch/powerpc/kernel/pci_32.c +++ b/arch/powerpc/kernel/pci_32.c @@ -26,12 +26,6 @@ #undef DEBUG -#ifdef DEBUG -#define DBG(x...) printk(x) -#else -#define DBG(x...) -#endif - unsigned long isa_io_base = 0; unsigned long pci_dram_offset = 0; int pcibios_assign_bus_offset = 1; @@ -53,12 +47,19 @@ LIST_HEAD(hose_list); static int pci_bus_count; +/* This will remain NULL for now, until isa-bridge.c is made common + * to both 32-bit and 64-bit. + */ +struct pci_dev *isa_bridge_pcidev; +EXPORT_SYMBOL_GPL(isa_bridge_pcidev); + static void -fixup_hide_host_resource_fsl(struct pci_dev* dev) +fixup_hide_host_resource_fsl(struct pci_dev *dev) { int i, class = dev->class >> 8; - if ((class == PCI_CLASS_PROCESSOR_POWERPC) && + if ((class == PCI_CLASS_PROCESSOR_POWERPC || + class == PCI_CLASS_BRIDGE_OTHER) && (dev->hdr_type == PCI_HEADER_TYPE_NORMAL) && (dev->bus->parent == NULL)) { for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) { @@ -265,17 +266,14 @@ pci_busdev_to_OF_node(struct pci_bus *bus, int devfn) { struct device_node *parent, *np; - if (!have_of) - return NULL; - - DBG("pci_busdev_to_OF_node(%d,0x%x)\n", bus->number, devfn); + pr_debug("pci_busdev_to_OF_node(%d,0x%x)\n", bus->number, devfn); parent = scan_OF_for_pci_bus(bus); if (parent == NULL) return NULL; - DBG(" parent is %s\n", parent ? parent->full_name : "<NULL>"); + pr_debug(" parent is %s\n", parent ? parent->full_name : "<NULL>"); np = scan_OF_for_pci_dev(parent, devfn); of_node_put(parent); - DBG(" result is %s\n", np ? np->full_name : "<NULL>"); + pr_debug(" result is %s\n", np ? np->full_name : "<NULL>"); /* XXX most callers don't release the returned node * mostly because ppc64 doesn't increase the refcount, @@ -308,8 +306,6 @@ pci_device_from_OF_node(struct device_node* node, u8* bus, u8* devfn) struct pci_controller* hose; struct pci_dev* dev = NULL; - if (!have_of) - return -ENODEV; /* Make sure it's really a PCI device */ hose = pci_find_hose_for_OF_device(node); if (!hose || !hose->dn) @@ -372,10 +368,41 @@ void pcibios_make_OF_bus_map(void) } #endif /* CONFIG_PPC_OF */ +static void __devinit pcibios_scan_phb(struct pci_controller *hose) +{ + struct pci_bus *bus; + struct device_node *node = hose->dn; + unsigned long io_offset; + struct resource *res = &hose->io_resource; + + pr_debug("PCI: Scanning PHB %s\n", + node ? node->full_name : "<NO NAME>"); + + /* Create an empty bus for the toplevel */ + bus = pci_create_bus(hose->parent, hose->first_busno, hose->ops, hose); + if (bus == NULL) { + printk(KERN_ERR "Failed to create bus for PCI domain %04x\n", + hose->global_number); + return; + } + bus->secondary = hose->first_busno; + hose->bus = bus; + + /* Fixup IO space offset */ + io_offset = (unsigned long)hose->io_base_virt - isa_io_base; + res->start = (res->start + io_offset) & 0xffffffffu; + res->end = (res->end + io_offset) & 0xffffffffu; + + /* Wire up PHB bus resources */ + pcibios_setup_phb_resources(hose); + + /* Scan children */ + hose->last_busno = bus->subordinate = pci_scan_child_bus(bus); +} + static int __init pcibios_init(void) { struct pci_controller *hose, *tmp; - struct pci_bus *bus; int next_busno = 0; printk(KERN_INFO "PCI: Probing PCI hardware\n"); @@ -388,12 +415,8 @@ static int __init pcibios_init(void) if (pci_assign_all_buses) hose->first_busno = next_busno; hose->last_busno = 0xff; - bus = pci_scan_bus_parented(hose->parent, hose->first_busno, - hose->ops, hose); - if (bus) { - pci_bus_add_devices(bus); - hose->last_busno = bus->subordinate; - } + pcibios_scan_phb(hose); + pci_bus_add_devices(hose->bus); if (pci_assign_all_buses || next_busno <= hose->last_busno) next_busno = hose->last_busno + pcibios_assign_bus_offset; } @@ -403,7 +426,7 @@ static int __init pcibios_init(void) * numbers vs. kernel bus numbers since we may have to * remap them. */ - if (pci_assign_all_buses && have_of) + if (pci_assign_all_buses) pcibios_make_OF_bus_map(); /* Call common code to handle resource allocation */ @@ -418,47 +441,6 @@ static int __init pcibios_init(void) subsys_initcall(pcibios_init); -void __devinit pcibios_do_bus_setup(struct pci_bus *bus) -{ - struct pci_controller *hose = (struct pci_controller *) bus->sysdata; - unsigned long io_offset; - struct resource *res; - int i; - - /* Hookup PHB resources */ - io_offset = (unsigned long)hose->io_base_virt - isa_io_base; - if (bus->parent == NULL) { - /* This is a host bridge - fill in its resources */ - hose->bus = bus; - - bus->resource[0] = res = &hose->io_resource; - if (!res->flags) { - if (io_offset) - printk(KERN_ERR "I/O resource not set for host" - " bridge %d\n", hose->global_number); - res->start = 0; - res->end = IO_SPACE_LIMIT; - res->flags = IORESOURCE_IO; - } - res->start = (res->start + io_offset) & 0xffffffffu; - res->end = (res->end + io_offset) & 0xffffffffu; - - for (i = 0; i < 3; ++i) { - res = &hose->mem_resources[i]; - if (!res->flags) { - if (i > 0) - continue; - printk(KERN_ERR "Memory resource not set for " - "host bridge %d\n", hose->global_number); - res->start = hose->pci_mem_offset; - res->end = ~0U; - res->flags = IORESOURCE_MEM; - } - bus->resource[i+1] = res; - } - } -} - /* the next one is stolen from the alpha port... */ void __init pcibios_update_irq(struct pci_dev *dev, int irq) diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index 30eedfc5a56..39fadc6e149 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -32,13 +32,6 @@ #include <asm/machdep.h> #include <asm/ppc-pci.h> -#ifdef DEBUG -#include <asm/udbg.h> -#define DBG(fmt...) printk(fmt) -#else -#define DBG(fmt...) -#endif - unsigned long pci_probe_only = 1; /* pci_io_base -- the base address from which io bars are offsets. @@ -52,35 +45,6 @@ EXPORT_SYMBOL(pci_io_base); LIST_HEAD(hose_list); -static struct dma_mapping_ops *pci_dma_ops; - -void set_pci_dma_ops(struct dma_mapping_ops *dma_ops) -{ - pci_dma_ops = dma_ops; -} - -struct dma_mapping_ops *get_pci_dma_ops(void) -{ - return pci_dma_ops; -} -EXPORT_SYMBOL(get_pci_dma_ops); - - -int pci_set_dma_mask(struct pci_dev *dev, u64 mask) -{ - return dma_set_mask(&dev->dev, mask); -} - -int pci_set_consistent_dma_mask(struct pci_dev *dev, u64 mask) -{ - int rc; - - rc = dma_set_mask(&dev->dev, mask); - dev->dev.coherent_dma_mask = dev->dma_mask; - - return rc; -} - static void fixup_broken_pcnet32(struct pci_dev* dev) { if ((dev->class>>8 == PCI_CLASS_NETWORK_ETHERNET)) { @@ -131,7 +95,7 @@ static void pci_parse_of_addrs(struct device_node *node, struct pci_dev *dev) addrs = of_get_property(node, "assigned-addresses", &proplen); if (!addrs) return; - DBG(" parse addresses (%d bytes) @ %p\n", proplen, addrs); + pr_debug(" parse addresses (%d bytes) @ %p\n", proplen, addrs); for (; proplen >= 20; proplen -= 20, addrs += 5) { flags = pci_parse_of_flags(addrs[0]); if (!flags) @@ -141,8 +105,9 @@ static void pci_parse_of_addrs(struct device_node *node, struct pci_dev *dev) if (!size) continue; i = addrs[0] & 0xff; - DBG(" base: %llx, size: %llx, i: %x\n", - (unsigned long long)base, (unsigned long long)size, i); + pr_debug(" base: %llx, size: %llx, i: %x\n", + (unsigned long long)base, + (unsigned long long)size, i); if (PCI_BASE_ADDRESS_0 <= i && i <= PCI_BASE_ADDRESS_5) { res = &dev->resource[(i - PCI_BASE_ADDRESS_0) >> 2]; @@ -173,7 +138,7 @@ struct pci_dev *of_create_pci_dev(struct device_node *node, if (type == NULL) type = ""; - DBG(" create device, devfn: %x, type: %s\n", devfn, type); + pr_debug(" create device, devfn: %x, type: %s\n", devfn, type); dev->bus = bus; dev->sysdata = node; @@ -194,8 +159,8 @@ struct pci_dev *of_create_pci_dev(struct device_node *node, dev->class = get_int_prop(node, "class-code", 0); dev->revision = get_int_prop(node, "revision-id", 0); - DBG(" class: 0x%x\n", dev->class); - DBG(" revision: 0x%x\n", dev->revision); + pr_debug(" class: 0x%x\n", dev->class); + pr_debug(" revision: 0x%x\n", dev->revision); dev->current_state = 4; /* unknown power state */ dev->error_state = pci_channel_io_normal; @@ -216,7 +181,7 @@ struct pci_dev *of_create_pci_dev(struct device_node *node, pci_parse_of_addrs(node, dev); - DBG(" adding to system ...\n"); + pr_debug(" adding to system ...\n"); pci_device_add(dev, bus); @@ -224,19 +189,20 @@ struct pci_dev *of_create_pci_dev(struct device_node *node, } EXPORT_SYMBOL(of_create_pci_dev); -void __devinit of_scan_bus(struct device_node *node, - struct pci_bus *bus) +static void __devinit __of_scan_bus(struct device_node *node, + struct pci_bus *bus, int rescan_existing) { struct device_node *child; const u32 *reg; int reglen, devfn; struct pci_dev *dev; - DBG("of_scan_bus(%s) bus no %d... \n", node->full_name, bus->number); + pr_debug("of_scan_bus(%s) bus no %d... \n", + node->full_name, bus->number); /* Scan direct children */ for_each_child_of_node(node, child) { - DBG(" * %s\n", child->full_name); + pr_debug(" * %s\n", child->full_name); reg = of_get_property(child, "reg", ®len); if (reg == NULL || reglen < 20) continue; @@ -246,11 +212,15 @@ void __devinit of_scan_bus(struct device_node *node, dev = of_create_pci_dev(child, bus, devfn); if (!dev) continue; - DBG(" dev header type: %x\n", dev->hdr_type); + pr_debug(" dev header type: %x\n", dev->hdr_type); } - /* Ally all fixups */ - pcibios_fixup_of_probed_bus(bus); + /* Apply all fixups necessary. We don't fixup the bus "self" + * for an existing bridge that is being rescanned + */ + if (!rescan_existing) + pcibios_setup_bus_self(bus); + pcibios_setup_bus_devices(bus); /* Now scan child busses */ list_for_each_entry(dev, &bus->devices, bus_list) { @@ -262,7 +232,20 @@ void __devinit of_scan_bus(struct device_node *node, } } } -EXPORT_SYMBOL(of_scan_bus); + +void __devinit of_scan_bus(struct device_node *node, + struct pci_bus *bus) +{ + __of_scan_bus(node, bus, 0); +} +EXPORT_SYMBOL_GPL(of_scan_bus); + +void __devinit of_rescan_bus(struct device_node *node, + struct pci_bus *bus) +{ + __of_scan_bus(node, bus, 1); +} +EXPORT_SYMBOL_GPL(of_rescan_bus); void __devinit of_scan_pci_bridge(struct device_node *node, struct pci_dev *dev) @@ -274,7 +257,7 @@ void __devinit of_scan_pci_bridge(struct device_node *node, unsigned int flags; u64 size; - DBG("of_scan_pci_bridge(%s)\n", node->full_name); + pr_debug("of_scan_pci_bridge(%s)\n", node->full_name); /* parse bus-range property */ busrange = of_get_property(node, "bus-range", &len); @@ -338,12 +321,12 @@ void __devinit of_scan_pci_bridge(struct device_node *node, } sprintf(bus->name, "PCI Bus %04x:%02x", pci_domain_nr(bus), bus->number); - DBG(" bus name: %s\n", bus->name); + pr_debug(" bus name: %s\n", bus->name); mode = PCI_PROBE_NORMAL; if (ppc_md.pci_probe_mode) mode = ppc_md.pci_probe_mode(bus); - DBG(" probe mode: %d\n", mode); + pr_debug(" probe mode: %d\n", mode); if (mode == PCI_PROBE_DEVTREE) of_scan_bus(node, bus); @@ -356,9 +339,10 @@ void __devinit scan_phb(struct pci_controller *hose) { struct pci_bus *bus; struct device_node *node = hose->dn; - int i, mode; + int mode; - DBG("PCI: Scanning PHB %s\n", node ? node->full_name : "<NO NAME>"); + pr_debug("PCI: Scanning PHB %s\n", + node ? node->full_name : "<NO NAME>"); /* Create an empty bus for the toplevel */ bus = pci_create_bus(hose->parent, hose->first_busno, hose->ops, node); @@ -374,26 +358,13 @@ void __devinit scan_phb(struct pci_controller *hose) pcibios_map_io_space(bus); /* Wire up PHB bus resources */ - DBG("PCI: PHB IO resource = %016lx-%016lx [%lx]\n", - hose->io_resource.start, hose->io_resource.end, - hose->io_resource.flags); - bus->resource[0] = &hose->io_resource; - for (i = 0; i < 3; ++i) { - DBG("PCI: PHB MEM resource %d = %016lx-%016lx [%lx]\n", i, - hose->mem_resources[i].start, - hose->mem_resources[i].end, - hose->mem_resources[i].flags); - bus->resource[i+1] = &hose->mem_resources[i]; - } - DBG("PCI: PHB MEM offset = %016lx\n", hose->pci_mem_offset); - DBG("PCI: PHB IO offset = %08lx\n", - (unsigned long)hose->io_base_virt - _IO_BASE); + pcibios_setup_phb_resources(hose); /* Get probe mode and perform scan */ mode = PCI_PROBE_NORMAL; if (node && ppc_md.pci_probe_mode) mode = ppc_md.pci_probe_mode(bus); - DBG(" probe mode: %d\n", mode); + pr_debug(" probe mode: %d\n", mode); if (mode == PCI_PROBE_DEVTREE) { bus->subordinate = hose->last_busno; of_scan_bus(node, bus); @@ -409,7 +380,7 @@ static int __init pcibios_init(void) printk(KERN_INFO "PCI: Probing PCI hardware\n"); - /* For now, override phys_mem_access_prot. If we need it, + /* For now, override phys_mem_access_prot. If we need it,g * later, we may move that initialization to each ppc_md */ ppc_md.phys_mem_access_prot = pci_phys_mem_access_prot; @@ -417,6 +388,11 @@ static int __init pcibios_init(void) if (pci_probe_only) ppc_pci_flags |= PPC_PCI_PROBE_ONLY; + /* On ppc64, we always enable PCI domains and we keep domain 0 + * backward compatible in /proc for video cards + */ + ppc_pci_flags |= PPC_PCI_ENABLE_PROC_DOMAINS | PPC_PCI_COMPAT_DOMAIN_0; + /* Scan all of the recorded PCI controllers. */ list_for_each_entry_safe(hose, tmp, &hose_list, list_node) { scan_phb(hose); @@ -451,11 +427,11 @@ int pcibios_unmap_io_space(struct pci_bus *bus) if (bus->self) { struct resource *res = bus->resource[0]; - DBG("IO unmapping for PCI-PCI bridge %s\n", - pci_name(bus->self)); + pr_debug("IO unmapping for PCI-PCI bridge %s\n", + pci_name(bus->self)); __flush_hash_table_range(&init_mm, res->start + _IO_BASE, - res->end - res->start + 1); + res->end + _IO_BASE + 1); return 0; } @@ -466,8 +442,8 @@ int pcibios_unmap_io_space(struct pci_bus *bus) if (hose->io_base_alloc == 0) return 0; - DBG("IO unmapping for PHB %s\n", hose->dn->full_name); - DBG(" alloc=0x%p\n", hose->io_base_alloc); + pr_debug("IO unmapping for PHB %s\n", hose->dn->full_name); + pr_debug(" alloc=0x%p\n", hose->io_base_alloc); /* This is a PHB, we fully unmap the IO area */ vunmap(hose->io_base_alloc); @@ -492,11 +468,11 @@ int __devinit pcibios_map_io_space(struct pci_bus *bus) * thus HPTEs will be faulted in when needed */ if (bus->self) { - DBG("IO mapping for PCI-PCI bridge %s\n", - pci_name(bus->self)); - DBG(" virt=0x%016lx...0x%016lx\n", - bus->resource[0]->start + _IO_BASE, - bus->resource[0]->end + _IO_BASE); + pr_debug("IO mapping for PCI-PCI bridge %s\n", + pci_name(bus->self)); + pr_debug(" virt=0x%016lx...0x%016lx\n", + bus->resource[0]->start + _IO_BASE, + bus->resource[0]->end + _IO_BASE); return 0; } @@ -525,11 +501,11 @@ int __devinit pcibios_map_io_space(struct pci_bus *bus) hose->io_base_virt = (void __iomem *)(area->addr + hose->io_base_phys - phys_page); - DBG("IO mapping for PHB %s\n", hose->dn->full_name); - DBG(" phys=0x%016lx, virt=0x%p (alloc=0x%p)\n", - hose->io_base_phys, hose->io_base_virt, hose->io_base_alloc); - DBG(" size=0x%016lx (alloc=0x%016lx)\n", - hose->pci_io_size, size_page); + pr_debug("IO mapping for PHB %s\n", hose->dn->full_name); + pr_debug(" phys=0x%016lx, virt=0x%p (alloc=0x%p)\n", + hose->io_base_phys, hose->io_base_virt, hose->io_base_alloc); + pr_debug(" size=0x%016lx (alloc=0x%016lx)\n", + hose->pci_io_size, size_page); /* Establish the mapping */ if (__ioremap_at(phys_page, area->addr, size_page, @@ -541,44 +517,13 @@ int __devinit pcibios_map_io_space(struct pci_bus *bus) hose->io_resource.start += io_virt_offset; hose->io_resource.end += io_virt_offset; - DBG(" hose->io_resource=0x%016lx...0x%016lx\n", - hose->io_resource.start, hose->io_resource.end); + pr_debug(" hose->io_resource=0x%016lx...0x%016lx\n", + hose->io_resource.start, hose->io_resource.end); return 0; } EXPORT_SYMBOL_GPL(pcibios_map_io_space); -void __devinit pcibios_setup_new_device(struct pci_dev *dev) -{ - struct dev_archdata *sd = &dev->dev.archdata; - - sd->of_node = pci_device_to_OF_node(dev); - - DBG("PCI: device %s OF node: %s\n", pci_name(dev), - sd->of_node ? sd->of_node->full_name : "<none>"); - - sd->dma_ops = pci_dma_ops; -#ifdef CONFIG_NUMA - sd->numa_node = pcibus_to_node(dev->bus); -#else - sd->numa_node = -1; -#endif - if (ppc_md.pci_dma_dev_setup) - ppc_md.pci_dma_dev_setup(dev); -} -EXPORT_SYMBOL(pcibios_setup_new_device); - -void __devinit pcibios_do_bus_setup(struct pci_bus *bus) -{ - struct pci_dev *dev; - - if (ppc_md.pci_dma_bus_setup) - ppc_md.pci_dma_bus_setup(bus); - - list_for_each_entry(dev, &bus->devices, bus_list) - pcibios_setup_new_device(dev); -} - unsigned long pci_address_to_pio(phys_addr_t address) { struct pci_controller *hose, *tmp; diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c index e1ea4fe5cfb..dcec1325d34 100644 --- a/arch/powerpc/kernel/ppc_ksyms.c +++ b/arch/powerpc/kernel/ppc_ksyms.c @@ -68,7 +68,7 @@ EXPORT_SYMBOL(single_step_exception); EXPORT_SYMBOL(sys_sigreturn); #endif -#ifdef CONFIG_FTRACE +#ifdef CONFIG_FUNCTION_TRACER EXPORT_SYMBOL(_mcount); #endif @@ -116,9 +116,6 @@ EXPORT_SYMBOL(giveup_spe); #ifndef CONFIG_PPC64 EXPORT_SYMBOL(flush_instruction_cache); -EXPORT_SYMBOL(flush_tlb_kernel_range); -EXPORT_SYMBOL(flush_tlb_page); -EXPORT_SYMBOL(_tlbie); #endif EXPORT_SYMBOL(__flush_icache_range); EXPORT_SYMBOL(flush_dcache_range); @@ -171,8 +168,7 @@ EXPORT_SYMBOL(cacheable_memcpy); #endif #ifdef CONFIG_PPC32 -EXPORT_SYMBOL(next_mmu_context); -EXPORT_SYMBOL(set_context); +EXPORT_SYMBOL(switch_mmu_context); #endif #ifdef CONFIG_PPC_STD_MMU_32 diff --git a/arch/powerpc/kernel/ppc_save_regs.S b/arch/powerpc/kernel/ppc_save_regs.S new file mode 100644 index 00000000000..5113bd2285e --- /dev/null +++ b/arch/powerpc/kernel/ppc_save_regs.S @@ -0,0 +1,74 @@ +/* + * Copyright (C) 1996 Paul Mackerras. + * + * 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. + * + * NOTE: assert(sizeof(buf) > 23 * sizeof(long)) + */ +#include <asm/processor.h> +#include <asm/ppc_asm.h> +#include <asm/asm-offsets.h> + +/* + * Grab the register values as they are now. + * This won't do a particularily good job because we really + * want our caller's caller's registers, and our caller has + * already executed its prologue. + * ToDo: We could reach back into the caller's save area to do + * a better job of representing the caller's state (note that + * that will be different for 32-bit and 64-bit, because of the + * different ABIs, though). + */ +_GLOBAL(ppc_save_regs) + PPC_STL r0,0*SZL(r3) + PPC_STL r2,2*SZL(r3) + PPC_STL r3,3*SZL(r3) + PPC_STL r4,4*SZL(r3) + PPC_STL r5,5*SZL(r3) + PPC_STL r6,6*SZL(r3) + PPC_STL r7,7*SZL(r3) + PPC_STL r8,8*SZL(r3) + PPC_STL r9,9*SZL(r3) + PPC_STL r10,10*SZL(r3) + PPC_STL r11,11*SZL(r3) + PPC_STL r12,12*SZL(r3) + PPC_STL r13,13*SZL(r3) + PPC_STL r14,14*SZL(r3) + PPC_STL r15,15*SZL(r3) + PPC_STL r16,16*SZL(r3) + PPC_STL r17,17*SZL(r3) + PPC_STL r18,18*SZL(r3) + PPC_STL r19,19*SZL(r3) + PPC_STL r20,20*SZL(r3) + PPC_STL r21,21*SZL(r3) + PPC_STL r22,22*SZL(r3) + PPC_STL r23,23*SZL(r3) + PPC_STL r24,24*SZL(r3) + PPC_STL r25,25*SZL(r3) + PPC_STL r26,26*SZL(r3) + PPC_STL r27,27*SZL(r3) + PPC_STL r28,28*SZL(r3) + PPC_STL r29,29*SZL(r3) + PPC_STL r30,30*SZL(r3) + PPC_STL r31,31*SZL(r3) + /* go up one stack frame for SP */ + PPC_LL r4,0(r1) + PPC_STL r4,1*SZL(r3) + /* get caller's LR */ + PPC_LL r0,LRSAVE(r4) + PPC_STL r0,_NIP-STACK_FRAME_OVERHEAD(r3) + PPC_STL r0,_LINK-STACK_FRAME_OVERHEAD(r3) + mfmsr r0 + PPC_STL r0,_MSR-STACK_FRAME_OVERHEAD(r3) + mfctr r0 + PPC_STL r0,_CTR-STACK_FRAME_OVERHEAD(r3) + mfxer r0 + PPC_STL r0,_XER-STACK_FRAME_OVERHEAD(r3) + mfcr r0 + PPC_STL r0,_CCR-STACK_FRAME_OVERHEAD(r3) + li r0,0 + PPC_STL r0,_TRAP-STACK_FRAME_OVERHEAD(r3) + blr diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 957bded0020..51b201ddf9a 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -467,6 +467,8 @@ static struct regbit { {MSR_VEC, "VEC"}, {MSR_VSX, "VSX"}, {MSR_ME, "ME"}, + {MSR_CE, "CE"}, + {MSR_DE, "DE"}, {MSR_IR, "IR"}, {MSR_DR, "DR"}, {0, NULL} @@ -998,7 +1000,7 @@ unsigned long get_wchan(struct task_struct *p) return 0; } -static int kstack_depth_to_print = 64; +static int kstack_depth_to_print = CONFIG_PRINT_STACK_DEPTH; void show_stack(struct task_struct *tsk, unsigned long *stack) { diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 87d83c56b31..6f73c739f1e 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -888,9 +888,10 @@ static u64 __init dt_mem_next_cell(int s, cell_t **cellp) */ static int __init early_init_dt_scan_drconf_memory(unsigned long node) { - cell_t *dm, *ls; + cell_t *dm, *ls, *usm; unsigned long l, n, flags; u64 base, size, lmb_size; + unsigned int is_kexec_kdump = 0, rngs; ls = (cell_t *)of_get_flat_dt_prop(node, "ibm,lmb-size", &l); if (ls == NULL || l < dt_root_size_cells * sizeof(cell_t)) @@ -905,6 +906,12 @@ static int __init early_init_dt_scan_drconf_memory(unsigned long node) if (l < (n * (dt_root_addr_cells + 4) + 1) * sizeof(cell_t)) return 0; + /* check if this is a kexec/kdump kernel. */ + usm = (cell_t *)of_get_flat_dt_prop(node, "linux,drconf-usable-memory", + &l); + if (usm != NULL) + is_kexec_kdump = 1; + for (; n != 0; --n) { base = dt_mem_next_cell(dt_root_addr_cells, &dm); flags = dm[3]; @@ -915,13 +922,34 @@ static int __init early_init_dt_scan_drconf_memory(unsigned long node) if ((flags & 0x80) || !(flags & 0x8)) continue; size = lmb_size; - if (iommu_is_off) { - if (base >= 0x80000000ul) + rngs = 1; + if (is_kexec_kdump) { + /* + * For each lmb in ibm,dynamic-memory, a corresponding + * entry in linux,drconf-usable-memory property contains + * a counter 'p' followed by 'p' (base, size) duple. + * Now read the counter from + * linux,drconf-usable-memory property + */ + rngs = dt_mem_next_cell(dt_root_size_cells, &usm); + if (!rngs) /* there are no (base, size) duple */ continue; - if ((base + size) > 0x80000000ul) - size = 0x80000000ul - base; } - lmb_add(base, size); + do { + if (is_kexec_kdump) { + base = dt_mem_next_cell(dt_root_addr_cells, + &usm); + size = dt_mem_next_cell(dt_root_size_cells, + &usm); + } + if (iommu_is_off) { + if (base >= 0x80000000ul) + continue; + if ((base + size) > 0x80000000ul) + size = 0x80000000ul - base; + } + lmb_add(base, size); + } while (--rngs); } lmb_dump_all(); return 0; @@ -1132,6 +1160,8 @@ static inline void __init phyp_dump_reserve_mem(void) {} void __init early_init_devtree(void *params) { + unsigned long limit; + DBG(" -> early_init_devtree(%p)\n", params); /* Setup flat device-tree pointer */ @@ -1164,12 +1194,27 @@ void __init early_init_devtree(void *params) /* Reserve LMB regions used by kernel, initrd, dt, etc... */ lmb_reserve(PHYSICAL_START, __pa(klimit) - PHYSICAL_START); + /* If relocatable, reserve first 32k for interrupt vectors etc. */ + if (PHYSICAL_START > MEMORY_START) + lmb_reserve(MEMORY_START, 0x8000); reserve_kdump_trampoline(); reserve_crashkernel(); early_reserve_mem(); phyp_dump_reserve_mem(); - lmb_enforce_memory_limit(memory_limit); + limit = memory_limit; + if (! limit) { + unsigned long memsize; + + /* Ensure that total memory size is page-aligned, because + * otherwise mark_bootmem() gets upset. */ + lmb_analyze(); + memsize = lmb_phys_mem_size(); + if ((memsize & PAGE_MASK) != memsize) + limit = memsize & PAGE_MASK; + } + lmb_enforce_memory_limit(limit); + lmb_analyze(); DBG("Phys. mem: %lx\n", lmb_phys_mem_size()); @@ -1240,6 +1285,37 @@ struct device_node *of_find_node_by_phandle(phandle handle) EXPORT_SYMBOL(of_find_node_by_phandle); /** + * of_find_next_cache_node - Find a node's subsidiary cache + * @np: node of type "cpu" or "cache" + * + * Returns a node pointer with refcount incremented, use + * of_node_put() on it when done. Caller should hold a reference + * to np. + */ +struct device_node *of_find_next_cache_node(struct device_node *np) +{ + struct device_node *child; + const phandle *handle; + + handle = of_get_property(np, "l2-cache", NULL); + if (!handle) + handle = of_get_property(np, "next-level-cache", NULL); + + if (handle) + return of_find_node_by_phandle(*handle); + + /* OF on pmac has nodes instead of properties named "l2-cache" + * beneath CPU nodes. + */ + if (!strcmp(np->type, "cpu")) + for_each_child_of_node(np, child) + if (!strcmp(child->type, "cache")) + return child; + + return NULL; +} + +/** * of_find_all_nodes - Get next node in global list * @prev: Previous node or NULL to start iteration * of_node_put() will be called on it diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index b72849ac7db..2445945d376 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -487,67 +487,6 @@ static int __init prom_setprop(phandle node, const char *nodename, return call_prom("interpret", 1, 1, (u32)(unsigned long) cmd); } -/* We can't use the standard versions because of RELOC headaches. */ -#define isxdigit(c) (('0' <= (c) && (c) <= '9') \ - || ('a' <= (c) && (c) <= 'f') \ - || ('A' <= (c) && (c) <= 'F')) - -#define isdigit(c) ('0' <= (c) && (c) <= '9') -#define islower(c) ('a' <= (c) && (c) <= 'z') -#define toupper(c) (islower(c) ? ((c) - 'a' + 'A') : (c)) - -unsigned long prom_strtoul(const char *cp, const char **endp) -{ - unsigned long result = 0, base = 10, value; - - if (*cp == '0') { - base = 8; - cp++; - if (toupper(*cp) == 'X') { - cp++; - base = 16; - } - } - - while (isxdigit(*cp) && - (value = isdigit(*cp) ? *cp - '0' : toupper(*cp) - 'A' + 10) < base) { - result = result * base + value; - cp++; - } - - if (endp) - *endp = cp; - - return result; -} - -unsigned long prom_memparse(const char *ptr, const char **retptr) -{ - unsigned long ret = prom_strtoul(ptr, retptr); - int shift = 0; - - /* - * We can't use a switch here because GCC *may* generate a - * jump table which won't work, because we're not running at - * the address we're linked at. - */ - if ('G' == **retptr || 'g' == **retptr) - shift = 30; - - if ('M' == **retptr || 'm' == **retptr) - shift = 20; - - if ('K' == **retptr || 'k' == **retptr) - shift = 10; - - if (shift) { - ret <<= shift; - (*retptr)++; - } - - return ret; -} - /* * Early parsing of the command line passed to the kernel, used for * "mem=x" and the options that affect the iommu @@ -1321,7 +1260,7 @@ static void __init prom_initialize_tce_table(void) * * -- Cort */ -extern void __secondary_hold(void); +extern char __secondary_hold; extern unsigned long __secondary_hold_spinloop; extern unsigned long __secondary_hold_acknowledge; @@ -1342,13 +1281,7 @@ static void __init prom_hold_cpus(void) = (void *) LOW_ADDR(__secondary_hold_spinloop); unsigned long *acknowledge = (void *) LOW_ADDR(__secondary_hold_acknowledge); -#ifdef CONFIG_PPC64 - /* __secondary_hold is actually a descriptor, not the text address */ - unsigned long secondary_hold - = __pa(*PTRRELOC((unsigned long *)__secondary_hold)); -#else unsigned long secondary_hold = LOW_ADDR(__secondary_hold); -#endif prom_debug("prom_hold_cpus: start...\n"); prom_debug(" 1) spinloop = 0x%x\n", (unsigned long)spinloop); @@ -2315,13 +2248,14 @@ static void __init prom_check_initrd(unsigned long r3, unsigned long r4) unsigned long __init prom_init(unsigned long r3, unsigned long r4, unsigned long pp, - unsigned long r6, unsigned long r7) + unsigned long r6, unsigned long r7, + unsigned long kbase) { struct prom_t *_prom; unsigned long hdr; - unsigned long offset = reloc_offset(); #ifdef CONFIG_PPC32 + unsigned long offset = reloc_offset(); reloc_got2(offset); #endif @@ -2355,9 +2289,11 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4, */ RELOC(of_platform) = prom_find_machine_type(); +#ifndef CONFIG_RELOCATABLE /* Bail if this is a kdump kernel. */ if (PHYSICAL_START > 0) prom_panic("Error: You can't boot a kdump kernel from OF!\n"); +#endif /* * Check for an initrd @@ -2377,7 +2313,7 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4, * Copy the CPU hold code */ if (RELOC(of_platform) != PLATFORM_POWERMAC) - copy_and_flush(0, KERNELBASE + offset, 0x100, 0); + copy_and_flush(0, kbase, 0x100, 0); /* * Do early parsing of command line @@ -2480,7 +2416,7 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4, reloc_got2(-offset); #endif - __start(hdr, KERNELBASE + offset, 0); + __start(hdr, kbase, 0); return 0; } diff --git a/arch/powerpc/kernel/prom_init_check.sh b/arch/powerpc/kernel/prom_init_check.sh index 2c7e8e87f77..ea3a2ec03ff 100644 --- a/arch/powerpc/kernel/prom_init_check.sh +++ b/arch/powerpc/kernel/prom_init_check.sh @@ -20,7 +20,7 @@ WHITELIST="add_reloc_offset __bss_start __bss_stop copy_and_flush _end enter_prom memcpy memset reloc_offset __secondary_hold __secondary_hold_acknowledge __secondary_hold_spinloop __start strcmp strcpy strlcpy strlen strncmp strstr logo_linux_clut224 -reloc_got2 kernstart_addr" +reloc_got2 kernstart_addr memstart_addr" NM="$1" OBJ="$2" diff --git a/arch/powerpc/kernel/prom_parse.c b/arch/powerpc/kernel/prom_parse.c index bc1fb27368a..8c133556608 100644 --- a/arch/powerpc/kernel/prom_parse.c +++ b/arch/powerpc/kernel/prom_parse.c @@ -250,8 +250,11 @@ int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq) * parsing */ dn = pci_device_to_OF_node(pdev); - if (dn) - return of_irq_map_one(dn, 0, out_irq); + if (dn) { + rc = of_irq_map_one(dn, 0, out_irq); + if (!rc) + return rc; + } /* Ok, we don't, time to have fun. Let's start by building up an * interrupt spec. we assume #interrupt-cells is 1, which is standard @@ -731,10 +734,7 @@ void of_irq_map_init(unsigned int flags) if (flags & OF_IMAP_NO_PHANDLE) { struct device_node *np; - for(np = NULL; (np = of_find_all_nodes(np)) != NULL;) { - if (of_get_property(np, "interrupt-controller", NULL) - == NULL) - continue; + for_each_node_with_property(np, "interrupt-controller") { /* Skip /chosen/interrupt-controller */ if (strcmp(np->name, "chosen") == 0) continue; diff --git a/arch/powerpc/kernel/reloc_64.S b/arch/powerpc/kernel/reloc_64.S new file mode 100644 index 00000000000..b47a0e1ab00 --- /dev/null +++ b/arch/powerpc/kernel/reloc_64.S @@ -0,0 +1,87 @@ +/* + * Code to process dynamic relocations in the kernel. + * + * Copyright 2008 Paul Mackerras, IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <asm/ppc_asm.h> + +RELA = 7 +RELACOUNT = 0x6ffffff9 +R_PPC64_RELATIVE = 22 + +/* + * r3 = desired final address of kernel + */ +_GLOBAL(relocate) + mflr r0 + bcl 20,31,$+4 +0: mflr r12 /* r12 has runtime addr of label 0 */ + mtlr r0 + ld r11,(p_dyn - 0b)(r12) + add r11,r11,r12 /* r11 has runtime addr of .dynamic section */ + ld r9,(p_rela - 0b)(r12) + add r9,r9,r12 /* r9 has runtime addr of .rela.dyn section */ + ld r10,(p_st - 0b)(r12) + add r10,r10,r12 /* r10 has runtime addr of _stext */ + + /* + * Scan the dynamic section for the RELA and RELACOUNT entries. + */ + li r7,0 + li r8,0 +1: ld r6,0(r11) /* get tag */ + cmpdi r6,0 + beq 4f /* end of list */ + cmpdi r6,RELA + bne 2f + ld r7,8(r11) /* get RELA pointer in r7 */ + b 3f +2: addis r6,r6,(-RELACOUNT)@ha + cmpdi r6,RELACOUNT@l + bne 3f + ld r8,8(r11) /* get RELACOUNT value in r8 */ +3: addi r11,r11,16 + b 1b +4: cmpdi r7,0 /* check we have both RELA and RELACOUNT */ + cmpdi cr1,r8,0 + beq 6f + beq cr1,6f + + /* + * Work out linktime address of _stext and hence the + * relocation offset to be applied. + * cur_offset [r7] = rela.run [r9] - rela.link [r7] + * _stext.link [r10] = _stext.run [r10] - cur_offset [r7] + * final_offset [r3] = _stext.final [r3] - _stext.link [r10] + */ + subf r7,r7,r9 /* cur_offset */ + subf r10,r7,r10 + subf r3,r10,r3 /* final_offset */ + + /* + * Run through the list of relocations and process the + * R_PPC64_RELATIVE ones. + */ + mtctr r8 +5: lwz r0,12(9) /* ELF64_R_TYPE(reloc->r_info) */ + cmpwi r0,R_PPC64_RELATIVE + bne 6f + ld r6,0(r9) /* reloc->r_offset */ + ld r0,16(r9) /* reloc->r_addend */ + add r0,r0,r3 + stdx r0,r7,r6 + addi r9,r9,24 + bdnz 5b + +6: blr + +p_dyn: .llong __dynamic_start - 0b +p_rela: .llong __rela_dyn_start - 0b +p_st: .llong _stext - 0b + diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 1f8505c2354..fdfe14c4bde 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -566,6 +566,32 @@ int rtas_get_sensor(int sensor, int index, int *state) } EXPORT_SYMBOL(rtas_get_sensor); +bool rtas_indicator_present(int token, int *maxindex) +{ + int proplen, count, i; + const struct indicator_elem { + u32 token; + u32 maxindex; + } *indicators; + + indicators = of_get_property(rtas.dev, "rtas-indicators", &proplen); + if (!indicators) + return false; + + count = proplen / sizeof(struct indicator_elem); + + for (i = 0; i < count; i++) { + if (indicators[i].token != token) + continue; + if (maxindex) + *maxindex = indicators[i].maxindex; + return true; + } + + return false; +} +EXPORT_SYMBOL(rtas_indicator_present); + int rtas_set_indicator(int indicator, int index, int new_value) { int token = rtas_token("set-indicator"); diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c index 589a2797eac..8869001ab5d 100644 --- a/arch/powerpc/kernel/rtas_pci.c +++ b/arch/powerpc/kernel/rtas_pci.c @@ -301,51 +301,3 @@ void __init find_and_init_phbs(void) #endif /* CONFIG_PPC32 */ } } - -/* RPA-specific bits for removing PHBs */ -int pcibios_remove_root_bus(struct pci_controller *phb) -{ - struct pci_bus *b = phb->bus; - struct resource *res; - int rc, i; - - res = b->resource[0]; - if (!res->flags) { - printk(KERN_ERR "%s: no IO resource for PHB %s\n", __func__, - b->name); - return 1; - } - - rc = pcibios_unmap_io_space(b); - if (rc) { - printk(KERN_ERR "%s: failed to unmap IO on bus %s\n", - __func__, b->name); - return 1; - } - - if (release_resource(res)) { - printk(KERN_ERR "%s: failed to release IO on bus %s\n", - __func__, b->name); - return 1; - } - - for (i = 1; i < 3; ++i) { - res = b->resource[i]; - if (!res->flags && i == 0) { - printk(KERN_ERR "%s: no MEM resource for PHB %s\n", - __func__, b->name); - return 1; - } - if (res->flags && release_resource(res)) { - printk(KERN_ERR - "%s: failed to release IO %d on bus %s\n", - __func__, i, b->name); - return 1; - } - } - - pcibios_free_controller(phb); - - return 0; -} -EXPORT_SYMBOL(pcibios_remove_root_bus); diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 9cc5a52711e..705fc4bf380 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -59,6 +59,7 @@ #include <asm/mmu.h> #include <asm/xmon.h> #include <asm/cputhreads.h> +#include <mm/mmu_decl.h> #include "setup.h" @@ -190,6 +191,12 @@ static int show_cpuinfo(struct seq_file *m, void *v) if (ppc_md.show_cpuinfo != NULL) ppc_md.show_cpuinfo(m); +#ifdef CONFIG_PPC32 + /* Display the amount of memory */ + seq_printf(m, "Memory\t\t: %d MB\n", + (unsigned int)(total_memory / (1024 * 1024))); +#endif + return 0; } @@ -254,8 +261,21 @@ static int show_cpuinfo(struct seq_file *m, void *v) /* If