diff options
Diffstat (limited to 'arch/powerpc')
27 files changed, 350 insertions, 149 deletions
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index 6900d0ac2421..089ee3ea55c8 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -35,7 +35,6 @@ endif BOOTCFLAGS := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \ -fno-strict-aliasing -O2 -msoft-float -mno-altivec -mno-vsx \ -pipe -fomit-frame-pointer -fno-builtin -fPIC -nostdinc \ - -include $(srctree)/include/linux/compiler_attributes.h \ $(LINUXINCLUDE) ifdef CONFIG_PPC64_BOOT_WRAPPER @@ -70,6 +69,7 @@ ifeq ($(call cc-option-yn, -fstack-protector),y) BOOTCFLAGS += -fno-stack-protector endif +BOOTCFLAGS += -include $(srctree)/include/linux/compiler_attributes.h BOOTCFLAGS += -I$(objtree)/$(obj) -I$(srctree)/$(obj) DTC_FLAGS ?= -p 1024 diff --git a/arch/powerpc/boot/dts/fsl/t1023rdb.dts b/arch/powerpc/boot/dts/fsl/t1023rdb.dts index 5ba6fbfca274..f82f85c65964 100644 --- a/arch/powerpc/boot/dts/fsl/t1023rdb.dts +++ b/arch/powerpc/boot/dts/fsl/t1023rdb.dts @@ -154,7 +154,7 @@ fm1mac3: ethernet@e4000 { phy-handle = <&sgmii_aqr_phy3>; - phy-connection-type = "sgmii-2500"; + phy-connection-type = "2500base-x"; sleep = <&rcpm 0x20000000>; }; diff --git a/arch/powerpc/include/asm/asm-const.h b/arch/powerpc/include/asm/asm-const.h index 0ce2368bd20f..dbfa5e1e3198 100644 --- a/arch/powerpc/include/asm/asm-const.h +++ b/arch/powerpc/include/asm/asm-const.h @@ -12,16 +12,6 @@ # define ASM_CONST(x) __ASM_CONST(x) #endif -/* - * Inline assembly memory constraint - * - * GCC 4.9 doesn't properly handle pre update memory constraint "m<>" - * - */ -#if defined(GCC_VERSION) && GCC_VERSION < 50000 -#define UPD_CONSTR "" -#else #define UPD_CONSTR "<>" -#endif #endif /* _ASM_POWERPC_ASM_CONST_H */ diff --git a/arch/powerpc/include/asm/book3s/32/kup.h b/arch/powerpc/include/asm/book3s/32/kup.h index d4b145b279f6..9f38040f0641 100644 --- a/arch/powerpc/include/asm/book3s/32/kup.h +++ b/arch/powerpc/include/asm/book3s/32/kup.h @@ -136,6 +136,14 @@ static inline void kuap_kernel_restore(struct pt_regs *regs, unsigned long kuap) if (kuap_is_disabled()) return; + if (unlikely(kuap != KUAP_NONE)) { + current->thread.kuap = KUAP_NONE; + kuap_lock(kuap, false); + } + + if (likely(regs->kuap == KUAP_NONE)) + return; + current->thread.kuap = regs->kuap; kuap_unlock(regs->kuap, false); diff --git a/arch/powerpc/include/asm/code-patching.h b/arch/powerpc/include/asm/code-patching.h index a95f63788c6b..4ba834599c4d 100644 --- a/arch/powerpc/include/asm/code-patching.h +++ b/arch/powerpc/include/asm/code-patching.h @@ -23,6 +23,7 @@ #define BRANCH_ABSOLUTE 0x2 bool is_offset_in_branch_range(long offset); +bool is_offset_in_cond_branch_range(long offset); int create_branch(struct ppc_inst *instr, const u32 *addr, unsigned long target, int flags); int create_cond_branch(struct ppc_inst *instr, const u32 *addr, diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h index 6b800d3e2681..a1d238255f07 100644 --- a/arch/powerpc/include/asm/interrupt.h +++ b/arch/powerpc/include/asm/interrupt.h @@ -265,13 +265,16 @@ static inline void interrupt_nmi_enter_prepare(struct pt_regs *regs, struct inte local_paca->irq_soft_mask = IRQS_ALL_DISABLED; local_paca->irq_happened |= PACA_IRQ_HARD_DIS; - if (is_implicit_soft_masked(regs)) { - // Adjust regs->softe soft implicit soft-mask, so - // arch_irq_disabled_regs(regs) behaves as expected. + if (!(regs->msr & MSR_EE) || is_implicit_soft_masked(regs)) { + /* + * Adjust regs->softe to be soft-masked if it had not been + * reconcied (e.g., interrupt entry with MSR[EE]=0 but softe + * not yet set disabled), or if it was in an implicit soft + * masked state. This makes arch_irq_disabled_regs(regs) + * behave as expected. + */ regs->softe = IRQS_ALL_DISABLED; } - if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) - BUG_ON(!arch_irq_disabled_regs(regs) && !