diff options
Diffstat (limited to 'arch/powerpc/kernel')
30 files changed, 467 insertions, 361 deletions
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 9bf2be123093..2919433be355 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -68,7 +68,7 @@ CFLAGS_REMOVE_syscall.o = -fstack-protector -fstack-protector-strong CFLAGS_syscall.o += -fno-stack-protector #endif -obj-y := cputable.o syscalls.o \ +obj-y := cputable.o syscalls.o switch.o \ irq.o align.o signal_$(BITS).o pmc.o vdso.o \ process.o systbl.o idle.o \ signal.o sysfs.o cacheinfo.o time.o \ @@ -165,9 +165,6 @@ endif obj64-$(CONFIG_PPC_TRANSACTIONAL_MEM) += tm.o -obj-$(CONFIG_PPC64) += $(obj64-y) -obj-$(CONFIG_PPC32) += $(obj32-y) - ifneq ($(CONFIG_XMON)$(CONFIG_KEXEC_CORE)(CONFIG_PPC_BOOK3S),) obj-y += ppc_save_regs.o endif @@ -209,10 +206,13 @@ CFLAGS_paca.o += -fno-stack-protector obj-$(CONFIG_PPC_FPU) += fpu.o obj-$(CONFIG_ALTIVEC) += vector.o -obj-$(CONFIG_PPC64) += entry_64.o -obj-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE) += prom_init.o -extra-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE) += prom_init_check +obj-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE) += prom_init.o +obj64-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE) += prom_entry_64.o +extra-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE) += prom_init_check + +obj-$(CONFIG_PPC64) += $(obj64-y) +obj-$(CONFIG_PPC32) += $(obj32-y) quiet_cmd_prom_init_check = PROMCHK $@ cmd_prom_init_check = $(CONFIG_SHELL) $< "$(NM)" $(obj)/prom_init.o; touch $@ diff --git a/arch/powerpc/kernel/cpu_setup_power.c b/arch/powerpc/kernel/cpu_setup_power.c index 097c033668f0..98bd4e6c1770 100644 --- a/arch/powerpc/kernel/cpu_setup_power.c +++ b/arch/powerpc/kernel/cpu_setup_power.c @@ -126,6 +126,12 @@ static void init_PMU_ISA31(void) mtspr(SPRN_MMCR0, MMCR0_FC | MMCR0_PMCCEXT); } +static void init_DEXCR(void) +{ + mtspr(SPRN_DEXCR, DEXCR_INIT); + mtspr(SPRN_HASHKEYR, 0); +} + /* * Note that we can be called twice of pseudo-PVRs. * The parameter offset is not used. @@ -241,6 +247,7 @@ void __setup_cpu_power10(unsigned long offset, struct cpu_spec *t) init_FSCR_power10(); init_PMU(); init_PMU_ISA31(); + init_DEXCR(); if (!init_hvmode_206(t)) return; @@ -263,6 +270,7 @@ void __restore_cpu_power10(void) init_FSCR_power10(); init_PMU(); init_PMU_ISA31(); + init_DEXCR(); msr = mfmsr(); if (!(msr & MSR_HV)) diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index d2873d17d2b1..e0ce81279624 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -671,9 +671,8 @@ static void eeh_bridge_check_link(struct eeh_dev *edev) eeh_ops->write_config(edev, cap + PCI_EXP_LNKCTL, 2, val); /* Check link */ - eeh_ops->read_config(edev, cap + PCI_EXP_LNKCAP, 4, &val); - if (!(val & PCI_EXP_LNKCAP_DLLLARC)) { - eeh_edev_dbg(edev, "No link reporting capability (0x%08x) \n", val); + if (!edev->pdev->link_active_reporting) { + eeh_edev_dbg(edev, "No link reporting capability\n"); msleep(1000); return; } diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 47f0dd9a45ad..fe27d41f9a3d 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -211,64 +211,6 @@ start_kernel_thread: 100: trap EMIT_BUG_ENTRY 100b,__FILE__,__LINE__,0 - -/* - * This routine switches between two different tasks. The process - * state of one is saved on its kernel stack. Then the state - * of the other is restored from its kernel stack. The memory - * management hardware is updated to the second process's state. - * Finally, we can return to the second process. - * On entry, r3 points to the THREAD for the current task, r4 - * points to the THREAD for the new task. - * - * This routine is always called with interrupts disabled. - * - * Note: there are two ways to get to the "going out" portion - * of this code; either by coming in via the entry (_switch) - * or via "fork" which must set up an environment equivalent - * to the "_switch" path. If you change this , you'll have to - * change the fork code also. - * - * The code which creates the new task context is in 'copy_thread' - * in arch/ppc/kernel/process.c - */ -_GLOBAL(_switch) - stwu r1,-SWITCH_FRAME_SIZE(r1) - mflr r0 - stw r0,SWITCH_FRAME_SIZE+4(r1) - /* r3-r12 are caller saved -- Cort */ - SAVE_NVGPRS(r1) - stw r0,_NIP(r1) /* Return to switch caller */ - mfcr r10 - stw r10,_CCR(r1) - stw r1,KSP(r3) /* Set old stack pointer */ - -#ifdef CONFIG_SMP - /* We need a sync somewhere here to make sure that if the - * previous task gets rescheduled on another CPU, it sees all - * stores it has performed on this one. - */ - sync -#endif /* CONFIG_SMP */ - - tophys(r0,r4) - mtspr SPRN_SPRG_THREAD,r0 /* Update current THREAD phys addr */ - lwz r1,KSP(r4) /* Load new stack pointer */ - - /* save the old current 'last' for return value */ - mr r3,r2 - addi r2,r4,-THREAD /* Update current */ - - lwz r0,_CCR(r1) - mtcrf 0xFF,r0 - /* r3-r12 are destroyed -- Cort */ - REST_NVGPRS(r1) - - lwz r4,_NIP(r1) /* Return to _switch caller in new task */ - mtlr r4 - addi r1,r1,SWITCH_FRAME_SIZE - blr - .globl fast_exception_return fast_exception_return: #if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE)) diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index 3f86091e68b3..7ab4c8c0f1ab 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -5,6 +5,7 @@ * Copyright (C) 2007 Ben. Herrenschmidt (benh@kernel.crashing.org), IBM Corp. */ +#include <linux/linkage.h> #include <linux/threads.h> #include <asm/reg.h> #include <asm/page.h> @@ -66,7 +67,7 @@ #define SPECIAL_EXC_LOAD(reg, name) \ ld reg, (SPECIAL_EXC_##name * 8 + SPECIAL_EXC_FRAME_OFFS)(r1) -special_reg_save: +SYM_CODE_START_LOCAL(special_reg_save) /* * We only need (or have stack space) to save this stuff if * we interrupted the kernel. @@ -131,8 +132,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV) SPECIAL_EXC_STORE(r10,CSRR1) blr +SYM_CODE_END(special_reg_save) -ret_from_level_except: +SYM_CODE_START_LOCAL(ret_from_level_except) ld r3,_MSR(r1) andi. r3,r3,MSR_PR beq 1f @@ -206,6 +208,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV) mtxer r11 blr +SYM_CODE_END(ret_from_level_except) .macro ret_from_level srr0 srr1 paca_ex scratch bl ret_from_level_except @@ -232,13 +235,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV) mfspr r13,\scratch .endm -ret_from_crit_except: +SYM_CODE_START_LOCAL(ret_from_crit_except) ret_from_level SPRN_CSRR0 SPRN_CSRR1 PACA_EXCRIT SPRN_SPRG_CRIT_SCRATCH rfci +SYM_CODE_END(ret_from_crit_except) -ret_from_mc_except: +SYM_CODE_START_LOCAL(ret_from_mc_except) ret_from_level SPRN_MCSRR0 SPRN_MCSRR1 PACA_EXMC SPRN_SPRG_MC_SCRATCH rfmci +SYM_CODE_END(ret_from_mc_except) /* Exception prolog code for all exceptions */ #define EXCEPTION_PROLOG(n, intnum, type, addition) \ @@ -978,20 +983,22 @@ masked_interrupt_book3e_0x2c0: * r14 and r15 containing the fault address and error code, with the * original values stashed away in the PACA */ -storage_fault_common: +SYM_CODE_START_LOCAL(storage_fault_common) addi r3,r1,STACK_INT_FRAME_REGS bl do_page_fault b interrupt_return +SYM_CODE_END(storage_fault_common) /* * Alignment exception doesn't fit entirely in the 0x100 bytes so it * continues here. */ -alignment_more: +SYM_CODE_START_LOCAL(alignment_more) addi r3,r1,STACK_INT_FRAME_REGS bl alignment_exception REST_NVGPRS(r1) b interrupt_return +SYM_CODE_END(alignment_more) /* * Trampolines used when spotting a bad kernel stack pointer in @@ -1030,8 +1037,7 @@ BAD_STACK_TRAMPOLINE(0xe00) BAD_STACK_TRAMPOLINE(0xf00) BAD_STACK_TRAMPOLINE(0xf20) - .globl bad_stack_book3e -bad_stack_book3e: +_GLOBAL(bad_stack_book3e) /* XXX: Needs to make SPRN_SPRG_GEN depend on exception type */ mfspr r10,SPRN_SRR0; /* read SRR0 before touching stack */ ld r1,PACAEMERGSP(r13) @@ -1285,8 +1291,7 @@ have_hes: * ever takes any parameters, the SCOM code must also be updated to * provide them. */ - .globl a2_tlbinit_code_start -a2_tlbinit_code_start: +_GLOBAL(a2_tlbinit_code_start) ori r11,r3,MAS0_WQ_ALLWAYS oris r11,r11,MAS0_ESEL(3)@h /* Use way 3: workaround A2 erratum 376 */ @@ -1479,8 +1484,7 @@ _GLOBAL(book3e_secondary_thread_init) mflr r28 b 3b - .globl init_core_book3e -init_core_book3e: +_GLOBAL(init_core_book3e) /* Establish the interrupt vector base */ tovirt(r2,r2) LOAD_REG_ADDR(r3, interrupt_base_book3e) @@ -1488,7 +1492,7 @@ init_core_book3e: sync blr -init_thread_book3e: +SYM_CODE_START_LOCAL(init_thread_book3e) lis r3,(SPRN_EPCR_ICM | SPRN_EPCR_GICM)@h mtspr SPRN_EPCR,r3 @@ -1502,6 +1506,7 @@ init_thread_book3e: mtspr SPRN_TSR,r3 blr +SYM_CODE_END(init_thread_book3e) _GLOBAL(__setup_base_ivors) SET_IVOR(0, 0x020) /* Critical Input */ diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index ea0a073abd96..3ff2da7b120b 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -654,6 +654,7 @@ int __init fadump_reserve_mem(void) return ret; error_out: fw_dump.fadump_enabled = 0; + fw_dump.reserve_dump_area_size = 0; return 0; } diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index f132d8704263..6440b1bb332a 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -375,8 +375,7 @@ _GLOBAL(generic_secondary_smp_init) beq 20f /* start the specified thread */ - LOAD_REG_ADDR(r5, fsl_secondary_thread_init) - ld r4, 0(r5) + LOAD_REG_ADDR(r5, DOTSYM(fsl_secondary_thread_init)) bl book3e_start_thread /* stop the current thread */ diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c index e34c72285b4e..c4f6d3c69ba9 100644 --- a/arch/powerpc/kernel/interrupt.c +++ b/arch/powerpc/kernel/interrupt.c @@ -125,7 +125,7 @@ static notrace void check_return_regs_valid(struct pt_regs *regs) case 0x1600: case 0x1800: validp = &local_paca->hsrr_valid; - if (!*validp) + if (!READ_ONCE(*validp)) return; srr0 = mfspr(SPRN_HSRR0); @@ -135,7 +135,7 @@ static notrace void check_return_regs_valid(struct pt_regs *regs) break; default: validp = &local_paca->srr_valid; - if (!*validp) + if (!READ_ONCE(*validp)) return; srr0 = mfspr(SPRN_SRR0); @@ -161,19 +161,17 @@ static notrace void check_return_regs_valid(struct pt_regs *regs) * such things will get caught most of the time, statistically * enough to be able to get a warning out. */ - barrier(); - - if (!*validp) + if (!READ_ONCE(*validp)) return; - if (!warned) { - warned = true; + if (!data_race(warned)) { + data_race(warned = true); printk("%sSRR0 was: %lx should be: %lx\n", h, srr0, regs->nip); printk("%sSRR1 was: %lx should be: %lx\n", h, srr1, regs->msr); show_regs(regs); } - *validp = 0; /* fixup */ + WRITE_ONCE(*validp, 0); /* fixup */ #endif } @@ -368,7 +366,6 @@ void preempt_schedule_irq(void); notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs) { - unsigned long flags; unsigned long ret = 0; unsigned long kuap; bool stack_store = read_thread_flags() & _TIF_EMULATE_STACK_STORE; @@ -392,7 +389,7 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs) kuap = kuap_get_and_assert_locked(); - local_irq_save(flags); + local_irq_disable(); if (!arch_irq_disabled_regs(regs)) { /* Returning to a kernel context with local irqs enabled. */ diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 67f0b01e6ff5..14251bc5219e 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -172,17 +172,28 @@ static int fail_iommu_bus_notify(struct notifier_block *nb, return 0; } -static struct notifier_block fail_iommu_bus_notifier = { +/* + * PCI and VIO buses need separate notifier_block structs, since they're linked + * list nodes. Sharing a notifier_block would mean that any notifiers later + * registered for PCI buses would also get called by VIO buses and vice versa. + */ +static struct notifier_block fail_iommu_pci_bus_notifier = { .notifier_call = fail_iommu_bus_notify }; +#ifdef CONFIG_IBMVIO +static struct notifier_block fail_iommu_vio_bus_notifier = { + .notifier_call = fail_iommu_bus_notify +}; +#endif + static int __init fail_iommu_setup(void) { #ifdef CONFIG_PCI - bus_register_notifier(&pci_bus_type, &fail_iommu_bus_notifier); + bus_register_notifier(&pci_bus_type, &fail_iommu_pci_bus_notifier); #endif #ifdef CONFIG_IBMVIO - bus_register_notifier(&vio_bus_type, &fail_iommu_bus_notifier); + bus_register_notifier(&vio_bus_type, &fail_iommu_vio_bus_notifier); #endif return 0; @@ -1090,6 +1101,7 @@ void iommu_tce_kill(struct iommu_table *tbl, } EXPORT_SYMBOL_GPL(iommu_tce_kill); +#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) static int iommu_take_ownership(struct iommu_table *tbl) { unsigned long flags, i, sz = (tbl->it_size + 7) >> 3; @@ -1140,6 +1152,7 @@ static void iommu_release_ownership(struct iommu_table *tbl) spin_unlock(&tbl->pools[i].lock); spin_unlock_irqrestore(&tbl->large_pool.lock, flags); } +#endif int iommu_add_device(struct iommu_table_group *table_group, struct device *dev) { @@ -1171,6 +1184,7 @@ int iommu_add_device(struct iommu_table_group *table_group, struct device *dev) } EXPORT_SYMBOL_GPL(iommu_add_device); +#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) /* * A simple iommu_table_group_ops which only allows reusing the existing * iommu_table. This handles VFIO for POWER7 or the nested KVM. @@ -1398,5 +1412,6 @@ static int __init spapr_tce_setup_phb_iommus_initcall(void) return 0; } postcore_initcall_sync(spapr_tce_setup_phb_iommus_initcall); +#endif #endif /* CONFIG_IOMMU_API */ diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c index c9ad12461d44..6ee65741dbd5 100644 --- a/arch/powerpc/kernel/legacy_serial.c +++ b/arch/powerpc/kernel/legacy_serial.c @@ -508,12 +508,16 @@ static void __init fixup_port_irq(int index, port->irq = virq; -#ifdef CONFIG_SERIAL_8250_FSL - if (of_device_is_compatible(np, "fsl,ns16550")) { - port->handle_irq = fsl8250_handle_irq; - port->has_sysrq = IS_ENABLED(CONFIG_SERIAL_8250_CONSOLE); + if (IS_ENABLED(CONFIG_SERIAL_8250) && + of_device_is_compatible(np, "fsl,ns16550")) { + if (IS_REACHABLE(CONFIG_SERIAL_8250_FSL)) { + port->handle_irq = fsl8250_handle_irq; + port->has_sysrq = IS_ENABLED(CONFIG_SERIAL_8250_CONSOLE); + } else { + pr_warn_once("Not activating Freescale specific workaround for device %pOFP\n", + np); + } } -#endif } static void __init fixup_port_pio(int index, diff --git a/arch/powerpc/kernel/ppc_save_regs.S b/arch/powerpc/kernel/ppc_save_regs.S index 49813f982468..a9b9c32d0c1f 100644 --- a/arch/powerpc/kernel/ppc_save_regs.S +++ b/arch/powerpc/kernel/ppc_save_regs.S @@ -31,10 +31,10 @@ _GLOBAL(ppc_save_regs) lbz r0,PACAIRQSOFTMASK(r13) PPC_STL r0,SOFTE(r3) #endif - /* go up one stack frame for SP */ - PPC_LL r4,0(r1) - PPC_STL r4,GPR1(r3) + /* store current SP */ + PPC_STL r1,GPR1(r3) /* get caller's LR */ + PPC_LL r4,0(r1) PPC_LL r0,LRSAVE(r4) PPC_STL r0,_LINK(r3) mflr r0 diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 1fefafb2b29b..b68898ac07e1 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1182,6 +1182,9 @@ static inline void save_sprs(struct thread_struct *t) */ t->tar = mfspr(SPRN_TAR); } + + if (cpu_has_feature(CPU_FTR_DEXCR_NPHIE)) + t->hashkeyr = mfspr(SPRN_HASHKEYR); #endif } @@ -1260,6 +1263,10 @@ static inline void restore_sprs(struct thread_struct *old_thread, if (cpu_has_feature(CPU_FTR_P9_TIDR) && old_thread->tidr != new_thread->tidr) mtspr(SPRN_TIDR, new_thread->tidr); + + if (cpu_has_feature(CPU_FTR_DEXCR_NPHIE) && + old_thread->hashkeyr != new_thread->hashkeyr) + mtspr(SPRN_HASHKEYR, new_thread->hashkeyr); #endif } @@ -1868,6 +1875,10 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) p->thread.tidr = 0; #endif +#ifdef CONFIG_PPC_BOOK3S_64 + if (cpu_has_feature(CPU_FTR_DEXCR_NPHIE)) + p->thread.hashkeyr = current->thread.hashkeyr; +#endif return 0; } @@ -1984,6 +1995,12 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp) current->thread.tm_tfiar = 0; current->thread.load_tm = 0; #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ +#ifdef CONFIG_PPC_BOOK3S_64 + if (cpu_has_feature(CPU_FTR_DEXCR_NPHIE)) { + current->thread.hashkeyr = get_random_long(); + mtspr(SPRN_HASHKEYR, current->thread.hashkeyr); + } +#endif /* CONFIG_PPC_BOOK3S_64 */ } EXPORT_SYMBOL(start_thread); diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 9d9ee4e9e1a1..0b5878c3125b 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -182,6 +182,7 @@ static struct ibm_feature ibm_pa_features[] __initdata = { .cpu_user_ftrs2 = PPC_FEATURE2_HTM_COMP | PPC_FEATURE2_HTM_NOSC_COMP }, { .pabyte = 64, .pabit = 0, .cpu_features = CPU_FTR_DAWR1 }, + { .pabyte = 68, .pabit = 5, .cpu_features = CPU_FTR_DEXCR_NPHIE }, }; /* diff --git a/arch/powerpc/kernel/prom_entry_64.S b/arch/powerpc/kernel/prom_entry_64.S new file mode 100644 index 000000000000..f1b8793d28c6 --- /dev/null +++ b/arch/powerpc/kernel/prom_entry_64.S @@ -0,0 +1,87 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * PowerPC version + * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org) + * Rewritten by Cort Dougan (cort@cs.nmt.edu) for PReP + * Copyright (C) 1996 Cort Dougan <cort@cs.nmt.edu> + * Adapted for Power Macintosh by Paul Mackerras. + * Low-level exception handlers and MMU support + * rewritten by Paul Mackerras. + * Copyright (C) 1996 Paul Mackerras. + * MPC8xx modifications Copyright (C) 1997 Dan Malek (dmalek@jlc.net). + * + * This file contains the 64-bit prom entry code. + */ +#include <asm/asm-offsets.h> +#ifdef CONFIG_PPC_BOOK3S +#include <asm/exception-64s.h> +#else +#include <asm/exception-64e.h> +#endif +#include <asm/ppc_asm.h> + +.section ".text","ax",@progbits + +_GLOBAL(enter_prom) + mflr r0 + std r0,16(r1) + stdu r1,-SWITCH_FRAME_SIZE(r1) /* Save SP and create stack space */ + + /* Because PROM is running in 32b mode, it