diff options
Diffstat (limited to 'arch')
42 files changed, 312 insertions, 140 deletions
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 232b439cbaf3..ff8f4511df71 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -75,6 +75,7 @@ #define ARM_CPU_PART_CORTEX_A77 0xD0D #define ARM_CPU_PART_NEOVERSE_V1 0xD40 #define ARM_CPU_PART_CORTEX_A78 0xD41 +#define ARM_CPU_PART_CORTEX_A78AE 0xD42 #define ARM_CPU_PART_CORTEX_X1 0xD44 #define ARM_CPU_PART_CORTEX_A510 0xD46 #define ARM_CPU_PART_CORTEX_A710 0xD47 @@ -130,6 +131,7 @@ #define MIDR_CORTEX_A77 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A77) #define MIDR_NEOVERSE_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V1) #define MIDR_CORTEX_A78 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78) +#define MIDR_CORTEX_A78AE MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78AE) #define MIDR_CORTEX_X1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1) #define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510) #define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710) diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h index 7f3c87f7a0ce..c31be7eda9df 100644 --- a/arch/arm64/include/asm/el2_setup.h +++ b/arch/arm64/include/asm/el2_setup.h @@ -107,7 +107,7 @@ isb // Make sure SRE is now set mrs_s x0, SYS_ICC_SRE_EL2 // Read SRE back, tbz x0, #0, .Lskip_gicv3_\@ // and check that it sticks - msr_s SYS_ICH_HCR_EL2, xzr // Reset ICC_HCR_EL2 to defaults + msr_s SYS_ICH_HCR_EL2, xzr // Reset ICH_HCR_EL2 to defaults .Lskip_gicv3_\@: .endm diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c index 3fb79b76e9d9..7bbf5104b7b7 100644 --- a/arch/arm64/kernel/alternative.c +++ b/arch/arm64/kernel/alternative.c @@ -42,7 +42,7 @@ bool alternative_is_applied(u16 cpufeature) /* * Check if the target PC is within an alternative block. */ -static bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc) +static __always_inline bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc) { unsigned long replptr = (unsigned long)ALT_REPL_PTR(alt); return !(pc >= replptr && pc <= (replptr + alt->alt_len)); @@ -50,7 +50,7 @@ static bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc) #define align_down(x, a) ((unsigned long)(x) & ~(((unsigned long)(a)) - 1)) -static u32 get_alt_insn(struct alt_instr *alt, __le32 *insnptr, __le32 *altinsnptr) +static __always_inline u32 get_alt_insn(struct alt_instr *alt, __le32 *insnptr, __le32 *altinsnptr) { u32 insn; @@ -95,7 +95,7 @@ static u32 get_alt_insn(struct alt_instr *alt, __le32 *insnptr, __le32 *altinsnp return insn; } -static void patch_alternative(struct alt_instr *alt, +static noinstr void patch_alternative(struct alt_instr *alt, __le32 *origptr, __le32 *updptr, int nr_inst) { __le32 *replptr; diff --git a/arch/arm64/kernel/elfcore.c b/arch/arm64/kernel/elfcore.c index 3ed39c61a510..2b3f3d0544b9 100644 --- a/arch/arm64/kernel/elfcore.c +++ b/arch/arm64/kernel/elfcore.c @@ -8,16 +8,9 @@ #include <asm/cpufeature.h> #include <asm/mte.h> -#ifndef VMA_ITERATOR -#define VMA_ITERATOR(name, mm, addr) \ - struct mm_struct *name = mm -#define for_each_vma(vmi, vma) \ - for (vma = vmi->mmap; vma; vma = vma->vm_next) -#endif - -#define for_each_mte_vma(vmi, vma) \ +#define for_each_mte_vma(tsk, vma) \ if (system_supports_mte()) \ - for_each_vma(vmi, vma) \ + for (vma = tsk->mm->mmap; vma; vma = vma->vm_next) \ if (vma->vm_flags & VM_MTE) static unsigned long mte_vma_tag_dump_size(struct vm_area_struct *vma) @@ -32,10 +25,11 @@ static unsigned long mte_vma_tag_dump_size(struct vm_area_struct *vma) static int mte_dump_tag_range(struct coredump_params *cprm, unsigned long start, unsigned long end) { + int ret = 1; unsigned long addr; + void *tags = NULL; for (addr = start; addr < end; addr += PAGE_SIZE) { - char tags[MTE_PAGE_TAG_STORAGE]; struct page *page = get_dump_page(addr); /* @@ -59,22 +53,36 @@ static int mte_dump_tag_range(struct coredump_params *cprm, continue; } + if (!tags) { + tags = mte_allocate_tag_storage(); + if (!tags) { + put_page(page); + ret = 0; + break; + } + } + mte_save_page_tags(page_address(page), tags); put_page(page); - if (!dump_emit(cprm, tags, MTE_PAGE_TAG_STORAGE)) - return 0; + if (!dump_emit(cprm, tags, MTE_PAGE_TAG_STORAGE)) { + mte_free_tag_storage(tags); + ret = 0; + break; + } } - return 1; + if (tags) + mte_free_tag_storage(tags); + + return ret; } Elf_Half elf_core_extra_phdrs(void) { struct vm_area_struct *vma; int vma_count = 0; - VMA_ITERATOR(vmi, current->mm, 0); - for_each_mte_vma(vmi, vma) + for_each_mte_vma(current, vma) vma_count++; return vma_count; @@ -83,9 +91,8 @@ Elf_Half elf_core_extra_phdrs(void) int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset) { struct vm_area_struct *vma; - VMA_ITERATOR(vmi, current->mm, 0); - for_each_mte_vma(vmi, vma) { + for_each_mte_vma(current, vma) { struct elf_phdr phdr; phdr.p_type = PT_ARM_MEMTAG_MTE; @@ -109,9 +116,8 @@ size_t elf_core_extra_data_size(void) { struct vm_area_struct *vma; size_t data_size = 0; - VMA_ITERATOR(vmi, current->mm, 0); - for_each_mte_vma(vmi, vma) + for_each_mte_vma(current, vma) data_size += mte_vma_tag_dump_size(vma); return data_size; @@ -120,9 +126,8 @@ size_t elf_core_extra_data_size(void) int elf_core_write_extra_data(struct coredump_params *cprm) { struct vm_area_struct *vma; - VMA_ITERATOR(vmi, current->mm, 0); - for_each_mte_vma(vmi, vma) { + for_each_mte_vma(current, vma) { if (vma->vm_flags & VM_DONTDUMP) continue; diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index 712e97c03e54..cd868084e724 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -701,7 +701,7 @@ NOKPROBE_SYMBOL(breakpoint_handler); * addresses. There is no straight-forward way, short of disassembling the * offending instruction, to map that address back to the watchpoint. This * function computes the distance of the memory access from the watchpoint as a - * heuristic for the likelyhood that a given access triggered the watchpoint. + * heuristic for the likelihood that a given access triggered the watchpoint. * * See Section D2.10.5 "Determining the memory location that caused a Watchpoint * exception" of ARMv8 Architecture Reference Manual for details. diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c index e53493d8b208..a3d0494f25a9 100644 --- a/arch/arm64/kernel/module-plts.c +++ b/arch/arm64/kernel/module-plts.c @@ -220,7 +220,7 @@ static unsigned int count_plts(Elf64_Sym *syms, Elf64_Rela *rela, int num, * increasing the section's alignment so that the * resulting address of this instruction is guaranteed * to equal the offset in that particular bit (as well - * as all less signficant bits). This ensures that the + * as all less significant bits). This ensures that the * address modulo 4 KB != 0xfff8 or 0xfffc (which would * have all ones in bits [11:3]) */ diff --git a/arch/arm64/kernel/patching.c b/arch/arm64/kernel/patching.c index 771f543464e0..33e0fabc0b79 100644 --- a/arch/arm64/kernel/patching.c +++ b/arch/arm64/kernel/patching.c @@ -117,8 +117,8 @@ static int __kprobes aarch64_insn_patch_text_cb(void *arg) int i, ret = 0; struct aarch64_insn_patch *pp = arg; - /* The first CPU becomes master */ - if (atomic_inc_return(&pp->cpu_count) == 1) { + /* The last CPU becomes master */ + if (atomic_inc_return(&pp->cpu_count) == num_online_cpus()) { for (i = 0; ret == 0 && i < pp->insn_cnt; i++) ret = aarch64_insn_patch_text_nosync(pp->text_addrs[i], pp->new_insns[i]); diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c index 5777929d35bf..40be3a7c2c53 100644 --- a/arch/arm64/kernel/proton-pack.c +++ b/arch/arm64/kernel/proton-pack.c @@ -853,6 +853,7 @@ u8 spectre_bhb_loop_affected(int scope) if (scope == SCOPE_LOCAL_CPU) { static const struct midr_range spectre_bhb_k32_list[] = { MIDR_ALL_VERSIONS(MIDR_CORTEX_A78), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A78AE), MIDR_ALL_VERSIONS(MIDR_CORTEX_A78C), MIDR_ALL_VERSIONS(MIDR_CORTEX_X1), MIDR_ALL_VERSIONS(MIDR_CORTEX_A710), diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 27df5c1e6baa..3b46041f2b97 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -234,6 +234,7 @@ asmlinkage notrace void secondary_start_kernel(void) * Log the CPU info before it is marked online and might get read. */ cpuinfo_store_cpu(); + store_cpu_topology(cpu); /* * Enable GIC and