diff options
Diffstat (limited to 'arch/powerpc/kernel')
-rw-r--r-- | arch/powerpc/kernel/cpu_setup_power.S | 2 | ||||
-rw-r--r-- | arch/powerpc/kernel/dma-iommu.c | 3 | ||||
-rw-r--r-- | arch/powerpc/kernel/dt_cpu_ftrs.c | 8 | ||||
-rw-r--r-- | arch/powerpc/kernel/eeh.c | 13 | ||||
-rw-r--r-- | arch/powerpc/kernel/exceptions-64s.S | 96 | ||||
-rw-r--r-- | arch/powerpc/kernel/head_8xx.S | 10 | ||||
-rw-r--r-- | arch/powerpc/kernel/iommu.c | 4 | ||||
-rw-r--r-- | arch/powerpc/kernel/kprobes.c | 3 | ||||
-rw-r--r-- | arch/powerpc/kernel/machine_kexec.c | 8 | ||||
-rw-r--r-- | arch/powerpc/kernel/module_64.c | 2 | ||||
-rw-r--r-- | arch/powerpc/kernel/prom.c | 21 | ||||
-rw-r--r-- | arch/powerpc/kernel/rtas.c | 153 | ||||
-rw-r--r-- | arch/powerpc/kernel/setup_64.c | 122 | ||||
-rw-r--r-- | arch/powerpc/kernel/smp.c | 6 | ||||
-rw-r--r-- | arch/powerpc/kernel/sysfs.c | 42 | ||||
-rw-r--r-- | arch/powerpc/kernel/tau_6xx.c | 82 | ||||
-rw-r--r-- | arch/powerpc/kernel/traps.c | 11 | ||||
-rw-r--r-- | arch/powerpc/kernel/vdso.c | 2 | ||||
-rw-r--r-- | arch/powerpc/kernel/vmlinux.lds.S | 14 |
19 files changed, 446 insertions, 156 deletions
diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S index 9daede99c131..f52e2c55a12b 100644 --- a/arch/powerpc/kernel/cpu_setup_power.S +++ b/arch/powerpc/kernel/cpu_setup_power.S @@ -189,7 +189,7 @@ __init_LPCR_ISA300: __init_FSCR: mfspr r3,SPRN_FSCR - ori r3,r3,FSCR_TAR|FSCR_DSCR|FSCR_EBB + ori r3,r3,FSCR_TAR|FSCR_EBB mtspr SPRN_FSCR,r3 blr diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c index 66f33e7f8d40..a39a1a0d844e 100644 --- a/arch/powerpc/kernel/dma-iommu.c +++ b/arch/powerpc/kernel/dma-iommu.c @@ -100,7 +100,8 @@ static u64 dma_iommu_get_required_mask(struct device *dev) if (!tbl) return 0; - mask = 1ULL < (fls_long(tbl->it_offset + tbl->it_size) - 1); + mask = 1ULL << (fls_long(tbl->it_offset + tbl->it_size) + + tbl->it_page_shift - 1); mask += mask - 1; return mask; diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index 7ed2b1b6643c..09134df01bfd 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -385,6 +385,14 @@ static int __init feat_enable_dscr(struct dt_cpu_feature *f) { u64 lpcr; + /* + * Linux relies on FSCR[DSCR] being clear, so that we can take the + * facility unavailable interrupt and track the task's usage of DSCR. + * See facility_unavailable_exception(). + * Clear the bit here so that feat_enable() doesn't set it. + */ + f->fscr_bit_nr = -1; + feat_enable(f); lpcr = mfspr(SPRN_LPCR); diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index d2ba7936d0d3..3f3f08d42266 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -365,14 +365,11 @@ static inline unsigned long eeh_token_to_phys(unsigned long token) pa = pte_pfn(*ptep); /* On radix we can do hugepage mappings for io, so handle that */ - if (hugepage_shift) { - pa <<= hugepage_shift; - pa |= token & ((1ul << hugepage_shift) - 1); - } else { - pa <<= PAGE_SHIFT; - pa |= token & (PAGE_SIZE - 1); - } + if (!hugepage_shift) + hugepage_shift = PAGE_SHIFT; + pa <<= PAGE_SHIFT; + pa |= token & ((1ul << hugepage_shift) - 1); return pa; } @@ -506,7 +503,7 @@ int eeh_dev_check_failure(struct eeh_dev *edev) rc = 1; if (pe->state & EEH_PE_ISOLATED) { pe->check_count++; - if (pe->check_count % EEH_MAX_FAILS == 0) { + if (pe->check_count == EEH_MAX_FAILS) { dn = pci_device_to_OF_node(dev); if (dn) location = of_get_property(dn, "ibm,loc-code", diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index cdc53fd90597..b313628966ad 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -484,7 +484,7 @@ EXC_COMMON_BEGIN(unrecover_mce) b 1b -EXC_REAL(data_access, 0x300, 0x80) +EXC_REAL_OOL(data_access, 0x300, 0x80) EXC_VIRT(data_access, 0x4300, 0x80, 0x300) TRAMP_KVM_SKIP(PACA_EXGEN, 0x300) @@ -516,13 +516,16 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) EXC_REAL_BEGIN(data_access_slb, 0x380, 0x80) SET_SCRATCH0(r13) EXCEPTION_PROLOG_0(PACA_EXSLB) + b tramp_data_access_slb +EXC_REAL_END(data_access_slb, 0x380, 