clobbers the high order half + * of all registers that it saves. We therefore save those registers + * PROM might touch to the stack. (r0, r3-r13 are caller saved) + */ + SAVE_GPR(2, r1) + SAVE_GPR(13, r1) + SAVE_NVGPRS(r1) + mfcr r10 + mfmsr r11 + std r10,_CCR(r1) + std r11,_MSR(r1) + + /* Put PROM address in SRR0 */ + mtsrr0 r4 + + /* Setup our trampoline return addr in LR */ + bcl 20,31,$+4 +0: mflr r4 + addi r4,r4,(1f - 0b) + mtlr r4 + + /* Prepare a 32-bit mode big endian MSR + */ +#ifdef CONFIG_PPC_BOOK3E_64 + rlwinm r11,r11,0,1,31 + mtsrr1 r11 + rfi +#else /* CONFIG_PPC_BOOK3E_64 */ + LOAD_REG_IMMEDIATE(r12, MSR_SF | MSR_LE) + andc r11,r11,r12 + mtsrr1 r11 + RFI_TO_KERNEL +#endif /* CONFIG_PPC_BOOK3E_64 */ + +1: /* Return from OF */ + FIXUP_ENDIAN + + /* Just make sure that r1 top 32 bits didn't get + * corrupt by OF + */ + rldicl r1,r1,0,32 + + /* Restore the MSR (back to 64 bits) */ + ld r0,_MSR(r1) + MTMSRD(r0) + isync + + /* Restore other registers */ + REST_GPR(2, r1) + REST_GPR(13, r1) + REST_NVGPRS(r1) + ld r4,_CCR(r1) + mtcr r4 + + addi r1,r1,SWITCH_FRAME_SIZE + ld r0,16(r1) + mtlr r0 + blr diff --git a/arch/powerpc/kernel/ptrace/ptrace-decl.h b/arch/powerpc/kernel/ptrace/ptrace-decl.h index eafe5f0f6289..4171a5727197 100644 --- a/arch/powerpc/kernel/ptrace/ptrace-decl.h +++ b/arch/powerpc/kernel/ptrace/ptrace-decl.h @@ -1,5 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0-or-later */ +#include <linux/regset.h> + /* * Set of msr bits that gdb can change on behalf of a process. */ @@ -55,6 +57,10 @@ enum powerpc_regset { REGSET_TAR, /* TAR register */ REGSET_EBB, /* EBB registers */ REGSET_PMR, /* Performance Monitor Registers */ + REGSET_DEXCR, /* DEXCR registers */ +#ifdef CONFIG_CHECKPOINT_RESTORE + REGSET_HASHKEYR, /* HASHKEYR register */ +#endif #endif #ifdef CONFIG_PPC_MEM_KEYS REGSET_PKEY, /* AMR register */ diff --git a/arch/powerpc/kernel/ptrace/ptrace-view.c b/arch/powerpc/kernel/ptrace/ptrace-view.c index 5fff0d04b23f..3910cd7bb2d9 100644 --- a/arch/powerpc/kernel/ptrace/ptrace-view.c +++ b/arch/powerpc/kernel/ptrace/ptrace-view.c @@ -454,7 +454,65 @@ static int pmu_set(struct task_struct *target, const struct user_regset *regset, 5 * sizeof(unsigned long)); return ret; } -#endif + +static int dexcr_active(struct task_struct *target, const struct user_regset *regset) +{ + if (!cpu_has_feature(CPU_FTR_ARCH_31)) + return -ENODEV; + + return regset->n; +} + +static int dexcr_get(struct task_struct *target, const struct user_regset *regset, + struct membuf to) +{ + if (!cpu_has_feature(CPU_FTR_ARCH_31)) + return -ENODEV; + + /* + * The DEXCR is currently static across all CPUs, so we don't + * store the target's value anywhere, but the static value + * will also be correct. + */ + membuf_store(&to, (u64)lower_32_bits(DEXCR_INIT)); + + /* + * Technically the HDEXCR is per-cpu, but a hypervisor can't reasonably + * change it between CPUs of the same guest. + */ + return membuf_store(&to, (u64)lower_32_bits(mfspr(SPRN_HDEXCR_RO))); +} + +#ifdef CONFIG_CHECKPOINT_RESTORE +static int hashkeyr_active(struct task_struct *target, const struct user_regset *regset) +{ + if (!cpu_has_feature(CPU_FTR_ARCH_31)) + return -ENODEV; + + return regset->n; +} + +static int hashkeyr_get(struct task_struct *target, const struct user_regset *regset, + struct membuf to) +{ + if (!cpu_has_feature(CPU_FTR_ARCH_31)) + return -ENODEV; + + return membuf_store(&to, target->thread.hashkeyr); +} + +static int hashkeyr_set(struct task_struct *target, const struct user_regset *regset, + unsigned int pos, unsigned int count, const void *kbuf, + const void __user *ubuf) +{ + if (!cpu_has_feature(CPU_FTR_ARCH_31)) + return -ENODEV; + + return user_regset_copyin(&pos, &count, &kbuf, &ubuf, &target->thread.hashkeyr, + 0, sizeof(unsigned long)); +} +#endif /* CONFIG_CHECKPOINT_RESTORE */ +#endif /* CONFIG_PPC_BOOK3S_64 */ #ifdef CONFIG_PPC_MEM_KEYS static int pkey_active(struct task_struct *target, const struct user_regset *regset) @@ -615,6 +673,18 @@ static const struct user_regset native_regsets[] = { .size = sizeof(u64), .align = sizeof(u64), .active = pmu_active, .regset_get = pmu_get, .set = pmu_set }, + [REGSET_DEXCR] = { + .core_note_type = NT_PPC_DEXCR, .n = ELF_NDEXCR, + .size = sizeof(u64), .align = sizeof(u64), + .active = dexcr_active, .regset_get = dexcr_get + }, +#ifdef CONFIG_CHECKPOINT_RESTORE + [REGSET_HASHKEYR] = { + .core_note_type = NT_PPC_HASHKEYR, .n = ELF_NHASHKEYR, + .size = sizeof(u64), .align = sizeof(u64), + .active = hashkeyr_active, .regset_get = hashkeyr_get, .set = hashkeyr_set + }, +#endif #endif #ifdef CONFIG_PPC_MEM_KEYS [REGSET_PKEY] = { diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c index 4caf5e3079eb..359577ec1680 100644 --- a/arch/powerpc/kernel/rtas_flash.c +++ b/arch/powerpc/kernel/rtas_flash.c @@ -709,9 +709,9 @@ static int __init rtas_flash_init(void) if (!rtas_validate_flash_data.buf) return -ENOMEM; - flash_block_cache = kmem_cache_create("rtas_flash_cache", - RTAS_BLK_SIZE, RTAS_BLK_SIZE, 0, - NULL); + flash_block_cache = kmem_cache_create_usercopy("rtas_flash_cache", + RTAS_BLK_SIZE, RTAS_BLK_SIZE, + 0, 0, RTAS_BLK_SIZE, NULL); if (!flash_block_cache) { printk(KERN_ERR "%s: failed to create block cache\n", __func__); diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c index 206475e3e0b4..4856e1a5161c 100644 --- a/arch/powerpc/kernel/security.c +++ b/arch/powerpc/kernel/security.c @@ -364,26 +364,27 @@ ssize_t cpu_show_spec_store_bypass(struct device *dev, struct device_attribute * static int ssb_prctl_get(struct task_struct *task) { + /* + * The STF_BARRIER feature is on by default, so if it's off that means + * firmware has explicitly said the CPU is not vulnerable via either + * the hypercall or device tree. + */ + if (!security_ftr_enabled(SEC_FTR_STF_BARRIER)) + return