timers. @@ -242,7 +243,6 @@ asmlinkage notrace void secondary_start_kernel(void) ipi_setup(cpu); - store_cpu_topology(cpu); numa_add_cpu(cpu); /* diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c index 19ee7c33769d..2b0887e58a7c 100644 --- a/arch/arm64/kernel/suspend.c +++ b/arch/arm64/kernel/suspend.c @@ -140,7 +140,7 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) /* * Restore pstate flags. OS lock and mdscr have been already * restored, so from this point onwards, debugging is fully - * renabled if it was enabled when core started shutdown. + * reenabled if it was enabled when core started shutdown. */ local_daif_restore(flags); diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 8ac25f19084e..1e7b1550e2fc 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -73,7 +73,7 @@ EXPORT_SYMBOL(memstart_addr); * In this scheme a comparatively quicker boot is observed. * * If ZONE_DMA configs are defined, crash kernel memory reservation - * is delayed until DMA zone memory range size initilazation performed in + * is delayed until DMA zone memory range size initialization performed in * zone_sizes_init(). The defer is necessary to steer clear of DMA zone * memory range to avoid overlap allocation. So crash kernel memory boundaries * are not known when mapping all bank memory ranges, which otherwise means @@ -81,7 +81,7 @@ EXPORT_SYMBOL(memstart_addr); * so page-granularity mappings are created for the entire memory range. * Hence a slightly slower boot is observed. * - * Note: Page-granularity mapppings are necessary for crash kernel memory + * Note: Page-granularity mappings are necessary for crash kernel memory * range for shrinking its size via /sys/kernel/kexec_crash_size interface. */ #if IS_ENABLED(CONFIG_ZONE_DMA) || IS_ENABLED(CONFIG_ZONE_DMA32) diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index 827038a33064..4def2bd17b9b 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -16,18 +16,6 @@ #include <asm/ppc-opcode.h> #include <asm/pte-walk.h> -#ifdef CONFIG_PPC_PSERIES -static inline bool kvmhv_on_pseries(void) -{ - return !cpu_has_feature(CPU_FTR_HVMODE); -} -#else -static inline bool kvmhv_on_pseries(void) -{ - return false; -} -#endif - /* * Structure for a nested guest, that is, for a guest that is managed by * one of our guests. diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index c583d0c37f31..838d4cb460b7 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -586,6 +586,18 @@ static inline bool kvm_hv_mode_active(void) { return false; } #endif +#ifdef CONFIG_PPC_PSERIES +static inline bool kvmhv_on_pseries(void) +{ + return !cpu_has_feature(CPU_FTR_HVMODE); +} +#else +static inline bool kvmhv_on_pseries(void) +{ + return false; +} +#endif + #ifdef CONFIG_KVM_XICS static inline int kvmppc_xics_enabled(struct kvm_vcpu *vcpu) { diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h index 254687258f42..f2c5c26869f1 100644 --- a/arch/powerpc/include/asm/page.h +++ b/arch/powerpc/include/asm/page.h @@ -132,7 +132,11 @@ static inline bool pfn_valid(unsigned long pfn) #define virt_to_page(kaddr) pfn_to_page(virt_to_pfn(kaddr)) #define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT) -#define virt_addr_valid(kaddr) pfn_valid(virt_to_pfn(kaddr)) +#define virt_addr_valid(vaddr) ({ \ + unsigned long _addr = (unsigned long)vaddr; \ + _addr >= PAGE_OFFSET && _addr < (unsigned long)high_memory && \ + pfn_valid(virt_to_pfn(_addr)); \ +}) /* * On Book-E parts we need __va to parse the device tree and we can't diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h index 049ca26893e6..8fa37ef5da4d 100644 --- a/arch/powerpc/include/asm/setup.h +++ b/arch/powerpc/include/asm/setup.h @@ -28,11 +28,13 @@ void setup_panic(void); #define ARCH_PANIC_TIMEOUT 180 #ifdef CONFIG_PPC_PSERIES +extern bool pseries_reloc_on_exception(void); extern bool pseries_enable_reloc_on_exc(void); extern void pseries_disable_reloc_on_exc(void); extern void pseries_big_endian_exceptions(void); void __init pseries_little_endian_exceptions(void); #else +static inline bool pseries_reloc_on_exception(void) { return false; } static inline bool pseries_enable_reloc_on_exc(void) { return false; } static inline void pseries_disable_reloc_on_exc(void) {} static inline void pseries_big_endian_exceptions(void) {} diff --git a/arch/powerpc/include/asm/static_call.h b/arch/powerpc/include/asm/static_call.h index 0a0bc79bd1fa..de1018cc522b 100644 --- a/arch/powerpc/include/asm/static_call.h +++ b/arch/powerpc/include/asm/static_call.h @@ -24,5 +24,6 @@ #define ARCH_DEFINE_STATIC_CALL_TRAMP(name, func) __PPC_SCT(name, "b " #func) #define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) __PPC_SCT(name, "blr") +#define ARCH_DEFINE_STATIC_CALL_RET0_TRAMP(name) __PPC_SCT(name, "b .