diff options
Diffstat (limited to 'arch/powerpc/kernel')
160 files changed, 5910 insertions, 5835 deletions
diff --git a/arch/powerpc/kernel/fsl_booke_entry_mapping.S b/arch/powerpc/kernel/85xx_entry_mapping.S index dedc17fac8f8..dedc17fac8f8 100644 --- a/arch/powerpc/kernel/fsl_booke_entry_mapping.S +++ b/arch/powerpc/kernel/85xx_entry_mapping.S diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 5fa68c2ef1f8..9b6146056e48 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -11,6 +11,7 @@ CFLAGS_prom_init.o += -fPIC CFLAGS_btext.o += -fPIC endif +CFLAGS_early_32.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) CFLAGS_cputable.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) CFLAGS_prom_init.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) CFLAGS_btext.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) @@ -19,6 +20,7 @@ CFLAGS_prom.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) CFLAGS_prom_init.o += -fno-stack-protector CFLAGS_prom_init.o += -DDISABLE_BRANCH_PROFILING CFLAGS_prom_init.o += -ffreestanding +CFLAGS_prom_init.o += $(call cc-option, -ftrivial-auto-var-init=uninitialized) ifdef CONFIG_FUNCTION_TRACER # Do not trace early boot code @@ -32,6 +34,19 @@ KASAN_SANITIZE_early_32.o := n KASAN_SANITIZE_cputable.o := n KASAN_SANITIZE_prom_init.o := n KASAN_SANITIZE_btext.o := n +KASAN_SANITIZE_paca.o := n +KASAN_SANITIZE_setup_64.o := n +KASAN_SANITIZE_mce.o := n +KASAN_SANITIZE_mce_power.o := n +KASAN_SANITIZE_udbg.o := n +KASAN_SANITIZE_udbg_16550.o := n + +# we have to be particularly careful in ppc64 to exclude code that +# runs with translations off, as we cannot access the shadow with +# translations off. However, ppc32 can sanitize this. +ifdef CONFIG_PPC64 +KASAN_SANITIZE_traps.o := n +endif ifdef CONFIG_KASAN CFLAGS_early_32.o += -DDISABLE_BRANCH_PROFILING @@ -39,6 +54,13 @@ CFLAGS_cputable.o += -DDISABLE_BRANCH_PROFILING CFLAGS_btext.o += -DDISABLE_BRANCH_PROFILING endif +#ifdef CONFIG_RANDOMIZE_KSTACK_OFFSET +# Remove stack protector to avoid triggering unneeded stack canary +# checks due to randomize_kstack_offset. +CFLAGS_REMOVE_syscall.o = -fstack-protector -fstack-protector-strong +CFLAGS_syscall.o += -fno-stack-protector +#endif + obj-y := cputable.o syscalls.o \ irq.o align.o signal_$(BITS).o pmc.o vdso.o \ process.o systbl.o idle.o \ @@ -47,10 +69,11 @@ obj-y := cputable.o syscalls.o \ udbg.o misc.o io.o misc_$(BITS).o \ of_platform.o prom_parse.o firmware.o \ hw_breakpoint_constraints.o interrupt.o \ - kdebugfs.o + kdebugfs.o stacktrace.o syscall.o obj-y += ptrace/ -obj-$(CONFIG_PPC64) += setup_64.o \ +obj-$(CONFIG_PPC64) += setup_64.o irq_64.o\ paca.o nvram_64.o note.o +obj-$(CONFIG_PPC32) += sys_ppc32.o obj-$(CONFIG_COMPAT) += sys_ppc32.o signal_32.o obj-$(CONFIG_VDSO32) += vdso32_wrapper.o obj-$(CONFIG_PPC_WATCHDOG) += watchdog.o @@ -59,7 +82,7 @@ obj-$(CONFIG_PPC_DAWR) += dawr.o obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_ppc970.o cpu_setup_pa6t.o obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_power.o obj-$(CONFIG_PPC_BOOK3S_64) += mce.o mce_power.o -obj-$(CONFIG_PPC_BOOK3E_64) += exceptions-64e.o idle_book3e.o +obj-$(CONFIG_PPC_BOOK3E_64) += exceptions-64e.o idle_64e.o obj-$(CONFIG_PPC_BARRIER_NOSPEC) += security.o obj-$(CONFIG_PPC64) += vdso64_wrapper.o obj-$(CONFIG_ALTIVEC) += vecemu.o @@ -67,7 +90,7 @@ obj-$(CONFIG_PPC_BOOK3S_IDLE) += idle_book3s.o procfs-y := proc_powerpc.o obj-$(CONFIG_PROC_FS) += $(procfs-y) rtaspci-$(CONFIG_PPC64)-$(CONFIG_PCI) := rtas_pci.o -obj-$(CONFIG_PPC_RTAS) += rtas.o rtas-rtc.o $(rtaspci-y-y) +obj-$(CONFIG_PPC_RTAS) += rtas_entry.o rtas.o rtas-rtc.o $(rtaspci-y-y) obj-$(CONFIG_PPC_RTAS_DAEMON) += rtasd.o obj-$(CONFIG_RTAS_FLASH) += rtas_flash.o obj-$(CONFIG_RTAS_PROC) += rtas-proc.o @@ -78,30 +101,28 @@ obj-$(CONFIG_GENERIC_TBSYNC) += smp-tbsync.o obj-$(CONFIG_CRASH_DUMP) += crash_dump.o obj-$(CONFIG_FA_DUMP) += fadump.o obj-$(CONFIG_PRESERVE_FA_DUMP) += fadump.o -ifdef CONFIG_PPC32 -obj-$(CONFIG_E500) += idle_e500.o -endif +obj-$(CONFIG_PPC_85xx) += idle_85xx.o obj-$(CONFIG_PPC_BOOK3S_32) += idle_6xx.o l2cr_6xx.o cpu_setup_6xx.o obj-$(CONFIG_TAU) += tau_6xx.o obj-$(CONFIG_HIBERNATION) += swsusp.o suspend.o -ifdef CONFIG_FSL_BOOKE -obj-$(CONFIG_HIBERNATION) += swsusp_booke.o +ifdef CONFIG_PPC_85xx +obj-$(CONFIG_HIBERNATION) += swsusp_85xx.o else obj-$(CONFIG_HIBERNATION) += swsusp_$(BITS).o endif obj64-$(CONFIG_HIBERNATION) += swsusp_asm64.o obj-$(CONFIG_MODULES) += module.o module_$(BITS).o obj-$(CONFIG_44x) += cpu_setup_44x.o -obj-$(CONFIG_PPC_FSL_BOOK3E) += cpu_setup_fsl_booke.o +obj-$(CONFIG_PPC_E500) += cpu_setup_e500.o obj-$(CONFIG_PPC_DOORBELL) += dbell.o obj-$(CONFIG_JUMP_LABEL) += jump_label.o -extra-$(CONFIG_PPC64) := head_64.o -extra-$(CONFIG_PPC_BOOK3S_32) := head_book3s_32.o -extra-$(CONFIG_40x) := head_40x.o -extra-$(CONFIG_44x) := head_44x.o -extra-$(CONFIG_FSL_BOOKE) := head_fsl_booke.o -extra-$(CONFIG_PPC_8xx) := head_8xx.o +obj-$(CONFIG_PPC64) += head_64.o +obj-$(CONFIG_PPC_BOOK3S_32) += head_book3s_32.o +obj-$(CONFIG_40x) += head_40x.o +obj-$(CONFIG_44x) += head_44x.o +obj-$(CONFIG_PPC_8xx) += head_8xx.o +obj-$(CONFIG_PPC_85xx) += head_85xx.o extra-y += vmlinux.lds obj-$(CONFIG_RELOCATABLE) += reloc_$(BITS).o @@ -116,7 +137,6 @@ obj-$(CONFIG_OPTPROBES) += optprobes.o optprobes_head.o obj-$(CONFIG_KPROBES_ON_FTRACE) += kprobes-ftrace.o obj-$(CONFIG_UPROBES) += uprobes.o obj-$(CONFIG_PPC_UDBG_16550) += legacy_serial.o udbg_16550.o -obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-$(CONFIG_SWIOTLB) += dma-swiotlb.o obj-$(CONFIG_ARCH_HAS_DMA_SET_MASK) += dma-mask.o @@ -177,10 +197,10 @@ KCOV_INSTRUMENT_paca.o := n CFLAGS_setup_64.o += -fno-stack-protector CFLAGS_paca.o += -fno-stack-protector -extra-$(CONFIG_PPC_FPU) += fpu.o -extra-$(CONFIG_ALTIVEC) += vector.o -extra-$(CONFIG_PPC64) += entry_64.o -extra-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE) += prom_init.o +obj-$(CONFIG_PPC_FPU) += fpu.o +obj-$(CONFIG_ALTIVEC) += vector.o +obj-$(CONFIG_PPC64) += entry_64.o +obj-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE) += prom_init.o extra-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE) += prom_init_check @@ -194,8 +214,8 @@ targets += prom_init_check clean-files := vmlinux.lds # Force dependency (incbin is bad) -$(obj)/vdso32_wrapper.o : $(obj)/vdso32/vdso32.so.dbg -$(obj)/vdso64_wrapper.o : $(obj)/vdso64/vdso64.so.dbg +$(obj)/vdso32_wrapper.o : $(obj)/vdso/vdso32.so.dbg +$(obj)/vdso64_wrapper.o : $(obj)/vdso/vdso64.so.dbg # for cleaning -subdir- += vdso32 vdso64 +subdir- += vdso diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c index bf96b954a4eb..3e37ece06739 100644 --- a/arch/powerpc/kernel/align.c +++ b/arch/powerpc/kernel/align.c @@ -105,7 +105,7 @@ static struct aligninfo spe_aligninfo[32] = { * so we don't need the address swizzling. */ static int emulate_spe(struct pt_regs *regs, unsigned int reg, - struct ppc_inst ppc_instr) + ppc_inst_t ppc_instr) { union { u64 ll; @@ -300,7 +300,7 @@ Efault_write: int fix_alignment(struct pt_regs *regs) { - struct ppc_inst instr; + ppc_inst_t instr; struct instruction_op op; int r, type; diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index cc05522f50bf..4ce2a4aa3985 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -54,12 +54,12 @@ #endif #ifdef CONFIG_PPC32 -#if defined(CONFIG_BOOKE) || defined(CONFIG_40x) +#ifdef CONFIG_BOOKE_OR_40x #include "head_booke.h" #endif #endif -#if defined(CONFIG_PPC_FSL_BOOK3E) +#if defined(CONFIG_PPC_E500) #include "../mm/mmu_decl.h" #endif @@ -94,7 +94,7 @@ int main(void) OFFSET(TASK_CPU, task_struct, thread_info.cpu); #endif -#ifdef CONFIG_LIVEPATCH +#ifdef CONFIG_LIVEPATCH_64 OFFSET(TI_livepatch_sp, thread_info, livepatch_sp); #endif @@ -139,6 +139,7 @@ int main(void) OFFSET(THR11, thread_struct, r11); OFFSET(THLR, thread_struct, lr); OFFSET(THCTR, thread_struct, ctr); + OFFSET(THSR0, thread_struct, sr0); #endif #ifdef CONFIG_SPE OFFSET(THREAD_EVR0, thread_struct, evr[0]); @@ -196,7 +197,7 @@ int main(void) OFFSET(PACAIRQHAPPENED, paca_struct, irq_happened); OFFSET(PACA_FTRACE_ENABLED, paca_struct, ftrace_enabled); -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 OFFSET(PACAPGD, paca_struct, pgd); OFFSET(PACA_KERNELPGD, paca_struct, kernel_pgd); OFFSET(PACA_EXGEN, paca_struct, exgen); @@ -212,16 +213,18 @@ int main(void) OFFSET(TCD_ESEL_NEXT, tlb_core_data, esel_next); OFFSET(TCD_ESEL_MAX, tlb_core_data, esel_max); OFFSET(TCD_ESEL_FIRST, tlb_core_data, esel_first); -#endif /* CONFIG_PPC_BOOK3E */ +#endif /* CONFIG_PPC_BOOK3E_64 */ #ifdef CONFIG_PPC_BOOK3S_64 OFFSET(PACA_EXGEN, paca_struct, exgen); OFFSET(PACA_EXMC, paca_struct, exmc); OFFSET(PACA_EXNMI, paca_struct, exnmi); +#ifdef CONFIG_PPC_64S_HASH_MMU OFFSET(PACA_SLBSHADOWPTR, paca_struct, slb_shadow_ptr); OFFSET(SLBSHADOW_STACKVSID, slb_shadow, save_area[SLB_NUM_BOLTED - 1].vsid); OFFSET(SLBSHADOW_STACKESID, slb_shadow, save_area[SLB_NUM_BOLTED - 1].esid); OFFSET(SLBSHADOW_SAVEAREA, slb_shadow, save_area); +#endif OFFSET(LPPACA_PMCINUSE, lppaca, pmcregs_in_use); #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE OFFSET(PACA_PMCINUSE, paca_struct, pmcregs_in_use); @@ -245,7 +248,7 @@ int main(void) #ifdef CONFIG_PPC64 OFFSET(PACA_EXIT_SAVE_R1, paca_struct, exit_save_r1); #endif -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 OFFSET(PACA_TRAP_SAVE, paca_struct, trap_save); #endif OFFSET(PACA_SPRG_VDSO, paca_struct, sprg_vdso); @@ -376,7 +379,7 @@ int main(void) OFFSET(VCPU_SPRG2, kvm_vcpu, arch.shregs.sprg2); OFFSET(VCPU_SPRG3, kvm_vcpu, arch.shregs.sprg3); #endif -#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING +#ifdef CONFIG_KVM_BOOK3S_HV_P8_TIMING OFFSET(VCPU_TB_RMENTRY, kvm_vcpu, arch.rm_entry); OFFSET(VCPU_TB_RMINTR, kvm_vcpu, arch.rm_intr); OFFSET(VCPU_TB_RMEXIT, kvm_vcpu, arch.rm_exit); @@ -648,7 +651,7 @@ int main(void) DEFINE(PGD_T_LOG2, PGD_T_LOG2); DEFINE(PTE_T_LOG2, PTE_T_LOG2); #endif -#ifdef CONFIG_PPC_FSL_BOOK3E +#ifdef CONFIG_PPC_E500 DEFINE(TLBCAM_SIZE, sizeof(struct tlbcam)); OFFSET(TLBCAM_MAS0, tlbcam, MAS0); OFFSET(TLBCAM_MAS1, tlbcam, MAS1); diff --git a/arch/powerpc/kernel/btext.c b/arch/powerpc/kernel/btext.c index 803c2a45b22a..2769889219bf 100644 --- a/arch/powerpc/kernel/btext.c +++ b/arch/powerpc/kernel/btext.c @@ -10,9 +10,9 @@ #include <linux/export.h> #include <linux/memblock.h> #include <linux/pgtable.h> +#include <linux/of.h> #include <asm/sections.h> -#include <asm/prom.h> #include <asm/btext.h> #include <asm/page.h> #include <asm/mmu.h> @@ -45,8 +45,7 @@ unsigned long disp_BAT[2] __initdata = {0, 0}; static unsigned char vga_font[cmapsz]; -int boot_text_mapped __force_data = 0; -int force_printk_to_btext = 0; +static int boot_text_mapped __force_data; extern void rmci_on(void); extern void rmci_off(void); @@ -74,7 +73,7 @@ static inline void rmci_maybe_off(void) * the display during identify_machine() and MMU_Init() * * The display is mapped to virtual address 0xD0000000, rather - * than 1:1, because some some CHRP machines put the frame buffer + * than 1:1, because some CHRP machines put the frame buffer * in the region starting at 0xC0000000 (PAGE_OFFSET). * This mapping is temporary and will disappear as soon as the * setup done by MMU_Init() is applied. @@ -161,7 +160,7 @@ void btext_map(void) boot_text_mapped = 1; } -static int btext_initialize(struct device_node *np) +static int __init btext_initialize(struct device_node *np) { unsigned int width, height, depth, pitch; unsigned long address = 0; @@ -241,8 +240,10 @@ int __init btext_find_display(int allow_nonstdout) rc = btext_initialize(np); printk("result: %d\n", rc); } - if (rc == 0) + if (rc == 0) { + of_node_put(np); break; + } } return rc; } @@ -290,7 +291,7 @@ void btext_update_display(unsigned long phys, int width, int height, } EXPORT_SYMBOL(btext_update_display); -void btext_clearscreen(void) +void __init btext_clearscreen(void) { unsigned int *base = (unsigned int *)calc_base(0, 0); unsigned long width = ((dispDeviceRect[2] - dispDeviceRect[0]) * @@ -308,7 +309,7 @@ void btext_clearscreen(void) rmci_maybe_off(); } -void btext_flushscreen(void) +void __init btext_flushscreen(void) { unsigned int *base = (unsigned int *)calc_base(0, 0); unsigned long width = ((dispDeviceRect[2] - dispDeviceRect[0]) * @@ -327,7 +328,7 @@ void btext_flushscreen(void) __asm__ __volatile__ ("sync" ::: "memory"); } -void btext_flushline(void) +void __init btext_flushline(void) { unsigned int *base = (unsigned int *)calc_base(0, g_loc_Y << 4); unsigned long width = ((dispDeviceRect[2] - dispDeviceRect[0]) * @@ -542,7 +543,7 @@ void btext_drawstring(const char *c) btext_drawchar(*c++); } -void btext_drawtext(const char *c, unsigned int len) +void __init btext_drawtext(const char *c, unsigned int len) { if (!boot_text_mapped) return; @@ -550,7 +551,7 @@ void btext_drawtext(const char *c, unsigned int len) btext_drawchar(*c++); } -void btext_drawhex(unsigned long v) +void __init btext_drawhex(unsigned long v) { if (!boot_text_mapped) return; diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c index cf1be75b7833..f502337dd37d 100644 --- a/arch/powerpc/kernel/cacheinfo.c +++ b/arch/powerpc/kernel/cacheinfo.c @@ -18,7 +18,6 @@ #include <linux/of.h> #include <linux/percpu.h> #include <linux/slab.h> -#include <asm/prom.h> #include <asm/cputhreads.h> #include <asm/smp.h> @@ -710,7 +709,7 @@ static struct kobj_attribute cache_shared_cpu_list_attr = __ATTR(shared_cpu_list, 0444, shared_cpu_list_show, NULL); /* Attributes which should always be created -- the kobject/sysfs core - * does this automatically via kobj_type->default_attrs. This is the + * does this automatically via kobj_type->default_groups. This is the * minimum data required to uniquely identify a cache. */ static struct attribute *cache_index_default_attrs[] = { @@ -720,6 +719,7 @@ static struct attribute *cache_index_default_attrs[] = { &cache_shared_cpu_list_attr.attr, NULL, }; +ATTRIBUTE_GROUPS(cache_index_default); /* Attributes which should be created if the cache device node has the * right properties -- see cacheinfo_create_index_opt_attrs @@ -738,7 +738,7 @@ static const struct sysfs_ops cache_index_ops = { static struct kobj_type cache_index_type = { .release = cache_index_release, .sysfs_ops = &cache_index_ops, - .default_attrs = cache_index_default_attrs, + .default_groups = cache_index_default_groups, }; static void cacheinfo_create_index_opt_attrs(struct cache_index_dir *dir) diff --git a/arch/powerpc/kernel/cpu_setup_fsl_booke.S b/arch/powerpc/kernel/cpu_setup_e500.S index 4bf33f1b4193..2ab25161b0ad 100644 --- a/arch/powerpc/kernel/cpu_setup_fsl_booke.S +++ b/arch/powerpc/kernel/cpu_setup_e500.S @@ -12,7 +12,7 @@ #include <asm/processor.h> #include <asm/cputable.h> #include <asm/ppc_asm.h> -#include <asm/nohash/mmu-book3e.h> +#include <asm/nohash/mmu-e500.h> #include <asm/asm-offsets.h> #include <asm/mpc85xx.h> @@ -108,7 +108,7 @@ _GLOBAL(__setup_cpu_e6500) #endif /* CONFIG_PPC_E500MC */ #ifdef CONFIG_PPC32 -#ifdef CONFIG_E500 +#ifdef CONFIG_PPC_E500 #ifndef CONFIG_PPC_E500MC _GLOBAL(__setup_cpu_e500v1) _GLOBAL(__setup_cpu_e500v2) @@ -156,7 +156,7 @@ _GLOBAL(__setup_cpu_e5500) mtlr r5 blr #endif /* CONFIG_PPC_E500MC */ -#endif /* CONFIG_E500 */ +#endif /* CONFIG_PPC_E500 */ #endif /* CONFIG_PPC32 */ #ifdef CONFIG_PPC_BOOK3E_64 diff --git a/arch/powerpc/kernel/cpu_setup_power.c b/arch/powerpc/kernel/cpu_setup_power.c index 3cca88ee96d7..097c033668f0 100644 --- a/arch/powerpc/kernel/cpu_setup_power.c +++ b/arch/powerpc/kernel/cpu_setup_power.c @@ -11,7 +11,7 @@ #include <asm/synch.h> #include <linux/bitops.h> #include <asm/cputable.h> -#include <asm/cpu_setup_power.h> +#include <asm/cpu_setup.h> /* Disable CPU_FTR_HVMODE and return false if MSR:HV is not set */ static bool init_hvmode_206(struct cpu_spec *t) @@ -109,7 +109,7 @@ static void init_PMU_HV_ISA207(void) static void init_PMU(void) { mtspr(SPRN_MMCRA, 0); - mtspr(SPRN_MMCR0, 0); + mtspr(SPRN_MMCR0, MMCR0_FC); mtspr(SPRN_MMCR1, 0); mtspr(SPRN_MMCR2, 0); } @@ -123,7 +123,7 @@ static void init_PMU_ISA31(void) { mtspr(SPRN_MMCR3, 0); mtspr(SPRN_MMCRA, MMCRA_BHRB_DISABLE); - mtspr(SPRN_MMCR0, MMCR0_PMCCEXT); + mtspr(SPRN_MMCR0, MMCR0_FC | MMCR0_PMCCEXT); } /* @@ -137,6 +137,7 @@ void __setup_cpu_power7(unsigned long offset, struct cpu_spec *t) return; mtspr(SPRN_LPID, 0); + mtspr(SPRN_AMOR, ~0); mtspr(SPRN_PCR, PCR_MASK); init_LPCR_ISA206(mfspr(SPRN_LPCR), LPCR_LPES1 >> LPCR_LPES_SH); } @@ -150,6 +151,7 @@ void __restore_cpu_power7(void) return; mtspr(SPRN_LPID, 0); + mtspr(SPRN_AMOR, ~0); mtspr(SPRN_PCR, PCR_MASK); init_LPCR_ISA206(mfspr(SPRN_LPCR), LPCR_LPES1 >> LPCR_LPES_SH); } @@ -164,6 +166,7 @@ void __setup_cpu_power8(unsigned long offset, struct cpu_spec *t) return; mtspr(SPRN_LPID, 0); + mtspr(SPRN_AMOR, ~0); mtspr(SPRN_PCR, PCR_MASK); init_LPCR_ISA206(mfspr(SPRN_LPCR) | LPCR_PECEDH, 0); /* LPES = 0 */ init_HFSCR(); @@ -184,6 +187,7 @@ void __restore_cpu_power8(void) return; mtspr(SPRN_LPID, 0); + mtspr(SPRN_AMOR, ~0); mtspr(SPRN_PCR, PCR_MASK); init_LPCR_ISA206(mfspr(SPRN_LPCR) | LPCR_PECEDH, 0); /* LPES = 0 */ init_HFSCR(); @@ -202,6 +206,7 @@ void __setup_cpu_power9(unsigned long offset, struct cpu_spec *t) mtspr(SPRN_PSSCR, 0); mtspr(SPRN_LPID, 0); mtspr(SPRN_PID, 0); + mtspr(SPRN_AMOR, ~0); mtspr(SPRN_PCR, PCR_MASK); init_LPCR_ISA300((mfspr(SPRN_LPCR) | LPCR_PECEDH | LPCR_PECE_HVEE |\ LPCR_HVICE | LPCR_HEIC) & ~(LPCR_UPRT | LPCR_HR), 0); @@ -223,6 +228,7 @@ void __restore_cpu_power9(void) mtspr(SPRN_PSSCR, 0); mtspr(SPRN_LPID, 0); mtspr(SPRN_PID, 0); + mtspr(SPRN_AMOR, ~0); mtspr(SPRN_PCR, PCR_MASK); init_LPCR_ISA300((mfspr(SPRN_LPCR) | LPCR_PECEDH | LPCR_PECE_HVEE |\ LPCR_HVICE | LPCR_HEIC) & ~(LPCR_UPRT | LPCR_HR), 0); @@ -242,6 +248,7 @@ void __setup_cpu_power10(unsigned long offset, struct cpu_spec *t) mtspr(SPRN_PSSCR, 0); mtspr(SPRN_LPID, 0); mtspr(SPRN_PID, 0); + mtspr(SPRN_AMOR, ~0); mtspr(SPRN_PCR, PCR_MASK); init_LPCR_ISA300((mfspr(SPRN_LPCR) | LPCR_PECEDH | LPCR_PECE_HVEE |\ LPCR_HVICE | LPCR_HEIC) & ~(LPCR_UPRT | LPCR_HR), 0); @@ -264,6 +271,7 @@ void __restore_cpu_power10(void) mtspr(SPRN_PSSCR, 0); mtspr(SPRN_LPID, 0); mtspr(SPRN_PID, 0); + mtspr(SPRN_AMOR, ~0); mtspr(SPRN_PCR, PCR_MASK); init_LPCR_ISA300((mfspr(SPRN_LPCR) | LPCR_PECEDH | LPCR_PECE_HVEE |\ LPCR_HVICE | LPCR_HEIC) & ~(LPCR_UPRT | LPCR_HR), 0); diff --git a/arch/powerpc/kernel/cpu_specs.h b/arch/powerpc/kernel/cpu_specs.h new file mode 100644 index 000000000000..85ded3f77204 --- /dev/null +++ b/arch/powerpc/kernel/cpu_specs.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifdef CONFIG_40x +#include "cpu_specs_40x.h" +#endif + +#ifdef CONFIG_PPC_47x +#include "cpu_specs_47x.h" +#elif defined(CONFIG_44x) +#include "cpu_specs_44x.h" +#endif + +#ifdef CONFIG_PPC_8xx +#include "cpu_specs_8xx.h" +#endif + +#ifdef CONFIG_PPC_E500MC +#include "cpu_specs_e500mc.h" +#elif defined(CONFIG_PPC_85xx) +#include "cpu_specs_85xx.h" +#endif + +#ifdef CONFIG_PPC_BOOK3S_32 +#include "cpu_specs_book3s_32.h" +#endif + +#ifdef CONFIG_PPC_BOOK3S_64 +#include "cpu_specs_book3s_64.h" +#endif diff --git a/arch/powerpc/kernel/cpu_specs_40x.h b/arch/powerpc/kernel/cpu_specs_40x.h new file mode 100644 index 000000000000..a1362a75b8c8 --- /dev/null +++ b/arch/powerpc/kernel/cpu_specs_40x.h @@ -0,0 +1,280 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org) + */ + +static struct cpu_spec cpu_specs[] __initdata = { + { /* STB 04xxx */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x41810000, + .cpu_name = "STB04xxx", + .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", + }, + { /* NP405L */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x41610000, + .cpu_name = "NP405L", + .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", + }, + { /* NP4GS3 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x40B10000, + .cpu_name = "NP4GS3", + .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", + }, + { /* NP405H */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x41410000, + .cpu_name = "NP405H", + .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", + }, + { /* 405GPr */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x50910000, + .cpu_name = "405GPr", + .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", + }, + { /* STBx25xx */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x51510000, + .cpu_name = "STBx25xx", + .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", + }, + { /* 405LP */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x41F10000, + .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, + .platform = "ppc405", + }, + { /* 405EP */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x51210000, + .cpu_name = "405EP", + .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", + }, + { /* 405EX Rev. A/B with Security */ + .pvr_mask = 0xffff000f, + .pvr_value = 0x12910007, + .cpu_name = "405EX Rev. A/B", + .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", + }, + { /* 405EX Rev. C without Security */ + .pvr_mask = 0xffff000f, + .pvr_value = 0x1291000d, + .cpu_name = "405EX Rev. C", + .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", + }, + { /* 405EX Rev. C with Security */ + .pvr_mask = 0xffff000f, + .pvr_value = 0x1291000f, + .cpu_name = "405EX Rev. C", + .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", + }, + { /* 405EX Rev. D without Security */ + .pvr_mask = 0xffff000f, + .pvr_value = 0x12910003, + .cpu_name = "405EX Rev. D", + .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", + }, + { /* 405EX Rev. D with Security */ + .pvr_mask = 0xffff000f, + .pvr_value = 0x12910005, + .cpu_name = "405EX Rev. D", + .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", + }, + { /* 405EXr Rev. A/B without Security */ + .pvr_mask = 0xffff000f, + .pvr_value = 0x12910001, + .cpu_name = "405EXr Rev. A/B", + .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", + }, + { /* 405EXr Rev. C without Security */ + .pvr_mask = 0xffff000f, + .pvr_value = 0x12910009, + .cpu_name = "405EXr Rev. C", + .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", + }, + { /* 405EXr Rev. C with Security */ + .pvr_mask = 0xffff000f, + .pvr_value = 0x1291000b, + .cpu_name = "405EXr Rev. C", + .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", + }, + { /* 405EXr Rev. D without Security */ + .pvr_mask = 0xffff000f, + .pvr_value = 0x12910000, + .cpu_name = "405EXr Rev. D", + .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", + }, + { /* 405EXr Rev. D with Security */ + .pvr_mask = 0xffff000f, + .pvr_value = 0x12910002, + .cpu_name = "405EXr Rev. D", + .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, + .platform = "ppc405", + }, + { /* APM8018X */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x7ff11432, + .cpu_name = "APM8018X", + .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", + }, + { /* default match */ + .pvr_mask = 0x00000000, + .pvr_value = 0x00000000, + .cpu_name = "(generic 40x PPC)", + .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", + } +}; diff --git a/arch/powerpc/kernel/cpu_specs_44x.h b/arch/powerpc/kernel/cpu_specs_44x.h new file mode 100644 index 000000000000..69c4cdc0cdee --- /dev/null +++ b/arch/powerpc/kernel/cpu_specs_44x.h @@ -0,0 +1,304 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org) + */ + +#define COMMON_USER_BOOKE (PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \ + PPC_FEATURE_BOOKE) + +static struct cpu_spec cpu_specs[] __initdata = { + { + .pvr_mask = 0xf0000fff, + .pvr_value = 0x40000850, + .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, + .platform = "ppc440", + }, + { /* Use logical PVR for 440EP (logical pvr = pvr | 0x8) */ + .pvr_mask = 0xf0000fff, + .pvr_value = 0x40000858, + .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, + .machine_check = machine_check_4xx, + .platform = "ppc440", + }, + { + .pvr_mask = 0xf0000fff, + .pvr_value = 0x400008d3, + .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, + .platform = "ppc440", + }, + { /* Matches both physical and logical PVR for 440EP (logical pvr = pvr | 0x8) */ + .pvr_mask = 0xf0000ff7, + .pvr_value = 0x400008d4, + .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, + .machine_check = machine_check_4xx, + .platform = "ppc440", + }, + { /* Use logical PVR for 440EP (logical pvr = pvr | 0x8) */ + .pvr_mask = 0xf0000fff, + .pvr_value = 0x400008db, + .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, + .machine_check = machine_check_4xx, + .platform = "ppc440", + }, + { /* 440GRX */ + .pvr_mask = 0xf0000ffb, + .pvr_value = 0x200008D0, + .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, + .machine_check = machine_check_440A, + .platform = "ppc440", + }, + { /* Use logical PVR for 440EPx (logical pvr = pvr | 0x8) */ + .pvr_mask = 0xf0000ffb, + .pvr_value = 0x200008D8, + .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, + .machine_check = machine_check_440A, + .platform = "ppc440", + }, + { /* 440GP Rev. B */ + .pvr_mask = 0xf0000fff, + .pvr_value = 0x40000440, + .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, + .platform = "ppc440gp", + }, + { /* 440GP Rev. C */ + .pvr_mask = 0xf0000fff, + .pvr_value = 0x40000481, + .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, + .platform = "ppc440gp", + }, + { /* 440GX Rev. A */ + .pvr_mask = 0xf0000fff, + .pvr_value = 0x50000850, + .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, + .machine_check = machine_check_440A, + .platform = "ppc440", + }, + { /* 440GX Rev. B */ + .pvr_mask = 0xf0000fff, + .pvr_value = 0x50000851, + .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, + .machine_check = machine_check_440A, + .platform = "ppc440", + }, + { /* 440GX Rev. C */ + .pvr_mask = 0xf0000fff, + .pvr_value = 0x50000892, + .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, + .machine_check = machine_check_440A, + .platform = "ppc440", + }, + { /* 440GX Rev. F */ + .pvr_mask = 0xf0000fff, + .pvr_value = 0x50000894, + .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, + .machine_check = machine_check_440A, + .platform = "ppc440", + }, + { /* 440SP Rev. A */ + .pvr_mask = 0xfff00fff, + .pvr_value = 0x53200891, + .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, + .platform = "ppc440", + }, + { /* 440SPe Rev. A */ + .pvr_mask = 0xfff00fff, + .pvr_value = 0x53400890, + .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, + .machine_check = machine_check_440A, + .platform = "ppc440", + }, + { /* 440SPe Rev. B */ + .pvr_mask = 0xfff00fff, + .pvr_value = 0x53400891, + .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, + .machine_check = machine_check_440A, + .platform = "ppc440", + }, + { /* 460EX */ + .pvr_mask = 0xffff0006, + .pvr_value = 0x13020002, + .cpu_name = "460EX", + .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, + .machine_check = machine_check_440A, + .platform = "ppc440", + }, + { /* 460EX Rev B */ + .pvr_mask = 0xffff0007, + .pvr_value = 0x13020004, + .cpu_name = "460EX Rev. B", + .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, + .machine_check = machine_check_440A, + .platform = "ppc440", + }, + { /* 460GT */ + .pvr_mask = 0xffff0006, + .pvr_value = 0x13020000, + .cpu_name = "460GT", + .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, + .machine_check = machine_check_440A, + .platform = "ppc440", + }, + { /* 460GT Rev B */ + .pvr_mask = 0xffff0007, + .pvr_value = 0x13020005, + .cpu_name = "460GT Rev. B", + .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, + .machine_check = machine_check_440A, + .platform = "ppc440", + }, + { /* 460SX */ + .pvr_mask = 0xffffff00, + .pvr_value = 0x13541800, + .cpu_name = "460SX", + .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_460sx, + .machine_check = machine_check_440A, + .platform = "ppc440", + }, + { /* 464 in APM821xx */ + .pvr_mask = 0xfffffff0, + .pvr_value = 0x12C41C80, + .cpu_name = "APM821XX", + .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_apm821xx, + .machine_check = machine_check_440A, + .platform = "ppc440", + }, + { /* default match */ + .pvr_mask = 0x00000000, + .pvr_value = 0x00000000, + .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, + .platform = "ppc440", + } +}; diff --git a/arch/powerpc/kernel/cpu_specs_47x.h b/arch/powerpc/kernel/cpu_specs_47x.h new file mode 100644 index 000000000000..3143cd504a51 --- /dev/null +++ b/arch/powerpc/kernel/cpu_specs_47x.h @@ -0,0 +1,74 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org) + */ + +#define COMMON_USER_BOOKE (PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \ + PPC_FEATURE_BOOKE) + +static struct cpu_spec cpu_specs[] __initdata = { + { /* 476 DD2 core */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x11a52080, + .cpu_name = "476", + .cpu_features = CPU_FTRS_47X | CPU_FTR_476_DD2, + .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, + .mmu_features = MMU_FTR_TYPE_47x | MMU_FTR_USE_TLBIVAX_BCAST | + MMU_FTR_LOCK_BCAST_INVAL, + .icache_bsize = 32, + .dcache_bsize = 128, + .machine_check = machine_check_47x, + .platform = "ppc470", + }, + { /* 476fpe */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x7ff50000, + .cpu_name = "476fpe", + .cpu_features = CPU_FTRS_47X | CPU_FTR_476_DD2, + .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, + .mmu_features = MMU_FTR_TYPE_47x | MMU_FTR_USE_TLBIVAX_BCAST | + MMU_FTR_LOCK_BCAST_INVAL, + .icache_bsize = 32, + .dcache_bsize = 128, + .machine_check = machine_check_47x, + .platform = "ppc470", + }, + { /* 476 iss */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00050000, + .cpu_name = "476", + .cpu_features = CPU_FTRS_47X, + .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, + .mmu_features = MMU_FTR_TYPE_47x | MMU_FTR_USE_TLBIVAX_BCAST | + MMU_FTR_LOCK_BCAST_INVAL, + .icache_bsize = 32, + .dcache_bsize = 128, + .machine_check = machine_check_47x, + .platform = "ppc470", + }, + { /* 476 others */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x11a50000, + .cpu_name = "476", + .cpu_features = CPU_FTRS_47X, + .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, + .mmu_features = MMU_FTR_TYPE_47x | MMU_FTR_USE_TLBIVAX_BCAST | + MMU_FTR_LOCK_BCAST_INVAL, + .icache_bsize = 32, + .dcache_bsize = 128, + .machine_check = machine_check_47x, + .platform = "ppc470", + }, + { /* default match */ + .pvr_mask = 0x00000000, + .pvr_value = 0x00000000, + .cpu_name = "(generic 47x PPC)", + .cpu_features = CPU_FTRS_47X, + .cpu_user_features = COMMON_USER_BOOKE, + .mmu_features = MMU_FTR_TYPE_47x, + .icache_bsize = 32, + .dcache_bsize = 128, + .machine_check = machine_check_47x, + .platform = "ppc470", + } +}; diff --git a/arch/powerpc/kernel/cpu_specs_85xx.h b/arch/powerpc/kernel/cpu_specs_85xx.h new file mode 100644 index 000000000000..aaae202c1a89 --- /dev/null +++ b/arch/powerpc/kernel/cpu_specs_85xx.h @@ -0,0 +1,57 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org) + */ + +#define COMMON_USER_BOOKE (PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \ + PPC_FEATURE_BOOKE) + +static struct cpu_spec cpu_specs[] __initdata = { + { /* e500 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x80200000, + .cpu_name = "e500", + .cpu_features = CPU_FTRS_E500, + .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_SPE_COMP | + PPC_FEATURE_HAS_EFP_SINGLE_COMP, + .cpu_user_features2 = PPC_FEATURE2_ISEL, + .mmu_features = MMU_FTR_TYPE_FSL_E, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 4, + .cpu_setup = __setup_cpu_e500v1, + .machine_check = machine_check_e500, + .platform = "ppc8540", + }, + { /* e500v2 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x80210000, + .cpu_name = "e500v2", + .cpu_features = CPU_FTRS_E500_2, + .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_SPE_COMP | + PPC_FEATURE_HAS_EFP_SINGLE_COMP | + PPC_FEATURE_HAS_EFP_DOUBLE_COMP, + .cpu_user_features2 = PPC_FEATURE2_ISEL, + .mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 4, + .cpu_setup = __setup_cpu_e500v2, + .machine_check = machine_check_e500, + .platform = "ppc8548", + .cpu_down_flush = cpu_down_flush_e500v2, + }, + { /* default match */ + .pvr_mask = 0x00000000, + .pvr_value = 0x00000000, + .cpu_name = "(generic E500 PPC)", + .cpu_features = CPU_FTRS_E500, + .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, + .platform = "powerpc", + } +}; diff --git a/arch/powerpc/kernel/cpu_specs_8xx.h b/arch/powerpc/kernel/cpu_specs_8xx.h new file mode 100644 index 000000000000..93ddbc202ba3 --- /dev/null +++ b/arch/powerpc/kernel/cpu_specs_8xx.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org) + */ + +static struct cpu_spec cpu_specs[] __initdata = { + { /* 8xx */ + .pvr_mask = 0xffff0000, + .pvr_value = PVR_8xx, + .cpu_name = "8xx", + /* + * CPU_FTR_MAYBE_CAN_DOZE is possible, + * 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, + .machine_check = machine_check_8xx, + .platform = "ppc823", + }, +}; diff --git a/arch/powerpc/kernel/cpu_specs_book3s_32.h b/arch/powerpc/kernel/cpu_specs_book3s_32.h new file mode 100644 index 000000000000..3714634d194a --- /dev/null +++ b/arch/powerpc/kernel/cpu_specs_book3s_32.h @@ -0,0 +1,605 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org) + */ + +#define COMMON_USER (PPC_FEATURE_32 | PPC_FEATURE_HAS_FPU | \ + PPC_FEATURE_HAS_MMU) + +static struct cpu_spec cpu_specs[] __initdata = { +#ifdef CONFIG_PPC_BOOK3S_603 + { /* 603 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00030000, + .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, + .machine_check = machine_check_generic, + .platform = "ppc603", + }, + { /* 603e */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00060000, + .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, + .machine_check = machine_check_generic, + .platform = "ppc603", + }, + { /* 603ev */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00070000, + .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, + .machine_check = machine_check_generic, + .platform = "ppc603", + }, + { /* 82xx (8240, 8245, 8260 are all 603e cores) */ + .pvr_mask = 0x7fff0000, + .pvr_value = 0x00810000, + .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, + .machine_check = machine_check_generic, + .platform = "ppc603", + }, + { /* All G2_LE (603e core, plus some) have the same pvr */ + .pvr_mask = 0x7fff0000, + .pvr_value = 0x00820000, + .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, + .machine_check = machine_check_generic, + .platform = "ppc603", + }, +#ifdef CONFIG_PPC_83xx + { /* e300c1 (a 603e core, plus some) on 83xx */ + .pvr_mask = 0x7fff0000, + .pvr_value = 0x00830000, + .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, + .machine_check = machine_check_83xx, + .platform = "ppc603", + }, + { /* e300c2 (an e300c1 core, plus some, minus FPU) on 83xx */ + .pvr_mask = 0x7fff0000, + .pvr_value = 0x00840000, + .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 | MMU_FTR_NEED_DTLB_SW_LRU, + .icache_bsize = 32, + .dcache_bsize = 32, + .cpu_setup = __setup_cpu_603, + .machine_check = machine_check_83xx, + .platform = "ppc603", + }, + { /* e300c3 (e300c1, plus one IU, half cache size) on 83xx */ + .pvr_mask = 0x7fff0000, + .pvr_value = 0x00850000, + .cpu_name = "e300c3", + .cpu_features = CPU_FTRS_E300, + .cpu_user_features = COMMON_USER, + .mmu_features = MMU_FTR_USE_HIGH_BATS | MMU_FTR_NEED_DTLB_SW_LRU, + .icache_bsize = 32, + .dcache_bsize = 32, + .cpu_setup = __setup_cpu_603, + .machine_check = machine_check_83xx, + .num_pmcs = 4, + .platform = "ppc603", + }, + { /* e300c4 (e300c1, plus one IU) */ + .pvr_mask = 0x7fff0000, + .pvr_value = 0x00860000, + .cpu_name = "e300c4", + .cpu_features = CPU_FTRS_E300, + .cpu_user_features = COMMON_USER, + .mmu_features = MMU_FTR_USE_HIGH_BATS | MMU_FTR_NEED_DTLB_SW_LRU, + .icache_bsize = 32, + .dcache_bsize = 32, + .cpu_setup = __setup_cpu_603, + .machine_check = machine_check_83xx, + .num_pmcs = 4, + .platform = "ppc603", + }, +#endif +#endif /* CONFIG_PPC_BOOK3S_603 */ +#ifdef CONFIG_PPC_BOOK3S_604 + { /* 604 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00040000, + .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, + .cpu_setup = __setup_cpu_604, + .machine_check = machine_check_generic, + .platform = "ppc604", + }, + { /* 604e */ + .pvr_mask = 0xfffff000, + .pvr_value = 0x00090000, + .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, + .cpu_setup = __setup_cpu_604, + .machine_check = machine_check_generic, + .platform = "ppc604", + }, + { /* 604r */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00090000, + .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, + .cpu_setup = __setup_cpu_604, + .machine_check = machine_check_generic, + .platform = "ppc604", + }, + { /* 604ev */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x000a0000, + .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, + .cpu_setup = __setup_cpu_604, + .machine_check = machine_check_generic, + .platform = "ppc604", + }, + { /* 740/750 (0x4202, don't support TAU ?) */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x00084202, + .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, + .cpu_setup = __setup_cpu_750, + .machine_check = machine_check_generic, + .platform = "ppc750", + }, + { /* 750CX (80100 and 8010x?) */ + .pvr_mask = 0xfffffff0, + .pvr_value = 0x00080100, + .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, + .cpu_setup = __setup_cpu_750cx, + .machine_check = machine_check_generic, + .platform = "ppc750", + }, + { /* 750CX (82201 and 82202) */ + .pvr_mask = 0xfffffff0, + .pvr_value = 0x00082200, + .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", + }, + { /* 750CXe (82214) */ + .pvr_mask = 0xfffffff0, + .pvr_value = 0x00082210, + .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", + }, + { /* 750CXe "Gekko" (83214) */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x00083214, + .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", + }, + { /* 750CL (and "Broadway") */ + .pvr_mask = 0xfffff0e0, + .pvr_value = 0x00087000, + .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", + }, + { /* 745/755 */ + .pvr_mask = 0xfffff000, + .pvr_value = 0x00083000, + .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", + }, + { /* 750FX rev 1.x */ + .pvr_mask = 0xffffff00, + .pvr_value = 0x70000100, + .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", + }, + { /* 750FX rev 2.0 must disable HID0[DPM] */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x70000200, + .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", + }, + { /* 750FX (All revs except 2.0) */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x70000000, + .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", + }, + { /* 750GX */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x70020000, + .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", + }, + { /* 740/750 (L2CR bit need fixup for 740) */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00080000, + .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", + }, + { /* 7400 rev 1.1 ? (no TAU) */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x000c1101, + .cpu_name = "7400 (1.1)", + .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", + }, + { /* 7400 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x000c0000, + .cpu_name = "7400", + .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", + }, + { /* 7410 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x800c0000, + .cpu_name = "7410", + .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", + }, + { /* 7450 2.0 - no doze/nap */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x80000200, + .cpu_name = "7450", + .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, + .machine_check = machine_check_generic, + .platform = "ppc7450", + }, + { /* 7450 2.1 */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x80000201, + .cpu_name = "7450", + .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, + .machine_check = machine_check_generic, + .platform = "ppc7450", + }, + { /* 7450 2.3 and newer */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x80000000, + .cpu_name = "7450", + .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, + .machine_check = machine_check_generic, + .platform = "ppc7450", + }, + { /* 7455 rev 1.x */ + .pvr_mask = 0xffffff00, + .pvr_value = 0x80010100, + .cpu_name = "7455", + .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, + .machine_check = machine_check_generic, + .platform = "ppc7450", + }, + { /* 7455 rev 2.0 */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x80010200, + .cpu_name = "7455", + .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, + .machine_check = machine_check_generic, + .platform = "ppc7450", + }, + { /* 7455 others */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x80010000, + .cpu_name = "7455", + .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, + .machine_check = machine_check_generic, + .platform = "ppc7450", + }, + { /* 7447/7457 Rev 1.0 */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x80020100, + .cpu_name = "7447/7457", + .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, + .machine_check = machine_check_generic, + .platform = "ppc7450", + }, + { /* 7447/7457 Rev 1.1 */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x80020101, + .cpu_name = "7447/7457", + .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, + .machine_check = machine_check_generic, + .platform = "ppc7450", + }, + { /* 7447/7457 Rev 1.2 and later */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x80020000, + .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, + .machine_check = machine_check_generic, + .platform = "ppc7450", + }, + { /* 7447A */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x80030000, + .cpu_name = "7447A", + .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, + .machine_check = machine_check_generic, + .platform = "ppc7450", + }, + { /* 7448 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x80040000, + .cpu_name = "7448", + .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, + .machine_check = machine_check_generic, + .platform = "ppc7450", + }, + { /* default match, we assume split I/D cache & TB (non-601)... */ + .pvr_mask = 0x00000000, + .pvr_value = 0x00000000, + .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, + .platform = "ppc603", + }, +#endif /* CONFIG_PPC_BOOK3S_604 */ +}; diff --git a/arch/powerpc/kernel/cpu_specs_book3s_64.h b/arch/powerpc/kernel/cpu_specs_book3s_64.h new file mode 100644 index 000000000000..c370c1b804a9 --- /dev/null +++ b/arch/powerpc/kernel/cpu_specs_book3s_64.h @@ -0,0 +1,481 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org) + * + * Modifications for ppc64: + * Copyright (C) 2003 Dave Engebretsen <engebret@us.ibm.com> + */ + +/* NOTE: + * Unlike ppc32, ppc64 will only call cpu_setup() for the boot CPU, it's + * the responsibility of the appropriate CPU save/restore functions to + * eventually copy these settings over. Those save/restore aren't yet + * part of the cputable though. That has to be fixed for both ppc32 + * and ppc64 + */ +#define COMMON_USER_PPC64 (PPC_FEATURE_32 | PPC_FEATURE_HAS_FPU | \ + PPC_FEATURE_HAS_MMU | PPC_FEATURE_64) +#define COMMON_USER_POWER4 (COMMON_USER_PPC64 | PPC_FEATURE_POWER4) +#define COMMON_USER_POWER5 (COMMON_USER_PPC64 | PPC_FEATURE_POWER5 |\ + PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP) +#define COMMON_USER_POWER5_PLUS (COMMON_USER_PPC64 | PPC_FEATURE_POWER5_PLUS|\ + PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP) +#define COMMON_USER_POWER6 (COMMON_USER_PPC64 | PPC_FEATURE_ARCH_2_05 |\ + PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP | \ + PPC_FEATURE_TRUE_LE | \ + PPC_FEATURE_PSERIES_PERFMON_COMPAT) +#define COMMON_USER_POWER7 (COMMON_USER_PPC64 | PPC_FEATURE_ARCH_2_06 |\ + PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP | \ + PPC_FEATURE_TRUE_LE | \ + PPC_FEATURE_PSERIES_PERFMON_COMPAT) +#define COMMON_USER2_POWER7 (PPC_FEATURE2_DSCR) +#define COMMON_USER_POWER8 (COMMON_USER_PPC64 | PPC_FEATURE_ARCH_2_06 |\ + PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP | \ + PPC_FEATURE_TRUE_LE | \ + PPC_FEATURE_PSERIES_PERFMON_COMPAT) +#define COMMON_USER2_POWER8 (PPC_FEATURE2_ARCH_2_07 | \ + PPC_FEATURE2_HTM_COMP | \ + PPC_FEATURE2_HTM_NOSC_COMP | \ + PPC_FEATURE2_DSCR | \ + PPC_FEATURE2_ISEL | PPC_FEATURE2_TAR | \ + PPC_FEATURE2_VEC_CRYPTO) +#define COMMON_USER_PA6T (COMMON_USER_PPC64 | PPC_FEATURE_PA6T |\ + PPC_FEATURE_TRUE_LE | \ + PPC_FEATURE_HAS_ALTIVEC_COMP) +#define COMMON_USER_POWER9 COMMON_USER_POWER8 +#define COMMON_USER2_POWER9 (COMMON_USER2_POWER8 | \ + PPC_FEATURE2_ARCH_3_00 | \ + PPC_FEATURE2_HAS_IEEE128 | \ + PPC_FEATURE2_DARN | \ + PPC_FEATURE2_SCV) +#define COMMON_USER_POWER10 COMMON_USER_POWER9 +#define COMMON_USER2_POWER10 (PPC_FEATURE2_ARCH_3_1 | \ + PPC_FEATURE2_MMA | \ + PPC_FEATURE2_ARCH_3_00 | \ + PPC_FEATURE2_HAS_IEEE128 | \ + PPC_FEATURE2_DARN | \ + PPC_FEATURE2_SCV | \ + PPC_FEATURE2_ARCH_2_07 | \ + PPC_FEATURE2_DSCR | \ + PPC_FEATURE2_ISEL | PPC_FEATURE2_TAR | \ + PPC_FEATURE2_VEC_CRYPTO) + +static struct cpu_spec cpu_specs[] __initdata = { + { /* PPC970 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00390000, + .cpu_name = "PPC970", + .cpu_features = CPU_FTRS_PPC970, + .cpu_user_features = COMMON_USER_POWER4 | PPC_FEATURE_HAS_ALTIVEC_COMP, + .mmu_features = MMU_FTRS_PPC970, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 8, + .pmc_type = PPC_PMC_IBM, + .cpu_setup = __setup_cpu_ppc970, + .cpu_restore = __restore_cpu_ppc970, + .platform = "ppc970", + }, + { /* PPC970FX */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x003c0000, + .cpu_name = "PPC970FX", + .cpu_features = CPU_FTRS_PPC970, + .cpu_user_features = COMMON_USER_POWER4 | PPC_FEATURE_HAS_ALTIVEC_COMP, + .mmu_features = MMU_FTRS_PPC970, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 8, + .pmc_type = PPC_PMC_IBM, + .cpu_setup = __setup_cpu_ppc970, + .cpu_restore = __restore_cpu_ppc970, + .platform = "ppc970", + }, + { /* PPC970MP DD1.0 - no DEEPNAP, use regular 970 init */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x00440100, + .cpu_name = "PPC970MP", + .cpu_features = CPU_FTRS_PPC970, + .cpu_user_features = COMMON_USER_POWER4 | PPC_FEATURE_HAS_ALTIVEC_COMP, + .mmu_features = MMU_FTRS_PPC970, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 8, + .pmc_type = PPC_PMC_IBM, + .cpu_setup = __setup_cpu_ppc970, + .cpu_restore = __restore_cpu_ppc970, + .platform = "ppc970", + }, + { /* PPC970MP */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00440000, + .cpu_name = "PPC970MP", + .cpu_features = CPU_FTRS_PPC970, + .cpu_user_features = COMMON_USER_POWER4 | PPC_FEATURE_HAS_ALTIVEC_COMP, + .mmu_features = MMU_FTRS_PPC970, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 8, + .pmc_type = PPC_PMC_IBM, + .cpu_setup = __setup_cpu_ppc970MP, + .cpu_restore = __restore_cpu_ppc970, + .platform = "ppc970", + }, + { /* PPC970GX */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00450000, + .cpu_name = "PPC970GX", + .cpu_features = CPU_FTRS_PPC970, + .cpu_user_features = COMMON_USER_POWER4 | PPC_FEATURE_HAS_ALTIVEC_COMP, + .mmu_features = MMU_FTRS_PPC970, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 8, + .pmc_type = PPC_PMC_IBM, + .cpu_setup = __setup_cpu_ppc970, + .platform = "ppc970", + }, + { /* Power5 GR */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x003a0000, + .cpu_name = "POWER5 (gr)", + .cpu_features = CPU_FTRS_POWER5, + .cpu_user_features = COMMON_USER_POWER5, + .mmu_features = MMU_FTRS_POWER5, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .pmc_type = PPC_PMC_IBM, + .platform = "power5", + }, + { /* Power5++ */ + .pvr_mask = 0xffffff00, + .pvr_value = 0x003b0300, + .cpu_name = "POWER5+ (gs)", + .cpu_features = CPU_FTRS_POWER5, + .cpu_user_features = COMMON_USER_POWER5_PLUS, + .mmu_features = MMU_FTRS_POWER5, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .platform = "power5+", + }, + { /* Power5 GS */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x003b0000, + .cpu_name = "POWER5+ (gs)", + .cpu_features = CPU_FTRS_POWER5, + .cpu_user_features = COMMON_USER_POWER5_PLUS, + .mmu_features = MMU_FTRS_POWER5, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .pmc_type = PPC_PMC_IBM, + .platform = "power5+", + }, + { /* POWER6 in P5+ mode; 2.04-compliant processor */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x0f000001, + .cpu_name = "POWER5+", + .cpu_features = CPU_FTRS_POWER5, + .cpu_user_features = COMMON_USER_POWER5_PLUS, + .mmu_features = MMU_FTRS_POWER5, + .icache_bsize = 128, + .dcache_bsize = 128, + .platform = "power5+", + }, + { /* Power6 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x003e0000, + .cpu_name = "POWER6 (raw)", + .cpu_features = CPU_FTRS_POWER6, + .cpu_user_features = COMMON_USER_POWER6 | PPC_FEATURE_POWER6_EXT, + .mmu_features = MMU_FTRS_POWER6, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .pmc_type = PPC_PMC_IBM, + .platform = "power6x", + }, + { /* 2.05-compliant processor, i.e. Power6 "architected" mode */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x0f000002, + .cpu_name = "POWER6 (architected)", + .cpu_features = CPU_FTRS_POWER6, + .cpu_user_features = COMMON_USER_POWER6, + .mmu_features = MMU_FTRS_POWER6, + .icache_bsize = 128, + .dcache_bsize = 128, + .platform = "power6", + }, + { /* 2.06-compliant processor, i.e. Power7 "architected" mode */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x0f000003, + .cpu_name = "POWER7 (architected)", + .cpu_features = CPU_FTRS_POWER7, + .cpu_user_features = COMMON_USER_POWER7, + .cpu_user_features2 = COMMON_USER2_POWER7, + .mmu_features = MMU_FTRS_POWER7, + .icache_bsize = 128, + .dcache_bsize = 128, + .cpu_setup = __setup_cpu_power7, + .cpu_restore = __restore_cpu_power7, + .machine_check_early = __machine_check_early_realmode_p7, + .platform = "power7", + }, + { /* 2.07-compliant processor, i.e. Power8 "architected" mode */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x0f000004, + .cpu_name = "POWER8 (architected)", + .cpu_features = CPU_FTRS_POWER8, + .cpu_user_features = COMMON_USER_POWER8, + .cpu_user_features2 = COMMON_USER2_POWER8, + .mmu_features = MMU_FTRS_POWER8, + .icache_bsize = 128, + .dcache_bsize = 128, + .cpu_setup = __setup_cpu_power8, + .cpu_restore = __restore_cpu_power8, + .machine_check_early = __machine_check_early_realmode_p8, + .platform = "power8", + }, + { /* 3.00-compliant processor, i.e. Power9 "architected" mode */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x0f000005, + .cpu_name = "POWER9 (architected)", + .cpu_features = CPU_FTRS_POWER9, + .cpu_user_features = COMMON_USER_POWER9, + .cpu_user_features2 = COMMON_USER2_POWER9, + .mmu_features = MMU_FTRS_POWER9, + .icache_bsize = 128, + .dcache_bsize = 128, + .cpu_setup = __setup_cpu_power9, + .cpu_restore = __restore_cpu_power9, + .platform = "power9", + }, + { /* 3.1-compliant processor, i.e. Power10 "architected" mode */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x0f000006, + .cpu_name = "POWER10 (architected)", + .cpu_features = CPU_FTRS_POWER10, + .cpu_user_features = COMMON_USER_POWER10, + .cpu_user_features2 = COMMON_USER2_POWER10, + .mmu_features = MMU_FTRS_POWER10, + .icache_bsize = 128, + .dcache_bsize = 128, + .cpu_setup = __setup_cpu_power10, + .cpu_restore = __restore_cpu_power10, + .platform = "power10", + }, + { /* Power7 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x003f0000, + .cpu_name = "POWER7 (raw)", + .cpu_features = CPU_FTRS_POWER7, + .cpu_user_features = COMMON_USER_POWER7, + .cpu_user_features2 = COMMON_USER2_POWER7, + .mmu_features = MMU_FTRS_POWER7, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .pmc_type = PPC_PMC_IBM, + .cpu_setup = __setup_cpu_power7, + .cpu_restore = __restore_cpu_power7, + .machine_check_early = __machine_check_early_realmode_p7, + .platform = "power7", + }, + { /* Power7+ */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x004A0000, + .cpu_name = "POWER7+ (raw)", + .cpu_features = CPU_FTRS_POWER7, + .cpu_user_features = COMMON_USER_POWER7, + .cpu_user_features2 = COMMON_USER2_POWER7, + .mmu_features = MMU_FTRS_POWER7, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .pmc_type = PPC_PMC_IBM, + .cpu_setup = __setup_cpu_power7, + .cpu_restore = __restore_cpu_power7, + .machine_check_early = __machine_check_early_realmode_p7, + .platform = "power7+", + }, + { /* Power8E */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x004b0000, + .cpu_name = "POWER8E (raw)", + .cpu_features = CPU_FTRS_POWER8E, + .cpu_user_features = COMMON_USER_POWER8, + .cpu_user_features2 = COMMON_USER2_POWER8, + .mmu_features = MMU_FTRS_POWER8, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .pmc_type = PPC_PMC_IBM, + .cpu_setup = __setup_cpu_power8, + .cpu_restore = __restore_cpu_power8, + .machine_check_early = __machine_check_early_realmode_p8, + .platform = "power8", + }, + { /* Power8NVL */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x004c0000, + .cpu_name = "POWER8NVL (raw)", + .cpu_features = CPU_FTRS_POWER8, + .cpu_user_features = COMMON_USER_POWER8, + .cpu_user_features2 = COMMON_USER2_POWER8, + .mmu_features = MMU_FTRS_POWER8, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .pmc_type = PPC_PMC_IBM, + .cpu_setup = __setup_cpu_power8, + .cpu_restore = __restore_cpu_power8, + .machine_check_early = __machine_check_early_realmode_p8, + .platform = "power8", + }, + { /* Power8 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x004d0000, + .cpu_name = "POWER8 (raw)", + .cpu_features = CPU_FTRS_POWER8, + .cpu_user_features = COMMON_USER_POWER8, + .cpu_user_features2 = COMMON_USER2_POWER8, + .mmu_features = MMU_FTRS_POWER8, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .pmc_type = PPC_PMC_IBM, + .cpu_setup = __setup_cpu_power8, + .cpu_restore = __restore_cpu_power8, + .machine_check_early = __machine_check_early_realmode_p8, + .platform = "power8", + }, + { /* Power9 DD2.0 */ + .pvr_mask = 0xffffefff, + .pvr_value = 0x004e0200, + .cpu_name = "POWER9 (raw)", + .cpu_features = CPU_FTRS_POWER9_DD2_0, + .cpu_user_features = COMMON_USER_POWER9, + .cpu_user_features2 = COMMON_USER2_POWER9, + .mmu_features = MMU_FTRS_POWER9, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .pmc_type = PPC_PMC_IBM, + .cpu_setup = __setup_cpu_power9, + .cpu_restore = __restore_cpu_power9, + .machine_check_early = __machine_check_early_realmode_p9, + .platform = "power9", + }, + { /* Power9 DD 2.1 */ + .pvr_mask = 0xffffefff, + .pvr_value = 0x004e0201, + .cpu_name = "POWER9 (raw)", + .cpu_features = CPU_FTRS_POWER9_DD2_1, + .cpu_user_features = COMMON_USER_POWER9, + .cpu_user_features2 = COMMON_USER2_POWER9, + .mmu_features = MMU_FTRS_POWER9, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .pmc_type = PPC_PMC_IBM, + .cpu_setup = __setup_cpu_power9, + .cpu_restore = __restore_cpu_power9, + .machine_check_early = __machine_check_early_realmode_p9, + .platform = "power9", + }, + { /* Power9 DD2.2 */ + .pvr_mask = 0xffffefff, + .pvr_value = 0x004e0202, + .cpu_name = "POWER9 (raw)", + .cpu_features = CPU_FTRS_POWER9_DD2_2, + .cpu_user_features = COMMON_USER_POWER9, + .cpu_user_features2 = COMMON_USER2_POWER9, + .mmu_features = MMU_FTRS_POWER9, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .pmc_type = PPC_PMC_IBM, + .cpu_setup = __setup_cpu_power9, + .cpu_restore = __restore_cpu_power9, + .machine_check_early = __machine_check_early_realmode_p9, + .platform = "power9", + }, + { /* Power9 DD2.3 or later */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x004e0000, + .cpu_name = "POWER9 (raw)", + .cpu_features = CPU_FTRS_POWER9_DD2_3, + .cpu_user_features = COMMON_USER_POWER9, + .cpu_user_features2 = COMMON_USER2_POWER9, + .mmu_features = MMU_FTRS_POWER9, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .pmc_type = PPC_PMC_IBM, + .cpu_setup = __setup_cpu_power9, + .cpu_restore = __restore_cpu_power9, + .machine_check_early = __machine_check_early_realmode_p9, + .platform = "power9", + }, + { /* Power10 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00800000, + .cpu_name = "POWER10 (raw)", + .cpu_features = CPU_FTRS_POWER10, + .cpu_user_features = COMMON_USER_POWER10, + .cpu_user_features2 = COMMON_USER2_POWER10, + .mmu_features = MMU_FTRS_POWER10, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .pmc_type = PPC_PMC_IBM, + .cpu_setup = __setup_cpu_power10, + .cpu_restore = __restore_cpu_power10, + .machine_check_early = __machine_check_early_realmode_p10, + .platform = "power10", + }, + { /* Cell Broadband Engine */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00700000, + .cpu_name = "Cell Broadband Engine", + .cpu_features = CPU_FTRS_CELL, + .cpu_user_features = COMMON_USER_PPC64 | PPC_FEATURE_CELL | + PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_SMT, + .mmu_features = MMU_FTRS_CELL, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 4, + .pmc_type = PPC_PMC_IBM, + .platform = "ppc-cell-be", + }, + { /* PA Semi PA6T */ + .pvr_mask = 0x7fff0000, + .pvr_value = 0x00900000, + .cpu_name = "PA6T", + .cpu_features = CPU_FTRS_PA6T, + .cpu_user_features = COMMON_USER_PA6T, + .mmu_features = MMU_FTRS_PA6T, + .icache_bsize = 64, + .dcache_bsize = 64, + .num_pmcs = 6, + .pmc_type = PPC_PMC_PA6T, + .cpu_setup = __setup_cpu_pa6t, + .cpu_restore = __restore_cpu_pa6t, + .platform = "pa6t", + }, + { /* default match */ + .pvr_mask = 0x00000000, + .pvr_value = 0x00000000, + .cpu_name = "POWER5 (compatible)", + .cpu_features = CPU_FTRS_COMPATIBLE, + .cpu_user_features = COMMON_USER_PPC64, + .mmu_features = MMU_FTRS_POWER, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .pmc_type = PPC_PMC_IBM, + .platform = "power5", + } +}; diff --git a/arch/powerpc/kernel/cpu_specs_e500mc.h b/arch/powerpc/kernel/cpu_specs_e500mc.h new file mode 100644 index 000000000000..ceb06b109f83 --- /dev/null +++ b/arch/powerpc/kernel/cpu_specs_e500mc.h @@ -0,0 +1,75 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org) + * + * Modifications for ppc64: + * Copyright (C) 2003 Dave Engebretsen <engebret@us.ibm.com> + */ + +#ifdef CONFIG_PPC64 +#define COMMON_USER_BOOKE (PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \ + PPC_FEATURE_HAS_FPU | PPC_FEATURE_64) +#else +#define COMMON_USER_BOOKE (PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \ + PPC_FEATURE_BOOKE) +#endif + +static struct cpu_spec cpu_specs[] __initdata = { +#ifdef CONFIG_PPC32 + { /* e500mc */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x80230000, + .cpu_name = "e500mc", + .cpu_features = CPU_FTRS_E500MC, + .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, + .cpu_user_features2 = PPC_FEATURE2_ISEL, + .mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS | MMU_FTR_USE_TLBILX, + .icache_bsize = 64, + .dcache_bsize = 64, + .num_pmcs = 4, + .cpu_setup = __setup_cpu_e500mc, + .machine_check = machine_check_e500mc, + .platform = "ppce500mc", + .cpu_down_flush = cpu_down_flush_e500mc, + }, +#endif /* CONFIG_PPC32 */ + { /* e5500 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x80240000, + .cpu_name = "e5500", + .cpu_features = CPU_FTRS_E5500, + .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, + .cpu_user_features2 = PPC_FEATURE2_ISEL, + .mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS | MMU_FTR_USE_TLBILX, + .icache_bsize = 64, + .dcache_bsize = 64, + .num_pmcs = 4, + .cpu_setup = __setup_cpu_e5500, +#ifndef CONFIG_PPC32 + .cpu_restore = __restore_cpu_e5500, +#endif + .machine_check = machine_check_e500mc, + .platform = "ppce5500", + .cpu_down_flush = cpu_down_flush_e5500, + }, + { /* e6500 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x80400000, + .cpu_name = "e6500", + .cpu_features = CPU_FTRS_E6500, + .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU | + PPC_FEATURE_HAS_ALTIVEC_COMP, + .cpu_user_features2 = PPC_FEATURE2_ISEL, + .mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS | MMU_FTR_USE_TLBILX, + .icache_bsize = 64, + .dcache_bsize = 64, + .num_pmcs = 6, + .cpu_setup = __setup_cpu_e6500, +#ifndef CONFIG_PPC32 + .cpu_restore = __restore_cpu_e6500, +#endif + .machine_check = machine_check_e500mc, + .platform = "ppce6500", + .cpu_down_flush = cpu_down_flush_e6500, + }, +}; diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index ae0fdef0ac11..8a32bffefa5b 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -12,12 +12,13 @@ #include <linux/init.h> #include <linux/export.h> #include <linux/jump_label.h> +#include <linux/of.h> #include <asm/cputable.h> -#include <asm/prom.h> /* for PTRRELOC on ARCH=ppc */ #include <asm/mce.h> #include <asm/mmu.h> #include <asm/setup.h> +#include <asm/cpu_setup.h> static struct cpu_spec the_cpu_spec __read_mostly; @@ -27,1954 +28,7 @@ EXPORT_SYMBOL(cur_cpu_spec); /* The platform string corresponding to the real PVR */ const char *powerpc_base_platform; -/* NOTE: - * Unlike ppc32, ppc64 will only call this once for the boot CPU, it's - * the responsibility of the appropriate CPU save/restore functions to - * eventually copy these settings over. Those save/restore aren't yet - * part of the cputable though. That has to be fixed for both ppc32 - * and ppc64 - */ -#ifdef CONFIG_PPC32 -extern void __setup_cpu_e500v1(unsigned long offset, struct cpu_spec* spec); -extern void __setup_cpu_e500v2(unsigned long offset, struct cpu_spec* spec); -extern void __setup_cpu_e500mc(unsigned long offset, struct cpu_spec* spec); -extern void __setup_cpu_440ep(unsigned long offset, struct cpu_spec* spec); -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_460sx(unsigned long offset, struct cpu_spec *spec); -extern void __setup_cpu_apm821xx(unsigned long offset, struct cpu_spec *spec); -extern void __setup_cpu_603(unsigned long offset, struct cpu_spec* spec); -extern void __setup_cpu_604(unsigned long offset, struct cpu_spec* spec); -extern void __setup_cpu_750(unsigned long offset, struct cpu_spec* spec); -extern void __setup_cpu_750cx(unsigned long offset, struct cpu_spec* spec); -extern void __setup_cpu_750fx(unsigned long offset, struct cpu_spec* spec); -extern void __setup_cpu_7400(unsigned long offset, struct cpu_spec* spec); -extern void __setup_cpu_7410(unsigned long offset, struct cpu_spec* spec); -extern void __setup_cpu_745x(unsigned long offset, struct cpu_spec* spec); -#endif /* CONFIG_PPC32 */ -#ifdef CONFIG_PPC64 -#include <asm/cpu_setup_power.h> -extern void __setup_cpu_ppc970(unsigned long offset, struct cpu_spec* spec); -extern void __setup_cpu_ppc970MP(unsigned long offset, struct cpu_spec* spec); -extern void __setup_cpu_pa6t(unsigned long offset, struct cpu_spec* spec); -extern void __restore_cpu_pa6t(void); -extern void __restore_cpu_ppc970(void); -extern long __machine_check_early_realmode_p7(struct pt_regs *regs); -extern long __machine_check_early_realmode_p8(struct pt_regs *regs); -extern long __machine_check_early_realmode_p9(struct pt_regs *regs); -#endif /* CONFIG_PPC64 */ -#if defined(CONFIG_E500) -extern void __setup_cpu_e5500(unsigned long offset, struct cpu_spec* spec); -extern void __setup_cpu_e6500(unsigned long offset, struct cpu_spec* spec); -extern void __restore_cpu_e5500(void); -extern void __restore_cpu_e6500(void); -#endif /* CONFIG_E500 */ - -/* This table only contains "desktop" CPUs, it need to be filled with embedded - * ones as well... - */ -#define COMMON_USER (PPC_FEATURE_32 | PPC_FEATURE_HAS_FPU | \ - PPC_FEATURE_HAS_MMU) -#define COMMON_USER_PPC64 (COMMON_USER | PPC_FEATURE_64) -#define COMMON_USER_POWER4 (COMMON_USER_PPC64 | PPC_FEATURE_POWER4) -#define COMMON_USER_POWER5 (COMMON_USER_PPC64 | PPC_FEATURE_POWER5 |\ - PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP) -#define COMMON_USER_POWER5_PLUS (COMMON_USER_PPC64 | PPC_FEATURE_POWER5_PLUS|\ - PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP) -#define COMMON_USER_POWER6 (COMMON_USER_PPC64 | PPC_FEATURE_ARCH_2_05 |\ - PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP | \ - PPC_FEATURE_TRUE_LE | \ - PPC_FEATURE_PSERIES_PERFMON_COMPAT) -#define COMMON_USER_POWER7 (COMMON_USER_PPC64 | PPC_FEATURE_ARCH_2_06 |\ - PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP | \ - PPC_FEATURE_TRUE_LE | \ - PPC_FEATURE_PSERIES_PERFMON_COMPAT) -#define COMMON_USER2_POWER7 (PPC_FEATURE2_DSCR) -#define COMMON_USER_POWER8 (COMMON_USER_PPC64 | PPC_FEATURE_ARCH_2_06 |\ - PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP | \ - PPC_FEATURE_TRUE_LE | \ - PPC_FEATURE_PSERIES_PERFMON_COMPAT) -#define COMMON_USER2_POWER8 (PPC_FEATURE2_ARCH_2_07 | \ - PPC_FEATURE2_HTM_COMP | \ - PPC_FEATURE2_HTM_NOSC_COMP | \ - PPC_FEATURE2_DSCR | \ - PPC_FEATURE2_ISEL | PPC_FEATURE2_TAR | \ - PPC_FEATURE2_VEC_CRYPTO) -#define COMMON_USER_PA6T (COMMON_USER_PPC64 | PPC_FEATURE_PA6T |\ - PPC_FEATURE_TRUE_LE | \ - PPC_FEATURE_HAS_ALTIVEC_COMP) -#define COMMON_USER_POWER9 COMMON_USER_POWER8 -#define COMMON_USER2_POWER9 (COMMON_USER2_POWER8 | \ - PPC_FEATURE2_ARCH_3_00 | \ - PPC_FEATURE2_HAS_IEEE128 | \ - PPC_FEATURE2_DARN | \ - PPC_FEATURE2_SCV) -#define COMMON_USER_POWER10 COMMON_USER_POWER9 -#define COMMON_USER2_POWER10 (PPC_FEATURE2_ARCH_3_1 | \ - PPC_FEATURE2_MMA | \ - PPC_FEATURE2_ARCH_3_00 | \ - PPC_FEATURE2_HAS_IEEE128 | \ - PPC_FEATURE2_DARN | \ - PPC_FEATURE2_SCV | \ - PPC_FEATURE2_ARCH_2_07 | \ - PPC_FEATURE2_DSCR | \ - PPC_FEATURE2_ISEL | PPC_FEATURE2_TAR | \ - PPC_FEATURE2_VEC_CRYPTO) - -#ifdef CONFIG_PPC_BOOK3E_64 -#define COMMON_USER_BOOKE (COMMON_USER_PPC64 | PPC_FEATURE_BOOKE) -#else -#define COMMON_USER_BOOKE (PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \ - PPC_FEATURE_BOOKE) -#endif - -static struct cpu_spec __initdata cpu_specs[] = { -#ifdef CONFIG_PPC_BOOK3S_64 - { /* PPC970 */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x00390000, - .cpu_name = "PPC970", - .cpu_features = CPU_FTRS_PPC970, - .cpu_user_features = COMMON_USER_POWER4 | - PPC_FEATURE_HAS_ALTIVEC_COMP, - .mmu_features = MMU_FTRS_PPC970, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 8, - .pmc_type = PPC_PMC_IBM, - .cpu_setup = __setup_cpu_ppc970, - .cpu_restore = __restore_cpu_ppc970, - .oprofile_cpu_type = "ppc64/970", - .platform = "ppc970", - }, - { /* PPC970FX */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x003c0000, - .cpu_name = "PPC970FX", - .cpu_features = CPU_FTRS_PPC970, - .cpu_user_features = COMMON_USER_POWER4 | - PPC_FEATURE_HAS_ALTIVEC_COMP, - .mmu_features = MMU_FTRS_PPC970, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 8, - .pmc_type = PPC_PMC_IBM, - .cpu_setup = __setup_cpu_ppc970, - .cpu_restore = __restore_cpu_ppc970, - .oprofile_cpu_type = "ppc64/970", - .platform = "ppc970", - }, - { /* PPC970MP DD1.0 - no DEEPNAP, use regular 970 init */ - .pvr_mask = 0xffffffff, - .pvr_value = 0x00440100, - .cpu_name = "PPC970MP", - .cpu_features = CPU_FTRS_PPC970, - .cpu_user_features = COMMON_USER_POWER4 | - PPC_FEATURE_HAS_ALTIVEC_COMP, - .mmu_features = MMU_FTRS_PPC970, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 8, - .pmc_type = PPC_PMC_IBM, - .cpu_setup = __setup_cpu_ppc970, - .cpu_restore = __restore_cpu_ppc970, - .oprofile_cpu_type = "ppc64/970MP", - .platform = "ppc970", - }, - { /* PPC970MP */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x00440000, - .cpu_name = "PPC970MP", - .cpu_features = CPU_FTRS_PPC970, - .cpu_user_features = COMMON_USER_POWER4 | - PPC_FEATURE_HAS_ALTIVEC_COMP, - .mmu_features = MMU_FTRS_PPC970, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 8, - .pmc_type = PPC_PMC_IBM, - .cpu_setup = __setup_cpu_ppc970MP, - .cpu_restore = __restore_cpu_ppc970, - .oprofile_cpu_type = "ppc64/970MP", - .platform = "ppc970", - }, - { /* PPC970GX */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x00450000, - .cpu_name = "PPC970GX", - .cpu_features = CPU_FTRS_PPC970, - .cpu_user_features = COMMON_USER_POWER4 | - PPC_FEATURE_HAS_ALTIVEC_COMP, - .mmu_features = MMU_FTRS_PPC970, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 8, - .pmc_type = PPC_PMC_IBM, - .cpu_setup = __setup_cpu_ppc970, - .oprofile_cpu_type = "ppc64/970", - .platform = "ppc970", - }, - { /* Power5 GR */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x003a0000, - .cpu_name = "POWER5 (gr)", - .cpu_features = CPU_FTRS_POWER5, - .cpu_user_features = COMMON_USER_POWER5, - .mmu_features = MMU_FTRS_POWER5, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 6, - .