PR_SPEC_NOT_AFFECTED; + + /* + * If the system's CPU has no known barrier (see setup_stf_barrier()) + * then assume that the CPU is not vulnerable. + */ if (stf_enabled_flush_types == STF_BARRIER_NONE) - /* - * We don't have an explicit signal from firmware that we're - * vulnerable or not, we only have certain CPU revisions that - * are known to be vulnerable. - * - * We assume that if we're on another CPU, where the barrier is - * NONE, then we are not vulnerable. - */ return PR_SPEC_NOT_AFFECTED; - else - /* - * If we do have a barrier type then we are vulnerable. The - * barrier is not a global or per-process mitigation, so the - * only value we can report here is PR_SPEC_ENABLE, which - * appears as "vulnerable" in /proc. - */ - return PR_SPEC_ENABLE; - - return -EINVAL; + + /* + * Otherwise the CPU is vulnerable. The barrier is not a global or + * per-process mitigation, so the only value that can be reported here + * is PR_SPEC_ENABLE, which appears as "vulnerable" in /proc. + */ + return PR_SPEC_ENABLE; } int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which) diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index c114c7f25645..7a718ed32b27 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -264,8 +264,9 @@ static void prepare_save_user_regs(int ctx_has_vsx_region) #endif } -static int __unsafe_save_user_regs(struct pt_regs *regs, struct mcontext __user *frame, - struct mcontext __user *tm_frame, int ctx_has_vsx_region) +static __always_inline int +__unsafe_save_user_regs(struct pt_regs *regs, struct mcontext __user *frame, + struct mcontext __user *tm_frame, int ctx_has_vsx_region) { unsigned long msr = regs->msr; @@ -364,8 +365,9 @@ static void prepare_save_tm_user_regs(void) current->thread.ckvrsave = mfspr(SPRN_VRSAVE); } -static int save_tm_user_regs_unsafe(struct pt_regs *regs, struct mcontext __user *frame, - struct mcontext __user *tm_frame, unsigned long msr) +static __always_inline int +save_tm_user_regs_unsafe(struct pt_regs *regs, struct mcontext __user *frame, + struct mcontext __user *tm_frame, unsigned long msr) { /* Save both sets of general registers */ unsafe_save_general_regs(¤t->thread.ckpt_regs, frame, failed); @@ -444,8 +446,9 @@ failed: #else static void prepare_save_tm_user_regs(void) { } -static int save_tm_user_regs_unsafe(struct pt_regs *regs, struct mcontext __user *frame, - struct mcontext __user *tm_frame, unsigned long msr) +static __always_inline int +save_tm_user_regs_unsafe(struct pt_regs *regs, struct mcontext __user *frame, + struct mcontext __user *tm_frame, unsigned long msr) { return 0; } diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 265801a3e94c..fbbb695bae3d 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -291,7 +291,7 @@ void smp_muxed_ipi_set_message(int cpu, int msg) * Order previous accesses before accesses in the IPI handler. */ smp_mb(); - message[msg] = 1; + WRITE_ONCE(message[msg], 1); } void smp_muxed_ipi_message_pass(int cpu, int msg) @@ -350,7 +350,7 @@ irqreturn_t smp_ipi_demux_relaxed(void) if (all & IPI_MESSAGE(PPC_MSG_NMI_IPI)) nmi_ipi_action(0, NULL); #endif - } while (info->messages); + } while (READ_ONCE(info->messages)); return IRQ_HANDLED; } @@ -417,9 +417,9 @@ noinstr static void nmi_ipi_lock_start(unsigned long *flags) { raw_local_irq_save(*flags); hard_irq_disable(); - while (arch_atomic_cmpxchg(&__nmi_ipi_lock, 0, 1) == 1) { + while (raw_atomic_cmpxchg(&__nmi_ipi_lock, 0, 1) == 1) { raw_local_irq_restore(*flags); - spin_until_cond(arch_atomic_read(&__nmi_ipi_lock) == 0); + spin_until_cond(raw_atomic_read(&__nmi_ipi_lock) == 0); raw_local_irq_save(*flags); hard_irq_disable(); } @@ -427,15 +427,15 @@ noinstr static void nmi_ipi_lock_start(unsigned long *flags) noinstr static void nmi_ipi_lock(void) { - while (arch_atomic_cmpxchg(&__nmi_ipi_lock, 0, 1) == 1) - spin_until_cond(arch_atomic_read(&__nmi_ipi_lock) == 0); + while (raw_atomic_cmpxchg(&__nmi_ipi_lock, 0, 1) == 1) + spin_until_cond(raw_atomic_read(&__nmi_ipi_lock) == 0); } noinstr static void nmi_ipi_unlock(void) { smp_mb(); - WARN_ON(arch_atomic_read(&__nmi_ipi_lock) != 1); - arch_atomic_set(&__nmi_ipi_lock, 0); + WARN_ON(raw_atomic_read(&__nmi_ipi_lock) != 1); + raw_atomic_set(&__nmi_ipi_lock, 0); } noinstr static void nmi_ipi_unlock_end(unsigned long *flags) @@ -1605,6 +1605,7 @@ static void add_cpu_to_masks(int cpu) } /* Activate a secondary processor. */ +__no_stack_protector void start_secondary(void *unused) { unsigned int cpu = raw_smp_processor_id(); diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c index 5de8597eaab8..b15f15dcacb5 100644 --- a/arch/powerpc/kernel/stacktrace.c +++ b/arch/powerpc/kernel/stacktrace.c @@ -221,8 +221,8 @@ static void raise_backtrace_ipi(cpumask_t *mask) } } -void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self) +void arch_trigger_cpumask_backtrace(const cpumask_t *mask, int exclude_cpu) { - nmi_trigger_cpumask_backtrace(mask, exclude_self, raise_backtrace_ipi); + nmi_trigger_cpumask_backtrace(mask, exclude_cpu, raise_backtrace_ipi); } #endif /* defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_NMI_IPI) */ diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/switch.S index 1bf1121e17f1..608c0ce7cec6 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/switch.S @@ -1,56 +1,21 @@ /* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * PowerPC version - * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org) - * Rewritten by Cort Dougan (cort@cs.nmt.edu) for PReP - * Copyright (C) 1996 Cort Dougan <cort@cs.nmt.edu> - * Adapted for Power Macintosh by Paul Mackerras. - * Low-level exception handlers and MMU support - * rewritten by Paul Mackerras. - * Copyright (C) 1996 Paul Mackerras. - * MPC8xx modifications Copyright (C) 1997 Dan Malek (dmalek@jlc.net). - * - * This file contains the