+20") #endif /* _ASM_POWERPC_STATIC_CALL_H */ diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 55caeee37c08..b66dd6f775a4 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -809,6 +809,10 @@ __start_interrupts: * - MSR_EE|MSR_RI is clear (no reentrant exceptions) * - Standard kernel environment is set up (stack, paca, etc) * + * KVM: + * These interrupts do not elevate HV 0->1, so HV is not involved. PR KVM + * ensures that FSCR[SCV] is disabled whenever it has to force AIL off. + * * Call convention: * * syscall register convention is in Documentation/powerpc/syscall64-abi.rst diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index e547066a06aa..a96f05063bc9 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -196,6 +196,34 @@ static void __init configure_exceptions(void) /* Under a PAPR hypervisor, we need hypercalls */ if (firmware_has_feature(FW_FEATURE_SET_MODE)) { + /* + * - PR KVM does not support AIL mode interrupts in the host + * while a PR guest is running. + * + * - SCV system call interrupt vectors are only implemented for + * AIL mode interrupts. + * + * - On pseries, AIL mode can only be enabled and disabled + * system-wide so when a PR VM is created on a pseries host, + * all CPUs of the host are set to AIL=0 mode. + * + * - Therefore host CPUs must not execute scv while a PR VM + * exists. + * + * - SCV support can not be disabled dynamically because the + * feature is advertised to host userspace. Disabling the + * facility and emulating it would be possible but is not + * implemented. + * + * - So SCV support is blanket disabled if PR KVM could possibly + * run. That is, PR support compiled in, booting on pseries + * with hash MMU. + */ + if (IS_ENABLED(CONFIG_KVM_BOOK3S_PR_POSSIBLE) && !radix_enabled()) { + init_task.thread.fscr &= ~FSCR_SCV; + cur_cpu_spec->cpu_user_features2 &= ~PPC_FEATURE2_SCV; + } + /* Enable AIL if possible */ if (!pseries_enable_reloc_on_exc()) { init_task.thread.fscr &= ~FSCR_SCV; diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index 18e58085447c..ddd88179110a 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -112,12 +112,21 @@ config KVM_BOOK3S_64_PR guest in user mode (problem state) and emulating all privileged instructions and registers. + This is only available for hash MMU mode and only supports + guests that use hash MMU mode. + This is not as fast as using hypervisor mode, but works on machines where hypervisor mode is not available or not usable, and can emulate processors that are different from the host processor, including emulating 32-bit processors on a 64-bit host. + Selecting this option will cause the SCV facility to be + disabled when the kernel is booted on the pseries platform in + hash MMU mode (regardless of PR VMs running). When any PR VMs + are running, "AIL" mode is disabled which may slow interrupts + and system calls on the host. + config KVM_BOOK3S_HV_EXIT_TIMING bool "Detailed timing for hypervisor real-mode code" depends on KVM_BOOK3S_HV_POSSIBLE && DEBUG_FS diff --git a/arch/powerpc/kvm/book3s_64_entry.S b/arch/powerpc/kvm/book3s_64_entry.S index 05e003eb5d90..e42d1c609e47 100644 --- a/arch/powerpc/kvm/book3s_64_entry.S +++ b/arch/powerpc/kvm/book3s_64_entry.S @@ -414,10 +414,16 @@ END_FTR_SECTION_IFSET(CPU_FTR_DAWR1) */ ld r10,HSTATE_SCRATCH0(r13) cmpwi r10,BOOK3S_INTERRUPT_MACHINE_CHECK - beq machine_check_common + beq .Lcall_machine_check_common cmpwi r10,BOOK3S_INTERRUPT_SYSTEM_RESET - beq system_reset_common + beq .Lcall_system_reset_common b . + +.Lcall_machine_check_common: + b machine_check_common + +.Lcall_system_reset_common: + b system_reset_common #endif diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index c886557638a1..6fa518f6501d 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -225,6 +225,13 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu) int cpu; struct rcuwait *waitp; + /* + * rcuwait_wake_up contains smp_mb() which orders prior stores that + * create pending work vs below loads of cpu fields. The other side + * is the barrier in vcpu run that orders setting the cpu fields vs + * testing for pending work. + */ + waitp = kvm_arch_vcpu_get_wait(vcpu); if (rcuwait_wake_up(waitp)) ++vcpu->stat.generic.halt_wakeup; @@ -1089,7 +1096,7 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) break; } tvcpu->arch.prodded = 1; - smp_mb(); + smp_mb(); /* This orders prodded store vs ceded load */ if (tvcpu->arch.ceded) kvmppc_fast_vcpu_kick_hv(tvcpu); break; @@ -3766,6 +3773,14 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) pvc = core_info.vc[sub]; pvc->pcpu = pcpu + thr; for_each_runnable_thread(i, vcpu, pvc) { + /* + * XXX: is kvmppc_start_thread called too late here? + * It updates vcpu->cpu and vcpu->arch.thread_cpu + * which are used by kvmppc_fast_vcpu_kick_hv(), but + * kick is called after new exceptions become available + * and exceptions are checked earlier than here, by + * kvmppc_core_prepare_to_enter. + */ kvmppc_start_thread(vcpu, pvc); kvmppc_create_dtl_entry(vcpu, pvc); trace_kvm_guest_enter(vcpu); @@ -4487,6 +4502,21 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, if (need_resched() || !kvm->arch.mmu_ready) goto out; + vcpu->cpu = pcpu; + vcpu->arch.thread_cpu = pcpu; + vc->pcpu = pcpu; + local_paca->kvm_hstate.kvm_vcpu = vcpu; + local_paca->kvm_hstate.ptid = 0; + local_paca->kvm_hstate.fake_suspend = 0; + + /* + * Orders set cpu/thread_cpu vs testing for pending interrupts and + * doorbells below. The other side is when these fields are set vs + * kvmppc_fast_vcpu_kick_hv reading the cpu/thread_cpu fields to + * kick a vCPU to notice the pending interrupt. + */ + smp_mb(); + if (!nested) { kvmppc_core_prepare_to_enter(vcpu); if (test_bit(BOOK3S_IRQPRIO_EXTERNAL, @@ -4506,13 +4536,6 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, tb = mftb(); - vcpu->cpu = pcpu; - vcpu->arch.thread_cpu = pcpu; - vc->pcpu = pcpu; - local_paca->kvm_hstate.kvm_vcpu = vcpu; - local_paca->kvm_hstate.ptid = 0; - local_paca->kvm_hstate.fake_suspend = 0; - __kvmppc_create_dtl_entry(vcpu, pcpu, tb + vc->tb_offset, 0); trace_kvm_guest_enter(vcpu); @@ -4614,6 +4637,8 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, run->exit_reason = KVM_EXIT_INTR; vcpu->arch.ret = -EINTR; out: + vcpu->cpu = -1; + vcpu->arch.thread_cpu = -1; powerpc_local_irq_pmu_restore(flags); preempt_enable(); goto done; diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index 34a801c3604a..7bf9e6ca5c2d 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -137,12 +137,15 @@ static void kvmppc_core_vcpu_load_pr(struct kvm_vcpu *vcpu, int cpu) svcpu->slb_max = to_book3s(vcpu)->slb_shadow_max; svcpu->in_use = 0; svcpu_put(svcpu); -#endif /* Disable AIL if supported */ - if (cpu_has_feature(CPU_FTR_HVMODE) && - cpu_has_feature(CPU_FTR_ARCH_207S)) - mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~LPCR_AIL); + if (cpu_has_feature(CPU_FTR_HVMODE)) { + if (cpu_has_feature(CPU_FTR_ARCH_207S)) + mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~LPCR_AIL); + if (cpu_has_feature(CPU_FTR_ARCH_300) && (current->thread.fscr & FSCR_SCV)) + mtspr(SPRN_FSCR, mfspr(SPRN_FSCR) & ~FSCR_SCV); + } +#endif vcpu->cpu = smp_processor_id(); #ifdef CONFIG_PPC_BOOK3S_32 @@ -165,6 +168,14 @@ static void kvmppc_core_vcpu_put_pr(struct kvm_vcpu *vcpu) memcpy(to_book3s(vcpu)->slb_shadow, svcpu->slb, sizeof(svcpu->slb)); to_book3s(vcpu)->slb_shadow_max = svcpu->slb_max; svcpu_put(svcpu); + + /* Enable AIL if supported */ + if (cpu_has_feature(CPU_FTR_HVMODE)) { + if (cpu_has_feature(CPU_FTR_ARCH_207S)) + mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) | LPCR_AIL_3); + if (cpu_has_feature(CPU_FTR_ARCH_300) && (current->thread.fscr & FSCR_SCV)) + mtspr(SPRN_FSCR, mfspr(SPRN_FSCR) | FSCR_SCV); + } #endif if (kvmppc_is_split_real(vcpu)) @@ -174,11 +185,6 @@ static void kvmppc_core_vcpu_put_pr(struct kvm_vcpu *vcpu) kvmppc_giveup_fac(vcpu, FSCR_TAR_LG); kvmppc_save_tm_pr(vcpu); - /* Enable AIL if supported */ - if (cpu_has_feature(CPU_FTR_HVMODE) && - cpu_has_feature(CPU_FTR_ARCH_207S)) - mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) | LPCR_AIL_3); - vcpu->cpu = -1; } @@ -1037,6 +1043,8 @@ static int kvmppc_handle_fac(struct kvm_vcpu *vcpu, ulong fac) void kvmppc_set_fscr(struct kvm_vcpu *vcpu, u64 fscr) { + if (fscr & FSCR_SCV) + fscr &= ~FSCR_SCV; /* SCV must not be enabled */ if ((vcpu->arch.fscr & FSCR_TAR) && !(fscr & FSCR_TAR)) { /* TAR got dropped, drop it in shadow too */ kvmppc_giveup_fac(vcpu, FSCR_TAR_LG); diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c index 1f10e7dfcdd0..dc4f51ac84bc 100644 --- a/arch/powerpc/kvm/book3s_pr_papr.c +++ b/arch/powerpc/kvm/book3s_pr_papr.c @@ -281,6 +281,22 @@ static int kvmppc_h_pr_logical_ci_store(struct kvm_vcpu *vcpu) return EMULATE_DONE; } +static int kvmppc_h_pr_set_mode(struct kvm_vcpu *vcpu) +{ + unsigned long mflags = kvmppc_get_gpr(vcpu, 4); + unsigned long resource = kvmppc_get_gpr(vcpu, 5); + + if (resource == H_SET_MODE_RESOURCE_ADDR_TRANS_MODE) { + /* KVM PR does not provide AIL!=0 to guests */ + if (mflags == 0) + kvmppc_set_gpr(vcpu, 3, H_SUCCESS); + else + kvmppc_set_gpr(vcpu, 3, H_UNSUPPORTED_FLAG_START - 63); + return EMULATE_DONE; + } + return EMULATE_FAIL; +} + #ifdef CONFIG_SPAPR_TCE_IOMMU static int kvmppc_h_pr_put_tce(struct kvm_vcpu *vcpu) { @@ -384,6 +400,8 @@ int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd) return kvmppc_h_pr_logical_ci_load(vcpu); case H_LOGICAL_CI_STORE: return kvmppc_h_pr_logical_ci_store(vcpu); + case H_SET_MODE: + return kvmppc_h_pr_set_mode(vcpu); case H_XIRR: case H_CPPR: case H_EOI: @@ -421,6 +439,7 @@ int kvmppc_hcall_impl_pr(unsigned long cmd) case H_CEDE: case H_LOGICAL_CI_LOAD: case H_LOGICAL_CI_STORE: + case H_SET_MODE: #ifdef CONFIG_KVM_XICS case H_XIRR: case H_CPPR: @@ -447,6 +466,7 @@ static unsigned int default_hcall_list[] = { H_BULK_REMOVE, H_PUT_TCE, H_CEDE, + H_SET_MODE, #ifdef CONFIG_KVM_XICS H_XIRR, H_CPPR, diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 9772b176e406..875c30c12db0 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -705,6 +705,23 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = 1; break; #endif + case KVM_CAP_PPC_AIL_MODE_3: + r = 0; + /* + * KVM PR, POWER7, and some POWER9s don't support AIL=3 mode. + * The POWER9s can support it if the guest runs in hash mode, + * but QEMU doesn't necessarily query the capability in time. + */ + if (hv_enabled) { + if (kvmhv_on_pseries()) { + if (pseries_reloc_on_exception()) + r = 1; + } else if (cpu_has_feature(CPU_FTR_ARCH_207S) && + !cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG)) { + r = 1; + } + } + break; default: r = 0; break; diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 8e301cd8925b..4d221d033804 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -255,7 +255,7 @@ void __init mem_init(void) #endif high_memory = (void *) __va(max_low_pfn * PAGE_SIZE); - set_max_mapnr(max_low_pfn); + set_max_mapnr(max_pfn); kasan_late_init(); diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index b9b7fefbb64b..13022d734951 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -1436,7 +1436,7 @@ int find_and_online_cpu_nid(int cpu) if (new_nid < 0 || !node_possible(new_nid)) new_nid = first_online_node; - if (NODE_DATA(new_nid) == NULL) { + if (!node_online(new_nid)) { #ifdef CONFIG_MEMORY_HOTPLUG /* * Need to ensure that NODE_DATA is initialized for a node from diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 069d7b3bb142..955ff8aa1644 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -353,6 +353,14 @@ static void pseries_lpar_idle(void) pseries_idle_epilog(); } +static bool pseries_reloc_on_exception_enabled; + +bool pseries_reloc_on_exception(void) +{ + return pseries_reloc_on_exception_enabled; +} +EXPORT_SYMBOL_GPL(pseries_reloc_on_exception); + /* * Enable relocation on during exceptions. This