0x80) + +TRAMP_REAL_BEGIN(tramp_data_access_slb) EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST_PR, 0x380) mr r12,r3 /* save r3 */ mfspr r3,SPRN_DAR mfspr r11,SPRN_SRR1 crset 4*cr6+eq BRANCH_TO_COMMON(r10, slb_miss_common) -EXC_REAL_END(data_access_slb, 0x380, 0x80) EXC_VIRT_BEGIN(data_access_slb, 0x4380, 0x80) SET_SCRATCH0(r13) @@ -537,7 +540,7 @@ EXC_VIRT_END(data_access_slb, 0x4380, 0x80) TRAMP_KVM_SKIP(PACA_EXSLB, 0x380) -EXC_REAL(instruction_access, 0x400, 0x80) +EXC_REAL_OOL(instruction_access, 0x400, 0x80) EXC_VIRT(instruction_access, 0x4400, 0x80, 0x400) TRAMP_KVM(PACA_EXGEN, 0x400) @@ -560,13 +563,16 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) EXC_REAL_BEGIN(instruction_access_slb, 0x480, 0x80) SET_SCRATCH0(r13) EXCEPTION_PROLOG_0(PACA_EXSLB) + b tramp_instruction_access_slb +EXC_REAL_END(instruction_access_slb, 0x480, 0x80) + +TRAMP_REAL_BEGIN(tramp_instruction_access_slb) EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST_PR, 0x480) mr r12,r3 /* save r3 */ mfspr r3,SPRN_SRR0 /* SRR0 is faulting address */ mfspr r11,SPRN_SRR1 crclr 4*cr6+eq BRANCH_TO_COMMON(r10, slb_miss_common) -EXC_REAL_END(instruction_access_slb, 0x480, 0x80) EXC_VIRT_BEGIN(instruction_access_slb, 0x4480, 0x80) SET_SCRATCH0(r13) @@ -830,13 +836,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_TM) EXC_REAL_OOL_MASKABLE(decrementer, 0x900, 0x80) -EXC_VIRT_MASKABLE(decrementer, 0x4900, 0x80, 0x900) +EXC_VIRT_OOL_MASKABLE(decrementer, 0x4900, 0x80, 0x900) TRAMP_KVM(PACA_EXGEN, 0x900) EXC_COMMON_ASYNC(decrementer_common, 0x900, timer_interrupt) -EXC_REAL_HV(hdecrementer, 0x980, 0x80) -EXC_VIRT_HV(hdecrementer, 0x4980, 0x80, 0x980) +EXC_REAL_OOL_HV(hdecrementer, 0x980, 0x80) +EXC_VIRT_OOL_HV(hdecrementer, 0x4980, 0x80, 0x980) TRAMP_KVM_HV(PACA_EXGEN, 0x980) EXC_COMMON(hdecrementer_common, 0x980, hdec_interrupt) @@ -1453,15 +1459,8 @@ TRAMP_REAL_BEGIN(stf_barrier_fallback) .endr blr -TRAMP_REAL_BEGIN(rfi_flush_fallback) - SET_SCRATCH0(r13); - GET_PACA(r13); - std r1,PACA_EXRFI+EX_R12(r13) - ld r1,PACAKSAVE(r13) - std r9,PACA_EXRFI+EX_R9(r13) - std r10,PACA_EXRFI+EX_R10(r13) - std r11,PACA_EXRFI+EX_R11(r13) - mfctr r9 +/* Clobbers r10, r11, ctr */ +.macro L1D_DISPLACEMENT_FLUSH ld r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13) ld r11,PACA_L1D_FLUSH_SIZE(r13) srdi r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */ @@ -1472,7 +1471,7 @@ TRAMP_REAL_BEGIN(rfi_flush_fallback) sync /* - * The load adresses are at staggered offsets within cachelines, + * The load addresses are at staggered offsets within cachelines, * which suits some pipelines better (on others it should not * hurt). */ @@ -1487,7 +1486,30 @@ TRAMP_REAL_BEGIN(rfi_flush_fallback) ld r11,(0x80 + 8)*7(r10) addi r10,r10,0x80*8 bdnz 1b +.endm + +TRAMP_REAL_BEGIN(entry_flush_fallback) + std r9,PACA_EXRFI+EX_R9(r13) + std r10,PACA_EXRFI+EX_R10(r13) + std r11,PACA_EXRFI+EX_R11(r13) + mfctr r9 + L1D_DISPLACEMENT_FLUSH + mtctr r9 + ld r9,PACA_EXRFI+EX_R9(r13) + ld r10,PACA_EXRFI+EX_R10(r13) + ld r11,PACA_EXRFI+EX_R11(r13) + blr +TRAMP_REAL_BEGIN(rfi_flush_fallback) + SET_SCRATCH0(r13); + GET_PACA(r13); + std r1,PACA_EXRFI+EX_R12(r13) + ld r1,PACAKSAVE(r13) + std r9,PACA_EXRFI+EX_R9(r13) + std r10,PACA_EXRFI+EX_R10(r13) + std r11,PACA_EXRFI+EX_R11(r13) + mfctr r9 + L1D_DISPLACEMENT_FLUSH mtctr r9 ld r9,PACA_EXRFI+EX_R9(r13) ld r10,PACA_EXRFI+EX_R10(r13) @@ -1505,32 +1527,7 @@ TRAMP_REAL_BEGIN(hrfi_flush_fallback) std r10,PACA_EXRFI+EX_R10(r13) std r11,PACA_EXRFI+EX_R11(r13) mfctr r9 - ld r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13) - ld r11,PACA_L1D_FLUSH_SIZE(r13) - srdi r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */ - mtctr r11 - DCBT_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */ - - /* order ld/st prior to dcbt stop all streams with flushing */ - sync - - /* - * The load adresses are at staggered offsets within cachelines, - * which suits some pipelines better (on others it should not - * hurt). - */ -1: - ld r11,(0x80 + 8)*0(r10) - ld r11,(0x80 + 8)*1(r10) - ld r11,(0x80 + 8)*2(r10) - ld r11,(0x80 + 8)*3(r10) - ld