we are a Freescale core do a simple check so * we dont have to keep adding cases in the future */ if (PVR_VER(pvr) & 0x8000) { - maj = PVR_MAJ(pvr); - min = PVR_MIN(pvr); + switch (PVR_VER(pvr)) { + case 0x8000: /* 7441/7450/7451, Voyager */ + case 0x8001: /* 7445/7455, Apollo 6 */ + case 0x8002: /* 7447/7457, Apollo 7 */ + case 0x8003: /* 7447A, Apollo 7 PM */ + case 0x8004: /* 7448, Apollo 8 */ + case 0x800c: /* 7410, Nitro */ + maj = ((pvr >> 8) & 0xF); + min = PVR_MIN(pvr); + break; + default: /* e500/book-e */ + maj = PVR_MAJ(pvr); + min = PVR_MIN(pvr); + break; + } } else { switch (PVR_VER(pvr)) { case 0x0020: /* 403 family */ diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index 066e65c59b5..9e1ca745d8f 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -38,6 +38,7 @@ #include <asm/time.h> #include <asm/serial.h> #include <asm/udbg.h> +#include <asm/mmu_context.h> #include "setup.h" @@ -49,12 +50,12 @@ int boot_cpuid; EXPORT_SYMBOL_GPL(boot_cpuid); int boot_cpuid_phys; +int smp_hw_index[NR_CPUS]; + unsigned long ISA_DMA_THRESHOLD; unsigned int DMA_MODE_READ; unsigned int DMA_MODE_WRITE; -int have_of = 1; - #ifdef CONFIG_VGA_CONSOLE unsigned long vgacon_remap_base; EXPORT_SYMBOL(vgacon_remap_base); @@ -97,6 +98,10 @@ notrace unsigned long __init early_init(unsigned long dt_ptr) PTRRELOC(&__start___ftr_fixup), PTRRELOC(&__stop___ftr_fixup)); + do_feature_fixups(spec->mmu_features, + PTRRELOC(&__start___mmu_ftr_fixup), + PTRRELOC(&__stop___mmu_ftr_fixup)); + do_lwsync_fixups(spec->cpu_features, PTRRELOC(&__start___lwsync_fixup), PTRRELOC(&__stop___lwsync_fixup)); @@ -111,7 +116,7 @@ notrace unsigned long __init early_init(unsigned long dt_ptr) * This is called very early on the boot process, after a minimal * MMU environment has been set up but before MMU_init is called. */ -notrace void __init machine_init(unsigned long dt_ptr, unsigned long phys) +notrace void __init machine_init(unsigned long dt_ptr) { /* Enable early debugging if any specified (see udbg.h) */ udbg_early_init(); @@ -121,6 +126,8 @@ notrace void __init machine_init(unsigned long dt_ptr, unsigned long phys) probe_machine(); + setup_kdump_trampoline(); + #ifdef CONFIG_6xx if (cpu_has_feature(CPU_FTR_CAN_DOZE) || cpu_has_feature(CPU_FTR_CAN_NAP)) @@ -209,23 +216,12 @@ EXPORT_SYMBOL(nvram_sync); #endif /* CONFIG_NVRAM */ -static DEFINE_PER_CPU(struct cpu, cpu_devices); - int __init ppc_init(void) { - int cpu; - /* clear the progress line */ if (ppc_md.progress) ppc_md.progress(" ", 0xffff); - /* register CPU devices */ - for_each_possible_cpu(cpu) { - struct cpu *c = &per_cpu(cpu_devices, cpu); - c->hotpluggable = 1; - register_cpu(c, cpu); - } - /* call platform init */ if (ppc_md.init != NULL) { ppc_md.init(); @@ -337,4 +333,8 @@ void __init setup_arch(char **cmdline_p) if ( ppc_md.progress ) ppc_md.progress("arch: exit", 0x3eab); paging_init(); + + /* Initialize the MMU context management stuff */ + mmu_context_init(); + } diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 8b25f51f03b..d8bd2161e73 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -70,7 +70,6 @@ #define DBG(fmt...) #endif -int have_of = 1; int boot_cpuid = 0; u64 ppc64_pft_size; @@ -255,9 +254,11 @@ void early_setup_secondary(void) #endif /* CONFIG_SMP */ #if defined(CONFIG_SMP) || defined(CONFIG_KEXEC) +extern unsigned long __secondary_hold_spinloop; +extern void generic_secondary_smp_init(void); + void smp_release_cpus(void) { - extern unsigned long __secondary_hold_spinloop; unsigned long *ptr; DBG(" -> smp_release_cpus()\n"); @@ -266,12 +267,11 @@ void smp_release_cpus(void) * all now so they can start to spin on their individual paca * spinloops. For non SMP kernels, the secondary cpus never get out * of the common spinloop. - * This is useless but harmless on iSeries, secondaries are already - * waiting on their paca spinloops. */ + */ ptr = (unsigned long *)((unsigned long)&__secondary_hold_spinloop - PHYSICAL_START); - *ptr = 1; + *ptr = __pa(generic_secondary_smp_init); mb(); DBG(" <- smp_release_cpus()\n"); @@ -361,6 +361,8 @@ void __init setup_system(void) */ do_feature_fixups(cur_cpu_spec->cpu_features, &__start___ftr_fixup, &__stop___ftr_fixup); + do_feature_fixups(cur_cpu_spec->mmu_features, + &__start___mmu_ftr_fixup, &__stop___mmu_ftr_fixup); do_feature_fixups(powerpc_firmware_features, &__start___fw_ftr_fixup, &__stop___fw_ftr_fixup); do_lwsync_fixups(cur_cpu_spec->cpu_features, @@ -443,9 +445,9 @@ void __init setup_system(void) if (htab_address) printk("htab_address = 0x%p\n", htab_address); printk("htab_hash_mask = 0x%lx\n", htab_hash_mask); -#if PHYSICAL_START > 0 - printk("physical_start = 0x%lx\n", PHYSICAL_START); -#endif + if (PHYSICAL_START > 0) + printk("physical_start = 0x%lx\n", + PHYSICAL_START); printk("-----------------------------------------------------\n"); DBG(" <- setup_system()\n"); @@ -605,8 +607,6 @@ void __init setup_per_cpu_areas(void) for_each_possible_cpu(i) { ptr = alloc_bootmem_pages_node(NODE_DATA(cpu_to_node(i)), size); - if (!ptr) - panic("Cannot allocate cpu data for CPU %d\n", i); paca[i].data_offset = ptr - __per_cpu_start; memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start); diff --git a/arch/powerpc/kernel/signal.h b/arch/powerpc/kernel/signal.h index 28f4b9f5fe5..b427bf8e1d8 100644 --- a/arch/powerpc/kernel/signal.h +++ b/arch/powerpc/kernel/signal.h @@ -12,6 +12,8 @@ #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) +extern void do_signal(struct pt_regs *regs, unsigned long thread_info_flags); + extern void __user * get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size); extern void restore_sigmask(sigset_t *set); diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 3e80aa32b8b..b13abf30599 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -410,7 +410,7 @@ inline unsigned long copy_fpr_from_user(struct task_struct *task, * altivec/spe instructions at some point. */ static int save_user_regs(struct pt_regs *regs, struct mcontext __user *frame, - int sigret) + int sigret, int ctx_has_vsx_region) { unsigned long msr = regs->msr; @@ -451,7 +451,7 @@ static int save_user_regs(struct pt_regs *regs, struct mcontext __user *frame, * the saved MSR value to indicate that frame->mc_vregs * contains valid data */ - if (current->thread.used_vsr) { + if (current->thread.used_vsr && ctx_has_vsx_region) { __giveup_vsx(current); if (copy_vsx_to_user(&frame->mc_vsregs, current)) return 1; @@ -858,11 +858,11 @@ int handle_rt_signal32(unsigned long sig, struct k_sigaction *ka, frame = &rt_sf->uc.uc_mcontext; addr = frame; if (vdso32_rt_sigtramp && current->mm->context.vdso_base) { - if (save_user_regs(regs, frame, 0)) + if (save_user_regs(regs, frame, 0, 1)) goto badframe; regs->link = current->mm->context.vdso_base + vdso32_rt_sigtramp; } else { - if (save_user_regs(regs, frame, __NR_rt_sigreturn)) + if (save_user_regs(regs, frame, __NR_rt_sigreturn, 1)) goto badframe; regs->link = (unsigned long) frame->tramp; } @@ -936,13 +936,26 @@ long sys_swapcontext(struct ucontext __user *old_ctx, int ctx_size, int r6, int r7, int r8, struct pt_regs *regs) { unsigned char tmp; + int ctx_has_vsx_region = 0; #ifdef CONFIG_PPC64 unsigned long new_msr = 0; - if (new_ctx && - __get_user(new_msr, &new_ctx->uc_mcontext.mc_gregs[PT_MSR])) - return -EFAULT; + if (new_ctx) { + struct mcontext __user *mcp; + u32 cmcp; + + /* + * Get pointer to the real mcontext. No need for + * access_ok since we are dealing with compat + * pointers. + */ + if (__get_user(cmcp, &new_ctx->uc_regs)) + return -EFAULT; + mcp = (struct mcontext __user *)(u64)cmcp; + if (__get_user(new_msr, &mcp->mc_gregs[PT_MSR])) + return -EFAULT; + } /* * Check that the context is not smaller than the original * size (with VMX but without VSX) @@ -956,16 +969,9 @@ long sys_swapcontext(struct ucontext __user *old_ctx, if ((ctx_size < sizeof(struct ucontext)) && (new_msr & MSR_VSX)) return -EINVAL; -#ifdef CONFIG_VSX - /* - * If userspace doesn't provide enough room for VSX data, - * but current thread has used VSX, we don't have anywhere - * to store the full context back into. - */ - if ((ctx_size < sizeof(struct ucontext)) && - (current->thread.used_vsr && old_ctx)) - return -EINVAL; -#endif + /* Does the context have enough room to store VSX data? */ + if (ctx_size >= sizeof(struct ucontext)) + ctx_has_vsx_region = 1; #else /* Context size is for future use. Right now, we only make sure * we are passed something we understand @@ -985,17 +991,17 @@ long sys_swapcontext(struct ucontext __user *old_ctx, */ mctx = (struct mcontext __user *) ((unsigned long) &old_ctx->uc_mcontext & ~0xfUL); - if (!access_ok(VERIFY_WRITE, old_ctx, sizeof(*old_ctx)) - || save_user_regs(regs, mctx, 0) + if (!access_ok(VERIFY_WRITE, old_ctx, ctx_size) + || save_user_regs(regs, mctx, 0, ctx_has_vsx_region) || put_sigset_t(&old_ctx->uc_sigmask, ¤t->blocked) || __put_user(to_user_ptr(mctx), &old_ctx->uc_regs)) return -EFAULT; } if (new_ctx == NULL) return 0; - if (!access_ok(VERIFY_READ, new_ctx, sizeof(*new_ctx)) + if (!access_ok(VERIFY_READ, new_ctx, ctx_size) || __get_user(tmp, (u8 __user *) new_ctx) - || __get_user(tmp, (u8 __user *) (new_ctx + 1) - 1)) + || __get_user(tmp, (u8 __user *) new_ctx + ctx_size - 1)) return -EFAULT; /* @@ -1196,11 +1202,11 @@ int handle_signal32(unsigned long sig, struct k_sigaction *ka, goto badframe; if (vdso32_sigtramp && current->mm->context.vdso_base) { - if (save_user_regs(regs, &frame->mctx, 0)) + if (save_user_regs(regs, &frame->mctx, 0, 1)) goto badframe; regs->link = current->mm->context.vdso_base + vdso32_sigtramp; } else { - if (save_user_regs(regs, &frame->mctx, __NR_sigreturn)) + if (save_user_regs(regs, &frame->mctx, __NR_sigreturn, 1)) goto badframe; regs->link = (unsigned long) frame->mctx.tramp; } diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 65ad925c3a8..e132891d3ce 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -74,7 +74,8 @@ static const char fmt64[] = KERN_INFO \ */ static long setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs, - int signr, sigset_t *set, unsigned long handler) + int signr, sigset_t *set, unsigned long handler, + int ctx_has_vsx_region) { /* When CONFIG_ALTIVEC is set, we _always_ setup v_regs even if the * process never used altivec yet (MSR_VEC is zero in pt_regs of @@ -121,7 +122,7 @@ static long setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs, * then out to userspace. Update v_regs to point after the * VMX data. */ - if (current->thread.used_vsr) { + if (current->thread.used_vsr && ctx_has_vsx_region) { __giveup_vsx(current); v_regs += ELF_NVRREG; err |= copy_vsx_to_user(v_regs, current); @@ -235,8 +236,6 @@ static long restore_sigcontext(struct pt_regs *regs, sigset_t *set, int sig, else for (i = 0; i < 32 ; i++) current->thread.fpr[i][TS_VSRLOWOFFSET] = 0; - -#else #endif return err; } @@ -284,9 +283,10 @@ int sys_swapcontext(struct ucontext __user *old_ctx, unsigned char tmp; sigset_t set; unsigned long new_msr = 0; + int ctx_has_vsx_region = 0; if (new_ctx && - __get_user(new_msr, &new_ctx->uc_mcontext.gp_regs[PT_MSR])) + get_user(new_msr, &new_ctx->uc_mcontext.gp_regs[PT_MSR])) return -EFAULT; /* * Check that the context is not smaller than the original @@ -301,28 +301,23 @@ int sys_swapcontext(struct ucontext __user *old_ctx, if ((ctx_size < sizeof(struct ucontext)) && (new_msr & MSR_VSX)) return -EINVAL; -#ifdef CONFIG_VSX - /* - * If userspace doesn't provide