has partition wide scope and * may take a while to complete, if it takes longer than one second we will @@ -377,6 +385,7 @@ bool pseries_enable_reloc_on_exc(void) " on exceptions: %ld\n", rc); return false; } + pseries_reloc_on_exception_enabled = true; return true; } @@ -404,7 +413,9 @@ void pseries_disable_reloc_on_exc(void) break; mdelay(get_longbusy_msecs(rc)); } - if (rc != H_SUCCESS) + if (rc == H_SUCCESS) + pseries_reloc_on_exception_enabled = false; + else pr_warn("Warning: Failed to disable relocation on exceptions: %ld\n", rc); } diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index e88791b420ee..fc7f458eb3de 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -302,7 +302,7 @@ static struct extra_reg intel_spr_extra_regs[] __read_mostly = { INTEL_UEVENT_EXTRA_REG(0x012a, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0), INTEL_UEVENT_EXTRA_REG(0x012b, MSR_OFFCORE_RSP_1, 0x3fffffffffull, RSP_1), INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd), - INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff17, FE), + INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff1f, FE), INTEL_UEVENT_EXTRA_REG(0x40ad, MSR_PEBS_FRONTEND, 0x7, FE), INTEL_UEVENT_EXTRA_REG(0x04c2, MSR_PEBS_FRONTEND, 0x8, FE), EVENT_EXTRA_END @@ -5536,7 +5536,11 @@ static void intel_pmu_check_event_constraints(struct event_constraint *event_con /* Disabled fixed counters which are not in CPUID */ c->idxmsk64 &= intel_ctrl; - if (c->idxmsk64 != INTEL_PMC_MSK_FIXED_REF_CYCLES) + /* + * Don't extend the pseudo-encoding to the + * generic counters + */ + if (!use_fixed_pseudo_encoding(c->code)) c->idxmsk64 |= (1ULL << num_counters) - 1; } c->idxmsk64 &= @@ -6212,6 +6216,7 @@ __init int intel_pmu_init(void) case INTEL_FAM6_ALDERLAKE: case INTEL_FAM6_ALDERLAKE_L: + case INTEL_FAM6_RAPTORLAKE: /* * Alder Lake has 2 types of CPU, core and atom. * diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index c6262b154c3a..5d7762288a24 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -40,7 +40,7 @@ * Model specific counters: * MSR_CORE_C1_RES: CORE C1 Residency Counter * perf code: 0x00 - * Available model: SLM,AMT,GLM,CNL,ICX,TNT,ADL + * Available model: SLM,AMT,GLM,CNL,ICX,TNT,ADL,RPL * Scope: Core (each processor core has a MSR) * MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter * perf code: 0x01 @@ -51,49 +51,50 @@ * perf code: 0x02 * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW, * SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX, - * TGL,TNT,RKL,ADL + * TGL,TNT,RKL,ADL,RPL * Scope: Core * MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter * perf code: 0x03 * Available model: SNB,IVB,HSW,BDW,SKL,CNL,KBL,CML, - * ICL,TGL,RKL,ADL + * ICL,TGL,RKL,ADL,RPL * Scope: Core * MSR_PKG_C2_RESIDENCY: Package C2 Residency Counter. * perf code: 0x00 * Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL, - * KBL,CML,ICL,ICX,TGL,TNT,RKL,ADL + * KBL,CML,ICL,ICX,TGL,TNT,RKL,ADL, + * RPL * Scope: Package (physical package) * MSR_PKG_C3_RESIDENCY: Package C3 Residency Counter. * perf code: 0x01 * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL, * GLM,CNL,KBL,CML,ICL,TGL,TNT,RKL, - * ADL + * ADL,RPL * Scope: Package (physical package) * MSR_PKG_C6_RESIDENCY: Package C6 Residency Counter. * perf code: 0x02 * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW, * SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX, - * TGL,TNT,RKL,ADL + * TGL,TNT,RKL,ADL,RPL * Scope: Package (physical package) * MSR_PKG_C7_RESIDENCY: Package C7 Residency Counter. * perf code: 0x03 * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,CNL, - * KBL,CML,ICL,TGL,RKL,ADL + * KBL,CML,ICL,TGL,RKL,ADL,RPL * Scope: Package (physical package) * MSR_PKG_C8_RESIDENCY: Package C8 Residency Counter. * perf code: 0x04 * Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL, - * ADL + * ADL,RPL * Scope: Package (physical package) * MSR_PKG_C9_RESIDENCY: Package C9 Residency Counter. * perf code: 0x05 * Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL, - * ADL + * ADL,RPL * Scope: Package (physical package) * MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter. * perf