diff options
Diffstat (limited to 'arch/powerpc/kernel')
67 files changed, 602 insertions, 767 deletions
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 4ddd161aef32..2e2a2a9bcf43 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -33,6 +33,17 @@ 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 + +# 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 @@ -68,7 +79,7 @@ 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 diff --git a/arch/powerpc/kernel/btext.c b/arch/powerpc/kernel/btext.c index 9d9d56b574cc..8f69bb07e500 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); diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c index 00b0992be3e7..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> diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index ae0fdef0ac11..a5dbfccd2047 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -12,9 +12,9 @@ #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> @@ -487,11 +487,29 @@ static struct cpu_spec __initdata cpu_specs[] = { .machine_check_early = __machine_check_early_realmode_p9, .platform = "power9", }, - { /* Power9 DD2.2 or later */ + { /* 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, + .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 DD2.3 or later */ .pvr_mask = 0xffff0000, .pvr_value = 0x004e0000, .cpu_name = "POWER9 (raw)", - .cpu_features = CPU_FTRS_POWER9_DD2_2, + .cpu_features = CPU_FTRS_POWER9_DD2_3, .cpu_user_features = COMMON_USER_POWER9, .cpu_user_features2 = COMMON_USER2_POWER9, .mmu_features = MMU_FTRS_POWER9, @@ -2025,7 +2043,7 @@ static struct cpu_spec * __init setup_cpu_spec(unsigned long offset, * 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 + * oprofile_cpu_type. Furthermore, let's ensure that the * fix for the PMAO bug is enabled on compatibility mode. */ if (old.oprofile_cpu_type != NULL) { @@ -2119,7 +2137,7 @@ 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 32b4a97f1b79..9a3b85bfc83f 100644 --- a/arch/powerpc/kernel/crash_dump.c +++ b/arch/powerpc/kernel/crash_dump.c @@ -12,9 +12,9 @@ #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/uio.h> #include <asm/rtas.h> diff --git a/arch/powerpc/kernel/dawr.c b/arch/powerpc/kernel/dawr.c index 64e423d2fe0f..30d4eca88d17 100644 --- a/arch/powerpc/kernel/dawr.c +++ b/arch/powerpc/kernel/dawr.c @@ -27,7 +27,7 @@ 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/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index 7d1b2c4a4891..2ad365c21afa 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> @@ -774,20 +774,26 @@ 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; } 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_driver.c b/arch/powerpc/kernel/eeh_driver.c index 422f80b5b27b..260273e56431 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 { 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 7748c278d13c..1d599df6f169 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -555,52 +555,3 @@ 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 9581906b5ee9..01ace4c56104 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -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) diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index 4c09c6688ac6..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. @@ -365,6 +366,11 @@ static unsigned long __init get_fadump_area_size(void) 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.*/ @@ -728,7 +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 @@ -867,7 +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) { @@ -886,7 +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) { @@ -968,11 +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; @@ -1164,6 +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; } @@ -1271,7 +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; @@ -1286,11 +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 */ @@ -1661,8 +1675,8 @@ int __init setup_fadump(void) } /* * Use subsys_initcall_sync() here because there is dependency with - * crash_save_vmcoreinfo_init(), which mush run first to ensure vmcoreinfo initialization - * is done before regisering with f/w. + * 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 */ diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 5c5181e8d5f1..d3eea633d11a 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. */ @@ -435,7 +435,7 @@ 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 diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c index 4ad79eb638c6..