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power5", - .platform = "power5", - }, - { /* Power5++ */ - .pvr_mask = 0xffffff00, - .pvr_value = 0x003b0300, - .cpu_name = "POWER5+ (gs)", - .cpu_features = CPU_FTRS_POWER5, - .cpu_user_features = COMMON_USER_POWER5_PLUS, - .mmu_features = MMU_FTRS_POWER5, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 6, - .oprofile_cpu_type = "ppc64/power5++", - .platform = "power5+", - }, - { /* Power5 GS */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x003b0000, - .cpu_name = "POWER5+ (gs)", - .cpu_features = CPU_FTRS_POWER5, - .cpu_user_features = COMMON_USER_POWER5_PLUS, - .mmu_features = MMU_FTRS_POWER5, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 6, - .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power5+", - .platform = "power5+", - }, - { /* POWER6 in P5+ mode; 2.04-compliant processor */ - .pvr_mask = 0xffffffff, - .pvr_value = 0x0f000001, - .cpu_name = "POWER5+", - .cpu_features = CPU_FTRS_POWER5, - .cpu_user_features = COMMON_USER_POWER5_PLUS, - .mmu_features = MMU_FTRS_POWER5, - .icache_bsize = 128, - .dcache_bsize = 128, - .oprofile_cpu_type = "ppc64/ibm-compat-v1", - .platform = "power5+", - }, - { /* Power6 */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x003e0000, - .cpu_name = "POWER6 (raw)", - .cpu_features = CPU_FTRS_POWER6, - .cpu_user_features = COMMON_USER_POWER6 | - PPC_FEATURE_POWER6_EXT, - .mmu_features = MMU_FTRS_POWER6, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 6, - .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power6", - .platform = "power6x", - }, - { /* 2.05-compliant processor, i.e. Power6 "architected" mode */ - .pvr_mask = 0xffffffff, - .pvr_value = 0x0f000002, - .cpu_name = "POWER6 (architected)", - .cpu_features = CPU_FTRS_POWER6, - .cpu_user_features = COMMON_USER_POWER6, - .mmu_features = MMU_FTRS_POWER6, - .icache_bsize = 128, - .dcache_bsize = 128, - .oprofile_cpu_type = "ppc64/ibm-compat-v1", - .platform = "power6", - }, - { /* 2.06-compliant processor, i.e. Power7 "architected" mode */ - .pvr_mask = 0xffffffff, - .pvr_value = 0x0f000003, - .cpu_name = "POWER7 (architected)", - .cpu_features = CPU_FTRS_POWER7, - .cpu_user_features = COMMON_USER_POWER7, - .cpu_user_features2 = COMMON_USER2_POWER7, - .mmu_features = MMU_FTRS_POWER7, - .icache_bsize = 128, - .dcache_bsize = 128, - .oprofile_cpu_type = "ppc64/ibm-compat-v1", - .cpu_setup = __setup_cpu_power7, - .cpu_restore = __restore_cpu_power7, - .machine_check_early = __machine_check_early_realmode_p7, - .platform = "power7", - }, - { /* 2.07-compliant processor, i.e. Power8 "architected" mode */ - .pvr_mask = 0xffffffff, - .pvr_value = 0x0f000004, - .cpu_name = "POWER8 (architected)", - .cpu_features = CPU_FTRS_POWER8, - .cpu_user_features = COMMON_USER_POWER8, - .cpu_user_features2 = COMMON_USER2_POWER8, - .mmu_features = MMU_FTRS_POWER8, - .icache_bsize = 128, - .dcache_bsize = 128, - .oprofile_cpu_type = "ppc64/ibm-compat-v1", - .cpu_setup = __setup_cpu_power8, - .cpu_restore = __restore_cpu_power8, - .machine_check_early = __machine_check_early_realmode_p8, - .platform = "power8", - }, - { /* 3.00-compliant processor, i.e. Power9 "architected" mode */ - .pvr_mask = 0xffffffff, - .pvr_value = 0x0f000005, - .cpu_name = "POWER9 (architected)", - .cpu_features = CPU_FTRS_POWER9, - .cpu_user_features = COMMON_USER_POWER9, - .cpu_user_features2 = COMMON_USER2_POWER9, - .mmu_features = MMU_FTRS_POWER9, - .icache_bsize = 128, - .dcache_bsize = 128, - .oprofile_cpu_type = "ppc64/ibm-compat-v1", - .cpu_setup = __setup_cpu_power9, - .cpu_restore = __restore_cpu_power9, - .platform = "power9", - }, - { /* 3.1-compliant processor, i.e. Power10 "architected" mode */ - .pvr_mask = 0xffffffff, - .pvr_value = 0x0f000006, - .cpu_name = "POWER10 (architected)", - .cpu_features = CPU_FTRS_POWER10, - .cpu_user_features = COMMON_USER_POWER10, - .cpu_user_features2 = COMMON_USER2_POWER10, - .mmu_features = MMU_FTRS_POWER10, - .icache_bsize = 128, - .dcache_bsize = 128, - .oprofile_cpu_type = "ppc64/ibm-compat-v1", - .cpu_setup = __setup_cpu_power10, - .cpu_restore = __restore_cpu_power10, - .platform = "power10", - }, - { /* Power7 */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x003f0000, - .cpu_name = "POWER7 (raw)", - .cpu_features = CPU_FTRS_POWER7, - .cpu_user_features = COMMON_USER_POWER7, - .cpu_user_features2 = COMMON_USER2_POWER7, - .mmu_features = MMU_FTRS_POWER7, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 6, - .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power7", - .cpu_setup = __setup_cpu_power7, - .cpu_restore = __restore_cpu_power7, - .machine_check_early = __machine_check_early_realmode_p7, - .platform = "power7", - }, - { /* Power7+ */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x004A0000, - .cpu_name = "POWER7+ (raw)", - .cpu_features = CPU_FTRS_POWER7, - .cpu_user_features = COMMON_USER_POWER7, - .cpu_user_features2 = COMMON_USER2_POWER7, - .mmu_features = MMU_FTRS_POWER7, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 6, - .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power7", - .cpu_setup = __setup_cpu_power7, - .cpu_restore = __restore_cpu_power7, - .machine_check_early = __machine_check_early_realmode_p7, - .platform = "power7+", - }, - { /* Power8E */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x004b0000, - .cpu_name = "POWER8E (raw)", - .cpu_features = CPU_FTRS_POWER8E, - .cpu_user_features = COMMON_USER_POWER8, - .cpu_user_features2 = COMMON_USER2_POWER8, - .mmu_features = MMU_FTRS_POWER8, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 6, - .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power8", - .cpu_setup = __setup_cpu_power8, - .cpu_restore = __restore_cpu_power8, - .machine_check_early = __machine_check_early_realmode_p8, - .platform = "power8", - }, - { /* Power8NVL */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x004c0000, - .cpu_name = "POWER8NVL (raw)", - .cpu_features = CPU_FTRS_POWER8, - .cpu_user_features = COMMON_USER_POWER8, - .cpu_user_features2 = COMMON_USER2_POWER8, - .mmu_features = MMU_FTRS_POWER8, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 6, - .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power8", - .cpu_setup = __setup_cpu_power8, - .cpu_restore = __restore_cpu_power8, - .machine_check_early = __machine_check_early_realmode_p8, - .platform = "power8", - }, - { /* Power8 */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x004d0000, - .cpu_name = "POWER8 (raw)", - .cpu_features = CPU_FTRS_POWER8, - .cpu_user_features = COMMON_USER_POWER8, - .cpu_user_features2 = COMMON_USER2_POWER8, - .mmu_features = MMU_FTRS_POWER8, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 6, - .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power8", - .cpu_setup = __setup_cpu_power8, - .cpu_restore = __restore_cpu_power8, - .machine_check_early = __machine_check_early_realmode_p8, - .platform = "power8", - }, - { /* Power9 DD2.0 */ - .pvr_mask = 0xffffefff, - .pvr_value = 0x004e0200, - .cpu_name = "POWER9 (raw)", - .cpu_features = CPU_FTRS_POWER9_DD2_0, - .cpu_user_features = COMMON_USER_POWER9, - .cpu_user_features2 = COMMON_USER2_POWER9, - .mmu_features = MMU_FTRS_POWER9, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 6, - .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power9", - .cpu_setup = __setup_cpu_power9, - .cpu_restore = __restore_cpu_power9, - .machine_check_early = __machine_check_early_realmode_p9, - .platform = "power9", - }, - { /* Power9 DD 2.1 */ - .pvr_mask = 0xffffefff, - .pvr_value = 0x004e0201, - .cpu_name = "POWER9 (raw)", - .cpu_features = CPU_FTRS_POWER9_DD2_1, - .cpu_user_features = COMMON_USER_POWER9, - .cpu_user_features2 = COMMON_USER2_POWER9, - .mmu_features = MMU_FTRS_POWER9, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 6, - .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power9", - .cpu_setup = __setup_cpu_power9, - .cpu_restore = __restore_cpu_power9, - .machine_check_early = __machine_check_early_realmode_p9, - .platform = "power9", - }, - { /* Power9 DD2.2 or later */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x004e0000, - .cpu_name = "POWER9 (raw)", - .cpu_features = CPU_FTRS_POWER9_DD2_2, - .cpu_user_features = COMMON_USER_POWER9, - .cpu_user_features2 = COMMON_USER2_POWER9, - .mmu_features = MMU_FTRS_POWER9, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 6, - .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power9", - .cpu_setup = __setup_cpu_power9, - .cpu_restore = __restore_cpu_power9, - .machine_check_early = __machine_check_early_realmode_p9, - .platform = "power9", - }, - { /* Power10 */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x00800000, - .cpu_name = "POWER10 (raw)", - .cpu_features = CPU_FTRS_POWER10, - .cpu_user_features = COMMON_USER_POWER10, - .cpu_user_features2 = COMMON_USER2_POWER10, - .mmu_features = MMU_FTRS_POWER10, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 6, - .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power10", - .cpu_setup = __setup_cpu_power10, - .cpu_restore = __restore_cpu_power10, - .machine_check_early = __machine_check_early_realmode_p10, - .platform = "power10", - }, - { /* Cell Broadband Engine */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x00700000, - .cpu_name = "Cell Broadband Engine", - .cpu_features = CPU_FTRS_CELL, - .cpu_user_features = COMMON_USER_PPC64 | - PPC_FEATURE_CELL | PPC_FEATURE_HAS_ALTIVEC_COMP | - PPC_FEATURE_SMT, - .mmu_features = MMU_FTRS_CELL, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 4, - .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/cell-be", - .platform = "ppc-cell-be", - }, - { /* PA Semi PA6T */ - .pvr_mask = 0x7fff0000, - .pvr_value = 0x00900000, - .cpu_name = "PA6T", - .cpu_features = CPU_FTRS_PA6T, - .cpu_user_features = COMMON_USER_PA6T, - .mmu_features = MMU_FTRS_PA6T, - .icache_bsize = 64, - .dcache_bsize = 64, - .num_pmcs = 6, - .pmc_type = PPC_PMC_PA6T, - .cpu_setup = __setup_cpu_pa6t, - .cpu_restore = __restore_cpu_pa6t, - .oprofile_cpu_type = "ppc64/pa6t", - .platform = "pa6t", - }, - { /* default match */ - .pvr_mask = 0x00000000, - .pvr_value = 0x00000000, - .cpu_name = "POWER5 (compatible)", - .cpu_features = CPU_FTRS_COMPATIBLE, - .cpu_user_features = COMMON_USER_PPC64, - .mmu_features = MMU_FTRS_POWER, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 6, - .pmc_type = PPC_PMC_IBM, - .platform = "power5", - } -#endif /* CONFIG_PPC_BOOK3S_64 */ - -#ifdef CONFIG_PPC32 -#ifdef CONFIG_PPC_BOOK3S_32 -#ifdef CONFIG_PPC_BOOK3S_604 - { /* 604 */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x00040000, - .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, - .cpu_setup = __setup_cpu_604, - .machine_check = machine_check_generic, - .platform = "ppc604", - }, - { /* 604e */ - .pvr_mask = 0xfffff000, - .pvr_value = 0x00090000, - .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, - .cpu_setup = __setup_cpu_604, - .machine_check = machine_check_generic, - .platform = "ppc604", - }, - { /* 604r */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x00090000, - .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, - .cpu_setup = __setup_cpu_604, - .machine_check = machine_check_generic, - .platform = "ppc604", - }, - { /* 604ev */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x000a0000, - .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, - .cpu_setup = __setup_cpu_604, - .machine_check = machine_check_generic, - .platform = "ppc604", - }, - { /* 740/750 (0x4202, don't support TAU ?) */ - .pvr_mask = 0xffffffff, - .pvr_value = 0x00084202, - .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, - .cpu_setup = __setup_cpu_750, - .machine_check = machine_check_generic, - .platform = "ppc750", - }, - { /* 750CX (80100 and 8010x?) */ - .pvr_mask = 0xfffffff0, - .pvr_value = 0x00080100, - .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, - .cpu_setup = __setup_cpu_750cx, - .machine_check = machine_check_generic, - .platform = "ppc750", - }, - { /* 750CX (82201 and 82202) */ - .pvr_mask = 0xfffffff0, - .pvr_value = 0x00082200, - .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", - }, - { /* 750CXe (82214) */ - .pvr_mask = 0xfffffff0, - .pvr_value = 0x00082210, - .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", - }, - { /* 750CXe "Gekko" (83214) */ - .pvr_mask = 0xffffffff, - .pvr_value = 0x00083214, - .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", - }, - { /* 750CL (and "Broadway") */ - .pvr_mask = 0xfffff0e0, - .pvr_value = 0x00087000, - .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", - .oprofile_cpu_type = "ppc/750", - }, - { /* 745/755 */ - .pvr_mask = 0xfffff000, - .pvr_value = 0x00083000, - .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", - }, - { /* 750FX rev 1.x */ - .pvr_mask = 0xffffff00, - .pvr_value = 0x70000100, - .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", - .oprofile_cpu_type = "ppc/750", - }, - { /* 750FX rev 2.0 must disable HID0[DPM] */ - .pvr_mask = 0xffffffff, - .pvr_value = 0x70000200, - .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", - .oprofile_cpu_type = "ppc/750", - }, - { /* 750FX (All revs except 2.0) */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x70000000, - .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", - .oprofile_cpu_type = "ppc/750", - }, - { /* 750GX */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x70020000, - .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", - .oprofile_cpu_type = "ppc/750", - }, - { /* 740/750 (L2CR bit need fixup for 740) */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x00080000, - .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", - }, - { /* 7400 rev 1.1 ? (no TAU) */ - .pvr_mask = 0xffffffff, - .pvr_value = 0x000c1101, - .cpu_name = "7400 (1.1)", - .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", - }, - { /* 7400 */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x000c0000, - .cpu_name = "7400", - .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", - }, - { /* 7410 */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x800c0000, - .cpu_name = "7410", - .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", - }, - { /* 7450 2.0 - no doze/nap */ - .pvr_mask = 0xffffffff, - .pvr_value = 0x80000200, - .cpu_name = "7450", - .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", - .machine_check = machine_check_generic, - .platform = "ppc7450", - }, - { /* 7450 2.1 */ - .pvr_mask = 0xffffffff, - .pvr_value = 0x80000201, - .cpu_name = "7450", - .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", - .machine_check = machine_check_generic, - .platform = "ppc7450", - }, - { /* 7450 2.3 and newer */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x80000000, - .cpu_name = "7450", - .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", - .machine_check = machine_check_generic, - .platform = "ppc7450", - }, - { /* 7455 rev 1.x */ - .pvr_mask = 0xffffff00, - .pvr_value = 0x80010100, - .cpu_name = "7455", - .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", - .machine_check = machine_check_generic, - .platform = "ppc7450", - }, - { /* 7455 rev 2.0 */ - .pvr_mask = 0xffffffff, - .pvr_value = 0x80010200, - .cpu_name = "7455", - .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", - .machine_check = machine_check_generic, - .platform = "ppc7450", - }, - { /* 7455 others */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x80010000, - .cpu_name = "7455", - .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", - .machine_check = machine_check_generic, - .platform = "ppc7450", - }, - { /* 7447/7457 Rev 1.0 */ - .pvr_mask = 0xffffffff, - .pvr_value = 0x80020100, - .cpu_name = "7447/7457", - .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", - .machine_check = machine_check_generic, - .platform = "ppc7450", - }, - { /* 7447/7457 Rev 1.1 */ - .pvr_mask = 0xffffffff, - .pvr_value = 0x80020101, - .cpu_name = "7447/7457", - .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", - .machine_check = machine_check_generic, - .platform = "ppc7450", - }, - { /* 7447/7457 Rev 1.2 and later */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x80020000, - .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", - .machine_check = machine_check_generic, - .platform = "ppc7450", - }, - { /* 7447A */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x80030000, - .cpu_name = "7447A", - .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", - .machine_check = machine_check_generic, - .platform = "ppc7450", - }, - { /* 7448 */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x80040000, - .cpu_name = "7448", - .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", - .machine_check = machine_check_generic, - .platform = "ppc7450", - }, -#endif /* CONFIG_PPC_BOOK3S_604 */ -#ifdef CONFIG_PPC_BOOK3S_603 - { /* 603 */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x00030000, - .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, - .machine_check = machine_check_generic, - .platform = "ppc603", - }, - { /* 603e */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x00060000, - .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, - .machine_check = machine_check_generic, - .platform = "ppc603", - }, - { /* 603ev */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x00070000, - .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, - .machine_check = machine_check_generic, - .platform = "ppc603", - }, - { /* 82xx (8240, 8245, 8260 are all 603e cores) */ - .pvr_mask = 0x7fff0000, - .pvr_value = 0x00810000, - .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, - .machine_check = machine_check_generic, - .platform = "ppc603", - }, - { /* All G2_LE (603e core, plus some) have the same pvr */ - .pvr_mask = 0x7fff0000, - .pvr_value = 0x00820000, - .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, - .machine_check = machine_check_generic, - .platform = "ppc603", - }, -#ifdef CONFIG_PPC_83xx - { /* e300c1 (a 603e core, plus some) on 83xx */ - .pvr_mask = 0x7fff0000, - .pvr_value = 0x00830000, - .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, - .machine_check = machine_check_83xx, - .platform = "ppc603", - }, - { /* e300c2 (an e300c1 core, plus some, minus FPU) on 83xx */ - .pvr_mask = 0x7fff0000, - .pvr_value = 0x00840000, - .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 | - MMU_FTR_NEED_DTLB_SW_LRU, - .icache_bsize = 32, - .dcache_bsize = 32, - .cpu_setup = __setup_cpu_603, - .machine_check = machine_check_83xx, - .platform = "ppc603", - }, - { /* e300c3 (e300c1, plus one IU, half cache size) on 83xx */ - .pvr_mask = 0x7fff0000, - .pvr_value = 0x00850000, - .cpu_name = "e300c3", - .cpu_features = CPU_FTRS_E300, - .cpu_user_features = COMMON_USER, - .mmu_features = MMU_FTR_USE_HIGH_BATS | - MMU_FTR_NEED_DTLB_SW_LRU, - .icache_bsize = 32, - .dcache_bsize = 32, - .cpu_setup = __setup_cpu_603, - .machine_check = machine_check_83xx, - .num_pmcs = 4, - .oprofile_cpu_type = "ppc/e300", - .platform = "ppc603", - }, - { /* e300c4 (e300c1, plus one IU) */ - .pvr_mask = 0x7fff0000, - .pvr_value = 0x00860000, - .cpu_name = "e300c4", - .cpu_features = CPU_FTRS_E300, - .cpu_user_features = COMMON_USER, - .mmu_features = MMU_FTR_USE_HIGH_BATS | - MMU_FTR_NEED_DTLB_SW_LRU, - .icache_bsize = 32, - .dcache_bsize = 32, - .cpu_setup = __setup_cpu_603, - .machine_check = machine_check_83xx, - .num_pmcs = 4, - .oprofile_cpu_type = "ppc/e300", - .platform = "ppc603", - }, -#endif -#endif /* CONFIG_PPC_BOOK3S_603 */ -#ifdef CONFIG_PPC_BOOK3S_604 - { /* default match, we assume split I/D cache & TB (non-601)... */ - .pvr_mask = 0x00000000, - .pvr_value = 0x00000000, - .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, - .platform = "ppc603", - }, -#endif /* CONFIG_PPC_BOOK3S_604 */ -#endif /* CONFIG_PPC_BOOK3S_32 */ -#ifdef CONFIG_PPC_8xx - { /* 8xx */ - .pvr_mask = 0xffff0000, - .pvr_value = PVR_8xx, - .cpu_name = "8xx", - /* CPU_FTR_MAYBE_CAN_DOZE is possible, - * 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, - .machine_check = machine_check_8xx, - .platform = "ppc823", - }, -#endif /* CONFIG_PPC_8xx */ -#ifdef CONFIG_40x - { /* STB 04xxx */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x41810000, - .cpu_name = "STB04xxx", - .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", - }, - { /* NP405L */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x41610000, - .cpu_name = "NP405L", - .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", - }, - { /* NP4GS3 */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x40B10000, - .cpu_name = "NP4GS3", - .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", - }, - { /* NP405H */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x41410000, - .cpu_name = "NP405H", - .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", - }, - { /* 405GPr */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x50910000, - .cpu_name = "405GPr", - .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", - }, - { /* STBx25xx */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x51510000, - .cpu_name = "STBx25xx", - .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", - }, - { /* 405LP */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x41F10000, - .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, - .platform = "ppc405", - }, - { /* 405EP */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x51210000, - .cpu_name = "405EP", - .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", - }, - { /* 405EX Rev. A/B with Security */ - .pvr_mask = 0xffff000f, - .pvr_value = 0x12910007, - .cpu_name = "405EX Rev. A/B", - .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", - }, - { /* 405EX Rev. C without Security */ - .pvr_mask = 0xffff000f, - .pvr_value = 0x1291000d, - .cpu_name = "405EX Rev. C", - .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", - }, - { /* 405EX Rev. C with Security */ - .pvr_mask = 0xffff000f, - .pvr_value = 0x1291000f, - .cpu_name = "405EX Rev. C", - .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", - }, - { /* 405EX Rev. D without Security */ - .pvr_mask = 0xffff000f, - .pvr_value = 0x12910003, - .cpu_name = "405EX Rev. D", - .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", - }, - { /* 405EX Rev. D with Security */ - .pvr_mask = 0xffff000f, - .pvr_value = 0x12910005, - .cpu_name = "405EX Rev. D", - .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", - }, - { /* 405EXr Rev. A/B without Security */ - .pvr_mask = 0xffff000f, - .pvr_value = 0x12910001, - .cpu_name = "405EXr Rev. A/B", - .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", - }, - { /* 405EXr Rev. C without Security */ - .pvr_mask = 0xffff000f, - .pvr_value = 0x12910009, - .cpu_name = "405EXr Rev. C", - .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", - }, - { /* 405EXr Rev. C with Security */ - .pvr_mask = 0xffff000f, - .pvr_value = 0x1291000b, - .cpu_name = "405EXr Rev. C", - .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", - }, - { /* 405EXr Rev. D without Security */ - .pvr_mask = 0xffff000f, - .pvr_value = 0x12910000, - .cpu_name = "405EXr Rev. D", - .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", - }, - { /* 405EXr Rev. D with Security */ - .pvr_mask = 0xffff000f, - .pvr_value = 0x12910002, - .cpu_name = "405EXr Rev. D", - .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, - .platform = "ppc405", - }, - { /* APM8018X */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x7ff11432, - .cpu_name = "APM8018X", - .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", - }, - { /* default match */ - .pvr_mask = 0x00000000, - .pvr_value = 0x00000000, - .cpu_name = "(generic 40x PPC)", - .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", - } - -#endif /* CONFIG_40x */ -#ifdef CONFIG_44x -#ifndef CONFIG_PPC_47x - { - .pvr_mask = 0xf0000fff, - .pvr_value = 0x40000850, - .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, - .platform = "ppc440", - }, - { /* Use logical PVR for 440EP (logical pvr = pvr | 0x8) */ - .pvr_mask = 0xf0000fff, - .pvr_value = 0x40000858, - .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, - .machine_check = machine_check_4xx, - .platform = "ppc440", - }, - { - .pvr_mask = 0xf0000fff, - .pvr_value = 0x400008d3, - .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, - .platform = "ppc440", - }, - { /* Matches both physical and logical PVR for 440EP (logical pvr = pvr | 0x8) */ - .pvr_mask = 0xf0000ff7, - .pvr_value = 0x400008d4, - .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, - .machine_check = machine_check_4xx, - .platform = "ppc440", - }, - { /* Use logical PVR for 440EP (logical pvr = pvr | 0x8) */ - .pvr_mask = 0xf0000fff, - .pvr_value = 0x400008db, - .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, - .machine_check = machine_check_4xx, - .platform = "ppc440", - }, - { /* 440GRX */ - .pvr_mask = 0xf0000ffb, - .pvr_value = 0x200008D0, - .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, - .machine_check = machine_check_440A, - .platform = "ppc440", - }, - { /* Use logical PVR for 440EPx (logical pvr = pvr | 0x8) */ - .pvr_mask = 0xf0000ffb, - .pvr_value = 0x200008D8, - .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, - .machine_check = machine_check_440A, - .platform = "ppc440", - }, - { /* 440GP Rev. B */ - .pvr_mask = 0xf0000fff, - .pvr_value = 0x40000440, - .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, - .platform = "ppc440gp", - }, - { /* 440GP Rev. C */ - .pvr_mask = 0xf0000fff, - .pvr_value = 0x40000481, - .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, - .platform = "ppc440gp", - }, - { /* 440GX Rev. A */ - .pvr_mask = 0xf0000fff, - .pvr_value = 0x50000850, - .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, - .machine_check = machine_check_440A, - .platform = "ppc440", - }, - { /* 440GX Rev. B */ - .pvr_mask = 0xf0000fff, - .pvr_value = 0x50000851, - .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, - .machine_check = machine_check_440A, - .platform = "ppc440", - }, - { /* 440GX Rev. C */ - .pvr_mask = 0xf0000fff, - .pvr_value = 0x50000892, - .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, - .machine_check = machine_check_440A, - .platform = "ppc440", - }, - { /* 440GX Rev. F */ - .pvr_mask = 0xf0000fff, - .pvr_value = 0x50000894, - .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, - .machine_check = machine_check_440A, - .platform = "ppc440", - }, - { /* 440SP Rev. A */ - .pvr_mask = 0xfff00fff, - .pvr_value = 0x53200891, - .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, - .platform = "ppc440", - }, - { /* 440SPe Rev. A */ - .pvr_mask = 0xfff00fff, - .pvr_value = 0x53400890, - .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, - .machine_check = machine_check_440A, - .platform = "ppc440", - }, - { /* 440SPe Rev. B */ - .pvr_mask = 0xfff00fff, - .pvr_value = 0x53400891, - .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, - .machine_check = machine_check_440A, - .platform = "ppc440", - }, - { /* 460EX */ - .pvr_mask = 0xffff0006, - .pvr_value = 0x13020002, - .cpu_name = "460EX", - .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, - .machine_check = machine_check_440A, - .platform = "ppc440", - }, - { /* 460EX Rev B */ - .pvr_mask = 0xffff0007, - .pvr_value = 0x13020004, - .cpu_name = "460EX Rev. B", - .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, - .machine_check = machine_check_440A, - .platform = "ppc440", - }, - { /* 460GT */ - .pvr_mask = 0xffff0006, - .pvr_value = 0x13020000, - .cpu_name = "460GT", - .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, - .machine_check = machine_check_440A, - .platform = "ppc440", - }, - { /* 460GT Rev B */ - .pvr_mask = 0xffff0007, - .pvr_value = 0x13020005, - .cpu_name = "460GT Rev. B", - .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, - .machine_check = machine_check_440A, - .platform = "ppc440", - }, - { /* 460SX */ - .pvr_mask = 0xffffff00, - .pvr_value = 0x13541800, - .cpu_name = "460SX", - .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_460sx, - .machine_check = machine_check_440A, - .platform = "ppc440", - }, - { /* 464 in APM821xx */ - .pvr_mask = 0xfffffff0, - .pvr_value = 0x12C41C80, - .cpu_name = "APM821XX", - .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_apm821xx, - .machine_check = machine_check_440A, - .platform = "ppc440", - }, - { /* default match */ - .pvr_mask = 0x00000000, - .pvr_value = 0x00000000, - .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, - .platform = "ppc440", - } -#else /* CONFIG_PPC_47x */ - { /* 476 DD2 core */ - .pvr_mask = 0xffffffff, - .pvr_value = 0x11a52080, - .cpu_name = "476", - .cpu_features = CPU_FTRS_47X | CPU_FTR_476_DD2, - .cpu_user_features = COMMON_USER_BOOKE | - PPC_FEATURE_HAS_FPU, - .mmu_features = MMU_FTR_TYPE_47x | - MMU_FTR_USE_TLBIVAX_BCAST | MMU_FTR_LOCK_BCAST_INVAL, - .icache_bsize = 32, - .dcache_bsize = 128, - .machine_check = machine_check_47x, - .platform = "ppc470", - }, - { /* 476fpe */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x7ff50000, - .cpu_name = "476fpe", - .cpu_features = CPU_FTRS_47X | CPU_FTR_476_DD2, - .cpu_user_features = COMMON_USER_BOOKE | - PPC_FEATURE_HAS_FPU, - .mmu_features = MMU_FTR_TYPE_47x | - MMU_FTR_USE_TLBIVAX_BCAST | MMU_FTR_LOCK_BCAST_INVAL, - .icache_bsize = 32, - .dcache_bsize = 128, - .machine_check = machine_check_47x, - .platform = "ppc470", - }, - { /* 476 iss */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x00050000, - .cpu_name = "476", - .cpu_features = CPU_FTRS_47X, - .cpu_user_features = COMMON_USER_BOOKE | - PPC_FEATURE_HAS_FPU, - .mmu_features = MMU_FTR_TYPE_47x | - MMU_FTR_USE_TLBIVAX_BCAST | MMU_FTR_LOCK_BCAST_INVAL, - .icache_bsize = 32, - .dcache_bsize = 128, - .machine_check = machine_check_47x, - .platform = "ppc470", - }, - { /* 476 others */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x11a50000, - .cpu_name = "476", - .cpu_features = CPU_FTRS_47X, - .cpu_user_features = COMMON_USER_BOOKE | - PPC_FEATURE_HAS_FPU, - .mmu_features = MMU_FTR_TYPE_47x | - MMU_FTR_USE_TLBIVAX_BCAST | MMU_FTR_LOCK_BCAST_INVAL, - .icache_bsize = 32, - .dcache_bsize = 128, - .machine_check = machine_check_47x, - .platform = "ppc470", - }, - { /* default match */ - .pvr_mask = 0x00000000, - .pvr_value = 0x00000000, - .cpu_name = "(generic 47x PPC)", - .cpu_features = CPU_FTRS_47X, - .cpu_user_features = COMMON_USER_BOOKE, - .mmu_features = MMU_FTR_TYPE_47x, - .icache_bsize = 32, - .dcache_bsize = 128, - .machine_check = machine_check_47x, - .platform = "ppc470", - } -#endif /* CONFIG_PPC_47x */ -#endif /* CONFIG_44x */ -#endif /* CONFIG_PPC32 */ -#ifdef CONFIG_E500 -#ifdef CONFIG_PPC32 -#ifndef CONFIG_PPC_E500MC - { /* e500 */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x80200000, - .cpu_name = "e500", - .cpu_features = CPU_FTRS_E500, - .cpu_user_features = COMMON_USER_BOOKE | - PPC_FEATURE_HAS_SPE_COMP | - PPC_FEATURE_HAS_EFP_SINGLE_COMP, - .cpu_user_features2 = PPC_FEATURE2_ISEL, - .mmu_features = MMU_FTR_TYPE_FSL_E, - .icache_bsize = 32, - .dcache_bsize = 32, - .num_pmcs = 4, - .oprofile_cpu_type = "ppc/e500", - .cpu_setup = __setup_cpu_e500v1, - .machine_check = machine_check_e500, - .platform = "ppc8540", - }, - { /* e500v2 */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x80210000, - .cpu_name = "e500v2", - .cpu_features = CPU_FTRS_E500_2, - .cpu_user_features = COMMON_USER_BOOKE | - PPC_FEATURE_HAS_SPE_COMP | - PPC_FEATURE_HAS_EFP_SINGLE_COMP | - PPC_FEATURE_HAS_EFP_DOUBLE_COMP, - .cpu_user_features2 = PPC_FEATURE2_ISEL, - .mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS, - .icache_bsize = 32, - .dcache_bsize = 32, - .num_pmcs = 4, - .oprofile_cpu_type = "ppc/e500", - .cpu_setup = __setup_cpu_e500v2, - .machine_check = machine_check_e500, - .platform = "ppc8548", - .cpu_down_flush = cpu_down_flush_e500v2, - }, -#else - { /* e500mc */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x80230000, - .cpu_name = "e500mc", - .cpu_features = CPU_FTRS_E500MC, - .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, - .cpu_user_features2 = PPC_FEATURE2_ISEL, - .mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS | - MMU_FTR_USE_TLBILX, - .icache_bsize = 64, - .dcache_bsize = 64, - .num_pmcs = 4, - .oprofile_cpu_type = "ppc/e500mc", - .cpu_setup = __setup_cpu_e500mc, - .machine_check = machine_check_e500mc, - .platform = "ppce500mc", - .cpu_down_flush = cpu_down_flush_e500mc, - }, -#endif /* CONFIG_PPC_E500MC */ -#endif /* CONFIG_PPC32 */ -#ifdef CONFIG_PPC_E500MC - { /* e5500 */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x80240000, - .cpu_name = "e5500", - .cpu_features = CPU_FTRS_E5500, - .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, - .cpu_user_features2 = PPC_FEATURE2_ISEL, - .mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS | - MMU_FTR_USE_TLBILX, - .icache_bsize = 64, - .dcache_bsize = 64, - .num_pmcs = 4, - .oprofile_cpu_type = "ppc/e500mc", - .cpu_setup = __setup_cpu_e5500, -#ifndef CONFIG_PPC32 - .cpu_restore = __restore_cpu_e5500, -#endif - .machine_check = machine_check_e500mc, - .platform = "ppce5500", - .cpu_down_flush = cpu_down_flush_e5500, - }, - { /* e6500 */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x80400000, - .cpu_name = "e6500", - .cpu_features = CPU_FTRS_E6500, - .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU | - PPC_FEATURE_HAS_ALTIVEC_COMP, - .cpu_user_features2 = PPC_FEATURE2_ISEL, - .mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS | - MMU_FTR_USE_TLBILX, - .icache_bsize = 64, - .dcache_bsize = 64, - .num_pmcs = 6, - .oprofile_cpu_type = "ppc/e6500", - .cpu_setup = __setup_cpu_e6500, -#ifndef CONFIG_PPC32 - .cpu_restore = __restore_cpu_e6500, -#endif - .machine_check = machine_check_e500mc, - .platform = "ppce6500", - .cpu_down_flush = cpu_down_flush_e6500, - }, -#endif /* CONFIG_PPC_E500MC */ -#ifdef CONFIG_PPC32 - { /* default match */ - .pvr_mask = 0x00000000, - .pvr_value = 0x00000000, - .cpu_name = "(generic E500 PPC)", - .cpu_features = CPU_FTRS_E500, - .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, - .platform = "powerpc", - } -#endif /* CONFIG_PPC32 */ -#endif /* CONFIG_E500 */ -}; +#include "cpu_specs.h" void __init set_cur_cpu_spec(struct cpu_spec *s) { @@ -2015,23 +69,10 @@ static struct cpu_spec * __init setup_cpu_spec(unsigned long offset, t->pmc_type = old.pmc_type; /* - * If we have passed through this logic once before and - * have pulled the default case because the real PVR was - * not found inside cpu_specs[], then we are possibly - * running in compatibility mode. In that case, let the - * oprofiler know which set of compatibility counters to - * pull from by making sure the oprofile_cpu_type string - * is set to that of compatibility mode. If the - * oprofile_cpu_type already has a value, then we are - * possibly overriding a real PVR with a logical one, - * and, in that case, keep the current value for - * oprofile_cpu_type. Futhermore, let's ensure that the + * Let's ensure that the * fix for the PMAO bug is enabled on compatibility mode. */ - if (old.oprofile_cpu_type != NULL) { - t->oprofile_cpu_type = old.oprofile_cpu_type; - t->cpu_features |= old.cpu_features & CPU_FTR_PMAO_BUG; - } + t->cpu_features |= old.cpu_features & CPU_FTR_PMAO_BUG; } *PTRRELOC(&cur_cpu_spec) = &the_cpu_spec; @@ -2063,6 +104,8 @@ struct cpu_spec * __init identify_cpu(unsigned long offset, unsigned int pvr) struct cpu_spec *s = cpu_specs; int i; + BUILD_BUG_ON(!ARRAY_SIZE(cpu_specs)); + s = PTRRELOC(s); for (i = 0; i < ARRAY_SIZE(cpu_specs); i++,s++) { @@ -2119,7 +162,7 @@ void __init cpu_feature_keys_init(void) struct static_key_true mmu_feature_keys[NUM_MMU_FTR_KEYS] = { [0 ... NUM_MMU_FTR_KEYS - 1] = STATIC_KEY_TRUE_INIT }; -EXPORT_SYMBOL_GPL(mmu_feature_keys); +EXPORT_SYMBOL(mmu_feature_keys); void __init mmu_feature_keys_init(void) { diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c index 5693e1c67c2b..9a3b85bfc83f 100644 --- a/arch/powerpc/kernel/crash_dump.c +++ b/arch/powerpc/kernel/crash_dump.c @@ -12,11 +12,11 @@ #include <linux/crash_dump.h> #include <linux/io.h> #include <linux/memblock.h> +#include <linux/of.h> #include <asm/code-patching.h> #include <asm/kdump.h> -#include <asm/prom.h> #include <asm/firmware.h> -#include <linux/uaccess.h> +#include <linux/uio.h> #include <asm/rtas.h> #include <asm/inst.h> @@ -68,33 +68,8 @@ void __init setup_kdump_trampoline(void) } #endif /* CONFIG_NONSTATIC_KERNEL */ -static size_t copy_oldmem_vaddr(void *vaddr, char *buf, size_t csize, - unsigned long offset, int userbuf) -{ - if (userbuf) { - if (copy_to_user((char __user *)buf, (vaddr + offset), csize)) - return -EFAULT; - } else - memcpy(buf, (vaddr + offset), csize); - - return csize; -} - -/** - * copy_oldmem_page - copy one page from "oldmem" - * @pfn: page frame number to be copied - * @buf: target memory address for the copy; this can be in kernel address - * space or user address space (see @userbuf) - * @csize: number of bytes to copy - * @offset: offset in bytes into the page (based on pfn) to begin the copy - * @userbuf: if set, @buf is in user address space, use copy_to_user(), - * otherwise @buf is in kernel address space, use memcpy(). - * - * Copy a page from "oldmem". For this page, there is no pte mapped - * in the current kernel. We stitch up a pte, similar to kmap_atomic. - */ -ssize_t copy_oldmem_page(unsigned long pfn, char *buf, - size_t csize, unsigned long offset, int userbuf) +ssize_t copy_oldmem_page(struct iov_iter *iter, unsigned long pfn, + size_t csize, unsigned long offset) { void *vaddr; phys_addr_t paddr; @@ -107,10 +82,10 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf, if (memblock_is_region_memory(paddr, csize)) { vaddr = __va(paddr); - csize = copy_oldmem_vaddr(vaddr, buf, csize, offset, userbuf); + csize = copy_to_iter(vaddr + offset, csize, iter); } else { vaddr = ioremap_cache(paddr, PAGE_SIZE); - csize = copy_oldmem_vaddr(vaddr, buf, csize, offset, userbuf); + csize = copy_to_iter(vaddr + offset, csize, iter); iounmap(vaddr); } diff --git a/arch/powerpc/kernel/dawr.c b/arch/powerpc/kernel/dawr.c index 64e423d2fe0f..909a05cd2809 100644 --- a/arch/powerpc/kernel/dawr.c +++ b/arch/powerpc/kernel/dawr.c @@ -11,6 +11,7 @@ #include <linux/debugfs.h> #include <asm/machdep.h> #include <asm/hvcall.h> +#include <asm/firmware.h> bool dawr_force_enable; EXPORT_SYMBOL_GPL(dawr_force_enable); @@ -27,7 +28,7 @@ int set_dawr(int nr, struct arch_hw_breakpoint *brk) dawrx |= (brk->type & (HW_BRK_TYPE_PRIV_ALL)) >> 3; /* * DAWR length is stored in field MDR bits 48:53. Matches range in - * doublewords (64 bits) baised by -1 eg. 0b000000=1DW and + * doublewords (64 bits) biased by -1 eg. 0b000000=1DW and * 0b111111=64DW. * brk->hw_len is in bytes. * This aligns up to double word size, shifts and does the bias. diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c index 5545c9cd17c1..f55c6fb34a3a 100644 --- a/arch/powerpc/kernel/dbell.c +++ b/arch/powerpc/kernel/dbell.c @@ -27,7 +27,8 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(doorbell_exception) ppc_msgsync(); - may_hard_irq_enable(); + if (should_hard_irq_enable()) + do_hard_irq_enable(); kvmppc_clear_host_ipi(smp_processor_id()); __this_cpu_inc(irq_stat.doorbell_irqs); diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c index fc7816126a40..ba256c37bcc0 100644 --- a/arch/powerpc/kernel/dma-swiotlb.c +++ b/arch/powerpc/kernel/dma-swiotlb.c @@ -10,6 +10,7 @@ #include <asm/swiotlb.h> unsigned int ppc_swiotlb_enable; +unsigned int ppc_swiotlb_flags; void __init swiotlb_detect_4g(void) { diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index ba527fb52993..c3fb9fdf5bd7 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -10,6 +10,7 @@ #include <linux/jump_label.h> #include <linux/libfdt.h> #include <linux/memblock.h> +#include <linux/of_fdt.h> #include <linux/printk.h> #include <linux/sched.h> #include <linux/string.h> @@ -19,7 +20,6 @@ #include <asm/dt_cpu_ftrs.h> #include <asm/mce.h> #include <asm/mmu.h> -#include <asm/prom.h> #include <asm/setup.h> @@ -80,6 +80,7 @@ static void __restore_cpu_cpufeatures(void) mtspr(SPRN_LPCR, system_registers.lpcr); if (hv_mode) { mtspr(SPRN_LPID, 0); + mtspr(SPRN_AMOR, ~0); mtspr(SPRN_HFSCR, system_registers.hfscr); mtspr(SPRN_PCR, system_registers.pcr); } @@ -101,7 +102,6 @@ static struct cpu_spec __initdata base_cpu_spec = { .dcache_bsize = 32, /* cache info init. */ .num_pmcs = 0, .pmc_type = PPC_PMC_DEFAULT, - .oprofile_cpu_type = NULL, .cpu_setup = NULL, .cpu_restore = __restore_cpu_cpufeatures, .machine_check_early = NULL, @@ -216,6 +216,7 @@ static int __init feat_enable_hv(struct dt_cpu_feature *f) } mtspr(SPRN_LPID, 0); + mtspr(SPRN_AMOR, ~0); lpcr = mfspr(SPRN_LPCR); lpcr &= ~LPCR_LPES0; /* HV external interrupts */ @@ -271,6 +272,9 @@ static int __init feat_enable_mmu_hash(struct dt_cpu_feature *f) { u64 lpcr; + if (!IS_ENABLED(CONFIG_PPC_64S_HASH_MMU)) + return 0; + lpcr = mfspr(SPRN_LPCR); lpcr &= ~LPCR_ISL; @@ -290,6 +294,9 @@ static int __init feat_enable_mmu_hash_v3(struct dt_cpu_feature *f) { u64 lpcr; + if (!IS_ENABLED(CONFIG_PPC_64S_HASH_MMU)) + return 0; + lpcr = mfspr(SPRN_LPCR); lpcr &= ~(LPCR_ISL | LPCR_UPRT | LPCR_HR); mtspr(SPRN_LPCR, lpcr); @@ -303,15 +310,15 @@ static int __init feat_enable_mmu_hash_v3(struct dt_cpu_feature *f) static int __init feat_enable_mmu_radix(struct dt_cpu_feature *f) { -#ifdef CONFIG_PPC_RADIX_MMU + if (!IS_ENABLED(CONFIG_PPC_RADIX_MMU)) + return 0; + + cur_cpu_spec->mmu_features |= MMU_FTR_KERNEL_RO; cur_cpu_spec->mmu_features |= MMU_FTR_TYPE_RADIX; - cur_cpu_spec->mmu_features |= MMU_FTRS_HASH_BASE; cur_cpu_spec->mmu_features |= MMU_FTR_GTSE; cur_cpu_spec->cpu_user_features |= PPC_FEATURE_HAS_MMU; return 1; -#endif - return 0; } static int __init feat_enable_dscr(struct dt_cpu_feature *f) @@ -336,7 +343,7 @@ static int __init feat_enable_dscr(struct dt_cpu_feature *f) return 1; } -static void hfscr_pmu_enable(void) +static void __init hfscr_pmu_enable(void) { u64 hfscr = mfspr(SPRN_HFSCR); hfscr |= PPC_BIT(60); @@ -351,7 +358,7 @@ static void init_pmu_power8(void) } mtspr(SPRN_MMCRA, 0); - mtspr(SPRN_MMCR0, 0); + mtspr(SPRN_MMCR0, MMCR0_FC); mtspr(SPRN_MMCR1, 0); mtspr(SPRN_MMCR2, 0); mtspr(SPRN_MMCRS, 0); @@ -379,7 +386,6 @@ static int __init feat_enable_pmu_power8(struct dt_cpu_feature *f) cur_cpu_spec->num_pmcs = 6; cur_cpu_spec->pmc_type = PPC_PMC_IBM; - cur_cpu_spec->oprofile_cpu_type = "ppc64/power8"; return 1; } @@ -390,7 +396,7 @@ static void init_pmu_power9(void) mtspr(SPRN_MMCRC, 0); mtspr(SPRN_MMCRA, 0); - mtspr(SPRN_MMCR0, 0); + mtspr(SPRN_MMCR0, MMCR0_FC); mtspr(SPRN_MMCR1, 0); mtspr(SPRN_MMCR2, 0); } @@ -415,7 +421,6 @@ static int __init feat_enable_pmu_power9(struct dt_cpu_feature *f) cur_cpu_spec->num_pmcs = 6; cur_cpu_spec->pmc_type = PPC_PMC_IBM; - cur_cpu_spec->oprofile_cpu_type = "ppc64/power9"; return 1; } @@ -426,7 +431,7 @@ static void init_pmu_power10(void) mtspr(SPRN_MMCR3, 0); mtspr(SPRN_MMCRA, MMCRA_BHRB_DISABLE); - mtspr(SPRN_MMCR0, MMCR0_PMCCEXT); + mtspr(SPRN_MMCR0, MMCR0_FC | MMCR0_PMCCEXT); } static int __init feat_enable_pmu_power10(struct dt_cpu_feature *f) @@ -441,7 +446,6 @@ static int __init feat_enable_pmu_power10(struct dt_cpu_feature *f) cur_cpu_spec->num_pmcs = 6; cur_cpu_spec->pmc_type = PPC_PMC_IBM; - cur_cpu_spec->oprofile_cpu_type = "ppc64/power10"; return 1; } @@ -766,20 +770,26 @@ static __init void cpufeatures_cpu_quirks(void) if ((version & 0xffffefff) == 0x004e0200) { /* DD2.0 has no feature flag */ cur_cpu_spec->cpu_features |= CPU_FTR_P9_RADIX_PREFETCH_BUG; + cur_cpu_spec->cpu_features &= ~(CPU_FTR_DAWR); } else if ((version & 0xffffefff) == 0x004e0201) { cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1; cur_cpu_spec->cpu_features |= CPU_FTR_P9_RADIX_PREFETCH_BUG; + cur_cpu_spec->cpu_features &= ~(CPU_FTR_DAWR); } else if ((version & 0xffffefff) == 0x004e0202) { cur_cpu_spec->cpu_features |= CPU_FTR_P9_TM_HV_ASSIST; cur_cpu_spec->cpu_features |= CPU_FTR_P9_TM_XER_SO_BUG; cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1; + cur_cpu_spec->cpu_features &= ~(CPU_FTR_DAWR); + } else if ((version & 0xffffefff) == 0x004e0203) { + cur_cpu_spec->cpu_features |= CPU_FTR_P9_TM_HV_ASSIST; + cur_cpu_spec->cpu_features |= CPU_FTR_P9_TM_XER_SO_BUG; + cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1; } else if ((version & 0xffff0000) == 0x004e0000) { /* DD2.1 and up have DD2_1 */ cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1; } if ((version & 0xffff0000) == 0x004e0000) { - cur_cpu_spec->cpu_features &= ~(CPU_FTR_DAWR); cur_cpu_spec->cpu_features |= CPU_FTR_P9_TIDR; } @@ -1089,7 +1099,7 @@ static int __init dt_cpu_ftrs_scan_callback(unsigned long node, const char prop = of_get_flat_dt_prop(node, "display-name", NULL); if (prop && strlen((char *)prop) != 0) { - strlcpy(dt_cpu_name, (char *)prop, sizeof(dt_cpu_name)); + strscpy(dt_cpu_name, (char *)prop, sizeof(dt_cpu_name)); cur_cpu_spec->cpu_name = dt_cpu_name; } diff --git a/arch/powerpc/kernel/early_32.c b/arch/powerpc/kernel/early_32.c index ef2ad4945904..03f1135ef64f 100644 --- a/arch/powerpc/kernel/early_32.c +++ b/arch/powerpc/kernel/early_32.c @@ -8,7 +8,6 @@ #include <linux/kernel.h> #include <asm/setup.h> #include <asm/sections.h> -#include <asm/asm-prototypes.h> /* * We're called here very early in the boot. diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 28bb1e7263a6..ab316e155ea9 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -1329,7 +1329,7 @@ int eeh_pe_set_option(struct eeh_pe *pe, int option) /* * EEH functionality could possibly be disabled, just - * return error for the case. And the EEH functinality + * return error for the case. And the EEH functionality * isn't expected to be disabled on one specific PE. */ switch (option) { @@ -1804,7 +1804,7 @@ static int eeh_debugfs_break_device(struct pci_dev *pdev) * PE freeze. Using the in_8() accessor skips the eeh detection hook * so the freeze hook so the EEH Detection machinery won't be * triggered here. This is to match the usual behaviour of EEH - * where the HW will asyncronously freeze a PE and it's up to + * where the HW will asynchronously freeze a PE and it's up to * the kernel to notice and deal with it. * * 3. Turn Memory space back on. This is more important for VFs diff --git a/arch/powerpc/kernel/eeh_cache.c b/arch/powerpc/kernel/eeh_cache.c index 9bdaaf7fddc9..2f9dbf8ad2ee 100644 --- a/arch/powerpc/kernel/eeh_cache.c +++ b/arch/powerpc/kernel/eeh_cache.c @@ -280,7 +280,7 @@ static int eeh_addr_cache_show(struct seq_file *s, void *v) } DEFINE_SHOW_ATTRIBUTE(eeh_addr_cache); -void eeh_cache_debugfs_init(void) +void __init eeh_cache_debugfs_init(void) { debugfs_create_file_unsafe("eeh_address_cache", 0400, arch_debugfs_dir, NULL, diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 350dab18e137..f279295179bd 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -16,7 +16,6 @@ #include <asm/eeh_event.h> #include <asm/ppc-pci.h> #include <asm/pci-bridge.h> -#include <asm/prom.h> #include <asm/rtas.h> struct eeh_rmv_data { @@ -751,7 +750,7 @@ static void eeh_pe_cleanup(struct eeh_pe *pe) * @pdev: pci_dev to check * * This function may return a false positive if we can't determine the slot's - * presence state. This might happen for for PCIe slots if the PE containing + * presence state. This might happen for PCIe slots if the PE containing * the upstream bridge is also frozen, or the bridge is part of the same PE * as the device. * @@ -905,18 +904,19 @@ void eeh_handle_normal_event(struct eeh_pe *pe) } #endif /* CONFIG_STACKTRACE */ + eeh_for_each_pe(pe, tmp_pe) + eeh_pe_for_each_dev(tmp_pe, edev, tmp) + edev->mode &= ~EEH_DEV_NO_HANDLER; + eeh_pe_update_time_stamp(pe); pe->freeze_count++; if (pe->freeze_count > eeh_max_freezes) { pr_err("EEH: PHB#%x-PE#%x has failed %d times in the last hour and has been permanently disabled.\n", pe->phb->global_number, pe->addr, pe->freeze_count); - result = PCI_ERS_RESULT_DISCONNECT; - } - eeh_for_each_pe(pe, tmp_pe) - eeh_pe_for_each_dev(tmp_pe, edev, tmp) - edev->mode &= ~EEH_DEV_NO_HANDLER; + goto recover_failed; + } /* Walk the various device drivers attached to this slot through * a reset sequence, giving each an opportunity to do what it needs @@ -928,39 +928,38 @@ void eeh_handle_normal_event(struct eeh_pe *pe) * the error. Override the result if necessary to have partially * hotplug for this case. */ - if (result != PCI_ERS_RESULT_DISCONNECT) { - pr_warn("EEH: This PCI device has failed %d times in the last hour and will be permanently disabled after %d failures.\n", - pe->freeze_count, eeh_max_freezes); - pr_info("EEH: Notify device drivers to shutdown\n"); - eeh_set_channel_state(pe, pci_channel_io_frozen); - eeh_set_irq_state(pe, false); - eeh_pe_report("error_detected(IO frozen)", pe, - eeh_report_error, &result); - if ((pe->type & EEH_PE_PHB) && - result != PCI_ERS_RESULT_NONE && - result != PCI_ERS_RESULT_NEED_RESET) - result = PCI_ERS_RESULT_NEED_RESET; - } + pr_warn("EEH: This PCI device has failed %d times in the last hour and will be permanently disabled after %d failures.\n", + pe->freeze_count, eeh_max_freezes); + pr_info("EEH: Notify device drivers to shutdown\n"); + eeh_set_channel_state(pe, pci_channel_io_frozen); + eeh_set_irq_state(pe, false); + eeh_pe_report("error_detected(IO frozen)", pe, + eeh_report_error, &result); + if (result == PCI_ERS_RESULT_DISCONNECT) + goto recover_failed; + + /* + * Error logged on a PHB are always fences which need a full + * PHB reset to clear so force that to happen. + */ + if ((pe->type & EEH_PE_PHB) && result != PCI_ERS_RESULT_NONE) + result = PCI_ERS_RESULT_NEED_RESET; /* Get the current PCI slot state. This can take a long time, * sometimes over 300 seconds for certain systems. */ - if (result != PCI_ERS_RESULT_DISCONNECT) { - rc = eeh_wait_state(pe, MAX_WAIT_FOR_RECOVERY*1000); - if (rc < 0 || rc == EEH_STATE_NOT_SUPPORT) { - pr_warn("EEH: Permanent failure\n"); - result = PCI_ERS_RESULT_DISCONNECT; - } + rc = eeh_wait_state(pe, MAX_WAIT_FOR_RECOVERY * 1000); + if (rc < 0 || rc == EEH_STATE_NOT_SUPPORT) { + pr_warn("EEH: Permanent failure\n"); + goto recover_failed; } /* Since rtas may enable MMIO when posting the error log, * don't post the error log until after all dev drivers * have been informed. */ - if (result != PCI_ERS_RESULT_DISCONNECT) { - pr_info("EEH: Collect temporary log\n"); - eeh_slot_error_detail(pe, EEH_LOG_TEMP); - } + pr_info("EEH: Collect temporary log\n"); + eeh_slot_error_detail(pe, EEH_LOG_TEMP); /* If all device drivers were EEH-unaware, then shut * down all of the device drivers, and hope they @@ -970,9 +969,8 @@ void eeh_handle_normal_event(struct eeh_pe *pe) pr_info("EEH: Reset with hotplug activity\n"); rc = eeh_reset_device(pe, bus, NULL, false); if (rc) { - pr_warn("%s: Unable to reset, err=%d\n", - __func__, rc); - result = PCI_ERS_RESULT_DISCONNECT; + pr_warn("%s: Unable to reset, err=%d\n", __func__, rc); + goto recover_failed; } } @@ -980,10 +978,10 @@ void eeh_handle_normal_event(struct eeh_pe *pe) if (result == PCI_ERS_RESULT_CAN_RECOVER) { pr_info("EEH: Enable I/O for affected devices\n"); rc = eeh_pci_enable(pe, EEH_OPT_THAW_MMIO); + if (rc < 0) + goto recover_failed; - if (rc < 0) { - result = PCI_ERS_RESULT_DISCONNECT; - } else if (rc) { + if (rc) { result = PCI_ERS_RESULT_NEED_RESET; } else { pr_info("EEH: Notify device drivers to resume I/O\n"); @@ -991,15 +989,13 @@ void eeh_handle_normal_event(struct eeh_pe *pe) eeh_report_mmio_enabled, &result); } } - - /* If all devices reported they can proceed, then re-enable DMA */ if (result == PCI_ERS_RESULT_CAN_RECOVER) { pr_info("EEH: Enabled DMA for affected devices\n"); rc = eeh_pci_enable(pe, EEH_OPT_THAW_DMA); + if (rc < 0) + goto recover_failed; - if (rc < 0) { - result = PCI_ERS_RESULT_DISCONNECT; - } else if (rc) { + if (rc) { result = PCI_ERS_RESULT_NEED_RESET; } else { /* @@ -1017,16 +1013,15 @@ void eeh_handle_normal_event(struct eeh_pe *pe) pr_info("EEH: Reset without hotplug activity\n"); rc = eeh_reset_device(pe, bus, &rmv_data, true); if (rc) { - pr_warn("%s: Cannot reset, err=%d\n", - __func__, rc); - result = PCI_ERS_RESULT_DISCONNECT; - } else { - result = PCI_ERS_RESULT_NONE; - eeh_set_channel_state(pe, pci_channel_io_normal); - eeh_set_irq_state(pe, true); - eeh_pe_report("slot_reset", pe, eeh_report_reset, - &result); + pr_warn("%s: Cannot reset, err=%d\n", __func__, rc); + goto recover_failed; } + + result = PCI_ERS_RESULT_NONE; + eeh_set_channel_state(pe, pci_channel_io_normal); + eeh_set_irq_state(pe, true); + eeh_pe_report("slot_reset", pe, eeh_report_reset, + &result); } if ((result == PCI_ERS_RESULT_RECOVERED) || @@ -1054,45 +1049,47 @@ void eeh_handle_normal_event(struct eeh_pe *pe) } pr_info("EEH: Recovery successful.\n"); - } else { - /* - * About 90% of all real-life EEH failures in the field - * are due to poorly seated PCI cards. Only 10% or so are - * due to actual, failed cards. - */ - pr_err("EEH: Unable to recover from failure from PHB#%x-PE#%x.\n" - "Please try reseating or replacing it\n", - pe->phb->global_number, pe->addr); + goto out; + } - eeh_slot_error_detail(pe, EEH_LOG_PERM); +recover_failed: + /* + * About 90% of all real-life EEH failures in the field + * are due to poorly seated PCI cards. Only 10% or so are + * due to actual, failed cards. + */ + pr_err("EEH: Unable to recover from failure from PHB#%x-PE#%x.\n" + "Please try reseating or replacing it\n", + pe->phb->global_number, pe->addr); - /* Notify all devices that they're about to go down. */ - eeh_set_channel_state(pe, pci_channel_io_perm_failure); - eeh_set_irq_state(pe, false); - eeh_pe_report("error_detected(permanent failure)", pe, - eeh_report_failure, NULL); + eeh_slot_error_detail(pe, EEH_LOG_PERM); - /* Mark the PE to be removed permanently */ - eeh_pe_state_mark(pe, EEH_PE_REMOVED); + /* Notify all devices that they're about to go down. */ + eeh_set_channel_state(pe, pci_channel_io_perm_failure); + eeh_set_irq_state(pe, false); + eeh_pe_report("error_detected(permanent failure)", pe, + eeh_report_failure, NULL); - /* - * Shut down the device drivers for good. We mark - * all removed devices correctly to avoid access - * the their PCI config any more. - */ - if (pe->type & EEH_PE_VF) { - eeh_pe_dev_traverse(pe, eeh_rmv_device, NULL); - eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED); - } else { - eeh_pe_state_clear(pe, EEH_PE_PRI_BUS, true); - eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED); + /* Mark the PE to be removed permanently */ + eeh_pe_state_mark(pe, EEH_PE_REMOVED); - pci_lock_rescan_remove(); - pci_hp_remove_devices(bus); - pci_unlock_rescan_remove(); - /* The passed PE should no longer be used */ - return; - } + /* + * Shut down the device drivers for good. We mark + * all removed devices correctly to avoid access + * the their PCI config any more. + */ + if (pe->type & EEH_PE_VF) { + eeh_pe_dev_traverse(pe, eeh_rmv_device, NULL); + eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED); + } else { + eeh_pe_state_clear(pe, EEH_PE_PRI_BUS, true); + eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED); + + pci_lock_rescan_remove(); + pci_hp_remove_devices(bus); + pci_unlock_rescan_remove(); + /* The passed PE should no longer be used */ + return; } out: diff --git a/arch/powerpc/kernel/eeh_event.c b/arch/powerpc/kernel/eeh_event.c index a7a8dc182efb..c23a454af08a 100644 --- a/arch/powerpc/kernel/eeh_event.c +++ b/arch/powerpc/kernel/eeh_event.c @@ -143,7 +143,7 @@ int __eeh_send_failure_event(struct eeh_pe *pe) int eeh_send_failure_event(struct eeh_pe *pe) { /* - * If we've manually supressed recovery events via debugfs + * If we've manually suppressed recovery events via debugfs * then just drop it on the floor. */ if (eeh_debugfs_no_recover) { diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index 845e024321d4..d2873d17d2b1 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -13,6 +13,7 @@ #include <linux/export.h> #include <linux/gfp.h> #include <linux/kernel.h> +#include <linux/of.h> #include <linux/pci.h> #include <linux/string.h> @@ -301,7 +302,7 @@ struct eeh_pe *eeh_pe_get(struct pci_controller *phb, int pe_no) * @new_pe_parent. * * If @new_pe_parent is NULL then the new PE will be inserted under - * directly under the the PHB. + * directly under the PHB. */ int eeh_pe_tree_insert(struct eeh_dev *edev, struct eeh_pe *new_pe_parent) { diff --git a/arch/powerpc/kernel/eeh_sysfs.c b/arch/powerpc/kernel/eeh_sysfs.c index 429620da73ba..706e1eb95efe 100644 --- a/arch/powerpc/kernel/eeh_sysfs.c +++ b/arch/powerpc/kernel/eeh_sysfs.c @@ -6,6 +6,7 @@ * * Send comments and feedback to Linas Vepstas <linas@austin.ibm.com> */ +#include <linux/of.h> #include <linux/pci.h> #include <linux/stat.h> #include <asm/ppc-pci.h> diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 61fdd53cdd9a..3fc7c9886bb7 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -49,7 +49,7 @@ */ .align 12 -#if defined(CONFIG_PPC_BOOK3S_32) || defined(CONFIG_E500) +#if defined(CONFIG_PPC_BOOK3S_32) || defined(CONFIG_PPC_E500) .globl prepare_transfer_to_handler prepare_transfer_to_handler: /* if from kernel, check interrupted DOZE/NAP mode */ @@ -68,18 +68,45 @@ prepare_transfer_to_handler: lwz r9,_MSR(r11) /* if sleeping, clear MSR.EE */ rlwinm r9,r9,0,~MSR_EE lwz r12,_LINK(r11) /* and return to address in LR */ - lwz r2, GPR2(r11) + REST_GPR(2, r11) b fast_exception_return _ASM_NOKPROBE_SYMBOL(prepare_transfer_to_handler) -#endif /* CONFIG_PPC_BOOK3S_32 || CONFIG_E500 */ +#endif /* CONFIG_PPC_BOOK3S_32 || CONFIG_PPC_E500 */ + +#if defined(CONFIG_PPC_KUEP) && defined(CONFIG_PPC_BOOK3S_32) + .globl __kuep_lock +__kuep_lock: + lwz r9, THREAD+THSR0(r2) + update_user_segments_by_4 r9, r10, r11, r12 + blr + +__kuep_unlock: + lwz r9, THREAD+THSR0(r2) + rlwinm r9,r9,0,~SR_NX + update_user_segments_by_4 r9, r10, r11, r12 + blr + +.macro kuep_lock + bl __kuep_lock +.endm +.macro kuep_unlock + bl __kuep_unlock +.endm +#else +.macro kuep_lock +.endm +.macro kuep_unlock +.endm +#endif .globl transfer_to_syscall transfer_to_syscall: + stw r3, ORIG_GPR3(r1) stw r11, GPR1(r1) stw r11, 0(r1) mflr r12 stw r12, _LINK(r1) -#if defined(CONFIG_BOOKE) || defined(CONFIG_40x) +#ifdef CONFIG_BOOKE_OR_40x rlwinm r9,r9,0,14,12 /* clear MSR_WE (necessary?) */ #endif lis r12,STACK_FRAME_REGS_MARKER@ha /* exception frame marker */ @@ -90,14 +117,14 @@ transfer_to_syscall: stw r12,8(r1) stw r2,_TRAP(r1) SAVE_GPR(0, r1) - SAVE_4GPRS(3, r1) - SAVE_2GPRS(7, r1) + SAVE_GPRS(3, 8, r1) addi r2,r10,-THREAD SAVE_NVGPRS(r1) + kuep_lock - /* Calling convention has r9 = orig r0, r10 = regs */ - addi r10,r1,STACK_FRAME_OVERHEAD - mr r9,r0 + /* Calling convention has r3 = regs, r4 = orig r0 */ + addi r3,r1,STACK_FRAME_OVERHEAD + mr r4,r0 bl system_call_exception ret_from_syscall: @@ -110,13 +137,14 @@ ret_from_syscall: cmplwi cr0,r5,0 bne- 2f #endif /* CONFIG_PPC_47x */ + kuep_unlock lwz r4,_LINK(r1) lwz r5,_CCR(r1) mtlr r4 lwz r7,_NIP(r1) lwz r8,_MSR(r1) cmpwi r3,0 - lwz r3,GPR3(r1) + REST_GPR(3, r1) syscall_exit_finish: mtspr SPRN_SRR0,r7 mtspr SPRN_SRR1,r8 @@ -124,8 +152,8 @@ syscall_exit_finish: bne 3f mtcr r5 -1: lwz r2,GPR2(r1) - lwz r1,GPR1(r1) +1: REST_GPR(2, r1) + REST_GPR(1, r1) rfi #ifdef CONFIG_40x b . /* Prevent prefetch past rfi */ @@ -137,10 +165,8 @@ syscall_exit_finish: REST_NVGPRS(r1) mtctr r4 mtxer r5 - lwz r0,GPR0(r1) - lwz r3,GPR3(r1) - REST_8GPRS(4,r1) - lwz r12,GPR12(r1) + REST_GPR(0, r1) + REST_GPRS(3, 12, r1) b 1b #ifdef CONFIG_44x @@ -232,13 +258,12 @@ fast_exception_return: beq 3f /* if not, we've got problems */ #endif -2: REST_4GPRS(3, r11) - lwz r10,_CCR(r11) - REST_2GPRS(1, r11) +2: lwz r10,_CCR(r11) + REST_GPRS(1, 6, r11) mtcr r10 lwz r10,_LINK(r11) mtlr r10 - /* Clear the exception_marker on the stack to avoid confusing stacktrace */ + /* Clear the exception marker on the stack to avoid confusing stacktrace */ li r10, 0 stw r10, 8(r11) REST_GPR(10, r11) @@ -249,7 +274,7 @@ fast_exception_return: mtspr SPRN_SRR0,r12 REST_GPR(9, r11) REST_GPR(12, r11) - lwz r11,GPR11(r11) + REST_GPR(11, r11) rfi #ifdef CONFIG_40x b . /* Prevent prefetch past rfi */ @@ -273,6 +298,7 @@ interrupt_return: beq .Lkernel_interrupt_return bl interrupt_exit_user_prepare cmpwi r3,0 + kuep_unlock bne- .Lrestore_nvgprs .Lfast_user_interrupt_return: @@ -294,20 +320,18 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS) li r0,0 /* - * Leaving a stale exception_marker on the stack can confuse + * Leaving a stale exception marker on the stack can confuse * the reliable stack unwinder later on. Clear it. */ stw r0,8(r1) - REST_4GPRS(7, r1) - REST_2GPRS(11, r1) + REST_GPRS(7, 12, r1) mtcr r3 mtlr r4 mtctr r5 mtspr SPRN_XER,r6 - REST_4GPRS(2, r1) - REST_GPR(6, r1) + REST_GPRS(2, 6, r1) REST_GPR(0, r1) REST_GPR(1, r1) rfi @@ -341,20 +365,19 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS) lwz r6,_CCR(r1) li r0,0 - REST_4GPRS(7, r1) - REST_2GPRS(11, r1) + REST_GPRS(7, 12, r1) mtlr r3 mtctr r4 mtspr SPRN_XER,r5 /* - * Leaving a stale exception_marker on the stack can confuse + * Leaving a stale exception marker on the stack can confuse * the reliable stack unwinder later on. Clear it. */ stw r0,8(r1) - REST_4GPRS(2, r1) + REST_GPRS(2, 5, r1) bne- cr1,1f /* emulate stack store */ mtcr r6 @@ -428,10 +451,8 @@ _ASM_NOKPROBE_SYMBOL(interrupt_return) lwz r3,_MSR(r1); \ andi. r3,r3,MSR_PR; \ bne interrupt_return; \ - lwz r0,GPR0(r1); \ - lwz r2,GPR2(r1); \ - REST_4GPRS(3, r1); \ - REST_2GPRS(7, r1); \ + REST_GPR(0, r1); \ + REST_GPRS(2, 8, r1); \ lwz r10,_XER(r1); \ lwz r11,_CTR(r1); \ mtspr SPRN_XER,r10; \ @@ -450,11 +471,8 @@ _ASM_NOKPROBE_SYMBOL(interrupt_return) lwz r12,_MSR(r1); \ mtspr exc_lvl_srr0,r11; \ mtspr exc_lvl_srr1,r12; \ - lwz r9,GPR9(r1); \ - lwz r12,GPR12(r1); \ - lwz r10,GPR10(r1); \ - lwz r11,GPR11(r1); \ - lwz r1,GPR1(r1); \ + REST_GPRS(9, 12, r1); \ + REST_GPR(1, r1); \ exc_lvl_rfi; \ b .; /* prevent prefetch past exc_lvl_rfi */ @@ -464,7 +482,7 @@ _ASM_NOKPROBE_SYMBOL(interrupt_return) mtspr SPRN_##exc_lvl_srr0,r9; \ mtspr SPRN_##exc_lvl_srr1,r10; -#if defined(CONFIG_PPC_BOOK3E_MMU) +#if defined(CONFIG_PPC_E500) #ifdef CONFIG_PHYS_64BIT #define RESTORE_MAS7 \ lwz r11,MAS7(r1); \ @@ -531,52 +549,3 @@ ret_from_mcheck_exc: _ASM_NOKPROBE_SYMBOL(ret_from_mcheck_exc) #endif /* CONFIG_BOOKE */ #endif /* !