(regs->msr & MSR_EE)); /* Don't do any per-CPU operations until interrupt state is fixed */ @@ -525,10 +528,9 @@ static __always_inline long ____##func(struct pt_regs *regs) /* kernel/traps.c */ DECLARE_INTERRUPT_HANDLER_NMI(system_reset_exception); #ifdef CONFIG_PPC_BOOK3S_64 -DECLARE_INTERRUPT_HANDLER_ASYNC(machine_check_exception); -#else -DECLARE_INTERRUPT_HANDLER_NMI(machine_check_exception); +DECLARE_INTERRUPT_HANDLER_ASYNC(machine_check_exception_async); #endif +DECLARE_INTERRUPT_HANDLER_NMI(machine_check_exception); DECLARE_INTERRUPT_HANDLER(SMIException); DECLARE_INTERRUPT_HANDLER(handle_hmi_exception); DECLARE_INTERRUPT_HANDLER(unknown_exception); diff --git a/arch/powerpc/include/asm/security_features.h b/arch/powerpc/include/asm/security_features.h index 792eefaf230b..27574f218b37 100644 --- a/arch/powerpc/include/asm/security_features.h +++ b/arch/powerpc/include/asm/security_features.h @@ -39,6 +39,11 @@ static inline bool security_ftr_enabled(u64 feature) return !!(powerpc_security_features & feature); } +#ifdef CONFIG_PPC_BOOK3S_64 +enum stf_barrier_type stf_barrier_type_get(void); +#else +static inline enum stf_barrier_type stf_barrier_type_get(void) { return STF_BARRIER_NONE; } +#endif // Features indicating support for Spectre/Meltdown mitigations diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c index 111249fd619d..038ce8d9061d 100644 --- a/arch/powerpc/kernel/dma-iommu.c +++ b/arch/powerpc/kernel/dma-iommu.c @@ -184,6 +184,15 @@ u64 dma_iommu_get_required_mask(struct device *dev) struct iommu_table *tbl = get_iommu_table_base(dev); u64 mask; + if (dev_is_pci(dev)) { + u64 bypass_mask = dma_direct_get_required_mask(dev); + + if (dma_iommu_dma_supported(dev, bypass_mask)) { + dev_info(dev, "%s: returning bypass mask 0x%llx\n", __func__, bypass_mask); + return bypass_mask; + } + } + if (!tbl) return 0; diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 37859e62a8dc..eaf1f72131a1 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -1243,7 +1243,7 @@ EXC_COMMON_BEGIN(machine_check_common) li r10,MSR_RI mtmsrd r10,1 addi r3,r1,STACK_FRAME_OVERHEAD - bl machine_check_exception + bl machine_check_exception_async b interrupt_return_srr @@ -1303,7 +1303,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) subi r12,r12,1 sth r12,PACA_IN_MCE(r13) - /* Invoke machine_check_exception to print MCE event and panic. */ + /* + * Invoke machine_check_exception to print MCE event and panic. + * This is the NMI version of the handler because we are called from + * the early handler which is a true NMI. + */ addi r3,r1,STACK_FRAME_OVERHEAD bl machine_check_exception @@ -1665,27 +1669,30 @@ EXC_COMMON_BEGIN(program_check_common) */ andi. r10,r12,MSR_PR - bne 2f /* If userspace, go normal path */ + bne .Lnormal_stack /* If userspace, go normal path */ andis. r10,r12,(SRR1_PROGTM)@h - bne 1f /* If TM, emergency */ + bne .Lemergency_stack /* If TM, emergency */ cmpdi r1,-INT_FRAME_SIZE /* check if r1 is in userspace */ - blt 2f /* normal path if not */ + blt .Lnormal_stack /* normal path if not */ /* Use the emergency stack */ -1: andi. r10,r12,MSR_PR /* Set CR0 correctly for label */ +.Lemergency_stack: + andi. r10,r12,MSR_PR /* Set CR0 correctly for label */ /* 3 in EXCEPTION_PROLOG_COMMON */ mr r10,r1 /* Save r1 */ ld r1,PACAEMERGSP(r13) /* Use emergency stack */ subi r1,r1,INT_FRAME_SIZE /* alloc stack frame */ __ISTACK(program_check)=0 __GEN_COMMON_BODY program_check - b 3f -2: + b .Ldo_program_check + +.Lnormal_stack: __ISTACK(program_check)=1 __GEN_COMMON_BODY program_check -3: + +.Ldo_program_check: addi r3,r1,STACK_FRAME_OVERHEAD bl program_check_exception REST_NVGPRS(r1) /* instruction emulation may change GPRs */ diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c index a73f3f70a657..de10a2697258 100644 --- a/arch/powerpc/kernel/interrupt.c +++ b/arch/powerpc/kernel/interrupt.c @@ -18,6 +18,7 @@ #include <asm/switch_to.h> #include <asm/syscall.h> #include <asm/time.h> +#include <asm/tm.h> #include <asm/unistd.h> #if defined(CONFIG_PPC_ADV_DEBUG_REGS) && defined(CONFIG_PPC32) @@ -136,6 +137,48 @@ notrace long system_call_exception(long r3, long r4, long r5, */ irq_soft_mask_regs_set_state(regs, IRQS_ENABLED); + /* + * If system call is called with TM active, set _TIF_RESTOREALL to + * prevent RFSCV being used to return to userspace, because POWER9 + * TM implementation has problems with this instruction returning to + * transactional state. Final register values are not relevant because + * the transaction will be aborted upon return anyway. Or in the case + * of unsupported_scv SIGILL fault, the return state does not much + * matter because it's an edge case. + */ + if (IS_ENABLED(CONFIG_PPC_TRANSACTIONAL_MEM) && + unlikely(MSR_TM_TRANSACTIONAL(regs->msr))) + current_thread_info()->flags |= _TIF_RESTOREALL; + + /* + * If the system call was made with a transaction active, doom it and + * return without performing the system call. Unless it was an + * unsupported scv vector, in which case it's treated like an illegal + * instruction. + */ +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (unlikely(MSR_TM_TRANSACTIONAL(regs->msr)) && + !trap_is_unsupported_scv(regs)) { + /* Enable TM in the kernel, and disable EE (for scv) */ + hard_irq_disable(); + mtmsr(mfmsr() | MSR_TM); + + /* tabort, this dooms the transaction, nothing else */ + asm volatile(".long 0x7c00071d | ((%0) << 16)" + :: "r"(TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT)); + + /* + * Userspace will never see the return value. Execution will + * resume after the tbegin. of the aborted transaction with the + * checkpointed register state. A context switch could occur + * or signal delivered to the process before resuming the + * doomed transaction context, but that should all be handled + * as expected. + */ + return -ENOSYS; + } +#endif // CONFIG_PPC_TRANSACTIONAL_MEM + local_irq_enable(); if (unlikely(current_thread_info()->flags & _TIF_SYSCALL_DOTRACE)) { diff --git a/arch/powerpc/kernel/interrupt_64.S b/arch/powerpc/kernel/interrupt_64.S index d4212d2ff0b5..ec950b08a8dc 100644 --- a/arch/powerpc/kernel/interrupt_64.S +++ b/arch/powerpc/kernel/interrupt_64.S @@ -12,7 +12,6 @@ #include <asm/mmu.h> #include <asm/ppc_asm.h> #include <asm/ptrace.h> -#include <asm/tm.h> .section ".toc","aw" SYS_CALL_TABLE: @@ -55,12 +54,6 @@ COMPAT_SYS_CALL_TABLE: .globl system_call_vectored_\name system_call_vectored_\name: _ASM_NOKPROBE_SYMBOL(system_call_vectored_\name) -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM -BEGIN_FTR_SECTION - extrdi. r10, r12, 1, (63-MSR_TS_T_LG) /* transaction active? */ - bne tabort_syscall -END_FTR_SECTION_IFSET(CPU_FTR_TM) -#endif SCV_INTERRUPT_TO_KERNEL mr r10,r1 ld r1,PACAKSAVE(r13) @@ -247,12 +240,6 @@ _ASM_NOKPROBE_SYMBOL(system_call_common_real) .globl system_call_common system_call_common: _ASM_NOKPROBE_SYMBOL(system_call_common) -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM -BEGIN_FTR_SECTION - extrdi. r10, r12, 1, (63-MSR_TS_T_LG) /* transaction active? */ - bne tabort_syscall -END_FTR_SECTION_IFSET(CPU_FTR_TM) -#endif mr r10,r1 ld r1,PACAKSAVE(r13) std r10,0(r1) @@ -425,34 +412,6 @@ SOFT_MASK_TABLE(.Lsyscall_rst_start, 1b) RESTART_TABLE(.Lsyscall_rst_start, .Lsyscall_rst_end, syscall_restart) #endif -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM -tabort_syscall: -_ASM_NOKPROBE_SYMBOL(tabort_syscall) - /* Firstly we need to enable TM in the kernel */ - mfmsr r10 - li r9, 1 - rldimi r10, r9, MSR_TM_LG, 63-MSR_TM_LG - mtmsrd r10, 0 - - /* tabort, this dooms the transaction, nothing else */ - li r9, (TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT) - TABORT(R9) - - /* - * Return directly to userspace. We have corrupted user register state, - * but userspace will never see that register state. Execution will - * resume after the tbegin of the aborted transaction with the - * checkpointed register state. - */ - li r9, MSR_RI - andc r10, r10, r9 - mtmsrd r10, 1 - mtspr SPRN_SRR0, r11 - mtspr SPRN_SRR1, r12 - RFI_TO_USER - b . /* prevent speculative execution */ -#endif - /* * If MSR EE/RI was never enabled, IRQs not reconciled, NVGPRs not * touched, no exit work created, then this can be used. diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 551b653228c4..c4f1d6b7d992 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -229,6 +229,9 @@ notrace void arch_local_irq_restore(unsigned long mask) return; } + if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) + WARN_ON_ONCE(in_nmi() || in_hardirq()); + /* * After the stb, interrupts are unmasked and there are no interrupts * pending replay. The restart sequence makes this atomic with @@ -321,6 +324,9 @@ notrace void arch_local_irq_restore(unsigned long 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 diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c index 47a683cd00d2..fd829f7f25a4 100644 --- a/arch/powerpc/kernel/mce.c +++ b/arch/powerpc/kernel/mce.c @@ -249,6 +249,7 @@ void machine_check_queue_event(void) { int index; struct machine_check_event