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); diff --git a/arch/powerpc/kernel/interrupt_64.S b/arch/powerpc/kernel/interrupt_64.S index 7bab2d7de372..ce25b28cf418 100644 --- a/arch/powerpc/kernel/interrupt_64.S +++ b/arch/powerpc/kernel/interrupt_64.S @@ -219,16 +219,6 @@ 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 @@ -721,7 +711,7 @@ _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..7e56ddb3e0b9 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> @@ -1065,7 +1064,7 @@ 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 +1079,7 @@ 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 752fb182eacb..ea38c13936c7 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -52,13 +52,13 @@ #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> @@ -217,7 +217,6 @@ static inline void replay_soft_interrupts_irqrestore(void) #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; @@ -313,82 +312,6 @@ happened: __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); /* @@ -730,6 +653,8 @@ static __always_inline void call_do_irq(struct pt_regs *regs, void *sp) ); } +DEFINE_STATIC_CALL_RET0(ppc_get_irq, *ppc_md.get_irq); + void __do_irq(struct pt_regs *regs) { unsigned int irq; @@ -741,7 +666,7 @@ void __do_irq(struct pt_regs *regs) * * 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 */ if (should_hard_irq_enable()) @@ -809,6 +734,9 @@ 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); } #ifdef CONFIG_BOOKE_OR_40x 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/kprobes.c b/arch/powerpc/kernel/kprobes.c index 7dae0b01abfb..1c97c0f177ae 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. @@ -107,7 +107,7 @@ kprobe_opcode_t *kprobe_lookup_name(const char *name, unsigned int offset) static bool arch_kprobe_on_func_entry(unsigned long offset) { -#ifdef PPC64_ELF_ABI_v2 +#ifdef CONFIG_PPC64_ELF_ABI_V2 #ifdef CONFIG_KPROBES_ON_FTRACE return offset <= 16; #else @@ -150,8 +150,8 @@ int arch_prepare_kprobe(struct kprobe *p) 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))) { diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c index cfc03e016ff2..5c58460b269a 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> diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index d38a019b38e1..fd6d8d3a548e 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -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 97a76a8619fb..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"); diff --git a/arch/powerpc/kernel/module_32.c b/arch/powerpc/kernel/module_32.c index a0432ef46967..ea6536171778 100644 --- a/arch/powerpc/kernel/module_32.c +++ b/arch/powerpc/kernel/module_32.c @@ -99,7 +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, @@ -256,9 +256,8 @@ int apply_relocate_add(Elf32_Shdr *sechdrs, value, (uint32_t)location); pr_debug("Location before: %08X.\n", *(uint32_t *)location); - value = (*(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; @@ -266,10 +265,8 @@ int apply_relocate_add(Elf32_Shdr *sechdrs, 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: @@ -289,23 +286,32 @@ int apply_relocate_add(Elf32_Shdr *sechdrs, } #ifdef CONFIG_DYNAMIC_FTRACE -int module_trampoline_target(struct module *mod, unsigned long addr, - unsigned long *target) +notrace int module_trampoline_target(struct module *mod, unsigned long addr, + unsigned long *target) { - unsigned int jmp[4]; + ppc_inst_t jmp[4]; /* Find where the trampoline jumps to */ - if (copy_from_kernel_nofault(jmp, (void *)addr, sizeof(jmp))) + 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 ((jmp[0] & 0xffff0000) != PPC_RAW_LIS(_R12, 0) || - (jmp[1] & 0xffff0000) != PPC_RAW_ADDI(_R12, _R12, 0) || - jmp[2] != PPC_RAW_MTCTR(_R12) || - jmp[3] != PPC_RAW_BCTR()) + 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 = (jmp[1] & 0xffff) | ((jmp[0] & 0xffff) << 16); + addr = (ppc_inst_val(jmp[1]) & 0xffff) | ((ppc_inst_val(jmp[0]) & 0xffff) << 16); if (addr & 0x8000) addr -= 0x10000; diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 794720530442..7e45dc98df8a 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -31,7 +31,7 @@ this, and makes other things simpler. Anton? --RR. */ -#ifdef PPC64_ELF_ABI_v2 +#ifdef CONFIG_PPC64_ELF_ABI_V2 static func_desc_t func_desc(unsigned long addr) { @@ -122,7 +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 @@ -194,7 +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, @@ -361,7 +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; @@ -653,8 +653,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, } /* Only replace bits 2 through 26 */ - value = (*(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; diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c index 0d9f9cd41e13..