(CONFIG_4xx || CONFIG_BOOKE) */ - -/* - * PROM code for specific machines follows. Put it - * here so it's easy to add arch-specific sections later. - * -- Cort - */ -#ifdef CONFIG_PPC_RTAS -/* - * On CHRP, the Run-Time Abstraction Services (RTAS) have to be - * called with the MMU off. - */ -_GLOBAL(enter_rtas) - stwu r1,-INT_FRAME_SIZE(r1) - mflr r0 - stw r0,INT_FRAME_SIZE+4(r1) - LOAD_REG_ADDR(r4, rtas) - lis r6,1f@ha /* physical return address for rtas */ - addi r6,r6,1f@l - tophys(r6,r6) - lwz r8,RTASENTRY(r4) - lwz r4,RTASBASE(r4) - mfmsr r9 - stw r9,8(r1) - LOAD_REG_IMMEDIATE(r0,MSR_KERNEL) - mtmsr r0 /* disable interrupts so SRR0/1 don't get trashed */ - li r9,MSR_KERNEL & ~(MSR_IR|MSR_DR) - mtlr r6 - stw r1, THREAD + RTAS_SP(r2) - mtspr SPRN_SRR0,r8 - mtspr SPRN_SRR1,r9 - rfi -1: - lis r8, 1f@h - ori r8, r8, 1f@l - LOAD_REG_IMMEDIATE(r9,MSR_KERNEL) - mtspr SPRN_SRR0,r8 - mtspr SPRN_SRR1,r9 - rfi /* Reactivate MMU translation */ -1: - lwz r8,INT_FRAME_SIZE+4(r1) /* get return address */ - lwz r9,8(r1) /* original msr value */ - addi r1,r1,INT_FRAME_SIZE - li r0,0 - stw r0, THREAD + RTAS_SP(r2) - mtlr r8 - mtmsr r9 - blr /* return to caller */ -_ASM_NOKPROBE_SYMBOL(enter_rtas) -#endif /* CONFIG_PPC_RTAS */ diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 70cff7b49e17..3e2e37e6ecab 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -180,7 +180,7 @@ _GLOBAL(_switch) #endif ld r8,KSP(r4) /* new stack pointer */ -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU BEGIN_MMU_FTR_SECTION b 2f END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX) @@ -232,7 +232,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) slbmte r7,r0 isync 2: -#endif /* CONFIG_PPC_BOOK3S_64 */ +#endif /* CONFIG_PPC_64S_HASH_MMU */ clrrdi r7, r8, THREAD_SHIFT /* base of new stack */ /* Note: this uses SWITCH_FRAME_SIZE rather than INT_FRAME_SIZE @@ -264,156 +264,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) addi r1,r1,SWITCH_FRAME_SIZE blr -#ifdef CONFIG_PPC_RTAS -/* - * On CHRP, the Run-Time Abstraction Services (RTAS) have to be - * called with the MMU off. - * - * In addition, we need to be in 32b mode, at least for now. - * - * Note: r3 is an input parameter to rtas, so don't trash it... - */ -_GLOBAL(enter_rtas) - mflr r0 - std r0,16(r1) - stdu r1,-SWITCH_FRAME_SIZE(r1) /* Save SP and create stack space. */ - - /* Because RTAS is running in 32b mode, it clobbers the high order half - * of all registers that it saves. We therefore save those registers - * RTAS might touch to the stack. (r0, r3-r13 are caller saved) - */ - SAVE_GPR(2, r1) /* Save the TOC */ - SAVE_GPR(13, r1) /* Save paca */ - SAVE_NVGPRS(r1) /* Save the non-volatiles */ - - mfcr r4 - std r4,_CCR(r1) - mfctr r5 - std r5,_CTR(r1) - mfspr r6,SPRN_XER - std r6,_XER(r1) - mfdar r7 - std r7,_DAR(r1) - mfdsisr r8 - std r8,_DSISR(r1) - - /* Temporary workaround to clear CR until RTAS can be modified to - * ignore all bits. - */ - li r0,0 - mtcr r0 - -#ifdef CONFIG_BUG - /* There is no way it is acceptable to get here with interrupts enabled, - * check it with the asm equivalent of WARN_ON - */ - lbz r0,PACAIRQSOFTMASK(r13) -1: tdeqi r0,IRQS_ENABLED - EMIT_WARN_ENTRY 1b,__FILE__,__LINE__,BUGFLAG_WARNING -#endif - - /* Hard-disable interrupts */ - mfmsr r6 - rldicl r7,r6,48,1 - rotldi r7,r7,16 - mtmsrd r7,1 - - /* Unfortunately, the stack pointer and the MSR are also clobbered, - * so they are saved in the PACA which allows us to restore - * our original state after RTAS returns. - */ - std r1,PACAR1(r13) - std r6,PACASAVEDMSR(r13) - - /* Setup our real return addr */ - LOAD_REG_ADDR(r4,rtas_return_loc) - clrldi r4,r4,2 /* convert to realmode address */ - mtlr r4 - - li r0,0 - ori r0,r0,MSR_EE|MSR_SE|MSR_BE|MSR_RI - andc r0,r6,r0 - - li r9,1 - rldicr r9,r9,MSR_SF_LG,(63-MSR_SF_LG) - ori r9,r9,MSR_IR|MSR_DR|MSR_FE0|MSR_FE1|MSR_FP|MSR_RI|MSR_LE - andc r6,r0,r9 - -__enter_rtas: - sync /* disable interrupts so SRR0/1 */ - mtmsrd r0 /* don't get trashed */ - - LOAD_REG_ADDR(r4, rtas) - ld r5,RTASENTRY(r4) /* get the rtas->entry value */ - ld r4,RTASBASE(r4) /* get the rtas->base value */ - - mtspr SPRN_SRR0,r5 - mtspr SPRN_SRR1,r6 - RFI_TO_KERNEL - b . /* prevent speculative execution */ - -rtas_return_loc: - FIXUP_ENDIAN - - /* - * Clear RI and set SF before anything. - */ - mfmsr r6 - li r0,MSR_RI - andc r6,r6,r0 - sldi r0,r0,(MSR_SF_LG - MSR_RI_LG) - or r6,r6,r0 - sync - mtmsrd r6 - - /* relocation is off at this point */ - GET_PACA(r4) - clrldi r4,r4,2 /* convert to realmode address */ - - bcl 20,31,$+4 -0: mflr r3 - ld r3,(1f-0b)(r3) /* get &rtas_restore_regs */ - - ld r1,PACAR1(r4) /* Restore our SP */ - ld r4,PACASAVEDMSR(r4) /* Restore our MSR */ - - mtspr SPRN_SRR0,r3 - mtspr SPRN_SRR1,r4 - RFI_TO_KERNEL - b . /* prevent speculative execution */ -_ASM_NOKPROBE_SYMBOL(__enter_rtas) -_ASM_NOKPROBE_SYMBOL(rtas_return_loc) - - .align 3 -1: .8byte rtas_restore_regs - -rtas_restore_regs: - /* relocation is on at this point */ - REST_GPR(2, r1) /* Restore the TOC */ - REST_GPR(13, r1) /* Restore paca */ - REST_NVGPRS(r1) /* Restore the non-volatiles */ - - GET_PACA(r13) - - ld r4,_CCR(r1) - mtcr r4 - ld r5,_CTR(r1) - mtctr r5 - ld r6,_XER(r1) - mtspr SPRN_XER,r6 - ld r7,_DAR(r1) - mtdar r7 - ld r8,_DSISR(r1) - mtdsisr r8 - - addi r1,r1,SWITCH_FRAME_SIZE /* Unstack our frame */ - ld r0,16(r1) /* get return address */ - - mtlr r0 - blr /* return to caller */ - -#endif /* CONFIG_PPC_RTAS */ - _GLOBAL(enter_prom) mflr r0 std r0,16(r1) @@ -442,16 +292,16 @@ _GLOBAL(enter_prom) /* Prepare a 32-bit mode big endian MSR */ -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 rlwinm r11,r11,0,1,31 mtsrr1 r11 rfi -#else /* CONFIG_PPC_BOOK3E */ +#else /* CONFIG_PPC_BOOK3E_64 */ LOAD_REG_IMMEDIATE(r12, MSR_SF | MSR_LE) andc r11,r11,r12 mtsrr1 r11 RFI_TO_KERNEL -#endif /* CONFIG_PPC_BOOK3E */ +#endif /* CONFIG_PPC_BOOK3E_64 */ 1: /* Return from OF */ FIXUP_ENDIAN diff --git a/arch/powerpc/kernel/epapr_paravirt.c b/arch/powerpc/kernel/epapr_paravirt.c index 93b0f3ec8fb0..d4b8aff20815 100644 --- a/arch/powerpc/kernel/epapr_paravirt.c +++ b/arch/powerpc/kernel/epapr_paravirt.c @@ -37,7 +37,7 @@ static int __init early_init_dt_scan_epapr(unsigned long node, return -1; for (i = 0; i < (len / 4); i++) { - struct ppc_inst inst = ppc_inst(be32_to_cpu(insts[i])); + ppc_inst_t inst = ppc_inst(be32_to_cpu(insts[i])); patch_instruction(epapr_hypercall_start + i, inst); #if !defined(CONFIG_64BIT) || defined(CONFIG_PPC_BOOK3E_64) patch_instruction(epapr_ev_idle_start + i, inst); diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index 711c66b76df1..2f68fb2ee4fc 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -198,8 +198,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV) stdcx. r0,0,r1 /* to clear the reservation */ - REST_4GPRS(2, r1) - REST_4GPRS(6, r1) + REST_GPRS(2, 9, r1) ld r10,_CTR(r1) ld r11,_XER(r1) @@ -217,17 +216,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV) mtlr r10 mtcr r11 - ld r10,GPR10(r1) - ld r11,GPR11(r1) - ld r12,GPR12(r1) + REST_GPRS(10, 12, r1) mtspr \scratch,r0 std r10,\paca_ex+EX_R10(r13); std r11,\paca_ex+EX_R11(r13); ld r10,_NIP(r1) ld r11,_MSR(r1) - ld r0,GPR0(r1) - ld r1,GPR1(r1) + REST_GPR(0, r1) + REST_GPR(1, r1) mtspr \srr0,r10 mtspr \srr1,r11 ld r10,\paca_ex+EX_R10(r13) @@ -292,7 +289,6 @@ ret_from_mc_except: #define SPRN_MC_SRR0 SPRN_MCSRR0 #define SPRN_MC_SRR1 SPRN_MCSRR1 -#ifdef CONFIG_PPC_FSL_BOOK3E #define GEN_BTB_FLUSH \ START_BTB_FLUSH_SECTION \ beq 1f; \ @@ -308,13 +304,6 @@ ret_from_mc_except: #define DBG_BTB_FLUSH CRIT_BTB_FLUSH #define MC_BTB_FLUSH CRIT_BTB_FLUSH #define GDBELL_BTB_FLUSH GEN_BTB_FLUSH -#else -#define GEN_BTB_FLUSH -#define CRIT_BTB_FLUSH -#define DBG_BTB_FLUSH -#define MC_BTB_FLUSH -#define GDBELL_BTB_FLUSH -#endif #define NORMAL_EXCEPTION_PROLOG(n, intnum, addition) \ EXCEPTION_PROLOG(n, intnum, GEN, addition##_GEN(n)) @@ -373,27 +362,24 @@ ret_from_mc_except: /* Core exception code for all exceptions except TLB misses. */ #define EXCEPTION_COMMON_LVL(n, scratch, excf) \ exc_##n##_common: \ - std r0,GPR0(r1); /* save r0 in stackframe */ \ - std r2,GPR2(r1); /* save r2 in stackframe */ \ - SAVE_4GPRS(3, r1); /* save r3 - r6 in stackframe */ \ - SAVE_2GPRS(7, r1); /* save r7, r8 in stackframe */ \ - std r9,GPR9(r1); /* save r9 in stackframe */ \ + SAVE_GPR(0, r1); /* save r0 in stackframe */ \ + SAVE_GPRS(2, 9, r1); /* save r2 - r9 in stackframe */ \ std r10,_NIP(r1); /* save SRR0 to stackframe */ \ std r11,_MSR(r1); /* save SRR1 to stackframe */ \ beq 2f; /* if from kernel mode */ \ 2: ld r3,excf+EX_R10(r13); /* get back r10 */ \ ld r4,excf+EX_R11(r13); /* get back r11 */ \ mfspr r5,scratch; /* get back r13 */ \ - std r12,GPR12(r1); /* save r12 in stackframe */ \ - ld r2,PACATOC(r13); /* get kernel TOC into r2 */ \ + SAVE_GPR(12, r1); /* save r12 in stackframe */ \ + LOAD_PACA_TOC(); /* get kernel TOC into r2 */ \ mflr r6; /* save LR in stackframe */ \ mfctr r7; /* save CTR in stackframe */ \ mfspr r8,SPRN_XER; /* save XER in stackframe */ \ ld r9,excf+EX_R1(r13); /* load orig r1 back from PACA */ \ lwz r10,excf+EX_CR(r13); /* load orig CR back from PACA */ \ lbz r11,PACAIRQSOFTMASK(r13); /* get current IRQ softe */ \ - ld r12,exception_marker@toc(r2); \ - li r0,0; \ + LOAD_REG_IMMEDIATE(r12, STACK_FRAME_REGS_MARKER); \ + ZEROIZE_GPR(0); \ std r3,GPR10(r1); /* save r10 to stackframe */ \ std r4,GPR11(r1); /* save r11 to stackframe */ \ std r5,GPR13(r1); /* save it to stackframe */ \ @@ -473,12 +459,6 @@ exc_##n##_bad_stack: \ bl hdlr; \ b interrupt_return -/* This value is used to mark exception frames on the stack. */ - .section ".toc","aw" -exception_marker: - .tc ID_EXC_MARKER[TC],STACK_FRAME_REGS_MARKER - - /* * And here we have the exception vectors ! */ @@ -707,9 +687,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) beq+ 1f #ifdef CONFIG_RELOCATABLE - ld r15,PACATOC(r13) - ld r14,interrupt_base_book3e@got(r15) - ld r15,__end_interrupts@got(r15) + __LOAD_PACA_TOC(r15) + LOAD_REG_ADDR_ALTTOC(r14, r15, interrupt_base_book3e) + LOAD_REG_ADDR_ALTTOC(r15, r15, __end_interrupts) cmpld cr0,r10,r14 cmpld cr1,r10,r15 #else @@ -778,9 +758,9 @@ kernel_dbg_exc: beq+ 1f #ifdef CONFIG_RELOCATABLE - ld r15,PACATOC(r13) - ld r14,interrupt_base_book3e@got(r15) - ld r15,__end_interrupts@got(r15) + __LOAD_PACA_TOC(r15) + LOAD_REG_ADDR_ALTTOC(r14, r15, interrupt_base_book3e) + LOAD_REG_ADDR_ALTTOC(r15, r15, __end_interrupts) cmpld cr0,r10,r14 cmpld cr1,r10,r15 #else @@ -833,6 +813,13 @@ kernel_dbg_exc: EXCEPTION_COMMON(0x260) CHECK_NAPPING() addi r3,r1,STACK_FRAME_OVERHEAD + /* + * XXX: Returning from performance_monitor_exception taken as a + * soft-NMI (Linux irqs disabled) may be risky to use interrupt_return + * and could cause bugs in return or elsewhere. That case should just + * restore registers and return. There is a workaround for one known + * problem in interrupt_exit_kernel_prepare(). + */ bl performance_monitor_exception b interrupt_return @@ -903,9 +890,9 @@ kernel_dbg_exc: .macro SEARCH_RESTART_TABLE #ifdef CONFIG_RELOCATABLE - ld r11,PACATOC(r13) - ld r14,__start___restart_table@got(r11) - ld r15,__stop___restart_table@got(r11) + __LOAD_PACA_TOC(r11) + LOAD_REG_ADDR_ALTTOC(r14, r11, __start___restart_table) + LOAD_REG_ADDR_ALTTOC(r15, r11, __stop___restart_table) #else LOAD_REG_IMMEDIATE_SYM(r14, r11, __start___restart_table) LOAD_REG_IMMEDIATE_SYM(r15, r11, __stop___restart_table) @@ -1059,17 +1046,14 @@ bad_stack_book3e: mfspr r11,SPRN_ESR std r10,_DEAR(r1) std r11,_ESR(r1) - std r0,GPR0(r1); /* save r0 in stackframe */ \ - std r2,GPR2(r1); /* save r2 in stackframe */ \ - SAVE_4GPRS(3, r1); /* save r3 - r6 in stackframe */ \ - SAVE_2GPRS(7, r1); /* save r7, r8 in stackframe */ \ - std r9,GPR9(r1); /* save r9 in stackframe */ \ + SAVE_GPR(0, r1); /* save r0 in stackframe */ \ + SAVE_GPRS(2, 9, r1); /* save r2 - r9 in stackframe */ \ ld r3,PACA_EXGEN+EX_R10(r13);/* get back r10 */ \ ld r4,PACA_EXGEN+EX_R11(r13);/* get back r11 */ \ mfspr r5,SPRN_SPRG_GEN_SCRATCH;/* get back r13 XXX can be wrong */ \ std r3,GPR10(r1); /* save r10 to stackframe */ \ std r4,GPR11(r1); /* save r11 to stackframe */ \ - std r12,GPR12(r1); /* save r12 in stackframe */ \ + SAVE_GPR(12, r1); /* save r12 in stackframe */ \ std r5,GPR13(r1); /* save it to stackframe */ \ mflr r10 mfctr r11 @@ -1077,15 +1061,14 @@ bad_stack_book3e: std r10,_LINK(r1) std r11,_CTR(r1) std r12,_XER(r1) - SAVE_10GPRS(14,r1) - SAVE_8GPRS(24,r1) + SAVE_NVGPRS(r1) lhz r12,PACA_TRAP_SAVE(r13) std r12,_TRAP(r1) addi r11,r1,INT_FRAME_SIZE std r11,0(r1) - li r12,0 + ZEROIZE_GPR(12) std r12,0(r11) - ld r2,PACATOC(r13) + LOAD_PACA_TOC() 1: addi r3,r1,STACK_FRAME_OVERHEAD bl kernel_bad_stack b 1b @@ -1326,8 +1309,8 @@ a2_tlbinit_after_linear_map: /* Now we branch the new virtual address mapped by this entry */ #ifdef CONFIG_RELOCATABLE - ld r5,PACATOC(r13) - ld r3,1f@got(r5) + __LOAD_PACA_TOC(r5) + LOAD_REG_ADDR_ALTTOC(r3, r5, 1f) #else LOAD_REG_IMMEDIATE_SYM(r3, r5, 1f) #endif diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index eaf1f72131a1..651c36b056bd 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -48,7 +48,7 @@ .balign IFETCH_ALIGN_BYTES; \ .global name; \ _ASM_NOKPROBE_SYMBOL(name); \ - DEFINE_FIXED_SYMBOL(name); \ + DEFINE_FIXED_SYMBOL(name, text); \ name: #define TRAMP_REAL_BEGIN(name) \ @@ -76,31 +76,18 @@ name: ld reg,PACAKBASE(r13); /* get high part of &label */ \ ori reg,reg,FIXED_SYMBOL_ABS_ADDR(label) -#define __LOAD_HANDLER(reg, label) \ +#define __LOAD_HANDLER(reg, label, section) \ ld reg,PACAKBASE(r13); \ - ori reg,reg,(ABS_ADDR(label))@l + ori reg,reg,(ABS_ADDR(label, section))@l /* * Branches from unrelocated code (e.g., interrupts) to labels outside * head-y require >64K offsets. */ -#define __LOAD_FAR_HANDLER(reg, label) \ +#define __LOAD_FAR_HANDLER(reg, label, section) \ ld reg,PACAKBASE(r13); \ - ori reg,reg,(ABS_ADDR(label))@l; \ - addis reg,reg,(ABS_ADDR(label))@h - -/* - * Branch to label using its 0xC000 address. This results in instruction - * address suitable for MSR[IR]=0 or 1, which allows relocation to be turned - * on using mtmsr rather than rfid. - * - * This could set the 0xc bits for !RELOCATABLE as an immediate, rather than - * load KBASE for a slight optimisation. - */ -#define BRANCH_TO_C000(reg, label) \ - __LOAD_FAR_HANDLER(reg, label); \ - mtctr reg; \ - bctr + ori reg,reg,(ABS_ADDR(label, section))@l; \ + addis reg,reg,(ABS_ADDR(label, section))@h /* * Interrupt code generation macros @@ -111,9 +98,10 @@ name: #define IAREA .L_IAREA_\name\() /* PACA save area */ #define IVIRT .L_IVIRT_\name\() /* Has virt mode entry point */ #define IISIDE .L_IISIDE_\name\() /* Uses SRR0/1 not DAR/DSISR */ +#define ICFAR .L_ICFAR_\name\() /* Uses CFAR */ +#define ICFAR_IF_HVMODE .L_ICFAR_IF_HVMODE_\name\() /* Uses CFAR if HV */ #define IDAR .L_IDAR_\name\() /* Uses DAR (or SRR0) */ #define IDSISR .L_IDSISR_\name\() /* Uses DSISR (or SRR1) */ -#define ISET_RI .L_ISET_RI_\name\() /* Run common code w/ MSR[RI]=1 */ #define IBRANCH_TO_COMMON .L_IBRANCH_TO_COMMON_\name\() /* ENTRY branch to common */ #define IREALMODE_COMMON .L_IREALMODE_COMMON_\name\() /* Common runs in realmode */ #define IMASK .L_IMASK_\name\() /* IRQ soft-mask bit */ @@ -151,15 +139,18 @@ do_define_int n .ifndef IISIDE IISIDE=0 .endif + .ifndef ICFAR + ICFAR=1 + .endif + .ifndef ICFAR_IF_HVMODE + ICFAR_IF_HVMODE=0 + .endif .ifndef IDAR IDAR=0 .endif .ifndef IDSISR IDSISR=0 .endif - .ifndef ISET_RI - ISET_RI=1 - .endif .ifndef IBRANCH_TO_COMMON IBRANCH_TO_COMMON=1 .endif @@ -290,10 +281,22 @@ BEGIN_FTR_SECTION mfspr r9,SPRN_PPR END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) HMT_MEDIUM - std r10,IAREA+EX_R10(r13) /* save r10 - r12 */ + std r10,IAREA+EX_R10(r13) /* save r10 */ + .if ICFAR BEGIN_FTR_SECTION mfspr r10,SPRN_CFAR END_FTR_SECTION_IFSET(CPU_FTR_CFAR) + .elseif ICFAR_IF_HVMODE +BEGIN_FTR_SECTION + BEGIN_FTR_SECTION_NESTED(69) + mfspr r10,SPRN_CFAR + END_FTR_SECTION_NESTED(CPU_FTR_CFAR, CPU_FTR_CFAR, 69) +FTR_SECTION_ELSE + BEGIN_FTR_SECTION_NESTED(69) + li r10,0 + END_FTR_SECTION_NESTED(CPU_FTR_CFAR, CPU_FTR_CFAR, 69) +ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) + .endif .if \ool .if !\virt b tramp_real_\name @@ -309,14 +312,16 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR) BEGIN_FTR_SECTION std r9,IAREA+EX_PPR(r13) END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) + .if ICFAR || ICFAR_IF_HVMODE BEGIN_FTR_SECTION std r10,IAREA+EX_CFAR(r13) END_FTR_SECTION_IFSET(CPU_FTR_CFAR) + .endif INTERRUPT_TO_KERNEL mfctr r10 std r10,IAREA+EX_CTR(r13) mfcr r9 - std r11,IAREA+EX_R11(r13) + std r11,IAREA+EX_R11(r13) /* save r11 - r12 */ std r12,IAREA+EX_R12(r13) /* @@ -376,7 +381,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR) * This switches to virtual mode and sets MSR[RI]. */ .macro __GEN_COMMON_ENTRY name -DEFINE_FIXED_SYMBOL(\name\()_common_real) +DEFINE_FIXED_SYMBOL(\name\()_common_real, text) \name\()_common_real: .if IKVM_REAL KVMTEST \name kvm_interrupt @@ -399,7 +404,7 @@ DEFINE_FIXED_SYMBOL(\name\()_common_real) .endif .balign IFETCH_ALIGN_BYTES -DEFINE_FIXED_SYMBOL(\name\()_common_virt) +DEFINE_FIXED_SYMBOL(\name\()_common_virt, text) \name\()_common_virt: .if IKVM_VIRT KVMTEST \name kvm_interrupt @@ -413,7 +418,7 @@ DEFINE_FIXED_SYMBOL(\name\()_common_virt) * want to run in real mode. */ .macro __GEN_REALMODE_COMMON_ENTRY name -DEFINE_FIXED_SYMBOL(\name\()_common_real) +DEFINE_FIXED_SYMBOL(\name\()_common_real, text) \name\()_common_real: .if IKVM_REAL KVMTEST \name kvm_interrupt @@ -512,11 +517,6 @@ DEFINE_FIXED_SYMBOL(\name\()_common_real) stb r10,PACASRR_VALID(r13) .endif - .if ISET_RI - li r10,MSR_RI - mtmsrd r10,1 /* Set MSR_RI */ - .endif - .if ISTACK .if IKUAP kuap_save_amr_and_lock r9, r10, cr1, cr0 @@ -568,16 +568,19 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) .endif BEGIN_FTR_SECTION + .if ICFAR || ICFAR_IF_HVMODE ld r10,IAREA+EX_CFAR(r13) + .else + li r10,0 + .endif std r10,ORIG_GPR3(r1) END_FTR_SECTION_IFSET(CPU_FTR_CFAR) ld r10,IAREA+EX_CTR(r13) std r10,_CTR(r1) std r2,GPR2(r1) /* save r2 in stackframe */ - SAVE_4GPRS(3, r1) /* save r3 - r6 in stackframe */ - SAVE_2GPRS(7, r1) /* save r7, r8 in stackframe */ + SAVE_GPRS(3, 8, r1) /* save r3 - r8 in stackframe */ mflr r9 /* Get LR, later save to stack */ - ld r2,PACATOC(r13) /* get kernel TOC into r2 */ + LOAD_PACA_TOC() /* get kernel TOC into r2 */ std r9,_LINK(r1) lbz r10,PACAIRQSOFTMASK(r13) mfspr r11,SPRN_XER /* save XER in stackframe */ @@ -586,7 +589,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR) li r9,IVEC std r9,_TRAP(r1) /* set trap number */ li r10,0 - ld r11,exception_marker@toc(r2) + LOAD_REG_IMMEDIATE(r11, STACK_FRAME_REGS_MARKER) std r10,RESULT(r1) /* clear regs->result */ std r11,STACK_FRAME_OVERHEAD-16(r1) /* mark the frame */ .endm @@ -607,7 +610,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR) .macro SEARCH_RESTART_TABLE #ifdef CONFIG_RELOCATABLE mr r12,r2 - ld r2,PACATOC(r13) + LOAD_PACA_TOC() LOAD_REG_ADDR(r9, __start___restart_table) LOAD_REG_ADDR(r10, __stop___restart_table) mr r2,r12 @@ -637,7 +640,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR) .macro SEARCH_SOFT_MASK_TABLE #ifdef CONFIG_RELOCATABLE mr r12,r2 - ld r2,PACATOC(r13) + LOAD_PACA_TOC() LOAD_REG_ADDR(r9, __start___soft_mask_table) LOAD_REG_ADDR(r10, __stop___soft_mask_table) mr r2,r12 @@ -693,14 +696,78 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR) mtlr r9 ld r9,_CCR(r1) mtcr r9 - REST_8GPRS(2, r1) - REST_4GPRS(10, r1) + REST_GPRS(2, 13, r1) REST_GPR(0, r1) /* restore original r1. */ ld r1,GPR1(r1) .endm /* + * EARLY_BOOT_FIXUP - Fix real-mode interrupt with wrong endian in early boot. + * + * There's a short window during boot where although the kernel is running + * little endian, any exceptions will cause the CPU to switch back to big + * endian. For example a WARN() boils down to a trap instruction, which will + * cause a program check, and we end up here but with the CPU in big endian + * mode. The first instruction of the program check handler (in GEN_INT_ENTRY + * below) is an mtsprg, which when executed in the wrong endian is an lhzu with + * a ~3GB displacement from r3. The content of r3 is random, so that is a load + * from some random location, and depending on the system can easily lead to a + * checkstop, or an infinitely recursive page fault. + * + * So to handle that case we have a trampoline here that can detect we are in + * the wrong endian and flip us back to the correct endian. We can't flip + * MSR[LE] using mtmsr, so we have to use rfid. That requires backing up SRR0/1 + * as well as a GPR. To do that we use SPRG0/2/3, as SPRG1 is already used for + * the paca. SPRG3 is user readable, but this trampoline is only active very + * early in boot, and SPRG3 will be reinitialised in vdso_getcpu_init() before + * userspace starts. + */ +.macro EARLY_BOOT_FIXUP +BEGIN_FTR_SECTION +#ifdef CONFIG_CPU_LITTLE_ENDIAN + tdi 0,0,0x48 // Trap never, or in reverse endian: b . + 8 + b 2f // Skip trampoline if endian is correct + .long 0xa643707d // mtsprg 0, r11 Backup r11 + .long 0xa6027a7d // mfsrr0 r11 + .long 0xa643727d // mtsprg 2, r11 Backup SRR0 in SPRG2 + .long 0xa6027b7d // mfsrr1 r11 + .long 0xa643737d // mtsprg 3, r11 Backup SRR1 in SPRG3 + .long 0xa600607d // mfmsr r11 + .long 0x01006b69 // xori r11, r11, 1 Invert MSR[LE] + .long 0xa6037b7d // mtsrr1 r11 + /* + * This is 'li r11,1f' where 1f is the absolute address of that + * label, byteswapped into the SI field of the instruction. + */ + .long 0x00006039 | \ + ((ABS_ADDR(1f, real_vectors) & 0x00ff) << 24) | \ + ((ABS_ADDR(1f, real_vectors) & 0xff00) << 8) + .long 0xa6037a7d // mtsrr0 r11 + .long 0x2400004c // rfid +1: + mfsprg r11, 3 + mtsrr1 r11 // Restore SRR1 + mfsprg r11, 2 + mtsrr0 r11 // Restore SRR0 + mfsprg r11, 0 // Restore r11 +2: +#endif + /* + * program check could hit at any time, and pseries can not block + * MSR[ME] in early boot. So check if there is anything useful in r13 + * yet, and spin forever if not. + */ + mtsprg 0, r11 + mfcr r11 + cmpdi r13, 0 + beq . + mtcr r11 + mfsprg r11, 0 +END_FTR_SECTION(0, 1) // nop out after boot +.endm + +/* * There are a few constraints to be concerned with. * - Real mode exceptions code/data must be located at their physical location. * - Virtual mode exceptions must be mapped at their 0xc000... location. @@ -807,6 +874,10 @@ __start_interrupts: * - MSR_EE|MSR_RI is clear (no reentrant exceptions) * - Standard kernel environment is set up (stack, paca, etc) * + * KVM: + * These interrupts do not elevate HV 0->1, so HV is not involved. PR KVM + * ensures that FSCR[SCV] is disabled whenever it has to force AIL off. + * * Call convention: * * syscall register convention is in Documentation/powerpc/syscall64-abi.rst @@ -850,12 +921,12 @@ SOFT_MASK_TABLE(0xc000000000003000, 0xc000000000004000) #ifdef CONFIG_RELOCATABLE TRAMP_VIRT_BEGIN(system_call_vectored_tramp) - __LOAD_HANDLER(r10, system_call_vectored_common) + __LOAD_HANDLER(r10, system_call_vectored_common, virt_trampolines) mtctr r10 bctr TRAMP_VIRT_BEGIN(system_call_vectored_sigill_tramp) - __LOAD_HANDLER(r10, system_call_vectored_sigill) + __LOAD_HANDLER(r10, system_call_vectored_sigill, virt_trampolines) mtctr r10 bctr #endif @@ -902,11 +973,6 @@ INT_DEFINE_BEGIN(system_reset) IVEC=0x100 IAREA=PACA_EXNMI IVIRT=0 /* no virt entry point */ - /* - * MSR_RI is not enabled, because PACA_EXNMI and nmi stack is - * being used, so a nested NMI exception would corrupt it. - */ - ISET_RI=0 ISTACK=0 IKVM_REAL=1 INT_DEFINE_END(system_reset) @@ -964,7 +1030,9 @@ TRAMP_REAL_BEGIN(system_reset_idle_wake) /* We are waking up from idle, so may clobber any volatile register */ cmpwi cr1,r5,2 bltlr cr1 /* no state loss, return to idle caller with r3=SRR1 */ - BRANCH_TO_C000(r12, DOTSYM(idle_return_gpr_loss)) + __LOAD_FAR_HANDLER(r12, DOTSYM(idle_return_gpr_loss), real_trampolines) + mtctr r12 + bctr #endif #ifdef CONFIG_PPC_PSERIES @@ -979,16 +1047,14 @@ TRAMP_REAL_BEGIN(system_reset_fwnmi) EXC_COMMON_BEGIN(system_reset_common) __GEN_COMMON_ENTRY system_reset /* - * Increment paca->in_nmi then enable MSR_RI. SLB or MCE will be able - * to recover, but nested NMI will notice in_nmi and not recover - * because of the use of the NMI stack. in_nmi reentrancy is tested in - * system_reset_exception. + * Increment paca->in_nmi. When the interrupt entry wrapper later + * enable MSR_RI, then SLB or MCE will be able to recover, but a nested + * NMI will notice in_nmi and not recover because of the use of the NMI + * stack. in_nmi reentrancy is tested in system_reset_exception. */ lhz r10,PACA_IN_NMI(r13) addi r10,r10,1 sth r10,PACA_IN_NMI(r13) - li r10,MSR_RI - mtmsrd r10,1 mr r10,r1 ld r1,PACA_NMI_EMERG_SP(r13) @@ -1062,12 +1128,6 @@ INT_DEFINE_BEGIN(machine_check_early) IAREA=PACA_EXMC IVIRT=0 /* no virt entry point */ IREALMODE_COMMON=1 - /* - * MSR_RI is not enabled, because PACA_EXMC is being used, so a - * nested machine check corrupts it. machine_check_common enables - * MSR_RI. - */ - ISET_RI=0 ISTACK=0 IDAR=1 IDSISR=1 @@ -1078,13 +1138,13 @@ INT_DEFINE_BEGIN(machine_check) IVEC=0x200 IAREA=PACA_EXMC IVIRT=0 /* no virt entry point */ - ISET_RI=0 IDAR=1 IDSISR=1 IKVM_REAL=1 INT_DEFINE_END(machine_check) EXC_REAL_BEGIN(machine_check, 0x200, 0x100) + EARLY_BOOT_FIXUP GEN_INT_ENTRY machine_check_early, virt=0 EXC_REAL_END(machine_check, 0x200, 0x100) EXC_VIRT_NONE(0x4200, 0x100) @@ -1148,10 +1208,10 @@ EXC_COMMON_BEGIN(machine_check_early_common) BEGIN_FTR_SECTION bl enable_machine_check END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) - li r10,MSR_RI - mtmsrd r10,1 - addi r3,r1,STACK_FRAME_OVERHEAD +BEGIN_FTR_SECTION + bl machine_check_early_boot +END_FTR_SECTION(0, 1) // nop out after boot bl machine_check_early std r3,RESULT(r1) /* Save result */ ld r12,_MSR(r1) @@ -1238,10 +1298,6 @@ EXC_COMMON_BEGIN(machine_check_common) * save area: PACA_EXMC instead of PACA_EXGEN. */ GEN_COMMON machine_check - - /* Enable MSR_RI when finished with PACA_EXMC */ - li r10,MSR_RI - mtmsrd r10,1 addi r3,r1,STACK_FRAME_OVERHEAD bl machine_check_exception_async b interrupt_return_srr @@ -1369,11 +1425,15 @@ EXC_COMMON_BEGIN(data_access_common) addi r3,r1,STACK_FRAME_OVERHEAD andis. r0,r4,DSISR_DABRMATCH@h bne- 1f +#ifdef CONFIG_PPC_64S_HASH_MMU BEGIN_MMU_FTR_SECTION bl do_hash_fault MMU_FTR_SECTION_ELSE bl do_page_fault ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) +#else + bl do_page_fault +#endif b interrupt_return_srr 1: bl do_break @@ -1416,6 +1476,7 @@ EXC_VIRT_BEGIN(data_access_slb, 0x4380, 0x80) EXC_VIRT_END(data_access_slb, 0x4380, 0x80) EXC_COMMON_BEGIN(data_access_slb_common) GEN_COMMON data_access_slb +#ifdef CONFIG_PPC_64S_HASH_MMU BEGIN_MMU_FTR_SECTION /* HPT case, do SLB fault */ addi r3,r1,STACK_FRAME_OVERHEAD @@ -1428,9 +1489,12 @@ MMU_FTR_SECTION_ELSE /* Radix case, access is outside page table range */ li r3,-EFAULT ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) +#else + li r3,-EFAULT +#endif std r3,RESULT(r1) addi r3,r1,STACK_FRAME_OVERHEAD - bl do_bad_slb_fault + bl do_bad_segment_interrupt b interrupt_return_srr @@ -1462,11 +1526,15 @@ EXC_VIRT_END(instruction_access, 0x4400, 0x80) EXC_COMMON_BEGIN(instruction_access_common) GEN_COMMON instruction_access addi r3,r1,STACK_FRAME_OVERHEAD +#ifdef CONFIG_PPC_64S_HASH_MMU BEGIN_MMU_FTR_SECTION bl do_hash_fault MMU_FTR_SECTION_ELSE bl do_page_fault ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) +#else + bl do_page_fault +#endif b interrupt_return_srr @@ -1496,6 +1564,7 @@ EXC_VIRT_BEGIN(instruction_access_slb, 0x4480, 0x80) EXC_VIRT_END(instruction_access_slb, 0x4480, 0x80) EXC_COMMON_BEGIN(instruction_access_slb_common) GEN_COMMON instruction_access_slb +#ifdef CONFIG_PPC_64S_HASH_MMU BEGIN_MMU_FTR_SECTION /* HPT case, do SLB fault */ addi r3,r1,STACK_FRAME_OVERHEAD @@ -1508,9 +1577,12 @@ MMU_FTR_SECTION_ELSE /* Radix case, access is outside page table range */ li r3,-EFAULT ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) +#else + li r3,-EFAULT +#endif std r3,RESULT(r1) addi r3,r1,STACK_FRAME_OVERHEAD - bl do_bad_slb_fault + bl do_bad_segment_interrupt b interrupt_return_srr @@ -1536,6 +1608,12 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) * * If soft masked, the masked handler will note the pending interrupt for * replay, and clear MSR[EE] in the interrupted context. + * + * CFAR is not required because this is an asynchronous interrupt that in + * general won't have much bearing on the state of the CPU, with the possible + * exception of crash/debug IPIs, but those are generally moving to use SRESET + * IPIs. Unless this is an HV interrupt and KVM HV is possible, in which case + * it may be exiting the guest and need CFAR to be saved. */ INT_DEFINE_BEGIN(hardware_interrupt) IVEC=0x500 @@ -1543,6 +1621,10 @@ INT_DEFINE_BEGIN(hardware_interrupt) IMASK=IRQS_DISABLED IKVM_REAL=1 IKVM_VIRT=1 + ICFAR=0 +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + ICFAR_IF_HVMODE=1 +#endif INT_DEFINE_END(hardware_interrupt) EXC_REAL_BEGIN(hardware_interrupt, 0x500, 0x100) @@ -1606,51 +1688,7 @@ INT_DEFINE_BEGIN(program_check) INT_DEFINE_END(program_check) EXC_REAL_BEGIN(program_check, 0x700, 0x100) - -#ifdef CONFIG_CPU_LITTLE_ENDIAN - /* - * There's a short window during boot where although the kernel is - * running little endian, any exceptions will cause the CPU to switch - * back to big endian. For example a WARN() boils down to a trap - * instruction, which will cause a program check, and we end up here but - * with the CPU in big endian mode. The first instruction of the program - * check handler (in GEN_INT_ENTRY below) is an mtsprg, which when - * executed in the wrong endian is an lhzu with a ~3GB displacement from - * r3. The content of r3 is random, so that is a load from some random - * location, and depending on the system can easily lead to a checkstop, - * or an infinitely recursive page fault. - * - * So to handle that case we have a trampoline here that can detect we - * are in the wrong endian and flip us back to the correct endian. We - * can't flip MSR[LE] using mtmsr, so we have to use rfid. That requires - * backing up SRR0/1 as well as a GPR. To do that we use SPRG0/2/3, as - * SPRG1 is already used for the paca. SPRG3 is user readable, but this - * trampoline is only active very early in boot, and SPRG3 will be - * reinitialised in vdso_getcpu_init() before userspace starts. - */ -BEGIN_FTR_SECTION - tdi 0,0,0x48 // Trap never, or in reverse endian: b . + 8 - b 1f // Skip trampoline if endian is correct - .long 0xa643707d // mtsprg 0, r11 Backup r11 - .long 0xa6027a7d // mfsrr0 r11 - .long 0xa643727d // mtsprg 2, r11 Backup SRR0 in SPRG2 - .long 0xa6027b7d // mfsrr1 r11 - .long 0xa643737d // mtsprg 3, r11 Backup SRR1 in SPRG3 - .long 0xa600607d // mfmsr r11 - .long 0x01006b69 // xori r11, r11, 1 Invert MSR[LE] - .long 0xa6037b7d // mtsrr1 r11 - .long 0x34076039 // li r11, 0x734 - .long 0xa6037a7d // mtsrr0 r11 - .long 0x2400004c // rfid - mfsprg r11, 3 - mtsrr1 r11 // Restore SRR1 - mfsprg r11, 2 - mtsrr0 r11 // Restore SRR0 - mfsprg r11, 0 // Restore r11 -1: -END_FTR_SECTION(0, 1) // nop out after boot -#endif /* CONFIG_CPU_LITTLE_ENDIAN */ - + EARLY_BOOT_FIXUP GEN_INT_ENTRY program_check, virt=0 EXC_REAL_END(program_check, 0x700, 0x100) EXC_VIRT_BEGIN(program_check, 0x4700, 0x100) @@ -1764,6 +1802,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_TM) * If PPC_WATCHDOG is configured, the soft masked handler will actually set * things back up to run soft_nmi_interrupt as a regular interrupt handler * on the emergency stack. + * + * CFAR is not required because this is asynchronous (see hardware_interrupt). + * A watchdog interrupt may like to have CFAR, but usually the interesting + * branch is long gone by that point (e.g., infinite loop). */ INT_DEFINE_BEGIN(decrementer) IVEC=0x900 @@ -1771,6 +1813,7 @@ INT_DEFINE_BEGIN(decrementer) #ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE IKVM_REAL=1 #endif + ICFAR=0 INT_DEFINE_END(decrementer) EXC_REAL_BEGIN(decrementer, 0x900, 0x80) @@ -1846,6 +1889,8 @@ EXC_COMMON_BEGIN(hdecrementer_common) * If soft masked, the masked handler will note the pending interrupt for * replay, leaving MSR[EE] enabled in the interrupted context because the * doorbells are edge triggered. + * + * CFAR is not required, similarly to hardware_interrupt. */ INT_DEFINE_BEGIN(doorbell_super) IVEC=0xa00 @@ -1853,6 +1898,7 @@ INT_DEFINE_BEGIN(doorbell_super) #ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE IKVM_REAL=1 #endif + ICFAR=0 INT_DEFINE_END(doorbell_super) EXC_REAL_BEGIN(doorbell_super, 0xa00, 0x100) @@ -1904,6 +1950,7 @@ INT_DEFINE_BEGIN(system_call) IVEC=0xc00 IKVM_REAL=1 IKVM_VIRT=1 + ICFAR=0 INT_DEFINE_END(system_call) .macro SYSTEM_CALL virt @@ -1942,12 +1989,12 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE) HMT_MEDIUM .if ! \virt - __LOAD_HANDLER(r10, system_call_common_real) + __LOAD_HANDLER(r10, system_call_common_real, real_vectors) mtctr r10 bctr .else #ifdef CONFIG_RELOCATABLE - __LOAD_HANDLER(r10, system_call_common) + __LOAD_HANDLER(r10, system_call_common, virt_vectors) mtctr r10 bctr #else @@ -2001,7 +2048,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) * Requires __LOAD_FAR_HANDLER beause kvmppc_hcall lives * outside the head section. */ - __LOAD_FAR_HANDLER(r10, kvmppc_hcall) + __LOAD_FAR_HANDLER(r10, kvmppc_hcall, real_trampolines) mtctr r10 bctr #else @@ -2202,6 +2249,11 @@ EXC_COMMON_BEGIN(hmi_exception_common) * Interrupt 0xe80 - Directed Hypervisor Doorbell Interrupt. * This is an asynchronous interrupt in response to a msgsnd doorbell. * Similar to the 0xa00 doorbell but for host rather than guest. + * + * CFAR is not required (similar to doorbell_interrupt), unless KVM HV + * is enabled, in which case it may be a guest exit. Most PowerNV kernels + * include KVM support so it would be nice if this could be dynamically + * patched out if KVM was not currently running any guests. */ INT_DEFINE_BEGIN(h_doorbell) IVEC=0xe80 @@ -2209,6 +2261,9 @@ INT_DEFINE_BEGIN(h_doorbell) IMASK=IRQS_DISABLED IKVM_REAL=1 IKVM_VIRT=1 +#ifndef CONFIG_KVM_BOOK3S_HV_POSSIBLE + ICFAR=0 +#endif INT_DEFINE_END(h_doorbell) EXC_REAL_BEGIN(h_doorbell, 0xe80, 0x20) @@ -2232,6 +2287,9 @@ EXC_COMMON_BEGIN(h_doorbell_common) * Interrupt 0xea0 - Hypervisor Virtualization Interrupt. * This is an asynchronous interrupt in response to an "external exception". * Similar to 0x500 but for host only. + * + * Like h_doorbell, CFAR is only required for KVM HV because this can be + * a guest exit. */ INT_DEFINE_BEGIN(h_virt_irq) IVEC=0xea0 @@ -2239,6 +2297,9 @@ INT_DEFINE_BEGIN(h_virt_irq) IMASK=IRQS_DISABLED IKVM_REAL=1 IKVM_VIRT=1 +#ifndef CONFIG_KVM_BOOK3S_HV_POSSIBLE + ICFAR=0 +#endif INT_DEFINE_END(h_virt_irq) EXC_REAL_BEGIN(h_virt_irq, 0xea0, 0x20) @@ -2275,6 +2336,8 @@ EXC_VIRT_NONE(0x4ee0, 0x20) * * If soft masked, the masked handler will note the pending interrupt for * replay, and clear MSR[EE] in the interrupted context. + * + * CFAR is not used by perf interrupts so not required. */ INT_DEFINE_BEGIN(performance_monitor) IVEC=0xf00 @@ -2282,6 +2345,7 @@ INT_DEFINE_BEGIN(performance_monitor) #ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE IKVM_REAL=1 #endif + ICFAR=0 INT_DEFINE_END(performance_monitor) EXC_REAL_BEGIN(performance_monitor, 0xf00, 0x20) @@ -2293,9 +2357,21 @@ EXC_VIRT_END(performance_monitor, 0x4f00, 0x20) EXC_COMMON_BEGIN(performance_monitor_common) GEN_COMMON performance_monitor addi r3,r1,STACK_FRAME_OVERHEAD - bl performance_monitor_exception + lbz r4,PACAIRQSOFTMASK(r13) + cmpdi r4,IRQS_ENABLED + bne 1f + bl performance_monitor_exception_async b interrupt_return_srr +1: + bl performance_monitor_exception_nmi + /* Clear MSR_RI before setting SRR0 and SRR1. */ + li r9,0 + mtmsrd r9,1 + + kuap_kernel_restore r9, r10 + EXCEPTION_RESTORE_REGS hsrr=0 + RFI_TO_KERNEL /** * Interrupt 0xf20 - Vector Unavailable Interrupt. @@ -2706,6 +2782,7 @@ EXC_VIRT_NONE(0x5800, 0x100) INT_DEFINE_BEGIN(soft_nmi) IVEC=0x900 ISTACK=0 + ICFAR=0 INT_DEFINE_END(soft_nmi) /* @@ -2739,7 +2816,7 @@ EXC_COMMON_BEGIN(soft_nmi_common) /* * An interrupt came in while soft-disabled. We set paca->irq_happened, then: - * - If it was a decrementer interrupt, we bump the dec to max and and return. + * - If it was a decrementer interrupt, we bump the dec to max and return. * - If it was a doorbell we return immediately since doorbells are edge * triggered and won't automatically refire. * - If it was a HMI we return immediately since we handled it in realmode @@ -2754,6 +2831,20 @@ masked_Hinterrupt: masked_interrupt: .endif stw r9,PACA_EXGEN+EX_CCR(r13) +#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG + /* + * Ensure there was no previous MUST_HARD_MASK interrupt or + * HARD_DIS setting. If this does fire, the interrupt is still + * masked and MSR[EE] will be cleared on return, so no need to + * panic, but somebody probably enabled MSR[EE] under + * PACA_IRQ_HARD_DIS, mtmsr(mfmsr() | MSR_x) being a common + * cause. + */ + lbz r9,PACAIRQHAPPENED(r13) + andi. r9,r9,(PACA_IRQ_MUST_HARD_MASK|PACA_IRQ_HARD_DIS) +0: tdnei r9,0 + EMIT_WARN_ENTRY 0b,__FILE__,__LINE__,(BUGFLAG_WARNING | BUGFLAG_ONCE) +#endif lbz r9,PACAIRQHAPPENED(r13) or r9,r9,r10 stb r9,PACAIRQHAPPENED(r13) @@ -2994,22 +3085,6 @@ EXPORT_SYMBOL(do_uaccess_flush) MASKED_INTERRUPT MASKED_INTERRUPT hsrr=1 - /* - * Relocation-on interrupts: A subset of the interrupts can be delivered - * with IR=1/DR=1, if AIL==2 and MSR.HV won't be changed by delivering - * it. Addresses are the same as the original interrupt addresses, but - * offset by 0xc000000000004000. - * It's impossible to receive interrupts below 0x300 via this mechanism. - * KVM: None of these traps are from the guest ; anything that escalated - * to HV=1 from HV=0 is delivered via real mode handlers. - */ - - /* - * This uses the standard macro, since the original 0x300 vector - * only has extra guff for STAB-based processors -- which never - * come here. - */ - USE_FIXED_SECTION(virt_trampolines) /* * All code below __end_soft_masked is treated as soft-masked. If @@ -3025,7 +3100,7 @@ USE_FIXED_SECTION(virt_trampolines) .align 7 .globl __end_interrupts __end_interrupts: -DEFINE_FIXED_SYMBOL(__end_interrupts) +DEFINE_FIXED_SYMBOL(__end_interrupts, virt_trampolines) CLOSE_FIXED_SECTION(real_vectors); CLOSE_FIXED_SECTION(real_trampolines); @@ -3035,7 +3110,7 @@ CLOSE_FIXED_SECTION(virt_trampolines); USE_TEXT_SECTION() /* MSR[RI] should be clear because this uses SRR[01] */ -enable_machine_check: +_GLOBAL(enable_machine_check) mflr r0 bcl 20,31,$+4 0: mflr r3 diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index b7ceb041743c..ea0a073abd96 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -25,9 +25,10 @@ #include <linux/cma.h> #include <linux/hugetlb.h> #include <linux/debugfs.h> +#include <linux/of.h> +#include <linux/of_fdt.h> #include <asm/page.h> -#include <asm/prom.h> #include <asm/fadump.h> #include <asm/fadump-internal.h> #include <asm/setup.h> @@ -73,8 +74,8 @@ static struct cma *fadump_cma; * The total size of fadump reserved memory covers for boot memory size * + cpu data size + hpte size and metadata. * Initialize only the area equivalent to boot memory size for CMA use. - * The reamining portion of fadump reserved memory will be not given - * to CMA and pages for thoes will stay reserved. boot memory size is + * The remaining portion of fadump reserved memory will be not given + * to CMA and pages for those will stay reserved. boot memory size is * aligned per CMA requirement to satisy cma_init_reserved_mem() call. * But for some reason even if it fails we still have the memory reservation * with us and we can still continue doing fadump. @@ -113,6 +114,12 @@ static int __init fadump_cma_init(void) } /* + * If CMA activation fails, keep the pages reserved, instead of + * exposing them to buddy allocator. Same as 'fadump=nocma' case. + */ + cma_reserve_pages_on_error(fadump_cma); + + /* * So we now have successfully initialized cma area for fadump. */ pr_info("Initialized 0x%lx bytes cma area at %ldMB from 0x%lx " @@ -251,7 +258,7 @@ bool is_fadump_reserved_mem_contiguous(void) } /* Print firmware assisted dump configurations for debugging purpose. */ -static void fadump_show_config(void) +static void __init fadump_show_config(void) { int i; @@ -353,12 +360,17 @@ static __init u64 fadump_calculate_reserve_size(void) * Calculate the total memory size required to be reserved for * firmware-assisted dump registration. */ -static unsigned long get_fadump_area_size(void) +static unsigned long __init get_fadump_area_size(void) { unsigned long size = 0; size += fw_dump.cpu_state_data_size; size += fw_dump.hpte_region_size; + /* + * Account for pagesize alignment of boot memory area destination address. + * This faciliates in mmap reading of first kernel's memory. + */ + size = PAGE_ALIGN(size); size += fw_dump.boot_memory_size; size += sizeof(struct fadump_crash_info_header); size += sizeof(struct elfhdr); /* ELF core header.*/ @@ -462,7 +474,7 @@ static int __init fadump_get_boot_mem_regions(void) * with the given memory range. * False, otherwise. */ -static bool overlaps_reserved_ranges(u64 base, u64 end, int *idx) +static bool __init overlaps_reserved_ranges(u64 base, u64 end, int *idx) { bool ret = false; int i; @@ -544,7 +556,7 @@ int __init fadump_reserve_mem(void) if (!fw_dump.nocma) { fw_dump.boot_memory_size = ALIGN(fw_dump.boot_memory_size, - FADUMP_CMA_ALIGNMENT); + CMA_MIN_ALIGNMENT_BYTES); } #endif @@ -722,7 +734,7 @@ void crash_fadump(struct pt_regs *regs, const char *str) else ppc_save_regs(&fdh->regs); - fdh->online_mask = *cpu_online_mask; + fdh->cpu_mask = *cpu_online_mask; /* * If we came in via system reset, wait a while for the secondary @@ -737,7 +749,7 @@ void crash_fadump(struct pt_regs *regs, const char *str) fw_dump.ops->fadump_trigger(fdh, str); } -u32 *fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs) +u32 *__init fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs) { struct elf_prstatus prstatus; @@ -746,13 +758,13 @@ u32 *fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs) * FIXME: How do i get PID? Do I really need it? * prstatus.pr_pid = ???? */ - elf_core_copy_kernel_regs(&prstatus.pr_reg, regs); + elf_core_copy_regs(&prstatus.pr_reg, regs); buf = append_elf_note(buf, CRASH_CORE_NOTE_NAME, NT_PRSTATUS, &prstatus, sizeof(prstatus)); return buf; } -void fadump_update_elfcore_header(char *bufp) +void __init fadump_update_elfcore_header(char *bufp) { struct elf_phdr *phdr; @@ -770,7 +782,7 @@ void fadump_update_elfcore_header(char *bufp) return; } -static void *fadump_alloc_buffer(unsigned long size) +static void *__init fadump_alloc_buffer(unsigned long size) { unsigned long count, i; struct page *page; @@ -792,7 +804,7 @@ static void fadump_free_buffer(unsigned long vaddr, unsigned long size) free_reserved_area((void *)vaddr, (void *)(vaddr + size), -1, NULL); } -s32 fadump_setup_cpu_notes_buf(u32 num_cpus) +s32 __init fadump_setup_cpu_notes_buf(u32 num_cpus) { /* Allocate buffer to hold cpu crash notes. */ fw_dump.cpu_notes_buf_size = num_cpus * sizeof(note_buf_t); @@ -861,7 +873,6 @@ static int fadump_alloc_mem_ranges(struct fadump_mrange_info *mrange_info) sizeof(struct fadump_memory_range)); return 0; } - static inline int fadump_add_mem_range(struct fadump_mrange_info *mrange_info, u64 base, u64 end) { @@ -880,7 +891,12 @@ static inline int fadump_add_mem_range(struct fadump_mrange_info *mrange_info, start = mem_ranges[mrange_info->mem_range_cnt - 1].base; size = mem_ranges[mrange_info->mem_range_cnt - 1].size; - if ((start + size) == base) + /* + * Boot memory area needs separate PT_LOAD segment(s) as it + * is moved to a different location at the time of crash. + * So, fold only if the region is not boot memory area. + */ + if ((start + size) == base && start >= fw_dump.boot_mem_top) is_adjacent = true; } if (!is_adjacent) { @@ -962,11 +978,14 @@ static int fadump_init_elfcore_header(char *bufp) elf->e_entry = 0; elf->e_phoff = sizeof(struct elfhdr); elf->e_shoff = 0; -#if defined(_CALL_ELF) - elf->e_flags = _CALL_ELF; -#else - elf->e_flags = 0; -#endif + + if (IS_ENABLED(CONFIG_PPC64_ELF_ABI_V2)) + elf->e_flags = 2; + else if (IS_ENABLED(CONFIG_PPC64_ELF_ABI_V1)) + elf->e_flags = 1; + else + elf->e_flags = 0; + elf->e_ehsize = sizeof(struct elfhdr); elf->e_phentsize = sizeof(struct elf_phdr); elf->e_phnum = 0; @@ -1158,6 +1177,11 @@ static unsigned long init_fadump_header(unsigned long addr) fdh->elfcorehdr_addr = addr; /* We will set the crashing cpu id in crash_fadump() during crash. */ fdh->crashing_cpu = FADUMP_CPU_UNKNOWN; + /* + * When LPAR is terminated by PYHP, ensure all possible CPUs' + * register data is processed while exporting the vmcore. + */ + fdh->cpu_mask = *cpu_possible_mask; return addr; } @@ -1265,7 +1289,6 @@ static void fadump_release_reserved_area(u64 start, u64 end) static void sort_and_merge_mem_ranges(struct fadump_mrange_info *mrange_info) { struct fadump_memory_range *mem_ranges; - struct fadump_memory_range tmp_range; u64 base, size; int i, j, idx; @@ -1280,11 +1303,8 @@ static void sort_and_merge_mem_ranges(struct fadump_mrange_info *mrange_info) if (mem_ranges[idx].base > mem_ranges[j].base) idx = j; } - if (idx != i) { - tmp_range = mem_ranges[idx]; - mem_ranges[idx] = mem_ranges[i]; - mem_ranges[i] = tmp_range; - } + if (idx != i) + swap(mem_ranges[idx], mem_ranges[i]); } /* Merge adjacent reserved ranges */ @@ -1447,7 +1467,7 @@ static ssize_t release_mem_store(struct kobject *kobj, } /* Release the reserved memory and disable the FADump */ -static void unregister_fadump(void) +static void __init unregister_fadump(void) { fadump_cleanup(); fadump_release_memory(fw_dump.reserve_dump_area_start, @@ -1547,7 +1567,7 @@ ATTRIBUTE_GROUPS(fadump); DEFINE_SHOW_ATTRIBUTE(fadump_region); -static void fadump_init_files(void) +static void __init fadump_init_files(void) { int rc = 0; @@ -1637,13 +1657,28 @@ int __init setup_fadump(void) if (fw_dump.ops->fadump_process(&fw_dump) < 0) fadump_invalidate_release_mem(); } - /* Initialize the kernel dump memory structure for FAD registration. */ - else if (fw_dump.reserve_dump_area_size) + /* Initialize the kernel dump memory structure and register with f/w */ + else if (fw_dump.reserve_dump_area_size) { fw_dump.ops->fadump_init_mem_struct(&fw_dump); + register_fadump(); + } + + /* + * In case of panic, fadump is triggered via ppc_panic_event() + * panic notifier. Setting crash_kexec_post_notifiers to 'true' + * lets panic() function take crash friendly path before panic + * notifiers are invoked. + */ + crash_kexec_post_notifiers = true; return 1; } -subsys_initcall(setup_fadump); +/* + * Use subsys_initcall_sync() here because there is dependency with + * crash_save_vmcoreinfo_init(), which must run first to ensure vmcoreinfo initialization + * is done before registering with f/w. + */ +subsys_initcall_sync(setup_fadump); #else /* !CONFIG_PRESERVE_FA_DUMP */ /* Scan the Firmware Assisted dump configuration details. */ diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S index ba4afe3b5a9c..f71f2bbd4de6 100644 --- a/arch/powerpc/kernel/fpu.S +++ b/arch/powerpc/kernel/fpu.S @@ -81,7 +81,12 @@ EXPORT_SYMBOL(store_fp_state) */ _GLOBAL(load_up_fpu) mfmsr r5 +#ifdef CONFIG_PPC_BOOK3S_64 + /* interrupt doesn't set MSR[RI] and HPT can fault on current access */ + ori r5,r5,MSR_FP|MSR_RI +#else ori r5,r5,MSR_FP +#endif #ifdef CONFIG_VSX BEGIN_FTR_SECTION oris r5,r5,MSR_VSX@h diff --git a/arch/powerpc/kernel/head_32.h b/arch/powerpc/kernel/head_32.h index 349c4a820231..c3286260a7d1 100644 --- a/arch/powerpc/kernel/head_32.h +++ b/arch/powerpc/kernel/head_32.h @@ -115,8 +115,7 @@ _ASM_NOKPROBE_SYMBOL(\name\()_virt) stw r10,8(r1) li r10, \trapno stw r10,_TRAP(r1) - SAVE_4GPRS(3, r1) - SAVE_2GPRS(7, r1) + SAVE_GPRS(3, 8, r1) SAVE_NVGPRS(r1) stw r2,GPR2(r1) stw r12,_NIP(r1) @@ -136,6 +135,12 @@ _ASM_NOKPROBE_SYMBOL(\name\()_virt) andi. r12,r9,MSR_PR bne 777f bl prepare_transfer_to_handler +#ifdef CONFIG_PPC_KUEP + b 778f +777: + bl __kuep_lock +778: +#endif 777: #endif .endm diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S index 7d72ee5ab387..088f500896c7 100644 --- a/arch/powerpc/kernel/head_40x.S +++ b/arch/powerpc/kernel/head_40x.S @@ -27,6 +27,7 @@ #include <linux/init.h> #include <linux/pgtable.h> +#include <linux/sizes.h> #include <asm/processor.h> #include <asm/page.h> #include <asm/mmu.h> @@ -52,8 +53,8 @@ * This is all going to change RSN when we add bi_recs....... -- Dan */ __HEAD -_ENTRY(_stext); -_ENTRY(_start); +_GLOBAL(_stext); +_GLOBAL(_start); mr r31,r3 /* save device tree ptr */ @@ -81,19 +82,19 @@ turn_on_mmu: */ . = 0xc0 crit_save: -_ENTRY(crit_r10) +_GLOBAL(crit_r10) .space 4 -_ENTRY(crit_r11) +_GLOBAL(crit_r11) .space 4 -_ENTRY(crit_srr0) +_GLOBAL(crit_srr0) .space 4 -_ENTRY(crit_srr1) +_GLOBAL(crit_srr1) .space 4 -_ENTRY(crit_r1) +_GLOBAL(crit_r1) .space 4 -_ENTRY(crit_dear) +_GLOBAL(crit_dear) .space 4 -_ENTRY(crit_esr) +_GLOBAL(crit_esr) .space 4 /* @@ -297,6 +298,10 @@ _ASM_NOKPROBE_SYMBOL(\name\()_virt) 3: mfspr r11,SPRN_SPRG_THREAD lwz r11,PGDIR(r11) +#ifdef CONFIG_PPC_KUAP + rlwinm. r9, r9, 0, 0xff + beq 5f /* Kuap fault */ +#endif 4: tophys(r11, r11) rlwimi r11, r10, 12, 20, 29 /* Create L1 (pgdir/pmd) address */ @@ -377,6 +382,10 @@ _ASM_NOKPROBE_SYMBOL(\name\()_virt) 3: mfspr r11,SPRN_SPRG_THREAD lwz r11,PGDIR(r11) +#ifdef CONFIG_PPC_KUAP + rlwinm. r9, r9, 0, 0xff + beq 5f /* Kuap fault */ +#endif 4: tophys(r11, r11) rlwimi r11, r10, 12, 20, 29 /* Create L1 (pgdir/pmd) address */ @@ -650,7 +659,7 @@ start_here: b . /* prevent prefetch past rfi */ /* Set up the initial MMU state so we can do the first level of - * kernel initialization. This maps the first 16 MBytes of memory 1:1 + * kernel initialization. This maps the first 32 MBytes of memory 1:1 * virtual to physical and more importantly sets the cache mode. */ initial_mmu: @@ -687,6 +696,12 @@ initial_mmu: tlbwe r4,r0,TLB_DATA /* Load the data portion of the entry */ tlbwe r3,r0,TLB_TAG /* Load the tag portion of the entry */ + li r0,62 /* TLB slot 62 */ + addis r4,r4,SZ_16M@h + addis r3,r3,SZ_16M@h + tlbwe r4,r0,TLB_DATA /* Load the data portion of the entry */ + tlbwe r3,r0,TLB_TAG /* Load the tag portion of the entry */ + isync /* Establish the exception vector base diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S index 02d2928d1e01..f15cb9fdb692 100644 --- a/arch/powerpc/kernel/head_44x.S +++ b/arch/powerpc/kernel/head_44x.S @@ -52,8 +52,8 @@ * */ __HEAD -_ENTRY(_stext); -_ENTRY(_start); +_GLOBAL(_stext); +_GLOBAL(_start); /* * Reserve a word at a fixed location to store the address * of abatron_pteptrs @@ -334,6 +334,10 @@ interrupt_base: mfspr r12,SPRN_MMUCR mfspr r13,SPRN_PID /* Get PID */ rlwimi r12,r13,0,24,31 /* Set TID */ +#ifdef CONFIG_PPC_KUAP + cmpwi r13,0 + beq 2f /* KUAP Fault */ +#endif 4: mtspr SPRN_MMUCR,r12 @@ -444,6 +448,10 @@ interrupt_base: mfspr r12,SPRN_MMUCR mfspr r13,SPRN_PID /* Get PID */ rlwimi r12,r13,0,24,31 /* Set TID */ +#ifdef CONFIG_PPC_KUAP + cmpwi r13,0 + beq 2f /* KUAP Fault */ +#endif 4: mtspr SPRN_MMUCR,r12 @@ -532,10 +540,7 @@ finish_tlb_load_44x: andi. r10,r12,_PAGE_USER /* User page ? */ beq 1f /* nope, leave U bits empty */ rlwimi r11,r11,3,26,28 /* yes, copy S bits to U */ -#ifdef CONFIG_PPC_KUEP -0: rlwinm r11,r11,0,~PPC44x_TLB_SX /* Clear SX if User page */ - patch_site 0b, patch__tlb_44x_kuep -#endif + rlwinm r11,r11,0,~PPC44x_TLB_SX /* Clear SX if User page */ 1: tlbwe r11,r13,PPC44x_TLB_ATTRIB /* Write ATTRIB */ /* Done...restore registers and get out of here. @@ -575,6 +580,10 @@ finish_tlb_load_44x: 3: mfspr r11,SPRN_SPRG3 lwz r11,PGDIR(r11) mfspr r12,SPRN_PID /* Get PID */ +#ifdef CONFIG_PPC_KUAP + cmpwi r12,0 + beq 2f /* KUAP Fault */ +#endif 4: mtspr SPRN_MMUCR,r12 /* Set MMUCR */ /* Mask of required permission bits. Note that while we @@ -672,6 +681,10 @@ finish_tlb_load_44x: 3: mfspr r11,SPRN_SPRG_THREAD lwz r11,PGDIR(r11) mfspr r12,SPRN_PID /* Get PID */ +#ifdef CONFIG_PPC_KUAP + cmpwi r12,0 + beq 2f /* KUAP Fault */ +#endif 4: mtspr SPRN_MMUCR,r12 /* Set MMUCR */ /* Make up the required permissions */ @@ -747,10 +760,7 @@ finish_tlb_load_47x: andi. r10,r12,_PAGE_USER /* User page ? */ beq 1f /* nope, leave U bits empty */ rlwimi r11,r11,3,26,28 /* yes, copy S bits to U */ -#ifdef CONFIG_PPC_KUEP -0: rlwinm r11,r11,0,~PPC47x_TLB2_SX /* Clear SX if User page */ - patch_site 0b, patch__tlb_47x_kuep -#endif + rlwinm r11,r11,0,~PPC47x_TLB2_SX /* Clear SX if User page */ 1: tlbwe r11,r13,2 /* Done...restore registers and get out of here. diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index f17ae2083733..dedcc6fe2263 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -111,7 +111,7 @@ __secondary_hold_acknowledge: #ifdef CONFIG_RELOCATABLE /* 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 + * is used by kexec-tools to keep the kdump kernel in the * crash_kernel region. The loader is responsible for * observing the alignment requirement. */ @@ -126,7 +126,7 @@ __secondary_hold_acknowledge: . = 0x5c .globl __run_at_load __run_at_load: -DEFINE_FIXED_SYMBOL(__run_at_load) +DEFINE_FIXED_SYMBOL(__run_at_load, first_256B) .long RUN_AT_LOAD_DEFAULT #endif @@ -143,7 +143,7 @@ DEFINE_FIXED_SYMBOL(__run_at_load) .globl __secondary_hold __secondary_hold: FIXUP_ENDIAN -#ifndef CONFIG_PPC_BOOK3E +#ifndef CONFIG_PPC_BOOK3E_64 mfmsr r24 ori r24,r24,MSR_RI mtmsrd r24 /* RI on */ @@ -156,20 +156,20 @@ __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,(ABS_ADDR(__secondary_hold_acknowledge))(0) + std r24,(ABS_ADDR(__secondary_hold_acknowledge, first_256B))(0) sync li r26,0 -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 tovirt(r26,r26) #endif /* All secondary cpus wait here until told to start. */ -100: ld r12,(ABS_ADDR(__secondary_hold_spinloop))(r26) +100: ld r12,(ABS_ADDR(__secondary_hold_spinloop, first_256B))(r26) cmpdi 0,r12,0 beq 100b #if defined(CONFIG_SMP) || defined(CONFIG_KEXEC_CORE) -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 tovirt(r12,r12) #endif mtctr r12 @@ -178,7 +178,7 @@ __secondary_hold: * it may be the case that other platforms have r4 right to * begin with, this gives us some safety in case it is not */ -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 mr r4,r25 #else li r4,0 @@ -192,13 +192,6 @@ __secondary_hold: #endif CLOSE_FIXED_SECTION(first_256B) -/* This value is used to mark exception frames on the stack. */ - .section ".toc","aw" -/* This value is used to mark exception frames on the stack. */ -exception_marker: - .tc ID_EXC_MARKER[TC],STACK_FRAME_REGS_MARKER - .previous - /* * On server, we include the exception vectors code here as it * relies on absolute addressing which is only possible within @@ -214,7 +207,7 @@ USE_TEXT_SECTION() #include "interrupt_64.S" -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 /* * The booting_thread_hwid holds the thread id we want to boot in cpu * hotplug case. It is set by cpu hotplug code, and is invalid by default. @@ -322,7 +315,7 @@ _GLOBAL(fsl_secondary_thread_init) bl book3e_secondary_thread_init b generic_secondary_common_init -#endif /* CONFIG_PPC_BOOK3E */ +#endif /* CONFIG_PPC_BOOK3E_64 */ /* * On pSeries and most other platforms, secondary processors spin @@ -345,7 +338,7 @@ _GLOBAL(generic_secondary_smp_init) bl relative_toc tovirt(r2,r2) -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 /* Book3E initialization */ mr r3,r24 mr r4,r25 @@ -400,8 +393,12 @@ generic_secondary_common_init: #else LOAD_REG_ADDR(r8, paca_ptrs) /* Load paca_ptrs pointe */ ld r8,0(r8) /* Get base vaddr of array */ +#if (NR_CPUS == 1) || defined(CONFIG_FORCE_NR_CPUS) + LOAD_REG_IMMEDIATE(r7, NR_CPUS) +#else LOAD_REG_ADDR(r7, nr_cpu_ids) /* Load nr_cpu_ids address */ lwz r7,0(r7) /* also the max paca allocated */ +#endif li r5,0 /* logical cpu id */ 1: sldi r9,r5,3 /* get paca_ptrs[] index from cpu id */ @@ -417,7 +414,7 @@ generic_secondary_common_init: b kexec_wait /* next kernel might do better */ 2: SET_PACA(r13) -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 addi r12,r13,PACA_EXTLB /* and TLB exc frame in another */ mtspr SPRN_SPRG_TLB_EXFRAME,r12 #endif @@ -435,7 +432,7 @@ generic_secondary_common_init: ld r12,CPU_SPEC_RESTORE(r23) cmpdi 0,r12,0 beq 3f -#ifdef PPC64_ELF_ABI_v1 +#ifdef CONFIG_PPC64_ELF_ABI_V1 ld r12,0(r12) #endif mtctr r12 @@ -494,6 +491,9 @@ __start_initialization_multiplatform: /* Make sure we are running in 64 bits mode */ bl enable_64b_mode + /* Zero r13 (paca) so early program check / mce don't use it */ + li r13,0 + /* Get TOC pointer (current runtime address) */ bl relative_toc @@ -519,7 +519,7 @@ __start_initialization_multiplatform: mr r29,r9 #endif -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 bl start_initialization_book3e b __after_prom_start #else @@ -540,7 +540,7 @@ __start_initialization_multiplatform: /* Switch off MMU if not already off */ bl __mmu_off b __after_prom_start -#endif /* CONFIG_PPC_BOOK3E */ +#endif /* CONFIG_PPC_BOOK3E_64 */ __REF __boot_from_prom: @@ -587,11 +587,11 @@ __after_prom_start: /* process relocations for the final address of the kernel */ lis r25,PAGE_OFFSET@highest /* compute virtual base of kernel */ sldi r25,r25,32 -#if defined(CONFIG_PPC_BOOK3E) +#if defined(CONFIG_PPC_BOOK3E_64) tovirt(r26,r26) /* on booke, we already run at PAGE_OFFSET */ #endif lwz r7,(FIXED_SYMBOL_ABS_ADDR(__run_at_load))(r26) -#if defined(CONFIG_PPC_BOOK3E) +#if defined(CONFIG_PPC_BOOK3E_64) tophys(r26,r26) #endif cmplwi cr0,r7,1 /* flagged to stay where we are ? */ @@ -599,7 +599,7 @@ __after_prom_start: add r25,r25,r26 1: mr r3,r25 bl relocate -#if defined(CONFIG_PPC_BOOK3E) +#if defined(CONFIG_PPC_BOOK3E_64) /* IVPR needs to be set after relocation. */ bl init_core_book3e #endif @@ -613,11 +613,11 @@ __after_prom_start: * Note: This process overwrites the OF exception vectors. */ li r3,0 /* target addr */ -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 tovirt(r3,r3) /* on booke, we already run at PAGE_OFFSET */ #endif mr. r4,r26 /* In some cases the loader may */ -#if defined(CONFIG_PPC_BOOK3E) +#if defined(CONFIG_PPC_BOOK3E_64) tovirt(r4,r4) #endif beq 9f /* have already put us at zero */ @@ -630,14 +630,14 @@ __after_prom_start: * variable __run_at_load, if it is set the kernel is treated as relocatable * kernel, otherwise it will be moved to PHYSICAL_START */ -#if defined(CONFIG_PPC_BOOK3E) +#if defined(CONFIG_PPC_BOOK3E_64) tovirt(r26,r26) /* on booke, we already run at PAGE_OFFSET */ #endif lwz r7,(FIXED_SYMBOL_ABS_ADDR(__run_at_load))(r26) cmplwi cr0,r7,1 bne 3f -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 LOAD_REG_ADDR(r5, __end_interrupts) LOAD_REG_ADDR(r11, _stext) sub r5,r5,r11 @@ -649,15 +649,15 @@ __after_prom_start: 3: #endif /* # bytes of memory to copy */ - lis r5,(ABS_ADDR(copy_to_here))@ha - addi r5,r5,(ABS_ADDR(copy_to_here))@l + lis r5,(ABS_ADDR(copy_to_here, text))@ha + addi r5,r5,(ABS_ADDR(copy_to_here, text))@l bl copy_and_flush /* copy the first n bytes */ /* this includes the code being */ /* executed here. */ /* Jump to the copy of this code that we just made */ - addis r8,r3,(ABS_ADDR(4f))@ha - addi r12,r8,(ABS_ADDR(4f))@l + addis r8,r3,(ABS_ADDR(4f, text))@ha + addi r12,r8,(ABS_ADDR(4f, text))@l mtctr r12 bctr @@ -669,8 +669,8 @@ p_end: .8byte _end - copy_to_here * Now copy the rest of the kernel up to _end, add * _end - copy_to_here to the copy limit and run again. */ - addis r8,r26,(ABS_ADDR(p_end))@ha - ld r8,(ABS_ADDR(p_end))@l(r8) + addis r8,r26,(ABS_ADDR(p_end, text))@ha + ld r8,(ABS_ADDR(p_end, text))@l(r8) add r5,r5,r8 5: bl copy_and_flush /* copy the rest */ @@ -848,7 +848,7 @@ __secondary_start: * before going into C code. */ start_secondary_prolog: - ld r2,PACATOC(r13) + LOAD_PACA_TOC() li r3,0 std r3,0(r1) /* Zero the stack frame pointer */ bl start_secondary @@ -871,10 +871,10 @@ _GLOBAL(start_secondary_resume) */ enable_64b_mode: mfmsr r11 /* grab the current MSR */ -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 oris r11,r11,0x8000 /* CM bit set, we'll set ICM later */ mtmsr r11 -#else /* CONFIG_PPC_BOOK3E */ +#else /* CONFIG_PPC_BOOK3E_64 */ LOAD_REG_IMMEDIATE(r12, MSR_64BIT) or r11,r11,r12 mtmsrd r11 @@ -904,7 +904,7 @@ _GLOBAL(relative_toc) blr .balign 8 -p_toc: .8byte __toc_start + 0x8000 - 0b +p_toc: .8byte .TOC. - 0b /* * This is where the main kernel code starts. @@ -940,7 +940,7 @@ start_here_multiplatform: std r29,8(r11); #endif -#ifndef CONFIG_PPC_BOOK3E +#ifndef CONFIG_PPC_BOOK3E_64 mfmsr r6 ori r6,r6,MSR_RI mtmsrd r6 /* RI on */ @@ -965,6 +965,9 @@ start_here_multiplatform: * and SLB setup before we turn on relocation. */ +#ifdef CONFIG_KASAN + bl kasan_early_init +#endif /* Restore parameters passed from prom_init/kexec */ mr r3,r31 LOAD_REG_ADDR(r12, DOTSYM(early_setup)) @@ -985,7 +988,7 @@ start_here_common: std r1,PACAKSAVE(r13) /* Load the TOC (virtual address) */ - ld r2,PACATOC(r13) + LOAD_PACA_TOC() /* Mark interrupts soft and hard disabled (they might be enabled * in the PACA when doing hotplug) diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_85xx.S index 0a9a0f301474..52c0ab416326 100644 --- a/arch/powerpc/kernel/head_fsl_booke.S +++ b/arch/powerpc/kernel/head_85xx.S @@ -54,8 +54,8 @@ * */ __HEAD -_ENTRY(_stext); -_ENTRY(_start); +_GLOBAL(_stext); +_GLOBAL(_start); /* * Reserve a word at a fixed location to store the address * of abatron_pteptrs @@ -129,7 +129,7 @@ _ENTRY(_start); /* * For the second relocation, we already set the right tlb entries - * for the kernel space, so skip the code in fsl_booke_entry_mapping.S + * for the kernel space, so skip the code in 85xx_entry_mapping.S */ cmpwi r19,1 beq set_ivor @@ -154,12 +154,12 @@ _ENTRY(_start); * if needed */ -_ENTRY(__early_start) +_GLOBAL(__early_start) LOAD_REG_ADDR_PIC(r20, kernstart_virt_addr) lwz r20,0(r20) #define ENTRY_MAPPING_BOOT_SETUP -#include "fsl_booke_entry_mapping.S" +#include "85xx_entry_mapping.S" #undef ENTRY_MAPPING_BOOT_SETUP set_ivor: @@ -462,6 +462,12 @@ END_BTB_FLUSH_SECTION mfspr r11,SPRN_SPRG_THREAD lwz r11,PGDIR(r11) +#ifdef CONFIG_PPC_KUAP + mfspr r12, SPRN_MAS1 + rlwinm. r12,r12,0,0x3fff0000 + beq 2f /* KUAP fault */ +#endif + 4: /* Mask of required permission bits. Note that while we * do copy ESR:ST to _PAGE_RW position as trying to write @@ -571,6 +577,12 @@ END_BTB_FLUSH_SECTION mfspr r11,SPRN_SPRG_THREAD lwz r11,PGDIR(r11) +#ifdef CONFIG_PPC_KUAP + mfspr r12, SPRN_MAS1 + rlwinm. r12,r12,0,0x3fff0000 + beq 2f /* KUAP fault */ +#endif + /* Make up the required permissions for user code */ #ifdef CONFIG_PTE_64BIT li r13,_PAGE_PRESENT | _PAGE_BAP_UX @@ -777,6 +789,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_BIG_PHYS) andi. r10, r11, _PAGE_USER /* Test for _PAGE_USER */ slwi r10, r12, 1 or r10, r10, r12 + rlwinm r10, r10, 0, ~_PAGE_EXEC /* Clear SX on user pages */ iseleq r12, r12, r10 rlwimi r13, r12, 0, 20, 31 /* Get RPN from PTE, merge w/ perms */ mtspr SPRN_MAS3, r13 @@ -899,7 +912,7 @@ get_phys_addr: * Global functions */ -#ifdef CONFIG_E500 +#ifdef CONFIG_PPC_E500 #ifndef CONFIG_PPC_E500MC /* Adjust or setup IVORs for e500v1/v2 */ _GLOBAL(__setup_e500_ivors) @@ -942,7 +955,7 @@ _GLOBAL(__setup_ehv_ivors) sync blr #endif /* CONFIG_PPC_E500MC */ -#endif /* CONFIG_E500 */ +#endif /* CONFIG_PPC_E500 */ #ifdef CONFIG_SPE /* diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index 0d073b9fd52c..0b05f2be66b9 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -53,8 +53,8 @@ #define PAGE_SHIFT_8M 23 __HEAD -_ENTRY(_stext); -_ENTRY(_start); +_GLOBAL(_stext); +_GLOBAL(_start); /* MPC8xx * This port was done on an MBX board with an 860. Right now I only diff --git a/arch/powerpc/kernel/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S index 68e5c0a7e99d..519b60695167 100644 --- a/arch/powerpc/kernel/head_book3s_32.S +++ b/arch/powerpc/kernel/head_book3s_32.S @@ -50,16 +50,13 @@ mtspr SPRN_DBAT##n##L,RB __HEAD - .stabs "arch/powerpc/kernel/",N_SO,0,0,0f - .stabs "head_book3s_32.S",N_SO,0,0,0f -0: -_ENTRY(_stext); +_GLOBAL(_stext); /* * _start is defined this way because the XCOFF loader in the OpenFirmware * on the powermac expects the entry point to be a procedure descriptor. */ -_ENTRY(_start); +_GLOBAL(_start); /* * These are here for legacy reasons, the kernel used to * need to look like a coff function entry for the pmac @@ -504,14 +501,12 @@ DataLoadTLBMiss: lwz r0,0(r2) /* get linux-style pte */ andc. r1,r1,r0 /* check access & ~permission */ bne- DataAddressInvalid /* return if access not permitted */ - /* - * NOTE! We are assuming this is not an SMP system, otherwise - * we would need to update the pte atomically with lwarx/stwcx. - */ /* Convert linux-style PTE to low word of PPC-style PTE */ rlwinm r1,r0,32-9,30,30 /* _PAGE_RW -> PP msb */ rlwimi r0,r0,32-1,30,30 /* _PAGE_USER -> PP msb */ + rlwimi r1,r0,32-3,24,24 /* _PAGE_RW -> _PAGE_DIRTY */ rlwimi r0,r0,32-1,31,31 /* _PAGE_USER -> PP lsb */ + xori r1,r1,_PAGE_DIRTY /* clear dirty when not rw */ ori r1,r1,0xe04 /* clear out reserved bits */ andc r1,r0,r1 /* PP = user? rw? 1: 3: 0 */ BEGIN_FTR_SECTION @@ -586,10 +581,6 @@ DataStoreTLBMiss: lwz r0,0(r2) /* get linux-style pte */ andc. r1,r1,r0 /* check access & ~permission */ bne- DataAddressInvalid /* return if access not permitted */ - /* - * NOTE! We are assuming this is not an SMP system, otherwise - * we would need to update the pte atomically with lwarx/stwcx. - */ /* Convert linux-style PTE to low word of PPC-style PTE */ rlwimi r0,r0,32-2,31,31 /* _PAGE_USER -> PP lsb */ li r1,0xe06 /* clear out reserved bits & PP msb */ @@ -784,7 +775,7 @@ relocate_kernel: * r3 = dest addr, r4 = source addr, r5 = copy limit, r6 = start offset * on exit, r3, r4, r5 are unchanged, r6 is updated to be >= r5. */ -_ENTRY(copy_and_flush) +_GLOBAL(copy_and_flush) addi r5,r5,-4 addi r6,r6,-4 4: li r0,L1_CACHE_BYTES/4 @@ -931,7 +922,11 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS) _GLOBAL(load_segment_registers) li r0, NUM_USER_SEGMENTS /* load up user segment register values */ mtctr r0 /* for context 0 */ +#ifdef CONFIG_PPC_KUEP + lis r3, SR_NX@h /* Kp = 0, Ks = 0, VSID = 0 */ +#else li r3, 0 /* Kp = 0, Ks = 0, VSID = 0 */ +#endif li r4, 0 3: mtsrin r3, r4 addi r3, r3, 0x111 /* increment VSID */ @@ -1078,7 +1073,7 @@ BEGIN_MMU_FTR_SECTION END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS) blr -_ENTRY(update_bats) +_GLOBAL(update_bats) lis r4, 1f@h ori r4, r4, 1f@l tophys(r4, r4) diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h index ef8d1b1c234e..1cb9d0f7cbf2 100644 --- a/arch/powerpc/kernel/head_booke.h +++ b/arch/powerpc/kernel/head_booke.h @@ -34,7 +34,7 @@ */ #define THREAD_NORMSAVE(offset) (THREAD_NORMSAVES + (offset * 4)) -#ifdef CONFIG_PPC_FSL_BOOK3E +#ifdef CONFIG_PPC_E500 #define BOOKE_CLEAR_BTB(reg) \ START_BTB_FLUSH_SECTION \ BTB_FLUSH(reg) \ @@ -87,8 +87,7 @@ END_BTB_FLUSH_SECTION stw r10, 8(r1) li r10, \trapno stw r10,_TRAP(r1) - SAVE_4GPRS(3, r1) - SAVE_2GPRS(7, r1) + SAVE_GPRS(3, 8, r1) SAVE_NVGPRS(r1) stw r2,GPR2(r1) stw r12,_NIP(r1) @@ -104,7 +103,7 @@ END_BTB_FLUSH_SECTION .endm .macro prepare_transfer_to_handler -#ifdef CONFIG_E500 +#ifdef CONFIG_PPC_E500 andi. r12,r9,MSR_PR bne 777f bl prepare_transfer_to_handler @@ -243,7 +242,7 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_EMB_HV) .macro SAVE_MMU_REGS -#ifdef CONFIG_PPC_BOOK3E_MMU +#ifdef CONFIG_PPC_E500 mfspr r0,SPRN_MAS0 stw r0,MAS0(r1) mfspr r0,SPRN_MAS1 @@ -258,7 +257,7 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_EMB_HV) mfspr r0,SPRN_MAS7 stw r0,MAS7(r1) #endif /* CONFIG_PHYS_64BIT */ -#endif /* CONFIG_PPC_BOOK3E_MMU */ +#endif /* CONFIG_PPC_E500 */ #ifdef CONFIG_44x mfspr r0,SPRN_MMUCR stw r0,MMUCR(r1) diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index 91a3be14808b..8db1a15d7acb 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -15,6 +15,7 @@ #include <linux/kernel.h> #include <linux/sched.h> #include <linux/smp.h> +#include <linux/spinlock.h> #include <linux/debugfs.h> #include <linux/init.h> @@ -129,7 +130,14 @@ struct breakpoint { bool ptrace_bp; }; +/* + * While kernel/events/hw_breakpoint.c does its own synchronization, we cannot + * rely on it safely synchronizing internals here; however, we can rely on it + * not requesting more breakpoints than available. + */ +static DEFINE_SPINLOCK(cpu_bps_lock); static DEFINE_PER_CPU(struct breakpoint *, cpu_bps[HBP_NUM_MAX]); +static DEFINE_SPINLOCK(task_bps_lock); static LIST_HEAD(task_bps); static struct breakpoint *alloc_breakpoint(struct perf_event *bp) @@ -174,7 +182,9 @@ static int task_bps_add(struct perf_event *bp) if (IS_ERR(tmp)) return PTR_ERR(tmp); + spin_lock(&task_bps_lock); list_add(&tmp->list, &task_bps); + spin_unlock(&task_bps_lock); return 0; } @@ -182,6 +192,7 @@ static void task_bps_remove(struct perf_event *bp) { struct list_head *pos, *q; + spin_lock(&task_bps_lock); list_for_each_safe(pos, q, &task_bps) { struct breakpoint *tmp = list_entry(pos, struct breakpoint, list); @@ -191,6 +202,7 @@ static void task_bps_remove(struct perf_event *bp) break; } } + spin_unlock(&task_bps_lock); } /* @@ -200,12 +212,17 @@ static void task_bps_remove(struct perf_event *bp) static bool all_task_bps_check(struct perf_event *bp) { struct breakpoint *tmp; + bool ret = false; + spin_lock(&task_bps_lock); list_for_each_entry(tmp, &task_bps, list) { - if (!can_co_exist(tmp, bp)) - return true; + if (!can_co_exist(tmp, bp)) { + ret = true; + break; + } } - return false; + spin_unlock(&task_bps_lock); + return ret; } /* @@ -215,13 +232,18 @@ static bool all_task_bps_check(struct perf_event *bp) static bool same_task_bps_check(struct perf_event *bp) { struct breakpoint *tmp; + bool ret = false; + spin_lock(&task_bps_lock); list_for_each_entry(tmp, &task_bps, list) { if (tmp->bp->hw.target == bp->hw.target && - !can_co_exist(tmp, bp)) - return true; + !can_co_exist(tmp, bp)) { + ret = true; + break; + } } - return false; + spin_unlock(&task_bps_lock); + return ret; } static int cpu_bps_add(struct perf_event *bp) @@ -234,6 +256,7 @@ static int cpu_bps_add(struct perf_event *bp) if (IS_ERR(tmp)) return PTR_ERR(tmp); + spin_lock(&cpu_bps_lock); cpu_bp = per_cpu_ptr(cpu_bps, bp->cpu); for (i = 0; i < nr_wp_slots(); i++) { if (!cpu_bp[i]) { @@ -241,6 +264,7 @@ static int cpu_bps_add(struct perf_event *bp) break; } } + spin_unlock(&cpu_bps_lock); return 0; } @@ -249,6 +273,7 @@ static void cpu_bps_remove(struct perf_event *bp) struct breakpoint **cpu_bp; int i = 0; + spin_lock(&cpu_bps_lock); cpu_bp = per_cpu_ptr(cpu_bps, bp->cpu); for (i = 0; i < nr_wp_slots(); i++) { if (!cpu_bp[i]) @@ -260,19 +285,25 @@ static void cpu_bps_remove(struct perf_event *bp) break; } } + spin_unlock(&cpu_bps_lock); } static bool cpu_bps_check(int cpu, struct perf_event *bp) { struct breakpoint **cpu_bp; + bool ret = false; int i; + spin_lock(&cpu_bps_lock); cpu_bp = per_cpu_ptr(cpu_bps, cpu); for (i = 0; i < nr_wp_slots(); i++) { - if (cpu_bp[i] && !can_co_exist(cpu_bp[i], bp)) - return true; + if (cpu_bp[i] && !can_co_exist(cpu_bp[i], bp)) { + ret = true; + break; + } } - return false; + spin_unlock(&cpu_bps_lock); + return ret; } static bool all_cpu_bps_check(struct perf_event *bp) @@ -286,10 +317,6 @@ static bool all_cpu_bps_check(struct perf_event *bp) return false; } -/* - * We don't use any locks to serialize accesses to cpu_bps or task_bps - * because are already inside nr_bp_mutex. - */ int arch_reserve_bp_slot(struct perf_event *bp) { int ret; @@ -523,7 +550,7 @@ static void larx_stcx_err(struct perf_event *bp, struct arch_hw_breakpoint *info static bool stepping_handler(struct pt_regs *regs, struct perf_event **bp, struct arch_hw_breakpoint **info, int *hit, - struct ppc_inst instr) + ppc_inst_t instr) { int i; int stepped; @@ -616,7 +643,7 @@ int hw_breakpoint_handler(struct die_args *args) int hit[HBP_NUM_MAX] = {0}; int nr_hit = 0; bool ptrace_bp = false; - struct ppc_inst instr = ppc_inst(0); + ppc_inst_t instr = ppc_inst(0); int type = 0; int size = 0; unsigned long ea; diff --git a/arch/powerpc/kernel/hw_breakpoint_constraints.c b/arch/powerpc/kernel/hw_breakpoint_constraints.c index 42b967e3d85c..a74623025f3a 100644 --- a/arch/powerpc/kernel/hw_breakpoint_constraints.c +++ b/arch/powerpc/kernel/hw_breakpoint_constraints.c @@ -80,7 +80,7 @@ static bool check_dawrx_constraints(struct pt_regs *regs, int type, * Return true if the event is valid wrt dawr configuration, * including extraneous exception. Otherwise return false. */ -bool wp_check_constraints(struct pt_regs *regs, struct ppc_inst instr, +bool wp_check_constraints(struct pt_regs *regs, ppc_inst_t instr, unsigned long ea, int type, int size, struct arch_hw_breakpoint *info) { @@ -127,7 +127,7 @@ bool wp_check_constraints(struct pt_regs *regs, struct ppc_inst instr, return false; } -void wp_get_instr_detail(struct pt_regs *regs, struct ppc_inst *instr, +void wp_get_instr_detail(struct pt_regs *regs, ppc_inst_t *instr, int *type, int *size, unsigned long *ea) { struct instruction_op op; diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c index 1f835539fda4..77cd4c5a2d63 100644 --- a/arch/powerpc/kernel/idle.c +++ b/arch/powerpc/kernel/idle.c @@ -37,7 +37,7 @@ static int __init powersave_off(char *arg) { ppc_md.power_save = NULL; cpuidle_disable = IDLE_POWERSAVE_OFF; - return 0; + return 1; } __setup("powersave=off", powersave_off); @@ -82,7 +82,7 @@ void power4_idle(void) return; if (cpu_has_feature(CPU_FTR_ALTIVEC)) - asm volatile("DSSALL ; sync" ::: "memory"); + asm volatile(PPC_DSSALL " ; sync" ::: "memory"); power4_idle_nap(); diff --git a/arch/powerpc/kernel/idle_book3e.S b/arch/powerpc/kernel/idle_64e.S index cc008de58b05..0fc680e03dee 100644 --- a/arch/powerpc/kernel/idle_book3e.S +++ b/arch/powerpc/kernel/idle_64e.S @@ -2,7 +2,7 @@ /* * Copyright 2010 IBM Corp, Benjamin Herrenschmidt <benh@kernel.crashing.org> * - * Generic idle routine for Book3E processors + * Generic idle routine for 64 bits e500 processors */ #include <linux/threads.h> @@ -16,8 +16,6 @@ #include <asm/hw_irq.h> /* 64-bit version only for now */ -#ifdef CONFIG_PPC64 - .macro BOOK3E_IDLE name loop _GLOBAL(\name) /* Save LR for later */ @@ -77,7 +75,7 @@ _GLOBAL(\name) .macro BOOK3E_IDLE_LOOP 1: - PPC_WAIT(0) + PPC_WAIT_v203 b 1b .endm @@ -98,6 +96,4 @@ epapr_ev_idle_start: BOOK3E_IDLE epapr_ev_idle EPAPR_EV_IDLE_LOOP -BOOK3E_IDLE book3e_idle BOOK3E_IDLE_LOOP - -#endif /* CONFIG_PPC64 */ +BOOK3E_IDLE e500_idle BOOK3E_IDLE_LOOP diff --git a/arch/powerpc/kernel/idle_6xx.S b/arch/powerpc/kernel/idle_6xx.S index 13cad9297d82..3c097356366b 100644 --- a/arch/powerpc/kernel/idle_6xx.S +++ b/arch/powerpc/kernel/idle_6xx.S @@ -129,7 +129,7 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFCLR(CPU_FTR_NO_DPM) mtspr SPRN_HID0,r4 BEGIN_FTR_SECTION - DSSALL + PPC_DSSALL sync END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) lwz r8,TI_LOCAL_FLAGS(r2) /* set napping bit */ diff --git a/arch/powerpc/kernel/idle_e500.S b/arch/powerpc/kernel/idle_85xx.S index 9e1bc4502c50..9e1bc4502c50 100644 --- a/arch/powerpc/kernel/idle_e500.S +++ b/arch/powerpc/kernel/idle_85xx.S diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c index 835b626cd476..fc6631a80527 100644 --- a/arch/powerpc/kernel/interrupt.c +++ b/arch/powerpc/kernel/interrupt.c @@ -5,7 +5,6 @@ #include <linux/compat.h> #include <linux/sched/debug.h> /* for show_regs */ -#include <asm/asm-prototypes.h> #include <asm/kup.h> #include <asm/cputime.h> #include <asm/hw_irq.h> @@ -25,8 +24,6 @@ unsigned long global_dbcr0[NR_CPUS]; #endif -typedef long (*syscall_fn)(long, long, long, long, long, long); - #ifdef CONFIG_PPC_BOOK3S_64 DEFINE_STATIC_KEY_FALSE(interrupt_exit_not_reentrant); static inline bool exit_must_hard_disable(void) @@ -74,165 +71,6 @@ static notrace __always_inline bool prep_irq_for_enabled_exit(bool restartable) return true; } -/* Has to run notrace because it is entered not completely "reconciled" */ -notrace long system_call_exception(long r3, long r4, long r5, - long r6, long r7, long r8, - unsigned long r0, struct pt_regs *regs) -{ - syscall_fn f; - - kuep_lock(); - - regs->orig_gpr3 = r3; - - if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) - BUG_ON(irq_soft_mask_return() != IRQS_ALL_DISABLED); - - trace_hardirqs_off(); /* finish reconciling */ - - CT_WARN_ON(ct_state() == CONTEXT_KERNEL); - user_exit_irqoff(); - - BUG_ON(regs_is_unrecoverable(regs)); - BUG_ON(!