r11,(0x80 + 8)*4(r10) - ld r11,(0x80 + 8)*5(r10) - ld r11,(0x80 + 8)*6(r10) - ld r11,(0x80 + 8)*7(r10) - addi r10,r10,0x80*8 - bdnz 1b - + L1D_DISPLACEMENT_FLUSH mtctr r9 ld r9,PACA_EXRFI+EX_R9(r13) ld r10,PACA_EXRFI+EX_R10(r13) @@ -1539,6 +1536,19 @@ TRAMP_REAL_BEGIN(hrfi_flush_fallback) GET_SCRATCH0(r13); hrfid +USE_TEXT_SECTION() + +_GLOBAL(do_uaccess_flush) + UACCESS_FLUSH_FIXUP_SECTION + nop + nop + nop + blr + L1D_DISPLACEMENT_FLUSH + blr +_ASM_NOKPROBE_SYMBOL(do_uaccess_flush) +EXPORT_SYMBOL(do_uaccess_flush) + /* * Real mode exceptions actually use this too, but alternate * instruction code patches (which end up in the common .text area) diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index 2d0d89e2cb9a..95ecfec96b49 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -301,7 +301,7 @@ SystemCall: /* On the MPC8xx, this is a software emulation interrupt. It occurs * for all unimplemented and illegal instructions. */ - EXCEPTION(0x1000, SoftEmu, program_check_exception, EXC_XFER_STD) + EXCEPTION(0x1000, SoftEmu, emulation_assist_interrupt, EXC_XFER_STD) . = 0x1100 /* @@ -398,11 +398,9 @@ _ENTRY(ITLBMiss_cmp) #if defined (CONFIG_HUGETLB_PAGE) && defined (CONFIG_PPC_4K_PAGES) rlwimi r10, r11, 1, MI_SPS16K #endif -#ifdef CONFIG_SWAP - rlwinm r11, r10, 32-5, _PAGE_PRESENT + rlwinm r11, r10, 32-11, _PAGE_PRESENT and r11, r11, r10 rlwimi r10, r11, 0, _PAGE_PRESENT -#endif li r11, RPN_PATTERN /* The Linux PTE won't go exactly into the MMU TLB. * Software indicator bits 20-23 and 28 must be clear. @@ -528,11 +526,9 @@ _ENTRY(DTLBMiss_jmp) * r11 = ((r10 & PRESENT) & ((r10 & ACCESSED) >> 5)); * r10 = (r10 & ~PRESENT) | r11; */ -#ifdef CONFIG_SWAP - rlwinm r11, r10, 32-5, _PAGE_PRESENT + rlwinm r11, r10, 32-11, _PAGE_PRESENT and r11, r11, r10 rlwimi r10, r11, 0, _PAGE_PRESENT -#endif /* The Linux PTE won't go exactly into the MMU TLB. * Software indicator bits 22 and 28 must be clear. * Software indicator bits 24, 25, 26, and 27 must be diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 80b6caaa9b92..87af91937c8a 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -1055,7 +1055,7 @@ int iommu_take_ownership(struct iommu_table *tbl) spin_lock_irqsave(&tbl->large_pool.lock, flags); for (i = 0; i < tbl->nr_pools; i++) - spin_lock(&tbl->pools[i].lock); + spin_lock_nest_lock(&tbl->pools[i].lock, &tbl->large_pool.lock); if (tbl->it_offset == 0) clear_bit(0, tbl->it_map); @@ -1084,7 +1084,7 @@ void iommu_release_ownership(struct iommu_table *tbl) spin_lock_irqsave(&tbl->large_pool.lock, flags); for (i = 0; i < tbl->nr_pools; i++) - spin_lock(&tbl->pools[i].lock); + spin_lock_nest_lock(&tbl->pools[i].lock, &tbl->large_pool.lock); memset(tbl->it_map, 0, sz); diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index 07d3f3b40246..b8b62df102f1 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -279,7 +279,8 @@ int kprobe_handler(struct pt_regs *regs) if (user_mode(regs)) return 0; - if (!(regs->msr & MSR_IR) || !(regs->msr & MSR_DR)) + if (!IS_ENABLED(CONFIG_BOOKE) && + (!(regs->msr & MSR_IR) || !(regs->msr & MSR_DR))) return 0; /* diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c index 9dafd7af39b8..cb4d6cd949fc 100644 --- a/arch/powerpc/kernel/machine_kexec.c +++ b/arch/powerpc/kernel/machine_kexec.c @@ -113,11 +113,12 @@ void machine_kexec(struct kimage *image) void __init reserve_crashkernel(void) { - unsigned long long crash_size, crash_base; + unsigned long long crash_size, crash_base, total_mem_sz; int ret; + total_mem_sz = memory_limit ? memory_limit : memblock_phys_mem_size(); /* use common parsing */ - ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(), + ret = parse_crashkernel(boot_command_line, total_mem_sz, &crash_size, &crash_base); if (ret == 0 && crash_size > 0) { crashk_res.start = crash_base; @@ -176,6 +177,7 @@ void __init reserve_crashkernel(void) /* Crash kernel trumps memory limit */ if (memory_limit && memory_limit <= crashk_res.end) { memory_limit = crashk_res.end + 1; + total_mem_sz = memory_limit; printk("Adjusted memory limit for