system call entry code, context switch - * code, and exception/interrupt return code for PowerPC. - */ - #include <linux/objtool.h> -#include <linux/errno.h> -#include <linux/err.h> -#include <asm/cache.h> -#include <asm/unistd.h> -#include <asm/processor.h> -#include <asm/page.h> -#include <asm/mmu.h> -#include <asm/thread_info.h> +#include <asm/asm-offsets.h> #include <asm/code-patching-asm.h> +#include <asm/mmu.h> #include <asm/ppc_asm.h> -#include <asm/asm-offsets.h> -#include <asm/cputable.h> -#include <asm/firmware.h> -#include <asm/bug.h> -#include <asm/ptrace.h> -#include <asm/irqflags.h> -#include <asm/hw_irq.h> -#include <asm/context_tracking.h> -#include <asm/ppc-opcode.h> -#include <asm/barrier.h> -#include <asm/export.h> -#include <asm/asm-compat.h> -#ifdef CONFIG_PPC_BOOK3S -#include <asm/exception-64s.h> -#else -#include <asm/exception-64e.h> -#endif -#include <asm/feature-fixups.h> #include <asm/kup.h> +#include <asm/thread_info.h> -/* - * System calls. - */ - .section ".text" +.section ".text","ax",@progbits #ifdef CONFIG_PPC_BOOK3S_64 +/* + * Cancel all explict user streams as they will have no use after context + * switch and will stop the HW from creating streams itself + */ +#define STOP_STREAMS \ + DCBT_BOOK3S_STOP_ALL_STREAM_IDS(r6) #define FLUSH_COUNT_CACHE \ 1: nop; \ @@ -105,87 +70,13 @@ flush_branch_caches: .endr blr -#else -#define FLUSH_COUNT_CACHE -#endif /* CONFIG_PPC_BOOK3S_64 */ +#ifdef CONFIG_PPC_64S_HASH_MMU +.balign 32 /* - * This routine switches between two different tasks. The process - * state of one is saved on its kernel stack. Then the state - * of the other is restored from its kernel stack. The memory - * management hardware is updated to the second process's state. - * Finally, we can return to the second process, via interrupt_return. - * On entry, r3 points to the THREAD for the current task, r4 - * points to the THREAD for the new task. - * - * Note: there are two ways to get to the "going out" portion - * of this code; either by coming in via the entry (_switch) - * or via "fork" which must set up an environment equivalent - * to the "_switch" path. If you change this you'll have to change - * the fork code also. - * - * The code which creates the new task context is in 'copy_thread' - * in arch/powerpc/kernel/process.c + * New stack pointer in r8, old stack pointer in r1, must not clobber r3 */ - .align 7 -_GLOBAL(_switch) - mflr r0 - std r0,16(r1) - stdu r1,-SWITCH_FRAME_SIZE(r1) - /* r3-r13 are caller saved -- Cort */ - SAVE_NVGPRS(r1) - std r0,_NIP(r1) /* Return to switch caller */ - mfcr r23 - std r23,_CCR(r1) - std r1,KSP(r3) /* Set old stack pointer */ - - kuap_check_amr r9, r10 - - FLUSH_COUNT_CACHE /* Clobbers r9, ctr */ - - /* - * On SMP kernels, care must be taken because a task may be - * scheduled off CPUx and on to CPUy. Memory ordering must be - * considered. - * - * Cacheable stores on CPUx will be visible when the task is - * scheduled on CPUy by virtue of the core scheduler barriers - * (see "Notes on Program-Order guarantees on SMP systems." in - * kernel/sched/core.c). - * - * Uncacheable stores in the case of involuntary preemption must - * be taken care of. The smp_mb__after_spinlock() in __schedule() - * is implemented as hwsync on powerpc, which orders MMIO too. So - * long as there is an hwsync in the context switch path, it will - * be executed on the source CPU after the task has performed - * all MMIO ops on that CPU, and on the destination CPU before the - * task performs any MMIO ops there. - */ - - /* - * The kernel context switch path must contain a spin_lock, - * which contains larx/stcx, which will clear any reservation - * of the task being switched. - */ -#ifdef CONFIG_PPC_BOOK3S -/* Cancel all explict user streams as they will have no use after context - * switch and will stop the HW from creating streams itself - */ - DCBT_BOOK3S_STOP_ALL_STREAM_IDS(r6) -#endif - - addi r6,r4,-THREAD /* Convert THREAD to 'current' */ - std r6,PACACURRENT(r13) /* Set new 'current' */ -#if defined(CONFIG_STACKPROTECTOR) - ld r6, TASK_CANARY(r6) - std r6, PACA_CANARY(r13) -#endif - - ld r8,KSP(r4) /* new stack pointer */ -#ifdef CONFIG_PPC_64S_HASH_MMU -BEGIN_MMU_FTR_SECTION - b 2f -END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX) +pin_stack_slb: BEGIN_FTR_SECTION clrrdi r6,r8,28 /* get its ESID */ clrrdi r9,r1,28 /* get current sp ESID */ @@ -233,15 +124,57 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) slbmte r7,r0 isync -2: +2: blr + .size pin_stack_slb,.-pin_stack_slb #endif /* CONFIG_PPC_64S_HASH_MMU */ - clrrdi r7, r8, THREAD_SHIFT /* base of new stack */ - /* Note: this uses SWITCH_FRAME_SIZE rather than INT_FRAME_SIZE - because we don't need to leave the 288-byte ABI gap at the - top of the kernel stack. */ +#else +#define STOP_STREAMS +#define FLUSH_COUNT_CACHE +#endif /* CONFIG_PPC_BOOK3S_64 */ + +/* + * do_switch_32/64 have the same calling convention as _switch, i.e., r3,r4 + * are prev and next thread_struct *, and returns prev task_struct * in r3. + + * This switches the stack, current, and does other task switch housekeeping. + */ +.macro do_switch_32 + tophys(r0,r4) + mtspr SPRN_SPRG_THREAD,r0 /* Update current THREAD phys addr */ + lwz r1,KSP(r4) /* Load new stack pointer */ + + /* save the old current 'last' for return value */ + mr r3,r2 + addi r2,r4,-THREAD /* Update current */ +.endm + +.macro do_switch_64 + ld r8,KSP(r4) /* Load new stack pointer */ + + kuap_check_amr r9, r10 + + FLUSH_COUNT_CACHE /* Clobbers r9, ctr */ + + STOP_STREAMS /* Clobbers r6 */ + + addi r3,r3,-THREAD /* old thread -> task_struct for return value */ + addi r6,r4,-THREAD /* new thread -> task_struct */ + std r6,PACACURRENT(r13) /* Set new task_struct to 'current' */ +#if defined(CONFIG_STACKPROTECTOR) + ld r6, TASK_CANARY(r6) + std