(regs->msr & MSR_PR)); - BUG_ON(arch_irq_disabled_regs(regs)); - -#ifdef CONFIG_PPC_PKEY - if (mmu_has_feature(MMU_FTR_PKEY)) { - unsigned long amr, iamr; - bool flush_needed = false; - /* - * When entering from userspace we mostly have the AMR/IAMR - * different from kernel default values. Hence don't compare. - */ - amr = mfspr(SPRN_AMR); - iamr = mfspr(SPRN_IAMR); - regs->amr = amr; - regs->iamr = iamr; - if (mmu_has_feature(MMU_FTR_BOOK3S_KUAP)) { - mtspr(SPRN_AMR, AMR_KUAP_BLOCKED); - flush_needed = true; - } - if (mmu_has_feature(MMU_FTR_BOOK3S_KUEP)) { - mtspr(SPRN_IAMR, AMR_KUEP_BLOCKED); - flush_needed = true; - } - if (flush_needed) - isync(); - } else -#endif - kuap_assert_locked(); - - booke_restore_dbcr0(); - - account_cpu_user_entry(); - - account_stolen_time(); - - /* - * This is not required for the syscall exit path, but makes the - * stack frame look nicer. If this was initialised in the first stack - * frame, or if the unwinder was taught the first stack frame always - * returns to user with IRQS_ENABLED, this store could be avoided! - */ - irq_soft_mask_regs_set_state(regs, IRQS_ENABLED); - - /* - * If system call is called with TM active, set _TIF_RESTOREALL to - * prevent RFSCV being used to return to userspace, because POWER9 - * TM implementation has problems with this instruction returning to - * transactional state. Final register values are not relevant because - * the transaction will be aborted upon return anyway. Or in the case - * of unsupported_scv SIGILL fault, the return state does not much - * matter because it's an edge case. - */ - if (IS_ENABLED(CONFIG_PPC_TRANSACTIONAL_MEM) && - unlikely(MSR_TM_TRANSACTIONAL(regs->msr))) - current_thread_info()->flags |= _TIF_RESTOREALL; - - /* - * If the system call was made with a transaction active, doom it and - * return without performing the system call. Unless it was an - * unsupported scv vector, in which case it's treated like an illegal - * instruction. - */ -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM - if (unlikely(MSR_TM_TRANSACTIONAL(regs->msr)) && - !trap_is_unsupported_scv(regs)) { - /* Enable TM in the kernel, and disable EE (for scv) */ - hard_irq_disable(); - mtmsr(mfmsr() | MSR_TM); - - /* tabort, this dooms the transaction, nothing else */ - asm volatile(".long 0x7c00071d | ((%0) << 16)" - :: "r"(TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT)); - - /* - * Userspace will never see the return value. Execution will - * resume after the tbegin. of the aborted transaction with the - * checkpointed register state. A context switch could occur - * or signal delivered to the process before resuming the - * doomed transaction context, but that should all be handled - * as expected. - */ - return -ENOSYS; - } -#endif // CONFIG_PPC_TRANSACTIONAL_MEM - - local_irq_enable(); - - if (unlikely(current_thread_info()->flags & _TIF_SYSCALL_DOTRACE)) { - if (unlikely(trap_is_unsupported_scv(regs))) { - /* Unsupported scv vector */ - _exception(SIGILL, regs, ILL_ILLOPC, regs->nip); - return regs->gpr[3]; - } - /* - * We use the return value of do_syscall_trace_enter() as the - * syscall number. If the syscall was rejected for any reason - * do_syscall_trace_enter() returns an invalid syscall number - * and the test against NR_syscalls will fail and the return - * value to be used is in regs->gpr[3]. - */ - r0 = do_syscall_trace_enter(regs); - if (unlikely(r0 >= NR_syscalls)) - return regs->gpr[3]; - r3 = regs->gpr[3]; - r4 = regs->gpr[4]; - r5 = regs->gpr[5]; - r6 = regs->gpr[6]; - r7 = regs->gpr[7]; - r8 = regs->gpr[8]; - - } else if (unlikely(r0 >= NR_syscalls)) { - if (unlikely(trap_is_unsupported_scv(regs))) { - /* Unsupported scv vector */ - _exception(SIGILL, regs, ILL_ILLOPC, regs->nip); - return regs->gpr[3]; - } - return -ENOSYS; - } - - /* May be faster to do array_index_nospec? */ - barrier_nospec(); - - if (unlikely(is_compat_task())) { - f = (void *)compat_sys_call_table[r0]; - - r3 &= 0x00000000ffffffffULL; - r4 &= 0x00000000ffffffffULL; - r5 &= 0x00000000ffffffffULL; - r6 &= 0x00000000ffffffffULL; - r7 &= 0x00000000ffffffffULL; - r8 &= 0x00000000ffffffffULL; - - } else { - f = (void *)sys_call_table[r0]; - } - - return f(r3, r4, r5, r6, r7, r8); -} - static notrace void booke_load_dbcr0(void) { #ifdef CONFIG_PPC_ADV_DEBUG_REGS @@ -343,7 +181,7 @@ interrupt_exit_user_prepare_main(unsigned long ret, struct pt_regs *regs) unsigned long ti_flags; again: - ti_flags = READ_ONCE(current_thread_info()->flags); + ti_flags = read_thread_flags(); while (unlikely(ti_flags & (_TIF_USER_WORK_MASK & ~_TIF_RESTORE_TM))) { local_irq_enable(); if (ti_flags & _TIF_NEED_RESCHED) { @@ -359,7 +197,7 @@ again: do_notify_resume(regs, ti_flags); } local_irq_disable(); - ti_flags = READ_ONCE(current_thread_info()->flags); + ti_flags = read_thread_flags(); } if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && IS_ENABLED(CONFIG_PPC_FPU)) { @@ -406,7 +244,6 @@ again: /* Restore user access locks last */ kuap_user_restore(regs); - kuep_unlock(); return ret; } @@ -437,7 +274,7 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3, /* Check whether the syscall is issued inside a restartable sequence */ rseq_syscall(regs); - ti_flags = current_thread_info()->flags; + ti_flags = read_thread_flags(); if (unlikely(r3 >= (unsigned long)-MAX_ERRNO) && is_not_scv) { if (likely(!(ti_flags & (_TIF_NOERROR | _TIF_RESTOREALL)))) { @@ -532,16 +369,23 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs) unsigned long flags; unsigned long ret = 0; unsigned long kuap; - bool stack_store = current_thread_info()->flags & - _TIF_EMULATE_STACK_STORE; + bool stack_store = read_thread_flags() & _TIF_EMULATE_STACK_STORE; if (regs_is_unrecoverable(regs)) unrecoverable_exception(regs); /* - * CT_WARN_ON comes here via program_check_exception, - * so avoid recursion. + * CT_WARN_ON comes here via program_check_exception, so avoid + * recursion. + * + * Skip the assertion on PMIs on 64e to work around a problem caused + * by NMI PMIs incorrectly taking this interrupt return path, it's + * possible for this to hit after interrupt exit to user switches + * context to user. See also the comment in the performance monitor + * handler in exceptions-64e.S */ - if (TRAP(regs) != INTERRUPT_PROGRAM) + if (!IS_ENABLED(CONFIG_PPC_BOOK3E_64) && + TRAP(regs) != INTERRUPT_PROGRAM && + TRAP(regs) != INTERRUPT_PERFMON) CT_WARN_ON(ct_state() == CONTEXT_USER); kuap = kuap_get_and_assert_locked(); @@ -554,7 +398,7 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs) again: if (IS_ENABLED(CONFIG_PREEMPT)) { /* Return to preemptible kernel context */ - if (unlikely(current_thread_info()->flags & _TIF_NEED_RESCHED)) { + if (unlikely(read_thread_flags() & _TIF_NEED_RESCHED)) { if (preempt_count() == 0) preempt_schedule_irq(); } @@ -595,16 +439,6 @@ again: if (unlikely(stack_store)) __hard_EE_RI_disable(); - /* - * Returning to a kernel context with local irqs disabled. - * Here, if EE was enabled in the interrupted context, enable - * it on return as well. A problem exists here where a soft - * masked interrupt may have cleared MSR[EE] and set HARD_DIS - * here, and it will still exist on return to the caller. This - * will be resolved by the masked interrupt firing again. - */ - if (regs->msr & MSR_EE) - local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS; #endif /* CONFIG_PPC64 */ } diff --git a/arch/powerpc/kernel/interrupt_64.S b/arch/powerpc/kernel/interrupt_64.S index ec950b08a8dc..a019ed6fc839 100644 --- a/arch/powerpc/kernel/interrupt_64.S +++ b/arch/powerpc/kernel/interrupt_64.S @@ -13,16 +13,6 @@ #include <asm/ppc_asm.h> #include <asm/ptrace.h> - .section ".toc","aw" -SYS_CALL_TABLE: - .tc sys_call_table[TC],sys_call_table - -#ifdef CONFIG_COMPAT -COMPAT_SYS_CALL_TABLE: - .tc compat_sys_call_table[TC],compat_sys_call_table -#endif - .previous - .align 7 .macro DEBUG_SRR_VALID srr @@ -30,21 +20,25 @@ COMPAT_SYS_CALL_TABLE: .ifc \srr,srr mfspr r11,SPRN_SRR0 ld r12,_NIP(r1) + clrrdi r11,r11,2 + clrrdi r12,r12,2 100: tdne r11,r12 - EMIT_BUG_ENTRY 100b,__FILE__,__LINE__,(BUGFLAG_WARNING | BUGFLAG_ONCE) + EMIT_WARN_ENTRY 100b,__FILE__,__LINE__,(BUGFLAG_WARNING | BUGFLAG_ONCE) mfspr r11,SPRN_SRR1 ld r12,_MSR(r1) 100: tdne r11,r12 - EMIT_BUG_ENTRY 100b,__FILE__,__LINE__,(BUGFLAG_WARNING | BUGFLAG_ONCE) + EMIT_WARN_ENTRY 100b,__FILE__,__LINE__,(BUGFLAG_WARNING | BUGFLAG_ONCE) .else mfspr r11,SPRN_HSRR0 ld r12,_NIP(r1) + clrrdi r11,r11,2 + clrrdi r12,r12,2 100: tdne r11,r12 - EMIT_BUG_ENTRY 100b,__FILE__,__LINE__,(BUGFLAG_WARNING | BUGFLAG_ONCE) + EMIT_WARN_ENTRY 100b,__FILE__,__LINE__,(BUGFLAG_WARNING | BUGFLAG_ONCE) mfspr r11,SPRN_HSRR1 ld r12,_MSR(r1) 100: tdne r11,r12 - EMIT_BUG_ENTRY 100b,__FILE__,__LINE__,(BUGFLAG_WARNING | BUGFLAG_ONCE) + EMIT_WARN_ENTRY 100b,__FILE__,__LINE__,(BUGFLAG_WARNING | BUGFLAG_ONCE) .endif #endif .endm @@ -63,16 +57,11 @@ _ASM_NOKPROBE_SYMBOL(system_call_vectored_\name) std r0,GPR0(r1) std r10,GPR1(r1) std r2,GPR2(r1) - ld r2,PACATOC(r13) + LOAD_PACA_TOC() mfcr r12 li r11,0 - /* Can we avoid saving r3-r8 in common case? */ - std r3,GPR3(r1) - std r4,GPR4(r1) - std r5,GPR5(r1) - std r6,GPR6(r1) - std r7,GPR7(r1) - std r8,GPR8(r1) + /* Save syscall parameters in r3-r8 */ + SAVE_GPRS(3, 8, r1) /* Zero r9-r12, this should only be required when restoring all GPRs */ std r11,GPR9(r1) std r11,GPR10(r1) @@ -87,9 +76,12 @@ _ASM_NOKPROBE_SYMBOL(system_call_vectored_\name) li r11,\trapnr std r11,_TRAP(r1) std r12,_CCR(r1) - addi r10,r1,STACK_FRAME_OVERHEAD - ld r11,exception_marker@toc(r2) - std r11,-16(r10) /* "regshere" marker */ + std r3,ORIG_GPR3(r1) + /* Calling convention has r3 = regs, r4 = orig r0 */ + addi r3,r1,STACK_FRAME_OVERHEAD + mr r4,r0 + LOAD_REG_IMMEDIATE(r11, STACK_FRAME_REGS_MARKER) + std r11,-16(r3) /* "regshere" marker */ BEGIN_FTR_SECTION HMT_MEDIUM @@ -104,8 +96,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) * but this is the best we can do. */ - /* Calling convention has r9 = orig r0, r10 = regs */ - mr r9,r0 bl system_call_exception .Lsyscall_vectored_\name\()_exit: @@ -144,17 +134,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) /* Could zero these as per ABI, but we may consider a stricter ABI * which preserves these if libc implementations can benefit, so * restore them for now until further measurement is done. */ - ld r0,GPR0(r1) - ld r4,GPR4(r1) - ld r5,GPR5(r1) - ld r6,GPR6(r1) - ld r7,GPR7(r1) - ld r8,GPR8(r1) + REST_GPR(0, r1) + REST_GPRS(4, 8, r1) /* Zero volatile regs that may contain sensitive kernel data */ - li r9,0 - li r10,0 - li r11,0 - li r12,0 + ZEROIZE_GPRS(9, 12) mtspr SPRN_XER,r0 /* @@ -162,10 +145,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) * The value of AMR only matters while we're in the kernel. */ mtcr r2 - ld r2,GPR2(r1) - ld r3,GPR3(r1) - ld r13,GPR13(r1) - ld r1,GPR1(r1) + REST_GPRS(2, 3, r1) + REST_GPR(13, r1) + REST_GPR(1, r1) RFSCV_TO_USER b . /* prevent speculative execution */ @@ -178,14 +160,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) ld r5,_XER(r1) REST_NVGPRS(r1) - ld r0,GPR0(r1) + REST_GPR(0, r1) mtcr r2 mtctr r3 mtlr r4 mtspr SPRN_XER,r5 - REST_10GPRS(2, r1) - REST_2GPRS(12, r1) - ld r1,GPR1(r1) + REST_GPRS(2, 13, r1) + REST_GPR(1, r1) RFI_TO_USER .Lsyscall_vectored_\name\()_rst_end: @@ -193,7 +174,7 @@ syscall_vectored_\name\()_restart: _ASM_NOKPROBE_SYMBOL(syscall_vectored_\name\()_restart) GET_PACA(r13) ld r1,PACA_EXIT_SAVE_R1(r13) - ld r2,PACATOC(r13) + LOAD_PACA_TOC() ld r3,RESULT(r1) addi r4,r1,STACK_FRAME_OVERHEAD li r11,IRQS_ALL_DISABLED @@ -217,16 +198,6 @@ system_call_vectored common 0x3000 */ system_call_vectored sigill 0x7ff0 - -/* - * Entered via kernel return set up by kernel/sstep.c, must match entry regs - */ - .globl system_call_vectored_emulate -system_call_vectored_emulate: -_ASM_NOKPROBE_SYMBOL(system_call_vectored_emulate) - li r10,IRQS_ALL_DISABLED - stb r10,PACAIRQSOFTMASK(r13) - b system_call_vectored_common #endif /* CONFIG_PPC_BOOK3S */ .balign IFETCH_ALIGN_BYTES @@ -248,21 +219,16 @@ _ASM_NOKPROBE_SYMBOL(system_call_common) std r0,GPR0(r1) std r10,GPR1(r1) std r2,GPR2(r1) -#ifdef CONFIG_PPC_FSL_BOOK3E +#ifdef CONFIG_PPC_E500 START_BTB_FLUSH_SECTION BTB_FLUSH(r10) END_BTB_FLUSH_SECTION #endif - ld r2,PACATOC(r13) + LOAD_PACA_TOC() mfcr r12 li r11,0 - /* Can we avoid saving r3-r8 in common case? */ - std r3,GPR3(r1) - std r4,GPR4(r1) - std r5,GPR5(r1) - std r6,GPR6(r1) - std r7,GPR7(r1) - std r8,GPR8(r1) + /* Save syscall parameters in r3-r8 */ + SAVE_GPRS(3, 8, r1) /* Zero r9-r12, this should only be required when restoring all GPRs */ std r11,GPR9(r1) std r11,GPR10(r1) @@ -283,9 +249,12 @@ END_BTB_FLUSH_SECTION std r10,_LINK(r1) std r11,_TRAP(r1) std r12,_CCR(r1) - addi r10,r1,STACK_FRAME_OVERHEAD - ld r11,exception_marker@toc(r2) - std r11,-16(r10) /* "regshere" marker */ + std r3,ORIG_GPR3(r1) + /* Calling convention has r3 = regs, r4 = orig r0 */ + addi r3,r1,STACK_FRAME_OVERHEAD + mr r4,r0 + LOAD_REG_IMMEDIATE(r11, STACK_FRAME_REGS_MARKER) + std r11,-16(r3) /* "regshere" marker */ #ifdef CONFIG_PPC_BOOK3S li r11,1 @@ -306,8 +275,6 @@ END_BTB_FLUSH_SECTION wrteei 1 #endif - /* Calling convention has r9 = orig r0, r10 = regs */ - mr r9,r0 bl system_call_exception .Lsyscall_exit: @@ -351,16 +318,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS) cmpdi r3,0 bne .Lsyscall_restore_regs /* Zero volatile regs that may contain sensitive kernel data */ - li r0,0 - li r4,0 - li r5,0 - li r6,0 - li r7,0 - li r8,0 - li r9,0 - li r10,0 - li r11,0 - li r12,0 + ZEROIZE_GPR(0) + ZEROIZE_GPRS(4, 12) mtctr r0 mtspr SPRN_XER,r0 .Lsyscall_restore_regs_cont: @@ -374,10 +333,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) * The value of AMR only matters while we're in the kernel. */ mtcr r2 - ld r2,GPR2(r1) - ld r3,GPR3(r1) - ld r13,GPR13(r1) - ld r1,GPR1(r1) + REST_GPRS(2, 3, r1) + REST_GPR(13, r1) + REST_GPR(1, r1) RFI_TO_USER b . /* prevent speculative execution */ @@ -387,9 +345,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) REST_NVGPRS(r1) mtctr r3 mtspr SPRN_XER,r4 - ld r0,GPR0(r1) - REST_8GPRS(4, r1) - ld r12,GPR12(r1) + REST_GPR(0, r1) + REST_GPRS(4, 12, r1) b .Lsyscall_restore_regs_cont .Lsyscall_rst_end: @@ -398,7 +355,7 @@ syscall_restart: _ASM_NOKPROBE_SYMBOL(syscall_restart) GET_PACA(r13) ld r1,PACA_EXIT_SAVE_R1(r13) - ld r2,PACATOC(r13) + LOAD_PACA_TOC() ld r3,RESULT(r1) addi r4,r1,STACK_FRAME_OVERHEAD li r11,IRQS_ALL_DISABLED @@ -518,17 +475,14 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS) ld r6,_XER(r1) li r0,0 - REST_4GPRS(7, r1) - REST_2GPRS(11, r1) - REST_GPR(13, r1) + REST_GPRS(7, 13, r1) mtcr r3 mtlr r4 mtctr r5 mtspr SPRN_XER,r6 - REST_4GPRS(2, r1) - REST_GPR(6, r1) + REST_GPRS(2, 6, r1) REST_GPR(0, r1) REST_GPR(1, r1) .ifc \srr,srr @@ -548,7 +502,7 @@ interrupt_return_\srr\()_user_restart: _ASM_NOKPROBE_SYMBOL(interrupt_return_\srr\()_user_restart) GET_PACA(r13) ld r1,PACA_EXIT_SAVE_R1(r13) - ld r2,PACATOC(r13) + LOAD_PACA_TOC() addi r3,r1,STACK_FRAME_OVERHEAD li r11,IRQS_ALL_DISABLED stb r11,PACAIRQSOFTMASK(r13) @@ -572,15 +526,63 @@ _ASM_NOKPROBE_SYMBOL(interrupt_return_\srr\()_kernel) ld r11,SOFTE(r1) cmpwi r11,IRQS_ENABLED stb r11,PACAIRQSOFTMASK(r13) - bne 1f + beq .Linterrupt_return_\srr\()_soft_enabled + + /* + * Returning to soft-disabled context. + * Check if a MUST_HARD_MASK interrupt has become pending, in which + * case we need to disable MSR[EE] in the return context. + * + * The MSR[EE] check catches among other things the short incoherency + * in hard_irq_disable() between clearing MSR[EE] and setting + * PACA_IRQ_HARD_DIS. + */ + ld r12,_MSR(r1) + andi. r10,r12,MSR_EE + beq .Lfast_kernel_interrupt_return_\srr\() // EE already disabled + lbz r11,PACAIRQHAPPENED(r13) + andi. r10,r11,PACA_IRQ_MUST_HARD_MASK + bne 1f // HARD_MASK is pending + // No HARD_MASK pending, clear possible HARD_DIS set by interrupt + andi. r11,r11,(~PACA_IRQ_HARD_DIS)@l + stb r11,PACAIRQHAPPENED(r13) + b .Lfast_kernel_interrupt_return_\srr\() + + +1: /* Must clear MSR_EE from _MSR */ +#ifdef CONFIG_PPC_BOOK3S + li r10,0 + /* Clear valid before changing _MSR */ + .ifc \srr,srr + stb r10,PACASRR_VALID(r13) + .else + stb r10,PACAHSRR_VALID(r13) + .endif +#endif + xori r12,r12,MSR_EE + std r12,_MSR(r1) + b .Lfast_kernel_interrupt_return_\srr\() + +.Linterrupt_return_\srr\()_soft_enabled: + /* + * In the soft-enabled case, need to double-check that we have no + * pending interrupts that might have come in before we reached the + * restart section of code, and restart the exit so those can be + * handled. + * + * If there are none, it is be possible that the interrupt still + * has PACA_IRQ_HARD_DIS set, which needs to be cleared for the + * interrupted context. This clear will not clobber a new pending + * interrupt coming in, because we're in the restart section, so + * such would return to the restart location. + */ #ifdef CONFIG_PPC_BOOK3S lbz r11,PACAIRQHAPPENED(r13) andi. r11,r11,(~PACA_IRQ_HARD_DIS)@l bne- interrupt_return_\srr\()_kernel_restart #endif li r11,0 - stb r11,PACAIRQHAPPENED(r13) # clear out possible HARD_DIS -1: + stb r11,PACAIRQHAPPENED(r13) // clear the possible HARD_DIS .Lfast_kernel_interrupt_return_\srr\(): cmpdi cr1,r3,0 @@ -625,20 +627,19 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS) ld r6,_CCR(r1) li r0,0 - REST_4GPRS(7, r1) - REST_2GPRS(11, r1) + REST_GPRS(7, 12, r1) mtlr r3 mtctr r4 mtspr SPRN_XER,r5 /* - * Leaving a stale exception_marker on the stack can confuse + * Leaving a stale STACK_FRAME_REGS_MARKER on the stack can confuse * the reliable stack unwinder later on. Clear it. */ std r0,STACK_FRAME_OVERHEAD-16(r1) - REST_4GPRS(2, r1) + REST_GPRS(2, 5, r1) bne- cr1,1f /* emulate stack store */ mtcr r6 @@ -682,7 +683,7 @@ interrupt_return_\srr\()_kernel_restart: _ASM_NOKPROBE_SYMBOL(interrupt_return_\srr\()_kernel_restart) GET_PACA(r13) ld r1,PACA_EXIT_SAVE_R1(r13) - ld r2,PACATOC(r13) + LOAD_PACA_TOC() addi r3,r1,STACK_FRAME_OVERHEAD li r11,IRQS_ALL_DISABLED stb r11,PACAIRQSOFTMASK(r13) @@ -703,7 +704,7 @@ interrupt_return_macro hsrr .globl __end_soft_masked __end_soft_masked: -DEFINE_FIXED_SYMBOL(__end_soft_masked) +DEFINE_FIXED_SYMBOL(__end_soft_masked, text) #endif /* CONFIG_PPC_BOOK3S */ #ifdef CONFIG_PPC_BOOK3S @@ -725,7 +726,7 @@ _GLOBAL(ret_from_kernel_thread) REST_NVGPRS(r1) mtctr r14 mr r3,r15 -#ifdef PPC64_ELF_ABI_v2 +#ifdef CONFIG_PPC64_ELF_ABI_V2 mr r12,r14 #endif bctrl diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 07093b7cdcb9..caebe1431596 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -27,7 +27,6 @@ #include <linux/sched.h> #include <linux/debugfs.h> #include <asm/io.h> -#include <asm/prom.h> #include <asm/iommu.h> #include <asm/pci-bridge.h> #include <asm/machdep.h> @@ -776,6 +775,11 @@ bool iommu_table_in_use(struct iommu_table *tbl) /* ignore reserved bit0 */ if (tbl->it_offset == 0) start = 1; + + /* Simple case with no reserved MMIO32 region */ + if (!tbl->it_reserved_start && !tbl->it_reserved_end) + return find_next_bit(tbl->it_map, tbl->it_size, start) != tbl->it_size; + end = tbl->it_reserved_start - tbl->it_offset; if (find_next_bit(tbl->it_map, end, start) != end) return true; @@ -1065,7 +1069,7 @@ extern long iommu_tce_xchg_no_kill(struct mm_struct *mm, long ret; unsigned long size = 0; - ret = tbl->it_ops->xchg_no_kill(tbl, entry, hpa, direction, false); + ret = tbl->it_ops->xchg_no_kill(tbl, entry, hpa, direction); if (!ret && ((*direction == DMA_FROM_DEVICE) || (*direction == DMA_BIDIRECTIONAL)) && !mm_iommu_is_devmem(mm, *hpa, tbl->it_page_shift, @@ -1080,7 +1084,7 @@ void iommu_tce_kill(struct iommu_table *tbl, unsigned long entry, unsigned long pages) { if (tbl->it_ops->tce_kill) - tbl->it_ops->tce_kill(tbl, entry, pages, false); + tbl->it_ops->tce_kill(tbl, entry, pages); } EXPORT_SYMBOL_GPL(iommu_tce_kill); diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index c4f1d6b7d992..9ede61a5a469 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -52,28 +52,21 @@ #include <linux/of_irq.h> #include <linux/vmalloc.h> #include <linux/pgtable.h> +#include <linux/static_call.h> #include <linux/uaccess.h> #include <asm/interrupt.h> #include <asm/io.h> #include <asm/irq.h> #include <asm/cache.h> -#include <asm/prom.h> #include <asm/ptrace.h> #include <asm/machdep.h> #include <asm/udbg.h> #include <asm/smp.h> -#include <asm/livepatch.h> -#include <asm/asm-prototypes.h> #include <asm/hw_irq.h> #include <asm/softirq_stack.h> +#include <asm/ppc_asm.h> -#ifdef CONFIG_PPC64 -#include <asm/paca.h> -#include <asm/firmware.h> -#include <asm/lv1call.h> -#include <asm/dbell.h> -#endif #define CREATE_TRACE_POINTS #include <asm/trace.h> #include <asm/cpu_has_feature.h> @@ -90,488 +83,6 @@ u32 tau_interrupts(unsigned long cpu); #endif #endif /* CONFIG_PPC32 */ -#ifdef CONFIG_PPC64 - -int distribute_irqs = 1; - -static inline notrace unsigned long get_irq_happened(void) -{ - unsigned long happened; - - __asm__ __volatile__("lbz %0,%1(13)" - : "=r" (happened) : "i" (offsetof(struct paca_struct, irq_happened))); - - return happened; -} - -void replay_soft_interrupts(void) -{ - struct pt_regs regs; - - /* - * Be careful here, calling these interrupt handlers can cause - * softirqs to be raised, which they may run when calling irq_exit, - * which will cause local_irq_enable() to be run, which can then - * recurse into this function. Don't keep any state across - * interrupt handler calls which may change underneath us. - * - * We use local_paca rather than get_paca() to avoid all the - * debug_smp_processor_id() business in this low level function. - */ - - ppc_save_regs(®s); - regs.softe = IRQS_ENABLED; - regs.msr |= MSR_EE; - -again: - if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) - WARN_ON_ONCE(mfmsr() & MSR_EE); - - /* - * Force the delivery of pending soft-disabled interrupts on PS3. - * Any HV call will have this side effect. - */ - if (firmware_has_feature(FW_FEATURE_PS3_LV1)) { - u64 tmp, tmp2; - lv1_get_version_info(&tmp, &tmp2); - } - - /* - * Check if an hypervisor Maintenance interrupt happened. - * This is a higher priority interrupt than the others, so - * replay it first. - */ - if (IS_ENABLED(CONFIG_PPC_BOOK3S) && (local_paca->irq_happened & PACA_IRQ_HMI)) { - local_paca->irq_happened &= ~PACA_IRQ_HMI; - regs.trap = INTERRUPT_HMI; - handle_hmi_exception(®s); - if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS)) - hard_irq_disable(); - } - - if (local_paca->irq_happened & PACA_IRQ_DEC) { - local_paca->irq_happened &= ~PACA_IRQ_DEC; - regs.trap = INTERRUPT_DECREMENTER; - timer_interrupt(®s); - if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS)) - hard_irq_disable(); - } - - if (local_paca->irq_happened & PACA_IRQ_EE) { - local_paca->irq_happened &= ~PACA_IRQ_EE; - regs.trap = INTERRUPT_EXTERNAL; - do_IRQ(®s); - if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS)) - hard_irq_disable(); - } - - if (IS_ENABLED(CONFIG_PPC_DOORBELL) && (local_paca->irq_happened & PACA_IRQ_DBELL)) { - local_paca->irq_happened &= ~PACA_IRQ_DBELL; - regs.trap = INTERRUPT_DOORBELL; - doorbell_exception(®s); - if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS)) - hard_irq_disable(); - } - - /* Book3E does not support soft-masking PMI interrupts */ - if (IS_ENABLED(CONFIG_PPC_BOOK3S) && (local_paca->irq_happened & PACA_IRQ_PMI)) { - local_paca->irq_happened &= ~PACA_IRQ_PMI; - regs.trap = INTERRUPT_PERFMON; - performance_monitor_exception(®s); - if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS)) - hard_irq_disable(); - } - - if (local_paca->irq_happened & ~PACA_IRQ_HARD_DIS) { - /* - * We are responding to the next interrupt, so interrupt-off - * latencies should be reset here. - */ - trace_hardirqs_on(); - trace_hardirqs_off(); - goto again; - } -} - -#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_PPC_KUAP) -static inline void replay_soft_interrupts_irqrestore(void) -{ - unsigned long kuap_state = get_kuap(); - - /* - * Check if anything calls local_irq_enable/restore() when KUAP is - * disabled (user access enabled). We handle that case here by saving - * and re-locking AMR but we shouldn't get here in the first place, - * hence the warning. - */ - kuap_assert_locked(); - - if (kuap_state != AMR_KUAP_BLOCKED) - set_kuap(AMR_KUAP_BLOCKED); - - replay_soft_interrupts(); - - if (kuap_state != AMR_KUAP_BLOCKED) - set_kuap(kuap_state); -} -#else -#define replay_soft_interrupts_irqrestore() replay_soft_interrupts() -#endif - -#ifdef CONFIG_CC_HAS_ASM_GOTO -notrace void arch_local_irq_restore(unsigned long mask) -{ - unsigned char irq_happened; - - /* Write the new soft-enabled value if it is a disable */ - if (mask) { - irq_soft_mask_set(mask); - return; - } - - if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) - WARN_ON_ONCE(in_nmi() || in_hardirq()); - - /* - * After the stb, interrupts are unmasked and there are no interrupts - * pending replay. The restart sequence makes this atomic with - * respect to soft-masked interrupts. If this was just a simple code - * sequence, a soft-masked interrupt could become pending right after - * the comparison and before the stb. - * - * This allows interrupts to be unmasked without hard disabling, and - * also without new hard interrupts coming in ahead of pending ones. - */ - asm_volatile_goto( -"1: \n" -" lbz 9,%0(13) \n" -" cmpwi 9,0 \n" -" bne %l[happened] \n" -" stb 9,%1(13) \n" -"2: \n" - RESTART_TABLE(1b, 2b, 1b) - : : "i" (offsetof(struct paca_struct, irq_happened)), - "i" (offsetof(struct paca_struct, irq_soft_mask)) - : "cr0", "r9" - : happened); - - if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) - WARN_ON_ONCE(!(mfmsr() & MSR_EE)); - - return; - -happened: - irq_happened = get_irq_happened(); - if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) - WARN_ON_ONCE(!irq_happened); - - if (irq_happened == PACA_IRQ_HARD_DIS) { - if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) - WARN_ON_ONCE(mfmsr() & MSR_EE); - irq_soft_mask_set(IRQS_ENABLED); - local_paca->irq_happened = 0; - __hard_irq_enable(); - return; - } - - /* Have interrupts to replay, need to hard disable first */ - if (!(irq_happened & PACA_IRQ_HARD_DIS)) { - if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) { - if (!(mfmsr() & MSR_EE)) { - /* - * An interrupt could have come in and cleared - * MSR[EE] and set IRQ_HARD_DIS, so check - * IRQ_HARD_DIS again and warn if it is still - * clear. - */ - irq_happened = get_irq_happened(); - WARN_ON_ONCE(!(irq_happened & PACA_IRQ_HARD_DIS)); - } - } - __hard_irq_disable(); - local_paca->irq_happened |= PACA_IRQ_HARD_DIS; - } else { - if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) { - if (WARN_ON_ONCE(mfmsr() & MSR_EE)) - __hard_irq_disable(); - } - } - - /* - * Disable preempt here, so that the below preempt_enable will - * perform resched if required (a replayed interrupt may set - * need_resched). - */ - preempt_disable(); - irq_soft_mask_set(IRQS_ALL_DISABLED); - trace_hardirqs_off(); - - replay_soft_interrupts_irqrestore(); - local_paca->irq_happened = 0; - - trace_hardirqs_on(); - irq_soft_mask_set(IRQS_ENABLED); - __hard_irq_enable(); - preempt_enable(); -} -#else -notrace void arch_local_irq_restore(unsigned long mask) -{ - unsigned char irq_happened; - - /* Write the new soft-enabled value */ - irq_soft_mask_set(mask); - if (mask) - return; - - if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) - WARN_ON_ONCE(in_nmi() || in_hardirq()); - - /* - * From this point onward, we can take interrupts, preempt, - * etc... unless we got hard-disabled. We check if an event - * happened. If none happened, we know we can just return. - * - * We may have preempted before the check below, in which case - * we are checking the "new" CPU instead of the old one. This - * is only a problem if an event happened on the "old" CPU. - * - * External interrupt events will have caused interrupts to - * be hard-disabled, so there is no problem, we - * cannot have preempted. - */ - irq_happened = get_irq_happened(); - if (!irq_happened) { - if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) - WARN_ON_ONCE(!(mfmsr() & MSR_EE)); - return; - } - - /* We need to hard disable to replay. */ - if (!(irq_happened & PACA_IRQ_HARD_DIS)) { - if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) - WARN_ON_ONCE(!(mfmsr() & MSR_EE)); - __hard_irq_disable(); - local_paca->irq_happened |= PACA_IRQ_HARD_DIS; - } else { - /* - * We should already be hard disabled here. We had bugs - * where that wasn't the case so let's dbl check it and - * warn if we are wrong. Only do that when IRQ tracing - * is enabled as mfmsr() can be costly. - */ - if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) { - if (WARN_ON_ONCE(mfmsr() & MSR_EE)) - __hard_irq_disable(); - } - - if (irq_happened == PACA_IRQ_HARD_DIS) { - local_paca->irq_happened = 0; - __hard_irq_enable(); - return; - } - } - - /* - * Disable preempt here, so that the below preempt_enable will - * perform resched if required (a replayed interrupt may set - * need_resched). - */ - preempt_disable(); - irq_soft_mask_set(IRQS_ALL_DISABLED); - trace_hardirqs_off(); - - replay_soft_interrupts_irqrestore(); - local_paca->irq_happened = 0; - - trace_hardirqs_on(); - irq_soft_mask_set(IRQS_ENABLED); - __hard_irq_enable(); - preempt_enable(); -} -#endif -EXPORT_SYMBOL(arch_local_irq_restore); - -/* - * This is a helper to use when about to go into idle low-power - * when the latter has the side effect of re-enabling interrupts - * (such as calling H_CEDE under pHyp). - * - * You call this function with interrupts soft-disabled (this is - * already the case when ppc_md.power_save is called). The function - * will return whether to enter power save or just return. - * - * In the former case, it will have notified lockdep of interrupts - * being re-enabled and generally sanitized the lazy irq state, - * and in the latter case it will leave with interrupts hard - * disabled and marked as such, so the local_irq_enable() call - * in arch_cpu_idle() will properly re-enable everything. - */ -bool prep_irq_for_idle(void) -{ - /* - * First we need to hard disable to ensure no interrupt - * occurs before we effectively enter the low power state - */ - __hard_irq_disable(); - local_paca->irq_happened |= PACA_IRQ_HARD_DIS; - - /* - * If anything happened while we were soft-disabled, - * we return now and do not enter the low power state. - */ - if (lazy_irq_pending()) - return false; - - /* Tell lockdep we are about to re-enable */ - trace_hardirqs_on(); - - /* - * Mark interrupts as soft-enabled and clear the - * PACA_IRQ_HARD_DIS from the pending mask since we - * are about to hard enable as well as a side effect - * of entering the low power state. - */ - local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS; - irq_soft_mask_set(IRQS_ENABLED); - - /* Tell the caller to enter the low power state */ - return true; -} - -#ifdef CONFIG_PPC_BOOK3S -/* - * This is for idle sequences that return with IRQs off, but the - * idle state itself wakes on interrupt. Tell the irq tracer that - * IRQs are enabled for the duration of idle so it does not get long - * off times. Must be paired with fini_irq_for_idle_irqsoff. - */ -bool prep_irq_for_idle_irqsoff(void) -{ - WARN_ON(!irqs_disabled()); - - /* - * First we need to hard disable to ensure no interrupt - * occurs before we effectively enter the low power state - */ - __hard_irq_disable(); - local_paca->irq_happened |= PACA_IRQ_HARD_DIS; - - /* - * If anything happened while we were soft-disabled, - * we return now and do not enter the low power state. - */ - if (lazy_irq_pending()) - return false; - - /* Tell lockdep we are about to re-enable */ - trace_hardirqs_on(); - - return true; -} - -/* - * Take the SRR1 wakeup reason, index into this table to find the - * appropriate irq_happened bit. - * - * Sytem reset exceptions taken in idle state also come through here, - * but they are NMI interrupts so do not need to wait for IRQs to be - * restored, and should be taken as early as practical. These are marked - * with 0xff in the table. The Power ISA specifies 0100b as the system - * reset interrupt reason. - */ -#define IRQ_SYSTEM_RESET 0xff - -static const u8 srr1_to_lazyirq[0x10] = { - 0, 0, 0, - PACA_IRQ_DBELL, - IRQ_SYSTEM_RESET, - PACA_IRQ_DBELL, - PACA_IRQ_DEC, - 0, - PACA_IRQ_EE, - PACA_IRQ_EE, - PACA_IRQ_HMI, - 0, 0, 0, 0, 0 }; - -void replay_system_reset(void) -{ - struct pt_regs regs; - - ppc_save_regs(®s); - regs.trap = 0x100; - get_paca()->in_nmi = 1; - system_reset_exception(®s); - get_paca()->in_nmi = 0; -} -EXPORT_SYMBOL_GPL(replay_system_reset); - -void irq_set_pending_from_srr1(unsigned long srr1) -{ - unsigned int idx = (srr1 & SRR1_WAKEMASK_P8) >> 18; - u8 reason = srr1_to_lazyirq[idx]; - - /* - * Take the system reset now, which is immediately after registers - * are restored from idle. It's an NMI, so interrupts need not be - * re-enabled before it is taken. - */ - if (unlikely(reason == IRQ_SYSTEM_RESET)) { - replay_system_reset(); - return; - } - - if (reason == PACA_IRQ_DBELL) { - /* - * When doorbell triggers a system reset wakeup, the message - * is not cleared, so if the doorbell interrupt is replayed - * and the IPI handled, the doorbell interrupt would still - * fire when EE is enabled. - * - * To avoid taking the superfluous doorbell interrupt, - * execute a msgclr here before the interrupt is replayed. - */ - ppc_msgclr(PPC_DBELL_MSGTYPE); - } - - /* - * The 0 index (SRR1[42:45]=b0000) must always evaluate to 0, - * so this can be called unconditionally with the SRR1 wake - * reason as returned by the idle code, which uses 0 to mean no - * interrupt. - * - * If a future CPU was to designate this as an interrupt reason, - * then a new index for no interrupt must be assigned. - */ - local_paca->irq_happened |= reason; -} -#endif /* CONFIG_PPC_BOOK3S */ - -/* - * Force a replay of the external interrupt handler on this CPU. - */ -void force_external_irq_replay(void) -{ - /* - * This must only be called with interrupts soft-disabled, - * the replay will happen when re-enabling. - */ - WARN_ON(!arch_irqs_disabled()); - - /* - * Interrupts must always be hard disabled before irq_happened is - * modified (to prevent lost update in case of interrupt between - * load and store). - */ - __hard_irq_disable(); - local_paca->irq_happened |= PACA_IRQ_HARD_DIS; - - /* Indicate in the PACA that we have an interrupt to replay */ - local_paca->irq_happened |= PACA_IRQ_EE; -} - -#endif /* CONFIG_PPC64 */ - int arch_show_interrupts(struct seq_file *p, int prec) { int j; @@ -674,22 +185,21 @@ u64 arch_irq_stat_cpu(unsigned int cpu) return sum; } -static inline void check_stack_overflow(void) +static inline void check_stack_overflow(unsigned long sp) { - long sp; - if (!IS_ENABLED(CONFIG_DEBUG_STACKOVERFLOW)) return; - sp = current_stack_pointer & (THREAD_SIZE - 1); + sp &= THREAD_SIZE - 1; - /* check for stack overflow: is there less than 2KB free? */ - if (unlikely(sp < 2048)) { + /* check for stack overflow: is there less than 1/4th free? */ + if (unlikely(sp < THREAD_SIZE / 4)) { pr_err("do_IRQ: stack overflow: %ld\n", sp); dump_stack(); } } +#ifdef CONFIG_SOFTIRQ_ON_OWN_STACK static __always_inline void call_do_softirq(const void *sp) { /* Temporarily switch r1 to sp, call __do_softirq() then restore r1. */ @@ -708,44 +218,28 @@ static __always_inline void call_do_softirq(const void *sp) "r11", "r12" ); } +#endif -static __always_inline void call_do_irq(struct pt_regs *regs, void *sp) -{ - register unsigned long r3 asm("r3") = (unsigned long)regs; - - /* Temporarily switch r1 to sp, call __do_irq() then restore r1. */ - asm volatile ( - PPC_STLU " %%r1, %[offset](%[sp]) ;" - "mr %%r1, %[sp] ;" - "bl %[callee] ;" - PPC_LL " %%r1, 0(%%r1) ;" - : // Outputs - "+r" (r3) - : // Inputs - [sp] "b" (sp), [offset] "i" (THREAD_SIZE - STACK_FRAME_OVERHEAD), - [callee] "i" (__do_irq) - : // Clobbers - "lr", "xer", "ctr", "memory", "cr0", "cr1", "cr5", "cr6", - "cr7", "r0", "r4", "r5", "r6", "r7", "r8", "r9", "r10", - "r11", "r12" - ); -} +DEFINE_STATIC_CALL_RET0(ppc_get_irq, *ppc_md.get_irq); -void __do_irq(struct pt_regs *regs) +static void __do_irq(struct pt_regs *regs, unsigned long oldsp) { unsigned int irq; trace_irq_entry(regs); + check_stack_overflow(oldsp); + /* * Query the platform PIC for the interrupt & ack it. * * This will typically lower the interrupt line to the CPU */ - irq = ppc_md.get_irq(); + irq = static_call(ppc_get_irq)(); /* We can hard enable interrupts now to allow perf interrupts */ - may_hard_irq_enable(); + if (should_hard_irq_enable()) + do_hard_irq_enable(); /* And finally process it */ if (unlikely(!irq)) @@ -756,6 +250,29 @@ void __do_irq(struct pt_regs *regs) trace_irq_exit(regs); } +static __always_inline void call_do_irq(struct pt_regs *regs, void *sp) +{ + register unsigned long r3 asm("r3") = (unsigned long)regs; + + /* Temporarily switch r1 to sp, call __do_irq() then restore r1. */ + asm volatile ( + PPC_STLU " %%r1, %[offset](%[sp]) ;" + "mr %%r4, %%r1 ;" + "mr %%r1, %[sp] ;" + "bl %[callee] ;" + PPC_LL " %%r1, 0(%%r1) ;" + : // Outputs + "+r" (r3) + : // Inputs + [sp] "b" (sp), [offset] "i" (THREAD_SIZE - STACK_FRAME_OVERHEAD), + [callee] "i" (__do_irq) + : // Clobbers + "lr", "xer", "ctr", "memory", "cr0", "cr1", "cr5", "cr6", + "cr7", "r0", "r4", "r5", "r6", "r7", "r8", "r9", "r10", + "r11", "r12" + ); +} + void __do_IRQ(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); @@ -766,16 +283,11 @@ void __do_IRQ(struct pt_regs *regs) irqsp = hardirq_ctx[raw_smp_processor_id()]; sirqsp = softirq_ctx[raw_smp_processor_id()]; - check_stack_overflow(); - - /* Already there ? */ - if (unlikely(cursp == irqsp || cursp == sirqsp)) { - __do_irq(regs); - set_irq_regs(old_regs); - return; - } - /* Switch stack and call */ - call_do_irq(regs, irqsp); + /* Already there ? If not switch stack and call */ + if (unlikely(cursp == irqsp || cursp == sirqsp)) + __do_irq(regs, current_stack_pointer); + else + call_do_irq(regs, irqsp); set_irq_regs(old_regs); } @@ -809,9 +321,12 @@ void __init init_IRQ(void) if (ppc_md.init_IRQ) ppc_md.init_IRQ(); + + if (!WARN_ON(!ppc_md.get_irq)) + static_call_update(ppc_get_irq, ppc_md.get_irq); } -#if defined(CONFIG_BOOKE) || defined(CONFIG_40x) +#ifdef CONFIG_BOOKE_OR_40x void *critirq_ctx[NR_CPUS] __read_mostly; void *dbgirq_ctx[NR_CPUS] __read_mostly; void *mcheckirq_ctx[NR_CPUS] __read_mostly; @@ -820,10 +335,12 @@ void *mcheckirq_ctx[NR_CPUS] __read_mostly; void *softirq_ctx[NR_CPUS] __read_mostly; void *hardirq_ctx[NR_CPUS] __read_mostly; +#ifdef CONFIG_SOFTIRQ_ON_OWN_STACK void do_softirq_own_stack(void) { call_do_softirq(softirq_ctx[smp_processor_id()]); } +#endif irq_hw_number_t virq_to_hw(unsigned int virq) { @@ -867,13 +384,3 @@ int irq_choose_cpu(const struct cpumask *mask) return hard_smp_processor_id(); } #endif - -#ifdef CONFIG_PPC64 -static int __init setup_noirqdistrib(char *str) -{ - distribute_irqs = 0; - return 1; -} - -__setup("noirqdistrib", setup_noirqdistrib); -#endif /* CONFIG_PPC64 */ diff --git a/arch/powerpc/kernel/irq_64.c b/arch/powerpc/kernel/irq_64.c new file mode 100644 index 000000000000..eb2b380e52a0 --- /dev/null +++ b/arch/powerpc/kernel/irq_64.c @@ -0,0 +1,495 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Derived from arch/i386/kernel/irq.c + * Copyright (C) 1992 Linus Torvalds + * Adapted from arch/i386 by Gary Thomas + * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org) + * Updated and modified by Cort Dougan <cort@fsmlabs.com> + * Copyright (C) 1996-2001 Cort Dougan + * Adapted for Power Macintosh by Paul Mackerras + * Copyright (C) 1996 Paul Mackerras (paulus@cs.anu.edu.au) + * + * This file contains the code used by various IRQ handling routines: + * asking for different IRQ's should be done through these routines + * instead of just grabbing them. Thus setups with different IRQ numbers + * shouldn't result in any weird surprises, and installing new handlers + * should be easier. + */ + +#undef DEBUG + +#include <linux/export.h> +#include <linux/threads.h> +#include <linux/kernel_stat.h> +#include <linux/signal.h> +#include <linux/sched.h> +#include <linux/ptrace.h> +#include <linux/ioport.h> +#include <linux/interrupt.h> +#include <linux/timex.h> +#include <linux/init.h> +#include <linux/slab.h> +#include <linux/delay.h> +#include <linux/irq.h> +#include <linux/seq_file.h> +#include <linux/cpumask.h> +#include <linux/profile.h> +#include <linux/bitops.h> +#include <linux/list.h> +#include <linux/radix-tree.h> +#include <linux/mutex.h> +#include <linux/pci.h> +#include <linux/debugfs.h> +#include <linux/of.h> +#include <linux/of_irq.h> +#include <linux/vmalloc.h> +#include <linux/pgtable.h> +#include <linux/static_call.h> + +#include <linux/uaccess.h> +#include <asm/interrupt.h> +#include <asm/io.h> +#include <asm/irq.h> +#include <asm/cache.h> +#include <asm/ptrace.h> +#include <asm/machdep.h> +#include <asm/udbg.h> +#include <asm/smp.h> +#include <asm/hw_irq.h> +#include <asm/softirq_stack.h> +#include <asm/ppc_asm.h> + +#include <asm/paca.h> +#include <asm/firmware.h> +#include <asm/lv1call.h> +#include <asm/dbell.h> +#include <asm/trace.h> +#include <asm/cpu_has_feature.h> + +int distribute_irqs = 1; + +static inline void next_interrupt(struct pt_regs *regs) +{ + /* + * Softirq processing can enable/disable irqs, which will leave + * MSR[EE] enabled and the soft mask set to IRQS_DISABLED. Fix + * this up. + */ + if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS)) + hard_irq_disable(); + else + irq_soft_mask_set(IRQS_ALL_DISABLED); + + /* + * We are responding to the next interrupt, so interrupt-off + * latencies should be reset here. + */ + trace_hardirqs_on(); + trace_hardirqs_off(); +} + +static inline bool irq_happened_test_and_clear(u8 irq) +{ + if (local_paca->irq_happened & irq) { + local_paca->irq_happened &= ~irq; + return true; + } + return false; +} + +void replay_soft_interrupts(void) +{ + struct pt_regs regs; + + /* + * Be careful here, calling these interrupt handlers can cause + * softirqs to be raised, which they may run when calling irq_exit, + * which will cause local_irq_enable() to be run, which can then + * recurse into this function. Don't keep any state across + * interrupt handler calls which may change underneath us. + * + * Softirqs can not be disabled over replay to stop this recursion + * because interrupts taken in idle code may require RCU softirq + * to run in the irq RCU tracking context. This is a hard problem + * to fix without changes to the softirq or idle layer. + * + * We use local_paca rather than get_paca() to avoid all the + * debug_smp_processor_id() business in this low level function. + */ + + if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) { + WARN_ON_ONCE(mfmsr() & MSR_EE); + WARN_ON(!(local_paca->irq_happened & PACA_IRQ_HARD_DIS)); + } + + ppc_save_regs(®s); + regs.softe = IRQS_ENABLED; + regs.msr |= MSR_EE; + +again: + /* + * Force the delivery of pending soft-disabled interrupts on PS3. + * Any HV call will have this side effect. + */ + if (firmware_has_feature(FW_FEATURE_PS3_LV1)) { + u64 tmp, tmp2; + lv1_get_version_info(&tmp, &tmp2); + } + + /* + * Check if an hypervisor Maintenance interrupt happened. + * This is a higher priority interrupt than the others, so + * replay it first. + */ + if (IS_ENABLED(CONFIG_PPC_BOOK3S) && + irq_happened_test_and_clear(PACA_IRQ_HMI)) { + regs.trap = INTERRUPT_HMI; + handle_hmi_exception(®s); + next_interrupt(®s); + } + + if (irq_happened_test_and_clear(PACA_IRQ_DEC)) { + regs.trap = INTERRUPT_DECREMENTER; + timer_interrupt(®s); + next_interrupt(®s); + } + + if (irq_happened_test_and_clear(PACA_IRQ_EE)) { + regs.trap = INTERRUPT_EXTERNAL; + do_IRQ(®s); + next_interrupt(®s); + } + + if (IS_ENABLED(CONFIG_PPC_DOORBELL) && + irq_happened_test_and_clear(PACA_IRQ_DBELL)) { + regs.trap = INTERRUPT_DOORBELL; + doorbell_exception(®s); + next_interrupt(®s); + } + + /* Book3E does not support soft-masking PMI interrupts */ + if (IS_ENABLED(CONFIG_PPC_BOOK3S) && + irq_happened_test_and_clear(PACA_IRQ_PMI)) { + regs.trap = INTERRUPT_PERFMON; + performance_monitor_exception(®s); + next_interrupt(®s); + } + + /* + * Softirq processing can enable and disable interrupts, which can + * result in new irqs becoming pending. Must keep looping until we + * have cleared out all pending interrupts. + */ + if (local_paca->irq_happened & ~PACA_IRQ_HARD_DIS) + goto again; +} + +#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_PPC_KUAP) +static inline void replay_soft_interrupts_irqrestore(void) +{ + unsigned long kuap_state = get_kuap(); + + /* + * Check if anything calls local_irq_enable/restore() when KUAP is + * disabled (user access enabled). We handle that case here by saving + * and re-locking AMR but we shouldn't get here in the first place, + * hence the warning. + */ + kuap_assert_locked(); + + if (kuap_state != AMR_KUAP_BLOCKED) + set_kuap(AMR_KUAP_BLOCKED); + + replay_soft_interrupts(); + + if (kuap_state != AMR_KUAP_BLOCKED) + set_kuap(kuap_state); +} +#else +#define replay_soft_interrupts_irqrestore() replay_soft_interrupts() +#endif + +notrace void arch_local_irq_restore(unsigned long mask) +{ + unsigned char irq_happened; + + /* Write the new soft-enabled value if it is a disable */ + if (mask) { + irq_soft_mask_set(mask); + return; + } + + if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) + WARN_ON_ONCE(in_nmi() || in_hardirq()); + + /* + * After the stb, interrupts are unmasked and there are no interrupts + * pending replay. The restart sequence makes this atomic with + * respect to soft-masked interrupts. If this was just a simple code + * sequence, a soft-masked interrupt could become pending right after + * the comparison and before the stb. + * + * This allows interrupts to be unmasked without hard disabling, and + * also without new hard interrupts coming in ahead of pending ones. + */ + asm_volatile_goto( +"1: \n" +" lbz 9,%0(13) \n" +" cmpwi 9,0 \n" +" bne %l[happened] \n" +" stb 9,%1(13) \n" +"2: \n" + RESTART_TABLE(1b, 2b, 1b) + : : "i" (offsetof(struct paca_struct, irq_happened)), + "i" (offsetof(struct paca_struct, irq_soft_mask)) + : "cr0", "r9" + : happened); + + if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) + WARN_ON_ONCE(!(mfmsr() & MSR_EE)); + + return; + +happened: + irq_happened = READ_ONCE(local_paca->irq_happened); + if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) + WARN_ON_ONCE(!irq_happened); + + if (irq_happened == PACA_IRQ_HARD_DIS) { + if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) + WARN_ON_ONCE(mfmsr() & MSR_EE); + irq_soft_mask_set(IRQS_ENABLED); + local_paca->irq_happened = 0; + __hard_irq_enable(); + return; + } + + /* Have interrupts to replay, need to hard disable first */ + if (!(irq_happened & PACA_IRQ_HARD_DIS)) { + if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) { + if (!(mfmsr() & MSR_EE)) { + /* + * An interrupt could have come in and cleared + * MSR[EE] and set IRQ_HARD_DIS, so check + * IRQ_HARD_DIS again and warn if it is still + * clear. + */ + irq_happened = READ_ONCE(local_paca->irq_happened); + WARN_ON_ONCE(!(irq_happened & PACA_IRQ_HARD_DIS)); + } + } + __hard_irq_disable(); + local_paca->irq_happened |= PACA_IRQ_HARD_DIS; + } else { + if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) { + if (WARN_ON_ONCE(mfmsr() & MSR_EE)) + __hard_irq_disable(); + } + } + + /* + * Disable preempt here, so that the below preempt_enable will + * perform resched if required (a replayed interrupt may set + * need_resched). + */ + preempt_disable(); + irq_soft_mask_set(IRQS_ALL_DISABLED); + trace_hardirqs_off(); + + replay_soft_interrupts_irqrestore(); + + trace_hardirqs_on(); + irq_soft_mask_set(IRQS_ENABLED); + if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) + WARN_ON(local_paca->irq_happened != PACA_IRQ_HARD_DIS); + local_paca->irq_happened = 0; + __hard_irq_enable(); + preempt_enable(); +} +EXPORT_SYMBOL(arch_local_irq_restore); + +/* + * This is a helper to use when about to go into idle low-power + * when the latter has the side effect of re-enabling interrupts + * (such as calling H_CEDE under pHyp). + * + * You call this function with interrupts soft-disabled (this is + * already the case when ppc_md.power_save is called). The function + * will return whether to enter power save or just return. + * + * In the former case, it will have notified lockdep of interrupts + * being re-enabled and generally sanitized the lazy irq state, + * and in the latter case it will leave with interrupts hard + * disabled and marked as such, so the local_irq_enable() call + * in arch_cpu_idle() will properly re-enable everything. + */ +bool prep_irq_for_idle(void) +{ + /* + * First we need to hard disable to ensure no interrupt + * occurs before we effectively enter the low power state + */ + __hard_irq_disable(); + local_paca->irq_happened |= PACA_IRQ_HARD_DIS; + + /* + * If anything happened while we were soft-disabled, + * we return now and do not enter the low power state. + */ + if (lazy_irq_pending()) + return false; + + /* Tell lockdep we are about to re-enable */ + trace_hardirqs_on(); + + /* + * Mark interrupts as soft-enabled and clear the + * PACA_IRQ_HARD_DIS from the pending mask since we + * are about to hard enable as well as a side effect + * of entering the low power state. + */ + local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS; + irq_soft_mask_set(IRQS_ENABLED); + + /* Tell the caller to enter the low power state */ + return true; +} + +#ifdef CONFIG_PPC_BOOK3S +/* + * This is for idle sequences that return with IRQs off, but the + * idle state itself wakes on interrupt. Tell the irq tracer that + * IRQs are enabled for the duration of idle so it does not get long + * off times. Must be paired with fini_irq_for_idle_irqsoff. + */ +bool prep_irq_for_idle_irqsoff(void) +{ + WARN_ON(!irqs_disabled()); + + /* + * First we need to hard disable to ensure no interrupt + * occurs before we effectively enter the low power state + */ + __hard_irq_disable(); + local_paca->irq_happened |= PACA_IRQ_HARD_DIS; + + /* + * If anything happened while we were soft-disabled, + * we return now and do not enter the low power state. + */ + if (lazy_irq_pending()) + return false; + + /* Tell lockdep we are about to re-enable */ + trace_hardirqs_on(); + + return true; +} + +/* + * Take the SRR1 wakeup reason, index into this table to find the + * appropriate irq_happened bit. + * + * Sytem reset exceptions taken in idle state also come through here, + * but they are NMI interrupts so do not need to wait for IRQs to be + * restored, and should be taken as early as practical. These are marked + * with 0xff in the table. The Power ISA specifies 0100b as the system + * reset interrupt reason. + */ +#define IRQ_SYSTEM_RESET 0xff + +static const u8 srr1_to_lazyirq[0x10] = { + 0, 0, 0, + PACA_IRQ_DBELL, + IRQ_SYSTEM_RESET, + PACA_IRQ_DBELL, + PACA_IRQ_DEC, + 0, + PACA_IRQ_EE, + PACA_IRQ_EE, + PACA_IRQ_HMI, + 0, 0, 0, 0, 0 }; + +void replay_system_reset(void) +{ + struct pt_regs regs; + + ppc_save_regs(®s); + regs.trap = 0x100; + get_paca()->in_nmi = 1; + system_reset_exception(®s); + get_paca()->in_nmi = 0; +} +EXPORT_SYMBOL_GPL(replay_system_reset); + +void irq_set_pending_from_srr1(unsigned long srr1) +{ + unsigned int idx = (srr1 & SRR1_WAKEMASK_P8) >> 18; + u8 reason = srr1_to_lazyirq[idx]; + + /* + * Take the system reset now, which is immediately after registers + * are restored from idle. It's an NMI, so interrupts need not be + * re-enabled before it is taken. + */ + if (unlikely(reason == IRQ_SYSTEM_RESET)) { + replay_system_reset(); + return; + } + + if (reason == PACA_IRQ_DBELL) { + /* + * When doorbell triggers a system reset wakeup, the message + * is not cleared, so if the doorbell interrupt is replayed + * and the IPI handled, the doorbell interrupt would still + * fire when EE is enabled. + * + * To avoid taking the superfluous doorbell interrupt, + * execute a msgclr here before the interrupt is replayed. + */ + ppc_msgclr(PPC_DBELL_MSGTYPE); + } + + /* + * The 0 index (SRR1[42:45]=b0000) must always evaluate to 0, + * so this can be called unconditionally with the SRR1 wake + * reason as returned by the idle code, which uses 0 to mean no + * interrupt. + * + * If a future CPU was to designate this as an interrupt reason, + * then a new index for no interrupt must be assigned. + */ + local_paca->irq_happened |= reason; +} +#endif /* CONFIG_PPC_BOOK3S */ + +/* + * Force a replay of the external interrupt handler on this CPU. + */ +void force_external_irq_replay(void) +{ + /* + * This must only be called with interrupts soft-disabled, + * the replay will happen when re-enabling. + */ + WARN_ON(!arch_irqs_disabled()); + + /* + * Interrupts must always be hard disabled before irq_happened is + * modified (to prevent lost update in case of interrupt between + * load and store). + */ + __hard_irq_disable(); + local_paca->irq_happened |= PACA_IRQ_HARD_DIS; + + /* Indicate in the PACA that we have an interrupt to replay */ + local_paca->irq_happened |= PACA_IRQ_EE; +} + +static int __init setup_noirqdistrib(char *str) +{ + distribute_irqs = 0; + return 1; +} + +__setup("noirqdistrib", setup_noirqdistrib); diff --git a/arch/powerpc/kernel/isa-bridge.c b/arch/powerpc/kernel/isa-bridge.c index 39c625737c09..dc746611ebc0 100644 --- a/arch/powerpc/kernel/isa-bridge.c +++ b/arch/powerpc/kernel/isa-bridge.c @@ -18,11 +18,11 @@ #include <linux/init.h> #include <linux/mm.h> #include <linux/notifier.h> +#include <linux/of_address.h> #include <linux/vmalloc.h> #include <asm/processor.h> #include <asm/io.h> -#include <asm/prom.h> #include <asm/pci-bridge.h> #include <asm/machdep.h> #include <asm/ppc-pci.h> diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c index bdee7262c080..1a1e9995dae3 100644 --- a/arch/powerpc/kernel/kgdb.c +++ b/arch/powerpc/kernel/kgdb.