enough room for VSX data, - * but current thread has used VSX, we don't have anywhere - * to store the full context back into. - */ - if ((ctx_size < sizeof(struct ucontext)) && - (current->thread.used_vsr && old_ctx)) - return -EINVAL; -#endif + /* Does the context have enough room to store VSX data? */ + if (ctx_size >= sizeof(struct ucontext)) + ctx_has_vsx_region = 1; + if (old_ctx != NULL) { - if (!access_ok(VERIFY_WRITE, old_ctx, sizeof(*old_ctx)) - || setup_sigcontext(&old_ctx->uc_mcontext, regs, 0, NULL, 0) + if (!access_ok(VERIFY_WRITE, old_ctx, ctx_size) + || setup_sigcontext(&old_ctx->uc_mcontext, regs, 0, NULL, 0, + ctx_has_vsx_region) || __copy_to_user(&old_ctx->uc_sigmask, ¤t->blocked, sizeof(sigset_t))) return -EFAULT; } if (new_ctx == NULL) return 0; - if (!access_ok(VERIFY_READ, new_ctx, sizeof(*new_ctx)) + if (!access_ok(VERIFY_READ, new_ctx, ctx_size) || __get_user(tmp, (u8 __user *) new_ctx) - || __get_user(tmp, (u8 __user *) (new_ctx + 1) - 1)) + || __get_user(tmp, (u8 __user *) new_ctx + ctx_size - 1)) return -EFAULT; /* @@ -425,7 +420,7 @@ int handle_rt_signal64(int signr, struct k_sigaction *ka, siginfo_t *info, &frame->uc.uc_stack.ss_flags); err |= __put_user(current->sas_ss_size, &frame->uc.uc_stack.ss_size); err |= setup_sigcontext(&frame->uc.uc_mcontext, regs, signr, NULL, - (unsigned long)ka->sa.sa_handler); + (unsigned long)ka->sa.sa_handler, 1); err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); if (err) goto badframe; diff --git a/arch/powerpc/kernel/smp-tbsync.c b/arch/powerpc/kernel/smp-tbsync.c index bc892e69b4f..a5e54526403 100644 --- a/arch/powerpc/kernel/smp-tbsync.c +++ b/arch/powerpc/kernel/smp-tbsync.c @@ -113,7 +113,7 @@ void __devinit smp_generic_give_timebase(void) { int i, score, score2, old, min=0, max=5000, offset=1000; - printk("Synchronizing timebase\n"); + pr_debug("Software timebase sync\n"); /* if this fails then this kernel won't work anyway... */ tbsync = kzalloc( sizeof(*tbsync), GFP_KERNEL ); @@ -123,13 +123,13 @@ void __devinit smp_generic_give_timebase(void) while (!tbsync->ack) barrier(); - printk("Got ack\n"); + pr_debug("Got ack\n"); /* binary search */ for (old = -1; old != offset ; offset = (min+max) / 2) { score = start_contest(kSetAndTest, offset, NUM_ITER); - printk("score %d, offset %d\n", score, offset ); + pr_debug("score %d, offset %d\n", score, offset ); if( score > 0 ) max = offset; @@ -140,8 +140,8 @@ void __devinit smp_generic_give_timebase(void) score = start_contest(kSetAndTest, min, NUM_ITER); score2 = start_contest(kSetAndTest, max, NUM_ITER); - printk("Min %d (score %d), Max %d (score %d)\n", - min, score, max, score2); + pr_debug("Min %d (score %d), Max %d (score %d)\n", + min, score, max, score2); score = abs(score); score2 = abs(score2); offset = (score < score2) ? min : max; @@ -155,7 +155,7 @@ void __devinit smp_generic_give_timebase(void) if (score2 <= score || score2 < 20) break; } - printk("Final offset: %d (%d/%d)\n", offset, score2, NUM_ITER ); + pr_debug("Final offset: %d (%d/%d)\n", offset, score2, NUM_ITER ); /* exiting */ tbsync->cmd = kExit; diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index c27b10a1bd7..8ac3f721d23 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -57,7 +57,6 @@ #define DBG(fmt...) #endif -int smp_hw_index[NR_CPUS]; struct thread_info *secondary_ti; cpumask_t cpu_possible_map = CPU_MASK_NONE; @@ -101,8 +100,7 @@ void smp_message_recv(int msg) generic_smp_call_function_interrupt(); break; case PPC_MSG_RESCHEDULE: - /* XXX Do we have to do this? */ - set_need_resched(); + /* we notice need_resched on exit */ break; case PPC_MSG_CALL_FUNC_SINGLE: generic_smp_call_function_single_interrupt(); @@ -124,6 +122,65 @@ void smp_message_recv(int msg) } } +static irqreturn_t call_function_action(int irq, void *data) +{ + generic_smp_call_function_interrupt(); + return IRQ_HANDLED; +} + +static irqreturn_t reschedule_action(int irq, void *data) +{ + /* we just need the return path side effect of checking need_resched */ + return IRQ_HANDLED; +} + +static irqreturn_t call_function_single_action(int irq, void *data) +{ + generic_smp_call_function_single_interrupt(); + return IRQ_HANDLED; +} + +static irqreturn_t debug_ipi_action(int irq, void *data) +{ + smp_message_recv(PPC_MSG_DEBUGGER_BREAK); + return IRQ_HANDLED; +} + +static irq_handler_t smp_ipi_action[] = { + [PPC_MSG_CALL_FUNCTION] = call_function_action, + [PPC_MSG_RESCHEDULE] = reschedule_action, + [PPC_MSG_CALL_FUNC_SINGLE] = call_function_single_action, + [PPC_MSG_DEBUGGER_BREAK] = debug_ipi_action, +}; + +const char *smp_ipi_name[] = { + [PPC_MSG_CALL_FUNCTION] = "ipi call function", + [PPC_MSG_RESCHEDULE] = "ipi reschedule", + [PPC_MSG_CALL_FUNC_SINGLE] = "ipi call function single", + [PPC_MSG_DEBUGGER_BREAK] = "ipi debugger", +}; + +/* optional function to request ipi, for controllers with >= 4 ipis */ +int smp_request_message_ipi(int virq, int msg) +{ + int err; + + if (msg < 0 || msg > PPC_MSG_DEBUGGER_BREAK) { + return -EINVAL; + } +#if !defined(CONFIG_DEBUGGER) && !defined(CONFIG_KEXEC) + if (msg == PPC_MSG_DEBUGGER_BREAK) { + return 1; + } +#endif + err = request_irq(virq, smp_ipi_action[msg], IRQF_DISABLED|IRQF_PERCPU, + smp_ipi_name[msg], 0); + WARN(err < 0, "unable to request_irq %d for %s (rc %d)\n", + virq, smp_ipi_name[msg], err); + + return err; +} + void smp_send_reschedule(int cpu) { if (likely(smp_ops)) @@ -409,8 +466,7 @@ out: static struct device_node *cpu_to_l2cache(int cpu) { struct device_node *np; - const phandle *php; - phandle ph; + struct device_node *cache; if (!cpu_present(cpu)) return NULL; @@ -419,13 +475,11 @@ static struct device_node *cpu_to_l2cache(int cpu) if (np == NULL) return NULL; - php = of_get_property(np, "l2-cache", NULL); - if (php == NULL) - return NULL; - ph = *php; + cache = of_find_next_cache_node(np); + of_node_put(np); - return of_find_node_by_phandle(ph); + return cache; } /* Activate a secondary processor. */ diff --git a/arch/powerpc/kernel/swsusp.c b/arch/powerpc/kernel/swsusp.c index 77b7b34b595..560c9611950 100644 --- a/arch/powerpc/kernel/swsusp.c +++ b/arch/powerpc/kernel/swsusp.c @@ -34,6 +34,6 @@ void save_processor_state(void) void restore_processor_state(void) { #ifdef CONFIG_PPC32 - set_context(current->active_mm->context.id, current->active_mm->pgd); + switch_mmu_context(NULL, current->active_mm); #endif } diff --git a/arch/powerpc/kernel/swsusp_32.S b/arch/powerpc/kernel/swsusp_32.S index 77fc76607ab..b47d8ceffb5 100644 --- a/arch/powerpc/kernel/swsusp_32.S +++ b/arch/powerpc/kernel/swsusp_32.S @@ -5,7 +5,7 @@ #include <asm/thread_info.h> #include <asm/ppc_asm.h> #include <asm/asm-offsets.h> - +#include <asm/mmu.h> /* * Structure for storing CPU registers on the save area. @@ -279,7 +279,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) mtibatl 3,r4 #endif -BEGIN_FTR_SECTION +BEGIN_MMU_FTR_SECTION li r4,0 mtspr SPRN_DBAT4U,r4 mtspr SPRN_DBAT4L,r4 @@ -297,7 +297,7 @@ BEGIN_FTR_SECTION mtspr SPRN_IBAT6L,r4 mtspr SPRN_IBAT7U,r4 mtspr SPRN_IBAT7L,r4 -END_FTR_SECTION_IFSET(CPU_FTR_HAS_HIGH_BATS) +END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS) /* Flush all TLBs */ lis r4,0x1000 diff --git a/arch/powerpc/kernel/swsusp_asm64.S b/arch/powerpc/kernel/swsusp_asm64.S index e092c3cbdb9..86ac1d90d02 100644 --- a/arch/powerpc/kernel/swsusp_asm64.S +++ b/arch/powerpc/kernel/swsusp_asm64.S @@ -133,7 +133,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) cmpdi r12,0 beq- nothing_to_copy - li r15,512 + li r15,PAGE_SIZE>>3 copyloop: ld r13,pbe_address(r12) ld r14,pbe_orig_address(r12) diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c index d98634c7606..bb1cfcfdbbb 100644 --- a/arch/powerpc/kernel/sys_ppc32.c +++ b/arch/powerpc/kernel/sys_ppc32.c @@ -61,42 +61,6 @@ asmlinkage long ppc32_select(u32 n, compat_ulong_t __user *inp, return compat_sys_select((int)n, inp, outp, exp, compat_ptr(tvp_x)); } -int cp_compat_stat(struct kstat *stat, struct compat_stat __user *statbuf) -{ - compat_ino_t ino; - long err; - - if (stat->size > MAX_NON_LFS || !new_valid_dev(stat->dev) || - !new_valid_dev(stat->rdev)) - return -EOVERFLOW; - - ino = stat->ino; - if (sizeof(ino) < sizeof(stat->ino) && ino != stat->ino) - return -EOVERFLOW; - - err = access_ok(VERIFY_WRITE, statbuf, sizeof(*statbuf)) ? 0 : -EFAULT; - err |= __put_user(new_encode_dev(stat->dev), &statbuf->st_dev); - err |= __put_user(ino, &statbuf->st_ino); - err |= __put_user(stat->mode, &statbuf->st_mode); - err |= __put_user(stat->nlink, &statbuf->st_nlink); - err |= __put_user(stat->uid, &statbuf->st_uid); - err |= __put_user(stat->gid, &statbuf->st_gid); - err |= __put_user(new_encode_dev(stat->rdev), &statbuf->st_rdev); - err |= __put_user(stat->size, &statbuf->st_size); - err |= __put_user(stat->atime.tv_sec, &statbuf->st_atime); - err |= __put_user(stat->atime.tv_nsec, &statbuf->st_atime_nsec); - err |= __put_user(stat->mtime.tv_sec, &statbuf->st_mtime); - err |= __put_user(stat->mtime.tv_nsec, &statbuf->st_mtime_nsec); - err |= __put_user(stat->ctime.tv_sec, &statbuf->st_ctime); - err |= __put_user(stat->ctime.tv_nsec, &statbuf->st_ctime_nsec); - err |= __put_user(stat->blksize, &statbuf->st_blksize); - err |= __put_user(stat->blocks, &statbuf->st_blocks); - err |= __put_user(0, &statbuf->__unused4[0]); - err |= __put_user(0, &statbuf->__unused4[1]); - - return err; -} - /* Note: it is necessary to treat option as an unsigned int, * with the corresponding cast to a signed int to insure that the * proper conversion (sign extension) between the register representation of a signed int (msr in 32-bit mode) @@ -107,77 +71,6 @@ asmlinkage long compat_sys_sysfs(u32 option, u32 arg1, u32 arg2) return sys_sysfs((int)option, arg1, arg2); } -asmlinkage long compat_sys_pause(void) -{ - current->state = TASK_INTERRUPTIBLE; - schedule(); - - return -ERESTARTNOHAND; -} - -static inline long get_ts32(struct timespec *o, struct compat_timeval __user *i) -{ - long usec; - - if (!access_ok(VERIFY_READ, i, sizeof(*i))) - return -EFAULT; - if (__get_user(o->tv_sec, &i->tv_sec)) - return -EFAULT; - if (__get_user(usec, &i->tv_usec)) - return -EFAULT; - o->tv_nsec = usec * 1000; - return 0; -} - -static inline long put_tv32(struct compat_timeval __user *o, struct timeval *i) -{ - return (!access_ok(VERIFY_WRITE, o, sizeof(*o)) || - (__put_user(i->tv_sec, &o->tv_sec) | - __put_user(i->tv_usec, &o->tv_usec))); -} - - - - -/* Translations due to time_t size differences. Which affects all - sorts of things, like timeval and itimerval. */ -extern struct timezone sys_tz; - -asmlinkage long compat_sys_gettimeofday(struct compat_timeval __user *tv, struct timezone __user *tz) -{ - if (tv) { - struct timeval ktv; - do_gettimeofday(&ktv); - if (put_tv32(tv, &ktv)) - return -EFAULT; - } - if (tz) { - if (copy_to_user(tz, &sys_tz, sizeof(sys_tz))) - return -EFAULT; - } - - return 0; -} - - - -asmlinkage long compat_sys_settimeofday(struct compat_timeval __user *tv, struct timezone __user *tz) -{ - struct timespec kts; - struct timezone ktz; - - if (tv) { - if (get_ts32(&kts, tv)) - return -EFAULT; - } - if (tz) { - if (copy_from_user(&ktz, tz, sizeof(ktz))) - return -EFAULT; - } - - return do_sys_settimeofday(tv ? &kts : NULL, tz ? &ktz : NULL); -} - #ifdef CONFIG_SYSVIPC long compat_sys_ipc(u32 call, u32 first, u32 second, u32 third, compat_uptr_t ptr, u32 fifth) diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index 56d172d16e5..0c64f10087b 