r6, PACA_CANARY(r13) +#endif + /* Set new PACAKSAVE */ + clrrdi r7,r8,THREAD_SHIFT /* base of new stack */ addi r7,r7,THREAD_SIZE-SWITCH_FRAME_SIZE + std r7,PACAKSAVE(r13) +#ifdef CONFIG_PPC_64S_HASH_MMU +BEGIN_MMU_FTR_SECTION + bl pin_stack_slb +END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX) +#endif /* * PMU interrupts in radix may come in here. They will use r1, not * PACAKSAVE, so this stack switch will not cause a problem. They @@ -251,81 +184,75 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) * active on the new CPU, will order those stores. */ mr r1,r8 /* start using new stack pointer */ - std r7,PACAKSAVE(r13) +.endm + +/* + * This routine switches between two different tasks. The process + * state of one is saved on its kernel stack. Then the state + * of the other is restored from its kernel stack. The memory + * management hardware is updated to the second process's state. + * Finally, we can return to the second process. + * On entry, r3 points to the THREAD for the current task, r4 + * points to the THREAD for the new task. + * + * This routine is always called with interrupts disabled. + * + * Note: there are two ways to get to the "going out" portion + * of this code; either by coming in via the entry (_switch) + * or via "fork" which must set up an environment equivalent + * to the "_switch" path. If you change this , you'll have to + * change the fork code also. + * + * The code which creates the new task context is in 'copy_thread' + * in arch/ppc/kernel/process.c + * + * Note: this uses SWITCH_FRAME_SIZE rather than USER_INT_FRAME_SIZE + * because we don't need to leave the redzone ABI gap at the top of + * the kernel stack. + */ +_GLOBAL(_switch) + PPC_CREATE_STACK_FRAME(SWITCH_FRAME_SIZE) + PPC_STL r1,KSP(r3) /* Set old stack pointer */ + SAVE_NVGPRS(r1) /* volatiles are caller-saved -- Cort */ + PPC_STL r0,_NIP(r1) /* Return to switch caller */ + mfcr r0 + stw r0,_CCR(r1) - ld r6,_CCR(r1) - mtcrf 0xFF,r6 + /* + * On SMP kernels, care must be taken because a task may be + * scheduled off CPUx and on to CPUy. Memory ordering must be + * considered. + * + * Cacheable stores on CPUx will be visible when the task is + * scheduled on CPUy by virtue of the core scheduler barriers + * (see "Notes on Program-Order guarantees on SMP systems." in + * kernel/sched/core.c). + * + * Uncacheable stores in the case of involuntary preemption must + * be taken care of. The smp_mb__after_spinlock() in __schedule() + * is implemented as hwsync on powerpc, which orders MMIO too. So + * long as there is an hwsync in the context switch path, it will + * be executed on the source CPU after the task has performed + * all MMIO ops on that CPU, and on the destination CPU before the + * task performs any MMIO ops there. + */ + + /* + * The kernel context switch path must contain a spin_lock, + * which contains larx/stcx, which will clear any reservation + * of the task being switched. + */ - /* r3-r13 are destroyed -- Cort */ - REST_NVGPRS(r1) +#ifdef CONFIG_PPC32 + do_switch_32 +#else + do_switch_64 +#endif - /* convert old thread to its task_struct for return value */ - addi r3,r3,-THREAD - ld r7,_NIP(r1) /* Return to _switch caller in new task */ - mtlr r7 + lwz r0,_CCR(r1) + mtcrf 0xFF,r0 + REST_NVGPRS(r1) /* volatiles are destroyed -- Cort */ + PPC_LL r0,_NIP(r1) /* Return to _switch caller in new task */ + mtlr r0 addi r1,r1,SWITCH_FRAME_SIZE blr - -_GLOBAL(enter_prom) - mflr r0 - std r0,16(r1) - stdu r1,-SWITCH_FRAME_SIZE(r1) /* Save SP and create stack space */ - - /* Because PROM is running in 32b mode, it clobbers the high order half - * of all registers that it saves. We therefore save those registers - * PROM might touch to the stack. (r0, r3-r13 are caller saved) - */ - SAVE_GPR(2, r1) - SAVE_GPR(13, r1) - SAVE_NVGPRS(r1) - mfcr r10 - mfmsr r11 - std r10,_CCR(r1) - std r11,_MSR(r1) - - /* Put PROM address in SRR0 */ - mtsrr0 r4 - - /* Setup our trampoline return addr in LR */ - bcl 20,31,$+4 -0: mflr r4 - addi r4,r4,(1f - 0b) - mtlr r4 - - /* Prepare a 32-bit mode big endian MSR - */ -#ifdef CONFIG_PPC_BOOK3E_64 - rlwinm r11,r11,0,1,31 - mtsrr1 r11 - rfi -#else /* CONFIG_PPC_BOOK3E_64 */ - LOAD_REG_IMMEDIATE(r12, MSR_SF | MSR_LE) - andc r11,r11,r12 - mtsrr1 r11 - RFI_TO_KERNEL -#endif /* CONFIG_PPC_BOOK3E_64 */ - -1: /* Return from OF */ - FIXUP_ENDIAN - - /* Just make sure that r1 top 32 bits didn't get - * corrupt by OF - */ - rldicl r1,r1,0,32 - - /* Restore the MSR (back to 64 bits) */ - ld r0,_MSR(r1) - MTMSRD(r0) - isync - - /* Restore other registers */ - REST_GPR(2, r1) - REST_GPR(13, r1) - REST_NVGPRS(r1) - ld r4,_CCR(r1) - mtcr r4 - - addi r1,r1,SWITCH_FRAME_SIZE - ld r0,16(r1) - mtlr r0 - blr diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index a0be127475b1..8c0b08b7a80e 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -537,3 +537,4 @@ 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv 450 nospu set_mempolicy_home_node sys_set_mempolicy_home_node +451 common cachestat sys_cachestat diff --git a/arch/powerpc/kernel/tau_6xx.c b/arch/powerpc/kernel/tau_6xx.c index 828d0f4106d2..cba6dd15de3b 100644 --- a/arch/powerpc/kernel/tau_6xx.c +++ b/arch/powerpc/kernel/tau_6xx.c @@ -200,7 +200,7 @@ static int __init TAU_init(void) tau_int_enable = IS_ENABLED(CONFIG_TAU_INT) && !strcmp(cur_cpu_spec->platform, "ppc750"); - tau_workq = alloc_workqueue("tau", WQ_UNBOUND, 1); + tau_workq = alloc_ordered_workqueue("tau", 0); if (!tau_workq) return -ENOMEM; diff --git a/arch/powerpc/kernel/trace/ftrace_mprofile.S b/arch/powerpc/kernel/trace/ftrace_mprofile.S index ffb1db386849..1f7d86de1538 100644 --- a/arch/powerpc/kernel/trace/ftrace_mprofile.S +++ b/arch/powerpc/kernel/trace/ftrace_mprofile.S @@ -33,6 +33,9 @@ * and then arrange for the ftrace function to be called. */ .macro ftrace_regs_entry