evt; + unsigned long msr; if (!get_mce_event(&evt, MCE_EVENT_RELEASE)) return; @@ -262,8 +263,20 @@ void machine_check_queue_event(void) memcpy(&local_paca->mce_info->mce_event_queue[index], &evt, sizeof(evt)); - /* Queue irq work to process this event later. */ - irq_work_queue(&mce_event_process_work); + /* + * Queue irq work to process this event later. Before + * queuing the work enable translation for non radix LPAR, + * as irq_work_queue may try to access memory outside RMO + * region. + */ + if (!radix_enabled() && firmware_has_feature(FW_FEATURE_LPAR)) { + msr = mfmsr(); + mtmsr(msr | MSR_IR | MSR_DR); + irq_work_queue(&mce_event_process_work); + mtmsr(msr); + } else { + irq_work_queue(&mce_event_process_work); + } } void mce_common_process_ue(struct pt_regs *regs, diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c index 1a998490fe60..15fb5ea1b9ea 100644 --- a/arch/powerpc/kernel/security.c +++ b/arch/powerpc/kernel/security.c @@ -263,6 +263,11 @@ static int __init handle_no_stf_barrier(char *p) early_param("no_stf_barrier", handle_no_stf_barrier); +enum stf_barrier_type stf_barrier_type_get(void) +{ + return stf_enabled_flush_types; +} + /* This is the generic flag used by other architectures */ static int __init handle_ssbd(char *p) { diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index e600764a926c..b93b87df499d 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -293,10 +293,8 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags) do_signal(current); } - if (thread_info_flags & _TIF_NOTIFY_RESUME) { + if (thread_info_flags & _TIF_NOTIFY_RESUME) tracehook_notify_resume(regs); - rseq_handle_notify_resume(NULL, regs); - } } static unsigned long get_tm_stackpointer(struct task_struct *tsk) diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index aac8c0412ff9..11741703d26e 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -340,10 +340,16 @@ static bool exception_common(int signr, struct pt_regs *regs, int code, return false; } - show_signal_msg(signr, regs, code, addr); + /* + * Must not enable interrupts even for user-mode exception, because + * this can be called from machine check, which may be a NMI or IRQ + * which don't like interrupts being enabled. Could check for + * in_hardirq || in_nmi perhaps, but there doesn't seem to be a good + * reason why _exception() should enable irqs for an exception handler, + * the handlers themselves do that directly. + */ - if (arch_irqs_disabled()) - interrupt_cond_local_irq_enable(regs); + show_signal_msg(signr, regs, code, addr); current->thread.trap_nr = code; @@ -790,24 +796,22 @@ void die_mce(const char *str, struct pt_regs *regs, long err) * do_exit() checks for in_interrupt() and panics in that case, so * exit the irq/nmi before calling die. */ - if (IS_ENABLED(CONFIG_PPC_BOOK3S_64)) - irq_exit(); - else + if (in_nmi()) nmi_exit(); + else + irq_exit(); die(str, regs, err); } /* - * BOOK3S_64 does not call this handler as a non-maskable interrupt + * BOOK3S_64 does not usually call this handler as a non-maskable interrupt * (it uses its own early real-mode handler to handle the MCE proper * and then raises irq_work to call this handler when interrupts are - * enabled). + * enabled). The only time when this is not true is if the early handler + * is unrecoverable, then it does call this directly to try to get a + * message out. */ -#ifdef CONFIG_PPC_BOOK3S_64 -DEFINE_INTERRUPT_HANDLER_ASYNC(machine_check_exception) -#else -DEFINE_INTERRUPT_HANDLER_NMI(machine_check_exception) -#endif +static void __machine_check_exception(struct pt_regs *regs) { int recover = 0; @@ -841,12 +845,19 @@ bail: /* Must die if the interrupt is not recoverable */ if (regs_is_unrecoverable(regs)) die_mce("Unrecoverable Machine check", regs, SIGBUS); +} #ifdef CONFIG_PPC_BOOK3S_64 - return; -#else - return 0; +DEFINE_INTERRUPT_HANDLER_ASYNC(machine_check_exception_async) +{ + __machine_check_exception(regs); +} #endif +DEFINE_INTERRUPT_HANDLER_NMI(machine_check_exception) +{ + __machine_check_exception(regs); + + return 0; } DEFINE_INTERRUPT_HANDLER(SMIException) /* async? */ diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 75079397c2a5..eb776d0c5d8e 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -255,13 +255,16 @@ kvm_novcpu_exit: * r3 contains the SRR1 wakeup value, SRR1 is