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * PowerPC backend to the KGDB stub. * @@ -8,10 +9,6 @@ * PPC32 support restored by Vitaly Wool <vwool@ru.mvista.com> and * Sergei Shtylyov <sshtylyov@ru.mvista.com> * Copyright (C) 2007-2008 Wind River Systems, Inc. - * - * This file is licensed under the terms of the GNU General Public License - * version 2. This program as licensed "as is" without any warranty of any - * kind, whether express or implied. */ #include <linux/kernel.h> @@ -48,9 +45,9 @@ static struct hard_trap_info { 0x0800, 0x08 /* SIGFPE */ }, /* fp unavailable */ { 0x0900, 0x0e /* SIGALRM */ }, /* decrementer */ { 0x0c00, 0x14 /* SIGCHLD */ }, /* system call */ -#if defined(CONFIG_40x) || defined(CONFIG_BOOKE) +#ifdef CONFIG_BOOKE_OR_40x { 0x2002, 0x05 /* SIGTRAP */ }, /* debug */ -#if defined(CONFIG_FSL_BOOKE) +#if defined(CONFIG_PPC_85xx) { 0x2010, 0x08 /* SIGFPE */ }, /* spe unavailable */ { 0x2020, 0x08 /* SIGFPE */ }, /* spe unavailable */ { 0x2030, 0x08 /* SIGFPE */ }, /* spe fp data */ @@ -60,14 +57,14 @@ static struct hard_trap_info { 0x2900, 0x08 /* SIGFPE */ }, /* apu unavailable */ { 0x3100, 0x0e /* SIGALRM */ }, /* fixed interval timer */ { 0x3200, 0x02 /* SIGINT */ }, /* watchdog */ -#else /* ! CONFIG_FSL_BOOKE */ +#else /* ! CONFIG_PPC_85xx */ { 0x1000, 0x0e /* SIGALRM */ }, /* prog interval timer */ { 0x1010, 0x0e /* SIGALRM */ }, /* fixed interval timer */ { 0x1020, 0x02 /* SIGINT */ }, /* watchdog */ { 0x2010, 0x08 /* SIGFPE */ }, /* fp unavailable */ { 0x2020, 0x08 /* SIGFPE */ }, /* ap unavailable */ #endif -#else /* ! (defined(CONFIG_40x) || defined(CONFIG_BOOKE)) */ +#else /* !CONFIG_BOOKE_OR_40x */ { 0x0d00, 0x05 /* SIGTRAP */ }, /* single-step */ #if defined(CONFIG_PPC_8xx) { 0x1000, 0x04 /* SIGILL */ }, /* software emulation */ @@ -211,7 +208,7 @@ void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p) for (reg = 14; reg < 32; reg++) PACK64(ptr, regs->gpr[reg]); -#ifdef CONFIG_FSL_BOOKE +#ifdef CONFIG_PPC_85xx #ifdef CONFIG_SPE for (reg = 0; reg < 32; reg++) PACK64(ptr, p->thread.evr[reg]); @@ -237,7 +234,7 @@ void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p) #define GDB_SIZEOF_REG sizeof(unsigned long) #define GDB_SIZEOF_REG_U32 sizeof(u32) -#ifdef CONFIG_FSL_BOOKE +#ifdef CONFIG_PPC_85xx #define GDB_SIZEOF_FLOAT_REG sizeof(unsigned long) #else #define GDB_SIZEOF_FLOAT_REG sizeof(u64) @@ -332,7 +329,7 @@ char *dbg_get_reg(int regno, void *mem, struct pt_regs *regs) if (regno >= 32 && regno < 64) { /* FP registers 32 -> 63 */ -#if defined(CONFIG_FSL_BOOKE) && defined(CONFIG_SPE) +#if defined(CONFIG_PPC_85xx) && defined(CONFIG_SPE) if (current) memcpy(mem, ¤t->thread.evr[regno-32], dbg_reg_def[regno].size); @@ -358,7 +355,7 @@ int dbg_set_reg(int regno, void *mem, struct pt_regs *regs) if (regno >= 32 && regno < 64) { /* FP registers 32 -> 63 */ -#if defined(CONFIG_FSL_BOOKE) && defined(CONFIG_SPE) +#if defined(CONFIG_PPC_85xx) && defined(CONFIG_SPE) memcpy(¤t->thread.evr[regno-32], mem, dbg_reg_def[regno].size); #else diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index 86d77ff056a6..bd7b1a035459 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -45,7 +45,7 @@ kprobe_opcode_t *kprobe_lookup_name(const char *name, unsigned int offset) { kprobe_opcode_t *addr = NULL; -#ifdef PPC64_ELF_ABI_v2 +#ifdef CONFIG_PPC64_ELF_ABI_V2 /* PPC64 ABIv2 needs local entry point */ addr = (kprobe_opcode_t *)kallsyms_lookup_name(name); if (addr && !offset) { @@ -63,7 +63,7 @@ kprobe_opcode_t *kprobe_lookup_name(const char *name, unsigned int offset) #endif addr = (kprobe_opcode_t *)ppc_function_entry(addr); } -#elif defined(PPC64_ELF_ABI_v1) +#elif defined(CONFIG_PPC64_ELF_ABI_V1) /* * 64bit powerpc ABIv1 uses function descriptors: * - Check for the dot variant of the symbol first. @@ -105,6 +105,27 @@ kprobe_opcode_t *kprobe_lookup_name(const char *name, unsigned int offset) return addr; } +static bool arch_kprobe_on_func_entry(unsigned long offset) +{ +#ifdef CONFIG_PPC64_ELF_ABI_V2 +#ifdef CONFIG_KPROBES_ON_FTRACE + return offset <= 16; +#else + return offset <= 8; +#endif +#else + return !offset; +#endif +} + +/* XXX try and fold the magic of kprobe_lookup_name() in this */ +kprobe_opcode_t *arch_adjust_kprobe_addr(unsigned long addr, unsigned long offset, + bool *on_func_entry) +{ + *on_func_entry = arch_kprobe_on_func_entry(offset); + return (kprobe_opcode_t *)(addr + offset); +} + void *alloc_insn_page(void) { void *page; @@ -124,13 +145,13 @@ int arch_prepare_kprobe(struct kprobe *p) { int ret = 0; struct kprobe *prev; - struct ppc_inst insn = ppc_inst_read(p->addr); + ppc_inst_t insn = ppc_inst_read(p->addr); if ((unsigned long)p->addr & 0x03) { printk("Attempt to register kprobe at an unaligned address\n"); ret = -EINVAL; - } else if (IS_MTMSRD(insn) || IS_RFID(insn)) { - printk("Cannot register a kprobe on mtmsr[d]/rfi[d]\n"); + } else if (!can_single_step(ppc_inst_val(insn))) { + printk("Cannot register a kprobe on instructions that can't be single stepped\n"); ret = -EINVAL; } else if ((unsigned long)p->addr & ~PAGE_MASK && ppc_inst_prefixed(ppc_inst_read(p->addr - 1))) { @@ -140,7 +161,13 @@ int arch_prepare_kprobe(struct kprobe *p) preempt_disable(); prev = get_kprobe(p->addr - 1); preempt_enable_no_resched(); - if (prev && ppc_inst_prefixed(ppc_inst_read(prev->ainsn.insn))) { + + /* + * When prev is a ftrace-based kprobe, we don't have an insn, and it + * doesn't probe for prefixed instruction. + */ + if (prev && !kprobe_ftrace(prev) && + ppc_inst_prefixed(ppc_inst_read(prev->ainsn.insn))) { printk("Cannot register a kprobe on the second word of prefixed instruction\n"); ret = -EINVAL; } @@ -218,19 +245,6 @@ static nokprobe_inline void set_current_kprobe(struct kprobe *p, struct pt_regs kcb->kprobe_saved_msr = regs->msr; } -bool arch_kprobe_on_func_entry(unsigned long offset) -{ -#ifdef PPC64_ELF_ABI_v2 -#ifdef CONFIG_KPROBES_ON_FTRACE - return offset <= 16; -#else - return offset <= 8; -#endif -#else - return !offset; -#endif -} - void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs) { ri->ret_addr = (kprobe_opcode_t *)regs->link; @@ -244,7 +258,7 @@ NOKPROBE_SYMBOL(arch_prepare_kretprobe); static int try_to_emulate(struct kprobe *p, struct pt_regs *regs) { int ret; - struct ppc_inst insn = ppc_inst_read(p->ainsn.insn); + ppc_inst_t insn = ppc_inst_read(p->ainsn.insn); /* regs->nip is also adjusted if emulate_step returns 1 */ ret = emulate_step(regs, insn); @@ -261,7 +275,7 @@ static int try_to_emulate(struct kprobe *p, struct pt_regs *regs) * So, we should never get here... but, its still * good to catch them, just in case... */ - printk("Can't step on instruction %s\n", ppc_inst_as_str(insn)); + printk("Can't step on instruction %08lx\n", ppc_inst_as_ulong(insn)); BUG(); } else { /* diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c index 6568823cf306..5b3c093611ba 100644 --- a/arch/powerpc/kernel/kvm.c +++ b/arch/powerpc/kernel/kvm.c @@ -455,7 +455,7 @@ static void __init kvm_check_ins(u32 *inst, u32 features) kvm_patch_ins_lwz(inst, magic_var(dsisr), inst_rt); break; -#ifdef CONFIG_PPC_BOOK3E_MMU +#ifdef CONFIG_PPC_E500 case KVM_INST_MFSPR(SPRN_MAS0): if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7) kvm_patch_ins_lwz(inst, magic_var(mas0), inst_rt); @@ -484,7 +484,7 @@ static void __init kvm_check_ins(u32 *inst, u32 features) if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7) kvm_patch_ins_lwz(inst, magic_var(mas7_3), inst_rt); break; -#endif /* CONFIG_PPC_BOOK3E_MMU */ +#endif /* CONFIG_PPC_E500 */ case KVM_INST_MFSPR(SPRN_SPRG4): #ifdef CONFIG_BOOKE @@ -557,7 +557,7 @@ static void __init kvm_check_ins(u32 *inst, u32 features) case KVM_INST_MTSPR(SPRN_DSISR): kvm_patch_ins_stw(inst, magic_var(dsisr), inst_rt); break; -#ifdef CONFIG_PPC_BOOK3E_MMU +#ifdef CONFIG_PPC_E500 case KVM_INST_MTSPR(SPRN_MAS0): if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7) kvm_patch_ins_stw(inst, magic_var(mas0), inst_rt); @@ -586,7 +586,7 @@ static void __init kvm_check_ins(u32 *inst, u32 features) if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7) kvm_patch_ins_stw(inst, magic_var(mas7_3), inst_rt); break; -#endif /* CONFIG_PPC_BOOK3E_MMU */ +#endif /* CONFIG_PPC_E500 */ case KVM_INST_MTSPR(SPRN_SPRG4): if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7) diff --git a/arch/powerpc/kernel/l2cr_6xx.S b/arch/powerpc/kernel/l2cr_6xx.S index 225511d73bef..f2e03ed423d0 100644 --- a/arch/powerpc/kernel/l2cr_6xx.S +++ b/arch/powerpc/kernel/l2cr_6xx.S @@ -96,7 +96,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_L2CR) /* Stop DST streams */ BEGIN_FTR_SECTION - DSSALL + PPC_DSSALL sync END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) @@ -292,7 +292,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_L3CR) isync /* Stop DST streams */ - DSSALL + PPC_DSSALL sync /* Get the current enable bit of the L3CR into r4 */ @@ -401,7 +401,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_L3CR) _GLOBAL(__flush_disable_L1) /* Stop pending alitvec streams and memory accesses */ BEGIN_FTR_SECTION - DSSALL + PPC_DSSALL END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) sync diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c index cfc03e016ff2..f048c424c525 100644 --- a/arch/powerpc/kernel/legacy_serial.c +++ b/arch/powerpc/kernel/legacy_serial.c @@ -7,10 +7,10 @@ #include <linux/pci.h> #include <linux/of_address.h> #include <linux/of_device.h> +#include <linux/of_irq.h> #include <linux/serial_reg.h> #include <asm/io.h> #include <asm/mmu.h> -#include <asm/prom.h> #include <asm/serial.h> #include <asm/udbg.h> #include <asm/pci-bridge.h> @@ -471,6 +471,8 @@ void __init find_legacy_serial_ports(void) } #endif + of_node_put(stdout); + DBG("legacy_serial_console = %d\n", legacy_serial_console); if (legacy_serial_console >= 0) setup_legacy_serial_console(legacy_serial_console); diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c index fd829f7f25a4..6c5d30fba766 100644 --- a/arch/powerpc/kernel/mce.c +++ b/arch/powerpc/kernel/mce.c @@ -24,23 +24,12 @@ #include <asm/machdep.h> #include <asm/mce.h> #include <asm/nmi.h> -#include <asm/asm-prototypes.h> #include "setup.h" -static void machine_check_process_queued_event(struct irq_work *work); -static void machine_check_ue_irq_work(struct irq_work *work); static void machine_check_ue_event(struct machine_check_event *evt); static void machine_process_ue_event(struct work_struct *work); -static struct irq_work mce_event_process_work = { - .func = machine_check_process_queued_event, -}; - -static struct irq_work mce_ue_event_irq_work = { - .func = machine_check_ue_irq_work, -}; - static DECLARE_WORK(mce_ue_event_work, machine_process_ue_event); static BLOCKING_NOTIFIER_HEAD(mce_notifier_list); @@ -89,6 +78,13 @@ static void mce_set_error_info(struct machine_check_event *mce, } } +void mce_irq_work_queue(void) +{ + /* Raise decrementer interrupt */ + arch_irq_work_raise(); + set_mce_pending_irq_work(); +} + /* * Decode and save high level MCE information into per cpu buffer which * is an array of machine_check_event structure. @@ -217,7 +213,7 @@ void release_mce_event(void) get_mce_event(NULL, true); } -static void machine_check_ue_irq_work(struct irq_work *work) +static void machine_check_ue_work(void) { schedule_work(&mce_ue_event_work); } @@ -239,7 +235,7 @@ static void machine_check_ue_event(struct machine_check_event *evt) evt, sizeof(*evt)); /* Queue work to process this event later. */ - irq_work_queue(&mce_ue_event_irq_work); + mce_irq_work_queue(); } /* @@ -249,7 +245,6 @@ void machine_check_queue_event(void) { int index; struct machine_check_event evt; - unsigned long msr; if (!get_mce_event(&evt, MCE_EVENT_RELEASE)) return; @@ -263,20 +258,7 @@ void machine_check_queue_event(void) memcpy(&local_paca->mce_info->mce_event_queue[index], &evt, sizeof(evt)); - /* - * Queue irq work to process this event later. Before - * queuing the work enable translation for non radix LPAR, - * as irq_work_queue may try to access memory outside RMO - * region. - */ - if (!radix_enabled() && firmware_has_feature(FW_FEATURE_LPAR)) { - msr = mfmsr(); - mtmsr(msr | MSR_IR | MSR_DR); - irq_work_queue(&mce_event_process_work); - mtmsr(msr); - } else { - irq_work_queue(&mce_event_process_work); - } + mce_irq_work_queue(); } void mce_common_process_ue(struct pt_regs *regs, @@ -338,7 +320,7 @@ static void machine_process_ue_event(struct work_struct *work) * process pending MCE event from the mce event queue. This function will be * called during syscall exit. */ -static void machine_check_process_queued_event(struct irq_work *work) +static void machine_check_process_queued_event(void) { int index; struct machine_check_event *evt; @@ -363,6 +345,27 @@ static void machine_check_process_queued_event(struct irq_work *work) } } +void set_mce_pending_irq_work(void) +{ + local_paca->mce_pending_irq_work = 1; +} + +void clear_mce_pending_irq_work(void) +{ + local_paca->mce_pending_irq_work = 0; +} + +void mce_run_irq_context_handlers(void) +{ + if (unlikely(local_paca->mce_pending_irq_work)) { + if (ppc_md.machine_check_log_err) + ppc_md.machine_check_log_err(); + machine_check_process_queued_event(); + machine_check_ue_work(); + clear_mce_pending_irq_work(); + } +} + void machine_check_print_event_info(struct machine_check_event *evt, bool user_mode, bool in_guest) { @@ -401,14 +404,14 @@ void machine_check_print_event_info(struct machine_check_event *evt, static const char *mc_ra_types[] = { "Indeterminate", "Instruction fetch (bad)", - "Instruction fetch (foreign)", + "Instruction fetch (foreign/control memory)", "Page table walk ifetch (bad)", - "Page table walk ifetch (foreign)", + "Page table walk ifetch (foreign/control memory)", "Load (bad)", "Store (bad)", "Page table walk Load/Store (bad)", - "Page table walk Load/Store (foreign)", - "Load/Store (foreign)", + "Page table walk Load/Store (foreign/control memory)", + "Load/Store (foreign/control memory)", }; static const char *mc_link_types[] = { "Indeterminate", @@ -586,7 +589,7 @@ void machine_check_print_event_info(struct machine_check_event *evt, mc_error_class[evt->error_class] : "Unknown"; printk("%sMCE: CPU%d: %s\n", level, evt->cpu, subtype); -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU /* Display faulty slb contents for SLB errors. */ if (evt->error_type == MCE_ERROR_TYPE_SLB && !in_guest) slb_dump_contents(local_paca->mce_faulty_slbs); @@ -753,7 +756,7 @@ void __init mce_init(void) mce_info = memblock_alloc_try_nid(sizeof(*mce_info), __alignof__(*mce_info), MEMBLOCK_LOW_LIMIT, - limit, cpu_to_node(i)); + limit, early_cpu_to_node(i)); if (!mce_info) goto err; paca_ptrs[i]->mce_info = mce_info; diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c index c2f55fe7092d..71e8f2a92e36 100644 --- a/arch/powerpc/kernel/mce_power.c +++ b/arch/powerpc/kernel/mce_power.c @@ -77,15 +77,15 @@ static bool mce_in_guest(void) } /* flush SLBs and reload */ -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU void flush_and_reload_slb(void) { - /* Invalidate all SLBs */ - slb_flush_all_realmode(); - if (early_radix_enabled()) return; + /* Invalidate all SLBs */ + slb_flush_all_realmode(); + /* * This probably shouldn't happen, but it may be possible it's * called in early boot before SLB shadows are allocated. @@ -99,7 +99,7 @@ void flush_and_reload_slb(void) void flush_erat(void) { -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU if (!early_cpu_has_feature(CPU_FTR_ARCH_300)) { flush_and_reload_slb(); return; @@ -114,7 +114,7 @@ void flush_erat(void) static int mce_flush(int what) { -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU if (what == MCE_FLUSH_SLB) { flush_and_reload_slb(); return 1; @@ -455,7 +455,7 @@ static int mce_find_instr_ea_and_phys(struct pt_regs *regs, uint64_t *addr, * in real-mode is tricky and can lead to recursive * faults */ - struct ppc_inst instr; + ppc_inst_t instr; unsigned long pfn, instr_addr; struct instruction_op op; struct pt_regs tmp = *regs; @@ -499,8 +499,10 @@ static int mce_handle_ierror(struct pt_regs *regs, unsigned long srr1, /* attempt to correct the error */ switch (table[i].error_type) { case MCE_ERROR_TYPE_SLB: +#ifdef CONFIG_PPC_64S_HASH_MMU if (local_paca->in_mce == 1) slb_save_contents(local_paca->mce_faulty_slbs); +#endif handled = mce_flush(MCE_FLUSH_SLB); break; case MCE_ERROR_TYPE_ERAT: @@ -588,8 +590,10 @@ static int mce_handle_derror(struct pt_regs *regs, /* attempt to correct the error */ switch (table[i].error_type) { case MCE_ERROR_TYPE_SLB: +#ifdef CONFIG_PPC_64S_HASH_MMU if (local_paca->in_mce == 1) slb_save_contents(local_paca->mce_faulty_slbs); +#endif if (mce_flush(MCE_FLUSH_SLB)) handled = 1; break; diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index d38a019b38e1..36184cada00b 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -286,7 +286,7 @@ kexec_flag: #ifdef CONFIG_KEXEC_CORE -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 /* * BOOK3E has no real MMU mode, so we have to setup the initial TLB * for a core to identity map v:0 to p:0. This current implementation @@ -354,7 +354,7 @@ _GLOBAL(kexec_smp_wait) * don't overwrite r3 here, it is live for kexec_wait above. */ real_mode: /* assume normal blr return */ -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 /* Create an identity mapping. */ b kexec_create_tlb #else @@ -413,7 +413,7 @@ _GLOBAL(kexec_sequence) lhz r25,PACAHWCPUID(r13) /* get our phys cpu from paca */ /* disable interrupts, we are overwriting kernel data next */ -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 wrteei 0 #else mfmsr r3 @@ -454,7 +454,7 @@ _GLOBAL(kexec_sequence) beq 1f /* clear out hardware hash page table and tlb */ -#ifdef PPC64_ELF_ABI_v1 +#ifdef CONFIG_PPC64_ELF_ABI_V1 ld r12,0(r27) /* deref function descriptor */ #else mr r12,r27 diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c index ed04a3ba66fe..f6d6ae0a1692 100644 --- a/arch/powerpc/kernel/module.c +++ b/arch/powerpc/kernel/module.c @@ -64,13 +64,13 @@ int module_finalize(const Elf_Ehdr *hdr, (void *)sect->sh_addr + sect->sh_size); #endif /* CONFIG_PPC64 */ -#ifdef PPC64_ELF_ABI_v1 +#ifdef CONFIG_PPC64_ELF_ABI_V1 sect = find_section(hdr, sechdrs, ".opd"); if (sect != NULL) { me->arch.start_opd = sect->sh_addr; me->arch.end_opd = sect->sh_addr + sect->sh_size; } -#endif /* PPC64_ELF_ABI_v1 */ +#endif /* CONFIG_PPC64_ELF_ABI_V1 */ #ifdef CONFIG_PPC_BARRIER_NOSPEC sect = find_section(hdr, sechdrs, "__spec_barrier_fixup"); @@ -90,17 +90,18 @@ int module_finalize(const Elf_Ehdr *hdr, } static __always_inline void * -__module_alloc(unsigned long size, unsigned long start, unsigned long end) +__module_alloc(unsigned long size, unsigned long start, unsigned long end, bool nowarn) { pgprot_t prot = strict_module_rwx_enabled() ? PAGE_KERNEL : PAGE_KERNEL_EXEC; + gfp_t gfp = GFP_KERNEL | (nowarn ? __GFP_NOWARN : 0); /* * Don't do huge page allocations for modules yet until more testing * is done. STRICT_MODULE_RWX may require extra work to support this * too. */ - return __vmalloc_node_range(size, 1, start, end, GFP_KERNEL, prot, - VM_FLUSH_RESET_PERMS | VM_NO_HUGE_VMAP, + return __vmalloc_node_range(size, 1, start, end, gfp, prot, + VM_FLUSH_RESET_PERMS, NUMA_NO_NODE, __builtin_return_address(0)); } @@ -114,13 +115,13 @@ void *module_alloc(unsigned long size) /* First try within 32M limit from _etext to avoid branch trampolines */ if (MODULES_VADDR < PAGE_OFFSET && MODULES_END > limit) - ptr = __module_alloc(size, limit, MODULES_END); + ptr = __module_alloc(size, limit, MODULES_END, true); if (!ptr) - ptr = __module_alloc(size, MODULES_VADDR, MODULES_END); + ptr = __module_alloc(size, MODULES_VADDR, MODULES_END, false); return ptr; #else - return __module_alloc(size, VMALLOC_START, VMALLOC_END); + return __module_alloc(size, VMALLOC_START, VMALLOC_END, false); #endif } diff --git a/arch/powerpc/kernel/module_32.c b/arch/powerpc/kernel/module_32.c index f417afc08d33..ea6536171778 100644 --- a/arch/powerpc/kernel/module_32.c +++ b/arch/powerpc/kernel/module_32.c @@ -18,6 +18,7 @@ #include <linux/bug.h> #include <linux/sort.h> #include <asm/setup.h> +#include <asm/code-patching.h> /* Count how many different relocations (different symbol, different addend) */ @@ -98,7 +99,7 @@ static unsigned long get_plt_size(const Elf32_Ehdr *hdr, /* Sort the relocation information based on a symbol and * addend key. This is a stable O(n*log n) complexity - * alogrithm but it will reduce the complexity of + * algorithm but it will reduce the complexity of * count_relocs() to linear complexity O(n) */ sort((void *)hdr + sechdrs[i].sh_offset, @@ -174,15 +175,25 @@ static uint32_t do_plt_call(void *location, entry++; } - entry->jump[0] = PPC_RAW_LIS(_R12, PPC_HA(val)); - entry->jump[1] = PPC_RAW_ADDI(_R12, _R12, PPC_LO(val)); - entry->jump[2] = PPC_RAW_MTCTR(_R12); - entry->jump[3] = PPC_RAW_BCTR(); + if (patch_instruction(&entry->jump[0], ppc_inst(PPC_RAW_LIS(_R12, PPC_HA(val))))) + return 0; + if (patch_instruction(&entry->jump[1], ppc_inst(PPC_RAW_ADDI(_R12, _R12, PPC_LO(val))))) + return 0; + if (patch_instruction(&entry->jump[2], ppc_inst(PPC_RAW_MTCTR(_R12)))) + return 0; + if (patch_instruction(&entry->jump[3], ppc_inst(PPC_RAW_BCTR()))) + return 0; pr_debug("Initialized plt for 0x%x at %p\n", val, entry); return (uint32_t)entry; } +static int patch_location_16(uint32_t *loc, u16 value) +{ + loc = PTR_ALIGN_DOWN(loc, sizeof(u32)); + return patch_instruction(loc, ppc_inst((*loc & 0xffff0000) | value)); +} + int apply_relocate_add(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, @@ -216,44 +227,46 @@ int apply_relocate_add(Elf32_Shdr *sechdrs, case R_PPC_ADDR16_LO: /* Low half of the symbol */ - *(uint16_t *)location = value; + if (patch_location_16(location, PPC_LO(value))) + return -EFAULT; break; case R_PPC_ADDR16_HI: /* Higher half of the symbol */ - *(uint16_t *)location = (value >> 16); + if (patch_location_16(location, PPC_HI(value))) + return -EFAULT; break; case R_PPC_ADDR16_HA: - /* Sign-adjusted lower 16 bits: PPC ELF ABI says: - (((x >> 16) + ((x & 0x8000) ? 1 : 0))) & 0xFFFF. - This is the same, only sane. - */ - *(uint16_t *)location = (value + 0x8000) >> 16; + if (patch_location_16(location, PPC_HA(value))) + return -EFAULT; break; case R_PPC_REL24: if ((int)(value - (uint32_t)location) < -0x02000000 - || (int)(value - (uint32_t)location) >= 0x02000000) + || (int)(value - (uint32_t)location) >= 0x02000000) { value = do_plt_call(location, value, sechdrs, module); + if (!value) + return -EFAULT; + } /* Only replace bits 2 through 26 */ pr_debug("REL24 value = %08X. location = %08X\n", value, (uint32_t)location); pr_debug("Location before: %08X.\n", *(uint32_t *)location); - *(uint32_t *)location - = (*(uint32_t *)location & ~0x03fffffc) - | ((value - (uint32_t)location) - & 0x03fffffc); + value = (*(uint32_t *)location & ~PPC_LI_MASK) | + PPC_LI(value - (uint32_t)location); + + if (patch_instruction(location, ppc_inst(value))) + return -EFAULT; + pr_debug("Location after: %08X.\n", *(uint32_t *)location); pr_debug("ie. jump to %08X+%08X = %08X\n", - *(uint32_t *)location & 0x03fffffc, - (uint32_t)location, - (*(uint32_t *)location & 0x03fffffc) - + (uint32_t)location); + *(uint32_t *)PPC_LI((uint32_t)location), (uint32_t)location, + (*(uint32_t *)PPC_LI((uint32_t)location)) + (uint32_t)location); break; case R_PPC_REL32: @@ -273,6 +286,40 @@ int apply_relocate_add(Elf32_Shdr *sechdrs, } #ifdef CONFIG_DYNAMIC_FTRACE +notrace int module_trampoline_target(struct module *mod, unsigned long addr, + unsigned long *target) +{ + ppc_inst_t jmp[4]; + + /* Find where the trampoline jumps to */ + if (copy_inst_from_kernel_nofault(jmp, (void *)addr)) + return -EFAULT; + if (__copy_inst_from_kernel_nofault(jmp + 1, (void *)addr + 4)) + return -EFAULT; + if (__copy_inst_from_kernel_nofault(jmp + 2, (void *)addr + 8)) + return -EFAULT; + if (__copy_inst_from_kernel_nofault(jmp + 3, (void *)addr + 12)) + return -EFAULT; + + /* verify that this is what we expect it to be */ + if ((ppc_inst_val(jmp[0]) & 0xffff0000) != PPC_RAW_LIS(_R12, 0)) + return -EINVAL; + if ((ppc_inst_val(jmp[1]) & 0xffff0000) != PPC_RAW_ADDI(_R12, _R12, 0)) + return -EINVAL; + if (ppc_inst_val(jmp[2]) != PPC_RAW_MTCTR(_R12)) + return -EINVAL; + if (ppc_inst_val(jmp[3]) != PPC_RAW_BCTR()) + return -EINVAL; + + addr = (ppc_inst_val(jmp[1]) & 0xffff) | ((ppc_inst_val(jmp[0]) & 0xffff) << 16); + if (addr & 0x8000) + addr -= 0x10000; + + *target = addr; + + return 0; +} + int module_finalize_ftrace(struct module *module, const Elf_Shdr *sechdrs) { module->arch.tramp = do_plt_call(module->core_layout.base, @@ -281,6 +328,14 @@ int module_finalize_ftrace(struct module *module, const Elf_Shdr *sechdrs) if (!module->arch.tramp) return -ENOENT; +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS + module->arch.tramp_regs = do_plt_call(module->core_layout.base, + (unsigned long)ftrace_regs_caller, + sechdrs, module); + if (!module->arch.tramp_regs) + return -ENOENT; +#endif + return 0; } #endif diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 6baa676e7cb6..7e45dc98df8a 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -14,6 +14,7 @@ #include <linux/ftrace.h> #include <linux/bug.h> #include <linux/uaccess.h> +#include <linux/kernel.h> #include <asm/module.h> #include <asm/firmware.h> #include <asm/code-patching.h> @@ -30,22 +31,15 @@ this, and makes other things simpler. Anton? --RR. */ -#ifdef PPC64_ELF_ABI_v2 - -/* An address is simply the address of the function. */ -typedef unsigned long func_desc_t; +#ifdef CONFIG_PPC64_ELF_ABI_V2 static func_desc_t func_desc(unsigned long addr) { - return addr; -} -static unsigned long func_addr(unsigned long addr) -{ - return addr; -} -static unsigned long stub_func_addr(func_desc_t func) -{ - return func; + func_desc_t desc = { + .addr = addr, + }; + + return desc; } /* PowerPC64 specific values for the Elf64_Sym st_other field. */ @@ -63,20 +57,9 @@ static unsigned int local_entry_offset(const Elf64_Sym *sym) } #else -/* An address is address of the OPD entry, which contains address of fn. */ -typedef struct ppc64_opd_entry func_desc_t; - static func_desc_t func_desc(unsigned long addr) { - return *(struct ppc64_opd_entry *)addr; -} -static unsigned long func_addr(unsigned long addr) -{ - return func_desc(addr).funcaddr; -} -static unsigned long stub_func_addr(func_desc_t func) -{ - return func.funcaddr; + return *(struct func_desc *)addr; } static unsigned int local_entry_offset(const Elf64_Sym *sym) { @@ -93,6 +76,16 @@ void *dereference_module_function_descriptor(struct module *mod, void *ptr) } #endif +static unsigned long func_addr(unsigned long addr) +{ + return func_desc(addr).addr; +} + +static unsigned long stub_func_addr(func_desc_t func) +{ + return func.addr; +} + #define STUB_MAGIC 0x73747562 /* stub */ /* Like PPC32, we need little trampolines to do > 24-bit jumps (into @@ -129,7 +122,7 @@ static u32 ppc64_stub_insns[] = { /* Save current r2 value in magic place on the stack. */ PPC_RAW_STD(_R2, _R1, R2_STACK_OFFSET), PPC_RAW_LD(_R12, _R11, 32), -#ifdef PPC64_ELF_ABI_v1 +#ifdef CONFIG_PPC64_ELF_ABI_V1 /* Set up new r2 from function descriptor */ PPC_RAW_LD(_R2, _R11, 40), #endif @@ -187,7 +180,7 @@ static int relacmp(const void *_x, const void *_y) static unsigned long get_stubs_size(const Elf64_Ehdr *hdr, const Elf64_Shdr *sechdrs) { - /* One extra reloc so it's always 0-funcaddr terminated */ + /* One extra reloc so it's always 0-addr terminated */ unsigned long relocs = 1; unsigned i; @@ -201,7 +194,7 @@ static unsigned long get_stubs_size(const Elf64_Ehdr *hdr, /* Sort the relocation information based on a symbol and * addend key. This is a stable O(n*log n) complexity - * alogrithm but it will reduce the complexity of + * algorithm but it will reduce the complexity of * count_relocs() to linear complexity O(n) */ sort((void *)sechdrs[i].sh_addr, @@ -277,6 +270,12 @@ static Elf64_Sym *find_dot_toc(Elf64_Shdr *sechdrs, return NULL; } +bool module_init_section(const char *name) +{ + /* We don't handle .init for the moment: always return false. */ + return false; +} + int module_frob_arch_sections(Elf64_Ehdr *hdr, Elf64_Shdr *sechdrs, char *secstrings, @@ -286,7 +285,6 @@ int module_frob_arch_sections(Elf64_Ehdr *hdr, /* Find .toc and .stubs sections, symtab and strtab */ for (i = 1; i < hdr->e_shnum; i++) { - char *p; if (strcmp(secstrings + sechdrs[i].sh_name, ".stubs") == 0) me->arch.stubs_section = i; else if (strcmp(secstrings + sechdrs[i].sh_name, ".toc") == 0) { @@ -298,10 +296,6 @@ int module_frob_arch_sections(Elf64_Ehdr *hdr, dedotify_versions((void *)hdr + sechdrs[i].sh_offset, sechdrs[i].sh_size); - /* We don't handle .init for the moment: rename to _init */ - while ((p = strstr(secstrings + sechdrs[i].sh_name, ".init"))) - p[0] = '_'; - if (sechdrs[i].sh_type == SHT_SYMTAB) dedotify((void *)hdr + sechdrs[i].sh_offset, sechdrs[i].sh_size / sizeof(Elf64_Sym), @@ -367,7 +361,7 @@ static inline int create_ftrace_stub(struct ppc64_stub_entry *entry, entry->jump[1] |= PPC_HA(reladdr); entry->jump[2] |= PPC_LO(reladdr); - /* Eventhough we don't use funcdata in the stub, it's needed elsewhere. */ + /* Even though we don't use funcdata in the stub, it's needed elsewhere. */ entry->funcdata = func_desc(addr); entry->magic = STUB_MAGIC; @@ -422,11 +416,17 @@ static inline int create_stub(const Elf64_Shdr *sechdrs, const char *name) { long reladdr; + func_desc_t desc; + int i; if (is_mprofile_ftrace_call(name)) return create_ftrace_stub(entry, addr, me); - memcpy(entry->jump, ppc64_stub_insns, sizeof(ppc64_stub_insns)); + for (i = 0; i < ARRAY_SIZE(ppc64_stub_insns); i++) { + if (patch_instruction(&entry->jump[i], + ppc_inst(ppc64_stub_insns[i]))) + return 0; + } /* Stub uses address relative to r2. */ reladdr = (unsigned long)entry - my_r2(sechdrs, me); @@ -437,10 +437,24 @@ static inline int create_stub(const Elf64_Shdr *sechdrs, } pr_debug("Stub %p get data from reladdr %li\n", entry, reladdr); - entry->jump[0] |= PPC_HA(reladdr); - entry->jump[1] |= PPC_LO(reladdr); - entry->funcdata = func_desc(addr); - entry->magic = STUB_MAGIC; + if (patch_instruction(&entry->jump[0], + ppc_inst(entry->jump[0] | PPC_HA(reladdr)))) + return 0; + + if (patch_instruction(&entry->jump[1], + ppc_inst(entry->jump[1] | PPC_LO(reladdr)))) + return 0; + + // func_desc_t is 8 bytes if ABIv2, else 16 bytes + desc = func_desc(addr); + for (i = 0; i < sizeof(func_desc_t) / sizeof(u32); i++) { + if (patch_instruction(((u32 *)&entry->funcdata) + i, + ppc_inst(((u32 *)(&desc))[i]))) + return 0; + } + + if (patch_instruction(&entry->magic, ppc_inst(STUB_MAGIC))) + return 0; return 1; } @@ -495,8 +509,11 @@ static int restore_r2(const char *name, u32 *instruction, struct module *me) me->name, *instruction, instruction); return 0; } + /* ld r2,R2_STACK_OFFSET(r1) */ - *instruction = PPC_INST_LD_TOC; + if (patch_instruction(instruction, ppc_inst(PPC_INST_LD_TOC))) + return 0; + return 1; } @@ -636,9 +653,11 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, } /* Only replace bits 2 through 26 */ - *(uint32_t *)location - = (*(uint32_t *)location & ~0x03fffffc) - | (value & 0x03fffffc); + value = (*(uint32_t *)location & ~PPC_LI_MASK) | PPC_LI(value); + + if (patch_instruction((u32 *)location, ppc_inst(value))) + return -EFAULT; + break; case R_PPC64_REL64: diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c index 3c8d9bbb51cf..e385d3164648 100644 --- a/arch/powerpc/kernel/nvram_64.c +++ b/arch/powerpc/kernel/nvram_64.c @@ -19,9 +19,9 @@ #include <linux/pstore.h> #include <linux/zlib.h> #include <linux/uaccess.h> +#include <linux/of.h> #include <asm/nvram.h> #include <asm/rtas.h> -#include <asm/prom.h> #include <asm/machdep.h> #undef DEBUG_NVRAM @@ -540,7 +540,7 @@ static struct pstore_info nvram_pstore_info = { .write = nvram_pstore_write, }; -static int nvram_pstore_init(void) +static int __init nvram_pstore_init(void) { int rc = 0; @@ -562,7 +562,7 @@ static int nvram_pstore_init(void) return rc; } #else -static int nvram_pstore_init(void) +static int __init nvram_pstore_init(void) { return -1; } @@ -755,7 +755,7 @@ static unsigned char __init nvram_checksum(struct nvram_header *p) * Per the criteria passed via nvram_remove_partition(), should this * partition be removed? 1=remove, 0=keep */ -static int nvram_can_remove_partition(struct nvram_partition *part, +static int __init nvram_can_remove_partition(struct nvram_partition *part, const char *name, int sig, const char *exceptions[]) { if (part->header.signature != sig) diff --git a/arch/powerpc/kernel/optprobes.c b/arch/powerpc/kernel/optprobes.c index ce1903064031..3b1c2236cbee 100644 --- a/arch/powerpc/kernel/optprobes.c +++ b/arch/powerpc/kernel/optprobes.c @@ -153,7 +153,7 @@ static void patch_imm_load_insns(unsigned long val, int reg, kprobe_opcode_t *ad int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, struct kprobe *p) { - struct ppc_inst branch_op_callback, branch_emulate_step, temp; + ppc_inst_t branch_op_callback, branch_emulate_step, temp; unsigned long op_callback_addr, emulate_step_addr; kprobe_opcode_t *buff; long b_offset; @@ -228,12 +228,8 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, struct kprobe *p) /* * 3. load instruction to be emulated into relevant register, and */ - if (IS_ENABLED(CONFIG_PPC64)) { - temp = ppc_inst_read(p->ainsn.insn); - patch_imm_load_insns(ppc_inst_as_ulong(temp), 4, buff + TMPL_INSN_IDX); - } else { - patch_imm_load_insns((unsigned long)p->ainsn.insn, 4, buff + TMPL_INSN_IDX); - } + temp = ppc_inst_read(p->ainsn.insn); + patch_imm_load_insns(ppc_inst_as_ulong(temp), 4, buff + TMPL_INSN_IDX); /* * 4. branch back from trampoline @@ -269,7 +265,7 @@ int arch_check_optimized_kprobe(struct optimized_kprobe *op) void arch_optimize_kprobes(struct list_head *oplist) { - struct ppc_inst instr; + ppc_inst_t instr; struct optimized_kprobe *op; struct optimized_kprobe *tmp; diff --git a/arch/powerpc/kernel/optprobes_head.S b/arch/powerpc/kernel/optprobes_head.S index 19ea3312403c..cd4e7bc32609 100644 --- a/arch/powerpc/kernel/optprobes_head.S +++ b/arch/powerpc/kernel/optprobes_head.S @@ -10,8 +10,8 @@ #include <asm/asm-offsets.h> #ifdef CONFIG_PPC64 -#define SAVE_30GPRS(base) SAVE_10GPRS(2,base); SAVE_10GPRS(12,base); SAVE_10GPRS(22,base) -#define REST_30GPRS(base) REST_10GPRS(2,base); REST_10GPRS(12,base); REST_10GPRS(22,base) +#define SAVE_30GPRS(base) SAVE_GPRS(2, 31, base) +#define REST_30GPRS(base) REST_GPRS(2, 31, base) #define TEMPLATE_FOR_IMM_LOAD_INSNS nop; nop; nop; nop; nop #else #define SAVE_30GPRS(base) stmw r2, GPR2(base) @@ -73,7 +73,7 @@ optprobe_template_entry: * further below. */ #ifdef CONFIG_PPC64 - ld r2,PACATOC(r13) + LOAD_PACA_TOC() #endif .global optprobe_template_op_address diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index 4208b4044d12..be8db402e963 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -16,7 +16,6 @@ #include <asm/kexec.h> #include <asm/svm.h> #include <asm/ultravisor.h> -#include <asm/rtas.h> #include "setup.h" @@ -139,8 +138,7 @@ static struct lppaca * __init new_lppaca(int cpu, unsigned long limit) } #endif /* CONFIG_PPC_PSERIES */ -#ifdef CONFIG_PPC_BOOK3S_64 - +#ifdef CONFIG_PPC_64S_HASH_MMU /* * 3 persistent SLBs are allocated here. The buffer will be zero * initially, hence will all be invaild until we actually write them. @@ -169,32 +167,7 @@ static struct slb_shadow * __init new_slb_shadow(int cpu, unsigned long limit) return s; } - -#endif /* CONFIG_PPC_BOOK3S_64 */ - -#ifdef CONFIG_PPC_PSERIES -/** - * new_rtas_args() - Allocates rtas args - * @cpu: CPU number - * @limit: Memory limit for this allocation - * - * Allocates a struct rtas_args and return it's pointer, - * if not in Hypervisor mode - * - * Return: Pointer to allocated rtas_args - * NULL if CPU in Hypervisor Mode - */ -static struct rtas_args * __init new_rtas_args(int cpu, unsigned long limit) -{ - limit = min_t(unsigned long, limit, RTAS_INSTANTIATE_MAX); - - if (early_cpu_has_feature(CPU_FTR_HVMODE)) - return NULL; - - return alloc_paca_data(sizeof(struct rtas_args), L1_CACHE_BYTES, - limit, cpu); -} -#endif /* CONFIG_PPC_PSERIES */ +#endif /* CONFIG_PPC_64S_HASH_MMU */ /* The Paca is an array with one entry per processor. Each contains an * lppaca, which contains the information shared between the @@ -213,7 +186,7 @@ void __init initialise_paca(struct paca_struct *new_paca, int cpu) #ifdef CONFIG_PPC_PSERIES new_paca->lppaca_ptr = NULL; #endif -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 new_paca->kernel_pgd = swapper_pg_dir; #endif new_paca->lock_token = 0x8000; @@ -226,18 +199,14 @@ void __init initialise_paca(struct paca_struct *new_paca, int cpu) new_paca->kexec_state = KEXEC_STATE_NONE; new_paca->__current = &init_task; new_paca->data_offset = 0xfeeeeeeeeeeeeeeeULL; -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU new_paca->slb_shadow_ptr = NULL; #endif -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 /* For now -- if we have threads this will be adjusted later */ new_paca->tcd_ptr = &new_paca->tcd; #endif - -#ifdef CONFIG_PPC_PSERIES - new_paca->rtas_args_reentrant = NULL; -#endif } /* Put the paca pointer into r13 and SPRG_PACA */ @@ -246,7 +215,7 @@ void setup_paca(struct paca_struct *new_paca) /* Setup r13 */ local_paca = new_paca; -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 /* On Book3E, initialize the TLB miss exception frames */ mtspr(SPRN_SPRG_TLB_EXFRAME, local_paca->extlb); #else @@ -307,12 +276,9 @@ void __init allocate_paca(int cpu) #ifdef CONFIG_PPC_PSERIES paca->lppaca_ptr = new_lppaca(cpu, limit); #endif -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU paca->slb_shadow_ptr = new_slb_shadow(cpu, limit); #endif -#ifdef CONFIG_PPC_PSERIES - paca->rtas_args_reentrant = new_rtas_args(cpu, limit); -#endif paca_struct_size += sizeof(struct paca_struct); } @@ -328,7 +294,7 @@ void __init free_unused_pacas(void) paca_nr_cpu_ids = nr_cpu_ids; paca_ptrs_size = new_ptrs_size; -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU if (early_radix_enabled()) { /* Ugly fixup, see new_slb_shadow() */ memblock_phys_free(__pa(paca_ptrs[boot_cpuid]->slb_shadow_ptr), @@ -341,22 +307,15 @@ void __init free_unused_pacas(void) paca_ptrs_size + paca_struct_size, nr_cpu_ids); } +#ifdef CONFIG_PPC_64S_HASH_MMU void copy_mm_to_paca(struct mm_struct *mm) { -#ifdef CONFIG_PPC_BOOK3S mm_context_t *context = &mm->context; -#ifdef CONFIG_PPC_MM_SLICES VM_BUG_ON(!mm_ctx_slb_addr_limit(context)); memcpy(&get_paca()->mm_ctx_low_slices_psize, mm_ctx_low_slices(context), LOW_SLICE_ARRAY_SZ); memcpy(&get_paca()->mm_ctx_high_slices_psize, mm_ctx_high_slices(context), TASK_SLICE_ARRAY_SZ(context)); -#else /* CONFIG_PPC_MM_SLICES */ - get_paca()->mm_ctx_user_psize = context->user_psize; - get_paca()->mm_ctx_sllp = context->sllp; -#endif -#else /* !CONFIG_PPC_BOOK3S */ - return; -#endif } +#endif /* CONFIG_PPC_64S_HASH_MMU */ diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 6749905932f4..d67cf79bf5d0 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -30,19 +30,20 @@ #include <linux/vgaarb.h> #include <linux/numa.h> #include <linux/msi.h> +#include <linux/irqdomain.h> #include <asm/processor.h> #include <asm/io.h> -#include <asm/prom.h> #include <asm/pci-bridge.h> #include <asm/byteorder.h> #include <asm/machdep.h> #include <asm/ppc-pci.h> #include <asm/eeh.h> +#include <asm/setup.h> #include "../../../drivers/pci/pci.h" -/* hose_spinlock protects accesses to the the phb_bitmap. */ +/* hose_spinlock protects accesses to the phb_bitmap. */ static DEFINE_SPINLOCK(hose_spinlock); LIST_HEAD(hose_list); @@ -62,28 +63,40 @@ EXPORT_SYMBOL(isa_mem_base); static const struct dma_map_ops *pci_dma_ops; -void set_pci_dma_ops(const struct dma_map_ops *dma_ops) +void __init set_pci_dma_ops(const struct dma_map_ops *dma_ops) { pci_dma_ops = dma_ops; } -/* - * This function should run under locking protection, specifically - * hose_spinlock. - */ static int get_phb_number(struct device_node *dn) { int ret, phb_id = -1; - u32 prop_32; u64 prop; /* * Try fixed PHB numbering first, by checking archs and reading - * the respective device-tree properties. Firstly, try powernv by - * reading "ibm,opal-phbid", only present in OPAL environment. + * the respective device-tree properties. Firstly, try reading + * standard "linux,pci-domain", then try reading "ibm,opal-phbid" + * (only present in powernv OPAL environment), then try device-tree + * alias and as the last try to use lower bits of "reg" property. */ - ret = of_property_read_u64(dn, "ibm,opal-phbid", &prop); + ret = of_get_pci_domain_nr(dn); + if (ret >= 0) { + prop = ret; + ret = 0; + } + if (ret) + ret = of_property_read_u64(dn, "ibm,opal-phbid", &prop); + + if (ret) { + ret = of_alias_get_id(dn, "pci"); + if (ret >= 0) { + prop = ret; + ret = 0; + } + } if (ret) { + u32 prop_32; ret = of_property_read_u32_index(dn, "reg", 1, &prop_32); prop = prop_32; } @@ -91,18 +104,20 @@ static int get_phb_number(struct device_node *dn) if (!ret) phb_id = (int)(prop & (MAX_PHBS - 1)); + spin_lock(&hose_spinlock); + /* We need to be sure to not use the same PHB number twice. */ if ((phb_id >= 0) && !test_and_set_bit(phb_id, phb_bitmap)) - return phb_id; + goto out_unlock; - /* - * If not pseries nor powernv, or if fixed PHB numbering tried to add - * the same PHB number twice, then fallback to dynamic PHB numbering. - */ + /* If everything fails then fallback to dynamic PHB numbering. */ phb_id = find_first_zero_bit(phb_bitmap, MAX_PHBS); BUG_ON(phb_id >= MAX_PHBS); set_bit(phb_id, phb_bitmap); +out_unlock: + spin_unlock(&hose_spinlock); + return phb_id; } @@ -113,11 +128,14 @@ struct pci_controller *pcibios_alloc_controller(struct device_node *dev) phb = zalloc_maybe_bootmem(sizeof(struct pci_controller), GFP_KERNEL); if (phb == NULL) return NULL; - spin_lock(&hose_spinlock); + phb->global_number = get_phb_number(dev); + + spin_lock(&hose_spinlock); list_add_tail(&phb->list_node, &hose_list); spin_unlock(&hose_spinlock); - phb->dn = dev; + + phb->dn = of_node_get(dev); phb->is_dynamic = slab_is_available(); #ifdef CONFIG_PPC64 if (dev) { @@ -140,7 +158,7 @@ void pcibios_free_controller(struct pci_controller *phb) /* Clear bit of phb_bitmap to allow reuse of this PHB number. */ if (phb->global_number < MAX_PHBS) clear_bit(phb->global_number, phb_bitmap); - + of_node_put(phb->dn); list_del(&phb->list_node); spin_unlock(&hose_spinlock); @@ -1087,7 +1105,7 @@ void pcibios_fixup_bus(struct pci_bus *bus) */ pci_read_bridge_bases(bus); - /* Now fixup the bus bus */ + /* Now fixup the bus */ pcibios_setup_bus_self(bus); } EXPORT_SYMBOL(pcibios_fixup_bus); @@ -1688,7 +1706,7 @@ EXPORT_SYMBOL_GPL(pcibios_scan_phb); static void fixup_hide_host_resource_fsl(struct pci_dev *dev) { int i, class = dev->class >> 8; - /* When configured as agent, programing interface = 1 */ + /* When configured as agent, programming interface = 1 */ int prog_if = dev->class & 0xf; if ((class == PCI_CLASS_PROCESSOR_POWERPC || diff --git a/arch/powerpc/kernel/pci-hotplug.c b/arch/powerpc/kernel/pci-hotplug.c index 2fc12198ec07..0fe251c6ac2c 100644 --- a/arch/powerpc/kernel/pci-hotplug.c +++ b/arch/powerpc/kernel/pci-hotplug.c @@ -12,6 +12,7 @@ #include <linux/pci.h> #include <linux/export.h> +#include <linux/of.h> #include <asm/pci-bridge.h> #include <asm/ppc-pci.h> #include <asm/firmware.h> diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c index b49e1060a3bf..855b59892c5c 100644 --- a/arch/powerpc/kernel/pci_32.c +++ b/arch/powerpc/kernel/pci_32.c @@ -21,7 +21,6 @@ #include <asm/processor.h> #include <asm/io.h> -#include <asm/prom.h> #include <asm/sections.h> #include <asm/pci-bridge.h> #include <asm/ppc-pci.h> @@ -37,18 +36,13 @@ int pcibios_assign_bus_offset = 1; EXPORT_SYMBOL(isa_io_base); EXPORT_SYMBOL(pci_dram_offset); -void pcibios_make_OF_bus_map(void); - static void fixup_cpc710_pci64(struct pci_dev* dev); -static u8* pci_to_OF_bus_map; /* By default, we don't re-assign bus numbers. We do this only on * some pmacs */ static int pci_assign_all_buses; -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. */ @@ -68,6 +62,11 @@ fixup_cpc710_pci64(struct pci_dev* dev) } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_CPC710_PCI64, fixup_cpc710_pci64); +#if defined(CONFIG_PPC_PMAC) || defined(CONFIG_PPC_CHRP) + +static u8* pci_to_OF_bus_map; +static int pci_bus_count; + /* * Functions below are used on OpenFirmware machines. */ @@ -109,7 +108,7 @@ make_one_node_map(struct device_node* node, u8 pci_bus) } } -void +static void __init pcibios_make_OF_bus_map(void) { int i; @@ -155,6 +154,7 @@ pcibios_make_OF_bus_map(void) } +#ifdef CONFIG_PPC_PMAC /* * Returns the PCI device matching a given OF node */ @@ -194,7 +194,9 @@ int pci_device_from_OF_node(struct device_node *node, u8 *bus, u8 *devfn) return -ENODEV; } EXPORT_SYMBOL(pci_device_from_OF_node); +#endif +#ifdef CONFIG_PPC_CHRP /* We create the "pci-OF-bus-map" property now so it appears in the * /proc device tree */ @@ -219,6 +221,9 @@ pci_create_OF_bus_map(void) of_node_put(dn); } } +#endif + +#endif /* defined(CONFIG_PPC_PMAC) || defined(CONFIG_PPC_CHRP) */ void pcibios_setup_phb_io_space(struct pci_controller *hose) { @@ -234,23 +239,40 @@ void pcibios_setup_phb_io_space(struct pci_controller *hose) static int __init pcibios_init(void) { struct pci_controller *hose, *tmp; +#ifndef CONFIG_PPC_PCI_BUS_NUM_DOMAIN_DEPENDENT int next_busno = 0; +#endif printk(KERN_INFO "PCI: Probing PCI hardware\n"); +#ifdef CONFIG_PPC_PCI_BUS_NUM_DOMAIN_DEPENDENT + /* + * Enable PCI domains in /proc when PCI bus numbers are not unique + * across all PCI domains to prevent conflicts. And keep PCI domain 0 + * backward compatible in /proc for video cards. + */ + pci_add_flags(PCI_ENABLE_PROC_DOMAINS | PCI_COMPAT_DOMAIN_0); +#endif + if (pci_has_flag(PCI_REASSIGN_ALL_BUS)) pci_assign_all_buses = 1; /* Scan all of the recorded PCI controllers. */ list_for_each_entry_safe(hose, tmp, &hose_list, list_node) { +#ifndef CONFIG_PPC_PCI_BUS_NUM_DOMAIN_DEPENDENT if (pci_assign_all_buses) hose->first_busno = next_busno; +#endif hose->last_busno = 0xff; pcibios_scan_phb(hose); pci_bus_add_devices(hose->bus); +#ifndef CONFIG_PPC_PCI_BUS_NUM_DOMAIN_DEPENDENT if (pci_assign_all_buses || next_busno <= hose->last_busno) next_busno = hose->last_busno + pcibios_assign_bus_offset; +#endif } + +#if defined(CONFIG_PPC_PMAC) || defined(CONFIG_PPC_CHRP) pci_bus_count = next_busno; /* OpenFirmware based machines need a map of OF bus @@ -259,6 +281,7 @@ static int __init pcibios_init(void) */ if (pci_assign_all_buses) pcibios_make_OF_bus_map(); +#endif /* Call common code to handle resource allocation */ pcibios_resource_survey(); diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index 3fb7e572abed..0c7cfb9fab04 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -19,10 +19,10 @@ #include <linux/syscalls.h> #include <linux/irq.h> #include <linux/vmalloc.h> +#include <linux/of.h> #include <asm/processor.h> #include <asm/io.h> -#include <asm/prom.h> #include <asm/pci-bridge.h> #include <asm/byteorder.h> #include <asm/machdep.h> @@ -285,3 +285,14 @@ int pcibus_to_node(struct pci_bus *bus) } EXPORT_SYMBOL(pcibus_to_node); #endif + +#ifdef CONFIG_PPC_PMAC +int pci_device_from_OF_node(struct device_node *np, u8 *bus, u8 *devfn) +{ + if (!PCI_DN(np)) + return -ENODEV; + *bus = PCI_DN(np)->busno; + *devfn = PCI_DN(np)->devfn; + return 0; +} +#endif diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c index 61571ae23953..38561d6a2079 100644 --- a/arch/powerpc/kernel/pci_dn.c +++ b/arch/powerpc/kernel/pci_dn.c @@ -12,9 +12,9 @@ #include <linux/export.h> #include <linux/init.h> #include <linux/gfp.h> +#include <linux/of.h> #include <asm/io.h> -#include <asm/prom.h> #include <asm/pci-bridge.h> #include <asm/ppc-pci.h> #include <asm/firmware.h> @@ -259,7 +259,7 @@ void remove_sriov_vf_pdns(struct pci_dev *pdev) if (edev) { /* * We allocate pci_dn's for the totalvfs count, - * but only only the vfs that were activated + * but only the vfs that were activated * have a configured PE. */ if (edev->pe) @@ -330,6 +330,7 @@ struct pci_dn *pci_add_device_node_info(struct pci_controller *hose, INIT_LIST_HEAD(&pdn->list); parent = of_get_parent(dn); pdn->parent = parent ? PCI_DN(parent) : NULL; + of_node_put(parent); if (pdn->parent) list_add_tail(&pdn->list, &pdn->parent->child_list); diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c index c3024f104765..756043dd06e9 100644 --- a/arch/powerpc/kernel/pci_of_scan.c +++ b/arch/powerpc/kernel/pci_of_scan.c @@ -13,8 +13,8 @@ #include <linux/pci.h> #include <linux/export.h> +#include <linux/of.h> #include <asm/pci-bridge.h> -#include <asm/prom.h> /** * get_int_prop - Decode a u32 from a device tree property @@ -244,7 +244,7 @@ EXPORT_SYMBOL(of_create_pci_dev); * @dev: pci_dev structure for the bridge * * of_scan_bus() calls this routine for each PCI bridge that it finds, and - * this routine in turn call of_scan_bus() recusively to scan for more child + * this routine in turn call of_scan_bus() recursively to scan for more child * devices. */ void of_scan_pci_bridge(struct pci_dev *dev) diff --git a/arch/powerpc/kernel/ppc32.h b/arch/powerpc/kernel/ppc32.h deleted file mode 100644 index 2346f8c7ff2e..000000000000 --- a/arch/powerpc/kernel/ppc32.h +++ /dev/null @@ -1,60 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -#ifndef _PPC64_PPC32_H -#define _PPC64_PPC32_H - -#include <linux/compat.h> -#include <asm/siginfo.h> -#include <asm/signal.h> - -/* - * Data types and macros for providing 32b PowerPC support. - */ - -/* These are here to support 32-bit syscalls on a 64-bit kernel. */ - -struct pt_regs32 { - unsigned int gpr[32]; - unsigned int nip; - unsigned int msr; - unsigned int orig_gpr3; /* Used for restarting system calls */ - unsigned int ctr; - unsigned int link; - unsigned int xer; - unsigned int ccr; - unsigned int mq; /* 601 only (not used at present) */ - unsigned int trap; /* Reason for being here */ - unsigned int dar; /* Fault registers */ - unsigned int dsisr; - unsigned int result; /* Result of a system call */ -}; - -struct sigcontext32 { - unsigned int _unused[4]; - int signal; - compat_uptr_t handler; - unsigned int oldmask; - compat_uptr_t regs; /* 4 byte pointer to the pt_regs32 structure. */ -}; - -struct mcontext32 { - elf_gregset_t32 mc_gregs; - elf_fpregset_t mc_fregs; - unsigned int mc_pad[2]; - elf_vrregset_t32 mc_vregs __attribute__((__aligned__(16))); - elf_vsrreghalf_t32 mc_vsregs __attribute__((__aligned__(16))); -}; - -struct ucontext32 { - unsigned int uc_flags; - unsigned int uc_link; - compat_stack_t uc_stack; - int uc_pad[7]; - compat_uptr_t uc_regs; /* points to uc_mcontext field */ - compat_sigset_t uc_sigmask; /* mask last for extensibility */ - /* glibc has 1024-bit signal masks, ours are 64-bit */ - int uc_maskext[30]; - int uc_pad2[3]; - struct mcontext32 uc_mcontext; -}; - -#endif /* _PPC64_PPC32_H */ diff --git a/arch/powerpc/kernel/proc_powerpc.c b/arch/powerpc/kernel/proc_powerpc.c index 877817471e3c..b109cd7b5d01 100644 --- a/arch/powerpc/kernel/proc_powerpc.c +++ b/arch/powerpc/kernel/proc_powerpc.c @@ -7,12 +7,12 @@ #include <linux/mm.h> #include <linux/proc_fs.h> #include <linux/kernel.h> +#include <linux/of.h> #include <asm/machdep.h> #include <asm/vdso_datapage.h> #include <asm/rtas.h> #include <linux/uaccess.h> -#include <asm/prom.h> #ifdef CONFIG_PPC64 @@ -25,7 +25,7 @@ static ssize_t page_map_read( struct file *file, char __user *buf, size_t nbytes loff_t *ppos) { return simple_read_from_buffer(buf, nbytes, ppos, - PDE_DATA(file_inode(file)), PAGE_SIZE); + pde_data(file_inode(file)), PAGE_SIZE); } static int page_map_mmap( struct file *file, struct vm_area_struct *vma ) @@ -34,7 +34,7 @@ static int page_map_mmap( struct file *file, struct vm_area_struct *vma ) return -EINVAL; remap_pfn_range(vma, vma->vm_start, - __pa(PDE_DATA(file_inode(file))) >> PAGE_SHIFT, + __pa(pde_data(file_inode(file))) >> PAGE_SHIFT, PAGE_SIZE, vma->vm_page_prot); return 0; } diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 406d7ee9e322..67da147fe34d 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -34,10 +34,8 @@ #include <linux/ftrace.h> #include <linux/kernel_stat.h> #include <linux/personality.h> -#include <linux/random.h> #include <linux/hw_breakpoint.h> #include <linux/uaccess.h> -#include <linux/elf-randomize.h> #include <linux/pkeys.h> #include <linux/seq_buf.h> @@ -45,7 +43,6 @@ #include <asm/io.h> #include <asm/processor.h> #include <asm/mmu.h> -#include <asm/prom.h> #include <asm/machdep.h> #include <asm/time.h> #include <asm/runlatch.h> @@ -130,7 +127,7 @@ unsigned long notrace msr_check_and_set(unsigned long bits) newmsr |= MSR_VSX; if (oldmsr != newmsr) - mtmsr_isync(newmsr); + newmsr = mtmsr_isync_irqsafe(newmsr); return newmsr; } @@ -148,7 +145,7 @@ void notrace __msr_check_and_clear(unsigned long bits) newmsr &= ~MSR_VSX; if (oldmsr != newmsr) - mtmsr_isync(newmsr); + mtmsr_isync_irqsafe(newmsr); } EXPORT_SYMBOL(__msr_check_and_clear); @@ -307,7 +304,7 @@ static void __giveup_vsx(struct task_struct *tsk) unsigned long msr = tsk->thread.regs->msr; /* - * We should never be ssetting MSR_VSX without also setting + * We should never be setting MSR_VSX without also setting * MSR_FP and MSR_VEC */ WARN_ON((msr & MSR_VSX) && !((msr & MSR_FP) && (msr & MSR_VEC))); @@ -628,7 +625,7 @@ static void do_break_handler(struct pt_regs *regs) { struct arch_hw_breakpoint null_brk = {0}; struct arch_hw_breakpoint *info; - struct ppc_inst instr = ppc_inst(0); + ppc_inst_t instr = ppc_inst(0); int type = 0; int size = 0; unsigned long ea; @@ -645,7 +642,7 @@ static void do_break_handler(struct pt_regs *regs) return; } - /* Otherwise findout which DAWR caused exception and disable it. */ + /* Otherwise find out which DAWR caused exception and disable it. */ wp_get_instr_detail(regs, &instr, &type, &size, &ea); for (i = 0; i < nr_wp_slots(); i++) { @@ -1156,6 +1153,40 @@ static inline void save_sprs(struct thread_struct *t) #endif } +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE +void kvmppc_save_user_regs(void) +{ + unsigned long usermsr; + + if (!current->thread.regs) + return; + + usermsr = current->thread.regs->msr; + + if (usermsr & MSR_FP) + save_fpu(current); + + if (usermsr & MSR_VEC) + save_altivec(current); + +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (usermsr & MSR_TM) { + current->thread.tm_tfhar = mfspr(SPRN_TFHAR); + current->thread.tm_tfiar = mfspr(SPRN_TFIAR); + current->thread.tm_texasr = mfspr(SPRN_TEXASR); + current->thread.regs->msr &= ~MSR_TM; + } +#endif +} +EXPORT_SYMBOL_GPL(kvmppc_save_user_regs); + +void kvmppc_save_current_sprs(void) +{ + save_sprs(¤t->thread); +} +EXPORT_SYMBOL_GPL(kvmppc_save_current_sprs); +#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */ + static inline void restore_sprs(struct thread_struct *old_thread, struct thread_struct *new_thread) { @@ -1206,7 +1237,7 @@ struct task_struct *__switch_to(struct task_struct *prev, { struct thread_struct *new_thread, *old_thread; struct task_struct *last; -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU struct ppc64_tlb_batch *batch; #endif @@ -1215,7 +1246,7 @@ struct task_struct *__switch_to(struct task_struct *prev, WARN_ON(!irqs_disabled()); -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU batch = this_cpu_ptr(&ppc64_tlb_batch); if (batch->active) { current_thread_info()->local_flags |= _TLF_LAZY_MMU; @@ -1281,9 +1312,9 @@ struct task_struct *__switch_to(struct task_struct *prev, set_return_regs_changed(); /* _switch changes stack (and regs) */ -#ifdef CONFIG_PPC32 - kuap_assert_locked(); -#endif + if (!IS_ENABLED(CONFIG_PPC_BOOK3S_64)) + kuap_assert_locked(); + last = _switch(old_thread, new_thread); /* @@ -1294,6 +1325,7 @@ struct task_struct *__switch_to(struct task_struct *prev, */ #ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU /* * This applies to a process that was context switched while inside * arch_enter_lazy_mmu_mode(), to re-activate the batch that was @@ -1305,6 +1337,7 @@ struct task_struct *__switch_to(struct task_struct *prev, batch = this_cpu_ptr(&ppc64_tlb_batch); batch->active = 1; } +#endif /* * Math facilities are masked out of the child MSR in copy_thread. @@ -1622,11 +1655,6 @@ EXPORT_SYMBOL_GPL(set_thread_tidr); #endif /* CONFIG_PPC64 */ -void -release_thread(struct task_struct *t) -{ -} - /* * this gets called so that we can store coprocessor state into memory and * copy the current task into the new thread. @@ -1655,7 +1683,7 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) static void setup_ksp_vsid(struct task_struct *p, unsigned long sp) { -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU unsigned long sp_vsid; unsigned long llp = mmu_psize_defs[mmu_linear_psize].sllp; @@ -1680,10 +1708,11 @@ static void setup_ksp_vsid(struct task_struct *p, unsigned long sp) /* * Copy architecture-specific thread state */ -int copy_thread(unsigned long clone_flags, unsigned long usp, - unsigned long kthread_arg, struct task_struct *p, - unsigned long tls) +int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { + unsigned long clone_flags = args->flags; + unsigned long usp = args->stack; + unsigned long tls = args->tls; struct pt_regs *childregs, *kregs; extern void ret_from_fork(void); extern void ret_from_fork_scv(void); @@ -1700,18 +1729,18 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, /* Copy registers */ sp -= sizeof(struct pt_regs); childregs = (struct pt_regs *) sp; - if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { + if (unlikely(args->fn)) { /* kernel thread */ memset(childregs, 0, sizeof(struct pt_regs)); childregs->gpr[1] = sp + sizeof(struct pt_regs); /* function */ - if (usp) - childregs->gpr[14] = ppc_function_entry((void *)usp); + if (args->fn) + childregs->gpr[14] = ppc_function_entry((void *)args->fn); #ifdef CONFIG_PPC64 clear_tsk_thread_flag(p, TIF_32BIT); childregs->softe = IRQS_ENABLED; #endif - childregs->gpr[15] = kthread_arg; + childregs->gpr[15] = (unsigned long)args->fn_arg; p->thread.regs = NULL; /* no user register state */ ti->flags |= _TIF_RESTOREALL; f = ret_from_kernel_thread; @@ -1767,6 +1796,9 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, #if defined(CONFIG_PPC_BOOK3S_32) && defined(CONFIG_PPC_KUAP) p->thread.kuap = KUAP_NONE; #endif +#if defined(CONFIG_BOOKE_OR_40x) && defined(CONFIG_PPC_KUAP) + p->thread.pid = MMU_NO_CONTEXT; +#endif setup_ksp_vsid(p, sp); @@ -1818,7 +1850,7 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp) tm_reclaim_current(0); #endif - memset(regs->gpr, 0, sizeof(regs->gpr)); + memset(®s->gpr[1], 0, sizeof(regs->gpr) - sizeof(regs->gpr[0])); regs->ctr = 0; regs->link = 0; regs->xer = 0; @@ -2121,12 +2153,12 @@ static unsigned long ___get_wchan(struct task_struct *p) return 0; do { - sp = *(unsigned long *)sp; + sp = READ_ONCE_NOCHECK(*(unsigned long *)sp); if (!validate_sp(sp, p, STACK_FRAME_OVERHEAD) || task_is_running(p)) return 0; if (count > 0) { - ip = ((unsigned long *)sp)[STACK_FRAME_LR_SAVE]; + ip = READ_ONCE_NOCHECK(((unsigned long *)sp)[STACK_FRAME_LR_SAVE]); if (!in_sched_functions(ip)) return ip; } @@ -2271,46 +2303,6 @@ void notrace __ppc64_runlatch_off(void) unsigned long arch_align_stack(unsigned long sp) { if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space) - sp -= get_random_int() & ~PAGE_MASK; + sp -= prandom_u32_max(PAGE_SIZE); return sp & ~0xf; } - -static inline unsigned long brk_rnd(void) -{ - unsigned long rnd = 0; - - /* 8MB for 32bit, 1GB for 64bit */ - if (is_32bit_task()) - rnd = (get_random_long() % (1UL<<(23-PAGE_SHIFT))); - else - rnd = (get_random_long() % (1UL<<(30-PAGE_SHIFT))); - - return rnd << PAGE_SHIFT; -} - -unsigned long arch_randomize_brk(struct mm_struct *mm) -{ - unsigned long base = mm->brk; - unsigned long ret; - -#ifdef CONFIG_PPC_BOOK3S_64 - /* - * If we are using 1TB segments and we are allowed to randomise - * the heap, we can put it above 1TB so it is backed by a 1TB - * segment. Otherwise the heap will be in the bottom 1TB - * which always uses 256MB segments and this may result in a - * performance penalty. We don't need to worry about radix. For - * radix, mmu_highuser_ssize remains unchanged from 256MB. - */ - if (!is_32bit_task() && (mmu_highuser_ssize == MMU_SEGSIZE_1T)) - base = max_t(unsigned long, mm->brk, 1UL << SID_SHIFT_1T); -#endif - - ret = PAGE_ALIGN(base + brk_rnd()); - - if (ret < mm->brk) - return mm->brk; - - return ret; -} - diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 2e67588f6f6e..1eed87d954ba 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -30,8 +30,8 @@ #include <linux/libfdt.h> #include <linux/cpu.h> #include <linux/pgtable.h> +#include <linux/seq_buf.h> -#include <asm/prom.h> #include <asm/rtas.h> #include <asm/page.h> #include <asm/processor.h> @@ -45,7 +45,7 @@ #include <asm/iommu.h> #include <asm/btext.h> #include <asm/sections.h> -#include <asm/machdep.h> +#include <asm/setup.h> #include <asm/pci-bridge.h> #include <asm/kexec.h> #include <asm/opal.h> @@ -55,6 +55,7 @@ #include <asm/dt_cpu_ftrs.h> #include <asm/drmem.h> #include <asm/ultravisor.h> +#include <asm/prom.h> #include <mm/mmu_decl.h> @@ -137,7 +138,7 @@ static void __init move_device_tree(void) } /* - * ibm,pa-features is a per-cpu property that contains a string of + * ibm,pa/pi-features is a per-cpu property that contains a string of * attribute descriptors, each of which has a 2 byte header plus up * to 254 bytes worth of processor attribute bits. First header * byte specifies the number of bytes following the header. @@ -149,15 +150,17 @@ static void __init move_device_tree(void) * is supported/not supported. Note that the bit numbers are * big-endian to match the definition in PAPR. */ -static struct ibm_pa_feature { +struct ibm_feature { unsigned long cpu_features; /* CPU_FTR_xxx bit */ unsigned long mmu_features; /* MMU_FTR_xxx bit */ unsigned int cpu_user_ftrs; /* PPC_FEATURE_xxx bit */ unsigned int cpu_user_ftrs2; /* PPC_FEATURE2_xxx bit */ - unsigned char pabyte; /* byte number in ibm,pa-features */ + unsigned char pabyte; /* byte number in ibm,pa/pi-features */ unsigned char pabit; /* bit number (big-endian) */ unsigned char invert; /* if 1, pa bit set => clear feature */ -} ibm_pa_features[] __initdata = { +}; + +static struct ibm_feature ibm_pa_features[] __initdata = { { .pabyte = 0, .pabit = 0, .cpu_user_ftrs = PPC_FEATURE_HAS_MMU }, { .pabyte = 0, .pabit = 1, .cpu_user_ftrs = PPC_FEATURE_HAS_FPU }, { .pabyte = 0, .pabit = 3, .cpu_features = CPU_FTR_CTRL }, @@ -179,9 +182,19 @@ static struct ibm_pa_feature { { .pabyte = 64, .pabit = 0, .cpu_features = CPU_FTR_DAWR1 }, }; +/* + * ibm,pi-features property provides the support of processor specific + * options not described in ibm,pa-features. Right now use byte 0, bit 3 + * which indicates the occurrence of DSI interrupt when the paste operation + * on the suspended NX window. + */ +static struct ibm_feature ibm_pi_features[] __initdata = { + { .pabyte = 0, .pabit = 3, .mmu_features = MMU_FTR_NX_DSI }, +}; + static void __init scan_features(unsigned long node, const unsigned char *ftrs, unsigned long tablelen, - struct ibm_pa_feature *fp, + struct ibm_feature *fp, unsigned long ft_size) { unsigned long i, len, bit; @@ -218,20 +231,21 @@ static void __init scan_features(unsigned long node, const unsigned char *ftrs, } } -static void __init check_cpu_pa_features(unsigned long node) +static void __init check_cpu_features(unsigned long node, char *name, + struct ibm_feature *fp, + unsigned long size) { const unsigned char *pa_ftrs; int tablelen; - pa_ftrs = of_get_flat_dt_prop(node, "ibm,pa-features", &tablelen); + pa_ftrs = of_get_flat_dt_prop(node, name, &tablelen); if (pa_ftrs == NULL) return; - scan_features(node, pa_ftrs, tablelen, - ibm_pa_features, ARRAY_SIZE(ibm_pa_features)); + scan_features(node, pa_ftrs, tablelen, fp, size); } -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU static void __init init_mmu_slb_size(unsigned long node) { const __be32 *slb_size_ptr; @@ -352,6 +366,9 @@ static int __init early_init_dt_scan_cpus(unsigned long node, be32_to_cpu(intserv[found_thread])); boot_cpuid = found; + // Pass the boot CPU's hard CPU id back to our caller + *((u32 *)data) = be32_to_cpu(intserv[found_thread]); + /* * PAPR defines "logical" PVR values for cpus that * meet various levels of the architecture: @@ -373,11 +390,16 @@ static int __init early_init_dt_scan_cpus(unsigned long node, */ if (!dt_cpu_ftrs_in_use()) { prop = of_get_flat_dt_prop(node, "cpu-version", NULL); - if (prop && (be32_to_cpup(prop) & 0xff000000) == 0x0f000000) + if (prop && (be32_to_cpup(prop) & 0xff000000) == 0x0f000000) { identify_cpu(0, be32_to_cpup(prop)); + seq_buf_printf(&ppc_hw_desc, "0x%04x ", be32_to_cpup(prop)); + } check_cpu_feature_properties(node); - check_cpu_pa_features(node); + check_cpu_features(node, "ibm,pa-features", ibm_pa_features, + ARRAY_SIZE(ibm_pa_features)); + check_cpu_features(node, "ibm,pi-features", ibm_pi_features, + ARRAY_SIZE(ibm_pi_features)); } identical_pvr_fixup(node); @@ -388,9 +410,7 @@ static int __init early_init_dt_scan_cpus(unsigned long node, cur_cpu_spec->cpu_features &= ~CPU_FTR_SMT; else if (!dt_cpu_ftrs_in_use()) cur_cpu_spec->cpu_features |= CPU_FTR_SMT; - allocate_paca(boot_cpuid); #endif - set_hard_smp_processor_id(found, be32_to_cpu(intserv[found_thread])); return 0; } @@ -402,7 +422,7 @@ static int __init early_init_dt_scan_chosen_ppc(unsigned long node, const unsigned long *lprop; /* All these set by kernel, so no need to convert endian */ /* Use common scan routine to determine if this is the chosen node */ - if (early_init_dt_scan_chosen(node, uname, depth, data) == 0) + if (early_init_dt_scan_chosen(data) < 0) return 0; #ifdef CONFIG_PPC64 @@ -447,7 +467,7 @@ static int __init early_init_dt_scan_chosen_ppc(unsigned long node, */ #ifdef CONFIG_SPARSEMEM -static bool validate_mem_limit(u64 base, u64 *size) +static bool __init validate_mem_limit(u64 base, u64 *size) { u64 max_mem = 1UL << (MAX_PHYSMEM_BITS); @@ -458,7 +478,7 @@ static bool validate_mem_limit(u64 base, u64 *size) return true; } #else -static bool validate_mem_limit(u64 base, u64 *size) +static bool __init validate_mem_limit(u64 base, u64 *size) { return true; } @@ -532,19 +552,18 @@ static int __init early_init_drmem_lmb(struct drmem_lmb *lmb, } #endif /* CONFIG_PPC_PSERIES */ -static int __init early_init_dt_scan_memory_ppc(unsigned long node, - const char *uname, - int depth, void *data) +static int __init early_init_dt_scan_memory_ppc(void) { #ifdef CONFIG_PPC_PSERIES - if (depth == 1 && - strcmp(uname, "ibm,dynamic-reconfiguration-memory") == 0) { + const void *fdt = initial_boot_params; + int node = fdt_path_offset(fdt, "/ibm,dynamic-reconfiguration-memory"); + + if (node > 0) walk_drmem_lmbs_early(node, NULL, early_init_drmem_lmb); - return 0; - } + #endif - - return early_init_dt_scan_memory(node, uname, depth, data); + + return early_init_dt_scan_memory(); } /* @@ -696,6 +715,23 @@ static void __init tm_init(void) static void tm_init(void) { } #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ +static int __init +early_init_dt_scan_model(unsigned long node, const char *uname, + int depth, void *data) +{ + const char *prop; + + if (depth != 0) + return 0; + + prop = of_get_flat_dt_prop(node, "model", NULL); + if (prop) + seq_buf_printf(&ppc_hw_desc, "%s ", prop); + + /* break now */ + return 1; +} + #ifdef CONFIG_PPC64 static void __init save_fscr_to_task(void) { @@ -715,6 +751,7 @@ static inline void save_fscr_to_task(void) {} void __init early_init_devtree(void *params) { + u32 boot_cpu_hwid; phys_addr_t limit; DBG(" -> early_init_devtree(%px)\n", params); @@ -723,6 +760,8 @@ void __init early_init_devtree(void *params) if (!early_init_dt_verify(params)) panic("BUG: Failed verifying flat device tree, bad version?"); + of_scan_flat_dt(early_init_dt_scan_model, NULL); + #ifdef CONFIG_PPC_RTAS /* Some machines might need RTAS info for debugging, grab it now. */ of_scan_flat_dt(early_init_dt_scan_rtas, NULL); @@ -748,9 +787,16 @@ void __init early_init_devtree(void *params) of_scan_flat_dt(early_init_dt_scan_chosen_ppc, boot_command_line); /* Scan memory nodes and rebuild MEMBLOCKs */ - of_scan_flat_dt(early_init_dt_scan_root, NULL); - of_scan_flat_dt(early_init_dt_scan_memory_ppc, NULL); + early_init_dt_scan_root(); + early_init_dt_scan_memory_ppc(); + /* + * As generic code authors expect to be able to use static keys + * in early_param() handlers, we initialize the static keys just + * before parsing early params (it's fine to call jump_label_init() + * more than once). + */ + jump_label_init(); parse_early_param(); /* make sure we've parsed cmdline for mem= before this */ @@ -791,16 +837,17 @@ void __init early_init_devtree(void *params) * FIXME .. and the initrd too? */ move_device_tree(); - allocate_paca_ptrs(); - DBG("Scanning CPUs ...