crashkernel, now 0x%llx\n", memory_limit); } @@ -184,7 +186,7 @@ void __init reserve_crashkernel(void) "for crashkernel (System RAM: %ldMB)\n", (unsigned long)(crash_size >> 20), (unsigned long)(crashk_res.start >> 20), - (unsigned long)(memblock_phys_mem_size() >> 20)); + (unsigned long)(total_mem_sz >> 20)); if (!memblock_is_region_memory(crashk_res.start, crash_size) || memblock_reserve(crashk_res.start, crash_size)) { diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 4d8f6291b766..bbf033bda55d 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -695,7 +695,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, /* * If found, replace it with: * addis r2, r12, (.TOC.-func)@ha - * addi r2, r12, (.TOC.-func)@l + * addi r2, r2, (.TOC.-func)@l */ ((uint32_t *)location)[0] = 0x3c4c0000 + PPC_HA(value); ((uint32_t *)location)[1] = 0x38420000 + PPC_LO(value); diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index d96b28415090..99409d0420d2 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -265,7 +265,7 @@ static struct feature_property { }; #if defined(CONFIG_44x) && defined(CONFIG_PPC_FPU) -static inline void identical_pvr_fixup(unsigned long node) +static __init void identical_pvr_fixup(unsigned long node) { unsigned int pvr; const char *model = of_get_flat_dt_prop(node, "model", NULL); @@ -658,6 +658,23 @@ static void __init early_reserve_mem(void) #endif } +#ifdef CONFIG_PPC64 +static void __init save_fscr_to_task(void) +{ + /* + * Ensure the init_task (pid 0, aka swapper) uses the value of FSCR we + * have configured via the device tree features or via __init_FSCR(). + * That value will then be propagated to pid 1 (init) and all future + * processes. + */ + if (early_cpu_has_feature(CPU_FTR_ARCH_207S)) + init_task.thread.fscr = mfspr(SPRN_FSCR); +} +#else +static inline void save_fscr_to_task(void) {}; +#endif + + void __init early_init_devtree(void *params) { phys_addr_t limit; @@ -743,6 +760,8 @@ void __init early_init_devtree(void *params) BUG(); } + save_fscr_to_task(); + #if defined(CONFIG_SMP) && defined(CONFIG_PPC64) /* We'll later wait for secondaries to check in; there are * NCPUS-1 non-boot CPUs :-) diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index a01f83ba739e..55b266d7afe1 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -1056,6 +1056,147 @@ struct pseries_errorlog *get_pseries_errorlog(struct rtas_error_log *log, return NULL; } +#ifdef CONFIG_PPC_RTAS_FILTER + +/* + * The sys_rtas syscall, as originally designed, allows root to pass + * arbitrary physical addresses to RTAS calls. A number of RTAS calls + * can be abused to write to arbitrary memory and do other things that + * are potentially harmful to system integrity, and thus should only + * be used inside the kernel and not exposed to userspace. + * + * All known legitimate users of the sys_rtas syscall will only ever + * pass addresses that fall within the RMO buffer, and use a known + * subset of RTAS calls. + * + * Accordingly, we filter RTAS requests to check that the call is + * permitted, and that provided pointers fall within the RMO buffer. + * The rtas_filters list contains an entry for each permitted call, + * with the indexes of the parameters which are expected to contain + * addresses and sizes of buffers allocated inside the RMO buffer. + */ +struct rtas_filter { + const char *name; + int token; + /* Indexes into the args buffer, -1 if not used */ + int buf_idx1; + int size_idx1; + int buf_idx2; + int size_idx2; + + int fixed_size; +}; + +static struct rtas_filter rtas_filters[] __ro_after_init = { + { "ibm,activate-firmware", -1, -1, -1, -1, -1 }, + { "ibm,configure-connector", -1, 0, -1, 1, -1, 4096 }, /* Special cased */ + { "display-character", -1, -1, -1, -1, -1 }, + { "ibm,display-message", -1, 0, -1, -1, -1 }, + { "ibm,errinjct", -1, 2, -1, -1, -1, 1024 }, + { "ibm,close-errinjct", -1, -1, -1, -1, -1 }, + { "ibm,open-errinjct", -1, -1, -1, -1, -1 }, + { "ibm,get-config-addr-info2", -1, -1, -1, -1, -1 }, + { "ibm,get-dynamic-sensor-state", -1, 1, -1, -1, -1 }, + { "ibm,get-indices", -1, 2, 3, -1, -1 }, + { "get-power-level", -1, -1, -1, -1, -1 }, + { "get-sensor-state", -1, -1, -1, -1, -1 }, + { "ibm,get-system-parameter", -1, 1, 2, -1, -1 }, + { "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,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 }, + { "ibm,set-eeh-option", -1, -1, -1, -1, -1 }, + { "set-indicator", -1, -1, -1, -1, -1 }, + { "set-power-level", -1, -1, -1, -1, -1 }, + { "set-time-for-power-on", -1, -1, -1, -1, -1 }, + { "ibm,set-system-parameter", -1, 1, -1, -1, -1 }, + { "set-time-of-day", -1, -1, -1, -1, -1 }, + { "ibm,suspend-me", -1, -1, -1, -1, -1 }, + { "ibm,update-nodes", -1, 0, -1, -1, -1, 4096 }, + { "ibm,update-properties", -1, 0, -1, -1, -1, 4096 }, + { "ibm,physical-attestation", -1, 0, 1, -1, -1 }, +}; + +static bool in_rmo_buf(u32 base, u32 end) +{ + return base >= rtas_rmo_buf && + base < (rtas_rmo_buf + RTAS_RMOBUF_MAX) && + base <= end && + end >= rtas_rmo_buf && + end < (rtas_rmo_buf + RTAS_RMOBUF_MAX); +} + +static bool block_rtas_call(int token, int nargs, + struct rtas_args *args) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(rtas_filters); i++) { + struct rtas_filter *f = &rtas_filters[i]; + u32 base, size, end; + + if (token != f->token) + continue; + + if (f->buf_idx1 != -1) { + base = be32_to_cpu(args->args[f->buf_idx1]); + if (f->size_idx1 != -1) + size = be32_to_cpu(args->args[f->size_idx1]); + else if (f->fixed_size) + size = f->fixed_size; + else + size = 1; + + end = base + size - 1; + if (!in_rmo_buf(base, end)) + goto err; + } + + if (f->buf_idx2 != -1) { + base = be32_to_cpu(args->args[f->buf_idx2]); + if (f->size_idx2 != -1) + size = be32_to_cpu(args->args[f->size_idx2]); + else if (f->fixed_size) + size = f->fixed_size; + else + size = 1; + end = base + size - 1; + + /* + * Special case for ibm,configure-connector where the + * address can be 0 + */ + if (!strcmp(f->name, "ibm,configure-connector") && + base == 0) + return false; + + if (!in_rmo_buf(base, end)) + goto err; + } + + return false; + } + +err: + pr_err_ratelimited("sys_rtas: RTAS call blocked - exploit attempt?\n"); + pr_err_ratelimited("sys_rtas: token=0x%x, nargs=%d (called by %s)\n", + token, nargs, current->comm); + return true; +} + +#else + +static bool block_rtas_call(int token, int nargs, + struct rtas_args *args) +{ + return false; +} + +#endif /* CONFIG_PPC_RTAS_FILTER */ + /* We assume to be passed big endian arguments */ asmlinkage int ppc_rtas(struct rtas_args __user *uargs) { @@ -1093,6 +1234,9 @@ asmlinkage int ppc_rtas(struct rtas_args __user *uargs) args.rets = &args.args[nargs]; memset(args.rets, 0, nret * sizeof(rtas_arg_t)); + if (block_rtas_call(token, nargs, &args)) + return -EINVAL; + /* Need to handle ibm,suspend_me call specially */ if (token == ibm_suspend_me_token) { @@ -1154,6 +1298,9 @@ void __init rtas_initialize(void) unsigned long rtas_region = RTAS_INSTANTIATE_MAX; u32 base, size, entry; int no_base, no_size, no_entry; +#ifdef CONFIG_PPC_RTAS_FILTER + int i; +#endif /* Get RTAS dev node and fill up our "rtas" structure with infos * about it. @@ -1189,6 +1336,12 @@ void __init rtas_initialize(void) #ifdef CONFIG_RTAS_ERROR_LOGGING rtas_last_error_token = rtas_token("rtas-last-error"); #endif + +#ifdef CONFIG_PPC_RTAS_FILTER + for (i = 0; i < ARRAY_SIZE(rtas_filters); i++) { + rtas_filters[i].token = rtas_token(rtas_filters[i].name); + } +#endif } int __init early_init_dt_scan_rtas(unsigned long node, diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index a1e336901cc8..a1eec409695e 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -792,7 +792,13 @@ early_initcall(disable_hardlockup_detector); static enum l1d_flush_type enabled_flush_types; static void *l1d_flush_fallback_area; static bool no_rfi_flush; +static bool no_entry_flush; +static bool no_uaccess_flush; bool rfi_flush; +bool entry_flush; +bool uaccess_flush; +DEFINE_STATIC_KEY_FALSE(uaccess_flush_key); +EXPORT_SYMBOL(uaccess_flush_key); static int __init handle_no_rfi_flush(char *p) { @@ -802,6 +808,22 @@ static int __init handle_no_rfi_flush(char *p) } early_param("no_rfi_flush", handle_no_rfi_flush); +static int __init handle_no_entry_flush(char *p) +{ + pr_info("entry-flush: disabled on command line."); + no_entry_flush = true; + return 0; +} +early_param("no_entry_flush", handle_no_entry_flush); + +static int __init handle_no_uaccess_flush(char *p) +{ + pr_info("uaccess-flush: disabled on command line."); + no_uaccess_flush = true; + return 0; +} +early_param("no_uaccess_flush", handle_no_uaccess_flush); + /* * The RFI flush is not KPTI, but because users will see doco that says to use * nopti we hijack that option here to also disable the RFI flush. @@ -833,6 +855,32 @@ void rfi_flush_enable(bool enable) rfi_flush = enable; } +void entry_flush_enable(bool enable) +{ + if (enable) { + do_entry_flush_fixups(enabled_flush_types); + on_each_cpu(do_nothing, NULL, 1); + } else { + do_entry_flush_fixups(L1D_FLUSH_NONE); + } + + entry_flush = enable; +} + +void uaccess_flush_enable(bool enable) +{ + if (enable) { + do_uaccess_flush_fixups(enabled_flush_types); + static_branch_enable(&uaccess_flush_key); + on_each_cpu(do_nothing, NULL, 1); + } else { + static_branch_disable(&uaccess_flush_key); + do_uaccess_flush_fixups(L1D_FLUSH_NONE); + } + + uaccess_flush = enable; +} + static void __ref init_fallback_flush(void) { u64 l1d_size, limit; @@ -874,10 +922,28 @@ void setup_rfi_flush(enum l1d_flush_type types, bool enable) enabled_flush_types = types; - if (!no_rfi_flush && !cpu_mitigations_off()) + if (!cpu_mitigations_off() && !no_rfi_flush) rfi_flush_enable(enable); } +void setup_entry_flush(bool enable) +{ + if (cpu_mitigations_off()) + return; + + if (!no_entry_flush) + entry_flush_enable(enable); +} + +void setup_uaccess_flush(bool enable) +{ + if (cpu_mitigations_off()) + return; + + if (!no_uaccess_flush) + uaccess_flush_enable(enable); +} + #ifdef CONFIG_DEBUG_FS static int rfi_flush_set(void *data, u64 val) { @@ -905,9 +971,63 @@ static int rfi_flush_get(void *data, u64 *val) DEFINE_SIMPLE_ATTRIBUTE(fops_rfi_flush, rfi_flush_get, rfi_flush_set, "%llu\n"); +static int entry_flush_set(void *data, u64 val) +{ + bool enable; + + if (val == 1) + enable = true; + else if (val == 0) + enable = false; + else + return -EINVAL; + + /* Only do anything if we're changing state */ + if (enable != entry_flush) + entry_flush_enable(enable); + + return 0; +} + +static int entry_flush_get(void *data, u64 *val) +{ + *val = entry_flush ? 1 : 0; + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(fops_entry_flush, entry_flush_get, entry_flush_set, "%llu\n"); + +static int uaccess_flush_set(void *data, u64 val) +{ + bool enable; + + if (val == 1) + enable = true; + else if (val == 0) + enable = false; + else + return -EINVAL; + + /* Only do anything if we're changing state */ + if (enable != uaccess_flush) + uaccess_flush_enable(enable); + + return 0; +} + +static int uaccess_flush_get(void *data, u64 *val) +{ + *val = uaccess_flush ? 1 : 0; + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(fops_uaccess_flush, uaccess_flush_get, uaccess_flush_set, "%llu\n"); + static __init int rfi_flush_debugfs_init(void) { debugfs_create_file("rfi_flush", 0600, powerpc_debugfs_root, NULL, &fops_rfi_flush); + debugfs_create_file("entry_flush", 0600, powerpc_debugfs_root, NULL, &fops_entry_flush); + debugfs_create_file("uaccess_flush", 0600, powerpc_debugfs_root, NULL, &fops_uaccess_flush); return 0; } device_initcall(rfi_flush_debugfs_init); diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index e0a4c1f82e25..7c7aa7c98ba3 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -985,6 +985,9 @@ void start_secondary(void *unused) vdso_getcpu_init(); #endif + set_numa_node(numa_cpu_lookup_table[cpu]); + set_numa_mem(local_memory_node(numa_cpu_lookup_table[cpu])); + /* Update topology CPU masks */ add_cpu_to_masks(cpu); @@ -995,9 +998,6 @@ void start_secondary(void *unused) if (!cpumask_equal(cpu_l2_cache_mask(cpu), cpu_sibling_mask(cpu))) shared_caches = true; - set_numa_node(numa_cpu_lookup_table[cpu]); - set_numa_mem(local_memory_node(numa_cpu_lookup_table[cpu])); - smp_wmb(); notify_cpu_starting(cpu); set_cpu_online(cpu, true); diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index 4437c70c7c2b..952fbc2d4abc 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -28,29 +28,27 @@ static DEFINE_PER_CPU(struct cpu, cpu_devices); -/* - * SMT snooze delay stuff, 64-bit only for now - */ - #ifdef CONFIG_PPC64 -/* Time in microseconds we delay before sleeping in the idle loop */ -static DEFINE_PER_CPU(long, smt_snooze_delay) = { 100 }; +/* + * Snooze delay has not been hooked up since 3fa8cad82b94 ("powerpc/pseries/cpuidle: + * smt-snooze-delay cleanup.") and has been broken even longer. As was foretold in + * 2014: + * + * "ppc64_util currently utilises it. Once we fix ppc64_util, propose to clean + * up the kernel code." + * + * powerpc-utils stopped using it as of 1.3.8. At some point in the future this + * code should be removed. + */ static ssize_t store_smt_snooze_delay(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - struct cpu *cpu = container_of(dev, struct cpu, dev); - ssize_t ret; - long snooze; - - ret = sscanf(buf, "%ld", &snooze); - if (ret != 1) - return -EINVAL; - - per_cpu(smt_snooze_delay, cpu->dev.id) = snooze; + pr_warn_once("%s (%d) stored to unsupported smt_snooze_delay, which has no effect.\n", + current->comm, current->pid); return count; } @@ -58,9 +56,9 @@ static ssize_t show_smt_snooze_delay(struct device *dev, struct device_attribute *attr, char *buf) { - struct cpu *cpu = container_of(dev, struct cpu, dev); - - return sprintf(buf, "%ld\n", per_cpu(smt_snooze_delay, cpu->dev.id)); + pr_warn_once("%s (%d) read from unsupported smt_snooze_delay\n", + current->comm, current->pid); + return sprintf(buf, "100\n"); } static DEVICE_ATTR(smt_snooze_delay, 0644, show_smt_snooze_delay, @@ -68,16 +66,10 @@ static DEVICE_ATTR(smt_snooze_delay, 0644, show_smt_snooze_delay, static int __init setup_smt_snooze_delay(char *str) { - unsigned int cpu; - long snooze; - if (!cpu_has_feature(CPU_FTR_SMT)) return 1; - snooze = simple_strtol(str, NULL, 10); - for_each_possible_cpu(cpu) - per_cpu(smt_snooze_delay, cpu) = snooze; - + pr_warn("smt-snooze-delay command line option has no effect\n"); return 1; } __setup("smt-snooze-delay=", setup_smt_snooze_delay); diff --git a/arch/powerpc/kernel/tau_6xx.c b/arch/powerpc/kernel/tau_6xx.c index a3374e8a258c..2615cd66dad8 100644 --- a/arch/powerpc/kernel/tau_6xx.c +++ b/arch/powerpc/kernel/tau_6xx.c @@ -38,8 +38,6 @@ static struct tau_temp struct timer_list tau_timer; -#undef DEBUG - /* TODO: put these in a /proc interface, with some sanity checks, and maybe * dynamic adjustment to minimize # of interrupts */ /* configurable values for step size and how much to expand the window when @@ -72,47 +70,33 @@ void set_thresholds(unsigned long cpu) void TAUupdate(int cpu) { - unsigned thrm; - -#ifdef DEBUG - printk("TAUupdate "); -#endif + u32 thrm; + u32 bits = THRM1_TIV | THRM1_TIN | THRM1_V; /* if both thresholds are crossed, the step_sizes cancel out * and the window winds up getting expanded twice. */ - if((thrm = mfspr(SPRN_THRM1)) & THRM1_TIV){ /* is valid? */ - if(thrm & THRM1_TIN){ /* crossed low threshold */ - if (tau[cpu].low >= step_size){ - tau[cpu].low -= step_size; - tau[cpu].high -= (step_size - window_expand); - } - tau[cpu].grew = 1; -#ifdef DEBUG - printk("low threshold crossed "); -#endif + thrm = mfspr(SPRN_THRM1); + if ((thrm & bits) == bits) { + mtspr(SPRN_THRM1, 0); + + if (tau[cpu].low >= step_size) { + tau[cpu].low -= step_size; + tau[cpu].high -= (step_size - window_expand); } + tau[cpu].grew = 1; + pr_debug("%s: low threshold crossed\n", __func__); } - if((thrm = mfspr(SPRN_THRM2)) & THRM1_TIV){ /* is valid? */ - if(thrm & THRM1_TIN){ /* crossed high threshold */ - if (tau[cpu].high <= 127-step_size){ - tau[cpu].low += (step_size - window_expand); - tau[cpu].high += step_size; - } - tau[cpu].grew = 1; -#ifdef DEBUG - printk("high threshold crossed "); -#endif + thrm = mfspr(SPRN_THRM2); + if ((thrm & bits) == bits) { + mtspr(SPRN_THRM2, 0); + + if (tau[cpu].high <= 127 - step_size) { + tau[cpu].low += (step_size - window_expand); + tau[cpu].high += step_size; } + tau[cpu].grew = 1; + pr_debug("%s: high threshold crossed\n", __func__); } - -#ifdef DEBUG - printk("grew = %d\n", tau[cpu].grew); -#endif - -#ifndef CONFIG_TAU_INT /* tau_timeout will do this if not using interrupts */ - set_thresholds(cpu); -#endif - } #ifdef CONFIG_TAU_INT @@ -137,18 +121,18 @@ void TAUException(struct pt_regs * regs) static void tau_timeout(void * info) { int cpu; - unsigned long flags; int size; int shrink; - /* disabling interrupts *should* be okay */ - local_irq_save(flags); cpu = smp_processor_id(); #ifndef CONFIG_TAU_INT TAUupdate(cpu); #endif + /* Stop thermal sensor comparisons and interrupts */ + mtspr(SPRN_THRM3, 0); + size = tau[cpu].high - tau[cpu].low; if (size > min_window && ! tau[cpu].grew) { /* do an exponential shrink of half the amount currently over size */ @@ -170,22 +154,12 @@ static void tau_timeout(void * info) set_thresholds(cpu); - /* - * Do the enable every time, since otherwise a bunch of (relatively) - * complex sleep code needs to be added. One mtspr every time - * tau_timeout is called is probably not a big deal. - * - * Enable thermal sensor and set up sample interval timer - * need 20 us to do the compare.. until a nice 'cpu_speed' function - * call is implemented, just assume a 500 mhz clock. It doesn't really - * matter if we take too long for a compare since it's all interrupt - * driven anyway. - * - * use a extra long time.. (60 us @ 500 mhz) + /* Restart thermal sensor comparisons and interrupts. + * The "PowerPC 740 and PowerPC 750 Microprocessor Datasheet" + * recommends that "the maximum value be set in THRM3 under all + * conditions." */ - mtspr(SPRN_THRM3, THRM3_SITV(500*60) | THRM3_E); - - local_irq_restore(flags); + mtspr(SPRN_THRM3, THRM3_SITV(0x1fff) | THRM3_E); } static void tau_timeout_smp(unsigned long unused) diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 3c9457420aee..05c1aabad01c 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -357,11 +357,14 @@ out: #ifdef CONFIG_PPC_BOOK3S_64 BUG_ON(get_paca()->in_nmi == 0); if (get_paca()->in_nmi > 1) - nmi_panic(regs, "Unrecoverable nested System Reset"); + die("Unrecoverable nested System Reset", regs, SIGABRT); #endif /* Must die if the interrupt is not recoverable */ - if (!(regs->msr & MSR_RI)) - nmi_panic(regs, "Unrecoverable System Reset"); + if (!(regs->msr & MSR_RI)) { + /* For the reason explained in die_mce, nmi_exit before die */ + nmi_exit(); + die("Unrecoverable System Reset", regs, SIGABRT); + } if (!nested) nmi_exit(); @@ -701,7 +704,7 @@ void machine_check_exception(struct pt_regs *regs) /* Must die if the interrupt is not recoverable */ if (!(regs->msr & MSR_RI)) - nmi_panic(regs, "Unrecoverable Machine check"); + die("Unrecoverable Machine check", regs, SIGBUS); return; diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index 22b01a3962f0..3edaee28b638 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -704,7 +704,7 @@ int vdso_getcpu_init(void) node = cpu_to_node(cpu); WARN_ON_ONCE(node > 0xffff); - val = (cpu & 0xfff) | ((node & 0xffff) << 16); + val = (cpu & 0xffff) | ((node & 0xffff) << 16); mtspr(SPRN_SPRG_VDSO_WRITE, val); get_paca()->sprg_vdso = val; diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index e4da937d6cf9..efb9a6982561 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -141,6 +141,20 @@ SECTIONS } . = ALIGN(8); + __uaccess_flush_fixup : AT(ADDR(__uaccess_flush_fixup) - LOAD_OFFSET) { + __start___uaccess_flush_fixup = .; + *(__uaccess_flush_fixup) + __stop___uaccess_flush_fixup = .; + } + + . = ALIGN(8); + __entry_flush_fixup : AT(ADDR(__entry_flush_fixup) - LOAD_OFFSET) { + __start___entry_flush_fixup = .; + *(__entry_flush_fixup) + __stop___entry_flush_fixup = .; + } + + . = ALIGN(8); __stf_exit_barrier_fixup : AT(ADDR(__stf_exit_barrier_fixup) - LOAD_OFFSET) { __start___stf_exit_barrier_fixup = .; *(__stf_exit_barrier_fixup) |