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 diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index 39da688a9455..ba593fd60124 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -344,15 +344,10 @@ void copy_mm_to_paca(struct mm_struct *mm) { 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 } #endif /* CONFIG_PPC_64S_HASH_MMU */ diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 8bc9cf62cd93..068410cd54a3 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -30,10 +30,10 @@ #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> @@ -42,7 +42,7 @@ #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); @@ -1688,7 +1688,7 @@ 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 48537964fba1..5a174936c9a0 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> diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index 3fb7e572abed..19b03ddf5631 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 +285,12 @@ int pcibus_to_node(struct pci_bus *bus) } EXPORT_SYMBOL(pcibus_to_node); #endif + +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; +} diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c index 61571ae23953..938ab8838ab5 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> 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/proc_powerpc.c b/arch/powerpc/kernel/proc_powerpc.c index 6a029f2378e1..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 diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 984813a4d5dc..d00b20c65966 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> @@ -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))); @@ -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++) { @@ -2313,42 +2310,3 @@ unsigned long arch_align_stack(unsigned long sp) sp -= get_random_int() & ~PAGE_MASK; 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. - */ - if (!radix_enabled() && !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 86c4f009563d..feae8509b59c 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -31,7 +31,6 @@ #include <linux/cpu.h> #include <linux/pgtable.h> -#include <asm/prom.h> #include <asm/rtas.h> #include <asm/page.h> #include <asm/processor.h> diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 0ac5faacc909..04694ec423f6 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> @@ -3416,7 +3418,7 @@ 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/ptrace/ptrace-view.c b/arch/powerpc/kernel/ptrace/ptrace-view.c index f15bc78caf71..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) { diff --git a/arch/powerpc/kernel/ptrace/ptrace.c b/arch/powerpc/kernel/ptrace/ptrace.c index 6d5026a9db4f..4d2dc22d4a2d 100644 --- a/arch/powerpc/kernel/ptrace/ptrace.c +++ b/arch/powerpc/kernel/ptrace/ptrace.c @@ -444,10 +444,4 @@ void __init pt_regs_check(void) * real registers. */ BUILD_BUG_ON(PT_DSCR < sizeof(struct user_pt_regs) / sizeof(unsigned long)); - -#ifdef PPC64_ELF_ABI_v1 - BUILD_BUG_ON(!IS_ENABLED(CONFIG_HAVE_FUNCTION_DESCRIPTORS)); -#else - BUILD_BUG_ON(IS_ENABLED(CONFIG_HAVE_FUNCTION_DESCRIPTORS)); -#endif } 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 1f42aabbbab3..9bb43aa53d43 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -24,9 +24,10 @@ #include <linux/slab.h> #include <linux/reboot.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> @@ -49,6 +50,19 @@ 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 */ @@ -462,6 +476,11 @@ int rtas_call(int token, int nargs, int nret, int *outputs, ...) if (!rtas.entry || token == RTAS_UNKNOWN_SERVICE) 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 */ diff --git a/arch/powerpc/kernel/rtas_entry.S b/arch/powerpc/kernel/rtas_entry.S new file mode 100644 index 000000000000..9a434d42e660 --- /dev/null +++ b/arch/powerpc/kernel/rtas_entry.S @@ -0,0 +1,172 @@ +/* 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. + */ + LOAD_REG_IMMEDIATE(r6, MSR_ME | MSR_RI) + + 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 cf0f42909ddf..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> diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 518ae5aa9410..9d83d16fef9a 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -23,19 +23,19 @@ #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/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> @@ -279,7 +279,7 @@ 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 */ @@ -680,8 +680,25 @@ 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 +708,63 @@ 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 diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index a6e9d36d7c01..813261789303 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> diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index a96f05063bc9..0e8fc1cd1c55 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -31,11 +31,12 @@ #include <linux/memory.h> #include <linux/nmi.h> #include <linux/pgtable.h> +#include <linux/of.h> +#include <linux/of_fdt.