\n"); dt_cpu_ftrs_scan(); + // We can now add the CPU name & PVR to the hardware description + seq_buf_printf(&ppc_hw_desc, "%s 0x%04lx ", cur_cpu_spec->cpu_name, mfspr(SPRN_PVR)); + /* Retrieve CPU related informations from the flat tree * (altivec support, boot CPU ID, ...) */ - of_scan_flat_dt(early_init_dt_scan_cpus, NULL); + of_scan_flat_dt(early_init_dt_scan_cpus, &boot_cpu_hwid); if (boot_cpuid < 0) { printk("Failed to identify boot CPU !\n"); BUG(); @@ -817,6 +864,11 @@ void __init early_init_devtree(void *params) mmu_early_init_devtree(); + // NB. paca is not installed until later in early_setup() + allocate_paca_ptrs(); + allocate_paca(boot_cpuid); + set_hard_smp_processor_id(boot_cpuid, boot_cpu_hwid); + #ifdef CONFIG_PPC_POWERNV /* Scan and build the list of machine check recoverable ranges */ of_scan_flat_dt(early_init_dt_scan_recoverable_ranges, NULL); @@ -857,8 +909,8 @@ void __init early_get_first_memblock_info(void *params, phys_addr_t *size) * mess the memblock. */ add_mem_to_memblock = 0; - of_scan_flat_dt(early_init_dt_scan_root, NULL); - of_scan_flat_dt(early_init_dt_scan_memory_ppc, NULL); + early_init_dt_scan_root(); + early_init_dt_scan_memory_ppc(); add_mem_to_memblock = 1; if (size) diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 18b04b08b983..d464ba412084 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -28,6 +28,8 @@ #include <linux/bitops.h> #include <linux/pgtable.h> #include <linux/printk.h> +#include <linux/of.h> +#include <linux/of_fdt.h> #include <asm/prom.h> #include <asm/rtas.h> #include <asm/page.h> @@ -40,7 +42,7 @@ #include <asm/iommu.h> #include <asm/btext.h> #include <asm/sections.h> -#include <asm/machdep.h> +#include <asm/setup.h> #include <asm/asm-prototypes.h> #include <asm/ultravisor-api.h> @@ -94,12 +96,6 @@ static int of_workarounds __prombss; #define OF_WA_CLAIM 1 /* do phys/virt claim separately, then map */ #define OF_WA_LONGTRAIL 2 /* work around longtrail bugs */ -#define PROM_BUG() do { \ - prom_printf("kernel BUG at %s line 0x%x!\n", \ - __FILE__, __LINE__); \ - __builtin_trap(); \ -} while (0) - #ifdef DEBUG_PROM #define prom_debug(x...) prom_printf(x) #else @@ -672,7 +668,7 @@ static inline int __init prom_getproplen(phandle node, const char *pname) return call_prom("getproplen", 2, 1, node, ADDR(pname)); } -static void add_string(char **str, const char *q) +static void __init add_string(char **str, const char *q) { char *p = *str; @@ -682,7 +678,7 @@ static void add_string(char **str, const char *q) *str = p; } -static char *tohex(unsigned int x) +static char *__init tohex(unsigned int x) { static const char digits[] __initconst = "0123456789abcdef"; static char result[9] __prombss; @@ -728,7 +724,7 @@ static int __init prom_setprop(phandle node, const char *nodename, #define prom_islower(c) ('a' <= (c) && (c) <= 'z') #define prom_toupper(c) (prom_islower(c) ? ((c) - 'a' + 'A') : (c)) -static unsigned long prom_strtoul(const char *cp, const char **endp) +static unsigned long __init prom_strtoul(const char *cp, const char **endp) { unsigned long result = 0, base = 10, value; @@ -753,7 +749,7 @@ static unsigned long prom_strtoul(const char *cp, const char **endp) return result; } -static unsigned long prom_memparse(const char *ptr, const char **retptr) +static unsigned long __init prom_memparse(const char *ptr, const char **retptr) { unsigned long ret = prom_strtoul(ptr, retptr); int shift = 0; @@ -1786,7 +1782,7 @@ static void __init prom_close_stdin(void) } #ifdef CONFIG_PPC_SVM -static int prom_rtas_hcall(uint64_t args) +static int __init prom_rtas_hcall(uint64_t args) { register uint64_t arg1 asm("r3") = H_RTAS; register uint64_t arg2 asm("r4") = args; @@ -2300,7 +2296,7 @@ static void __init prom_init_stdout(void) static int __init prom_find_machine_type(void) { - char compat[256]; + static char compat[256] __prombss; int len, i = 0; #ifdef CONFIG_PPC64 phandle rtas; @@ -2991,7 +2987,7 @@ static void __init fixup_device_tree_efika_add_phy(void) /* Check if the phy-handle property exists - bail if it does */ rv = prom_getprop(node, "phy-handle", prop, sizeof(prop)); - if (!rv) + if (rv <= 0) return; /* @@ -3248,7 +3244,7 @@ static void __init prom_check_initrd(unsigned long r3, unsigned long r4) /* * Perform the Enter Secure Mode ultracall. */ -static int enter_secure_mode(unsigned long kbase, unsigned long fdt) +static int __init enter_secure_mode(unsigned long kbase, unsigned long fdt) { register unsigned long r3 asm("r3") = UV_ESM; register unsigned long r4 asm("r4") = kbase; @@ -3416,7 +3412,7 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4, * * PowerMacs use a different mechanism to spin CPUs * - * (This must be done after instanciating RTAS) + * (This must be done after instantiating RTAS) */ if (of_platform != PLATFORM_POWERMAC) prom_hold_cpus(); diff --git a/arch/powerpc/kernel/prom_init_check.sh b/arch/powerpc/kernel/prom_init_check.sh index b183ab9c5107..311890d71c4c 100644 --- a/arch/powerpc/kernel/prom_init_check.sh +++ b/arch/powerpc/kernel/prom_init_check.sh @@ -13,7 +13,7 @@ # If you really need to reference something from prom_init.o add # it to the list below: -grep "^CONFIG_KASAN=y$" .config >/dev/null +grep "^CONFIG_KASAN=y$" ${KCONFIG_CONFIG} >/dev/null if [ $? -eq 0 ] then MEM_FUNCS="__memcpy __memset" @@ -26,8 +26,7 @@ _end enter_prom $MEM_FUNCS reloc_offset __secondary_hold __secondary_hold_acknowledge __secondary_hold_spinloop __start logo_linux_clut224 btext_prepare_BAT reloc_got2 kernstart_addr memstart_addr linux_banner _stext -__prom_init_toc_start __prom_init_toc_end btext_setup_display TOC. -relocate" +btext_setup_display TOC. relocate" NM="$1" OBJ="$2" diff --git a/arch/powerpc/kernel/ptrace/ptrace-fpu.c b/arch/powerpc/kernel/ptrace/ptrace-fpu.c index 5dca19361316..09c49632bfe5 100644 --- a/arch/powerpc/kernel/ptrace/ptrace-fpu.c +++ b/arch/powerpc/kernel/ptrace/ptrace-fpu.c @@ -17,9 +17,13 @@ int ptrace_get_fpr(struct task_struct *child, int index, unsigned long *data) #ifdef CONFIG_PPC_FPU_REGS flush_fp_to_thread(child); - if (fpidx < (PT_FPSCR - PT_FPR0)) - memcpy(data, &child->thread.TS_FPR(fpidx), sizeof(long)); - else + if (fpidx < (PT_FPSCR - PT_FPR0)) { + if (IS_ENABLED(CONFIG_PPC32)) + // On 32-bit the index we are passed refers to 32-bit words + *data = ((u32 *)child->thread.fp_state.fpr)[fpidx]; + else + memcpy(data, &child->thread.TS_FPR(fpidx), sizeof(long)); + } else *data = child->thread.fp_state.fpscr; #else *data = 0; @@ -39,9 +43,13 @@ int ptrace_put_fpr(struct task_struct *child, int index, unsigned long data) #ifdef CONFIG_PPC_FPU_REGS flush_fp_to_thread(child); - if (fpidx < (PT_FPSCR - PT_FPR0)) - memcpy(&child->thread.TS_FPR(fpidx), &data, sizeof(long)); - else + if (fpidx < (PT_FPSCR - PT_FPR0)) { + if (IS_ENABLED(CONFIG_PPC32)) + // On 32-bit the index we are passed refers to 32-bit words + ((u32 *)child->thread.fp_state.fpr)[fpidx] = data; + else + memcpy(&child->thread.TS_FPR(fpidx), &data, sizeof(long)); + } else child->thread.fp_state.fpscr = data; #endif diff --git a/arch/powerpc/kernel/ptrace/ptrace-view.c b/arch/powerpc/kernel/ptrace/ptrace-view.c index b8be1d6668b5..076d867412c7 100644 --- a/arch/powerpc/kernel/ptrace/ptrace-view.c +++ b/arch/powerpc/kernel/ptrace/ptrace-view.c @@ -174,7 +174,7 @@ int ptrace_get_reg(struct task_struct *task, int regno, unsigned long *data) /* * softe copies paca->irq_soft_mask variable state. Since irq_soft_mask is - * no more used as a flag, lets force usr to alway see the softe value as 1 + * no more used as a flag, lets force usr to always see the softe value as 1 * which means interrupts are not soft disabled. */ if (IS_ENABLED(CONFIG_PPC64) && regno == PT_SOFTE) { @@ -841,7 +841,7 @@ static const struct user_regset_view user_ppc_compat_view = { const struct user_regset_view *task_user_regset_view(struct task_struct *task) { - if (IS_ENABLED(CONFIG_PPC64) && test_tsk_thread_flag(task, TIF_32BIT)) + if (IS_ENABLED(CONFIG_COMPAT) && is_tsk_32bit_task(task)) return &user_ppc_compat_view; return &user_ppc_native_view; } diff --git a/arch/powerpc/kernel/ptrace/ptrace-vsx.c b/arch/powerpc/kernel/ptrace/ptrace-vsx.c index 1da4303128ef..7df08004c47d 100644 --- a/arch/powerpc/kernel/ptrace/ptrace-vsx.c +++ b/arch/powerpc/kernel/ptrace/ptrace-vsx.c @@ -71,7 +71,7 @@ int fpr_set(struct task_struct *target, const struct user_regset *regset, } /* - * Currently to set and and get all the vsx state, you need to call + * Currently to set and get all the vsx state, you need to call * the fp and VMX calls as well. This only get/sets the lower 32 * 128bit VSX registers. */ diff --git a/arch/powerpc/kernel/ptrace/ptrace.c b/arch/powerpc/kernel/ptrace/ptrace.c index 7c7093c17c45..5d7a72b41ae7 100644 --- a/arch/powerpc/kernel/ptrace/ptrace.c +++ b/arch/powerpc/kernel/ptrace/ptrace.c @@ -16,13 +16,12 @@ */ #include <linux/regset.h> -#include <linux/tracehook.h> +#include <linux/ptrace.h> #include <linux/audit.h> #include <linux/context_tracking.h> #include <linux/syscalls.h> #include <asm/switch_to.h> -#include <asm/asm-prototypes.h> #include <asm/debug.h> #define CREATE_TRACE_POINTS @@ -260,16 +259,15 @@ long do_syscall_trace_enter(struct pt_regs *regs) { u32 flags; - flags = READ_ONCE(current_thread_info()->flags) & - (_TIF_SYSCALL_EMU | _TIF_SYSCALL_TRACE); + flags = read_thread_flags() & (_TIF_SYSCALL_EMU | _TIF_SYSCALL_TRACE); if (flags) { - int rc = tracehook_report_syscall_entry(regs); + int rc = ptrace_report_syscall_entry(regs); if (unlikely(flags & _TIF_SYSCALL_EMU)) { /* * A nonzero return code from - * tracehook_report_syscall_entry() tells us to prevent + * ptrace_report_syscall_entry() tells us to prevent * the syscall execution, but we are not going to * execute it anyway. * @@ -335,7 +333,7 @@ void do_syscall_trace_leave(struct pt_regs *regs) step = test_thread_flag(TIF_SINGLESTEP); if (step || test_thread_flag(TIF_SYSCALL_TRACE)) - tracehook_report_syscall_exit(regs, step); + ptrace_report_syscall_exit(regs, step); } void __init pt_regs_check(void); @@ -446,4 +444,7 @@ void __init pt_regs_check(void) * real registers. */ BUILD_BUG_ON(PT_DSCR < sizeof(struct user_pt_regs) / sizeof(unsigned long)); + + // ptrace_get/put_fpr() rely on PPC32 and VSX being incompatible + BUILD_BUG_ON(IS_ENABLED(CONFIG_PPC32) && IS_ENABLED(CONFIG_VSX)); } diff --git a/arch/powerpc/kernel/reloc_64.S b/arch/powerpc/kernel/reloc_64.S index 02d4719bf43a..efd52f2e7033 100644 --- a/arch/powerpc/kernel/reloc_64.S +++ b/arch/powerpc/kernel/reloc_64.S @@ -8,8 +8,10 @@ #include <asm/ppc_asm.h> RELA = 7 -RELACOUNT = 0x6ffffff9 +RELASZ = 8 +RELAENT = 9 R_PPC64_RELATIVE = 22 +R_PPC64_UADDR64 = 43 /* * r3 = desired final address of kernel @@ -25,29 +27,38 @@ _GLOBAL(relocate) 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 */ + ld r4,(p_sym - 0b)(r12) + add r4,r4,r12 /* r4 has runtime addr of .dynsym */ /* - * Scan the dynamic section for the RELA and RELACOUNT entries. + * Scan the dynamic section for the RELA, RELASZ and RELAENT entries. */ li r7,0 li r8,0 -1: ld r6,0(r11) /* get tag */ +.Ltags: + ld r6,0(r11) /* get tag */ cmpdi r6,0 - beq 4f /* end of list */ + beq .Lend_of_list /* 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 + b 4f +2: cmpdi r6,RELASZ 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 */ + ld r8,8(r11) /* get RELASZ value in r8 */ + b 4f +3: cmpdi r6,RELAENT + bne 4f + ld r12,8(r11) /* get RELAENT value in r12 */ +4: addi r11,r11,16 + b .Ltags +.Lend_of_list: + cmpdi r7,0 /* check we have RELA, RELASZ, RELAENT */ cmpdi cr1,r8,0 - beq 6f - beq cr1,6f + beq .Lout + beq cr1,.Lout + cmpdi r12,0 + beq .Lout /* * Work out linktime address of _stext and hence the @@ -62,23 +73,39 @@ _GLOBAL(relocate) /* * Run through the list of relocations and process the - * R_PPC64_RELATIVE ones. + * R_PPC64_RELATIVE and R_PPC64_UADDR64 ones. */ + divd r8,r8,r12 /* RELASZ / RELAENT */ mtctr r8 -5: ld r0,8(9) /* ELF64_R_TYPE(reloc->r_info) */ +.Lrels: ld r0,8(r9) /* ELF64_R_TYPE(reloc->r_info) */ cmpdi r0,R_PPC64_RELATIVE - bne 6f + bne .Luaddr64 ld r6,0(r9) /* reloc->r_offset */ ld r0,16(r9) /* reloc->r_addend */ + b .Lstore +.Luaddr64: + srdi r5,r0,32 /* ELF64_R_SYM(reloc->r_info) */ + clrldi r0,r0,32 + cmpdi r0,R_PPC64_UADDR64 + bne .Lnext + ld r6,0(r9) + ld r0,16(r9) + mulli r5,r5,24 /* 24 == sizeof(elf64_sym) */ + add r5,r5,r4 /* elf64_sym[ELF64_R_SYM] */ + ld r5,8(r5) + add r0,r0,r5 +.Lstore: add r0,r0,r3 stdx r0,r7,r6 - addi r9,r9,24 - bdnz 5b - -6: blr +.Lnext: + add r9,r9,r12 + bdnz .Lrels +.Lout: + blr .balign 8 p_dyn: .8byte __dynamic_start - 0b p_rela: .8byte __rela_dyn_start - 0b +p_sym: .8byte __dynamic_symtab - 0b p_st: .8byte _stext - 0b diff --git a/arch/powerpc/kernel/rtas-proc.c b/arch/powerpc/kernel/rtas-proc.c index 6857a5b0a1c3..081b2b741a8c 100644 --- a/arch/powerpc/kernel/rtas-proc.c +++ b/arch/powerpc/kernel/rtas-proc.c @@ -24,11 +24,11 @@ #include <linux/seq_file.h> #include <linux/bitops.h> #include <linux/rtc.h> +#include <linux/of.h> #include <linux/uaccess.h> #include <asm/processor.h> #include <asm/io.h> -#include <asm/prom.h> #include <asm/rtas.h> #include <asm/machdep.h> /* for ppc_md */ #include <asm/time.h> @@ -259,7 +259,6 @@ __initcall(proc_rtas_init); static int parse_number(const char __user *p, size_t count, u64 *val) { char buf[40]; - char *end; if (count > 39) return -EINVAL; @@ -269,11 +268,7 @@ static int parse_number(const char __user *p, size_t count, u64 *val) buf[count] = 0; - *val = simple_strtoull(buf, &end, 10); - if (*end && *end != '\n') - return -EINVAL; - - return 0; + return kstrtoull(buf, 10, val); } /* ****************************************************************** */ diff --git a/arch/powerpc/kernel/rtas-rtc.c b/arch/powerpc/kernel/rtas-rtc.c index 33c07c8af6c8..5a31d1829bca 100644 --- a/arch/powerpc/kernel/rtas-rtc.c +++ b/arch/powerpc/kernel/rtas-rtc.c @@ -6,7 +6,6 @@ #include <linux/rtc.h> #include <linux/delay.h> #include <linux/ratelimit.h> -#include <asm/prom.h> #include <asm/rtas.h> #include <asm/time.h> diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index ff80bbad22a5..e847f9b1c5b9 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -23,10 +23,12 @@ #include <linux/memblock.h> #include <linux/slab.h> #include <linux/reboot.h> +#include <linux/security.h> #include <linux/syscalls.h> +#include <linux/of.h> +#include <linux/of_fdt.h> #include <asm/interrupt.h> -#include <asm/prom.h> #include <asm/rtas.h> #include <asm/hvcall.h> #include <asm/machdep.h> @@ -42,13 +44,25 @@ #include <asm/time.h> #include <asm/mmu.h> #include <asm/topology.h> -#include <asm/paca.h> /* This is here deliberately so it's only used in this file */ void enter_rtas(unsigned long); static inline void do_enter_rtas(unsigned long args) { + unsigned long msr; + + /* + * Make sure MSR[RI] is currently enabled as it will be forced later + * in enter_rtas. + */ + msr = mfmsr(); + BUG_ON(!(msr & MSR_RI)); + + BUG_ON(!irqs_disabled()); + + hard_irq_disable(); /* Ensure MSR[EE] is disabled on PPC64 */ + enter_rtas(args); srr_regs_clobbered(); /* rtas uses SRRs, invalidate */ @@ -450,6 +464,9 @@ void rtas_call_unlocked(struct rtas_args *args, int token, int nargs, int nret, va_end(list); } +static int ibm_open_errinjct_token; +static int ibm_errinjct_token; + int rtas_call(int token, int nargs, int nret, int *outputs, ...) { va_list list; @@ -462,6 +479,21 @@ int rtas_call(int token, int nargs, int nret, int *outputs, ...) if (!rtas.entry || token == RTAS_UNKNOWN_SERVICE) return -1; + if (token == ibm_open_errinjct_token || token == ibm_errinjct_token) { + /* + * It would be nicer to not discard the error value + * from security_locked_down(), but callers expect an + * RTAS status, not an errno. + */ + if (security_locked_down(LOCKDOWN_RTAS_ERROR_INJECTION)) + return -1; + } + + if ((mfmsr() & (MSR_IR|MSR_DR)) != (MSR_IR|MSR_DR)) { + WARN_ON_ONCE(1); + return -1; + } + s = lock_rtas(); /* We use the global rtas args buffer */ @@ -492,8 +524,25 @@ int rtas_call(int token, int nargs, int nret, int *outputs, ...) } EXPORT_SYMBOL(rtas_call); -/* For RTAS_BUSY (-2), delay for 1 millisecond. For an extended busy status - * code of 990n, perform the hinted delay of 10^n (last digit) milliseconds. +/** + * rtas_busy_delay_time() - From an RTAS status value, calculate the + * suggested delay time in milliseconds. + * + * @status: a value returned from rtas_call() or similar APIs which return + * the status of a RTAS function call. + * + * Context: Any context. + * + * Return: + * * 100000 - If @status is 9905. + * * 10000 - If @status is 9904. + * * 1000 - If @status is 9903. + * * 100 - If @status is 9902. + * * 10 - If @status is 9901. + * * 1 - If @status is either 9900 or -2. This is "wrong" for -2, but + * some callers depend on this behavior, and the worst outcome + * is that they will delay for longer than necessary. + * * 0 - If @status is not a busy or extended delay value. */ unsigned int rtas_busy_delay_time(int status) { @@ -513,17 +562,77 @@ unsigned int rtas_busy_delay_time(int status) } EXPORT_SYMBOL(rtas_busy_delay_time); -/* For an RTAS busy status code, perform the hinted delay. */ -unsigned int rtas_busy_delay(int status) +/** + * rtas_busy_delay() - helper for RTAS busy and extended delay statuses + * + * @status: a value returned from rtas_call() or similar APIs which return + * the status of a RTAS function call. + * + * Context: Process context. May sleep or schedule. + * + * Return: + * * true - @status is RTAS_BUSY or an extended delay hint. The + * caller may assume that the CPU has been yielded if necessary, + * and that an appropriate delay for @status has elapsed. + * Generally the caller should reattempt the RTAS call which + * yielded @status. + * + * * false - @status is not @RTAS_BUSY nor an extended delay hint. The + * caller is responsible for handling @status. + */ +bool rtas_busy_delay(int status) { unsigned int ms; + bool ret; - might_sleep(); - ms = rtas_busy_delay_time(status); - if (ms && need_resched()) - msleep(ms); + switch (status) { + case RTAS_EXTENDED_DELAY_MIN...RTAS_EXTENDED_DELAY_MAX: + ret = true; + ms = rtas_busy_delay_time(status); + /* + * The extended delay hint can be as high as 100 seconds. + * Surely any function returning such a status is either + * buggy or isn't going to be significantly slowed by us + * polling at 1HZ. Clamp the sleep time to one second. + */ + ms = clamp(ms, 1U, 1000U); + /* + * The delay hint is an order-of-magnitude suggestion, not + * a minimum. It is fine, possibly even advantageous, for + * us to pause for less time than hinted. For small values, + * use usleep_range() to ensure we don't sleep much longer + * than actually needed. + * + * See Documentation/timers/timers-howto.rst for + * explanation of the threshold used here. In effect we use + * usleep_range() for 9900 and 9901, msleep() for + * 9902-9905. + */ + if (ms <= 20) + usleep_range(ms * 100, ms * 1000); + else + msleep(ms); + break; + case RTAS_BUSY: + ret = true; + /* + * We should call again immediately if there's no other + * work to do. + */ + cond_resched(); + break; + default: + ret = false; + /* + * Not a busy or extended delay status; the caller should + * handle @status itself. Ensure we warn on misuses in + * atomic context regardless. + */ + might_sleep(); + break; + } - return ms; + return ret; } EXPORT_SYMBOL(rtas_busy_delay); @@ -809,13 +918,13 @@ void rtas_os_term(char *str) /** * rtas_activate_firmware() - Activate a new version of firmware. * + * Context: This function may sleep. + * * Activate a new version of partition firmware. The OS must call this * after resuming from a partition hibernation or migration in order * to maintain the ability to perform live firmware updates. It's not * catastrophic for this method to be absent or to fail; just log the * condition in that case. - * - * Context: This function may sleep. */ void rtas_activate_firmware(void) { @@ -836,68 +945,16 @@ void rtas_activate_firmware(void) pr_err("ibm,activate-firmware failed (%i)\n", fwrc); } -#ifdef CONFIG_PPC_PSERIES /** - * rtas_call_reentrant() - Used for reentrant rtas calls - * @token: Token for desired reentrant RTAS call - * @nargs: Number of Input Parameters - * @nret: Number of Output Parameters - * @outputs: Array of outputs - * @...: Inputs for desired RTAS call - * - * According to LoPAR documentation, only "ibm,int-on", "ibm,int-off", - * "ibm,get-xive" and "ibm,set-xive" are currently reentrant. - * Reentrant calls need their own rtas_args buffer, so not using rtas.args, but - * PACA one instead. - * - * Return: -1 on error, - * First output value of RTAS call if (nret > 0), - * 0 otherwise, - */ -int rtas_call_reentrant(int token, int nargs, int nret, int *outputs, ...) -{ - va_list list; - struct rtas_args *args; - unsigned long flags; - int i, ret = 0; - - if (!rtas.entry || token == RTAS_UNKNOWN_SERVICE) - return -1; - - local_irq_save(flags); - preempt_disable(); - - /* We use the per-cpu (PACA) rtas args buffer */ - args = local_paca->rtas_args_reentrant; - - va_start(list, outputs); - va_rtas_call_unlocked(args, token, nargs, nret, list); - va_end(list); - - if (nret > 1 && outputs) - for (i = 0; i < nret - 1; ++i) - outputs[i] = be32_to_cpu(args->rets[i + 1]); - - if (nret > 0) - ret = be32_to_cpu(args->rets[0]); - - local_irq_restore(flags); - preempt_enable(); - - return ret; -} - -#endif /* CONFIG_PPC_PSERIES */ - -/** - * Find a specific pseries error log in an RTAS extended event log. + * get_pseries_errorlog() - Find a specific pseries error log in an RTAS + * extended event log. * @log: RTAS error/event log * @section_id: two character section identifier * - * Returns a pointer to the specified errorlog or NULL if not found. + * Return: A pointer to the specified errorlog or NULL if not found. */ -struct pseries_errorlog *get_pseries_errorlog(struct rtas_error_log *log, - uint16_t section_id) +noinstr struct pseries_errorlog *get_pseries_errorlog(struct rtas_error_log *log, + uint16_t section_id) { struct rtas_ext_event_log_v6 *ext_log = (struct rtas_ext_event_log_v6 *)log->buffer; @@ -974,7 +1031,7 @@ static struct rtas_filter rtas_filters[] __ro_after_init = { { "get-time-of-day", -1, -1, -1, -1, -1 }, { "ibm,get-vpd", -1, 0, -1, 1, 2 }, { "ibm,lpar-perftools", -1, 2, 3, -1, -1 }, - { "ibm,platform-dump", -1, 4, 5, -1, -1 }, + { "ibm,platform-dump", -1, 4, 5, -1, -1 }, /* Special cased */ { "ibm,read-slot-reset-state", -1, -1, -1, -1, -1 }, { "ibm,scan-log-dump", -1, 0, 1, -1, -1 }, { "ibm,set-dynamic-indicator", -1, 2, -1, -1, -1 }, @@ -1023,6 +1080,15 @@ static bool block_rtas_call(int token, int nargs, size = 1; end = base + size - 1; + + /* + * Special case for ibm,platform-dump - NULL buffer + * address is used to indicate end of dump processing + */ + if (!strcmp(f->name, "ibm,platform-dump") && + base == 0) + return false; + if (!in_rmo_buf(base, end)) goto err; } @@ -1121,6 +1187,14 @@ SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs) if (block_rtas_call(token, nargs, &args)) return -EINVAL; + if (token == ibm_open_errinjct_token || token == ibm_errinjct_token) { + int err; + + err = security_locked_down(LOCKDOWN_RTAS_ERROR_INJECTION); + if (err) + return err; + } + /* Need to handle ibm,suspend_me call specially */ if (token == rtas_token("ibm,suspend-me")) { @@ -1219,7 +1293,8 @@ void __init rtas_initialize(void) #ifdef CONFIG_RTAS_ERROR_LOGGING rtas_last_error_token = rtas_token("rtas-last-error"); #endif - + ibm_open_errinjct_token = rtas_token("ibm,open-errinjct"); + ibm_errinjct_token = rtas_token("ibm,errinjct"); rtas_syscall_filter_init(); } @@ -1235,6 +1310,12 @@ int __init early_init_dt_scan_rtas(unsigned long node, entryp = of_get_flat_dt_prop(node, "linux,rtas-entry", NULL); sizep = of_get_flat_dt_prop(node, "rtas-size", NULL); +#ifdef CONFIG_PPC64 + /* need this feature to decide the crashkernel offset */ + if (of_get_flat_dt_prop(node, "ibm,hypertas-functions", NULL)) + powerpc_firmware_features |= FW_FEATURE_LPAR; +#endif + if (basep && entryp && sizep) { rtas.base = *basep; rtas.entry = *entryp; diff --git a/arch/powerpc/kernel/rtas_entry.S b/arch/powerpc/kernel/rtas_entry.S new file mode 100644 index 000000000000..6ce95ddadbcd --- /dev/null +++ b/arch/powerpc/kernel/rtas_entry.S @@ -0,0 +1,176 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#include <asm/asm-offsets.h> +#include <asm/bug.h> +#include <asm/page.h> +#include <asm/ppc_asm.h> + +/* + * RTAS is called with MSR IR, DR, EE disabled, and LR in the return address. + * + * Note: r3 is an input parameter to rtas, so don't trash it... + */ + +#ifdef CONFIG_PPC32 +_GLOBAL(enter_rtas) + stwu r1,-INT_FRAME_SIZE(r1) + mflr r0 + stw r0,INT_FRAME_SIZE+4(r1) + LOAD_REG_ADDR(r4, rtas) + lis r6,1f@ha /* physical return address for rtas */ + addi r6,r6,1f@l + tophys(r6,r6) + lwz r8,RTASENTRY(r4) + lwz r4,RTASBASE(r4) + mfmsr r9 + stw r9,8(r1) + li r9,MSR_KERNEL & ~(MSR_IR|MSR_DR) + mtlr r6 + stw r1, THREAD + RTAS_SP(r2) + mtspr SPRN_SRR0,r8 + mtspr SPRN_SRR1,r9 + rfi +1: + lis r8, 1f@h + ori r8, r8, 1f@l + LOAD_REG_IMMEDIATE(r9,MSR_KERNEL) + mtspr SPRN_SRR0,r8 + mtspr SPRN_SRR1,r9 + rfi /* Reactivate MMU translation */ +1: + lwz r8,INT_FRAME_SIZE+4(r1) /* get return address */ + lwz r9,8(r1) /* original msr value */ + addi r1,r1,INT_FRAME_SIZE + li r0,0 + stw r0, THREAD + RTAS_SP(r2) + mtlr r8 + mtmsr r9 + blr /* return to caller */ +_ASM_NOKPROBE_SYMBOL(enter_rtas) + +#else /* CONFIG_PPC32 */ +#include <asm/exception-64s.h> + +/* + * 32-bit rtas on 64-bit machines has the additional problem that RTAS may + * not preserve the upper parts of registers it uses. + */ +_GLOBAL(enter_rtas) + mflr r0 + std r0,16(r1) + stdu r1,-SWITCH_FRAME_SIZE(r1) /* Save SP and create stack space. */ + + /* Because RTAS is running in 32b mode, it clobbers the high order half + * of all registers that it saves. We therefore save those registers + * RTAS might touch to the stack. (r0, r3-r12 are caller saved) + */ + SAVE_GPR(2, r1) /* Save the TOC */ + SAVE_NVGPRS(r1) /* Save the non-volatiles */ + + mfcr r4 + std r4,_CCR(r1) + mfctr r5 + std r5,_CTR(r1) + mfspr r6,SPRN_XER + std r6,_XER(r1) + mfdar r7 + std r7,_DAR(r1) + mfdsisr r8 + std r8,_DSISR(r1) + + /* Temporary workaround to clear CR until RTAS can be modified to + * ignore all bits. + */ + li r0,0 + mtcr r0 + + mfmsr r6 + + /* Unfortunately, the stack pointer and the MSR are also clobbered, + * so they are saved in the PACA which allows us to restore + * our original state after RTAS returns. + */ + std r1,PACAR1(r13) + std r6,PACASAVEDMSR(r13) + + /* Setup our real return addr */ + LOAD_REG_ADDR(r4,rtas_return_loc) + clrldi r4,r4,2 /* convert to realmode address */ + mtlr r4 + +__enter_rtas: + LOAD_REG_ADDR(r4, rtas) + ld r5,RTASENTRY(r4) /* get the rtas->entry value */ + ld r4,RTASBASE(r4) /* get the rtas->base value */ + + /* + * RTAS runs in 32-bit big endian real mode, but leave MSR[RI] on as we + * may hit NMI (SRESET or MCE) while in RTAS. RTAS should disable RI in + * its critical regions (as specified in PAPR+ section 7.2.1). MSR[S] + * is not impacted by RFI_TO_KERNEL (only urfid can unset it). So if + * MSR[S] is set, it will remain when entering RTAS. + * If we're in HV mode, RTAS must also run in HV mode, so extract MSR_HV + * from the saved MSR value and insert into the value RTAS will use. + */ + extrdi r0, r6, 1, 63 - MSR_HV_LG + LOAD_REG_IMMEDIATE(r6, MSR_ME | MSR_RI) + insrdi r6, r0, 1, 63 - MSR_HV_LG + + li r0,0 + mtmsrd r0,1 /* disable RI before using SRR0/1 */ + + mtspr SPRN_SRR0,r5 + mtspr SPRN_SRR1,r6 + RFI_TO_KERNEL + b . /* prevent speculative execution */ +rtas_return_loc: + FIXUP_ENDIAN + + /* Set SF before anything. */ + LOAD_REG_IMMEDIATE(r6, MSR_KERNEL & ~(MSR_IR|MSR_DR)) + mtmsrd r6 + + /* relocation is off at this point */ + GET_PACA(r13) + + bcl 20,31,$+4 +0: mflr r3 + ld r3,(1f-0b)(r3) /* get &rtas_restore_regs */ + + ld r1,PACAR1(r13) /* Restore our SP */ + ld r4,PACASAVEDMSR(r13) /* Restore our MSR */ + + mtspr SPRN_SRR0,r3 + mtspr SPRN_SRR1,r4 + RFI_TO_KERNEL + b . /* prevent speculative execution */ +_ASM_NOKPROBE_SYMBOL(enter_rtas) +_ASM_NOKPROBE_SYMBOL(__enter_rtas) +_ASM_NOKPROBE_SYMBOL(rtas_return_loc) + + .align 3 +1: .8byte rtas_restore_regs + +rtas_restore_regs: + /* relocation is on at this point */ + REST_GPR(2, r1) /* Restore the TOC */ + REST_NVGPRS(r1) /* Restore the non-volatiles */ + + ld r4,_CCR(r1) + mtcr r4 + ld r5,_CTR(r1) + mtctr r5 + ld r6,_XER(r1) + mtspr SPRN_XER,r6 + ld r7,_DAR(r1) + mtdar r7 + ld r8,_DSISR(r1) + mtdsisr r8 + + addi r1,r1,SWITCH_FRAME_SIZE /* Unstack our frame */ + ld r0,16(r1) /* get return address */ + + mtlr r0 + blr /* return to caller */ + +#endif /* CONFIG_PPC32 */ diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c index a99179d83538..bc817a5619d6 100644 --- a/arch/powerpc/kernel/rtas_flash.c +++ b/arch/powerpc/kernel/rtas_flash.c @@ -120,7 +120,7 @@ static struct kmem_cache *flash_block_cache = NULL; /* * Local copy of the flash block list. * - * The rtas_firmware_flash_list varable will be + * The rtas_firmware_flash_list variable will be * set once the data is fully read. * * For convenience as we build the list we use virtual addrs, diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c index 781c1869902e..5a2f5ea3b054 100644 --- a/arch/powerpc/kernel/rtas_pci.c +++ b/arch/powerpc/kernel/rtas_pci.c @@ -14,10 +14,11 @@ #include <linux/string.h> #include <linux/init.h> #include <linux/pgtable.h> +#include <linux/of_address.h> +#include <linux/of_fdt.h> #include <asm/io.h> #include <asm/irq.h> -#include <asm/prom.h> #include <asm/machdep.h> #include <asm/pci-bridge.h> #include <asm/iommu.h> diff --git a/arch/powerpc/kernel/rtasd.c b/arch/powerpc/kernel/rtasd.c index 32ee17753eb4..5270b450bbde 100644 --- a/arch/powerpc/kernel/rtasd.c +++ b/arch/powerpc/kernel/rtasd.c @@ -22,7 +22,6 @@ #include <linux/uaccess.h> #include <asm/io.h> #include <asm/rtas.h> -#include <asm/prom.h> #include <asm/nvram.h> #include <linux/atomic.h> #include <asm/machdep.h> @@ -455,7 +454,7 @@ static void rtas_event_scan(struct work_struct *w) } #ifdef CONFIG_PPC64 -static void retrieve_nvram_error_log(void) +static void __init retrieve_nvram_error_log(void) { unsigned int err_type ; int rc ; @@ -473,12 +472,12 @@ static void retrieve_nvram_error_log(void) } } #else /* CONFIG_PPC64 */ -static void retrieve_nvram_error_log(void) +static void __init retrieve_nvram_error_log(void) { } #endif /* CONFIG_PPC64 */ -static void start_event_scan(void) +static void __init start_event_scan(void) { printk(KERN_DEBUG "RTAS daemon started\n"); pr_debug("rtasd: will sleep for %d milliseconds\n", diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c index 15fb5ea1b9ea..206475e3e0b4 100644 --- a/arch/powerpc/kernel/security.c +++ b/arch/powerpc/kernel/security.c @@ -16,6 +16,7 @@ #include <asm/asm-prototypes.h> #include <asm/code-patching.h> #include <asm/security_features.h> +#include <asm/sections.h> #include <asm/setup.h> #include <asm/inst.h> @@ -34,7 +35,7 @@ static enum branch_cache_flush_type link_stack_flush_type = BRANCH_CACHE_FLUSH_N bool barrier_nospec_enabled; static bool no_nospec; static bool btb_flush_enabled; -#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_BOOK3S_64) +#if defined(CONFIG_PPC_E500) || defined(CONFIG_PPC_BOOK3S_64) static bool no_spectrev2; #endif @@ -44,7 +45,7 @@ static void enable_barrier_nospec(bool enable) do_barrier_nospec_fixups(enable); } -void setup_barrier_nospec(void) +void __init setup_barrier_nospec(void) { bool enable; @@ -121,7 +122,7 @@ static __init int security_feature_debugfs_init(void) device_initcall(security_feature_debugfs_init); #endif /* CONFIG_DEBUG_FS */ -#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_BOOK3S_64) +#if defined(CONFIG_PPC_E500) || defined(CONFIG_PPC_BOOK3S_64) static int __init handle_nospectre_v2(char *p) { no_spectrev2 = true; @@ -129,17 +130,17 @@ static int __init handle_nospectre_v2(char *p) return 0; } early_param("nospectre_v2", handle_nospectre_v2); -#endif /* CONFIG_PPC_FSL_BOOK3E || CONFIG_PPC_BOOK3S_64 */ +#endif /* CONFIG_PPC_E500 || CONFIG_PPC_BOOK3S_64 */ -#ifdef CONFIG_PPC_FSL_BOOK3E -void setup_spectre_v2(void) +#ifdef CONFIG_PPC_E500 +void __init setup_spectre_v2(void) { if (no_spectrev2 || cpu_mitigations_off()) do_btb_flush_fixups(); else btb_flush_enabled = true; } -#endif /* CONFIG_PPC_FSL_BOOK3E */ +#endif /* CONFIG_PPC_E500 */ #ifdef CONFIG_PPC_BOOK3S_64 ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) @@ -747,14 +748,29 @@ static int count_cache_flush_get(void *data, u64 *val) return 0; } +static int link_stack_flush_get(void *data, u64 *val) +{ + if (link_stack_flush_type == BRANCH_CACHE_FLUSH_NONE) + *val = 0; + else + *val = 1; + + return 0; +} + DEFINE_DEBUGFS_ATTRIBUTE(fops_count_cache_flush, count_cache_flush_get, count_cache_flush_set, "%llu\n"); +DEFINE_DEBUGFS_ATTRIBUTE(fops_link_stack_flush, link_stack_flush_get, + count_cache_flush_set, "%llu\n"); static __init int count_cache_flush_debugfs_init(void) { debugfs_create_file_unsafe("count_cache_flush", 0600, arch_debugfs_dir, NULL, &fops_count_cache_flush); + debugfs_create_file_unsafe("link_stack_flush", 0600, + arch_debugfs_dir, NULL, + &fops_link_stack_flush); return 0; } device_initcall(count_cache_flush_debugfs_init); diff --git a/arch/powerpc/kernel/secvar-sysfs.c b/arch/powerpc/kernel/secvar-sysfs.c index a0a78aba2083..1ee4640a2641 100644 --- a/arch/powerpc/kernel/secvar-sysfs.c +++ b/arch/powerpc/kernel/secvar-sysfs.c @@ -26,15 +26,18 @@ static ssize_t format_show(struct kobject *kobj, struct kobj_attribute *attr, const char *format; node = of_find_compatible_node(NULL, NULL, "ibm,secvar-backend"); - if (!of_device_is_available(node)) - return -ENODEV; + if (!of_device_is_available(node)) { + rc = -ENODEV; + goto out; + } rc = of_property_read_string(node, "format", &format); if (rc) - return rc; + goto out; rc = sprintf(buf, "%s\n", format); +out: of_node_put(node); return rc; diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 4f1322b65760..6d041993a45d 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -18,24 +18,26 @@ #include <linux/delay.h> #include <linux/initrd.h> #include <linux/platform_device.h> +#include <linux/printk.h> #include <linux/seq_file.h> #include <linux/ioport.h> #include <linux/console.h> #include <linux/screen_info.h> #include <linux/root_dev.h> -#include <linux/notifier.h> #include <linux/cpu.h> #include <linux/unistd.h> +#include <linux/seq_buf.h> #include <linux/serial.h> #include <linux/serial_8250.h> #include <linux/percpu.h> #include <linux/memblock.h> +#include <linux/of_irq.h> +#include <linux/of_fdt.h> #include <linux/of_platform.h> #include <linux/hugetlb.h> #include <linux/pgtable.h> #include <asm/io.h> #include <asm/paca.h> -#include <asm/prom.h> #include <asm/processor.h> #include <asm/vdso_datapage.h> #include <asm/smp.h> @@ -161,9 +163,7 @@ void machine_restart(char *cmd) void machine_power_off(void) { machine_shutdown(); - if (pm_power_off) - pm_power_off(); - + do_kernel_power_off(); smp_send_stop(); machine_hang(); } @@ -173,6 +173,14 @@ EXPORT_SYMBOL_GPL(machine_power_off); void (*pm_power_off)(void); EXPORT_SYMBOL_GPL(pm_power_off); +size_t __must_check arch_get_random_seed_longs(unsigned long *v, size_t max_longs) +{ + if (max_longs && ppc_md.get_random_seed && ppc_md.get_random_seed(v)) + return 1; + return 0; +} +EXPORT_SYMBOL(arch_get_random_seed_longs); + void machine_halt(void) { machine_shutdown(); @@ -279,7 +287,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) proc_freq / 1000000, proc_freq % 1000000); /* If we are a Freescale core do a simple check so - * we dont have to keep adding cases in the future */ + * we don't have to keep adding cases in the future */ if (PVR_VER(pvr) & 0x8000) { switch (PVR_VER(pvr)) { case 0x8000: /* 7441/7450/7451, Voyager */ @@ -456,8 +464,8 @@ void __init smp_setup_cpu_maps(void) intserv = of_get_property(dn, "ibm,ppc-interrupt-server#s", &len); if (intserv) { - DBG(" ibm,ppc-interrupt-server#s -> %d threads\n", - nthreads); + DBG(" ibm,ppc-interrupt-server#s -> %lu threads\n", + (len / sizeof(int))); } else { DBG(" no ibm,ppc-interrupt-server#s -> 1 thread\n"); intserv = of_get_property(dn, "reg", &len); @@ -582,7 +590,16 @@ static __init int add_pcspkr(void) device_initcall(add_pcspkr); #endif /* CONFIG_PCSPKR_PLATFORM */ -void probe_machine(void) +static char ppc_hw_desc_buf[128] __initdata; + +struct seq_buf ppc_hw_desc __initdata = { + .buffer = ppc_hw_desc_buf, + .size = sizeof(ppc_hw_desc_buf), + .len = 0, + .readpos = 0, +}; + +static __init void probe_machine(void) { extern struct machdep_calls __machine_desc_start; extern struct machdep_calls __machine_desc_end; @@ -622,7 +639,13 @@ void probe_machine(void) for (;;); } - printk(KERN_INFO "Using %s machine description\n", ppc_md.name); + // Append the machine name to other info we've gathered + seq_buf_puts(&ppc_hw_desc, ppc_md.name); + + // Set the generic hardware description shown in oopses + dump_stack_set_arch_desc(ppc_hw_desc.buffer); + + pr_info("Hardware name: %s\n", ppc_hw_desc.buffer); } /* Match a class of boards, not a specific device configuration. */ @@ -680,8 +703,25 @@ int check_legacy_ioport(unsigned long base_port) } EXPORT_SYMBOL(check_legacy_ioport); -static int ppc_panic_event(struct notifier_block *this, - unsigned long event, void *ptr) +/* + * Panic notifiers setup + * + * We have 3 notifiers for powerpc, each one from a different "nature": + * + * - ppc_panic_fadump_handler() is a hypervisor notifier, which hard-disables + * IRQs and deal with the Firmware-Assisted dump, when it is configured; + * should run early in the panic path. + * + * - dump_kernel_offset() is an informative notifier, just showing the KASLR + * offset if we have RANDOMIZE_BASE set. + * + * - ppc_panic_platform_handler() is a low-level handler that's registered + * only if the platform wishes to perform final actions in the panic path, + * hence it should run late and might not even return. Currently, only + * pseries and ps3 platforms register callbacks. + */ +static int ppc_panic_fadump_handler(struct notifier_block *this, + unsigned long event, void *ptr) { /* * panic does a local_irq_disable, but we really @@ -691,45 +731,63 @@ static int ppc_panic_event(struct notifier_block *this, /* * If firmware-assisted dump has been registered then trigger - * firmware-assisted dump and let firmware handle everything else. + * its callback and let the firmware handles everything else. */ crash_fadump(NULL, ptr); - if (ppc_md.panic) - ppc_md.panic(ptr); /* May not return */ + return NOTIFY_DONE; } -static struct notifier_block ppc_panic_block = { - .notifier_call = ppc_panic_event, - .priority = INT_MIN /* may not return; must be done last */ -}; - -/* - * Dump out kernel offset information on panic. - */ static int dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p) { pr_emerg("Kernel Offset: 0x%lx from 0x%lx\n", kaslr_offset(), KERNELBASE); - return 0; + return NOTIFY_DONE; } +static int ppc_panic_platform_handler(struct notifier_block *this, + unsigned long event, void *ptr) +{ + /* + * This handler is only registered if we have a panic callback + * on ppc_md, hence NULL check is not needed. + * Also, it may not return, so it runs really late on panic path. + */ + ppc_md.panic(ptr); + + return NOTIFY_DONE; +} + +static struct notifier_block ppc_fadump_block = { + .notifier_call = ppc_panic_fadump_handler, + .priority = INT_MAX, /* run early, to notify the firmware ASAP */ +}; + static struct notifier_block kernel_offset_notifier = { - .notifier_call = dump_kernel_offset + .notifier_call = dump_kernel_offset, +}; + +static struct notifier_block ppc_panic_block = { + .notifier_call = ppc_panic_platform_handler, + .priority = INT_MIN, /* may not return; must be done last */ }; void __init setup_panic(void) { + /* Hard-disables IRQs + deal with FW-assisted dump (fadump) */ + atomic_notifier_chain_register(&panic_notifier_list, + &ppc_fadump_block); + if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && kaslr_offset() > 0) atomic_notifier_chain_register(&panic_notifier_list, &kernel_offset_notifier); - /* PPC64 always does a hard irq disable in its panic handler */ - if (!IS_ENABLED(CONFIG_PPC64) && !ppc_md.panic) - return; - atomic_notifier_chain_register(&panic_notifier_list, &ppc_panic_block); + /* Low-level platform-specific routines that should run on panic */ + if (ppc_md.panic) + atomic_notifier_chain_register(&panic_notifier_list, + &ppc_panic_block); } #ifdef CONFIG_CHECK_CACHE_COHERENCY @@ -902,12 +960,6 @@ void __init setup_arch(char **cmdline_p) /* Print various info about the machine that has been gathered so far. */ print_system_info(); - /* Reserve large chunks of memory for use by CMA for KVM. */ - kvm_cma_reserve(); - - /* Reserve large chunks of memory for us by CMA for hugetlb */ - gigantic_hugetlb_cma_reserve(); - klp_init_thread_info(&init_task); setup_initial_init_mm(_stext, _etext, _edata, _end); @@ -922,6 +974,13 @@ void __init setup_arch(char **cmdline_p) initmem_init(); + /* + * Reserve large chunks of memory for use by CMA for KVM and hugetlb. These must + * be called after initmem_init(), so that pageblock_order is initialised. + */ + kvm_cma_reserve(); + gigantic_hugetlb_cma_reserve(); + early_memtest(min_low_pfn << PAGE_SHIFT, max_low_pfn << PAGE_SHIFT); if (ppc_md.setup_arch) diff --git a/arch/powerpc/kernel/setup.h b/arch/powerpc/kernel/setup.h index 84058bbc8fe9..7912bb50a7cb 100644 --- a/arch/powerpc/kernel/setup.h +++ b/arch/powerpc/kernel/setup.h @@ -23,13 +23,13 @@ void check_smt_enabled(void); static inline void check_smt_enabled(void) { } #endif -#if defined(CONFIG_PPC_BOOK3E) && defined(CONFIG_SMP) +#if defined(CONFIG_PPC_BOOK3E_64) && defined(CONFIG_SMP) void setup_tlb_core_data(void); #else static inline void setup_tlb_core_data(void) { } #endif -#if defined(CONFIG_PPC_BOOK3E) || defined(CONFIG_BOOKE) || defined(CONFIG_40x) +#ifdef CONFIG_BOOKE_OR_40x void exc_lvl_early_init(void); #else static inline void exc_lvl_early_init(void) { } diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index 7ec5c47fce0e..b761cc1a403c 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -20,9 +20,10 @@ #include <linux/export.h> #include <linux/nvram.h> #include <linux/pgtable.h> +#include <linux/of_fdt.h> +#include <linux/irq.h> #include <asm/io.h> -#include <asm/prom.h> #include <asm/processor.h> #include <asm/setup.h> #include <asm/smp.h> @@ -75,7 +76,7 @@ EXPORT_SYMBOL(DMA_MODE_WRITE); notrace void __init machine_init(u64 dt_ptr) { u32 *addr = (u32 *)patch_site_addr(&patch__memset_nocache); - struct ppc_inst insn; + ppc_inst_t insn; /* Configure static keys first, now that we're relocated. */ setup_feature_keys(); @@ -175,7 +176,7 @@ void __init emergency_stack_init(void) } #endif -#if defined(CONFIG_BOOKE) || defined(CONFIG_40x) +#ifdef CONFIG_BOOKE_OR_40x void __init exc_lvl_early_init(void) { unsigned int i, hw_cpu; @@ -206,7 +207,7 @@ void __init setup_power_save(void) ppc_md.power_save = ppc6xx_idle; #endif -#ifdef CONFIG_E500 +#ifdef CONFIG_PPC_E500 if (cpu_has_feature(CPU_FTR_CAN_DOZE) || cpu_has_feature(CPU_FTR_CAN_NAP)) ppc_md.power_save = e500_idle; diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 6052f5d5ded3..a0dee7354fe6 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -31,11 +31,13 @@ #include <linux/memory.h> #include <linux/nmi.h> #include <linux/pgtable.h> +#include <linux/of.h> +#include <linux/of_fdt.h> +#include <asm/asm-prototypes.h> #include <asm/kvm_guest.h> #include <asm/io.h> #include <asm/kdump.h> -#include <asm/prom.h> #include <asm/processor.h> #include <asm/smp.h> #include <asm/elf.h> @@ -59,7 +61,7 @@ #include <asm/udbg.h> #include <asm/kexec.h> #include <asm/code-patching.h> -#include <asm/livepatch.h> +#include <asm/ftrace.h> #include <asm/opal.h> #include <asm/cputhreads.h> #include <asm/hw_irq.h> @@ -67,7 +69,6 @@ #include <asm/kup.h> #include <asm/early_ioremap.h> #include <asm/pgalloc.h> -#include <asm/asm-prototypes.h> #include "setup.h" @@ -86,7 +87,7 @@ struct ppc64_caches ppc64_caches = { }; EXPORT_SYMBOL_GPL(ppc64_caches); -#if defined(CONFIG_PPC_BOOK3E) && defined(CONFIG_SMP) +#if defined(CONFIG_PPC_BOOK3E_64) && defined(CONFIG_SMP) void __init setup_tlb_core_data(void) { int cpu; @@ -113,7 +114,6 @@ void __init setup_tlb_core_data(void) * Should we panic instead? */ WARN_ONCE(smt_enabled_at_boot >= 2 && - !mmu_has_feature(MMU_FTR_USE_TLBRSRV) && book3e_htw_mode != PPC_HTW_E6500, "%s: unsupported MMU configuration\n", __func__); } @@ -177,14 +177,26 @@ early_param("smt-enabled", early_smt_enabled); #endif /* CONFIG_SMP */ /** Fix up paca fields required for the boot cpu */ -static void __init fixup_boot_paca(void) +static void __init fixup_boot_paca(struct paca_struct *boot_paca) { /* The boot cpu is started */ - get_paca()->cpu_start = 1; + boot_paca->cpu_start = 1; +#ifdef CONFIG_PPC_BOOK3S_64 + /* + * Give the early boot machine check stack somewhere to use, use + * half of the init stack. This is a bit hacky but there should not be + * deep stack usage in early init so shouldn't overflow it or overwrite + * things. + */ + boot_paca->mc_emergency_sp = (void *)&init_thread_union + + (THREAD_SIZE/2); +#endif /* Allow percpu accesses to work until we setup percpu data */ - get_paca()->data_offset = 0; - /* Mark interrupts disabled in PACA */ - irq_soft_mask_set(IRQS_DISABLED); + boot_paca->data_offset = 0; + /* Mark interrupts soft and hard disabled in PACA */ + boot_paca->irq_soft_mask = IRQS_DISABLED; + boot_paca->irq_happened = PACA_IRQ_HARD_DIS; + WARN_ON(mfmsr() & MSR_EE); } static void __init configure_exceptions(void) @@ -197,6 +209,34 @@ static void __init configure_exceptions(void) /* Under a PAPR hypervisor, we need hypercalls */ if (firmware_has_feature(FW_FEATURE_SET_MODE)) { + /* + * - PR KVM does not support AIL mode interrupts in the host + * while a PR guest is running. + * + * - SCV system call interrupt vectors are only implemented for + * AIL mode interrupts. + * + * - On pseries, AIL mode can only be enabled and disabled + * system-wide so when a PR VM is created on a pseries host, + * all CPUs of the host are set to AIL=0 mode. + * + * - Therefore host CPUs must not execute scv while a PR VM + * exists. + * + * - SCV support can not be disabled dynamically because the + * feature is advertised to host userspace. Disabling the + * facility and emulating it would be possible but is not + * implemented. + * + * - So SCV support is blanket disabled if PR KVM could possibly + * run. That is, PR support compiled in, booting on pseries + * with hash MMU. + */ + if (IS_ENABLED(CONFIG_KVM_BOOK3S_PR_POSSIBLE) && !radix_enabled()) { + init_task.thread.fscr &= ~FSCR_SCV; + cur_cpu_spec->cpu_user_features2 &= ~PPC_FEATURE2_SCV; + } + /* Enable AIL if possible */ if (!pseries_enable_reloc_on_exc()) { init_task.thread.fscr &= ~FSCR_SCV; @@ -323,11 +363,15 @@ void __init early_setup(unsigned long dt_ptr) * what CPU we are on. */ initialise_paca(&boot_paca, 0); - setup_paca(&boot_paca); - fixup_boot_paca(); + fixup_boot_paca(&boot_paca); + WARN_ON(local_paca != 0); + setup_paca(&boot_paca); /* install the paca into registers */ /* -------- printk is now safe to use ------- */ + if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && (mfmsr() & MSR_HV)) + enable_machine_check(); + /* Try new device tree based feature discovery ... */ if (!dt_cpu_ftrs_init(__va(dt_ptr))) /* Otherwise use the old style CPU table */ @@ -350,8 +394,8 @@ void __init early_setup(unsigned long dt_ptr) /* Poison paca_ptrs[0] again if it's not the boot cpu */ memset(&paca_ptrs[0], 0x88, sizeof(paca_ptrs[0])); } - setup_paca(paca_ptrs[boot_cpuid]); - fixup_boot_paca(); + fixup_boot_paca(paca_ptrs[boot_cpuid]); + setup_paca(paca_ptrs[boot_cpuid]); /* install the paca into registers */ /* * Configure exception handlers. This include setting up trampolines @@ -499,7 +543,7 @@ void smp_release_cpus(void) * routines and/or provided to userland */ -static void init_cache_info(struct ppc_cache_info *info, u32 size, u32 lsize, +static void __init init_cache_info(struct ppc_cache_info *info, u32 size, u32 lsize, u32 bsize, u32 sets) { info->size = size; @@ -646,7 +690,7 @@ void __init initialize_cache_info(void) */ __init u64 ppc64_bolted_size(void) { -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 /* Freescale BookE bolts the entire linear mapping */ /* XXX: BookE ppc64_rma_limit setup seems to disagree? */ if (early_mmu_has_feature(MMU_FTR_TYPE_FSL_E)) @@ -696,7 +740,7 @@ void __init irqstack_early_init(void) } } -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 void __init exc_lvl_early_init(void) { unsigned int i; @@ -771,50 +815,6 @@ void __init emergency_stack_init(void) } #ifdef CONFIG_SMP -/** - * pcpu_alloc_bootmem - NUMA friendly alloc_bootmem wrapper for percpu - * @cpu: cpu to allocate for - * @size: size allocation in bytes - * @align: alignment - * - * Allocate @size bytes aligned at @align for cpu @cpu. This wrapper - * does the right thing for NUMA regardless of the current - * configuration. - * - * RETURNS: - * Pointer to the allocated area on success, NULL on failure. - */ -static void * __init pcpu_alloc_bootmem(unsigned int cpu, size_t size, - size_t align) -{ - const unsigned long goal = __pa(MAX_DMA_ADDRESS); -#ifdef CONFIG_NUMA - int node = early_cpu_to_node(cpu); - void *ptr; - - if (!node_online(node) || !NODE_DATA(node)) { - ptr = memblock_alloc_from(size, align, goal); - pr_info("cpu %d has no node %d or node-local memory\n", - cpu, node); - pr_debug("per cpu data for cpu%d %lu bytes at %016lx\n", - cpu, size, __pa(ptr)); - } else { - ptr = memblock_alloc_try_nid(size, align, goal, - MEMBLOCK_ALLOC_ACCESSIBLE, node); - pr_debug("per cpu data for cpu%d %lu bytes on node%d at " - "%016lx\n", cpu, size, node, __pa(ptr)); - } - return ptr; -#else - return memblock_alloc_from(size, align, goal); -#endif -} - -static void __init pcpu_free_bootmem(void *ptr, size_t size) -{ - memblock_free(ptr, size); -} - static int pcpu_cpu_distance(unsigned int from, unsigned int to) { if (early_cpu_to_node(from) == early_cpu_to_node(to)) @@ -823,53 +823,13 @@ static int pcpu_cpu_distance(unsigned int from, unsigned int to) return REMOTE_DISTANCE; } -unsigned long __per_cpu_offset[NR_CPUS] __read_mostly; -EXPORT_SYMBOL(__per_cpu_offset); - -static void __init pcpu_populate_pte(unsigned long addr) +static __init int pcpu_cpu_to_node(int cpu) { - pgd_t *pgd = pgd_offset_k(addr); - p4d_t *p4d; - pud_t *pud; - pmd_t *pmd; - - p4d = p4d_offset(pgd, addr); - if (p4d_none(*p4d)) { - pud_t *new; - - new = memblock_alloc(PUD_TABLE_SIZE, PUD_TABLE_SIZE); - if (!new) - goto err_alloc; - p4d_populate(&init_mm, p4d, new); - } - - pud = pud_offset(p4d, addr); - if (pud_none(*pud)) { - pmd_t *new; - - new = memblock_alloc(PMD_TABLE_SIZE, PMD_TABLE_SIZE); - if (!new) - goto err_alloc; - pud_populate(&init_mm, pud, new); - } - - pmd = pmd_offset(pud, addr); - if (!pmd_present(*pmd)) { - pte_t *new; - - new = memblock_alloc(PTE_TABLE_SIZE, PTE_TABLE_SIZE); - if (!new) - goto err_alloc; - pmd_populate_kernel(&init_mm, pmd, new); - } - - return; - -err_alloc: - panic("%s: Failed to allocate %lu bytes align=%lx from=%lx\n", - __func__, PAGE_SIZE, PAGE_SIZE, PAGE_SIZE); + return early_cpu_to_node(cpu); } +unsigned long __per_cpu_offset[NR_CPUS] __read_mostly; +EXPORT_SYMBOL(__per_cpu_offset); void __init setup_per_cpu_areas(void) { @@ -880,18 +840,27 @@ void __init setup_per_cpu_areas(void) int rc = -EINVAL; /* - * Linear mapping is one of 4K, 1M and 16M. For 4K, no need - * to group units. For larger mappings, use 1M atom which - * should be large enough to contain a number of units. + * BookE and BookS radix are historical values and should be revisited. */ - if (mmu_linear_psize == MMU_PAGE_4K) + if (IS_ENABLED(CONFIG_PPC_BOOK3E_64)) { + atom_size = SZ_1M; + } else if (radix_enabled()) { atom_size = PAGE_SIZE; - else - atom_size = 1 << 20; + } else if (IS_ENABLED(CONFIG_PPC_64S_HASH_MMU)) { + /* + * Linear mapping is one of 4K, 1M and 16M. For 4K, no need + * to group units. For larger mappings, use 1M atom which + * should be large enough to contain a number of units. + */ + if (mmu_linear_psize == MMU_PAGE_4K) + atom_size = PAGE_SIZE; + else + atom_size = SZ_1M; + } if (pcpu_chosen_fc != PCPU_FC_PAGE) { rc = pcpu_embed_first_chunk(0, dyn_size, atom_size, pcpu_cpu_distance, - pcpu_alloc_bootmem, pcpu_free_bootmem); + pcpu_cpu_to_node); if (rc) pr_warn("PERCPU: %s allocator failed (%d), " "falling back to page size\n", @@ -899,8 +868,7 @@ void __init setup_per_cpu_areas(void) } if (rc < 0) - rc = pcpu_page_first_chunk(0, pcpu_alloc_bootmem, pcpu_free_bootmem, - pcpu_populate_pte); + rc = pcpu_page_first_chunk(0, pcpu_cpu_to_node); if (rc < 0) panic("cannot initialize percpu area (err=%d)", rc); diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index b93b87df499d..68a91e553e14 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -9,7 +9,7 @@ * this archive for more details. */ -#include <linux/tracehook.h> +#include <linux/resume_user_mode.h> #include <linux/signal.h> #include <linux/uprobes.h> #include <linux/key.h> @@ -141,6 +141,21 @@ unsigned long copy_ckvsx_from_user(struct task_struct *task, int show_unhandled_signals = 1; +unsigned long get_min_sigframe_size(void) +{ + if (IS_ENABLED(CONFIG_PPC64)) + return get_min_sigframe_size_64(); + else + return get_min_sigframe_size_32(); +} + +#ifdef CONFIG_COMPAT +unsigned long get_min_sigframe_size_compat(void) +{ + return get_min_sigframe_size_32(); +} +#endif + /* * Allocate space for the signal frame */ @@ -294,7 +309,7 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags) } if (thread_info_flags & _TIF_NOTIFY_RESUME) - tracehook_notify_resume(regs); + resume_user_mode_work(regs); } static unsigned long get_tm_stackpointer(struct task_struct *tsk) diff --git a/arch/powerpc/kernel/signal.h b/arch/powerpc/kernel/signal.h index 618aeccdf691..a429c57ed433 100644 --- a/arch/powerpc/kernel/signal.h +++ b/arch/powerpc/kernel/signal.h @@ -196,9 +196,6 @@ extern int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, #else /* CONFIG_PPC64 */ -extern long sys_rt_sigreturn(void); -extern long sys_sigreturn(void); - static inline int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, struct task_struct *tsk) { diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 3e053e2fd6b6..c114c7f25645 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -43,7 +43,7 @@ #include <asm/tm.h> #include <asm/asm-prototypes.h> #ifdef CONFIG_PPC64 -#include "ppc32.h" +#include <asm/syscalls_32.h> #include <asm/unistd.h> #else #include <asm/ucontext.h> @@ -233,6 +233,12 @@ struct rt_sigframe { int abigap[56]; }; +unsigned long get_min_sigframe_size_32(void) +{ + return max(sizeof(struct rt_sigframe) + __SIGNAL_FRAMESIZE + 16, + sizeof(struct sigframe) + __SIGNAL_FRAMESIZE); +} + /* * Save the current user registers on the user stack. * We only save the altivec/spe registers if the process has used @@ -527,16 +533,20 @@ static long restore_user_regs(struct pt_regs *regs, regs_set_return_msr(regs, regs->msr & ~(MSR_FP | MSR_FE0 | MSR_FE1)); #ifdef CONFIG_SPE - /* force the process to reload the spe registers from - current->thread when it next does spe instructions */ + /* + * Force the process to reload the spe registers from + * current->thread when it next does spe instructions. + * Since this is user ABI, we must enforce the sizing. + */ + BUILD_BUG_ON(sizeof(current->thread.spe) != ELF_NEVRREG * sizeof(u32)); regs_set_return_msr(regs, regs->msr & ~MSR_SPE); if (msr & MSR_SPE) { /* restore spe registers from the stack */ - unsafe_copy_from_user(current->thread.evr, &sr->mc_vregs, - ELF_NEVRREG * sizeof(u32), failed); + unsafe_copy_from_user(¤t->thread.spe, &sr->mc_vregs, + sizeof(current->thread.spe), failed); current->thread.used_spe = true; } else if (current->thread.used_spe) - memset(current->thread.evr, 0, ELF_NEVRREG * sizeof(u32)); + memset(¤t->thread.spe, 0, sizeof(current->thread.spe)); /* Always get SPEFSCR back */ unsafe_get_user(current->thread.spefscr, (u32 __user *)&sr->mc_vregs + ELF_NEVRREG, failed); diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index d1e1fc0acbea..86bb5bb4c143 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -66,6 +66,11 @@ struct rt_sigframe { char abigap[USER_REDZONE_SIZE]; } __attribute__ ((aligned (16))); +unsigned long get_min_sigframe_size_64(void) +{ + return sizeof(struct rt_sigframe) + __SIGNAL_FRAMESIZE; +} + /* * This computes a quad word aligned pointer inside the vmx_reserve array * element. For historical reasons sigcontext might not be quad word aligned, @@ -123,7 +128,7 @@ static long notrace __unsafe_setup_sigcontext(struct sigcontext __user *sc, #endif struct pt_regs *regs = tsk->thread.regs; unsigned long msr = regs->msr; - /* Force usr to alway see softe as 1 (interrupts enabled) */ + /* Force usr to always see softe as 1 (interrupts enabled) */ unsigned long softe = 0x1; BUG_ON(tsk != current); @@ -372,9 +377,12 @@ static long notrace __unsafe_restore_sigcontext(struct task_struct *tsk, sigset_ unsafe_get_user(set->sig[0], &sc->oldmask, efault_out); /* - * Force reload of FP/VEC. - * This has to be done before copying stuff into tsk->thread.fpr/vr - * for the reasons explained in the previous comment. + * Force reload of FP/VEC/VSX so userspace sees any changes. + * Clear these bits from the user process' MSR before copying into the + * thread struct. If we are rescheduled or preempted and another task + * uses FP/VEC/VSX, and this process has the MSR bits set, then the + * context switch code will save the current CPU state into the + * thread_struct - possibly overwriting the data we are updating here. */ regs_set_return_msr(regs, regs->msr & ~(MSR_FP | MSR_FE0 | MSR_FE1 | MSR_VEC | MSR_VSX)); @@ -936,11 +944,11 @@ int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, * descriptor is the entry address of signal and the second * entry is the TOC value we need to use. */ - func_descr_t __user *funct_desc_ptr = - (func_descr_t __user *) ksig->ka.sa.sa_handler; + struct func_desc __user *ptr = + (struct func_desc __user *)ksig->ka.sa.sa_handler; - err |= get_user(regs->ctr, &funct_desc_ptr->entry); - err |= get_user(regs->gpr[2], &funct_desc_ptr->toc); + err |= get_user(regs->ctr, &ptr->addr); + err |= get_user(regs->gpr[2], &ptr->toc); } /* enter the signal handler in native-endian mode */ diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index c23ee842c4c3..0da6e59161cd 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -35,6 +35,7 @@ #include <linux/stackprotector.h> #include <linux/pgtable.h> #include <linux/clockchips.h> +#include <linux/kexec.h> #include <asm/ptrace.h> #include <linux/atomic.h> @@ -43,7 +44,6 @@ #include <asm/kvm_ppc.h> #include <asm/dbell.h> #include <asm/page.h> -#include <asm/prom.h> #include <asm/smp.h> #include <asm/time.h> #include <asm/machdep.h> @@ -56,11 +56,10 @@ #endif #include <asm/vdso.h> #include <asm/debug.h> -#include <asm/kexec.h> -#include <asm/asm-prototypes.h> #include <asm/cpu_has_feature.h> #include <asm/ftrace.h> #include <asm/kup.h> +#include <asm/fadump.h> #ifdef DEBUG #include <asm/udbg.h> @@ -412,32 +411,32 @@ static struct cpumask nmi_ipi_pending_mask; static bool nmi_ipi_busy = false; static void (*nmi_ipi_function)(struct pt_regs *) = NULL; -static void nmi_ipi_lock_start(unsigned long *flags) +noinstr static void nmi_ipi_lock_start(unsigned long *flags) { raw_local_irq_save(*flags); hard_irq_disable(); - while (atomic_cmpxchg(&__nmi_ipi_lock, 0, 1) == 1) { + while (arch_atomic_cmpxchg(&__nmi_ipi_lock, 0, 1) == 1) { raw_local_irq_restore(*flags); - spin_until_cond(atomic_read(&__nmi_ipi_lock) == 0); + spin_until_cond(arch_atomic_read(&__nmi_ipi_lock) == 0); raw_local_irq_save(*flags); hard_irq_disable(); } } -static void nmi_ipi_lock(void) +noinstr static void nmi_ipi_lock(void) { - while (atomic_cmpxchg(&__nmi_ipi_lock, 0, 1) == 1) - spin_until_cond(atomic_read(&__nmi_ipi_lock) == 0); + while (arch_atomic_cmpxchg(&__nmi_ipi_lock, 0, 1) == 1) + spin_until_cond(arch_atomic_read(&__nmi_ipi_lock) == 0); } -static void nmi_ipi_unlock(void) +noinstr static void nmi_ipi_unlock(void) { smp_mb(); - WARN_ON(atomic_read(&__nmi_ipi_lock) != 1); - atomic_set(&__nmi_ipi_lock, 0); + WARN_ON(arch_atomic_read(&__nmi_ipi_lock) != 1); + arch_atomic_set(&__nmi_ipi_lock, 0); } -static void nmi_ipi_unlock_end(unsigned long *flags) +noinstr static void nmi_ipi_unlock_end(unsigned long *flags) { nmi_ipi_unlock(); raw_local_irq_restore(*flags); @@ -446,7 +445,7 @@ static void nmi_ipi_unlock_end(unsigned long *flags) /* * Platform NMI handler calls this to ack */ -int smp_handle_nmi_ipi(struct pt_regs *regs) +noinstr int smp_handle_nmi_ipi(struct pt_regs *regs) { void (*fn)(struct pt_regs *) = NULL; unsigned long flags; @@ -620,6 +619,34 @@ void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *)) } #endif +void crash_smp_send_stop(void) +{ + static bool stopped = false; + + /* + * In case of fadump, register data for all CPUs is captured by f/w + * on ibm,os-term rtas call. Skip IPI callbacks to other CPUs before + * this rtas call to avoid tricky post processing of those CPUs' + * backtraces. + */ + if (should_fadump_crash()) + return; + + if (stopped) + return; + + stopped = true; + +#ifdef CONFIG_KEXEC_CORE + if (kexec_crash_image) { + crash_kexec_prepare(); + return; + } +#endif + + smp_send_stop(); +} + #ifdef CONFIG_NMI_IPI static void nmi_stop_this_cpu(struct pt_regs *regs) { @@ -676,12 +703,12 @@ void smp_send_stop(void) } #endif /* CONFIG_NMI_IPI */ -struct task_struct *current_set[NR_CPUS]; +static struct task_struct *current_set[NR_CPUS]; static void smp_store_cpu_info(int id) { per_cpu(cpu_pvr, id) = mfspr(SPRN_PVR); -#ifdef CONFIG_PPC_FSL_BOOK3E +#ifdef CONFIG_PPC_E500 per_cpu(next_tlbcam_idx, id) = (mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY) - 1; #endif @@ -836,7 +863,7 @@ out_free: * @tg : The thread-group structure of the CPU node which @cpu belongs * to. * - * Returns the index to tg->thread_list that points to the the start + * Returns the index to tg->thread_list that points to the start * of the thread_group that @cpu belongs to. * * Returns -1 if cpu doesn't belong to any of the groups pointed to by @@ -896,7 +923,8 @@ out: return tg; } -static int update_mask_from_threadgroup(cpumask_var_t *mask, struct thread_groups *tg, int cpu, int cpu_group_start) +static int __init update_mask_from_threadgroup(cpumask_var_t *mask, struct thread_groups *tg, + int cpu, int cpu_group_start) { int first_thread = cpu_first_thread_sibling(cpu); int i; @@ -1062,7 +1090,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus) DBG("smp_prepare_cpus\n"); /* - * setup_cpu may need to be called on the boot cpu. We havent + * setup_cpu may need to be called on the boot cpu. We haven't * spun any cpus up but lets be paranoid. */ BUG_ON(boot_cpuid != smp_processor_id()); @@ -1229,7 +1257,12 @@ static void cpu_idle_thread_init(unsigned int cpu, struct task_struct *idle) int __cpu_up(unsigned int cpu, struct task_struct *tidle) { - int rc, c; + const unsigned long boot_spin_ms = 5 * MSEC_PER_SEC; + const bool booting = system_state < SYSTEM_RUNNING; + const unsigned long hp_spin_ms = 1; + unsigned long deadline; + int rc; + const unsigned long spin_wait_ms = booting ? boot_spin_ms : hp_spin_ms; /* * Don't allow secondary threads to come online if inhibited @@ -1274,22 +1307,23 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle) } /* - * wait to see if the cpu made a callin (is actually up). - * use this value that I found through experimentation. - * -- Cort + * At boot time, simply spin on the callin word until the + * deadline passes. + * + * At run time, spin for an optimistic amount of time to avoid + * sleeping in the common case. */ - if (system_state < SYSTEM_RUNNING) - for (c = 50000; c && !cpu_callin_map[cpu]; c--) - udelay(100); -#ifdef CONFIG_HOTPLUG_CPU - else - /* - * CPUs can take much longer to come up in the - * hotplug case. Wait five seconds. - */ - for (c = 5000; c && !cpu_callin_map[cpu]; c--) - msleep(1); -#endif + deadline = jiffies + msecs_to_jiffies(spin_wait_ms); + spin_until_cond(cpu_callin_map[cpu] || time_is_before_jiffies(deadline)); + + if (!cpu_callin_map[cpu] && system_state >= SYSTEM_RUNNING) { + const unsigned long sleep_interval_us = 10 * USEC_PER_MSEC; + const unsigned long sleep_wait_ms = 100 * MSEC_PER_SEC; + + deadline = jiffies + msecs_to_jiffies(sleep_wait_ms); + while (!cpu_callin_map[cpu] && time_is_after_jiffies(deadline)) + fsleep(sleep_interval_us); + } if (!cpu_callin_map[cpu]) { printk(KERN_ERR "Processor %u is stuck.