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -15,18 +15,24 @@ #include <asm/firmware.h> #include <asm/hvcall.h> #include <asm/prom.h> -#include <asm/paca.h> -#include <asm/lppaca.h> #include <asm/machdep.h> #include <asm/smp.h> +#ifdef CONFIG_PPC64 +#include <asm/paca.h> +#include <asm/lppaca.h> +#endif + static DEFINE_PER_CPU(struct cpu, cpu_devices); static DEFINE_PER_CPU(struct kobject *, cache_toplevel); -/* SMT stuff */ +/* + * SMT snooze delay stuff, 64-bit only for now + */ + +#ifdef CONFIG_PPC64 -#ifdef CONFIG_PPC_MULTIPLATFORM /* Time in microseconds we delay before sleeping in the idle loop */ DEFINE_PER_CPU(unsigned long, smt_snooze_delay) = { 100 }; @@ -106,7 +112,7 @@ static int __init setup_smt_snooze_delay(char *str) } __setup("smt-snooze-delay=", setup_smt_snooze_delay); -#endif /* CONFIG_PPC_MULTIPLATFORM */ +#endif /* CONFIG_PPC64 */ /* * Enabling PMCs will slow partition context switch times so we only do @@ -115,7 +121,7 @@ __setup("smt-snooze-delay=", setup_smt_snooze_delay); static DEFINE_PER_CPU(char, pmcs_enabled); -void ppc64_enable_pmcs(void) +void ppc_enable_pmcs(void) { /* Only need to enable them once */ if (__get_cpu_var(pmcs_enabled)) @@ -126,8 +132,9 @@ void ppc64_enable_pmcs(void) if (ppc_md.enable_pmcs) ppc_md.enable_pmcs(); } -EXPORT_SYMBOL(ppc64_enable_pmcs); +EXPORT_SYMBOL(ppc_enable_pmcs); +#if defined(CONFIG_6xx) || defined(CONFIG_PPC64) /* XXX convert to rusty's on_one_cpu */ static unsigned long run_on_cpu(unsigned long cpu, unsigned long (*func)(unsigned long), @@ -146,6 +153,7 @@ static unsigned long run_on_cpu(unsigned long cpu, return ret; } +#endif #define SYSFS_PMCSETUP(NAME, ADDRESS) \ static unsigned long read_##NAME(unsigned long junk) \ @@ -154,7 +162,7 @@ static unsigned long read_##NAME(unsigned long junk) \ } \ static unsigned long write_##NAME(unsigned long val) \ { \ - ppc64_enable_pmcs(); \ + ppc_enable_pmcs(); \ mtspr(ADDRESS, val); \ return 0; \ } \ @@ -184,28 +192,53 @@ static ssize_t __used \ * that are implemented on the current processor */ +#if defined(CONFIG_PPC64) +#define HAS_PPC_PMC_CLASSIC 1 +#define HAS_PPC_PMC_IBM 1 +#define HAS_PPC_PMC_PA6T 1 +#elif defined(CONFIG_6xx) +#define HAS_PPC_PMC_CLASSIC 1 +#define HAS_PPC_PMC_IBM 1 +#define HAS_PPC_PMC_G4 1 +#endif + + +#ifdef HAS_PPC_PMC_CLASSIC SYSFS_PMCSETUP(mmcr0, SPRN_MMCR0); SYSFS_PMCSETUP(mmcr1, SPRN_MMCR1); -SYSFS_PMCSETUP(mmcra, SPRN_MMCRA); SYSFS_PMCSETUP(pmc1, SPRN_PMC1); SYSFS_PMCSETUP(pmc2, SPRN_PMC2); SYSFS_PMCSETUP(pmc3, SPRN_PMC3); SYSFS_PMCSETUP(pmc4, SPRN_PMC4); SYSFS_PMCSETUP(pmc5, SPRN_PMC5); SYSFS_PMCSETUP(pmc6, SPRN_PMC6); + +#ifdef HAS_PPC_PMC_G4 +SYSFS_PMCSETUP(mmcr2, SPRN_MMCR2); +#endif + +#ifdef CONFIG_PPC64 SYSFS_PMCSETUP(pmc7, SPRN_PMC7); SYSFS_PMCSETUP(pmc8, SPRN_PMC8); + +SYSFS_PMCSETUP(mmcra, SPRN_MMCRA); SYSFS_PMCSETUP(purr, SPRN_PURR); SYSFS_PMCSETUP(spurr, SPRN_SPURR); SYSFS_PMCSETUP(dscr, SPRN_DSCR); +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); +#endif /* CONFIG_PPC64 */ + +#ifdef HAS_PPC_PMC_PA6T SYSFS_PMCSETUP(pa6t_pmc0, SPRN_PA6T_PMC0); SYSFS_PMCSETUP(pa6t_pmc1, SPRN_PA6T_PMC1); SYSFS_PMCSETUP(pa6t_pmc2, SPRN_PA6T_PMC2); SYSFS_PMCSETUP(pa6t_pmc3, SPRN_PA6T_PMC3); SYSFS_PMCSETUP(pa6t_pmc4, SPRN_PA6T_PMC4); SYSFS_PMCSETUP(pa6t_pmc5, SPRN_PA6T_PMC5); - #ifdef CONFIG_DEBUG_KERNEL SYSFS_PMCSETUP(hid0, SPRN_HID0); SYSFS_PMCSETUP(hid1, SPRN_HID1); @@ -236,28 +269,37 @@ SYSFS_PMCSETUP(tsr1, SPRN_PA6T_TSR1); SYSFS_PMCSETUP(tsr2, SPRN_PA6T_TSR2); SYSFS_PMCSETUP(tsr3, SPRN_PA6T_TSR3); #endif /* CONFIG_DEBUG_KERNEL */ +#endif /* HAS_PPC_PMC_PA6T */ -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); - +#ifdef HAS_PPC_PMC_IBM static struct sysdev_attribute ibm_common_attrs[] = { _SYSDEV_ATTR(mmcr0, 0600, show_mmcr0, store_mmcr0), _SYSDEV_ATTR(mmcr1, 0600, show_mmcr1, store_mmcr1), }; +#endif /* HAS_PPC_PMC_G4 */ + +#ifdef HAS_PPC_PMC_G4 +static struct sysdev_attribute g4_common_attrs[] = { + _SYSDEV_ATTR(mmcr0, 0600, show_mmcr0, store_mmcr0), + _SYSDEV_ATTR(mmcr1, 0600, show_mmcr1, store_mmcr1), + _SYSDEV_ATTR(mmcr2, 0600, show_mmcr2, store_mmcr2), +}; +#endif /* HAS_PPC_PMC_G4 */ -static struct sysdev_attribute ibm_pmc_attrs[] = { +static struct sysdev_attribute classic_pmc_attrs[] = { _SYSDEV_ATTR(pmc1, 0600, show_pmc1, store_pmc1), _SYSDEV_ATTR(pmc2, 0600, show_pmc2, store_pmc2), _SYSDEV_ATTR(pmc3, 0600, show_pmc3, store_pmc3), _SYSDEV_ATTR(pmc4, 0600, show_pmc4, store_pmc4), _SYSDEV_ATTR(pmc5, 0600, show_pmc5, store_pmc5), _SYSDEV_ATTR(pmc6, 0600, show_pmc6, store_pmc6), +#ifdef CONFIG_PPC64 _SYSDEV_ATTR(pmc7, 0600, show_pmc7, store_pmc7), _SYSDEV_ATTR(pmc8, 0600, show_pmc8, store_pmc8), +#endif }; +#ifdef HAS_PPC_PMC_PA6T static struct sysdev_attribute pa6t_attrs[] = { _SYSDEV_ATTR(mmcr0, 0600, show_mmcr0, store_mmcr0), _SYSDEV_ATTR(mmcr1, 0600, show_mmcr1, store_mmcr1), @@ -298,6 +340,8 @@ static struct sysdev_attribute pa6t_attrs[] = { _SYSDEV_ATTR(tsr3, 0600, show_tsr3, store_tsr3), #endif /* CONFIG_DEBUG_KERNEL */ }; +#endif /* HAS_PPC_PMC_PA6T */ +#endif /* HAS_PPC_PMC_CLASSIC */ struct cache_desc { struct kobject kobj; @@ -522,7 +566,6 @@ static bool cache_is_unified(struct device_node *np) static struct cache_desc * __cpuinit create_cache_index_info(struct device_node *np, struct kobject *parent, int index, int level) { - const phandle *next_cache_phandle; struct device_node *next_cache; struct cache_desc *new, **end; @@ -547,11 +590,7 @@ static struct cache_desc * __cpuinit create_cache_index_info(struct device_node while (*end) end = &(*end)->next; - next_cache_phandle = of_get_property(np, "l2-cache", NULL); - if (!next_cache_phandle) - goto out; - - next_cache = of_find_node_by_phandle(*next_cache_phandle); + next_cache = of_find_next_cache_node(np); if (!next_cache) goto out; @@ -588,23 +627,36 @@ static void __cpuinit register_cpu_online(unsigned int cpu) struct sysdev_attribute *attrs, *pmc_attrs; int i, nattrs; +#ifdef CONFIG_PPC64 if (!firmware_has_feature(FW_FEATURE_ISERIES) && cpu_has_feature(CPU_FTR_SMT)) sysdev_create_file(s, &attr_smt_snooze_delay); +#endif /* PMC stuff */ switch (cur_cpu_spec->pmc_type) { +#ifdef HAS_PPC_PMC_IBM case PPC_PMC_IBM: attrs = ibm_common_attrs; nattrs = sizeof(ibm_common_attrs) / sizeof(struct sysdev_attribute); - pmc_attrs = ibm_pmc_attrs; + pmc_attrs = classic_pmc_attrs; + break; +#endif /* HAS_PPC_PMC_IBM */ +#ifdef HAS_PPC_PMC_G4 + case PPC_PMC_G4: + attrs = g4_common_attrs; + nattrs = sizeof(g4_common_attrs) / sizeof(struct sysdev_attribute); + pmc_attrs = classic_pmc_attrs; break; +#endif /* HAS_PPC_PMC_G4 */ +#ifdef HAS_PPC_PMC_PA6T case PPC_PMC_PA6T: /* PA Semi starts counting at PMC0 */ attrs = pa6t_attrs; nattrs = sizeof(pa6t_attrs) / sizeof(struct sysdev_attribute); pmc_attrs = NULL; break; +#endif /* HAS_PPC_PMC_PA6T */ default: attrs = NULL; nattrs = 0; @@ -618,6 +670,7 @@ static void __cpuinit register_cpu_online(unsigned int cpu) for (i = 0; i < cur_cpu_spec->num_pmcs; i++) sysdev_create_file(s, &pmc_attrs[i]); +#ifdef CONFIG_PPC64 if (cpu_has_feature(CPU_FTR_MMCRA)) sysdev_create_file(s, &attr_mmcra); @@ -629,6 +682,7 @@ static void __cpuinit register_cpu_online(unsigned int cpu) if (cpu_has_feature(CPU_FTR_DSCR)) sysdev_create_file(s, &attr_dscr); +#endif /* CONFIG_PPC64 */ create_cache_info(s); } @@ -641,16 +695,9 @@ static void remove_cache_info(struct sys_device *sysdev) int cpu = sysdev->id; cache_desc = per_cpu(cache_desc, cpu); - if (cache_desc != NULL) { - sysfs_remove_file(&cache_desc->kobj, &cache_size_attr.attr); - sysfs_remove_file(&cache_desc->kobj, &cache_line_size_attr.attr); - sysfs_remove_file(&cache_desc->kobj, &cache_type_attr.attr); - sysfs_remove_file(&cache_desc->kobj, &cache_level_attr.attr); - sysfs_remove_file(&cache_desc->kobj, &cache_nr_sets_attr.attr); - sysfs_remove_file(&cache_desc->kobj, &cache_assoc_attr.attr); - + if (cache_desc != NULL) kobject_put(&cache_desc->kobj); - } + cache_toplevel = per_cpu(cache_toplevel, cpu); if (cache_toplevel != NULL) kobject_put(cache_toplevel); @@ -665,23 +712,36 @@ static void unregister_cpu_online(unsigned int cpu) BUG_ON(!c->hotpluggable); +#ifdef CONFIG_PPC64 if (!firmware_has_feature(FW_FEATURE_ISERIES) && cpu_has_feature(CPU_FTR_SMT)) sysdev_remove_file(s, &attr_smt_snooze_delay); +#endif /* PMC stuff */ switch (cur_cpu_spec->pmc_type) { +#ifdef HAS_PPC_PMC_IBM case PPC_PMC_IBM: attrs = ibm_common_attrs; nattrs = sizeof(ibm_common_attrs) / sizeof(struct sysdev_attribute); - pmc_attrs = ibm_pmc_attrs; + pmc_attrs = classic_pmc_attrs; + break; +#endif /* HAS_PPC_PMC_IBM */ +#ifdef HAS_PPC_PMC_G4 + case PPC_PMC_G4: + attrs = g4_common_attrs; + nattrs = sizeof(g4_common_attrs) / sizeof(struct sysdev_attribute); + pmc_attrs = classic_pmc_attrs; break; +#endif /* HAS_PPC_PMC_G4 */ +#ifdef HAS_PPC_PMC_PA6T case PPC_PMC_PA6T: /* PA Semi starts counting at PMC0 */ attrs = pa6t_attrs; nattrs = sizeof(pa6t_attrs) / sizeof(struct sysdev_attribute); pmc_attrs = NULL; break; +#endif /* HAS_PPC_PMC_PA6T */ default: attrs = NULL; nattrs = 0; @@ -695,6 +755,7 @@ static void unregister_cpu_online(unsigned int cpu) for (i = 0; i < cur_cpu_spec->num_pmcs; i++) sysdev_remove_file(s, &pmc_attrs[i]); +#ifdef CONFIG_PPC64 if (cpu_has_feature(CPU_FTR_MMCRA)) sysdev_remove_file(s, &attr_mmcra); @@ -706,6 +767,7 @@ static void unregister_cpu_online(unsigned int cpu) if (cpu_has_feature(CPU_FTR_DSCR)) sysdev_remove_file(s, &attr_dscr); +#endif /* CONFIG_PPC64 */ remove_cache_info(s); } diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index e2ee66b5831..e1f3a514042 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -164,8 +164,6 @@ static u64 tb_to_ns_scale __read_mostly; static unsigned tb_to_ns_shift __read_mostly; static unsigned long boot_tb __read_mostly; -static struct gettimeofday_struct do_gtod; - extern struct timezone sys_tz; static long timezone_offset; @@ -415,31 +413,9 @@ void udelay(unsigned long usecs) } EXPORT_SYMBOL(udelay); - -/* - * There are two copies of tb_to_xs and stamp_xsec so that no - * lock is needed to access and use these values in - * do_gettimeofday. We alternate the copies and as long as a - * reasonable time elapses between changes, there will never - * be inconsistent values. ntpd has a minimum of one minute - * between updates. - */ static inline void update_gtod(u64 new_tb_stamp, u64 new_stamp_xsec, u64 new_tb_to_xs) { - unsigned temp_idx; - struct gettimeofday_vars *temp_varp; - - temp_idx = (do_gtod.var_idx == 0); - temp_varp = &do_gtod.vars[temp_idx]; - - temp_varp->tb_to_xs = new_tb_to_xs; - temp_varp->tb_orig_stamp = new_tb_stamp; - temp_varp->stamp_xsec = new_stamp_xsec; - smp_mb(); - do_gtod.varp = temp_varp; - do_gtod.var_idx = temp_idx; - /* * tb_update_count is used to allow the userspace gettimeofday code * to assure itself that it sees a consistent view of the tb_to_xs and @@ -456,6 +432,7 @@ static inline void update_gtod(u64 new_tb_stamp, u64 new_stamp_xsec, vdso_data->tb_to_xs = new_tb_to_xs; vdso_data->wtom_clock_sec = wall_to_monotonic.tv_sec; vdso_data->wtom_clock_nsec = wall_to_monotonic.tv_nsec; + vdso_data->stamp_xtime = xtime; smp_wmb(); ++(vdso_data->tb_update_count); } @@ -514,9 +491,7 @@ static int __init iSeries_tb_recal(void) tb_ticks_per_sec = new_tb_ticks_per_sec; calc_cputime_factors(); div128_by_32( XSEC_PER_SEC, 0, tb_ticks_per_sec, &divres ); - do_gtod.tb_ticks_per_sec = tb_ticks_per_sec; tb_to_xs = divres.result_low; - do_gtod.varp->tb_to_xs = tb_to_xs; vdso_data->tb_ticks_per_sec = tb_ticks_per_sec; vdso_data->tb_to_xs = tb_to_xs; } @@ -988,15 +963,6 @@ void __init time_init(void) sys_tz.tz_dsttime = 0; } - do_gtod.varp = &do_gtod.vars[0]; - do_gtod.var_idx = 0; - do_gtod.varp->tb_orig_stamp = tb_last_jiffy; - __get_cpu_var(last_jiffy) = tb_last_jiffy; - do_gtod.varp->stamp_xsec = (u64) xtime.tv_sec * XSEC_PER_SEC; - do_gtod.tb_ticks_per_sec = tb_ticks_per_sec; - do_gtod.varp->tb_to_xs = tb_to_xs; - do_gtod.tb_to_us = tb_to_us; - vdso_data->tb_orig_stamp = tb_last_jiffy; vdso_data->tb_update_count = 0; vdso_data->tb_ticks_per_sec = tb_ticks_per_sec; diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index f5def6cf5cd..5457e957568 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -1160,37 +1160,85 @@ void CacheLockingException(struct pt_regs *regs, unsigned long address, #ifdef CONFIG_SPE void SPEFloatingPointException(struct pt_regs *regs) { + extern int do_spe_mathemu(struct pt_regs *regs); unsigned long spefscr; int fpexc_mode; int code = 0; + int err; + + preempt_disable(); + if (regs->msr & MSR_SPE) + giveup_spe(current); + preempt_enable(); spefscr = current->thread.spefscr; fpexc_mode = current->thread.fpexc_mode; - /* Hardware does not neccessarily set sticky - * underflow/overflow/invalid flags */ if ((spefscr & SPEFSCR_FOVF) && (fpexc_mode & PR_FP_EXC_OVF)) { code = FPE_FLTOVF; - spefscr |= SPEFSCR_FOVFS; } else if ((spefscr & SPEFSCR_FUNF) && (fpexc_mode & PR_FP_EXC_UND)) { code = FPE_FLTUND; - spefscr |= SPEFSCR_FUNFS; } else if ((spefscr & SPEFSCR_FDBZ) && (fpexc_mode & PR_FP_EXC_DIV)) code = FPE_FLTDIV; else if ((spefscr & SPEFSCR_FINV) && (fpexc_mode & PR_FP_EXC_INV)) { code = FPE_FLTINV; - spefscr |= SPEFSCR_FINVS; } else if ((spefscr & (SPEFSCR_FG | SPEFSCR_FX)) && (fpexc_mode & PR_FP_EXC_RES)) code = FPE_FLTRES; - current->thread.spefscr = spefscr; + err = do_spe_mathemu(regs); + if (err == 0) { + regs->nip += 4; /* skip emulated instruction */ + emulate_single_step(regs); + return; + } + + if (err == -EFAULT) { + /* got an error reading the instruction */ + _exception(SIGSEGV, regs, SEGV_ACCERR, regs->nip); + } else if (err == -EINVAL) { + /* didn't recognize the instruction */ + printk(KERN_ERR "unrecognized spe instruction " + "in %s at %lx\n", current->comm, regs->nip); + } else { + _exception(SIGFPE, regs, code, regs->nip); + } - _exception(SIGFPE, regs, code, regs->nip); return; } + +void SPEFloatingPointRoundException(struct pt_regs *regs) +{ + extern int speround_handler(struct pt_regs *regs); + int err; + + preempt_disable(); + if (regs->msr & MSR_SPE) + giveup_spe(current); + preempt_enable(); + + regs->nip -= 4; + err = speround_handler(regs); + if (err == 0) { + regs->nip += 4; /* skip emulated instruction */ + emulate_single_step(regs); + return; + } + + if (err == -EFAULT) { + /* got an error reading the instruction */ + _exception(SIGSEGV, regs, SEGV_ACCERR, regs->nip); + } else if (err == -EINVAL) { + /* didn't recognize the instruction */ + printk(KERN_ERR "unrecognized spe instruction " + "in %s at %lx\n", current->comm, regs->nip); + } else { + _exception(SIGFPE, regs, 0, regs->nip); + return; + } +} #endif /* diff --git a/arch/powerpc/kernel/udbg_16550.c b/arch/powerpc/kernel/udbg_16550.c index cb01ebc5938..7b7da8cfd5e 100644 --- a/arch/powerpc/kernel/udbg_16550.c +++ b/arch/powerpc/kernel/udbg_16550.c @@ -142,7 +142,7 @@ unsigned int udbg_probe_uart_speed(void __iomem *comport, unsigned int clock) speed = (clock / prescaler) / (divisor * 16); /* sanity check */ - if (speed < 0 || speed > (clock / 16)) + if (speed > (clock / 16)) speed = 9600; return speed; diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index 65639a43e64..ad06d5c75b1 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -184,8 +184,7 @@ static void dump_vdso_pages(struct vm_area_struct * vma) * This is called from binfmt_elf, we create the special vma for the * vDSO and insert it into the mm struct tree */ -int arch_setup_additional_pages(struct linux_binprm *bprm, - int executable_stack) +int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) { struct mm_struct *mm = current->mm; struct page **vdso_pagelist; @@ -567,6 +566,11 @@ static __init int vdso_fixup_features(struct lib32_elfinfo *v32, do_feature_fixups(cur_cpu_spec->cpu_features, start64, start64 + size64); + start64 = find_section64(v64->hdr, "__mmu_ftr_fixup", &size64); + if (start64) + do_feature_fixups(cur_cpu_spec->mmu_features, + start64, start64 + size64); + start64 = find_section64(v64->hdr, "__fw_ftr_fixup", &size64); if (start64) do_feature_fixups(powerpc_firmware_features, @@ -583,6 +587,11 @@ static __init int vdso_fixup_features(struct lib32_elfinfo *v32, do_feature_fixups(cur_cpu_spec->cpu_features, start32, start32 + size32); + start32 = find_section32(v32->hdr, "__mmu_ftr_fixup", &size32); + if (start32) + do_feature_fixups(cur_cpu_spec->mmu_features, + start32, start32 + size32); + #ifdef CONFIG_PPC64 start32 = find_section32(v32->hdr, "__fw_ftr_fixup", &size32); if (start32) diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S index 72ca26df457..ee038d4bf25 100644 --- a/arch/powerpc/kernel/vdso32/gettimeofday.S +++ b/arch/powerpc/kernel/vdso32/gettimeofday.S @@ -16,6 +16,13 @@ #include <asm/asm-offsets.h> #include <asm/unistd.h> +/* Offset for the low 32-bit part of a field of long type */ +#ifdef CONFIG_PPC64 +#define LOPART 4 +#else +#define LOPART 0 +#endif + .text /* * Exact prototype of gettimeofday @@ -90,101 +97,53 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime) mflr r12 /* r12 saves lr */ .cfi_register lr,r12 - mr r10,r3 /* r10 saves id */ mr r11,r4 /* r11 saves tp */ bl __get_datapage@local /* get data page */ mr r9,r3 /* datapage ptr in r9 */ - beq cr1,50f /* if monotonic -> jump there */ - - /* - * CLOCK_REALTIME - */ - - bl __do_get_xsec@local /* get xsec from tb & kernel */ - bne- 98f /* out of line -> do syscall */ - - /* seconds are xsec >> 20 */ - rlwinm r5,r4,12,20,31 - rlwimi r5,r3,12,0,19 - stw r5,TSPC32_TV_SEC(r11) - /* get remaining xsec and convert to nsec. we scale - * up remaining xsec by 12 bits and get the top 32 bits - * of the multiplication, then we multiply by 1000 - */ - rlwinm r5,r4,12,0,19 - lis r6,1000000@h - ori r6,r6,1000000@l - mulhwu r5,r5,r6 - mulli r5,r5,1000 - stw r5,TSPC32_TV_NSEC(r11) - mtlr r12 - crclr cr0*4+so - li r3,0 - blr +50: bl __do_get_tspec@local /* get sec/nsec from tb & kernel */ + bne cr1,80f /* not monotonic -> all done */ /* * CLOCK_MONOTONIC */ -50: bl __do_get_xsec@local /* get xsec from tb & kernel */ - bne- 98f /* out of line -> do syscall */ - - /* seconds are xsec >> 20 */ - rlwinm r6,r4,12,20,31 - rlwimi r6,r3,12,0,19 - - /* get remaining xsec and convert to nsec. we scale - * up remaining xsec by 12 bits and get the top 32 bits - * of the multiplication, then we multiply by 1000 - */ - rlwinm r7,r4,12,0,19 - lis r5,1000000@h - ori r5,r5,1000000@l - mulhwu r7,r7,r5 - mulli r7,r7,1000 - /* now we must fixup using wall to monotonic. We need to snapshot * that value and do the counter trick again. Fortunately, we still * have the counter value in r8 that was returned by __do_get_xsec. - * At this point, r6,r7 contain our sec/nsec values, r3,r4 and r5 - * can be used + * At this point, r3,r4 contain our sec/nsec values, r5 and r6 + * can be used, r7 contains NSEC_PER_SEC. */ - lwz r3,WTOM_CLOCK_SEC(r9) - lwz r4,WTOM_CLOCK_NSEC(r9) + lwz r5,WTOM_CLOCK_SEC(r9) + lwz r6,WTOM_CLOCK_NSEC(r9) - /* We now have our result in r3,r4. We create a fake dependency - * on that result and re-check the counter + /* We now have our offset in r5,r6. We create a fake dependency + * on that value and re-check the counter */ - or r5,r4,r3 - xor r0,r5,r5 + or r0,r6,r5 + xor r0,r0,r0 add r9,r9,r0 -#ifdef CONFIG_PPC64 - lwz r0,(CFG_TB_UPDATE_COUNT+4)(r9) -#else - lwz r0,(CFG_TB_UPDATE_COUNT)(r9) -#endif + lwz r0,(CFG_TB_UPDATE_COUNT+LOPART)(r9) cmpl cr0,r8,r0 /* check if updated */ bne- 50b - /* Calculate and store result. Note that this mimmics the C code, + /* Calculate and store result. Note that this mimics the C code, * which may cause funny results if nsec goes negative... is that * possible at all ? */ - add r3,r3,r6 - add r4,r4,r7 - lis r5,NSEC_PER_SEC@h - ori r5,r5,NSEC_PER_SEC@l - cmpl cr0,r4,r5 - cmpli cr1,r4,0 + add r3,r3,r5 + add r4,r4,r6 + cmpw cr0,r4,r7 + cmpwi cr1,r4,0 blt 1f - subf r4,r5,r4 + subf r4,r7,r4 addi r3,r3,1 -1: bge cr1,1f +1: bge cr1,80f addi r3,r3,-1 - add r4,r4,r5 -1: stw r3,TSPC32_TV_SEC(r11) + add r4,r4,r7 + +80: stw r3,TSPC32_TV_SEC(r11) stw r4,TSPC32_TV_NSEC(r11) mtlr r12 @@ -195,10 +154,6 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime) /* * syscall fallback */ -98: - mtlr r12 - mr r3,r10 - mr r4,r11 99: li r0,__NR_clock_gettime sc @@ -254,11 +209,7 @@ __do_get_xsec: /* Check for update count & load values. We use the low * order 32 bits of the update count */ -#ifdef CONFIG_PPC64 -1: lwz r8,(CFG_TB_UPDATE_COUNT+4)(r9) -#else -1: lwz r8,(CFG_TB_UPDATE_COUNT)(r9) -#endif +1: lwz r8,(CFG_TB_UPDATE_COUNT+LOPART)(r9) andi. r0,r8,1 /* pending update ? loop */ bne- 1b xor r0,r8,r8 /* create dependency */ @@ -305,11 +256,7 @@ __do_get_xsec: or r6,r4,r3 xor r0,r6,r6 add r9,r9,r0 -#ifdef CONFIG_PPC64 - lwz r0,(CFG_TB_UPDATE_COUNT+4)(r9) -#else - lwz r0,(CFG_TB_UPDATE_COUNT)(r9) -#endif + lwz r0,(CFG_TB_UPDATE_COUNT+LOPART)(r9) cmpl cr0,r8,r0 /* check if updated */ bne- 1b @@ -322,3 +269,98 @@ __do_get_xsec: */ 3: blr .cfi_endproc + +/* + * This is the core of clock_gettime(), it returns the current + * time in seconds and nanoseconds in r3 and r4. + * It expects the datapage ptr in r9 and doesn't clobber it. + * It clobbers r0, r5, r6, r10 and returns NSEC_PER_SEC in r7. + * On return, r8 contains the counter value that can be reused. + * This clobbers cr0 but not any other cr field. + */ +__do_get_tspec: + .cfi_startproc + /* Check for update count & load values. We use the low + * order 32 bits of the update count + */ +1: lwz r8,(CFG_TB_UPDATE_COUNT+LOPART)(r9) + andi. r0,r8,1 /* pending update ? loop */ + bne- 1b + xor r0,r8,r8 /* create dependency */ + add r9,r9,r0 + + /* Load orig stamp (offset to TB) */ + lwz r5,CFG_TB_ORIG_STAMP(r9) + lwz r6,(CFG_TB_ORIG_STAMP+4)(r9) + + /* Get a stable TB value */ +2: mftbu r3 + mftbl r4 + mftbu r0 + cmpl cr0,r3,r0 + bne- 2b + + /* Subtract tb orig stamp and shift left 12 bits. + */ + subfc r7,r6,r4 + subfe r0,r5,r3 + slwi r0,r0,12 + rlwimi. r0,r7,12,20,31 + slwi r7,r7,12 + + /* Load scale factor & do multiplication */ + lwz r5,CFG_TB_TO_XS(r9) /* load values */ + lwz r6,(CFG_TB_TO_XS+4)(r9) + mulhwu r3,r7,r6 + mullw r10,r7,r5 + mulhwu r4,r7,r5 + addc r10,r3,r10 + li r3,0 + + beq+ 4f /* skip high part computation if 0 */ + mulhwu r3,r0,r5 + mullw r7,r0,r5 + mulhwu r5,r0,r6 + mullw r6,r0,r6 + adde r4,r4,r7 + addze r3,r3 + addc r4,r4,r5 + addze r3,r3 + addc r10,r10,r6 + +4: addze r4,r4 /* add in carry */ + lis r7,NSEC_PER_SEC@h + ori r7,r7,NSEC_PER_SEC@l + mulhwu r4,r4,r7 /* convert to nanoseconds */ + + /* At this point, we have seconds & nanoseconds since the xtime + * stamp in r3+CA and r4. Load & add the xtime stamp. + */ +#ifdef CONFIG_PPC64 + lwz r5,STAMP_XTIME+TSPC64_TV_SEC+LOPART(r9) + lwz r6,STAMP_XTIME+TSPC64_TV_NSEC+LOPART(r9) +#else + lwz r5,STAMP_XTIME+TSPC32_TV_SEC(r9) + lwz r6,STAMP_XTIME+TSPC32_TV_NSEC(r9) +#endif + add r4,r4,r6 + adde r3,r3,r5 + + /* We now have our result in r3,r4. We create a fake dependency + * on that