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> diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index f7f8620663c7..68a91e553e14 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -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 */ diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index d84c434b2b78..157a7403e3eb 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -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 diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 73d483b07ff3..472596a109e2 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); diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index de0f6f09a5dd..bcefab484ea6 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -43,7 +43,6 @@ #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> @@ -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; @@ -875,7 +874,7 @@ 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 @@ -1102,7 +1101,7 @@ 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()); diff --git a/arch/powerpc/kernel/syscalls.c b/arch/powerpc/kernel/syscalls.c index c4f5b4ce926f..fc999140bc27 100644 --- a/arch/powerpc/kernel/syscalls.c +++ b/arch/powerpc/kernel/syscalls.c @@ -73,7 +73,7 @@ SYSCALL_DEFINE6(mmap, unsigned long, addr, size_t, len, 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 ) + if ((unsigned long)n >= 4096) return sys_old_select((void __user *)n); return sys_select(n, inp, outp, exp, tvp); diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index 2069bbb90a9a..3a10cda9c05e 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> diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index f80cce0e3899..587adcc12860 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> @@ -63,7 +65,6 @@ #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> @@ -156,10 +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; @@ -185,6 +182,8 @@ static inline unsigned long read_spurr(unsigned long tb) #include <asm/dtl.h> +void (*dtl_consumer)(struct dtl_entry *, u64); + /* * Scan the dispatch trace log and count up the stolen time. * Should be called with interrupts disabled. @@ -829,7 +828,7 @@ 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) @@ -974,7 +973,7 @@ 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/trace/Makefile b/arch/powerpc/kernel/trace/Makefile index 542aa7a8b2b4..af8527538fe4 100644 --- a/arch/powerpc/kernel/trace/Makefile +++ b/arch/powerpc/kernel/trace/Makefile @@ -14,10 +14,7 @@ obj64-$(CONFIG_FUNCTION_TRACER) += ftrace_mprofile.o else obj64-$(CONFIG_FUNCTION_TRACER) += ftrace_64_pg.o endif -obj-$(CONFIG_FUNCTION_TRACER) += ftrace_low.o -obj-$(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 4ee04aacf9f1..2a893e06e4f1 100644 --- a/arch/powerpc/kernel/trace/ftrace.c +++ b/arch/powerpc/kernel/trace/ftrace.c @@ -28,9 +28,6 @@ #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 @@ -48,12 +45,12 @@ ftrace_call_replace(unsigned long ip, unsigned long addr, int link) 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 +static inline int ftrace_modify_code(unsigned long ip, ppc_inst_t old, ppc_inst_t new) { ppc_inst_t replaced; @@ -78,10 +75,7 @@ ftrace_modify_code(unsigned long ip, ppc_inst_t old, ppc_inst_t new) } /* replace the text with the new text */ - if (patch_instruction((u32 *)ip, new)) - return -EPERM; - - return 0; + return patch_instruction((u32 *)ip, new); } /* @@ -89,28 +83,26 @@ ftrace_modify_code(unsigned long ip, ppc_inst_t old, ppc_inst_t new) */ static int test_24bit_addr(unsigned long ip, unsigned long addr) { - ppc_inst_t 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(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(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, 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; @@ -119,7 +111,6 @@ static unsigned long find_bl_target(unsigned long ip, ppc_inst_t op) } #ifdef CONFIG_MODULES -#ifdef CONFIG_PPC64 static int __ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr) @@ -159,25 +150,39 @@ __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 %s around bl _mcount\n", + ppc_inst_as_str(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 %s\n", PPC_INST_LD_TOC, ppc_inst_as_str(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) @@ -189,23 +194,10 @@ __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"); @@ -214,54 +206,16 @@ __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) { - ppc_inst_t op; - unsigned long ip = rec->ip; - unsigned long tramp, ptr; - - 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); - - /* Find where the trampoline jumps to */ - if (module_trampoline_target(mod, tramp, &ptr)) { - pr_err("Failed to get trampoline target\n"); - return -EFAULT; - } - - if (ptr != 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; - ppc_inst_t instr; /* * We have the compiler generated long_branch tramps at the end @@ -270,8 +224,7 @@ 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; @@ -301,23 +254,12 @@ static int