\n", cpu); @@ -1635,12 +1669,7 @@ void start_secondary(void *unused) BUG(); } -int setup_profiling_timer(unsigned int multiplier) -{ - return 0; -} - -static void fixup_topology(void) +static void __init fixup_topology(void) { int i; diff --git a/arch/powerpc/kernel/swsusp_32.S b/arch/powerpc/kernel/swsusp_32.S index f73f4d72fea4..e0cbd63007f2 100644 --- a/arch/powerpc/kernel/swsusp_32.S +++ b/arch/powerpc/kernel/swsusp_32.S @@ -181,7 +181,7 @@ _GLOBAL(swsusp_arch_resume) #ifdef CONFIG_ALTIVEC /* Stop pending alitvec streams and memory accesses */ BEGIN_FTR_SECTION - DSSALL + PPC_DSSALL END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) #endif sync diff --git a/arch/powerpc/kernel/swsusp_booke.S b/arch/powerpc/kernel/swsusp_85xx.S index 88cfdbd530f1..88cfdbd530f1 100644 --- a/arch/powerpc/kernel/swsusp_booke.S +++ b/arch/powerpc/kernel/swsusp_85xx.S diff --git a/arch/powerpc/kernel/swsusp_asm64.S b/arch/powerpc/kernel/swsusp_asm64.S index 96bb20715aa9..f645652c2654 100644 --- a/arch/powerpc/kernel/swsusp_asm64.S +++ b/arch/powerpc/kernel/swsusp_asm64.S @@ -76,16 +76,10 @@ swsusp_save_area: .space SL_SIZE - .section ".toc","aw" -swsusp_save_area_ptr: - .tc swsusp_save_area[TC],swsusp_save_area -restore_pblist_ptr: - .tc restore_pblist[TC],restore_pblist - .section .text .align 5 _GLOBAL(swsusp_arch_suspend) - ld r11,swsusp_save_area_ptr@toc(r2) + LOAD_REG_ADDR(r11, swsusp_save_area) SAVE_SPECIAL(LR) SAVE_REGISTER(r1) SAVE_SPECIAL(CR) @@ -131,7 +125,7 @@ END_FW_FTR_SECTION_IFCLR(FW_FEATURE_LPAR) bl swsusp_save /* restore LR */ - ld r11,swsusp_save_area_ptr@toc(r2) + LOAD_REG_ADDR(r11, swsusp_save_area) RESTORE_SPECIAL(LR) addi r1,r1,128 @@ -141,11 +135,11 @@ END_FW_FTR_SECTION_IFCLR(FW_FEATURE_LPAR) _GLOBAL(swsusp_arch_resume) /* Stop pending alitvec streams and memory accesses */ BEGIN_FTR_SECTION - DSSALL + PPC_DSSALL END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) sync - ld r12,restore_pblist_ptr@toc(r2) + LOAD_REG_ADDR(r11, restore_pblist) ld r12,0(r12) cmpdi r12,0 @@ -187,7 +181,7 @@ nothing_to_copy: tlbia #endif - ld r11,swsusp_save_area_ptr@toc(r2) + LOAD_REG_ADDR(r11, swsusp_save_area) RESTORE_SPECIAL(CR) @@ -265,7 +259,7 @@ END_FW_FTR_SECTION_IFCLR(FW_FEATURE_LPAR) bl do_after_copyback addi r1,r1,128 - ld r11,swsusp_save_area_ptr@toc(r2) + LOAD_REG_ADDR(r11, swsusp_save_area) RESTORE_SPECIAL(LR) li r3, 0 diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c index 16ff0399a257..d451a8229223 100644 --- a/arch/powerpc/kernel/sys_ppc32.c +++ b/arch/powerpc/kernel/sys_ppc32.c @@ -1,13 +1,23 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * sys_ppc32.c: Conversion between 32bit and 64bit native syscalls. + * sys_ppc32.c: 32-bit system calls with complex calling conventions. * * Copyright (C) 2001 IBM * Copyright (C) 1997,1998 Jakub Jelinek (jj@sunsite.mff.cuni.cz) * Copyright (C) 1997 David S. Miller (davem@caip.rutgers.edu) * - * These routines maintain argument size conversion between 32bit and 64bit - * environment. + * 32-bit system calls with 64-bit arguments pass those in register pairs. + * This must be specially dealt with on 64-bit kernels. The compat_arg_u64_dual + * in generic compat syscalls is not always usable because the register + * pairing is constrained depending on preceding arguments. + * + * An analogous problem exists on 32-bit kernels with ARCH_HAS_SYSCALL_WRAPPER, + * the defined system call functions take the pt_regs as an argument, and there + * is a mapping macro which maps registers to arguments + * (SC_POWERPC_REGS_TO_ARGS) which also does not deal with these 64-bit + * arguments. + * + * This file contains these system calls. */ #include <linux/kernel.h> @@ -25,7 +35,6 @@ #include <linux/poll.h> #include <linux/personality.h> #include <linux/stat.h> -#include <linux/mman.h> #include <linux/in.h> #include <linux/syscalls.h> #include <linux/unistd.h> @@ -48,75 +57,79 @@ #include <asm/syscalls.h> #include <asm/switch_to.h> -unsigned long compat_sys_mmap2(unsigned long addr, size_t len, - unsigned long prot, unsigned long flags, - unsigned long fd, unsigned long pgoff) -{ - /* This should remain 12 even if PAGE_SIZE changes */ - return sys_mmap(addr, len, prot, flags, fd, pgoff << 12); -} - -/* - * long long munging: - * The 32 bit ABI passes long longs in an odd even register pair. - * High and low parts are swapped depending on endian mode, - * so define a macro (similar to mips linux32) to handle that. - */ -#ifdef __LITTLE_ENDIAN__ -#define merge_64(low, high) ((u64)high << 32) | low +#ifdef CONFIG_PPC32 +#define PPC32_SYSCALL_DEFINE4 SYSCALL_DEFINE4 +#define PPC32_SYSCALL_DEFINE5 SYSCALL_DEFINE5 +#define PPC32_SYSCALL_DEFINE6 SYSCALL_DEFINE6 #else -#define merge_64(high, low) ((u64)high << 32) | low +#define PPC32_SYSCALL_DEFINE4 COMPAT_SYSCALL_DEFINE4 +#define PPC32_SYSCALL_DEFINE5 COMPAT_SYSCALL_DEFINE5 +#define PPC32_SYSCALL_DEFINE6 COMPAT_SYSCALL_DEFINE6 #endif -compat_ssize_t compat_sys_pread64(unsigned int fd, char __user *ubuf, compat_size_t count, - u32 reg6, u32 pos1, u32 pos2) +PPC32_SYSCALL_DEFINE6(ppc_pread64, + unsigned int, fd, + char __user *, ubuf, compat_size_t, count, + u32, reg6, u32, pos1, u32, pos2) { return ksys_pread64(fd, ubuf, count, merge_64(pos1, pos2)); } -compat_ssize_t compat_sys_pwrite64(unsigned int fd, const char __user *ubuf, compat_size_t count, - u32 reg6, u32 pos1, u32 pos2) +PPC32_SYSCALL_DEFINE6(ppc_pwrite64, + unsigned int, fd, + const char __user *, ubuf, compat_size_t, count, + u32, reg6, u32, pos1, u32, pos2) { return ksys_pwrite64(fd, ubuf, count, merge_64(pos1, pos2)); } -compat_ssize_t compat_sys_readahead(int fd, u32 r4, u32 offset1, u32 offset2, u32 count) +PPC32_SYSCALL_DEFINE5(ppc_readahead, + int, fd, u32, r4, + u32, offset1, u32, offset2, u32, count) { return ksys_readahead(fd, merge_64(offset1, offset2), count); } -asmlinkage int compat_sys_truncate64(const char __user * path, u32 reg4, - unsigned long len1, unsigned long len2) +PPC32_SYSCALL_DEFINE4(ppc_truncate64, + const char __user *, path, u32, reg4, + unsigned long, len1, unsigned long, len2) { return ksys_truncate(path, merge_64(len1, len2)); } -asmlinkage long compat_sys_fallocate(int fd, int mode, u32 offset1, u32 offset2, - u32 len1, u32 len2) -{ - return ksys_fallocate(fd, mode, ((loff_t)offset1 << 32) | offset2, - merge_64(len1, len2)); -} - -asmlinkage int compat_sys_ftruncate64(unsigned int fd, u32 reg4, unsigned long len1, - unsigned long len2) +PPC32_SYSCALL_DEFINE4(ppc_ftruncate64, + unsigned int, fd, u32, reg4, + unsigned long, len1, unsigned long, len2) { return ksys_ftruncate(fd, merge_64(len1, len2)); } -long ppc32_fadvise64(int fd, u32 unused, u32 offset1, u32 offset2, - size_t len, int advice) +PPC32_SYSCALL_DEFINE6(ppc32_fadvise64, + int, fd, u32, unused, u32, offset1, u32, offset2, + size_t, len, int, advice) { return ksys_fadvise64_64(fd, merge_64(offset1, offset2), len, advice); } -asmlinkage long compat_sys_sync_file_range2(int fd, unsigned int flags, - unsigned offset1, unsigned offset2, - unsigned nbytes1, unsigned nbytes2) +PPC32_SYSCALL_DEFINE6(ppc_sync_file_range2, + int, fd, unsigned int, flags, + unsigned int, offset1, unsigned int, offset2, + unsigned int, nbytes1, unsigned int, nbytes2) { loff_t offset = merge_64(offset1, offset2); loff_t nbytes = merge_64(nbytes1, nbytes2); return ksys_sync_file_range(fd, offset, nbytes, flags); } + +#ifdef CONFIG_PPC32 +SYSCALL_DEFINE6(ppc_fallocate, + int, fd, int, mode, + u32, offset1, u32, offset2, u32, len1, u32, len2) +{ + return ksys_fallocate(fd, mode, + merge_64(offset1, offset2), + merge_64(len1, len2)); +} +#endif diff --git a/arch/powerpc/kernel/syscall.c b/arch/powerpc/kernel/syscall.c new file mode 100644 index 000000000000..18b9d325395f --- /dev/null +++ b/arch/powerpc/kernel/syscall.c @@ -0,0 +1,189 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#include <linux/compat.h> +#include <linux/context_tracking.h> +#include <linux/randomize_kstack.h> + +#include <asm/interrupt.h> +#include <asm/kup.h> +#include <asm/syscall.h> +#include <asm/time.h> +#include <asm/tm.h> +#include <asm/unistd.h> + + +/* Has to run notrace because it is entered not completely "reconciled" */ +notrace long system_call_exception(struct pt_regs *regs, unsigned long r0) +{ + long ret; + syscall_fn f; + + kuap_lock(); + + add_random_kstack_offset(); + + if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) + BUG_ON(irq_soft_mask_return() != IRQS_ALL_DISABLED); + + trace_hardirqs_off(); /* finish reconciling */ + + CT_WARN_ON(ct_state() == CONTEXT_KERNEL); + user_exit_irqoff(); + + BUG_ON(regs_is_unrecoverable(regs)); + BUG_ON(!(regs->msr & MSR_PR)); + BUG_ON(arch_irq_disabled_regs(regs)); + +#ifdef CONFIG_PPC_PKEY + if (mmu_has_feature(MMU_FTR_PKEY)) { + unsigned long amr, iamr; + bool flush_needed = false; + /* + * When entering from userspace we mostly have the AMR/IAMR + * different from kernel default values. Hence don't compare. + */ + amr = mfspr(SPRN_AMR); + iamr = mfspr(SPRN_IAMR); + regs->amr = amr; + regs->iamr = iamr; + if (mmu_has_feature(MMU_FTR_BOOK3S_KUAP)) { + mtspr(SPRN_AMR, AMR_KUAP_BLOCKED); + flush_needed = true; + } + if (mmu_has_feature(MMU_FTR_BOOK3S_KUEP)) { + mtspr(SPRN_IAMR, AMR_KUEP_BLOCKED); + flush_needed = true; + } + if (flush_needed) + isync(); + } else +#endif + kuap_assert_locked(); + + booke_restore_dbcr0(); + + account_cpu_user_entry(); + + account_stolen_time(); + + /* + * This is not required for the syscall exit path, but makes the + * stack frame look nicer. If this was initialised in the first stack + * frame, or if the unwinder was taught the first stack frame always + * returns to user with IRQS_ENABLED, this store could be avoided! + */ + irq_soft_mask_regs_set_state(regs, IRQS_ENABLED); + + /* + * If system call is called with TM active, set _TIF_RESTOREALL to + * prevent RFSCV being used to return to userspace, because POWER9 + * TM implementation has problems with this instruction returning to + * transactional state. Final register values are not relevant because + * the transaction will be aborted upon return anyway. Or in the case + * of unsupported_scv SIGILL fault, the return state does not much + * matter because it's an edge case. + */ + if (IS_ENABLED(CONFIG_PPC_TRANSACTIONAL_MEM) && + unlikely(MSR_TM_TRANSACTIONAL(regs->msr))) + set_bits(_TIF_RESTOREALL, ¤t_thread_info()->flags); + + /* + * If the system call was made with a transaction active, doom it and + * return without performing the system call. Unless it was an + * unsupported scv vector, in which case it's treated like an illegal + * instruction. + */ +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (unlikely(MSR_TM_TRANSACTIONAL(regs->msr)) && + !trap_is_unsupported_scv(regs)) { + /* Enable TM in the kernel, and disable EE (for scv) */ + hard_irq_disable(); + mtmsr(mfmsr() | MSR_TM); + + /* tabort, this dooms the transaction, nothing else */ + asm volatile(".long 0x7c00071d | ((%0) << 16)" + :: "r"(TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT)); + + /* + * Userspace will never see the return value. Execution will + * resume after the tbegin. of the aborted transaction with the + * checkpointed register state. A context switch could occur + * or signal delivered to the process before resuming the + * doomed transaction context, but that should all be handled + * as expected. + */ + return -ENOSYS; + } +#endif // CONFIG_PPC_TRANSACTIONAL_MEM + + local_irq_enable(); + + if (unlikely(read_thread_flags() & _TIF_SYSCALL_DOTRACE)) { + if (unlikely(trap_is_unsupported_scv(regs))) { + /* Unsupported scv vector */ + _exception(SIGILL, regs, ILL_ILLOPC, regs->nip); + return regs->gpr[3]; + } + /* + * We use the return value of do_syscall_trace_enter() as the + * syscall number. If the syscall was rejected for any reason + * do_syscall_trace_enter() returns an invalid syscall number + * and the test against NR_syscalls will fail and the return + * value to be used is in regs->gpr[3]. + */ + r0 = do_syscall_trace_enter(regs); + if (unlikely(r0 >= NR_syscalls)) + return regs->gpr[3]; + + } else if (unlikely(r0 >= NR_syscalls)) { + if (unlikely(trap_is_unsupported_scv(regs))) { + /* Unsupported scv vector */ + _exception(SIGILL, regs, ILL_ILLOPC, regs->nip); + return regs->gpr[3]; + } + return -ENOSYS; + } + + /* May be faster to do array_index_nospec? */ + barrier_nospec(); + +#ifdef CONFIG_ARCH_HAS_SYSCALL_WRAPPER + // No COMPAT if we have SYSCALL_WRAPPER, see Kconfig + f = (void *)sys_call_table[r0]; + ret = f(regs); +#else + if (unlikely(is_compat_task())) { + unsigned long r3, r4, r5, r6, r7, r8; + + f = (void *)compat_sys_call_table[r0]; + + r3 = regs->gpr[3] & 0x00000000ffffffffULL; + r4 = regs->gpr[4] & 0x00000000ffffffffULL; + r5 = regs->gpr[5] & 0x00000000ffffffffULL; + r6 = regs->gpr[6] & 0x00000000ffffffffULL; + r7 = regs->gpr[7] & 0x00000000ffffffffULL; + r8 = regs->gpr[8] & 0x00000000ffffffffULL; + + ret = f(r3, r4, r5, r6, r7, r8); + } else { + f = (void *)sys_call_table[r0]; + + ret = f(regs->gpr[3], regs->gpr[4], regs->gpr[5], + regs->gpr[6], regs->gpr[7], regs->gpr[8]); + } +#endif + + /* + * Ultimately, this value will get limited by KSTACK_OFFSET_MAX(), + * so the maximum stack offset is 1k bytes (10 bits). + * + * The actual entropy will be further reduced by the compiler when + * applying stack alignment constraints: the powerpc architecture + * may have two kinds of stack alignment (16-bytes and 8-bytes). + * + * So the resulting 6 or 7 bits of entropy is seen in SP[9:4] or SP[9:3]. + */ + choose_random_kstack_offset(mftb()); + + return ret; +} diff --git a/arch/powerpc/kernel/syscalls.c b/arch/powerpc/kernel/syscalls.c index 825931e400df..68ebb23a5af4 100644 --- a/arch/powerpc/kernel/syscalls.c +++ b/arch/powerpc/kernel/syscalls.c @@ -35,11 +35,10 @@ #include <asm/syscalls.h> #include <asm/time.h> #include <asm/unistd.h> -#include <asm/asm-prototypes.h> -static inline long do_mmap2(unsigned long addr, size_t len, - unsigned long prot, unsigned long flags, - unsigned long fd, unsigned long off, int shift) +static long do_mmap2(unsigned long addr, size_t len, + unsigned long prot, unsigned long flags, + unsigned long fd, unsigned long off, int shift) { if (!arch_validate_prot(prot, addr)) return -EINVAL; @@ -57,6 +56,16 @@ SYSCALL_DEFINE6(mmap2, unsigned long, addr, size_t, len, return do_mmap2(addr, len, prot, flags, fd, pgoff, PAGE_SHIFT-12); } +#ifdef CONFIG_COMPAT +COMPAT_SYSCALL_DEFINE6(mmap2, + unsigned long, addr, size_t, len, + unsigned long, prot, unsigned long, flags, + unsigned long, fd, unsigned long, off_4k) +{ + return do_mmap2(addr, len, prot, flags, fd, off_4k, PAGE_SHIFT-12); +} +#endif + SYSCALL_DEFINE6(mmap, unsigned long, addr, size_t, len, unsigned long, prot, unsigned long, flags, unsigned long, fd, off_t, offset) @@ -64,43 +73,39 @@ SYSCALL_DEFINE6(mmap, unsigned long, addr, size_t, len, return do_mmap2(addr, len, prot, flags, fd, offset, PAGE_SHIFT); } -#ifdef CONFIG_PPC32 -/* - * Due to some executables calling the wrong select we sometimes - * get wrong args. This determines how the args are being passed - * (a single ptr to them all args passed) then calls - * sys_select() with the appropriate args. -- Cort - */ -int -ppc_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct __kernel_old_timeval __user *tvp) -{ - if ( (unsigned long)n >= 4096 ) - return sys_old_select((void __user *)n); - - return sys_select(n, inp, outp, exp, tvp); -} -#endif - #ifdef CONFIG_PPC64 -long ppc64_personality(unsigned long personality) +static long do_ppc64_personality(unsigned long personality) { long ret; if (personality(current->personality) == PER_LINUX32 && personality(personality) == PER_LINUX) personality = (personality & ~PER_MASK) | PER_LINUX32; - ret = sys_personality(personality); + ret = ksys_personality(personality); if (personality(ret) == PER_LINUX32) ret = (ret & ~PER_MASK) | PER_LINUX; return ret; } -#endif -long ppc_fadvise64_64(int fd, int advice, u32 offset_high, u32 offset_low, - u32 len_high, u32 len_low) +SYSCALL_DEFINE1(ppc64_personality, unsigned long, personality) +{ + return do_ppc64_personality(personality); +} + +#ifdef CONFIG_COMPAT +COMPAT_SYSCALL_DEFINE1(ppc64_personality, unsigned long, personality) +{ + return do_ppc64_personality(personality); +} +#endif /* CONFIG_COMPAT */ +#endif /* CONFIG_PPC64 */ + +SYSCALL_DEFINE6(ppc_fadvise64_64, + int, fd, int, advice, u32, offset_high, u32, offset_low, + u32, len_high, u32, len_low) { - return ksys_fadvise64_64(fd, (u64)offset_high << 32 | offset_low, - (u64)len_high << 32 | len_low, advice); + return ksys_fadvise64_64(fd, merge_64(offset_high, offset_low), + merge_64(len_high, len_low), advice); } SYSCALL_DEFINE0(switch_endian) diff --git a/arch/powerpc/kernel/syscalls/Makefile b/arch/powerpc/kernel/syscalls/Makefile index 5476f62eb80f..9d7bd81510b8 100644 --- a/arch/powerpc/kernel/syscalls/Makefile +++ b/arch/powerpc/kernel/syscalls/Makefile @@ -2,8 +2,7 @@ kapi := arch/$(SRCARCH)/include/generated/asm uapi := arch/$(SRCARCH)/include/generated/uapi/asm -_dummy := $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') \ - $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)') +$(shell mkdir -p $(uapi) $(kapi)) syscall := $(src)/syscall.tbl syshdr := $(srctree)/scripts/syscallhdr.sh diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index 15109af9d075..a0be127475b1 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -110,7 +110,7 @@ 79 common settimeofday sys_settimeofday compat_sys_settimeofday 80 common getgroups sys_getgroups 81 common setgroups sys_setgroups -82 32 select ppc_select sys_ni_syscall +82 32 select sys_old_select compat_sys_old_select 82 64 select sys_ni_syscall 82 spu select sys_ni_syscall 83 common symlink sys_symlink @@ -178,9 +178,9 @@ 133 common fchdir sys_fchdir 134 common bdflush sys_ni_syscall 135 common sysfs sys_sysfs -136 32 personality sys_personality ppc64_personality -136 64 personality ppc64_personality -136 spu personality ppc64_personality +136 32 personality sys_personality compat_sys_ppc64_personality +136 64 personality sys_ppc64_personality +136 spu personality sys_ppc64_personality 137 common afs_syscall sys_ni_syscall 138 common setfsuid sys_setfsuid 139 common setfsgid sys_setfsgid @@ -228,8 +228,10 @@ 176 64 rt_sigtimedwait sys_rt_sigtimedwait 177 nospu rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo 178 nospu rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend -179 common pread64 sys_pread64 compat_sys_pread64 -180 common pwrite64 sys_pwrite64 compat_sys_pwrite64 +179 32 pread64 sys_ppc_pread64 compat_sys_ppc_pread64 +179 64 pread64 sys_pread64 +180 32 pwrite64 sys_ppc_pwrite64 compat_sys_ppc_pwrite64 +180 64 pwrite64 sys_pwrite64 181 common chown sys_chown 182 common getcwd sys_getcwd 183 common capget sys_capget @@ -242,10 +244,11 @@ 188 common putpmsg sys_ni_syscall 189 nospu vfork sys_vfork 190 common ugetrlimit sys_getrlimit compat_sys_getrlimit -191 common readahead sys_readahead compat_sys_readahead +191 32 readahead sys_ppc_readahead compat_sys_ppc_readahead +191 64 readahead sys_readahead 192 32 mmap2 sys_mmap2 compat_sys_mmap2 -193 32 truncate64 sys_truncate64 compat_sys_truncate64 -194 32 ftruncate64 sys_ftruncate64 compat_sys_ftruncate64 +193 32 truncate64 sys_ppc_truncate64 compat_sys_ppc_truncate64 +194 32 ftruncate64 sys_ppc_ftruncate64 compat_sys_ppc_ftruncate64 195 32 stat64 sys_stat64 196 32 lstat64 sys_lstat64 197 32 fstat64 sys_fstat64 @@ -288,7 +291,8 @@ 230 common io_submit sys_io_submit compat_sys_io_submit 231 common io_cancel sys_io_cancel 232 nospu set_tid_address sys_set_tid_address -233 common fadvise64 sys_fadvise64 ppc32_fadvise64 +233 32 fadvise64 sys_ppc32_fadvise64 compat_sys_ppc32_fadvise64 +233 64 fadvise64 sys_fadvise64 234 nospu exit_group sys_exit_group 235 nospu lookup_dcookie sys_lookup_dcookie compat_sys_lookup_dcookie 236 common epoll_create sys_epoll_create @@ -323,7 +327,7 @@ 251 spu utimes sys_utimes 252 common statfs64 sys_statfs64 compat_sys_statfs64 253 common fstatfs64 sys_fstatfs64 compat_sys_fstatfs64 -254 32 fadvise64_64 ppc_fadvise64_64 +254 32 fadvise64_64 sys_ppc_fadvise64_64 254 spu fadvise64_64 sys_ni_syscall 255 common rtas sys_rtas 256 32 sys_debug_setcontext sys_debug_setcontext sys_ni_syscall @@ -390,8 +394,11 @@ 305 common signalfd sys_signalfd compat_sys_signalfd 306 common timerfd_create sys_timerfd_create 307 common eventfd sys_eventfd -308 common sync_file_range2 sys_sync_file_range2 compat_sys_sync_file_range2 -309 nospu fallocate sys_fallocate compat_sys_fallocate +308 32 sync_file_range2 sys_ppc_sync_file_range2 compat_sys_ppc_sync_file_range2 +308 64 sync_file_range2 sys_sync_file_range2 +308 spu sync_file_range2 sys_sync_file_range2 +309 32 fallocate sys_ppc_fallocate compat_sys_fallocate +309 64 fallocate sys_fallocate 310 nospu subpage_prot sys_subpage_prot 311 32 timerfd_settime sys_timerfd_settime32 311 64 timerfd_settime sys_timerfd_settime @@ -529,3 +536,4 @@ # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv +450 nospu set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index 08d8072d6e7a..ef9a61718940 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -9,12 +9,12 @@ #include <linux/nodemask.h> #include <linux/cpumask.h> #include <linux/notifier.h> +#include <linux/of.h> #include <asm/current.h> #include <asm/processor.h> #include <asm/cputable.h> #include <asm/hvcall.h> -#include <asm/prom.h> #include <asm/machdep.h> #include <asm/smp.h> #include <asm/pmc.h> @@ -214,7 +214,7 @@ static ssize_t __used store_dscr_default(struct device *dev, static DEVICE_ATTR(dscr_default, 0600, show_dscr_default, store_dscr_default); -static void sysfs_create_dscr_default(void) +static void __init sysfs_create_dscr_default(void) { if (cpu_has_feature(CPU_FTR_DSCR)) { int cpu; @@ -228,7 +228,7 @@ static void sysfs_create_dscr_default(void) } #endif /* CONFIG_PPC64 */ -#ifdef CONFIG_PPC_FSL_BOOK3E +#ifdef CONFIG_PPC_E500 #define MAX_BIT 63 static u64 pw20_wt; @@ -744,12 +744,12 @@ static ssize_t show_svm(struct device *dev, struct device_attribute *attr, char } static DEVICE_ATTR(svm, 0444, show_svm, NULL); -static void create_svm_file(void) +static void __init create_svm_file(void) { device_create_file(cpu_subsys.dev_root, &dev_attr_svm); } #else -static void create_svm_file(void) +static void __init create_svm_file(void) { } #endif /* CONFIG_PPC_SVM */ @@ -907,7 +907,7 @@ static int register_cpu_online(unsigned int cpu) device_create_file(s, &dev_attr_tscr); #endif /* CONFIG_PPC64 */ -#ifdef CONFIG_PPC_FSL_BOOK3E +#ifdef CONFIG_PPC_E500 if (PVR_VER(cur_cpu_spec->pvr_value) == PVR_VER_E6500) { device_create_file(s, &dev_attr_pw20_state); device_create_file(s, &dev_attr_pw20_wait_time); @@ -1003,7 +1003,7 @@ static int unregister_cpu_online(unsigned int cpu) device_remove_file(s, &dev_attr_tscr); #endif /* CONFIG_PPC64 */ -#ifdef CONFIG_PPC_FSL_BOOK3E +#ifdef CONFIG_PPC_E500 if (PVR_VER(cur_cpu_spec->pvr_value) == PVR_VER_E6500) { device_remove_file(s, &dev_attr_pw20_state); device_remove_file(s, &dev_attr_pw20_wait_time); @@ -1110,14 +1110,6 @@ EXPORT_SYMBOL_GPL(cpu_remove_dev_attr_group); /* NUMA stuff */ #ifdef CONFIG_NUMA -static void register_nodes(void) -{ - int i; - - for (i = 0; i < MAX_NUMNODES; i++) - register_one_node(i); -} - int sysfs_add_device_to_node(struct device *dev, int nid) { struct node *node = node_devices[nid]; @@ -1132,13 +1124,6 @@ void sysfs_remove_device_from_node(struct device *dev, int nid) sysfs_remove_link(&node->dev.kobj, kobject_name(&dev->kobj)); } EXPORT_SYMBOL_GPL(sysfs_remove_device_from_node); - -#else -static void register_nodes(void) -{ - return; -} - #endif /* Only valid if CPU is present. */ @@ -1155,8 +1140,6 @@ static int __init topology_init(void) { int cpu, r; - register_nodes(); - for_each_possible_cpu(cpu) { struct cpu *c = &per_cpu(cpu_devices, cpu); diff --git a/arch/powerpc/kernel/systbl.S b/arch/powerpc/kernel/systbl.c index cb3358886203..4305f2a2162f 100644 --- a/arch/powerpc/kernel/systbl.S +++ b/arch/powerpc/kernel/systbl.c @@ -10,31 +10,37 @@ * PPC64 updates by Dave Engebretsen (engebret@us.ibm.com) */ -#include <asm/ppc_asm.h> +#include <linux/syscalls.h> +#include <linux/compat.h> +#include <asm/unistd.h> +#include <asm/syscalls.h> -.section .rodata,"a" +#undef __SYSCALL_WITH_COMPAT +#define __SYSCALL_WITH_COMPAT(nr, entry, compat) __SYSCALL(nr, entry) -#ifdef CONFIG_PPC64 - .p2align 3 -#define __SYSCALL(nr, entry) .8byte entry +#undef __SYSCALL +#ifdef CONFIG_ARCH_HAS_SYSCALL_WRAPPER +#define __SYSCALL(nr, entry) [nr] = entry, #else -#define __SYSCALL(nr, entry) .long entry +/* + * Coerce syscall handlers with arbitrary parameters to common type + * requires cast to void* to avoid -Wcast-function-type. + */ +#define __SYSCALL(nr, entry) [nr] = (void *) entry, #endif -#define __SYSCALL_WITH_COMPAT(nr, native, compat) __SYSCALL(nr, native) -.globl sys_call_table -sys_call_table: +const syscall_fn sys_call_table[] = { #ifdef CONFIG_PPC64 #include <asm/syscall_table_64.h> #else #include <asm/syscall_table_32.h> #endif +}; #ifdef CONFIG_COMPAT #undef __SYSCALL_WITH_COMPAT #define __SYSCALL_WITH_COMPAT(nr, native, compat) __SYSCALL(nr, compat) -.globl compat_sys_call_table -compat_sys_call_table: -#define compat_sys_sigsuspend sys_sigsuspend +const syscall_fn compat_sys_call_table[] = { #include <asm/syscall_table_32.h> -#endif +}; +#endif /* CONFIG_COMPAT */ diff --git a/arch/powerpc/kernel/systbl_chk.sh b/arch/powerpc/kernel/systbl_chk.sh deleted file mode 100644 index c7ac3ed657c4..000000000000 --- a/arch/powerpc/kernel/systbl_chk.sh +++ /dev/null @@ -1,30 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0-or-later -# -# Just process the CPP output from systbl_chk.c and complain -# if anything is out of order. -# -# Copyright © 2008 IBM Corporation -# - -awk 'BEGIN { num = -1; } # Ignore the beginning of the file - /^#/ { next; } - /^[ \t]*$/ { next; } - /^START_TABLE/ { num = 0; next; } - /^END_TABLE/ { - if (num != $2) { - printf "Error: NR_syscalls (%s) is not one more than the last syscall (%s)\n", - $2, num - 1; - exit(1); - } - num = -1; # Ignore the rest of the file - } - { - if (num == -1) next; - if (($1 != -1) && ($1 != num)) { - printf "Error: Syscall %s out of order (expected %s)\n", - $1, num; - exit(1); - }; - num++; - }' "$1" diff --git a/arch/powerpc/kernel/tau_6xx.c b/arch/powerpc/kernel/tau_6xx.c index 8e83d19fe8fa..828d0f4106d2 100644 --- a/arch/powerpc/kernel/tau_6xx.c +++ b/arch/powerpc/kernel/tau_6xx.c @@ -29,7 +29,6 @@ #include <asm/cache.h> #include <asm/8xx_immap.h> #include <asm/machdep.h> -#include <asm/asm-prototypes.h> #include "setup.h" diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index cae8f03a44fe..a2ab397065c6 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -54,8 +54,10 @@ #include <linux/of_clk.h> #include <linux/suspend.h> #include <linux/processor.h> -#include <asm/trace.h> +#include <linux/mc146818rtc.h> +#include <linux/platform_device.h> +#include <asm/trace.h> #include <asm/interrupt.h> #include <asm/io.h> #include <asm/nvram.h> @@ -63,13 +65,12 @@ #include <asm/machdep.h> #include <linux/uaccess.h> #include <asm/time.h> -#include <asm/prom.h> #include <asm/irq.h> #include <asm/div64.h> #include <asm/smp.h> #include <asm/vdso_datapage.h> #include <asm/firmware.h> -#include <asm/asm-prototypes.h> +#include <asm/mce.h> /* powerpc clocksource/clockevent code */ @@ -88,6 +89,7 @@ static struct clocksource clocksource_timebase = { #define DECREMENTER_DEFAULT_MAX 0x7FFFFFFF u64 decrementer_max = DECREMENTER_DEFAULT_MAX; +EXPORT_SYMBOL_GPL(decrementer_max); /* for KVM HDEC */ static int decrementer_set_next_event(unsigned long evt, struct clock_event_device *dev); @@ -106,7 +108,13 @@ struct clock_event_device decrementer_clockevent = { }; EXPORT_SYMBOL(decrementer_clockevent); -DEFINE_PER_CPU(u64, decrementers_next_tb); +/* + * This always puts next_tb beyond now, so the clock event will never fire + * with the usual comparison, no need for a separate test for stopped. + */ +#define DEC_CLOCKEVENT_STOPPED ~0ULL +DEFINE_PER_CPU(u64, decrementers_next_tb) = DEC_CLOCKEVENT_STOPPED; +EXPORT_SYMBOL_GPL(decrementers_next_tb); static DEFINE_PER_CPU(struct clock_event_device, decrementers); #define XSEC_PER_SEC (1024*1024) @@ -149,10 +157,6 @@ bool tb_invalid; u64 __cputime_usec_factor; EXPORT_SYMBOL(__cputime_usec_factor); -#ifdef CONFIG_PPC_SPLPAR -void (*dtl_consumer)(struct dtl_entry *, u64); -#endif - static void calc_cputime_factors(void) { struct div_result res; @@ -174,90 +178,6 @@ static inline unsigned long read_spurr(unsigned long tb) return tb; } -#ifdef CONFIG_PPC_SPLPAR - -#include <asm/dtl.h> - -/* - * Scan the dispatch trace log and count up the stolen time. - * Should be called with interrupts disabled. - */ -static u64 scan_dispatch_log(u64 stop_tb) -{ - u64 i = local_paca->dtl_ridx; - struct dtl_entry *dtl = local_paca->dtl_curr; - struct dtl_entry *dtl_end = local_paca->dispatch_log_end; - struct lppaca *vpa = local_paca->lppaca_ptr; - u64 tb_delta; - u64 stolen = 0; - u64 dtb; - - if (!dtl) - return 0; - - if (i == be64_to_cpu(vpa->dtl_idx)) - return 0; - while (i < be64_to_cpu(vpa->dtl_idx)) { - dtb = be64_to_cpu(dtl->timebase); - tb_delta = be32_to_cpu(dtl->enqueue_to_dispatch_time) + - be32_to_cpu(dtl->ready_to_enqueue_time); - barrier(); - if (i + N_DISPATCH_LOG < be64_to_cpu(vpa->dtl_idx)) { - /* buffer has overflowed */ - i = be64_to_cpu(vpa->dtl_idx) - N_DISPATCH_LOG; - dtl = local_paca->dispatch_log + (i % N_DISPATCH_LOG); - continue; - } - if (dtb > stop_tb) - break; - if (dtl_consumer) - dtl_consumer(dtl, i); - stolen += tb_delta; - ++i; - ++dtl; - if (dtl == dtl_end) - dtl = local_paca->dispatch_log; - } - local_paca->dtl_ridx = i; - local_paca->dtl_curr = dtl; - return stolen; -} - -/* - * Accumulate stolen time by scanning the dispatch trace log. - * Called on entry from user mode. - */ -void notrace accumulate_stolen_time(void) -{ - u64 sst, ust; - struct cpu_accounting_data *acct = &local_paca->accounting; - - sst = scan_dispatch_log(acct->starttime_user); - ust = scan_dispatch_log(acct->starttime); - acct->stime -= sst; - acct->utime -= ust; - acct->steal_time += ust + sst; -} - -static inline u64 calculate_stolen_time(u64 stop_tb) -{ - if (!firmware_has_feature(FW_FEATURE_SPLPAR)) - return 0; - - if (get_paca()->dtl_ridx != be64_to_cpu(get_lppaca()->dtl_idx)) - return scan_dispatch_log(stop_tb); - - return 0; -} - -#else /* CONFIG_PPC_SPLPAR */ -static inline u64 calculate_stolen_time(u64 stop_tb) -{ - return 0; -} - -#endif /* CONFIG_PPC_SPLPAR */ - /* * Account time for a transition between system, hard irq * or soft irq state. @@ -316,7 +236,11 @@ static unsigned long vtime_delta(struct cpu_accounting_data *acct, *stime_scaled = vtime_delta_scaled(acct, now, stime); - *steal_time = calculate_stolen_time(now); + if (IS_ENABLED(CONFIG_PPC_SPLPAR) && + firmware_has_feature(FW_FEATURE_SPLPAR)) + *steal_time = pseries_calculate_stolen_time(now); + else + *steal_time = 0; return stime; } @@ -496,6 +420,16 @@ EXPORT_SYMBOL(profile_pc); * 64-bit uses a byte in the PACA, 32-bit uses a per-cpu variable... */ #ifdef CONFIG_PPC64 +static inline unsigned long test_irq_work_pending(void) +{ + unsigned long x; + + asm volatile("lbz %0,%1(13)" + : "=r" (x) + : "i" (offsetof(struct paca_struct, irq_work_pending))); + return x; +} + static inline void set_irq_work_pending_flag(void) { asm volatile("stb %0,%1(13)" : : @@ -539,13 +473,45 @@ void arch_irq_work_raise(void) preempt_enable(); } +static void set_dec_or_work(u64 val) +{ + set_dec(val); + /* We may have raced with new irq work */ + if (unlikely(test_irq_work_pending())) + set_dec(1); +} + #else /* CONFIG_IRQ_WORK */ #define test_irq_work_pending() 0 #define clear_irq_work_pending() +static void set_dec_or_work(u64 val) +{ + set_dec(val); +} #endif /* CONFIG_IRQ_WORK */ +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE +void timer_rearm_host_dec(u64 now) +{ + u64 *next_tb = this_cpu_ptr(&decrementers_next_tb); + + WARN_ON_ONCE(!arch_irqs_disabled()); + WARN_ON_ONCE(mfmsr() & MSR_EE); + + if (now >= *next_tb) { + local_paca->irq_happened |= PACA_IRQ_DEC; + } else { + now = *next_tb - now; + if (now > decrementer_max) + now = decrementer_max; + set_dec_or_work(now); + } +} +EXPORT_SYMBOL_GPL(timer_rearm_host_dec); +#endif + /* * timer_interrupt - gets called when the decrementer overflows, * with interrupts disabled. @@ -566,22 +532,23 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt) return; } - /* Ensure a positive value is written to the decrementer, or else - * some CPUs will continue to take decrementer exceptions. When the - * PPC_WATCHDOG (decrementer based) is configured, keep this at most - * 31 bits, which is about 4 seconds on most systems, which gives - * the watchdog a chance of catching timer interrupt hard lockups. - */ - if (IS_ENABLED(CONFIG_PPC_WATCHDOG)) - set_dec(0x7fffffff); - else - set_dec(decrementer_max); - - /* Conditionally hard-enable interrupts now that the DEC has been - * bumped to its maximum value - */ - may_hard_irq_enable(); + /* Conditionally hard-enable interrupts. */ + if (should_hard_irq_enable()) { + /* + * Ensure a positive value is written to the decrementer, or + * else some CPUs will continue to take decrementer exceptions. + * When the PPC_WATCHDOG (decrementer based) is configured, + * keep this at most 31 bits, which is about 4 seconds on most + * systems, which gives the watchdog a chance of catching timer + * interrupt hard lockups. + */ + if (IS_ENABLED(CONFIG_PPC_WATCHDOG)) + set_dec(0x7fffffff); + else + set_dec(decrementer_max); + do_hard_irq_enable(); + } #if defined(CONFIG_PPC32) && defined(CONFIG_PPC_PMAC) if (atomic_read(&ppc_n_lost_interrupts) != 0) @@ -594,22 +561,19 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt) if (test_irq_work_pending()) { clear_irq_work_pending(); + mce_run_irq_context_handlers(); irq_work_run(); } now = get_tb(); if (now >= *next_tb) { - *next_tb = ~(u64)0; - if (evt->event_handler) - evt->event_handler(evt); + evt->event_handler(evt); __this_cpu_inc(irq_stat.timer_irqs_event); } else { now = *next_tb - now; - if (now <= decrementer_max) - set_dec(now); - /* We may have raced with new irq work */ - if (test_irq_work_pending()) - set_dec(1); + if (now > decrementer_max) + now = decrementer_max; + set_dec_or_work(now); __this_cpu_inc(irq_stat.timer_irqs_others); } @@ -622,9 +586,6 @@ EXPORT_SYMBOL(timer_interrupt); #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST void timer_broadcast_interrupt(void) { - u64 *next_tb = this_cpu_ptr(&decrementers_next_tb); - - *next_tb = ~(u64)0; tick_receive_broadcast(); __this_cpu_inc(irq_stat.broadcast_irqs_event); } @@ -730,7 +691,7 @@ static int __init get_freq(char *name, int cells, unsigned long *val) static void start_cpu_decrementer(void) { -#if defined(CONFIG_BOOKE) || defined(CONFIG_40x) +#ifdef CONFIG_BOOKE_OR_40x unsigned int tcr; /* Clear any pending timer interrupts */ @@ -786,7 +747,7 @@ static void __read_persistent_clock(struct timespec64 *ts) static int first = 1; ts->tv_nsec = 0; - /* XXX this is a litle fragile but will work okay in the short term */ + /* XXX this is a little fragile but will work okay in the short term */ if (first) { first = 0; if (ppc_md.time_init) @@ -843,18 +804,16 @@ static int decrementer_set_next_event(unsigned long evt, struct clock_event_device *dev) { __this_cpu_write(decrementers_next_tb, get_tb() + evt); - set_dec(evt); - - /* We may have raced with new irq work */ - if (test_irq_work_pending()) - set_dec(1); + set_dec_or_work(evt); return 0; } static int decrementer_shutdown(struct clock_event_device *dev) { - decrementer_set_next_event(decrementer_max, dev); + __this_cpu_write(decrementers_next_tb, DEC_CLOCKEVENT_STOPPED); + set_dec_or_work(decrementer_max); + return 0; } @@ -933,7 +892,7 @@ void secondary_cpu_time_init(void) */ start_cpu_decrementer(); - /* FIME: Should make unrelatred change to move snapshot_timebase + /* FIME: Should make unrelated change to move snapshot_timebase * call here ! */ register_decrementer_clockevent(smp_processor_id()); } diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S index 2b91f233b05d..5a0f023a26e9 100644 --- a/arch/powerpc/kernel/tm.S +++ b/arch/powerpc/kernel/tm.S @@ -226,11 +226,8 @@ _GLOBAL(tm_reclaim) /* Sync the userland GPRs 2-12, 14-31 to thread->regs: */ SAVE_GPR(0, r7) /* user r0 */ - SAVE_GPR(2, r7) /* user r2 */ - SAVE_4GPRS(3, r7) /* user r3-r6 */ - SAVE_GPR(8, r7) /* user r8 */ - SAVE_GPR(9, r7) /* user r9 */ - SAVE_GPR(10, r7) /* user r10 */ + SAVE_GPRS(2, 6, r7) /* user r2-r6 */ + SAVE_GPRS(8, 10, r7) /* user r8-r10 */ ld r3, GPR1(r1) /* user r1 */ ld r4, GPR7(r1) /* user r7 */ ld r5, GPR11(r1) /* user r11 */ @@ -445,12 +442,9 @@ restore_gprs: ld r6, THREAD_TM_PPR(r3) REST_GPR(0, r7) /* GPR0 */ - REST_2GPRS(2, r7) /* GPR2-3 */ - REST_GPR(4, r7) /* GPR4 */ - REST_4GPRS(8, r7) /* GPR8-11 */ - REST_2GPRS(12, r7) /* GPR12-13 */ - - REST_NVGPRS(r7) /* GPR14-31 */ + REST_GPRS(2, 4, r7) /* GPR2-4 */ + REST_GPRS(8, 12, r7) /* GPR8-12 */ + REST_GPRS(14, 31, r7) /* GPR14-31 */ /* Load up PPR and DSCR here so we don't run with user values for long */ mtspr SPRN_DSCR, r5 @@ -486,18 +480,24 @@ restore_gprs: REST_GPR(6, r7) /* - * Store r1 and r5 on the stack so that we can access them after we - * clear MSR RI. + * Store user r1 and r5 and r13 on the stack (in the unused save + * areas / compiler reserved areas), so that we can access them after + * we clear MSR RI. */ REST_GPR(5, r7) std r5, -8(r1) - ld r5, GPR1(r7) + ld r5, GPR13(r7) std r5, -16(r1) + ld r5, GPR1(r7) + std r5, -24(r1) REST_GPR(7, r7) - /* Clear MSR RI since we are about to use SCRATCH0. EE is already off */ + /* Stash the stack pointer away for use after recheckpoint */ + std r1, PACAR1(r13) + + /* Clear MSR RI since we are about to clobber r13. EE is already off */ li r5, 0 mtmsrd r5, 1 @@ -508,9 +508,9 @@ restore_gprs: * until we turn MSR RI back on. */ - SET_SCRATCH0(r1) ld r5, -8(r1) - ld r1, -16(r1) + ld r13, -16(r1) + ld r1, -24(r1) /* Commit register state as checkpointed state: */ TRECHKPT @@ -526,9 +526,9 @@ restore_gprs: */ GET_PACA(r13) - GET_SCRATCH0(r1) + ld r1, PACAR1(r13) - /* R1 is restored, so we are recoverable again. EE is still off */ + /* R13, R1 is restored, so we are recoverable again. EE is still off */ li r4, MSR_RI mtmsrd r4, 1 diff --git a/arch/powerpc/kernel/trace/Makefile b/arch/powerpc/kernel/trace/Makefile index 858503775c58..af8527538fe4 100644 --- a/arch/powerpc/kernel/trace/Makefile +++ b/arch/powerpc/kernel/trace/Makefile @@ -8,16 +8,13 @@ ifdef CONFIG_FUNCTION_TRACER CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE) endif -obj32-$(CONFIG_FUNCTION_TRACER) += ftrace_32.o -obj64-$(CONFIG_FUNCTION_TRACER) += ftrace_64.o +obj32-$(CONFIG_FUNCTION_TRACER) += ftrace_mprofile.o ifdef CONFIG_MPROFILE_KERNEL -obj64-$(CONFIG_FUNCTION_TRACER) += ftrace_64_mprofile.o +obj64-$(CONFIG_FUNCTION_TRACER) += ftrace_mprofile.o else obj64-$(CONFIG_FUNCTION_TRACER) += ftrace_64_pg.o endif -obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o -obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o -obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o +obj-$(CONFIG_FUNCTION_TRACER) += ftrace_low.o ftrace.o obj-$(CONFIG_TRACING) += trace_clock.o obj-$(CONFIG_PPC64) += $(obj64-y) diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c index d89c5df4f206..7b85c3b460a3 100644 --- a/arch/powerpc/kernel/trace/ftrace.c +++ b/arch/powerpc/kernel/trace/ftrace.c @@ -22,16 +22,12 @@ #include <linux/init.h> #include <linux/list.h> -#include <asm/asm-prototypes.h> #include <asm/cacheflush.h> #include <asm/code-patching.h> #include <asm/ftrace.h> #include <asm/syscall.h> #include <asm/inst.h> - -#ifdef CONFIG_DYNAMIC_FTRACE - /* * We generally only have a single long_branch tramp and at most 2 or 3 plt * tramps generated. But, we don't use the plt tramps currently. We also allot @@ -41,23 +37,23 @@ #define NUM_FTRACE_TRAMPS 8 static unsigned long ftrace_tramps[NUM_FTRACE_TRAMPS]; -static struct ppc_inst +static ppc_inst_t ftrace_call_replace(unsigned long ip, unsigned long addr, int link) { - struct ppc_inst op; + ppc_inst_t op; addr = ppc_function_entry((void *)addr); /* if (link) set op to 'bl' else 'b' */ - create_branch(&op, (u32 *)ip, addr, link ? 1 : 0); + create_branch(&op, (u32 *)ip, addr, link ? BRANCH_SET_LINK : 0); return op; } -static int -ftrace_modify_code(unsigned long ip, struct ppc_inst old, struct ppc_inst new) +static inline int +ftrace_modify_code(unsigned long ip, ppc_inst_t old, ppc_inst_t new) { - struct ppc_inst replaced; + ppc_inst_t replaced; /* * Note: @@ -73,16 +69,13 @@ ftrace_modify_code(unsigned long ip, struct ppc_inst old, struct ppc_inst new) /* Make sure it is what we expect it to be */ if (!ppc_inst_equal(replaced, old)) { - pr_err("%p: replaced (%s) != old (%s)", - (void *)ip, ppc_inst_as_str(replaced), ppc_inst_as_str(old)); + pr_err("%p: replaced (%08lx) != old (%08lx)", (void *)ip, + ppc_inst_as_ulong(replaced), ppc_inst_as_ulong(old)); return -EINVAL; } /* replace the text with the new text */ - if (patch_instruction((u32 *)ip, new)) - return -EPERM; - - return 0; + return patch_instruction((u32 *)ip, new); } /* @@ -90,28 +83,26 @@ ftrace_modify_code(unsigned long ip, struct ppc_inst old, struct ppc_inst new) */ static int test_24bit_addr(unsigned long ip, unsigned long addr) { - struct ppc_inst op; addr = ppc_function_entry((void *)addr); - /* use the create_branch to verify that this offset can be branched */ - return create_branch(&op, (u32 *)ip, addr, 0) == 0; + return is_offset_in_branch_range(addr - ip); } -static int is_bl_op(struct ppc_inst op) +static int is_bl_op(ppc_inst_t op) { - return (ppc_inst_val(op) & 0xfc000003) == 0x48000001; + return (ppc_inst_val(op) & ~PPC_LI_MASK) == PPC_RAW_BL(0); } -static int is_b_op(struct ppc_inst op) +static int is_b_op(ppc_inst_t op) { - return (ppc_inst_val(op) & 0xfc000003) == 0x48000000; + return (ppc_inst_val(op) & ~PPC_LI_MASK) == PPC_RAW_BRANCH(0); } -static unsigned long find_bl_target(unsigned long ip, struct ppc_inst op) +static unsigned long find_bl_target(unsigned long ip, ppc_inst_t op) { int offset; - offset = (ppc_inst_val(op) & 0x03fffffc); + offset = PPC_LI(ppc_inst_val(op)); /* make it signed */ if (offset & 0x02000000) offset |= 0xfe000000; @@ -120,14 +111,13 @@ static unsigned long find_bl_target(unsigned long ip, struct ppc_inst op) } #ifdef CONFIG_MODULES -#ifdef CONFIG_PPC64 static int __ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr) { unsigned long entry, ptr, tramp; unsigned long ip = rec->ip; - struct ppc_inst op, pop; + ppc_inst_t op, pop; /* read where this goes */ if (copy_inst_from_kernel_nofault(&op, (void *)ip)) { @@ -135,9 +125,9 @@ __ftrace_make_nop(struct module *mod, return -EFAULT; } - /* Make sure that that this is still a 24bit jump */ + /* Make sure that this is still a 24bit jump */ if (!is_bl_op(op)) { - pr_err("Not expected bl: opcode is %s\n", ppc_inst_as_str(op)); + pr_err("Not expected bl: opcode is %08lx\n", ppc_inst_as_ulong(op)); return -EINVAL; } @@ -160,25 +150,40 @@ __ftrace_make_nop(struct module *mod, return -EINVAL; } -#ifdef CONFIG_MPROFILE_KERNEL - /* When using -mkernel_profile there is no load to jump over */ - pop = ppc_inst(PPC_RAW_NOP()); + if (IS_ENABLED(CONFIG_MPROFILE_KERNEL)) { + if (copy_inst_from_kernel_nofault(&op, (void *)(ip - 4))) { + pr_err("Fetching instruction at %lx failed.\n", ip - 4); + return -EFAULT; + } - if (copy_inst_from_kernel_nofault(&op, (void *)(ip - 4))) { - pr_err("Fetching instruction at %lx failed.\n", ip - 4); - return -EFAULT; - } + /* We expect either a mflr r0, or a std r0, LRSAVE(r1) */ + if (!ppc_inst_equal(op, ppc_inst(PPC_RAW_MFLR(_R0))) && + !ppc_inst_equal(op, ppc_inst(PPC_INST_STD_LR))) { + pr_err("Unexpected instruction %08lx around bl _mcount\n", + ppc_inst_as_ulong(op)); + return -EINVAL; + } + } else if (IS_ENABLED(CONFIG_PPC64)) { + /* + * Check what is in the next instruction. We can see ld r2,40(r1), but + * on first pass after boot we will see mflr r0. + */ + if (copy_inst_from_kernel_nofault(&op, (void *)(ip + 4))) { + pr_err("Fetching op failed.\n"); + return -EFAULT; + } - /* We expect either a mflr r0, or a std r0, LRSAVE(r1) */ - if (!ppc_inst_equal(op, ppc_inst(PPC_RAW_MFLR(_R0))) && - !ppc_inst_equal(op, ppc_inst(PPC_INST_STD_LR))) { - pr_err("Unexpected instruction %s around bl _mcount\n", - ppc_inst_as_str(op)); - return -EINVAL; + if (!ppc_inst_equal(op, ppc_inst(PPC_INST_LD_TOC))) { + pr_err("Expected %08lx found %08lx\n", PPC_INST_LD_TOC, + ppc_inst_as_ulong(op)); + return -EINVAL; + } } -#else + /* - * Our original call site looks like: + * When using -mprofile-kernel or PPC32 there is no load to jump over. + * + * Otherwise our original call site looks like: * * bl <tramp> * ld r2,XX(r1) @@ -190,23 +195,10 @@ __ftrace_make_nop(struct module *mod, * * Use a b +8 to jump over the load. */ - - pop = ppc_inst(PPC_INST_BRANCH | 8); /* b +8 */ - - /* - * Check what is in the next instruction. We can see ld r2,40(r1), but - * on first pass after boot we will see mflr r0. - */ - if (copy_inst_from_kernel_nofault(&op, (void *)(ip + 4))) { - pr_err("Fetching op failed.\n"); - return -EFAULT; - } - - if (!ppc_inst_equal(op, ppc_inst(PPC_INST_LD_TOC))) { - pr_err("Expected %08lx found %s\n", PPC_INST_LD_TOC, ppc_inst_as_str(op)); - return -EINVAL; - } -#endif /* CONFIG_MPROFILE_KERNEL */ + if (IS_ENABLED(CONFIG_MPROFILE_KERNEL) || IS_ENABLED(CONFIG_PPC32)) + pop = ppc_inst(PPC_RAW_NOP()); + else + pop = ppc_inst(PPC_RAW_BRANCH(8)); /* b +8 */ if (patch_instruction((u32 *)ip, pop)) { pr_err("Patching NOP failed.\n"); @@ -215,83 +207,16 @@ __ftrace_make_nop(struct module *mod, return 0; } - -#else /* !PPC64 */ -static int -__ftrace_make_nop(struct module *mod, - struct dyn_ftrace *rec, unsigned long addr) +#else +static int __ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr) { - struct ppc_inst op; - unsigned int jmp[4]; - unsigned long ip = rec->ip; - unsigned long tramp; - - if (copy_from_kernel_nofault(&op, (void *)ip, MCOUNT_INSN_SIZE)) - return -EFAULT; - - /* Make sure that that this is still a 24bit jump */ - if (!is_bl_op(op)) { - pr_err("Not expected bl: opcode is %s\n", ppc_inst_as_str(op)); - return -EINVAL; - } - - /* lets find where the pointer goes */ - tramp = find_bl_target(ip, op); - - /* - * On PPC32 the trampoline looks like: - * 0x3d, 0x80, 0x00, 0x00 lis r12,sym@ha - * 0x39, 0x8c, 0x00, 0x00 addi r12,r12,sym@l - * 0x7d, 0x89, 0x03, 0xa6 mtctr r12 - * 0x4e, 0x80, 0x04, 0x20 bctr - */ - - pr_devel("ip:%lx jumps to %lx", ip, tramp); - - /* Find where the trampoline jumps to */ - if (copy_from_kernel_nofault(jmp, (void *)tramp, sizeof(jmp))) { - pr_err("Failed to read %lx\n", tramp); - return -EFAULT; - } - - pr_devel(" %08x %08x ", jmp[0], jmp[1]); - - /* verify that this is what we expect it to be */ - if (((jmp[0] & 0xffff0000) != 0x3d800000) || - ((jmp[1] & 0xffff0000) != 0x398c0000) || - (jmp[2] != 0x7d8903a6) || - (jmp[3] != 0x4e800420)) { - pr_err("Not a trampoline\n"); - return -EINVAL; - } - - tramp = (jmp[1] & 0xffff) | - ((jmp[0] & 0xffff) << 16); - if (tramp & 0x8000) - tramp -= 0x10000; - - pr_devel(" %lx ", tramp); - - if (tramp != addr) { - pr_err("Trampoline location %08lx does not match addr\n", - tramp); - return -EINVAL; - } - - op = ppc_inst(PPC_RAW_NOP()); - - if (patch_instruction((u32 *)ip, op)) - return -EPERM; - return 0; } -#endif /* PPC64 */ #endif /* CONFIG_MODULES */ static unsigned long find_ftrace_tramp(unsigned long ip) { int i; - struct ppc_inst instr; /* * We have the compiler generated long_branch tramps at the end @@ -300,8 +225,7 @@ static unsigned long find_ftrace_tramp(unsigned long ip) for (i = NUM_FTRACE_TRAMPS - 1; i >= 0; i--) if (!ftrace_tramps[i]) continue; - else if (create_branch(&instr, (void *)ip, - ftrace_tramps[i], 0) == 0) + else if (is_offset_in_branch_range(ftrace_tramps[i] - ip)) return ftrace_tramps[i]; return 0; @@ -329,25 +253,14 @@ static int add_ftrace_tramp(unsigned long tramp) static int setup_mcount_compiler_tramp(unsigned long tramp) { int i; - struct ppc_inst op; + ppc_inst_t op; unsigned long ptr; - struct ppc_inst instr; - static unsigned long ftrace_plt_tramps[NUM_FTRACE_TRAMPS]; /* Is this a known long jump tramp? */ for (i = 0; i < NUM_FTRACE_TRAMPS; i++) - if (!ftrace_tramps[i]) - break; - else if (ftrace_tramps[i] == tramp) + if (ftrace_tramps[i] == tramp) return 0; - /* Is this a known plt tramp? */ - for (i = 0; i < NUM_FTRACE_TRAMPS; i++) - if (!ftrace_plt_tramps[i]) - break; - else if (ftrace_plt_tramps[i] == tramp) - return -1; - /* New trampoline -- read where this goes */ if (copy_inst_from_kernel_nofault(&op, (void *)tramp)) { pr_debug("Fetching opcode failed.\n"); @@ -369,16 +282,10 @@ static int setup_mcount_compiler_tramp(unsigned long tramp) } /* Let's re-write the tramp to go to ftrace_[regs_]caller */ -#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS - ptr = ppc_global_function_entry((void *)ftrace_regs_caller); -#else - ptr = ppc_global_function_entry((void *)ftrace_caller); -#endif - if (create_branch(&instr, (void *)tramp, ptr, 0)) { - pr_debug("%ps is not reachable from existing mcount tramp\n", - (void *)ptr); - return -1; - } + if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS)) + ptr = ppc_global_function_entry((void *)ftrace_regs_caller); + else + ptr = ppc_global_function_entry((void *)ftrace_caller); if (patch_branch((u32 *)tramp, ptr, 0)) { pr_debug("REL24 out of range!\n"); @@ -396,7 +303,7 @@ static int setup_mcount_compiler_tramp(unsigned long tramp) static int __ftrace_make_nop_kernel(struct dyn_ftrace *rec, unsigned long addr) { unsigned long tramp, ip = rec->ip; - struct ppc_inst op; + ppc_inst_t op; /* Read where this goes */ if (copy_inst_from_kernel_nofault(&op, (void *)ip)) { @@ -404,9 +311,9 @@ static int __ftrace_make_nop_kernel(struct dyn_ftrace *rec, unsigned long addr) return -EFAULT; } - /* Make sure that that this is still a 24bit jump */ + /* Make sure that this is still a 24bit jump */ if (!is_bl_op(op)) { - pr_err("Not expected bl: opcode is %s\n", ppc_inst_as_str(op)); + pr_err("Not expected bl: opcode is %08lx\n", ppc_inst_as_ulong(op)); return -EINVAL; } @@ -436,7 +343,7 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr) { unsigned long ip = rec->ip; - struct ppc_inst old, new; + ppc_inst_t old, new; /* * If the calling address is more that 24 bits away, @@ -448,10 +355,12 @@ int ftrace_make_nop(struct module *mod, old = ftrace_call_replace(ip, addr, 1); new = ppc_inst(PPC_RAW_NOP()); return ftrace_modify_code(ip, old, new); - } else if (core_kernel_text(ip)) + } else if (core_kernel_text(ip)) { return __ftrace_make_nop_kernel(rec, addr); + } else if (!IS_ENABLED(CONFIG_MODULES)) { + return -EINVAL; + } -#ifdef CONFIG_MODULES /* * Out of range jumps are called from modules. * We should either already have a pointer to the module @@ -474,53 +383,27 @@ int ftrace_make_nop(struct module *mod, mod = rec->arch.mod; return __ftrace_make_nop(mod, rec, addr); -#else - /* We should not get here without modules */ - return -EINVAL; -#endif /* CONFIG_MODULES */ } #ifdef CONFIG_MODULES -#ifdef CONFIG_PPC64 /* * Examine the existing instructions for __ftrace_make_call. * They should effectively be a NOP, and follow formal constraints, * depending on the ABI. Return false if they don't. */ -#ifndef CONFIG_MPROFILE_KERNEL -static int -expected_nop_sequence(void *ip, struct ppc_inst op0, struct ppc_inst op1) +static bool expected_nop_sequence(void *ip, ppc_inst_t op0, ppc_inst_t op1) { - /* - * We expect to see: - * - * b +8 - * ld r2,XX(r1) - * - * The load offset is different depending on the ABI. For simplicity - * just mask it out when doing the compare. - */ - if (!ppc_inst_equal(op0, ppc_inst(0x48000008)) || - (ppc_inst_val(op1) & 0xffff0000) != 0xe8410000) - return 0; - return 1; -} -#else -static int -expected_nop_sequence(void *ip, struct ppc_inst op0, struct ppc_inst op1) -{ - /* look for patched "NOP" on ppc64 with -mprofile-kernel */ - if (!ppc_inst_equal(op0, ppc_inst(PPC_RAW_NOP()))) - return 0; - return 1; + if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS)) + return ppc_inst_equal(op0, ppc_inst(PPC_RAW_NOP())); + else + return ppc_inst_equal(op0, ppc_inst(PPC_RAW_BRANCH(8))) && + ppc_inst_equal(op1, ppc_inst(PPC_INST_LD_TOC)); } -#endif static int __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) { - struct ppc_inst op[2]; - struct ppc_inst instr; + ppc_inst_t op[2]; void *ip = (void *)rec->ip; unsigned long entry, ptr, tramp; struct module *mod = rec->arch.mod; @@ -529,30 +412,26 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) if (copy_inst_from_kernel_nofault(op, ip)) return -EFAULT; - if (copy_inst_from_kernel_nofault(op + 1, ip + 4)) + if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) && + copy_inst_from_kernel_nofault(op + 1, ip + 4)) return -EFAULT; if (!expected_nop_sequence(ip, op[0], op[1])) { - pr_err("Unexpected call sequence at %p: %s %s\n", - ip, ppc_inst_as_str(op[0]), ppc_inst_as_str(op[1])); + pr_err("Unexpected call sequence at %p: %08lx %08lx\n", ip, + ppc_inst_as_ulong(op[0]), ppc_inst_as_ulong(op[1])); return -EINVAL; } /* If we never set up ftrace trampoline(s), then bail */ -#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS - if (!mod->arch.tramp || !mod->arch.tramp_regs) { -#else - if (!mod->arch.tramp) { -#endif + if (!mod->arch.tramp || + (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) && !mod->arch.tramp_regs)) { pr_err("No ftrace trampoline\n"); return -EINVAL; } -#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS - if (rec->flags & FTRACE_FL_REGS) + if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) && rec->flags & FTRACE_FL_REGS) tramp = mod->arch.tramp_regs; else -#endif tramp = mod->arch.tramp; if (module_trampoline_target(mod, tramp, &ptr)) { @@ -569,12 +448,6 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) return -EINVAL; } - /* Ensure branch is within 24 bits */ - if (create_branch(&instr, ip, tramp, BRANCH_SET_LINK)) { - pr_err("Branch out of range\n"); - return -EINVAL; - } - if (patch_branch(ip, tramp, BRANCH_SET_LINK)) { pr_err("REL24 out of range!\n"); return -EINVAL; @@ -582,51 +455,16 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) return 0; } - -#else /* !CONFIG_PPC64: */ -static int -__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) +#else +static int __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) { - int err; - struct ppc_inst op; - u32 *ip = (u32 *)rec->ip; - - /* read where this goes */ - if (copy_inst_from_kernel_nofault(&op, ip)) - return -EFAULT; - - /* It should be pointing to a nop */ - if (!ppc_inst_equal(op, ppc_inst(PPC_RAW_NOP()))) { - pr_err("Expected NOP but have %s\n", ppc_inst_as_str(op)); - return -EINVAL; - } - - /* If we never set up a trampoline to ftrace_caller, then bail */ - if (!rec->arch.mod->arch.tramp) { - pr_err("No ftrace trampoline\n"); - return -EINVAL; - } - - /* create the branch to the trampoline */ - err = create_branch(&op, ip, rec->arch.mod->arch.tramp, BRANCH_SET_LINK); - if (err) { - pr_err("REL24 out of range!\n"); - return -EINVAL; - } - - pr_devel("write to %lx\n", rec->ip); - - if (patch_instruction(ip, op)) - return -EPERM; - return 0; } -#endif /* CONFIG_PPC64 */ #endif /* CONFIG_MODULES */ static int __ftrace_make_call_kernel(struct dyn_ftrace *rec, unsigned long addr) { - struct ppc_inst op; + ppc_inst_t op; void *ip = (void *)rec->ip; unsigned long tramp, entry, ptr; @@ -634,16 +472,12 @@ static int __ftrace_make_call_kernel(struct dyn_ftrace *rec, unsigned long addr) entry = ppc_global_function_entry((void *)ftrace_caller); ptr = ppc_global_function_entry((void *)addr); - if (ptr != entry) { -#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS + if (ptr != entry && IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS)) entry = ppc_global_function_entry((void *)ftrace_regs_caller); - if (ptr != entry) { -#endif - pr_err("Unknown ftrace addr to patch: %ps\n", (void *)ptr); - return -EINVAL; -#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS - } -#endif + + if (ptr != entry) { + pr_err("Unknown ftrace addr to patch: %ps\n", (void *)ptr); + return -EINVAL; } /* Make sure we have a nop */ @@ -653,7 +487,8 @@ static int __ftrace_make_call_kernel(struct dyn_ftrace *rec, unsigned long addr) } if (!ppc_inst_equal(op, ppc_inst(PPC_RAW_NOP()))) { - pr_err("Unexpected call sequence at %p: %s\n", ip, ppc_inst_as_str(op)); + pr_err("Unexpected call sequence at %p: %08lx\n", + ip, ppc_inst_as_ulong(op)); return -EINVAL; } @@ -674,7 +509,7 @@ static int __ftrace_make_call_kernel(struct dyn_ftrace *rec, unsigned long addr) int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) { unsigned long ip = rec->ip; - struct ppc_inst old, new; + ppc_inst_t old, new; /* * If the calling address is more that 24 bits away, @@ -686,10 +521,13 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) old = ppc_inst(PPC_RAW_NOP()); new = ftrace_call_replace(ip, addr, 1); return ftrace_modify_code(ip, old, new); - } else if (core_kernel_text(ip)) + } else if (core_kernel_text(ip)) { return __ftrace_make_call_kernel(rec, addr); + } else if (!IS_ENABLED(CONFIG_MODULES)) { + /* We should not get here without modules */ + return -EINVAL; + } -#ifdef CONFIG_MODULES /* * Out of range jumps are called from modules. * Being that we are converting from nop, it had better @@ -701,10 +539,6 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) } return __ftrace_make_call(rec, addr); -#else - /* We should not get here without modules */ - return -EINVAL; -#endif /* CONFIG_MODULES */ } #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS @@ -713,7 +547,7 @@ static int __ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr) { - struct ppc_inst op; + ppc_inst_t op; unsigned long ip = rec->ip; unsigned long entry, ptr, tramp; struct module *mod = rec->arch.mod; @@ -730,9 +564,9 @@ __ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, return -EFAULT; } - /* Make sure that that this is still a 24bit jump */ + /* Make sure that this is still a 24bit jump */ if (!is_bl_op(op)) { - pr_err("Not expected bl: opcode is %s\n", ppc_inst_as_str(op)); + pr_err("Not expected bl: opcode is %08lx\n", ppc_inst_as_ulong(op)); return -EINVAL; } @@ -788,12 +622,6 @@ __ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, return -EINVAL; } - /* Ensure branch is within 24 bits */ - if (create_branch(&op, (u32 *)ip, tramp, BRANCH_SET_LINK)) { - pr_err("Branch out of range\n"); - return -EINVAL; - } - if (patch_branch((u32 *)ip, tramp, BRANCH_SET_LINK)) { pr_err("REL24 out of range!\n"); return -EINVAL; @@ -801,13 +629,18 @@ __ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, return 0; } +#else +static int __ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr) +{ + return 0; +} #endif int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr) { unsigned long ip = rec->ip; - struct ppc_inst old, new; + ppc_inst_t old, new; /* * If the calling address is more that 24 bits away, @@ -825,9 +658,11 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, * variant, so there is nothing to do here */ return 0; + } else if (!IS_ENABLED(CONFIG_MODULES)) { + /* We should not get here without modules */ + return -EINVAL; } -#ifdef CONFIG_MODULES /* * Out of range jumps are called from modules. */ @@ -837,32 +672,26 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, } return __ftrace_modify_call(rec, old_addr, addr); -#else - /* We should not get here without modules */ - return -EINVAL; -#endif /* CONFIG_MODULES */ } #endif int ftrace_update_ftrace_func(ftrace_func_t func) { unsigned long ip = (unsigned long)(&ftrace_call); - struct ppc_inst old, new; + ppc_inst_t old, new; int ret; old = ppc_inst_read((u32 *)&ftrace_call); new = ftrace_call_replace(ip, (unsigned long)func, 1); ret = ftrace_modify_code(ip, old, new); -#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS /* Also update the regs callback function */ - if (!ret) { + if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) && !ret) { ip = (unsigned long)(&ftrace_regs_call); old = ppc_inst_read((u32 *)&ftrace_regs_call); new = ftrace_call_replace(ip, (unsigned long)func, 1); ret = ftrace_modify_code(ip, old, new); } -#endif return ret; } @@ -881,25 +710,39 @@ void arch_ftrace_update_code(int command) extern unsigned int ftrace_tramp_text[], ftrace_tramp_init[]; +void ftrace_free_init_tramp(void) +{ + int i; + + for (i = 0; i < NUM_FTRACE_TRAMPS && ftrace_tramps[i]; i++) + if (ftrace_tramps[i] == (unsigned long)ftrace_tramp_init) { + ftrace_tramps[i] = 0; + return; + } +} + int __init ftrace_dyn_arch_init(void) { int i; unsigned int *tramp[] = { ftrace_tramp_text, ftrace_tramp_init }; u32 stub_insns[] = { - 0xe98d0000 | PACATOC, /* ld r12,PACATOC(r13) */ - 0x3d8c0000, /* addis r12,r12,<high> */ - 0x398c0000, /* addi r12,r12,<low> */ - 0x7d8903a6, /* mtctr r12 */ - 0x4e800420, /* bctr */ + PPC_RAW_LD(_R12, _R13, PACATOC), + PPC_RAW_ADDIS(_R12, _R12, 0), + PPC_RAW_ADDI(_R12, _R12, 0), + PPC_RAW_MTCTR(_R12), + PPC_RAW_BCTR() }; -#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS - unsigned long addr = ppc_global_function_entry((void *)ftrace_regs_caller); -#else - unsigned long addr = ppc_global_function_entry((void *)ftrace_caller); -#endif - long reladdr = addr - kernel_toc_addr(); + unsigned long addr; + long reladdr; + + if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS)) + addr = ppc_global_function_entry((void *)ftrace_regs_caller); + else + addr = ppc_global_function_entry((void *)ftrace_caller); - if (reladdr > 0x7FFFFFFF || reladdr < -(0x80000000L)) { + reladdr = addr - kernel_toc_addr(); + + if (reladdr >= SZ_2G || reladdr < -(long)SZ_2G) { pr_err("Address of %ps out of range of kernel_toc.