allregs + /* Create a minimal stack frame for representing B */ + PPC_STLU r1, -STACK_FRAME_MIN_SIZE(r1) + /* Create our stack frame + pt_regs */ PPC_STLU r1,-SWITCH_FRAME_SIZE(r1) @@ -42,7 +45,7 @@ #ifdef CONFIG_PPC64 /* Save the original return address in A's stack frame */ - std r0, LRSAVE+SWITCH_FRAME_SIZE(r1) + std r0, LRSAVE+SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE(r1) /* Ok to continue? */ lbz r3, PACA_FTRACE_ENABLED(r13) cmpdi r3, 0 @@ -77,6 +80,8 @@ mflr r7 /* Save it as pt_regs->nip */ PPC_STL r7, _NIP(r1) + /* Also save it in B's stackframe header for proper unwind */ + PPC_STL r7, LRSAVE+SWITCH_FRAME_SIZE(r1) /* Save the read LR in pt_regs->link */ PPC_STL r0, _LINK(r1) @@ -142,7 +147,7 @@ #endif /* Pop our stack frame */ - addi r1, r1, SWITCH_FRAME_SIZE + addi r1, r1, SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE #ifdef CONFIG_LIVEPATCH_64 /* Based on the cmpd above, if the NIP was altered handle livepatch */ diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 9bdd79aa51cf..7ef147e2a20d 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -1508,14 +1508,25 @@ static void do_program_check(struct pt_regs *regs) if (!(regs->msr & MSR_PR) && /* not user-mode */ report_bug(bugaddr, regs) == BUG_TRAP_TYPE_WARN) { - const struct exception_table_entry *entry; + regs_add_return_ip(regs, 4); + return; + } + + if (cpu_has_feature(CPU_FTR_DEXCR_NPHIE) && user_mode(regs)) { + ppc_inst_t insn; - entry = search_exception_tables(bugaddr); - if (entry) { - regs_set_return_ip(regs, extable_fixup(entry) + regs->nip - bugaddr); + if (get_user_instr(insn, (void __user *)regs->nip)) { + _exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip); + return; + } + + if (ppc_inst_primary_opcode(insn) == 31 && + get_xop(ppc_inst_val(insn)) == OP_31_XOP_HASHCHK) { + _exception(SIGILL, regs, ILL_ILLOPN, regs->nip); return; } } + _exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip); return; } diff --git a/arch/powerpc/kernel/vdso/Makefile b/arch/powerpc/kernel/vdso/Makefile index 4c3f34485f08..0c7d82c270c3 100644 --- a/arch/powerpc/kernel/vdso/Makefile +++ b/arch/powerpc/kernel/vdso/Makefile @@ -54,8 +54,10 @@ KASAN_SANITIZE := n KCSAN_SANITIZE := n ccflags-y := -fno-common -fno-builtin -ldflags-y := -Wl,--hash-style=both -nostdlib -shared -z noexecstack +ldflags-y := -Wl,--hash-style=both -nostdlib -shared -z noexecstack $(CLANG_FLAGS) ldflags-$(CONFIG_LD_IS_LLD) += $(call cc-option,--ld-path=$(LD),-fuse-ld=lld) +ldflags-$(CONFIG_LD_ORPHAN_WARN) += -Wl,--orphan-handling=$(CONFIG_LD_ORPHAN_WARN_LEVEL) + # Filter flags that clang will warn are unused for linking ldflags-y += $(filter-out $(CC_AUTO_VAR_INIT_ZERO_ENABLER) $(CC_FLAGS_FTRACE) -Wa$(comma)%, $(KBUILD_CFLAGS)) diff --git a/arch/powerpc/kernel/vdso/vdso32.lds.S b/arch/powerpc/kernel/vdso/vdso32.lds.S index bc0be274a9ac..426e1ccc6971 100644 --- a/arch/powerpc/kernel/vdso/vdso32.lds.S +++ b/arch/powerpc/kernel/vdso/vdso32.lds.S @@ -83,9 +83,11 @@ SECTIONS /DISCARD/ : { *(.note.GNU-stack) + *(*.EMB.apuinfo) + *(.branch_lt) *(.data .data.* .gnu.linkonce.d.* .sdata*) *(.bss .sbss .dynbss .dynsbss) - *(.got1) + *(.got1 .glink .iplt .rela*) } } diff --git a/arch/powerpc/kernel/vdso/vdso64.lds.S b/arch/powerpc/kernel/vdso/vdso64.lds.S index 744ae5363e6c..bda6c8cdd459 100644 --- a/arch/powerpc/kernel/vdso/vdso64.lds.S +++ b/arch/powerpc/kernel/vdso/vdso64.lds.S @@ -32,7 +32,7 @@ SECTIONS . = ALIGN(16); .text : { *(.text .stub .text.* .gnu.linkonce.t.* __ftr_alt_*) - *(.sfpr .glink) + *(.sfpr) } :text PROVIDE(__etext = .); PROVIDE(_etext = .); @@ -81,10 +81,12 @@ SECTIONS /DISCARD/ : { *(.note.GNU-stack) + *(*.EMB.apuinfo) *(.branch_lt) *(.data .data.* .gnu.linkonce.d.* .sdata*) *(.bss .sbss .dynbss .dynsbss) *(.opd) + *(.glink .iplt .plt .rela*) } } diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c index dbcc4a793f0b..8c464a5d8246 100644 --- a/arch/powerpc/kernel/watchdog.c +++ b/arch/powerpc/kernel/watchdog.c @@ -245,7 +245,7 @@ static void watchdog_smp_panic(int cpu) __cpumask_clear_cpu(c, &wd_smp_cpus_ipi); } } else { - trigger_allbutself_cpu_backtrace(); + trigger_allbutcpu_cpu_backtrace(cpu); cpumask_clear(&wd_smp_cpus_ipi); } @@ -416,7 +416,7 @@ DEFINE_INTERRUPT_HANDLER_NMI(soft_nmi_interrupt) xchg(&__wd_nmi_output, 1); // see wd_lockup_ipi if (sysctl_hardlockup_all_cpu_backtrace) - trigger_allbutself_cpu_backtrace(); + trigger_allbutcpu_cpu_backtrace(cpu); if (hardlockup_panic) nmi_panic(regs, "Hard LOCKUP"); @@ -438,7 +438,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) { int cpu = smp_processor_id(); - if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) + if (!(watchdog_enabled & WATCHDOG_HARDLOCKUP_ENABLED)) return HRTIMER_NORESTART; if (!cpumask_test_cpu(cpu, &watchdog_cpumask)) @@ -479,7 +479,7 @@ static void start_watchdog(void *arg) return; } - if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) + if (!(watchdog_enabled & WATCHDOG_HARDLOCKUP_ENABLED)) return; if (!cpumask_test_cpu(cpu, &watchdog_cpumask)) @@ -546,7 +546,7 @@ static void watchdog_calc_timeouts(void) wd_timer_period_ms = watchdog_thresh * 1000 * 2 / 5; } -void watchdog_nmi_stop(void) +void watchdog_hardlockup_stop(void) { int cpu; @@ -554,7 +554,7 @@ void watchdog_nmi_stop(void) stop_watchdog_on_cpu(cpu); } -void watchdog_nmi_start(void) +void watchdog_hardlockup_start(void) { int cpu; @@ -566,7 +566,7 @@ void watchdog_nmi_start(void) /* * Invoked from core watchdog init. */ -int __init watchdog_nmi_probe(void) +int __init watchdog_hardlockup_probe(void) { int err; @@ -582,7 +582,7 @@ int __init watchdog_nmi_probe(void) } #ifdef CONFIG_PPC_PSERIES -void watchdog_nmi_set_timeout_pct(u64 pct) +void watchdog_hardlockup_set_timeout_pct(u64 pct) { pr_info("Set the NMI watchdog timeout factor to %llu%%\n", pct); WRITE_ONCE(wd_timeout_pct, pct); |