setup_mcount_compiler_tramp(unsigned long tramp) int i; ppc_inst_t op; unsigned long ptr; - ppc_inst_t 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"); @@ -339,16 +281,10 @@ 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"); @@ -418,10 +354,12 @@ 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 @@ -444,53 +382,27 @@ 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, ppc_inst_t op0, ppc_inst_t 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, ppc_inst_t op0, ppc_inst_t 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_PPC64_ELF_ABI_V1)) + return ppc_inst_equal(op0, ppc_inst(PPC_RAW_BRANCH(8))) && + ppc_inst_equal(op1, ppc_inst(PPC_INST_LD_TOC)); + else + return ppc_inst_equal(op0, ppc_inst(PPC_RAW_NOP())); } -#endif static int __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) { ppc_inst_t op[2]; - ppc_inst_t instr; void *ip = (void *)rec->ip; unsigned long entry, ptr, tramp; struct module *mod = rec->arch.mod; @@ -499,7 +411,8 @@ __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_PPC64_ELF_ABI_V1) && + copy_inst_from_kernel_nofault(op + 1, ip + 4)) return -EFAULT; if (!expected_nop_sequence(ip, op[0], op[1])) { @@ -509,20 +422,15 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) } /* 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)) { @@ -539,12 +447,6 @@ __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; @@ -552,58 +454,11 @@ __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) -{ - int err; - ppc_inst_t op; - u32 *ip = (u32 *)rec->ip; - struct module *mod = rec->arch.mod; - unsigned long tramp; - - /* 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 */ -#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS - if (!mod->arch.tramp || !mod->arch.tramp_regs) { #else - if (!mod->arch.tramp) { -#endif - pr_err("No ftrace trampoline\n"); - return -EINVAL; - } - -#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS - if (rec->flags & FTRACE_FL_REGS) - tramp = mod->arch.tramp_regs; - else -#endif - tramp = mod->arch.tramp; - /* create the branch to the trampoline */ - err = create_branch(&op, ip, 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; - +static int __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) +{ return 0; } -#endif /* CONFIG_PPC64 */ #endif /* CONFIG_MODULES */ static int __ftrace_make_call_kernel(struct dyn_ftrace *rec, unsigned long addr) @@ -616,16 +471,12 @@ 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 */ @@ -668,10 +519,13 @@ 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 @@ -683,10 +537,6 @@ 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 @@ -770,12 +620,6 @@ __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; @@ -783,6 +627,11 @@ __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, @@ -807,9 +656,11 @@ 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. */ @@ -819,10 +670,6 @@ 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 @@ -836,15 +683,13 @@ int ftrace_update_ftrace_func(ftrace_func_t func) 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; } @@ -863,25 +708,39 @@ 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; @@ -896,13 +755,7 @@ 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 @@ -939,8 +792,8 @@ int ftrace_disable_ftrace_graph_caller(void) * 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; @@ -969,12 +822,18 @@ out: 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]); + 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] != '.') @@ -982,4 +841,4 @@ 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/traps.c b/arch/powerpc/kernel/traps.c index a08bb7cefdc5..3aaa50e5c72f 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -393,7 +393,7 @@ 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 +433,9 @@ 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) 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..0da287544054 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> diff --git a/arch/powerpc/kernel/vdso/Makefile b/arch/powerpc/kernel/vdso/Makefile index 954974287ee7..096b0bf1335f 100644 --- a/arch/powerpc/kernel/vdso/Makefile +++ b/arch/powerpc/kernel/vdso/Makefile @@ -48,6 +48,7 @@ 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 diff --git a/arch/powerpc/kernel/vdso/vdso32.lds.S b/arch/powerpc/kernel/vdso/vdso32.lds.S index 58e0099f70f4..e0d19d74455f 100644 --- a/arch/powerpc/kernel/vdso/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 { diff --git a/arch/powerpc/kernel/vdso/vdso64.lds.S b/arch/powerpc/kernel/vdso/vdso64.lds.S index 0288cad428b0..1a4a7bc4c815 100644 --- a/arch/powerpc/kernel/vdso/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 { diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c index bfc27496fe7e..7d28b9553654 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 |