\n", (void *)addr); return -1; @@ -914,53 +757,48 @@ int __init ftrace_dyn_arch_init(void) return 0; } -#else -int __init ftrace_dyn_arch_init(void) -{ - return 0; -} #endif -#endif /* CONFIG_DYNAMIC_FTRACE */ #ifdef CONFIG_FUNCTION_GRAPH_TRACER extern void ftrace_graph_call(void); extern void ftrace_graph_stub(void); -int ftrace_enable_ftrace_graph_caller(void) +static int ftrace_modify_ftrace_graph_caller(bool enable) { unsigned long ip = (unsigned long)(&ftrace_graph_call); unsigned long addr = (unsigned long)(&ftrace_graph_caller); unsigned long stub = (unsigned long)(&ftrace_graph_stub); - struct ppc_inst old, new; + ppc_inst_t old, new; + + if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_ARGS)) + return 0; - old = ftrace_call_replace(ip, stub, 0); - new = ftrace_call_replace(ip, addr, 0); + old = ftrace_call_replace(ip, enable ? stub : addr, 0); + new = ftrace_call_replace(ip, enable ? addr : stub, 0); return ftrace_modify_code(ip, old, new); } -int ftrace_disable_ftrace_graph_caller(void) +int ftrace_enable_ftrace_graph_caller(void) { - unsigned long ip = (unsigned long)(&ftrace_graph_call); - unsigned long addr = (unsigned long)(&ftrace_graph_caller); - unsigned long stub = (unsigned long)(&ftrace_graph_stub); - struct ppc_inst old, new; - - old = ftrace_call_replace(ip, addr, 0); - new = ftrace_call_replace(ip, stub, 0); + return ftrace_modify_ftrace_graph_caller(true); +} - return ftrace_modify_code(ip, old, new); +int ftrace_disable_ftrace_graph_caller(void) +{ + return ftrace_modify_ftrace_graph_caller(false); } /* * Hook the return address and push it in the stack of return addrs * in current thread info. Return the address we want to divert to. */ -unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip, - unsigned long sp) +static unsigned long +__prepare_ftrace_return(unsigned long parent, unsigned long ip, unsigned long sp) { unsigned long return_hooker; + int bit; if (unlikely(ftrace_graph_is_dead())) goto out; @@ -968,16 +806,36 @@ unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip, if (unlikely(atomic_read(¤t->tracing_graph_pause))) goto out; + bit = ftrace_test_recursion_trylock(ip, parent); + if (bit < 0) + goto out; + return_hooker = ppc_function_entry(return_to_handler); if (!function_graph_enter(parent, ip, 0, (unsigned long *)sp)) parent = return_hooker; + + ftrace_test_recursion_unlock(bit); out: return parent; } + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS +void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct ftrace_regs *fregs) +{ + fregs->regs.link = __prepare_ftrace_return(parent_ip, ip, fregs->regs.gpr[1]); +} +#else +unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip, + unsigned long sp) +{ + return __prepare_ftrace_return(parent, ip, sp); +} +#endif #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ -#ifdef PPC64_ELF_ABI_v1 +#ifdef CONFIG_PPC64_ELF_ABI_V1 char *arch_ftrace_match_adjust(char *str, const char *search) { if (str[0] == '.' && search[0] != '.') @@ -985,4 +843,4 @@ char *arch_ftrace_match_adjust(char *str, const char *search) else return str; } -#endif /* PPC64_ELF_ABI_v1 */ +#endif /* CONFIG_PPC64_ELF_ABI_V1 */ diff --git a/arch/powerpc/kernel/trace/ftrace_32.S b/arch/powerpc/kernel/trace/ftrace_32.S deleted file mode 100644 index e023ae59c429..000000000000 --- a/arch/powerpc/kernel/trace/ftrace_32.S +++ /dev/null @@ -1,95 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Split from entry_32.S - */ - -#include <linux/magic.h> -#include <asm/reg.h> -#include <asm/ppc_asm.h> -#include <asm/asm-offsets.h> -#include <asm/ftrace.h> -#include <asm/export.h> - -_GLOBAL(mcount) -_GLOBAL(_mcount) - /* - * 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 r0, 4(r1) - mtlr r0 - bctr - -_GLOBAL(ftrace_caller) - MCOUNT_SAVE_FRAME - /* r3 ends up with link register */ - subi r3, r3, MCOUNT_INSN_SIZE -.globl ftrace_call -ftrace_call: - bl ftrace_stub - nop -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -.globl ftrace_graph_call -ftrace_graph_call: - b ftrace_graph_stub -_GLOBAL(ftrace_graph_stub) -#endif - MCOUNT_RESTORE_FRAME - /* old link register ends up in ctr reg */ - bctr - -EXPORT_SYMBOL(_mcount) - -_GLOBAL(ftrace_stub) - blr - -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -_GLOBAL(ftrace_graph_caller) - addi r5, r1, 48 - /* load r4 with local address */ - lwz r4, 44(r1) - subi r4, r4, MCOUNT_INSN_SIZE - - /* Grab the LR out of the caller stack frame */ - lwz r3,52(r1) - - bl prepare_ftrace_return - nop - - /* - * prepare_ftrace_return gives us the address we divert to. - * Change the LR in the callers stack frame to this. - */ - stw r3,52(r1) - - MCOUNT_RESTORE_FRAME - /* old link register ends up in ctr reg */ - bctr - -_GLOBAL(return_to_handler) - /* need to save return values */ - stwu r1, -32(r1) - stw r3, 20(r1) - stw r4, 16(r1) - stw r31, 12(r1) - mr r31, r1 - - bl ftrace_return_to_handler - nop - - /* return value has real return address */ - mtlr r3 - - lwz r3, 20(r1) - lwz r4, 16(r1) - lwz r31,12(r1) - lwz r1, 0(r1) - - /* Jump back to real return address */ - blr -#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/powerpc/kernel/trace/ftrace_64.S b/arch/powerpc/kernel/trace/ftrace_low.S index 25e5b9e47c06..294d1e05958a 100644 --- a/arch/powerpc/kernel/trace/ftrace_64.S +++ b/arch/powerpc/kernel/trace/ftrace_low.S @@ -10,6 +10,7 @@ #include <asm/ppc-opcode.h> #include <asm/export.h> +#ifdef CONFIG_PPC64 .pushsection ".tramp.ftrace.text","aw",@progbits; .globl ftrace_tramp_text ftrace_tramp_text: @@ -21,6 +22,7 @@ ftrace_tramp_text: ftrace_tramp_init: .space 64 .popsection +#endif _GLOBAL(mcount) _GLOBAL(_mcount) @@ -33,6 +35,7 @@ EXPORT_SYMBOL(_mcount) #ifdef CONFIG_FUNCTION_GRAPH_TRACER _GLOBAL(return_to_handler) /* need to save return values */ +#ifdef CONFIG_PPC64 std r4, -32(r1) std r3, -24(r1) /* save TOC */ @@ -45,7 +48,12 @@ _GLOBAL(return_to_handler) * We might be called from a module. * Switch to our TOC to run inside the core kernel. */ - ld r2, PACATOC(r13) + LOAD_PACA_TOC() +#else + stwu r1, -16(r1) + stw r3, 8(r1) + stw r4, 12(r1) +#endif bl ftrace_return_to_handler nop @@ -53,11 +61,17 @@ _GLOBAL(return_to_handler) /* return value has real return address */ mtlr r3 +#ifdef CONFIG_PPC64 ld r1, 0(r1) ld r4, -32(r1) ld r3, -24(r1) ld r2, -16(r1) ld r31, -8(r1) +#else + lwz r3, 8(r1) + lwz r4, 12(r1) + addi r1, r1, 16 +#endif /* Jump back to real return address */ blr diff --git a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S b/arch/powerpc/kernel/trace/ftrace_mprofile.S index f9fd5f743eba..d031093bc436 100644 --- a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S +++ b/arch/powerpc/kernel/trace/ftrace_mprofile.S @@ -32,53 +32,69 @@ * Our job is to save the register state into a struct pt_regs (on the stack) * and then arrange for the ftrace function to be called. */ -_GLOBAL(ftrace_regs_caller) - /* Save the original return address in A's stack frame */ - std r0,LRSAVE(r1) - +.macro ftrace_regs_entry allregs /* Create our stack frame + pt_regs */ - stdu r1,-SWITCH_FRAME_SIZE(r1) + PPC_STLU r1,-SWITCH_FRAME_SIZE(r1) /* Save all gprs to pt_regs */ SAVE_GPR(0, r1) - SAVE_10GPRS(2, r1) + SAVE_GPRS(3, 10, r1) +#ifdef CONFIG_PPC64 + /* Save the original return address in A's stack frame */ + std r0, LRSAVE+SWITCH_FRAME_SIZE(r1) /* Ok to continue? */ lbz r3, PACA_FTRACE_ENABLED(r13) cmpdi r3, 0 beq ftrace_no_trace +#endif - SAVE_10GPRS(12, r1) - SAVE_10GPRS(22, r1) + .if \allregs == 1 + SAVE_GPR(2, r1) + SAVE_GPRS(11, 31, r1) + .else +#ifdef CONFIG_LIVEPATCH_64 + SAVE_GPR(14, r1) +#endif + .endif /* Save previous stack pointer (r1) */ addi r8, r1, SWITCH_FRAME_SIZE - std r8, GPR1(r1) + PPC_STL r8, GPR1(r1) + .if \allregs == 1 /* Load special regs for save below */ mfmsr r8 mfctr r9 mfxer r10 mfcr r11 + .else + /* Clear MSR to flag as ftrace_caller versus frace_regs_caller */ + li r8, 0 + .endif /* Get the _mcount() call site out of LR */ mflr r7 /* Save it as pt_regs->nip */ - std r7, _NIP(r1) + PPC_STL r7, _NIP(r1) /* Save the read LR in pt_regs->link */ - std r0, _LINK(r1) + PPC_STL r0, _LINK(r1) +#ifdef CONFIG_PPC64 /* Save callee's TOC in the ABI compliant location */ - std r2, 24(r1) - ld r2,PACATOC(r13) /* get kernel TOC in r2 */ - - addis r3,r2,function_trace_op@toc@ha - addi r3,r3,function_trace_op@toc@l + std r2, STK_GOT(r1) + LOAD_PACA_TOC() /* get kernel TOC in r2 */ + LOAD_REG_ADDR(r3, function_trace_op) ld r5,0(r3) +#else + lis r3,function_trace_op@ha + lwz r5,function_trace_op@l(r3) +#endif -#ifdef CONFIG_LIVEPATCH - mr r14,r7 /* remember old NIP */ +#ifdef CONFIG_LIVEPATCH_64 + mr r14, r7 /* remember old NIP */ #endif + /* Calculate ip from nip-4 into r3 for call below */ subi r3, r7, MCOUNT_INSN_SIZE @@ -86,130 +102,87 @@ _GLOBAL(ftrace_regs_caller) mr r4, r0 /* Save special regs */ - std r8, _MSR(r1) - std r9, _CTR(r1) - std r10, _XER(r1) - std r11, _CCR(r1) + PPC_STL r8, _MSR(r1) + .if \allregs == 1 + PPC_STL r9, _CTR(r1) + PPC_STL r10, _XER(r1) + PPC_STL r11, _CCR(r1) + .endif /* Load &pt_regs in r6 for call below */ - addi r6, r1 ,STACK_FRAME_OVERHEAD - - /* ftrace_call(r3, r4, r5, r6) */ -.globl ftrace_regs_call -ftrace_regs_call: - bl ftrace_stub - nop + addi r6, r1, STACK_FRAME_OVERHEAD +.endm +.macro ftrace_regs_exit allregs /* Load ctr with the possibly modified NIP */ - ld r3, _NIP(r1) + PPC_LL r3, _NIP(r1) mtctr r3 -#ifdef CONFIG_LIVEPATCH + +#ifdef CONFIG_LIVEPATCH_64 cmpd r14, r3 /* has NIP been altered? */ #endif /* Restore gprs */ - REST_GPR(0,r1) - REST_10GPRS(2,r1) - REST_10GPRS(12,r1) - REST_10GPRS(22,r1) + .if \allregs == 1 + REST_GPRS(2, 31, r1) + .else + REST_GPRS(3, 10, r1) +#ifdef CONFIG_LIVEPATCH_64 + REST_GPR(14, r1) +#endif + .endif /* Restore possibly modified LR */ - ld r0, _LINK(r1) + PPC_LL r0, _LINK(r1) mtlr r0 +#ifdef CONFIG_PPC64 /* Restore callee's TOC */ - ld r2, 24(r1) + ld r2, STK_GOT(r1) +#endif /* Pop our stack frame */ addi r1, r1, SWITCH_FRAME_SIZE -#ifdef CONFIG_LIVEPATCH +#ifdef CONFIG_LIVEPATCH_64 /* Based on the cmpd above, if the NIP was altered handle livepatch */ bne- livepatch_handler #endif - -ftrace_caller_common: -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -.globl ftrace_graph_call -ftrace_graph_call: - b ftrace_graph_stub -_GLOBAL(ftrace_graph_stub) -#endif - bctr /* jump after _mcount site */ +.endm -_GLOBAL(ftrace_stub) - blr - -ftrace_no_trace: - mflr r3 - mtctr r3 - REST_GPR(3, r1) - addi r1, r1, SWITCH_FRAME_SIZE - mtlr r0 - bctr +_GLOBAL(ftrace_regs_caller) + ftrace_regs_entry 1 + /* ftrace_call(r3, r4, r5, r6) */ +.globl ftrace_regs_call +ftrace_regs_call: + bl ftrace_stub + nop + ftrace_regs_exit 1 _GLOBAL(ftrace_caller) - /* Save the original return address in A's stack frame */ - std r0, LRSAVE(r1) - - /* Create our stack frame + pt_regs */ - stdu r1, -SWITCH_FRAME_SIZE(r1) - - /* Save all gprs to pt_regs */ - SAVE_8GPRS(3, r1) - - lbz r3, PACA_FTRACE_ENABLED(r13) - cmpdi r3, 0 - beq ftrace_no_trace - - /* Get the _mcount() call site out of LR */ - mflr r7 - std r7, _NIP(r1) - - /* Save callee's TOC in the ABI compliant location */ - std r2, 24(r1) - ld r2, PACATOC(r13) /* get kernel TOC in r2 */ - - addis r3, r2, function_trace_op@toc@ha - addi r3, r3, function_trace_op@toc@l - ld r5, 0(r3) - - /* Calculate ip from nip-4 into r3 for call below */ - subi r3, r7, MCOUNT_INSN_SIZE - - /* Put the original return address in r4 as parent_ip */ - mr r4, r0 - - /* Set pt_regs to NULL */ - li r6, 0 - + ftrace_regs_entry 0 /* ftrace_call(r3, r4, r5, r6) */ .globl ftrace_call ftrace_call: bl ftrace_stub nop + ftrace_regs_exit 0 - ld r3, _NIP(r1) - mtctr r3 - - /* Restore gprs */ - REST_8GPRS(3,r1) - - /* Restore callee's TOC */ - ld r2, 24(r1) +_GLOBAL(ftrace_stub) + blr - /* Pop our stack frame */ +#ifdef CONFIG_PPC64 +ftrace_no_trace: + mflr r3 + mtctr r3 + REST_GPR(3, r1) addi r1, r1, SWITCH_FRAME_SIZE - - /* Reload original LR */ - ld r0, LRSAVE(r1) mtlr r0 + bctr +#endif - /* Handle function_graph or go back */ - b ftrace_caller_common - -#ifdef CONFIG_LIVEPATCH +#ifdef CONFIG_LIVEPATCH_64 /* * This function runs in the mcount context, between two functions. As * such it can only clobber registers which are volatile and used in @@ -276,55 +249,3 @@ livepatch_handler: /* Return to original caller of live patched function */ blr #endif /* CONFIG_LIVEPATCH */ - -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -_GLOBAL(ftrace_graph_caller) - stdu r1, -112(r1) - /* with -mprofile-kernel, parameter regs are still alive at _mcount */ - std r10, 104(r1) - std r9, 96(r1) - std r8, 88(r1) - std r7, 80(r1) - std r6, 72(r1) - std r5, 64(r1) - std r4, 56(r1) - std r3, 48(r1) - - /* Save callee's TOC in the ABI compliant location */ - std r2, 24(r1) - ld r2, PACATOC(r13) /* get kernel TOC in r2 */ - - addi r5, r1, 112 - mfctr r4 /* ftrace_caller has moved local addr here */ - std r4, 40(r1) - mflr r3 /* ftrace_caller has restored LR from stack */ - subi r4, r4, MCOUNT_INSN_SIZE - - bl prepare_ftrace_return - nop - - /* - * prepare_ftrace_return gives us the address we divert to. - * Change the LR to this. - */ - mtlr r3 - - ld r0, 40(r1) - mtctr r0 - ld r10, 104(r1) - ld r9, 96(r1) - ld r8, 88(r1) - ld r7, 80(r1) - ld r6, 72(r1) - ld r5, 64(r1) - ld r4, 56(r1) - ld r3, 48(r1) - - /* Restore callee's TOC */ - ld r2, 24(r1) - - addi r1, r1, 112 - mflr r0 - std r0, LRSAVE(r1) - bctr -#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 11741703d26e..9bdd79aa51cf 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -68,6 +68,7 @@ #include <asm/stacktrace.h> #include <asm/nmi.h> #include <asm/disassemble.h> +#include <asm/udbg.h> #if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC_CORE) int (*__debugger)(struct pt_regs *regs) __read_mostly; @@ -245,7 +246,7 @@ static void oops_end(unsigned long flags, struct pt_regs *regs, if (panic_on_oops) panic("Fatal exception"); - do_exit(signr); + make_task_dead(signr); } NOKPROBE_SYMBOL(oops_end); @@ -393,7 +394,7 @@ void _exception(int signr, struct pt_regs *regs, int code, unsigned long addr) * Builds that do not support KVM could take this second option to increase * the recoverability of NMIs. */ -void hv_nmi_check_nonrecoverable(struct pt_regs *regs) +noinstr void hv_nmi_check_nonrecoverable(struct pt_regs *regs) { #ifdef CONFIG_PPC_POWERNV unsigned long kbase = (unsigned long)_stext; @@ -433,7 +434,9 @@ void hv_nmi_check_nonrecoverable(struct pt_regs *regs) return; nonrecoverable: - regs_set_unrecoverable(regs); + regs->msr &= ~MSR_RI; + local_paca->hsrr_valid = 0; + local_paca->srr_valid = 0; #endif } DEFINE_INTERRUPT_HANDLER_NMI(system_reset_exception) @@ -598,7 +601,7 @@ static inline int check_io_access(struct pt_regs *regs) #define inst_length(reason) (((reason) & REASON_PREFIXED) ? 8 : 4) -#if defined(CONFIG_E500) +#if defined(CONFIG_PPC_E500) int machine_check_e500mc(struct pt_regs *regs) { unsigned long mcsr = mfspr(SPRN_MCSR); @@ -792,9 +795,9 @@ int machine_check_generic(struct pt_regs *regs) void die_mce(const char *str, struct pt_regs *regs, long err) { /* - * The machine check wants to kill the interrupted context, but - * do_exit() checks for in_interrupt() and panics in that case, so - * exit the irq/nmi before calling die. + * The machine check wants to kill the interrupted context, + * but make_task_dead() checks for in_interrupt() and panics + * in that case, so exit the irq/nmi before calling die. */ if (in_nmi()) nmi_exit(); @@ -848,6 +851,19 @@ bail: } #ifdef CONFIG_PPC_BOOK3S_64 +DEFINE_INTERRUPT_HANDLER_RAW(machine_check_early_boot) +{ + udbg_printf("Machine check (early boot)\n"); + udbg_printf("SRR0=0x%016lx SRR1=0x%016lx\n", regs->nip, regs->msr); + udbg_printf(" DAR=0x%016lx DSISR=0x%08lx\n", regs->dar, regs->dsisr); + udbg_printf(" LR=0x%016lx R1=0x%08lx\n", regs->link, regs->gpr[1]); + udbg_printf("------\n"); + die("Machine check (early boot)", regs, SIGBUS); + for (;;) + ; + return 0; +} + DEFINE_INTERRUPT_HANDLER_ASYNC(machine_check_exception_async) { __machine_check_exception(regs); @@ -1674,7 +1690,7 @@ DEFINE_INTERRUPT_HANDLER(vsx_unavailable_exception) die("Unrecoverable VSX Unavailable Exception", regs, SIGABRT); } -#ifdef CONFIG_PPC64 +#ifdef CONFIG_PPC_BOOK3S_64 static void tm_unavailable(struct pt_regs *regs) { #ifdef CONFIG_PPC_TRANSACTIONAL_MEM @@ -2083,7 +2099,7 @@ DEFINE_INTERRUPT_HANDLER(altivec_assist_exception) } #endif /* CONFIG_ALTIVEC */ -#ifdef CONFIG_FSL_BOOKE +#ifdef CONFIG_PPC_85xx DEFINE_INTERRUPT_HANDLER(CacheLockingException) { unsigned long error_code = regs->dsisr; @@ -2096,12 +2112,11 @@ DEFINE_INTERRUPT_HANDLER(CacheLockingException) _exception(SIGILL, regs, ILL_PRVOPC, regs->nip); return; } -#endif /* CONFIG_FSL_BOOKE */ +#endif /* CONFIG_PPC_85xx */ #ifdef CONFIG_SPE DEFINE_INTERRUPT_HANDLER(SPEFloatingPointException) { - extern int do_spe_mathemu(struct pt_regs *regs); unsigned long spefscr; int fpexc_mode; int code = FPE_FLTUNK; @@ -2151,7 +2166,6 @@ DEFINE_INTERRUPT_HANDLER(SPEFloatingPointException) DEFINE_INTERRUPT_HANDLER(SPEFloatingPointRoundException) { - extern int speround_handler(struct pt_regs *regs); int err; interrupt_cond_local_irq_enable(regs); diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c index b1544b2f6321..92b3fc258d11 100644 --- a/arch/powerpc/kernel/udbg.c +++ b/arch/powerpc/kernel/udbg.c @@ -67,6 +67,8 @@ void __init udbg_early_init(void) udbg_init_debug_opal_raw(); #elif defined(CONFIG_PPC_EARLY_DEBUG_OPAL_HVSI) udbg_init_debug_opal_hvsi(); +#elif defined(CONFIG_PPC_EARLY_DEBUG_16550) + udbg_init_debug_16550(); #endif #ifdef CONFIG_PPC_EARLY_DEBUG diff --git a/arch/powerpc/kernel/udbg_16550.c b/arch/powerpc/kernel/udbg_16550.c index 8513aa49614e..74ddf836f7a2 100644 --- a/arch/powerpc/kernel/udbg_16550.c +++ b/arch/powerpc/kernel/udbg_16550.c @@ -8,6 +8,7 @@ #include <asm/udbg.h> #include <asm/io.h> #include <asm/reg_a2.h> +#include <asm/early_ioremap.h> extern u8 real_readb(volatile u8 __iomem *addr); extern void real_writeb(u8 data, volatile u8 __iomem *addr); @@ -84,7 +85,7 @@ static int udbg_uart_getc(void) return udbg_uart_in(UART_RBR); } -static void udbg_use_uart(void) +static void __init udbg_use_uart(void) { udbg_putc = udbg_uart_putc; udbg_flush = udbg_uart_flush; @@ -92,7 +93,7 @@ static void udbg_use_uart(void) udbg_getc_poll = udbg_uart_getc_poll; } -void udbg_uart_setup(unsigned int speed, unsigned int clock) +void __init udbg_uart_setup(unsigned int speed, unsigned int clock) { unsigned int dll, base_bauds; @@ -121,7 +122,7 @@ void udbg_uart_setup(unsigned int speed, unsigned int clock) udbg_uart_out(UART_FCR, 0x7); } -unsigned int udbg_probe_uart_speed(unsigned int clock) +unsigned int __init udbg_probe_uart_speed(unsigned int clock) { unsigned int dll, dlm, divisor, prescaler, speed; u8 old_lcr; @@ -172,7 +173,7 @@ static void udbg_uart_out_pio(unsigned int reg, u8 data) outb(data, udbg_uart.pio_base + (reg * udbg_uart_stride)); } -void udbg_uart_init_pio(unsigned long port, unsigned int stride) +void __init udbg_uart_init_pio(unsigned long port, unsigned int stride) { if (!port) return; @@ -194,7 +195,7 @@ static void udbg_uart_out_mmio(unsigned int reg, u8 data) } -void udbg_uart_init_mmio(void __iomem *addr, unsigned int stride) +void __init udbg_uart_init_mmio(void __iomem *addr, unsigned int stride) { if (!addr) return; @@ -297,41 +298,34 @@ void __init udbg_init_40x_realmode(void) #endif /* CONFIG_PPC_EARLY_DEBUG_40x */ -#ifdef CONFIG_PPC_EARLY_DEBUG_MICROWATT +#ifdef CONFIG_PPC_EARLY_DEBUG_16550 -#define UDBG_UART_MW_ADDR ((void __iomem *)0xc0002000) +static void __iomem *udbg_uart_early_addr; -static u8 udbg_uart_in_isa300_rm(unsigned int reg) +void __init udbg_init_debug_16550(void) { - uint64_t msr = mfmsr(); - uint8_t c; - - mtmsr(msr & ~(MSR_EE|MSR_DR)); - isync(); - eieio(); - c = __raw_rm_readb(UDBG_UART_MW_ADDR + (reg << 2)); - mtmsr(msr); - isync(); - return c; + udbg_uart_early_addr = early_ioremap(CONFIG_PPC_EARLY_DEBUG_16550_PHYSADDR, 0x1000); + udbg_uart_init_mmio(udbg_uart_early_addr, CONFIG_PPC_EARLY_DEBUG_16550_STRIDE); } -static void udbg_uart_out_isa300_rm(unsigned int reg, u8 val) +static int __init udbg_init_debug_16550_ioremap(void) { - uint64_t msr = mfmsr(); - - mtmsr(msr & ~(MSR_EE|MSR_DR)); - isync(); - eieio(); - __raw_rm_writeb(val, UDBG_UART_MW_ADDR + (reg << 2)); - mtmsr(msr); - isync(); -} + void __iomem *addr; -void __init udbg_init_debug_microwatt(void) -{ - udbg_uart_in = udbg_uart_in_isa300_rm; - udbg_uart_out = udbg_uart_out_isa300_rm; - udbg_use_uart(); + if (!udbg_uart_early_addr) + return 0; + + addr = ioremap(CONFIG_PPC_EARLY_DEBUG_16550_PHYSADDR, 0x1000); + if (WARN_ON(!addr)) + return -ENOMEM; + + udbg_uart_init_mmio(addr, CONFIG_PPC_EARLY_DEBUG_16550_STRIDE); + early_iounmap(udbg_uart_early_addr, 0x1000); + udbg_uart_early_addr = NULL; + + return 0; } -#endif /* CONFIG_PPC_EARLY_DEBUG_MICROWATT */ +early_initcall(udbg_init_debug_16550_ioremap); + +#endif /* CONFIG_PPC_EARLY_DEBUG_16550 */ diff --git a/arch/powerpc/kernel/uprobes.c b/arch/powerpc/kernel/uprobes.c index c6975467d9ff..95a41ae9dfa7 100644 --- a/arch/powerpc/kernel/uprobes.c +++ b/arch/powerpc/kernel/uprobes.c @@ -48,6 +48,11 @@ int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, return -EINVAL; } + if (!can_single_step(ppc_inst_val(ppc_inst_read(auprobe->insn)))) { + pr_info_ratelimited("Cannot register a uprobe on instructions that can't be single stepped\n"); + return -ENOTSUPP; + } + return 0; } diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index 717f2c9a7573..4abc01949702 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -25,7 +25,6 @@ #include <asm/processor.h> #include <asm/mmu.h> #include <asm/mmu_context.h> -#include <asm/prom.h> #include <asm/machdep.h> #include <asm/cputable.h> #include <asm/sections.h> @@ -40,6 +39,8 @@ extern char vdso32_start, vdso32_end; extern char vdso64_start, vdso64_end; +long sys_ni_syscall(void); + /* * The vdso data page (aka. systemcfg for old ppc64 fans) is here. * Once the early boot kernel code no longer needs to muck around @@ -114,18 +115,18 @@ struct vdso_data *arch_get_vdso_data(void *vvar_page) int vdso_join_timens(struct task_struct *task, struct time_namespace *ns) { struct mm_struct *mm = task->mm; + VMA_ITERATOR(vmi, mm, 0); struct vm_area_struct *vma; mmap_read_lock(mm); - - for (vma = mm->mmap; vma; vma = vma->vm_next) { + for_each_vma(vmi, vma) { unsigned long size = vma->vm_end - vma->vm_start; if (vma_is_special_mapping(vma, &vvar_spec)) zap_page_range(vma, vma->vm_start, size); } - mmap_read_unlock(mm); + return 0; } @@ -201,28 +202,19 @@ static int __arch_setup_additional_pages(struct linux_binprm *bprm, int uses_int if (is_32bit_task()) { vdso_spec = &vdso32_spec; vdso_size = &vdso32_end - &vdso32_start; - vdso_base = VDSO32_MBASE; } else { vdso_spec = &vdso64_spec; vdso_size = &vdso64_end - &vdso64_start; - /* - * On 64bit we don't have a preferred map address. This - * allows get_unmapped_area to find an area near other mmaps - * and most likely share a SLB entry. - */ - vdso_base = 0; } mappings_size = vdso_size + vvar_size; mappings_size += (VDSO_ALIGNMENT - 1) & PAGE_MASK; /* - * pick a base address for the vDSO in process space. We try to put it - * at vdso_base which is the "natural" base for it, but we might fail - * and end up putting it elsewhere. + * Pick a base address for the vDSO in process space. * Add enough to the size so that the result can be aligned. */ - vdso_base = get_unmapped_area(NULL, vdso_base, mappings_size, 0, 0); + vdso_base = get_unmapped_area(NULL, 0, mappings_size, 0, 0); if (IS_ERR_VALUE(vdso_base)) return vdso_base; @@ -314,10 +306,10 @@ static void __init vdso_setup_syscall_map(void) unsigned int i; for (i = 0; i < NR_syscalls; i++) { - if (sys_call_table[i] != (unsigned long)&sys_ni_syscall) + if (sys_call_table[i] != (void *)&sys_ni_syscall) vdso_data->syscall_map[i >> 5] |= 0x80000000UL >> (i & 0x1f); if (IS_ENABLED(CONFIG_COMPAT) && - compat_sys_call_table[i] != (unsigned long)&sys_ni_syscall) + compat_sys_call_table[i] != (void *)&sys_ni_syscall) vdso_data->compat_syscall_map[i >> 5] |= 0x80000000UL >> (i & 0x1f); } } diff --git a/arch/powerpc/kernel/vdso32/.gitignore b/arch/powerpc/kernel/vdso/.gitignore index 824b863ec6bd..dd9bdd67758b 100644 --- a/arch/powerpc/kernel/vdso32/.gitignore +++ b/arch/powerpc/kernel/vdso/.gitignore @@ -1,3 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only vdso32.lds vdso32.so.dbg +vdso64.lds +vdso64.so.dbg diff --git a/arch/powerpc/kernel/vdso/Makefile b/arch/powerpc/kernel/vdso/Makefile new file mode 100644 index 000000000000..a2e7b0ce5b19 --- /dev/null +++ b/arch/powerpc/kernel/vdso/Makefile @@ -0,0 +1,104 @@ +# SPDX-License-Identifier: GPL-2.0 + +# List of files in the vdso, has to be asm only for now + +ARCH_REL_TYPE_ABS := R_PPC_JUMP_SLOT|R_PPC_GLOB_DAT|R_PPC_ADDR32|R_PPC_ADDR24|R_PPC_ADDR16|R_PPC_ADDR16_LO|R_PPC_ADDR16_HI|R_PPC_ADDR16_HA|R_PPC_ADDR14|R_PPC_ADDR14_BRTAKEN|R_PPC_ADDR14_BRNTAKEN|R_PPC_REL24 +include $(srctree)/lib/vdso/Makefile + +obj-vdso32 = sigtramp32-32.o gettimeofday-32.o datapage-32.o cacheflush-32.o note-32.o getcpu-32.o +obj-vdso64 = sigtramp64-64.o gettimeofday-64.o datapage-64.o cacheflush-64.o note-64.o getcpu-64.o + +ifneq ($(c-gettimeofday-y),) + CFLAGS_vgettimeofday-32.o += -include $(c-gettimeofday-y) + CFLAGS_vgettimeofday-32.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) + CFLAGS_vgettimeofday-32.o += $(call cc-option, -fno-stack-protector) + CFLAGS_vgettimeofday-32.o += -DDISABLE_BRANCH_PROFILING + CFLAGS_vgettimeofday-32.o += -ffreestanding -fasynchronous-unwind-tables + CFLAGS_REMOVE_vgettimeofday-32.o = $(CC_FLAGS_FTRACE) + CFLAGS_REMOVE_vgettimeofday-32.o += -mcmodel=medium -mabi=elfv1 -mabi=elfv2 -mcall-aixdesc + CFLAGS_vgettimeofday-64.o += -include $(c-gettimeofday-y) + CFLAGS_vgettimeofday-64.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) + CFLAGS_vgettimeofday-64.o += $(call cc-option, -fno-stack-protector) + CFLAGS_vgettimeofday-64.o += -DDISABLE_BRANCH_PROFILING + CFLAGS_vgettimeofday-64.o += -ffreestanding -fasynchronous-unwind-tables + CFLAGS_REMOVE_vgettimeofday-64.o = $(CC_FLAGS_FTRACE) +# Go prior to 1.16.x assumes r30 is not clobbered by any VDSO code. That used to be true +# by accident when the VDSO was hand-written asm code, but may not be now that the VDSO is +# compiler generated. To avoid breaking Go tell GCC not to use r30. Impact on code +# generation is minimal, it will just use r29 instead. + CFLAGS_vgettimeofday-64.o += $(call cc-option, -ffixed-r30) +endif + +# Build rules + +ifdef CROSS32_COMPILE + VDSOCC := $(CROSS32_COMPILE)gcc +else + VDSOCC := $(CC) +endif + +targets := $(obj-vdso32) vdso32.so.dbg vgettimeofday-32.o +obj-vdso32 := $(addprefix $(obj)/, $(obj-vdso32)) +targets += $(obj-vdso64) vdso64.so.dbg vgettimeofday-64.o +obj-vdso64 := $(addprefix $(obj)/, $(obj-vdso64)) + +GCOV_PROFILE := n +KCOV_INSTRUMENT := n +UBSAN_SANITIZE := n +KASAN_SANITIZE := n + +ccflags-y := -shared -fno-common -fno-builtin -nostdlib -Wl,--hash-style=both +ccflags-$(CONFIG_LD_IS_LLD) += $(call cc-option,--ld-path=$(LD),-fuse-ld=lld) + +CC32FLAGS := -Wl,-soname=linux-vdso32.so.1 -m32 +AS32FLAGS := -D__VDSO32__ -s + +CC64FLAGS := -Wl,-soname=linux-vdso64.so.1 +AS64FLAGS := -D__VDSO64__ -s + +targets += vdso32.lds +CPPFLAGS_vdso32.lds += -P -C -Upowerpc +targets += vdso64.lds +CPPFLAGS_vdso64.lds += -P -C -U$(ARCH) + +# link rule for the .so file, .lds has to be first +$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) $(obj)/vgettimeofday-32.o FORCE + $(call if_changed,vdso32ld_and_check) +$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) $(obj)/vgettimeofday-64.o FORCE + $(call if_changed,vdso64ld_and_check) + +# assembly rules for the .S files +$(obj-vdso32): %-32.o: %.S FORCE + $(call if_changed_dep,vdso32as) +$(obj)/vgettimeofday-32.o: %-32.o: %.c FORCE + $(call if_changed_dep,vdso32cc) +$(obj-vdso64): %-64.o: %.S FORCE + $(call if_changed_dep,vdso64as) +$(obj)/vgettimeofday-64.o: %-64.o: %.c FORCE + $(call if_changed_dep,cc_o_c) + +# Generate VDSO offsets using helper script +gen-vdso32sym := $(srctree)/$(src)/gen_vdso32_offsets.sh +quiet_cmd_vdso32sym = VDSO32SYM $@ + cmd_vdso32sym = $(NM) $< | $(gen-vdso32sym) | LC_ALL=C sort > $@ +gen-vdso64sym := $(srctree)/$(src)/gen_vdso64_offsets.sh +quiet_cmd_vdso64sym = VDSO64SYM $@ + cmd_vdso64sym = $(NM) $< | $(gen-vdso64sym) | LC_ALL=C sort > $@ + +include/generated/vdso32-offsets.h: $(obj)/vdso32.so.dbg FORCE + $(call if_changed,vdso32sym) +include/generated/vdso64-offsets.h: $(obj)/vdso64.so.dbg FORCE + $(call if_changed,vdso64sym) + +# actual build commands +quiet_cmd_vdso32ld_and_check = VDSO32L $@ + cmd_vdso32ld_and_check = $(VDSOCC) $(c_flags) $(CC32FLAGS) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) -z noexecstack ; $(cmd_vdso_check) +quiet_cmd_vdso32as = VDSO32A $@ + cmd_vdso32as = $(VDSOCC) $(a_flags) $(CC32FLAGS) $(AS32FLAGS) -c -o $@ $< +quiet_cmd_vdso32cc = VDSO32C $@ + cmd_vdso32cc = $(VDSOCC) $(c_flags) $(CC32FLAGS) -c -o $@ $< + +quiet_cmd_vdso64ld_and_check = VDSO64L $@ + cmd_vdso64ld_and_check = $(VDSOCC) $(c_flags) $(CC64FLAGS) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) -z noexecstack ; $(cmd_vdso_check) +quiet_cmd_vdso64as = VDSO64A $@ + cmd_vdso64as = $(VDSOCC) $(a_flags) $(CC64FLAGS) $(AS64FLAGS) -c -o $@ $< diff --git a/arch/powerpc/kernel/vdso32/cacheflush.S b/arch/powerpc/kernel/vdso/cacheflush.S index f340e82d1981..0085ae464dac 100644 --- a/arch/powerpc/kernel/vdso32/cacheflush.S +++ b/arch/powerpc/kernel/vdso/cacheflush.S @@ -46,7 +46,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) add r8,r8,r5 /* ensure we get enough */ #ifdef CONFIG_PPC64 lwz r9,CFG_DCACHE_LOGBLOCKSZ(r10) - srw. r8,r8,r9 /* compute line count */ + PPC_SRL. r8,r8,r9 /* compute line count */ #else srwi. r8, r8, L1_CACHE_SHIFT mr r7, r6 @@ -72,7 +72,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) subf r8,r6,r4 /* compute length */ add r8,r8,r5 lwz r9,CFG_ICACHE_LOGBLOCKSZ(r10) - srw. r8,r8,r9 /* compute line count */ + PPC_SRL. r8,r8,r9 /* compute line count */ crclr cr0*4+so beqlr /* nothing to do? */ #endif @@ -91,6 +91,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) 3: crclr cr0*4+so sync + icbi 0,r1 isync li r3,0 blr diff --git a/arch/powerpc/kernel/vdso32/datapage.S b/arch/powerpc/kernel/vdso/datapage.S index 65244416ab94..db8e167f0166 100644 --- a/arch/powerpc/kernel/vdso32/datapage.S +++ b/arch/powerpc/kernel/vdso/datapage.S @@ -30,11 +30,15 @@ V_FUNCTION_BEGIN(__kernel_get_syscall_map) mr. r4,r3 get_datapage r3 mtlr r12 +#ifdef __powerpc64__ + addi r3,r3,CFG_SYSCALL_MAP64 +#else addi r3,r3,CFG_SYSCALL_MAP32 +#endif + crclr cr0*4+so beqlr li r0,NR_syscalls stw r0,0(r4) - crclr cr0*4+so blr .cfi_endproc V_FUNCTION_END(__kernel_get_syscall_map) @@ -49,8 +53,10 @@ V_FUNCTION_BEGIN(__kernel_get_tbfreq) mflr r12 .cfi_register lr,r12 get_datapage r3 +#ifndef __powerpc64__ lwz r4,(CFG_TB_TICKS_PER_SEC + 4)(r3) - lwz r3,CFG_TB_TICKS_PER_SEC(r3) +#endif + PPC_LL r3,CFG_TB_TICKS_PER_SEC(r3) mtlr r12 crclr cr0*4+so blr diff --git a/arch/powerpc/kernel/vdso32/gen_vdso_offsets.sh b/arch/powerpc/kernel/vdso/gen_vdso32_offsets.sh index c7b54a5dcd3e..c7b54a5dcd3e 100755 --- a/arch/powerpc/kernel/vdso32/gen_vdso_offsets.sh +++ b/arch/powerpc/kernel/vdso/gen_vdso32_offsets.sh diff --git a/arch/powerpc/kernel/vdso64/gen_vdso_offsets.sh b/arch/powerpc/kernel/vdso/gen_vdso64_offsets.sh index 4bf15ffd5933..4bf15ffd5933 100755 --- a/arch/powerpc/kernel/vdso64/gen_vdso_offsets.sh +++ b/arch/powerpc/kernel/vdso/gen_vdso64_offsets.sh diff --git a/arch/powerpc/kernel/vdso32/getcpu.S b/arch/powerpc/kernel/vdso/getcpu.S index ff5e214fec41..8e08ccf19062 100644 --- a/arch/powerpc/kernel/vdso32/getcpu.S +++ b/arch/powerpc/kernel/vdso/getcpu.S @@ -19,8 +19,8 @@ V_FUNCTION_BEGIN(__kernel_getcpu) .cfi_startproc mfspr r5,SPRN_SPRG_VDSO_READ - cmpwi cr0,r3,0 - cmpwi cr1,r4,0 + PPC_LCMPI cr0,r3,0 + PPC_LCMPI cr1,r4,0 clrlwi r6,r5,16 rlwinm r7,r5,16,31-15,31-0 beq cr0,1f diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso/gettimeofday.S index d21d08140a5e..0c4ecc8fec5a 100644 --- a/arch/powerpc/kernel/vdso32/gettimeofday.S +++ b/arch/powerpc/kernel/vdso/gettimeofday.S @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0-or-later */ /* - * Userland implementation of gettimeofday() for 32 bits processes in a - * ppc64 kernel for use in the vDSO + * Userland implementation of gettimeofday() for processes + * for use in the vDSO * * Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org, * IBM Corp. @@ -12,7 +12,54 @@ #include <asm/vdso_datapage.h> #include <asm/asm-offsets.h> #include <asm/unistd.h> -#include <asm/vdso/gettimeofday.h> + +/* + * The macro sets two stack frames, one for the caller and one for the callee + * because there are no requirement for the caller to set a stack frame when + * calling VDSO so it may have omitted to set one, especially on PPC64 + */ + +.macro cvdso_call funct call_time=0 + .cfi_startproc + PPC_STLU r1, -PPC_MIN_STKFRM(r1) + .cfi_adjust_cfa_offset PPC_MIN_STKFRM + mflr r0 + PPC_STLU r1, -PPC_MIN_STKFRM(r1) + .cfi_adjust_cfa_offset PPC_MIN_STKFRM + PPC_STL r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1) + .cfi_rel_offset lr, PPC_MIN_STKFRM + PPC_LR_STKOFF +#ifdef __powerpc64__ + PPC_STL r2, PPC_MIN_STKFRM + STK_GOT(r1) + .cfi_rel_offset r2, PPC_MIN_STKFRM + STK_GOT +#endif + get_datapage r5 + .ifeq \call_time + addi r5, r5, VDSO_DATA_OFFSET + .else + addi r4, r5, VDSO_DATA_OFFSET + .endif + bl DOTSYM(\funct) + PPC_LL r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1) +#ifdef __powerpc64__ + PPC_LL r2, PPC_MIN_STKFRM + STK_GOT(r1) + .cfi_restore r2 +#endif + .ifeq \call_time + cmpwi r3, 0 + .endif + mtlr r0 + addi r1, r1, 2 * PPC_MIN_STKFRM + .cfi_restore lr + .cfi_def_cfa_offset 0 + crclr so + .ifeq \call_time + beqlr+ + crset so + neg r3, r3 + .endif + blr + .cfi_endproc +.endm .text /* @@ -41,9 +88,11 @@ V_FUNCTION_END(__kernel_clock_gettime) * int __kernel_clock_gettime64(clockid_t clock_id, struct __timespec64 *ts); * */ +#ifndef __powerpc64__ V_FUNCTION_BEGIN(__kernel_clock_gettime64) cvdso_call __c_kernel_clock_gettime64 V_FUNCTION_END(__kernel_clock_gettime64) +#endif /* * Exact prototype of clock_getres() @@ -63,12 +112,13 @@ V_FUNCTION_END(__kernel_clock_getres) * */ V_FUNCTION_BEGIN(__kernel_time) - cvdso_call_time __c_kernel_time + cvdso_call __c_kernel_time call_time=1 V_FUNCTION_END(__kernel_time) /* Routines for restoring integer registers, called by the compiler. */ /* Called with r11 pointing to the stack header word of the caller of the */ /* function, just beyond the end of the integer restore area. */ +#ifndef __powerpc64__ _GLOBAL(_restgpr_31_x) _GLOBAL(_rest32gpr_31_x) lwz r0,4(r11) @@ -76,3 +126,4 @@ _GLOBAL(_rest32gpr_31_x) mtlr r0 mr r1,r11 blr +#endif diff --git a/arch/powerpc/kernel/vdso32/note.S b/arch/powerpc/kernel/vdso/note.S index 227a7327399e..227a7327399e 100644 --- a/arch/powerpc/kernel/vdso32/note.S +++ b/arch/powerpc/kernel/vdso/note.S diff --git a/arch/powerpc/kernel/vdso32/sigtramp.S b/arch/powerpc/kernel/vdso/sigtramp32.S index 0bcc5e5fe789..0bcc5e5fe789 100644 --- a/arch/powerpc/kernel/vdso32/sigtramp.S +++ b/arch/powerpc/kernel/vdso/sigtramp32.S diff --git a/arch/powerpc/kernel/vdso64/sigtramp.S b/arch/powerpc/kernel/vdso/sigtramp64.S index 2d4067561293..2d4067561293 100644 --- a/arch/powerpc/kernel/vdso64/sigtramp.S +++ b/arch/powerpc/kernel/vdso/sigtramp64.S diff --git a/arch/powerpc/kernel/vdso32/vdso32.lds.S b/arch/powerpc/kernel/vdso/vdso32.lds.S index 58e0099f70f4..bc0be274a9ac 100644 --- a/arch/powerpc/kernel/vdso32/vdso32.lds.S +++ b/arch/powerpc/kernel/vdso/vdso32.lds.S @@ -13,7 +13,6 @@ OUTPUT_FORMAT("elf32-powerpcle", "elf32-powerpcle", "elf32-powerpcle") OUTPUT_FORMAT("elf32-powerpc", "elf32-powerpc", "elf32-powerpc") #endif OUTPUT_ARCH(powerpc:common) -ENTRY(_start) SECTIONS { @@ -79,7 +78,6 @@ SECTIONS __end = .; PROVIDE(end = .); - STABS_DEBUG DWARF_DEBUG ELF_DETAILS diff --git a/arch/powerpc/kernel/vdso64/vdso64.lds.S b/arch/powerpc/kernel/vdso/vdso64.lds.S index 0288cad428b0..744ae5363e6c 100644 --- a/arch/powerpc/kernel/vdso64/vdso64.lds.S +++ b/arch/powerpc/kernel/vdso/vdso64.lds.S @@ -13,7 +13,6 @@ OUTPUT_FORMAT("elf64-powerpcle", "elf64-powerpcle", "elf64-powerpcle") OUTPUT_FORMAT("elf64-powerpc", "elf64-powerpc", "elf64-powerpc") #endif OUTPUT_ARCH(powerpc:common64) -ENTRY(_start) SECTIONS { @@ -77,7 +76,6 @@ SECTIONS _end = .; PROVIDE(end = .); - STABS_DEBUG DWARF_DEBUG ELF_DETAILS diff --git a/arch/powerpc/kernel/vdso32/vgettimeofday.c b/arch/powerpc/kernel/vdso/vgettimeofday.c index 65fb03fb1731..55a287c9a736 100644 --- a/arch/powerpc/kernel/vdso32/vgettimeofday.c +++ b/arch/powerpc/kernel/vdso/vgettimeofday.c @@ -2,8 +2,22 @@ /* * Powerpc userspace implementations of gettimeofday() and similar. */ +#include <linux/time.h> #include <linux/types.h> +#ifdef __powerpc64__ +int __c_kernel_clock_gettime(clockid_t clock, struct __kernel_timespec *ts, + const struct vdso_data *vd) +{ + return __cvdso_clock_gettime_data(vd, clock, ts); +} + +int __c_kernel_clock_getres(clockid_t clock_id, struct __kernel_timespec *res, + const struct vdso_data *vd) +{ + return __cvdso_clock_getres_data(vd, clock_id, res); +} +#else int __c_kernel_clock_gettime(clockid_t clock, struct old_timespec32 *ts, const struct vdso_data *vd) { @@ -16,16 +30,17 @@ int __c_kernel_clock_gettime64(clockid_t clock, struct __kernel_timespec *ts, return __cvdso_clock_gettime_data(vd, clock, ts); } -int __c_kernel_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz, +int __c_kernel_clock_getres(clockid_t clock_id, struct old_timespec32 *res, const struct vdso_data *vd) { - return __cvdso_gettimeofday_data(vd, tv, tz); + return __cvdso_clock_getres_time32_data(vd, clock_id, res); } +#endif -int __c_kernel_clock_getres(clockid_t clock_id, struct old_timespec32 *res, +int __c_kernel_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz, const struct vdso_data *vd) { - return __cvdso_clock_getres_time32_data(vd, clock_id, res); + return __cvdso_gettimeofday_data(vd, tv, tz); } __kernel_old_time_t __c_kernel_time(__kernel_old_time_t *time, const struct vdso_data *vd) diff --git a/arch/powerpc/kernel/vdso32/Makefile b/arch/powerpc/kernel/vdso32/Makefile deleted file mode 100644 index 7d9a6fee0e3d..000000000000 --- a/arch/powerpc/kernel/vdso32/Makefile +++ /dev/null @@ -1,73 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 - -# List of files in the vdso, has to be asm only for now - -ARCH_REL_TYPE_ABS := R_PPC_JUMP_SLOT|R_PPC_GLOB_DAT|R_PPC_ADDR32|R_PPC_ADDR24|R_PPC_ADDR16|R_PPC_ADDR16_LO|R_PPC_ADDR16_HI|R_PPC_ADDR16_HA|R_PPC_ADDR14|R_PPC_ADDR14_BRTAKEN|R_PPC_ADDR14_BRNTAKEN|R_PPC_REL24 -include $(srctree)/lib/vdso/Makefile - -obj-vdso32 = sigtramp.o gettimeofday.o datapage.o cacheflush.o note.o getcpu.o - -ifneq ($(c-gettimeofday-y),) - CFLAGS_vgettimeofday.o += -include $(c-gettimeofday-y) - CFLAGS_vgettimeofday.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) - CFLAGS_vgettimeofday.o += $(call cc-option, -fno-stack-protector) - CFLAGS_vgettimeofday.o += -DDISABLE_BRANCH_PROFILING - CFLAGS_vgettimeofday.o += -ffreestanding -fasynchronous-unwind-tables - CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -endif - -# Build rules - -ifdef CROSS32_COMPILE - VDSOCC := $(CROSS32_COMPILE)gcc -else - VDSOCC := $(CC) -endif - -CC32FLAGS := -ifdef CONFIG_PPC64 -CC32FLAGS += -m32 -KBUILD_CFLAGS := $(filter-out -mcmodel=medium -mabi=elfv1 -mabi=elfv2 -mcall-aixdesc,$(KBUILD_CFLAGS)) -endif - -targets := $(obj-vdso32) vdso32.so.dbg vgettimeofday.o -obj-vdso32 := $(addprefix $(obj)/, $(obj-vdso32)) - -GCOV_PROFILE := n -KCOV_INSTRUMENT := n -UBSAN_SANITIZE := n -KASAN_SANITIZE := n - -ccflags-y := -shared -fno-common -fno-builtin -nostdlib \ - -Wl,-soname=linux-vdso32.so.1 -Wl,--hash-style=both -asflags-y := -D__VDSO32__ -s - -obj-y += vdso32_wrapper.o -targets += vdso32.lds -CPPFLAGS_vdso32.lds += -P -C -Upowerpc - -# link rule for the .so file, .lds has to be first -$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) $(obj)/vgettimeofday.o FORCE - $(call if_changed,vdso32ld_and_check) - -# assembly rules for the .S files -$(obj-vdso32): %.o: %.S FORCE - $(call if_changed_dep,vdso32as) -$(obj)/vgettimeofday.o: %.o: %.c FORCE - $(call if_changed_dep,vdso32cc) - -# Generate VDSO offsets using helper script -gen-vdsosym := $(srctree)/$(src)/gen_vdso_offsets.sh -quiet_cmd_vdsosym = VDSOSYM $@ - cmd_vdsosym = $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@ - -include/generated/vdso32-offsets.h: $(obj)/vdso32.so.dbg FORCE - $(call if_changed,vdsosym) - -# actual build commands -quiet_cmd_vdso32ld_and_check = VDSO32L $@ - cmd_vdso32ld_and_check = $(VDSOCC) $(c_flags) $(CC32FLAGS) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) ; $(cmd_vdso_check) -quiet_cmd_vdso32as = VDSO32A $@ - cmd_vdso32as = $(VDSOCC) $(a_flags) $(CC32FLAGS) -c -o $@ $< -quiet_cmd_vdso32cc = VDSO32C $@ - cmd_vdso32cc = $(VDSOCC) $(c_flags) $(CC32FLAGS) -c -o $@ $< diff --git a/arch/powerpc/kernel/vdso32_wrapper.S b/arch/powerpc/kernel/vdso32_wrapper.S index 3f5ef035b0a9..10f92f265d51 100644 --- a/arch/powerpc/kernel/vdso32_wrapper.S +++ b/arch/powerpc/kernel/vdso32_wrapper.S @@ -7,7 +7,7 @@ .globl vdso32_start, vdso32_end .balign PAGE_SIZE vdso32_start: - .incbin "arch/powerpc/kernel/vdso32/vdso32.so.dbg" + .incbin "arch/powerpc/kernel/vdso/vdso32.so.dbg" .balign PAGE_SIZE vdso32_end: diff --git a/arch/powerpc/kernel/vdso64/.gitignore b/arch/powerpc/kernel/vdso64/.gitignore deleted file mode 100644 index 84151a7ba31d..000000000000 --- a/arch/powerpc/kernel/vdso64/.gitignore +++ /dev/null @@ -1,3 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -vdso64.lds -vdso64.so.dbg diff --git a/arch/powerpc/kernel/vdso64/Makefile b/arch/powerpc/kernel/vdso64/Makefile deleted file mode 100644 index 3c5baaa6f1e7..000000000000 --- a/arch/powerpc/kernel/vdso64/Makefile +++ /dev/null @@ -1,56 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -# List of files in the vdso, has to be asm only for now - -ARCH_REL_TYPE_ABS := R_PPC_JUMP_SLOT|R_PPC_GLOB_DAT|R_PPC_ADDR32|R_PPC_ADDR24|R_PPC_ADDR16|R_PPC_ADDR16_LO|R_PPC_ADDR16_HI|R_PPC_ADDR16_HA|R_PPC_ADDR14|R_PPC_ADDR14_BRTAKEN|R_PPC_ADDR14_BRNTAKEN|R_PPC_REL24 -include $(srctree)/lib/vdso/Makefile - -obj-vdso64 = sigtramp.o gettimeofday.o datapage.o cacheflush.o note.o getcpu.o - -ifneq ($(c-gettimeofday-y),) - CFLAGS_vgettimeofday.o += -include $(c-gettimeofday-y) - CFLAGS_vgettimeofday.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) - CFLAGS_vgettimeofday.o += $(call cc-option, -fno-stack-protector) - CFLAGS_vgettimeofday.o += -DDISABLE_BRANCH_PROFILING - CFLAGS_vgettimeofday.o += -ffreestanding -fasynchronous-unwind-tables - CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -endif - -# Build rules - -targets := $(obj-vdso64) vdso64.so.dbg vgettimeofday.o -obj-vdso64 := $(addprefix $(obj)/, $(obj-vdso64)) - -GCOV_PROFILE := n -KCOV_INSTRUMENT := n -UBSAN_SANITIZE := n -KASAN_SANITIZE := n - -ccflags-y := -shared -fno-common -fno-builtin -nostdlib \ - -Wl,-soname=linux-vdso64.so.1 -Wl,--hash-style=both - -# Go prior to 1.16.x assumes r30 is not clobbered by any VDSO code. That used to be true -# by accident when the VDSO was hand-written asm code, but may not be now that the VDSO is -# compiler generated. To avoid breaking Go tell GCC not to use r30. Impact on code -# generation is minimal, it will just use r29 instead. -ccflags-y += $(call cc-option, -ffixed-r30) - -asflags-y := -D__VDSO64__ -s - -targets += vdso64.lds -CPPFLAGS_vdso64.lds += -P -C -U$(ARCH) - -# link rule for the .so file, .lds has to be first -$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) $(obj)/vgettimeofday.o FORCE - $(call if_changed,vdso64ld_and_check) - -# Generate VDSO offsets using helper script -gen-vdsosym := $(srctree)/$(src)/gen_vdso_offsets.sh -quiet_cmd_vdsosym = VDSOSYM $@ - cmd_vdsosym = $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@ - -include/generated/vdso64-offsets.h: $(obj)/vdso64.so.dbg FORCE - $(call if_changed,vdsosym) - -# actual build commands -quiet_cmd_vdso64ld_and_check = VDSO64L $@ - cmd_vdso64ld_and_check = $(CC) $(c_flags) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^); $(cmd_vdso_check) diff --git a/arch/powerpc/kernel/vdso64/cacheflush.S b/arch/powerpc/kernel/vdso64/cacheflush.S deleted file mode 100644 index 76c3c8cf8ece..000000000000 --- a/arch/powerpc/kernel/vdso64/cacheflush.S +++ /dev/null @@ -1,75 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * vDSO provided cache flush routines - * - * Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org), - * IBM Corp. - */ -#include <asm/processor.h> -#include <asm/ppc_asm.h> -#include <asm/vdso.h> -#include <asm/vdso_datapage.h> -#include <asm/asm-offsets.h> - - .text - -/* - * Default "generic" version of __kernel_sync_dicache. - * - * void __kernel_sync_dicache(unsigned long start, unsigned long end) - * - * Flushes the data cache & invalidate the instruction cache for the - * provided range [start, end[ - */ -V_FUNCTION_BEGIN(__kernel_sync_dicache) - .cfi_startproc -BEGIN_FTR_SECTION - b 3f -END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) - mflr r12 - .cfi_register lr,r12 - get_datapage r10 - mtlr r12 - .cfi_restore lr - - lwz r7,CFG_DCACHE_BLOCKSZ(r10) - addi r5,r7,-1 - andc r6,r3,r5 /* round low to line bdy */ - subf r8,r6,r4 /* compute length */ - add r8,r8,r5 /* ensure we get enough */ - lwz r9,CFG_DCACHE_LOGBLOCKSZ(r10) - srd. r8,r8,r9 /* compute line count */ - crclr cr0*4+so - beqlr /* nothing to do? */ - mtctr r8 -1: dcbst 0,r6 - add r6,r6,r7 - bdnz 1b - sync - -/* Now invalidate the instruction cache */ - - lwz r7,CFG_ICACHE_BLOCKSZ(r10) - addi r5,r7,-1 - andc r6,r3,r5 /* round low to line bdy */ - subf r8,r6,r4 /* compute length */ - add r8,r8,r5 - lwz r9,CFG_ICACHE_LOGBLOCKSZ(r10) - srd. r8,r8,r9 /* compute line count */ - crclr cr0*4+so - beqlr /* nothing to do? */ - mtctr r8 -2: icbi 0,r6 - add r6,r6,r7 - bdnz 2b - isync - li r3,0 - blr -3: - crclr cr0*4+so - sync - isync - li r3,0 - blr - .cfi_endproc -V_FUNCTION_END(__kernel_sync_dicache) diff --git a/arch/powerpc/kernel/vdso64/datapage.S b/arch/powerpc/kernel/vdso64/datapage.S deleted file mode 100644 index 00760dc69d68..000000000000 --- a/arch/powerpc/kernel/vdso64/datapage.S +++ /dev/null @@ -1,59 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Access to the shared data page by the vDSO & syscall map - * - * Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org), IBM Corp. - */ - -#include <asm/processor.h> -#include <asm/ppc_asm.h> -#include <asm/asm-offsets.h> -#include <asm/unistd.h> -#include <asm/vdso.h> -#include <asm/vdso_datapage.h> - - .text - -/* - * void *__kernel_get_syscall_map(unsigned int *syscall_count) ; - * - * returns a pointer to the syscall map. the map is agnostic to the - * size of "long", unlike kernel bitops, it stores bits from top to - * bottom so that memory actually contains a linear bitmap - * check for syscall N by testing bit (0x80000000 >> (N & 0x1f)) of - * 32 bits int at N >> 5. - */ -V_FUNCTION_BEGIN(__kernel_get_syscall_map) - .cfi_startproc - mflr r12 - .cfi_register lr,r12 - mr r4,r3 - get_datapage r3 - mtlr r12 - addi r3,r3,CFG_SYSCALL_MAP64 - cmpldi cr0,r4,0 - crclr cr0*4+so - beqlr - li r0,NR_syscalls - stw r0,0(r4) - blr - .cfi_endproc -V_FUNCTION_END(__kernel_get_syscall_map) - - -/* - * void unsigned long __kernel_get_tbfreq(void); - * - * returns the timebase frequency in HZ - */ -V_FUNCTION_BEGIN(__kernel_get_tbfreq) - .cfi_startproc - mflr r12 - .cfi_register lr,r12 - get_datapage r3 - ld r3,CFG_TB_TICKS_PER_SEC(r3) - mtlr r12 - crclr cr0*4+so - blr - .cfi_endproc -V_FUNCTION_END(__kernel_get_tbfreq) diff --git a/arch/powerpc/kernel/vdso64/getcpu.S b/arch/powerpc/kernel/vdso64/getcpu.S deleted file mode 100644 index 12bbf236cdc4..000000000000 --- a/arch/powerpc/kernel/vdso64/getcpu.S +++ /dev/null @@ -1,33 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * - * Copyright (C) IBM Corporation, 2012 - * - * Author: Anton Blanchard <anton@au.ibm.com> - */ -#include <asm/ppc_asm.h> -#include <asm/vdso.h> - - .text -/* - * Exact prototype of getcpu - * - * int __kernel_getcpu(unsigned *cpu, unsigned *node); - * - */ -V_FUNCTION_BEGIN(__kernel_getcpu) - .cfi_startproc - mfspr r5,SPRN_SPRG_VDSO_READ - cmpdi cr0,r3,0 - cmpdi cr1,r4,0 - clrlwi r6,r5,16 - rlwinm r7,r5,16,31-15,31-0 - beq cr0,1f - stw r6,0(r3) -1: beq cr1,2f - stw r7,0(r4) -2: crclr cr0*4+so - li r3,0 /* always success */ - blr - .cfi_endproc -V_FUNCTION_END(__kernel_getcpu) diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S deleted file mode 100644 index d7a7bfb51081..000000000000 --- a/arch/powerpc/kernel/vdso64/gettimeofday.S +++ /dev/null @@ -1,58 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Userland implementation of gettimeofday() for 64 bits processes in a - * ppc64 kernel for use in the vDSO - * - * Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org), - * IBM Corp. - */ -#include <asm/processor.h> -#include <asm/ppc_asm.h> -#include <asm/vdso.h> -#include <asm/vdso_datapage.h> -#include <asm/asm-offsets.h> -#include <asm/unistd.h> -#include <asm/vdso/gettimeofday.h> - - .text -/* - * Exact prototype of gettimeofday - * - * int __kernel_gettimeofday(struct timeval *tv, struct timezone *tz); - * - */ -V_FUNCTION_BEGIN(__kernel_gettimeofday) - cvdso_call __c_kernel_gettimeofday -V_FUNCTION_END(__kernel_gettimeofday) - - -/* - * Exact prototype of clock_gettime() - * - * int __kernel_clock_gettime(clockid_t clock_id, struct timespec *tp); - * - */ -V_FUNCTION_BEGIN(__kernel_clock_gettime) - cvdso_call __c_kernel_clock_gettime -V_FUNCTION_END(__kernel_clock_gettime) - - -/* - * Exact prototype of clock_getres() - * - * int __kernel_clock_getres(clockid_t clock_id, struct timespec *res); - * - */ -V_FUNCTION_BEGIN(__kernel_clock_getres) - cvdso_call __c_kernel_clock_getres -V_FUNCTION_END(__kernel_clock_getres) - -/* - * Exact prototype of time() - * - * time_t time(time *t); - * - */ -V_FUNCTION_BEGIN(__kernel_time) - cvdso_call_time __c_kernel_time -V_FUNCTION_END(__kernel_time) diff --git a/arch/powerpc/kernel/vdso64/note.S b/arch/powerpc/kernel/vdso64/note.S deleted file mode 100644 index dc2a509f7e8a..000000000000 --- a/arch/powerpc/kernel/vdso64/note.S +++ /dev/null @@ -1 +0,0 @@ -#include "../vdso32/note.S" diff --git a/arch/powerpc/kernel/vdso64/vgettimeofday.c b/arch/powerpc/kernel/vdso64/vgettimeofday.c deleted file mode 100644 index 5b5500058344..000000000000 --- a/arch/powerpc/kernel/vdso64/vgettimeofday.c +++ /dev/null @@ -1,29 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Powerpc userspace implementations of gettimeofday() and similar. - */ -#include <linux/time.h> -#include <linux/types.h> - -int __c_kernel_clock_gettime(clockid_t clock, struct __kernel_timespec *ts, - const struct vdso_data *vd) -{ - return __cvdso_clock_gettime_data(vd, clock, ts); -} - -int __c_kernel_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz, - const struct vdso_data *vd) -{ - return __cvdso_gettimeofday_data(vd, tv, tz); -} - -int __c_kernel_clock_getres(clockid_t clock_id, struct __kernel_timespec *res, - const struct vdso_data *vd) -{ - return __cvdso_clock_getres_data(vd, clock_id, res); -} - -__kernel_old_time_t __c_kernel_time(__kernel_old_time_t *time, const struct vdso_data *vd) -{ - return __cvdso_time_data(vd, time); -} diff --git a/arch/powerpc/kernel/vdso64_wrapper.S b/arch/powerpc/kernel/vdso64_wrapper.S index 1d56d81fe3b3..839d1a61411d 100644 --- a/arch/powerpc/kernel/vdso64_wrapper.S +++ b/arch/powerpc/kernel/vdso64_wrapper.S @@ -7,7 +7,7 @@ .globl vdso64_start, vdso64_end .balign PAGE_SIZE vdso64_start: - .incbin "arch/powerpc/kernel/vdso64/vdso64.so.dbg" + .incbin "arch/powerpc/kernel/vdso/vdso64.so.dbg" .balign PAGE_SIZE vdso64_end: diff --git a/arch/powerpc/kernel/vecemu.c b/arch/powerpc/kernel/vecemu.c index ae632569446f..fd9432875ebc 100644 --- a/arch/powerpc/kernel/vecemu.c +++ b/arch/powerpc/kernel/vecemu.c @@ -261,7 +261,7 @@ static unsigned int rfin(unsigned int x) int emulate_altivec(struct pt_regs *regs) { - struct ppc_inst instr; + ppc_inst_t instr; unsigned int i, word; unsigned int va, vb, vc, vd; vector128 *vrs; diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S index ba03eedfdcd8..5cf64740edb8 100644 --- a/arch/powerpc/kernel/vector.S +++ b/arch/powerpc/kernel/vector.S @@ -47,6 +47,10 @@ EXPORT_SYMBOL(store_vr_state) */ _GLOBAL(load_up_altivec) mfmsr r5 /* grab the current MSR */ +#ifdef CONFIG_PPC_BOOK3S_64 + /* interrupt doesn't set MSR[RI] and HPT can fault on current access */ + ori r5,r5,MSR_RI +#endif oris r5,r5,MSR_VEC@h MTMSRD(r5) /* enable use of AltiVec now */ isync @@ -126,6 +130,12 @@ _GLOBAL(load_up_vsx) andis. r5,r12,MSR_VEC@h beql+ load_up_altivec /* skip if already loaded */ +#ifdef CONFIG_PPC_BOOK3S_64 + /* interrupt doesn't set MSR[RI] and HPT can fault on current access */ + li r5,MSR_RI + mtmsrd r5,1 +#endif + ld r4,PACACURRENT(r13) addi r4,r4,THREAD /* Get THREAD */ li r6,1 @@ -145,8 +155,8 @@ _GLOBAL(load_up_vsx) * usage of floating-point registers. These routines must be called * with preempt disabled. */ -#ifdef CONFIG_PPC32 .data +#ifdef CONFIG_PPC32 fpzero: .long 0 fpone: @@ -159,18 +169,17 @@ fphalf: lfs fr,name@l(r11) #else - .section ".toc","aw" fpzero: - .tc FD_0_0[TC],0 + .quad 0 fpone: - .tc FD_3ff00000_0[TC],0x3ff0000000000000 /* 1.0 */ + .quad 0x3ff0000000000000 /* 1.0 */ fphalf: - .tc FD_3fe00000_0[TC],0x3fe0000000000000 /* 0.5 */ + .quad 0x3fe0000000000000 /* 0.5 */ -#define LDCONST(fr, name) \ - lfd fr,name@toc(r2) +#define LDCONST(fr, name) \ + addis r11,r2,name@toc@ha; \ + lfd fr,name@toc@l(r11) #endif - .text /* * Internal routine to enable floating point and set FPSCR to 0. diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 18e42c74abdd..7786e3ac7611 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -32,6 +32,10 @@ #define STRICT_ALIGN_SIZE (1 << CONFIG_DATA_SHIFT) +#if STRICT_ALIGN_SIZE < PAGE_SIZE +#error "CONFIG_DATA_SHIFT must be >= PAGE_SHIFT" +#endif + ENTRY(_stext) PHDRS { @@ -67,7 +71,7 @@ SECTIONS .head.text : AT(ADDR(.head.text) - LOAD_OFFSET) { #ifdef CONFIG_PPC64 KEEP(*(.head.text.first_256B)); -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 #else KEEP(*(.head.text.real_vectors)); *(.head.text.real_trampolines); @@ -122,14 +126,6 @@ SECTIONS *(.sfpr); MEM_KEEP(init.text) MEM_KEEP(exit.text) - -#ifdef CONFIG_PPC32 - *(.got1) - __got2_start = .; - *(.got2) - __got2_end = .; -#endif /* CONFIG_PPC32 */ - } :text . = ALIGN(PAGE_SIZE); @@ -139,15 +135,57 @@ SECTIONS /* Read-only data */ RO_DATA(PAGE_SIZE) -#ifdef CONFIG_PPC64 +#ifdef CONFIG_PPC32 + .sdata2 : AT(ADDR(.sdata2) - LOAD_OFFSET) { + *(.sdata2) + } +#endif + + .data.rel.ro : AT(ADDR(.data.rel.ro) - LOAD_OFFSET) { + *(.data.rel.ro*) + } + + .branch_lt : AT(ADDR(.branch_lt) - LOAD_OFFSET) { + *(.branch_lt) + } + +#ifdef CONFIG_PPC32 + .got1 : AT(ADDR(.got1) - LOAD_OFFSET) { + *(.got1) + } + .got2 : AT(ADDR(.got2) - LOAD_OFFSET) { + __got2_start = .; + *(.got2) + __got2_end = .; + } + .got : AT(ADDR(.got) - LOAD_OFFSET) { + *(.got) + *(.got.plt) + } + .plt : AT(ADDR(.plt) - LOAD_OFFSET) { + /* XXX: is .plt (and .got.plt) required? */ + *(.plt) + } + +#else /* CONFIG_PPC32 */ + .toc1 : AT(ADDR(.toc1) - LOAD_OFFSET) { + *(.toc1) + } + + .got : AT(ADDR(.got) - LOAD_OFFSET) ALIGN(256) { + *(.got .toc) + } + SOFT_MASK_TABLE(8) RESTART_TABLE(8) +#ifdef CONFIG_PPC64_ELF_ABI_V1 .opd : AT(ADDR(.opd) - LOAD_OFFSET) { __start_opd = .; KEEP(*(.opd)) __end_opd = .; } +#endif . = ALIGN(8); __stf_entry_barrier_fixup : AT(ADDR(__stf_entry_barrier_fixup) - LOAD_OFFSET) { @@ -190,7 +228,7 @@ SECTIONS *(__rfi_flush_fixup) __stop___rfi_flush_fixup = .; } -#endif /* CONFIG_PPC64 */ +#endif /* CONFIG_PPC32 */ #ifdef CONFIG_PPC_BARRIER_NOSPEC . = ALIGN(8); @@ -201,7 +239,7 @@ SECTIONS } #endif /* CONFIG_PPC_BARRIER_NOSPEC */ -#ifdef CONFIG_PPC_FSL_BOOK3E +#ifdef CONFIG_PPC_E500 . = ALIGN(8); __spec_btb_flush_fixup : AT(ADDR(__spec_btb_flush_fixup) - LOAD_OFFSET) { __start__btb_flush_fixup = .; @@ -210,12 +248,17 @@ SECTIONS } #endif + /* + * Various code relies on __init_begin being at the strict RWX boundary. + */ + . = ALIGN(STRICT_ALIGN_SIZE); + __srwx_boundary = .; + __end_rodata = .; + __init_begin = .; + /* * Init sections discarded at runtime */ - . = ALIGN(STRICT_ALIGN_SIZE); - __init_begin = .; - . = ALIGN(PAGE_SIZE); .init.text : AT(ADDR(.init.text) - LOAD_OFFSET) { _sinittext = .; INIT_TEXT @@ -281,9 +324,7 @@ SECTIONS . = ALIGN(8); .dynsym : AT(ADDR(.dynsym) - LOAD_OFFSET) { -#ifdef CONFIG_PPC32 __dynamic_symtab = .; -#endif *(.dynsym) } .dynstr : AT(ADDR(.dynstr) - LOAD_OFFSET) { *(.dynstr) } @@ -319,44 +360,13 @@ SECTIONS . = ALIGN(PAGE_SIZE); _sdata = .; -#ifdef CONFIG_PPC32 .data : AT(ADDR(.data) - LOAD_OFFSET) { DATA_DATA -#ifdef CONFIG_UBSAN - *(.data..Lubsan_data*) - *(.data..Lubsan_type*) -#endif *(.data.rel*) +#ifdef CONFIG_PPC32 *(SDATA_MAIN) - *(.sdata2) - *(.got.plt) *(.got) - *(.plt) - *(.branch_lt) - } -#else - .data : AT(ADDR(.data) - LOAD_OFFSET) { - DATA_DATA -#ifdef CONFIG_UBSAN - *(.data..Lubsan_data*) - *(.data..Lubsan_type*) #endif - *(.data.rel*) - *(.toc1) - *(.branch_lt) - } - - . = ALIGN(256); - .got : AT(ADDR(.got) - LOAD_OFFSET) { - __toc_start = .; -#ifndef CONFIG_RELOCATABLE - __prom_init_toc_start = .; - arch/powerpc/kernel/prom_init.o*(.toc .got) - __prom_init_toc_end = .; -#endif - *(.got) - *(.toc) } -#endif /* The initial task and kernel stack */ INIT_TASK_DATA_SECTION(THREAD_ALIGN) @@ -394,7 +404,6 @@ SECTIONS _end = . ; PROVIDE32 (end = .); - STABS_DEBUG DWARF_DEBUG ELF_DETAILS diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c index 3fa6d240bade..dbcc4a793f0b 100644 --- a/arch/powerpc/kernel/watchdog.c +++ b/arch/powerpc/kernel/watchdog.c @@ -56,7 +56,7 @@ * solved by also having a SMP watchdog where all CPUs check all other * CPUs heartbeat. * - * The SMP checker can detect lockups on other CPUs. A gobal "pending" + * The SMP checker can detect lockups on other CPUs. A global "pending" * cpumask is kept, containing all CPUs which enable the watchdog. Each * CPU clears their pending bit in their heartbeat timer. When the bitmask * becomes empty, the last CPU to clear its pending bit updates a global @@ -85,10 +85,41 @@ static DEFINE_PER_CPU(u64, wd_timer_tb); /* SMP checker bits */ static unsigned long __wd_smp_lock; +static unsigned long __wd_reporting; +static unsigned long __wd_nmi_output; static cpumask_t wd_smp_cpus_pending; static cpumask_t wd_smp_cpus_stuck; static u64 wd_smp_last_reset_tb; +#ifdef CONFIG_PPC_PSERIES +static u64 wd_timeout_pct; +#endif + +/* + * Try to take the exclusive watchdog action / NMI IPI / printing lock. + * wd_smp_lock must be held. If this fails, we should return and wait + * for the watchdog to kick in again (or another CPU to trigger it). + * + * Importantly, if hardlockup_panic is set, wd_try_report failure should + * not delay the panic, because whichever other CPU is reporting will + * call panic. + */ +static bool wd_try_report(void) +{ + if (__wd_reporting) + return false; + __wd_reporting = 1; + return true; +} + +/* End printing after successful wd_try_report. wd_smp_lock not required. */ +static void wd_end_reporting(void) +{ + smp_mb(); /* End printing "critical section" */ + WARN_ON_ONCE(__wd_reporting == 0); + WRITE_ONCE(__wd_reporting, 0); +} + static inline void wd_smp_lock(unsigned long *flags) { /* @@ -128,109 +159,182 @@ static void wd_lockup_ipi(struct pt_regs *regs) else dump_stack(); + /* + * __wd_nmi_output must be set after we printk from NMI context. + * + * printk from NMI context defers printing to the console to irq_work. + * If that NMI was taken in some code that is hard-locked, then irqs + * are disabled so irq_work will never fire. That can result in the + * hard lockup messages being delayed (indefinitely, until something + * else kicks the console drivers). + * + * Setting __wd_nmi_output will cause another CPU to notice and kick + * the console drivers for us. + * + * xchg is not needed here (it could be a smp_mb and store), but xchg + * gives the memory ordering and atomicity required. + */ + xchg(&__wd_nmi_output, 1); + /* Do not panic from here because that can recurse into NMI IPI layer */ } -static void set_cpumask_stuck(const struct cpumask *cpumask, u64 tb) +static bool set_cpu_stuck(int cpu) { - cpumask_or(&wd_smp_cpus_stuck, &wd_smp_cpus_stuck, cpumask); - cpumask_andnot(&wd_smp_cpus_pending, &wd_smp_cpus_pending, cpumask); + cpumask_set_cpu(cpu, &wd_smp_cpus_stuck); + cpumask_clear_cpu(cpu, &wd_smp_cpus_pending); + /* + * See wd_smp_clear_cpu_pending() + */ + smp_mb(); if (cpumask_empty(&wd_smp_cpus_pending)) { - wd_smp_last_reset_tb = tb; + wd_smp_last_reset_tb = get_tb(); cpumask_andnot(&wd_smp_cpus_pending, &wd_cpus_enabled, &wd_smp_cpus_stuck); + return true; } -} -static void set_cpu_stuck(int cpu, u64 tb) -{ - set_cpumask_stuck(cpumask_of(cpu), tb); + return false; } -static void watchdog_smp_panic(int cpu, u64 tb) +static void watchdog_smp_panic(int cpu) { + static cpumask_t wd_smp_cpus_ipi; // protected by reporting unsigned long flags; + u64 tb, last_reset; int c; wd_smp_lock(&flags); /* Double check some things under lock */ - if ((s64)(tb - wd_smp_last_reset_tb) < (s64)wd_smp_panic_timeout_tb) + tb = get_tb(); + last_reset = wd_smp_last_reset_tb; + if ((s64)(tb - last_reset) < (s64)wd_smp_panic_timeout_tb) goto out; if (cpumask_test_cpu(cpu, &wd_smp_cpus_pending)) goto out; - if (cpumask_weight(&wd_smp_cpus_pending) == 0) + if (!wd_try_report()) goto out; + for_each_online_cpu(c) { + if (!cpumask_test_cpu(c, &wd_smp_cpus_pending)) + continue; + if (c == cpu) + continue; // should not happen + + __cpumask_set_cpu(c, &wd_smp_cpus_ipi); + if (set_cpu_stuck(c)) + break; + } + if (cpumask_empty(&wd_smp_cpus_ipi)) { + wd_end_reporting(); + goto out; + } + wd_smp_unlock(&flags); pr_emerg("CPU %d detected hard LOCKUP on other CPUs %*pbl\n", - cpu, cpumask_pr_args(&wd_smp_cpus_pending)); + cpu, cpumask_pr_args(&wd_smp_cpus_ipi)); pr_emerg("CPU %d TB:%lld, last SMP heartbeat TB:%lld (%lldms ago)\n", - cpu, tb, wd_smp_last_reset_tb, - tb_to_ns(tb - wd_smp_last_reset_tb) / 1000000); + cpu, tb, last_reset, tb_to_ns(tb - last_reset) / 1000000); if (!sysctl_hardlockup_all_cpu_backtrace) { /* * Try to trigger the stuck CPUs, unless we are going to * get a backtrace on all of them anyway. */ - for_each_cpu(c, &wd_smp_cpus_pending) { - if (c == cpu) - continue; + for_each_cpu(c, &wd_smp_cpus_ipi) { smp_send_nmi_ipi(c, wd_lockup_ipi, 1000000); + __cpumask_clear_cpu(c, &wd_smp_cpus_ipi); } - } - - /* Take the stuck CPUs out of the watch group */ - set_cpumask_stuck(&wd_smp_cpus_pending, tb); - - wd_smp_unlock(&flags); - - if (sysctl_hardlockup_all_cpu_backtrace) + } else { trigger_allbutself_cpu_backtrace(); - - /* - * Force flush any remote buffers that might be stuck in IRQ context - * and therefore could not run their irq_work. - */ - printk_trigger_flush(); + cpumask_clear(&wd_smp_cpus_ipi); + } if (hardlockup_panic) nmi_panic(NULL, "Hard LOCKUP"); + wd_end_reporting(); + return; out: wd_smp_unlock(&flags); } -static void wd_smp_clear_cpu_pending(int cpu, u64 tb) +static void wd_smp_clear_cpu_pending(int cpu) { if (!cpumask_test_cpu(cpu, &wd_smp_cpus_pending)) { if (unlikely(cpumask_test_cpu(cpu, &wd_smp_cpus_stuck))) { struct pt_regs *regs = get_irq_regs(); unsigned long flags; - wd_smp_lock(&flags); - pr_emerg("CPU %d became unstuck TB:%lld\n", - cpu, tb); + cpu, get_tb()); print_irqtrace_events(current); if (regs) show_regs(regs); else dump_stack(); + wd_smp_lock(&flags); cpumask_clear_cpu(cpu, &wd_smp_cpus_stuck); wd_smp_unlock(&flags); + } else { + /* + * The last CPU to clear pending should have reset the + * watchdog so we generally should not find it empty + * here if our CPU was clear. However it could happen + * due to a rare race with another CPU taking the + * last CPU out of the mask concurrently. + * + * We can't add a warning for it. But just in case + * there is a problem with the watchdog that is causing + * the mask to not be reset, try to kick it along here. + */ + if (unlikely(cpumask_empty(&wd_smp_cpus_pending))) + goto none_pending; } return; } + + /* + * All other updates to wd_smp_cpus_pending are performed under + * wd_smp_lock. All of them are atomic except the case where the + * mask becomes empty and is reset. This will not happen here because + * cpu was tested to be in the bitmap (above), and a CPU only clears + * its own bit. _Except_ in the case where another CPU has detected a + * hard lockup on our CPU and takes us out of the pending mask. So in + * normal operation there will be no race here, no problem. + * + * In the lockup case, this atomic clear-bit vs a store that refills + * other bits in the accessed word wll not be a problem. The bit clear + * is atomic so it will not cause the store to get lost, and the store + * will never set this bit so it will not overwrite the bit clear. The + * only way for a stuck CPU to return to the pending bitmap is to + * become unstuck itself. + */ cpumask_clear_cpu(cpu, &wd_smp_cpus_pending); + + /* + * Order the store to clear pending with the load(s) to check all + * words in the pending mask to check they are all empty. This orders + * with the same barrier on another CPU. This prevents two CPUs + * clearing the last 2 pending bits, but neither seeing the other's + * store when checking if the mask is empty, and missing an empty + * mask, which ends with a false positive. + */ + smp_mb(); if (cpumask_empty(&wd_smp_cpus_pending)) { unsigned long flags; +none_pending: + /* + * Double check under lock because more than one CPU could see + * a clear mask with the lockless check after clearing their + * pending bits. + */ wd_smp_lock(&flags); if (cpumask_empty(&wd_smp_cpus_pending)) { - wd_smp_last_reset_tb = tb; + wd_smp_last_reset_tb = get_tb(); cpumask_andnot(&wd_smp_cpus_pending, &wd_cpus_enabled, &wd_smp_cpus_stuck); @@ -245,10 +349,21 @@ static void watchdog_timer_interrupt(int cpu) per_cpu(wd_timer_tb, cpu) = tb; - wd_smp_clear_cpu_pending(cpu, tb); + wd_smp_clear_cpu_pending(cpu); if ((s64)(tb - wd_smp_last_reset_tb) >= (s64)wd_smp_panic_timeout_tb) - watchdog_smp_panic(cpu, tb); + watchdog_smp_panic(cpu); + + if (__wd_nmi_output && xchg(&__wd_nmi_output, 0)) { + /* + * Something has called printk from NMI context. It might be + * stuck, so this triggers a flush that will get that + * printk output to the console. + * + * See wd_lockup_ipi. + */ + printk_trigger_flush(); + } } DEFINE_INTERRUPT_HANDLER_NMI(soft_nmi_interrupt) @@ -267,12 +382,27 @@ DEFINE_INTERRUPT_HANDLER_NMI(soft_nmi_interrupt) tb = get_tb(); if (tb - per_cpu(wd_timer_tb, cpu) >= wd_panic_timeout_tb) { + /* + * Taking wd_smp_lock here means it is a soft-NMI lock, which + * means we can't take any regular or irqsafe spin locks while + * holding this lock. This is why timers can't printk while + * holding the lock. + */ wd_smp_lock(&flags); if (cpumask_test_cpu(cpu, &wd_smp_cpus_stuck)) { wd_smp_unlock(&flags); return 0; } - set_cpu_stuck(cpu, tb); + if (!wd_try_report()) { + wd_smp_unlock(&flags); + /* Couldn't report, try again in 100ms */ + mtspr(SPRN_DEC, 100 * tb_ticks_per_usec * 1000); + return 0; + } + + set_cpu_stuck(cpu); + + wd_smp_unlock(&flags); pr_emerg("CPU %d self-detected hard LOCKUP @ %pS\n", cpu, (void *)regs->nip); @@ -283,14 +413,21 @@ DEFINE_INTERRUPT_HANDLER_NMI(soft_nmi_interrupt) print_irqtrace_events(current); show_regs(regs); - wd_smp_unlock(&flags); + xchg(&__wd_nmi_output, 1); // see wd_lockup_ipi if (sysctl_hardlockup_all_cpu_backtrace) trigger_allbutself_cpu_backtrace(); if (hardlockup_panic) nmi_panic(regs, "Hard LOCKUP"); + + wd_end_reporting(); } + /* + * We are okay to change DEC in soft_nmi_interrupt because the masked + * handler has marked a DEC as pending, so the timer interrupt will be + * replayed as soon as local irqs are enabled again. + */ if (wd_panic_timeout_tb < 0x7fffffff) mtspr(SPRN_DEC, wd_panic_timeout_tb); @@ -318,11 +455,15 @@ void arch_touch_nmi_watchdog(void) { unsigned long ticks = tb_ticks_per_usec * wd_timer_period_ms * 1000; int cpu = smp_processor_id(); - u64 tb = get_tb(); + u64 tb; + if (!cpumask_test_cpu(cpu, &watchdog_cpumask)) + return; + + tb = get_tb(); if (tb - per_cpu(wd_timer_tb, cpu) >= ticks) { per_cpu(wd_timer_tb, cpu) = tb; - wd_smp_clear_cpu_pending(cpu, tb); + wd_smp_clear_cpu_pending(cpu); } } EXPORT_SYMBOL(arch_touch_nmi_watchdog); @@ -380,7 +521,7 @@ static void stop_watchdog(void *arg) cpumask_clear_cpu(cpu, &wd_cpus_enabled); wd_smp_unlock(&flags); - wd_smp_clear_cpu_pending(cpu, get_tb()); + wd_smp_clear_cpu_pending(cpu); } static int stop_watchdog_on_cpu(unsigned int cpu) @@ -390,7 +531,13 @@ static int stop_watchdog_on_cpu(unsigned int cpu) static void watchdog_calc_timeouts(void) { - wd_panic_timeout_tb = watchdog_thresh * ppc_tb_freq; + u64 threshold = watchdog_thresh; + +#ifdef CONFIG_PPC_PSERIES + threshold += (READ_ONCE(wd_timeout_pct) * threshold) / 100; +#endif + + wd_panic_timeout_tb = threshold * ppc_tb_freq; /* Have the SMP detector trigger a bit later */ wd_smp_panic_timeout_tb = wd_panic_timeout_tb * 3 / 2; @@ -433,3 +580,12 @@ int __init watchdog_nmi_probe(void) } return 0; } + +#ifdef CONFIG_PPC_PSERIES +void watchdog_nmi_set_timeout_pct(u64 pct) +{ + pr_info("Set the NMI watchdog timeout factor to %llu%%\n", pct); + WRITE_ONCE(wd_timeout_pct, pct); + lockup_detector_reconfigure(); +} +#endif |