result and re-check the counter + */ + or r6,r4,r3 + xor r0,r6,r6 + add r9,r9,r0 + lwz r0,(CFG_TB_UPDATE_COUNT+LOPART)(r9) + cmpl cr0,r8,r0 /* check if updated */ + bne- 1b + + /* check for nanosecond overflow and adjust if necessary */ + cmpw r4,r7 + bltlr /* all done if no overflow */ + subf r4,r7,r4 /* adjust if overflow */ + addi r3,r3,1 + + blr + .cfi_endproc diff --git a/arch/powerpc/kernel/vdso32/vdso32.lds.S b/arch/powerpc/kernel/vdso32/vdso32.lds.S index be3b6a41dc0..904ef1360dd 100644 --- a/arch/powerpc/kernel/vdso32/vdso32.lds.S +++ b/arch/powerpc/kernel/vdso32/vdso32.lds.S @@ -34,6 +34,9 @@ SECTIONS __ftr_fixup : { *(__ftr_fixup) } . = ALIGN(8); + __mmu_ftr_fixup : { *(__mmu_ftr_fixup) } + + . = ALIGN(8); __lwsync_fixup : { *(__lwsync_fixup) } #ifdef CONFIG_PPC64 diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S index c6401f9e37f..262cd5857a5 100644 --- a/arch/powerpc/kernel/vdso64/gettimeofday.S +++ b/arch/powerpc/kernel/vdso64/gettimeofday.S @@ -75,90 +75,49 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime) mflr r12 /* r12 saves lr */ .cfi_register lr,r12 - mr r10,r3 /* r10 saves id */ mr r11,r4 /* r11 saves tp */ bl V_LOCAL_FUNC(__get_datapage) /* get data page */ - beq cr1,50f /* if monotonic -> jump there */ - - /* - * CLOCK_REALTIME - */ - - bl V_LOCAL_FUNC(__do_get_xsec) /* get xsec from tb & kernel */ - - lis r7,15 /* r7 = 1000000 = USEC_PER_SEC */ - ori r7,r7,16960 - rldicl r5,r4,44,20 /* r5 = sec = xsec / XSEC_PER_SEC */ - rldicr r6,r5,20,43 /* r6 = sec * XSEC_PER_SEC */ - std r5,TSPC64_TV_SEC(r11) /* store sec in tv */ - subf r0,r6,r4 /* r0 = xsec = (xsec - r6) */ - mulld r0,r0,r7 /* usec = (xsec * USEC_PER_SEC) / - * XSEC_PER_SEC - */ - rldicl r0,r0,44,20 - mulli r0,r0,1000 /* nsec = usec * 1000 */ - std r0,TSPC64_TV_NSEC(r11) /* store nsec in tp */ - - mtlr r12 - crclr cr0*4+so - li r3,0 - blr +50: bl V_LOCAL_FUNC(__do_get_tspec) /* get time from tb & kernel */ + bne cr1,80f /* if not monotonic, all done */ /* * CLOCK_MONOTONIC */ -50: bl V_LOCAL_FUNC(__do_get_xsec) /* get xsec from tb & kernel */ - - lis r7,15 /* r7 = 1000000 = USEC_PER_SEC */ - ori r7,r7,16960 - rldicl r5,r4,44,20 /* r5 = sec = xsec / XSEC_PER_SEC */ - rldicr r6,r5,20,43 /* r6 = sec * XSEC_PER_SEC */ - subf r0,r6,r4 /* r0 = xsec = (xsec - r6) */ - mulld r0,r0,r7 /* usec = (xsec * USEC_PER_SEC) / - * XSEC_PER_SEC - */ - rldicl r6,r0,44,20 - mulli r6,r6,1000 /* nsec = usec * 1000 */ - /* now we must fixup using wall to monotonic. We need to snapshot * that value and do the counter trick again. Fortunately, we still - * have the counter value in r8 that was returned by __do_get_xsec. - * At this point, r5,r6 contain our sec/nsec values. - * can be used + * have the counter value in r8 that was returned by __do_get_tspec. + * At this point, r4,r5 contain our sec/nsec values. */ - lwa r4,WTOM_CLOCK_SEC(r3) - lwa r7,WTOM_CLOCK_NSEC(r3) + lwa r6,WTOM_CLOCK_SEC(r3) + lwa r9,WTOM_CLOCK_NSEC(r3) - /* We now have our result in r4,r7. We create a fake dependency + /* We now have our result in r6,r9. We create a fake dependency * on that result and re-check the counter */ - or r9,r4,r7 - xor r0,r9,r9 + or r0,r6,r9 + xor r0,r0,r0 add r3,r3,r0 ld r0,CFG_TB_UPDATE_COUNT(r3) cmpld cr0,r0,r8 /* check if updated */ bne- 50b - /* Calculate and store result. Note that this mimmics the C code, - * which may cause funny results if nsec goes negative... is that - * possible at all ? + /* Add wall->monotonic offset and check for overflow or underflow. */ - add r4,r4,r5 - add r7,r7,r6 - lis r9,NSEC_PER_SEC@h - ori r9,r9,NSEC_PER_SEC@l - cmpl cr0,r7,r9 - cmpli cr1,r7,0 + add r4,r4,r6 + add r5,r5,r9 + cmpd cr0,r5,r7 + cmpdi cr1,r5,0 blt 1f - subf r7,r9,r7 + subf r5,r7,r5 addi r4,r4,1 -1: bge cr1,1f +1: bge cr1,80f addi r4,r4,-1 - add r7,r7,r9 -1: std r4,TSPC64_TV_SEC(r11) - std r7,TSPC64_TV_NSEC(r11) + add r5,r5,r7 + +80: std r4,TSPC64_TV_SEC(r11) + std r5,TSPC64_TV_NSEC(r11) mtlr r12 crclr cr0*4+so @@ -168,10 +127,6 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime) /* * syscall fallback */ -98: - mtlr r12 - mr r3,r10 - mr r4,r11 99: li r0,__NR_clock_gettime sc @@ -253,3 +208,59 @@ V_FUNCTION_BEGIN(__do_get_xsec) blr .cfi_endproc V_FUNCTION_END(__do_get_xsec) + +/* + * This is the core of clock_gettime(), it returns the current + * time in seconds and nanoseconds in r4 and r5. + * It expects the datapage ptr in r3 and doesn't clobber it. + * It clobbers r0 and r6 and returns NSEC_PER_SEC in r7. + * On return, r8 contains the counter value that can be reused. + * This clobbers cr0 but not any other cr field. + */ +V_FUNCTION_BEGIN(__do_get_tspec) + .cfi_startproc + /* check for update count & load values */ +1: ld r8,CFG_TB_UPDATE_COUNT(r3) + andi. r0,r8,1 /* pending update ? loop */ + bne- 1b + xor r0,r8,r8 /* create dependency */ + add r3,r3,r0 + + /* Get TB & offset it. We use the MFTB macro which will generate + * workaround code for Cell. + */ + MFTB(r7) + ld r9,CFG_TB_ORIG_STAMP(r3) + subf r7,r9,r7 + + /* Scale result */ + ld r5,CFG_TB_TO_XS(r3) + sldi r7,r7,12 /* compute time since stamp_xtime */ + mulhdu r6,r7,r5 /* in units of 2^-32 seconds */ + + /* Add stamp since epoch */ + ld r4,STAMP_XTIME+TSPC64_TV_SEC(r3) + ld r5,STAMP_XTIME+TSPC64_TV_NSEC(r3) + or r0,r4,r5 + or r0,r0,r6 + xor r0,r0,r0 + add r3,r3,r0 + ld r0,CFG_TB_UPDATE_COUNT(r3) + cmpld r0,r8 /* check if updated */ + bne- 1b /* reload if so */ + + /* convert to seconds & nanoseconds and add to stamp */ + lis r7,NSEC_PER_SEC@h + ori r7,r7,NSEC_PER_SEC@l + mulhwu r0,r6,r7 /* compute nanoseconds and */ + srdi r6,r6,32 /* seconds since stamp_xtime */ + clrldi r0,r0,32 + add r5,r5,r0 /* add nanoseconds together */ + cmpd r5,r7 /* overflow? */ + add r4,r4,r6 + bltlr /* all done if no overflow */ + subf r5,r7,r5 /* if overflow, adjust */ + addi r4,r4,1 + blr + .cfi_endproc +V_FUNCTION_END(__do_get_tspec) diff --git a/arch/powerpc/kernel/vdso64/vdso64.lds.S b/arch/powerpc/kernel/vdso64/vdso64.lds.S index d0b2526dd38..0e615404e24 100644 --- a/arch/powerpc/kernel/vdso64/vdso64.lds.S +++ b/arch/powerpc/kernel/vdso64/vdso64.lds.S @@ -35,6 +35,9 @@ SECTIONS __ftr_fixup : { *(__ftr_fixup) } . = ALIGN(8); + __mmu_ftr_fixup : { *(__mmu_ftr_fixup) } + + . = ALIGN(8); __lwsync_fixup : { *(__lwsync_fixup) } . = ALIGN(8); diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c index 2750fbab197..94aa7b011b2 100644 --- a/arch/powerpc/kernel/vio.c +++ b/arch/powerpc/kernel/vio.c @@ -41,9 +41,9 @@ static struct bus_type vio_bus_type; static struct vio_dev vio_bus_device = { /* fake "parent" device */ - .name = vio_bus_device.dev.bus_id, + .name = "vio", .type = "", - .dev.bus_id = "vio", + .dev.init_name = "vio", .dev.bus = &vio_bus_type, }; @@ -516,10 +516,10 @@ static void vio_dma_iommu_free_coherent(struct device *dev, size_t size, vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE)); } -static dma_addr_t vio_dma_iommu_map_single(struct device *dev, void *vaddr, - size_t size, - enum dma_data_direction direction, - struct dma_attrs *attrs) +static dma_addr_t vio_dma_iommu_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, + enum dma_data_direction direction, + struct dma_attrs *attrs) { struct vio_dev *viodev = to_vio_dev(dev); dma_addr_t ret = DMA_ERROR_CODE; @@ -529,7 +529,7 @@ static dma_addr_t vio_dma_iommu_map_single(struct device *dev, void *vaddr, return ret; } - ret = dma_iommu_ops.map_single(dev, vaddr, size, direction, attrs); + ret = dma_iommu_ops.map_page(dev, page, offset, size, direction, attrs); if (unlikely(dma_mapping_error(dev, ret))) { vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE)); atomic_inc(&viodev->cmo.allocs_failed); @@ -538,14 +538,14 @@ static dma_addr_t vio_dma_iommu_map_single(struct device *dev, void *vaddr, return ret; } -static void vio_dma_iommu_unmap_single(struct device *dev, - dma_addr_t dma_handle, size_t size, - enum dma_data_direction direction, - struct dma_attrs *attrs) +static void vio_dma_iommu_unmap_page(struct device *dev, dma_addr_t dma_handle, + size_t size, + enum dma_data_direction direction, + struct dma_attrs *attrs) { struct vio_dev *viodev = to_vio_dev(dev); - dma_iommu_ops.unmap_single(dev, dma_handle, size, direction, attrs); + dma_iommu_ops.unmap_page(dev, dma_handle, size, direction, attrs); vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE)); } @@ -603,10 +603,11 @@ static void vio_dma_iommu_unmap_sg(struct device *dev, struct dma_mapping_ops vio_dma_mapping_ops = { .alloc_coherent = vio_dma_iommu_alloc_coherent, .free_coherent = vio_dma_iommu_free_coherent, - .map_single = vio_dma_iommu_map_single, - .unmap_single = vio_dma_iommu_unmap_single, .map_sg = vio_dma_iommu_map_sg, .unmap_sg = vio_dma_iommu_unmap_sg, + .map_page = vio_dma_iommu_map_page, + .unmap_page = vio_dma_iommu_unmap_page, + }; /** @@ -1215,7 +1216,7 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node) viodev->irq = irq_of_parse_and_map(of_node, 0); - snprintf(viodev->dev.bus_id, BUS_ID_SIZE, "%x", *unit_address); + dev_set_name(&viodev->dev, "%x", *unit_address); viodev->name = of_node->name; viodev->type = of_node->type; viodev->unit_address = *unit_address; @@ -1232,7 +1233,7 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node) else viodev->dev.archdata.dma_ops = &dma_iommu_ops; viodev->dev.archdata.dma_data = vio_build_iommu_table(viodev); - viodev->dev.archdata.numa_node = of_node_to_nid(of_node); + set_dev_node(&viodev->dev, of_node_to_nid(of_node)); /* init generic 'struct device' fields: */ viodev->dev.parent = &vio_bus_device.dev; @@ -1242,7 +1243,7 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node) /* register with generic device framework */ if (device_register(&viodev->dev)) { printk(KERN_ERR "%s: failed to register device %s\n", - __func__, viodev->dev.bus_id); + __func__, dev_name(&viodev->dev)); /* XXX free TCE table */ kfree(viodev); return NULL; @@ -1399,13 +1400,13 @@ static struct vio_dev *vio_find_name(const char *name) struct vio_dev *vio_find_node(struct device_node *vnode) { const uint32_t *unit_address; - char kobj_name[BUS_ID_SIZE]; + char kobj_name[20]; /* construct the kobject name from the device node */ unit_address = of_get_property(vnode, "reg", NULL); if (!unit_address) return NULL; - snprintf(kobj_name, BUS_ID_SIZE, "%x", *unit_address); + snprintf(kobj_name, sizeof(kobj_name), "%x", *unit_address); return vio_find_name(kobj_name); } diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 9f6c1ca1739..47bf15cd2c9 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -152,6 +152,12 @@ SECTIONS __stop___ftr_fixup = .; } . = ALIGN(8); + __mmu_ftr_fixup : AT(ADDR(__mmu_ftr_fixup) - LOAD_OFFSET) { + __start___mmu_ftr_fixup = .; + *(__mmu_ftr_fixup) + __stop___mmu_ftr_fixup = .; + } + . = ALIGN(8); __lwsync_fixup : AT(ADDR(__lwsync_fixup) - LOAD_OFFSET) { __start___lwsync_fixup = .; *(__lwsync_fixup) @@ -187,6 +193,23 @@ SECTIONS *(.machine.desc) __machine_desc_end = . ; } +#ifdef CONFIG_RELOCATABLE + . = ALIGN(8); + .dynsym : AT(ADDR(.dynsym) - LOAD_OFFSET) { *(.dynsym) } + .dynstr : AT(ADDR(.dynstr) - LOAD_OFFSET) { *(.dynstr) } + .dynamic : AT(ADDR(.dynamic) - LOAD_OFFSET) + { + __dynamic_start = .; + *(.dynamic) + } + .hash : AT(ADDR(.hash) - LOAD_OFFSET) { *(.hash) } + .interp : AT(ADDR(.interp) - LOAD_OFFSET) { *(.interp) } + .rela.dyn : AT(ADDR(.rela.dyn) - LOAD_OFFSET) + { + __rela_dyn_start = .; + *(.rela*) + } +#endif /* freed after init ends here */ . = ALIGN(PAGE_SIZE); |