trashed. */ _GLOBAL(idle_kvm_start_guest) - ld r4,PACAEMERGSP(r13) mfcr r5 mflr r0 - std r1,0(r4) - std r5,8(r4) - std r0,16(r4) - subi r1,r4,STACK_FRAME_OVERHEAD + std r5, 8(r1) // Save CR in caller's frame + std r0, 16(r1) // Save LR in caller's frame + // Create frame on emergency stack + ld r4, PACAEMERGSP(r13) + stdu r1, -SWITCH_FRAME_SIZE(r4) + // Switch to new frame on emergency stack + mr r1, r4 + std r3, 32(r1) // Save SRR1 wakeup value SAVE_NVGPRS(r1) /* @@ -313,6 +316,10 @@ kvm_unsplit_wakeup: kvm_secondary_got_guest: + // About to go to guest, clear saved SRR1 + li r0, 0 + std r0, 32(r1) + /* Set HSTATE_DSCR(r13) to something sensible */ ld r6, PACA_DSCR_DEFAULT(r13) std r6, HSTATE_DSCR(r13) @@ -392,13 +399,12 @@ kvm_no_guest: mfspr r4, SPRN_LPCR rlwimi r4, r3, 0, LPCR_PECE0 | LPCR_PECE1 mtspr SPRN_LPCR, r4 - /* set up r3 for return */ - mfspr r3,SPRN_SRR1 + // Return SRR1 wakeup value, or 0 if we went into the guest + ld r3, 32(r1) REST_NVGPRS(r1) - addi r1, r1, STACK_FRAME_OVERHEAD - ld r0, 16(r1) - ld r5, 8(r1) - ld r1, 0(r1) + ld r1, 0(r1) // Switch back to caller stack + ld r0, 16(r1) // Reload LR + ld r5, 8(r1) // Reload CR mtlr r0 mtcr r5 blr @@ -2536,7 +2542,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_P9_TM_HV_ASSIST) /* The following code handles the fake_suspend = 1 case */ mflr r0 std r0, PPC_LR_STKOFF(r1) - stdu r1, -PPC_MIN_STKFRM(r1) + stdu r1, -TM_FRAME_SIZE(r1) /* Turn on TM. */ mfmsr r8 @@ -2551,10 +2557,42 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_XER_SO_BUG) nop + /* + * It's possible that treclaim. may modify registers, if we have lost + * track of fake-suspend state in the guest due to it using rfscv. + * Save and restore registers in case this occurs. + */ + mfspr r3, SPRN_DSCR + mfspr r4, SPRN_XER + mfspr r5, SPRN_AMR + /* SPRN_TAR would need to be saved here if the kernel ever used it */ + mfcr r12 + SAVE_NVGPRS(r1) + SAVE_GPR(2, r1) + SAVE_GPR(3, r1) + SAVE_GPR(4, r1) + SAVE_GPR(5, r1) + stw r12, 8(r1) + std r1, HSTATE_HOST_R1(r13) + /* We have to treclaim here because that's the only way to do S->N */ li r3, TM_CAUSE_KVM_RESCHED TRECLAIM(R3) + GET_PACA(r13) + ld r1, HSTATE_HOST_R1(r13) + REST_GPR(2, r1) + REST_GPR(3, r1) + REST_GPR(4, r1) + REST_GPR(5, r1) + lwz r12, 8(r1) + REST_NVGPRS(r1) + mtspr SPRN_DSCR, r3 + mtspr SPRN_XER, r4 + mtspr SPRN_AMR, r5 + mtcr r12 + HMT_MEDIUM + /* * We were in fake suspend, so we are not going to save the * register state as the guest checkpointed state (since @@ -2582,7 +2620,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_XER_SO_BUG) std r5, VCPU_TFHAR(r9) std r6, VCPU_TFIAR(r9) - addi r1, r1, PPC_MIN_STKFRM + addi r1, r1, TM_FRAME_SIZE ld r0, PPC_LR_STKOFF(r1) mtlr r0 blr diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c index f9a3019e37b4..c5ed98823835 100644 --- a/arch/powerpc/lib/code-patching.c +++ b/arch/powerpc/lib/code-patching.c @@ -228,6 +228,11 @@ bool is_offset_in_branch_range(long offset) return (offset >= -0x2000000 && offset <= 0x1fffffc && !(offset & 0x3)); } +bool is_offset_in_cond_branch_range(long offset) +{ + return offset >= -0x8000 && offset <= 0x7fff && !(offset & 0x3); +} + /* * Helper to check if a given instruction is a conditional branch * Derived from the conditional checks in analyse_instr() @@ -280,7 +285,7 @@ int create_cond_branch(struct ppc_inst *instr, const u32 *addr, offset = offset - (unsigned long)addr; /* Check we can represent the target in the instruction format */ - if (offset < -0x8000 || offset > 0x7FFF || offset & 0x3) + if (!is_offset_in_cond_branch_range(offset)) return 1; /* Mask out the flags and target, so they don't step on each other. */ diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h index 99fad093f43e..7e9b978b768e 100644 --- a/arch/powerpc/net/bpf_jit.h +++ b/arch/powerpc/net/bpf_jit.h @@ -24,16 +24,30 @@ #define EMIT(instr) PLANT_INSTR(image, ctx->idx, instr) /* Long jump; (unconditional 'branch') */ -#define PPC_JMP(dest) EMIT(PPC_INST_BRANCH | \ - (((dest) - (ctx->idx * 4)) & 0x03fffffc)) +#define PPC_JMP(dest) \ + do { \ + long offset = (long)(dest) - (ctx->idx * 4); \ + if (!is_offset_in_branch_range(offset)) { \ + pr_err_ratelimited("Branch offset 0x%lx (@%u) out of range\n", offset, ctx->idx); \ + return -ERANGE; \ + } \ + EMIT(PPC_INST_BRANCH | (offset & 0x03fffffc)); \ + } while (0) + /* blr; (unconditional 'branch' with link) to absolute address */ #define PPC_BL_ABS(dest) EMIT(PPC_INST_BL | \ (((dest) - (unsigned long)(image + ctx->idx)) & 0x03fffffc)) /* "cond" here covers BO:BI fields. */ -#define PPC_BCC_SHORT(cond, dest) EMIT(PPC_INST_BRANCH_COND | \ - (((cond) & 0x3ff) << 16) | \ - (((dest) - (ctx->idx * 4)) & \ - 0xfffc)) +#define PPC_BCC_SHORT(cond, dest) \ + do { \ + long offset = (long)(dest) - (ctx->idx * 4); \ + if (!is_offset_in_cond_branch_range(offset)) { \ + pr_err_ratelimited("Conditional branch offset 0x%lx (@%u) out of range\n", offset, ctx->idx); \ + return -ERANGE; \ + } \ + EMIT(PPC_INST_BRANCH_COND | (((cond) & 0x3ff) << 16) | (offset & 0xfffc)); \ + } while (0) + /* Sign-extended 32-bit immediate load */ #define PPC_LI32(d, i) do { \ if ((int)(uintptr_t)(i) >= -32768 && \ @@ -78,11 +92,6 @@ #define PPC_FUNC_ADDR(d,i) do { PPC_LI32(d, i); } while(0) #endif -static inline bool is_nearbranch(int offset) -{ - return (offset < 32768) && (offset >= -32768); -} - /* * The fly in the ointment of code size changing from pass to pass is * avoided by padding the short branch case with a NOP. If code size differs @@ -91,7 +100,7 @@ static inline bool is_nearbranch(int offset) * state. */ #define PPC_BCC(cond, dest) do { \ - if (is_nearbranch((dest) - (ctx->idx * 4))) { \ + if (is_offset_in_cond_branch_range((long)(dest) - (ctx->idx * 4))) { \ PPC_BCC_SHORT(cond, dest); \ EMIT(PPC_RAW_NOP()); \ } else { \ diff --git a/arch/powerpc/net/bpf_jit64.h b/arch/powerpc/net/bpf_jit64.h index 7b713edfa7e2..b63b35e45e55 100644 --- a/arch/powerpc/net/bpf_jit64.h +++ b/arch/powerpc/net/bpf_jit64.h @@ -16,18 +16,18 @@ * with our redzone usage. * * [ prev sp ] <------------- - * [ nv gpr save area ] 6*8 | + * [ nv gpr save area ] 5*8 | * [ tail_call_cnt ] 8 | - * [ local_tmp_var ] 8 | + * [ local_tmp_var ] 16 | * fp (r31) --> [ ebpf stack space ] upto 512 | * [ frame header ] 32/112 | * sp (r1) ---> [ stack pointer ] -------------- */ /* for gpr non volatile registers BPG_REG_6 to 10 */ -#define BPF_PPC_STACK_SAVE (6*8) +#define BPF_PPC_STACK_SAVE (5*8) /* for bpf JIT code internal usage */ -#define BPF_PPC_STACK_LOCALS 16 +#define BPF_PPC_STACK_LOCALS 24 /* stack frame excluding BPF stack, ensure this is quadword aligned */ #define BPF_PPC_STACKFRAME (STACK_FRAME_MIN_SIZE + \ BPF_PPC_STACK_LOCALS + BPF_PPC_STACK_SAVE) diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index 53aefee3fe70..fcbf7a917c56 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -210,7 +210,11 @@ skip_init_ctx: /* Now build the prologue, body code & epilogue for real. */ cgctx.idx = 0; bpf_jit_build_prologue(code_base, &cgctx); - bpf_jit_build_body(fp, code_base, &cgctx, addrs, extra_pass); + if (bpf_jit_build_body(fp, code_base, &cgctx, addrs, extra_pass)) { + bpf_jit_binary_free(bpf_hdr); + fp = org_fp; + goto out_addrs; + } bpf_jit_build_epilogue(code_base, &cgctx); if (bpf_jit_enable > 1) diff --git a/arch/powerpc/net/bpf_jit_comp32.c b/arch/powerpc/net/bpf_jit_comp32.c index beb12cbc8c29..0da31d41d413 100644 --- a/arch/powerpc/net/bpf_jit_comp32.c +++ b/arch/powerpc/net/bpf_jit_comp32.c @@ -200,7 +200,7 @@ void bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, u64 fun } } -static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 out) +static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 out) { /* * By now, the eBPF program has already setup parameters in r3-r6 @@ -261,7 +261,9 @@ static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 bpf_jit_emit_common_epilogue(image, ctx); EMIT(PPC_RAW_BCTR()); + /* out: */ + return 0; } /* Assemble the body code between the prologue & epilogue */ @@ -355,7 +357,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * PPC_LI32(_R0, imm); EMIT(PPC_RAW_ADDC(dst_reg, dst_reg, _R0)); } - if (imm >= 0) + if (imm >= 0 || (BPF_OP(code) == BPF_SUB && imm == 0x80000000)) EMIT(PPC_RAW_ADDZE(dst_reg_h, dst_reg_h)); else EMIT(PPC_RAW_ADDME(dst_reg_h, dst_reg_h)); @@ -623,7 +625,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * EMIT(PPC_RAW_LI(dst_reg_h, 0)); break; case BPF_ALU | BPF_ARSH | BPF_X: /* (s32) dst >>= src */ - EMIT(PPC_RAW_SRAW(dst_reg_h, dst_reg, src_reg)); + EMIT(PPC_RAW_SRAW(dst_reg, dst_reg, src_reg)); break; case BPF_ALU64 | BPF_ARSH | BPF_X: /* (s64) dst >>= src */ bpf_set_seen_register(ctx, tmp_reg); @@ -1073,7 +1075,7 @@ cond_branch: break; case BPF_JMP32 | BPF_JSET | BPF_K: /* andi does not sign-extend the immediate */ - if (imm >= -32768 && imm < 32768) { + if (imm >= 0 && imm < 32768) { /* PPC_ANDI is _only/always_ dot-form */ EMIT(PPC_RAW_ANDI(_R0, dst_reg, imm)); } else { @@ -1090,7 +1092,9 @@ cond_branch: */ case BPF_JMP | BPF_TAIL_CALL: ctx->seen |= SEEN_TAILCALL; - bpf_jit_emit_tail_call(image, ctx, addrs[i + 1]); + ret = bpf_jit_emit_tail_call(image, ctx, addrs[i + 1]); + if (ret < 0) + return ret; break; default: @@ -1103,7 +1107,7 @@ cond_branch: return -EOPNOTSUPP; } if (BPF_CLASS(code) == BPF_ALU && !fp->aux->verifier_zext && - !insn_is_zext(&insn[i + 1])) + !insn_is_zext(&insn[i + 1]) && !(BPF_OP(code) == BPF_END && imm == 64)) EMIT(PPC_RAW_LI(dst_reg_h, 0)); } diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index b87a63dba9c8..8b5157ccfeba 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -15,6 +15,7 @@ #include <linux/if_vlan.h> #include <asm/kprobes.h> #include <linux/bpf.h> +#include <asm/security_features.h> #include "bpf_jit64.h" @@ -35,9 +36,9 @@ static inline bool bpf_has_stack_frame(struct codegen_context *ctx) * [ prev sp ] <------------- * [ ... ] | * sp (r1) ---> [ stack pointer ] -------------- - * [ nv gpr save area ] 6*8 + * [ nv gpr save area ] 5*8 * [ tail_call_cnt ] 8 - * [ local_tmp_var ] 8 + * [ local_tmp_var ] 16 * [ unused red zone ] 208 bytes protected */ static int bpf_jit_stack_local(struct codegen_context *ctx) @@ -45,12 +46,12 @@ static int bpf_jit_stack_local(struct codegen_context *ctx) if (bpf_has_stack_frame(ctx)) return STACK_FRAME_MIN_SIZE + ctx->stack_size; else - return -(BPF_PPC_STACK_SAVE + 16); + return -(BPF_PPC_STACK_SAVE + 24); } static int bpf_jit_stack_tailcallcnt(struct codegen_context *ctx) { - return bpf_jit_stack_local(ctx) + 8; + return bpf_jit_stack_local(ctx) + 16; } static int bpf_jit_stack_offsetof(struct codegen_context *ctx, int reg) @@ -206,7 +207,7 @@ void bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, u64 fun EMIT(PPC_RAW_BCTRL()); } -static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 out) +static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 out) { /* * By now, the eBPF program has already setup parameters in r3, r4 and r5 @@ -267,13 +268,38 @@ static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 bpf_jit_emit_common_epilogue(image, ctx); EMIT(PPC_RAW_BCTR()); + /* out: */ + return 0; } +/* + * We spill into the redzone always, even if the bpf program has its own stackframe. + * Offsets hardcoded based on BPF_PPC_STACK_SAVE -- see bpf_jit_stack_local() + */ +void bpf_stf_barrier(void); + +asm ( +" .global bpf_stf_barrier ;" +" bpf_stf_barrier: ;" +" std 21,-64(1) ;" +" std 22,-56(1) ;" +" sync ;" +" ld 21,-64(1) ;" +" ld 22,-56(1) ;" +" ori 31,31,0 ;" +" .rept 14 ;" +" b 1f ;" +" 1: ;" +" .endr ;" +" blr ;" +); + /* Assemble the body code between the prologue & epilogue */ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *ctx, u32 *addrs, bool extra_pass) { + enum stf_barrier_type stf_barrier = stf_barrier_type_get(); const struct bpf_insn *insn = fp->insnsi; int flen = fp->len; int i, ret; @@ -328,18 +354,25 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * EMIT(PPC_RAW_SUB(dst_reg, dst_reg, src_reg)); goto bpf_alu32_trunc; case BPF_ALU | BPF_ADD | BPF_K: /* (u32) dst += (u32) imm */ - case BPF_ALU | BPF_SUB | BPF_K: /* (u32) dst -= (u32) imm */ case BPF_ALU64 | BPF_ADD | BPF_K: /* dst += imm */ + if (!imm) { + goto bpf_alu32_trunc; + } else if (imm >= -32768 && imm < 32768) { + EMIT(PPC_RAW_ADDI(dst_reg, dst_reg, IMM_L(imm))); + } else { + PPC_LI32(b2p[TMP_REG_1], imm); + EMIT(PPC_RAW_ADD(dst_reg, dst_reg, b2p[TMP_REG_1])); + } + goto bpf_alu32_trunc; + case BPF_ALU | BPF_SUB | BPF_K: /* (u32) dst -= (u32) imm */ case BPF_ALU64 | BPF_SUB | BPF_K: /* dst -= imm */ - if (BPF_OP(code) == BPF_SUB) - imm = -imm; - if (imm) { - if (imm >= -32768 && imm < 32768) - EMIT(PPC_RAW_ADDI(dst_reg, dst_reg, IMM_L(imm))); - else { - PPC_LI32(b2p[TMP_REG_1], imm); - EMIT(PPC_RAW_ADD(dst_reg, dst_reg, b2p[TMP_REG_1])); - } + if (!imm) { + goto bpf_alu32_trunc; + } else if (imm > -32768 && imm <= 32768) { + EMIT(PPC_RAW_ADDI(dst_reg, dst_reg, IMM_L(-imm))); + } else { + PPC_LI32(b2p[TMP_REG_1], imm); + EMIT(PPC_RAW_SUB(dst_reg, dst_reg, b2p[TMP_REG_1])); } goto bpf_alu32_trunc; case BPF_ALU | BPF_MUL | BPF_X: /* (u32) dst *= (u32) src */ @@ -389,8 +422,14 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ if (imm == 0) return -EINVAL; - else if (imm == 1) - goto bpf_alu32_trunc; + if (imm == 1) { + if (BPF_OP(code) == BPF_DIV) { + goto bpf_alu32_trunc; + } else { + EMIT(PPC_RAW_LI(dst_reg, 0)); + break; + } + } PPC_LI32(b2p[TMP_REG_1], imm); switch (BPF_CLASS(code)) { @@ -631,6 +670,29 @@ emit_clear: * BPF_ST NOSPEC (speculation barrier) */ case BPF_ST | BPF_NOSPEC: + if (!security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) || + !security_ftr_enabled(SEC_FTR_STF_BARRIER)) + break; + + switch (stf_barrier) { + case STF_BARRIER_EIEIO: + EMIT(PPC_RAW_EIEIO() | 0x02000000); + break; + case STF_BARRIER_SYNC_ORI: + EMIT(PPC_RAW_SYNC()); + EMIT(PPC_RAW_LD(b2p[TMP_REG_1], _R13, 0)); + EMIT(PPC_RAW_ORI(_R31, _R31, 0)); + break; + case STF_BARRIER_FALLBACK: + EMIT(PPC_RAW_MFLR(b2p[TMP_REG_1])); + PPC_LI64(12, dereference_kernel_function_descriptor(bpf_stf_barrier)); + EMIT(PPC_RAW_MTCTR(12)); + EMIT(PPC_RAW_BCTRL()); + EMIT(PPC_RAW_MTLR(b2p[TMP_REG_1])); + break; + case STF_BARRIER_NONE: + break; + } break; /* @@ -993,7 +1055,9 @@ cond_branch: */ case BPF_JMP | BPF_TAIL_CALL: ctx->seen |= SEEN_TAILCALL; - bpf_jit_emit_tail_call(image, ctx, addrs[i + 1]); + ret = bpf_jit_emit_tail_call(image, ctx, addrs[i + 1]); + if (ret < 0) + return ret; break; default: diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index bc15200852b7..09fafcf2d3a0 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -867,6 +867,10 @@ static int __init eeh_pseries_init(void) if (is_kdump_kernel() || reset_devices) { pr_info("Issue PHB reset ...\n"); list_for_each_entry(phb, &hose_list, list_node) { + // Skip if the slot is empty + if (list_empty(&PCI_DN(phb->dn)->child_list)) + continue; + pdn = list_first_entry(&PCI_DN(phb->dn)->child_list, struct pci_dn, list); config_addr = pseries_eeh_get_pe_config_addr(pdn); diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c index 1b305e411862..8627362f613e 100644 --- a/arch/powerpc/platforms/pseries/msi.c +++ b/arch/powerpc/platforms/pseries/msi.c @@ -507,12 +507,27 @@ static void pseries_msi_unmask(struct irq_data *d) irq_chip_unmask_parent(d); } +static void pseries_msi_write_msg(struct irq_data *data, struct msi_msg *msg) +{ + struct msi_desc *entry = irq_data_get_msi_desc(data); + + /* + * Do not update the MSIx vector table. It's not strictly necessary + * because the table is initialized by the underlying hypervisor, PowerVM + * or QEMU/KVM. However, if the MSIx vector entry is cleared, any further + * activation will fail. This can happen in some drivers (eg. IPR) which + * deactivate an IRQ used for testing MSI support. + */ + entry->msg = *msg; +} + static struct irq_chip pseries_pci_msi_irq_chip = { .name = "pSeries-PCI-MSI", .irq_shutdown = pseries_msi_shutdown, .irq_mask = pseries_msi_mask, .irq_unmask = pseries_msi_unmask, .irq_eoi = irq_chip_eoi_parent, + .irq_write_msi_msg = pseries_msi_write_msg, }; static struct msi_domain_info pseries_msi_domain_info = { diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c index 5c1a157a83b8..244a727c6ba4 100644 --- a/arch/powerpc/sysdev/xics/xics-common.c +++ b/arch/powerpc/sysdev/xics/xics-common.c @@ -348,9 +348,9 @@ static int xics_host_map(struct irq_domain *domain, unsigned int virq, if (xics_ics->check(xics_ics, hwirq)) return -EINVAL; - /* No chip data for the XICS domain */ + /* Let the ICS be the chip data for the XICS domain. For ICS native */ irq_domain_set_info(domain, virq, hwirq, xics_ics->chip, - NULL, handle_fasteoi_irq, NULL, NULL); + xics_ics, handle_fasteoi_irq, NULL, NULL); return 0; } diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c index c732ce5a3e1a..c5d75c02ad8b 100644 --- a/arch/powerpc/sysdev/xive/common.c +++ b/arch/powerpc/sysdev/xive/common.c @@ -945,7 +945,8 @@ static int xive_get_irqchip_state(struct irq_data *data, * interrupt to be inactive in that case. */ *state = (pq != XIVE_ESB_INVALID) && !xd->stale_p && - (xd->saved_p || !!(pq & XIVE_ESB_VAL_P)); + (xd->saved_p || (!!(pq & XIVE_ESB_VAL_P) && + !irqd_irq_disabled(data))); return 0; default: return -EINVAL; |