code: 0x06 * Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL, - * TNT,RKL,ADL + * TNT,RKL,ADL,RPL * Scope: Package (physical package) * */ @@ -680,6 +681,7 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(ROCKETLAKE, &icl_cstates), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, &adl_cstates), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &adl_cstates), + X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &adl_cstates), { }, }; MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match); diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index e497da9bf427..7695dcae280e 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -1828,6 +1828,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(ROCKETLAKE, &rkl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, &adl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &adl_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &adl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &spr_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D, &snr_uncore_init), {}, diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index f698a55bde81..4262351f52b6 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -79,6 +79,10 @@ #define PCI_DEVICE_ID_INTEL_ADL_14_IMC 0x4650 #define PCI_DEVICE_ID_INTEL_ADL_15_IMC 0x4668 #define PCI_DEVICE_ID_INTEL_ADL_16_IMC 0x4670 +#define PCI_DEVICE_ID_INTEL_RPL_1_IMC 0xA700 +#define PCI_DEVICE_ID_INTEL_RPL_2_IMC 0xA702 +#define PCI_DEVICE_ID_INTEL_RPL_3_IMC 0xA706 +#define PCI_DEVICE_ID_INTEL_RPL_4_IMC 0xA709 /* SNB event control */ #define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff @@ -1406,6 +1410,22 @@ static const struct pci_device_id tgl_uncore_pci_ids[] = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_16_IMC), .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_RPL_1_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_RPL_2_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_RPL_3_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_RPL_4_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, { /* end: all zeroes */ } }; diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c index 96c775abe31f..6d759f88315c 100644 --- a/arch/x86/events/msr.c +++ b/arch/x86/events/msr.c @@ -103,6 +103,7 @@ static bool test_intel(int idx, void *data) case INTEL_FAM6_ROCKETLAKE: case INTEL_FAM6_ALDERLAKE: case INTEL_FAM6_ALDERLAKE_L: + case INTEL_FAM6_RAPTORLAKE: if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF) return true; break; diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index c878fed3056f..fbcfec4dc4cc 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -154,24 +154,24 @@ # define DEFINE_EXTABLE_TYPE_REG \ ".macro extable_type_reg type:req reg:req\n" \ - ".set found, 0\n" \ - ".set regnr, 0\n" \ + ".set .Lfound, 0\n" \ + ".set .Lregnr, 0\n" \ ".irp rs,rax,rcx,rdx,rbx,rsp,rbp,rsi,rdi,r8,r9,r10,r11,r12,r13,r14,r15\n" \ ".ifc \\reg, %%\\rs\n" \ - ".set found, found+1\n" \ - ".long \\type + (regnr << 8)\n" \ + ".set .Lfound, .Lfound+1\n" \ + ".long \\type + (.Lregnr << 8)\n" \ ".endif\n" \ - ".set regnr, regnr+1\n" \ + ".set .Lregnr, .Lregnr+1\n" \ ".endr\n" \ - ".set regnr, 0\n" \ + ".set .Lregnr, 0\n" \ ".irp rs,eax,ecx,edx,ebx,esp,ebp,esi,edi,r8d,r9d,r10d,r11d,r12d,r13d,r14d,r15d\n" \ ".ifc \\reg, %%\\rs\n" \ - ".set found, found+1\n" \ - ".long \\type + (regnr << 8)\n" \ + ".set .Lfound, .Lfound+1\n" \ + ".long \\type + (.Lregnr << 8)\n" \ ".endif\n" \ - ".set regnr, regnr+1\n" \ + ".set .Lregnr, .Lregnr+1\n" \ ".endr\n" \ - ".if (found != 1)\n" \ + ".if (.Lfound != 1)\n" \ ".error \"extable_type_reg: bad register argument\"\n" \ ".endif\n" \ ".endm\n" diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index 4d20a293c6fd..aaf0cb0db4ae 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -78,9 +78,9 @@ do { \ */ #define __WARN_FLAGS(flags) \ do { \ - __auto_type f = BUGFLAG_WARNING|(flags); \ + __auto_type __flags = BUGFLAG_WARNING|(flags); \ instrumentation_begin(); \ - _BUG_FLAGS(ASM_UD2, f, ASM_REACHABLE); \ + _BUG_FLAGS(ASM_UD2, __flags, ASM_REACHABLE); \ instrumentation_end(); \ } while (0) diff --git a/arch/x86/include/asm/msi.h b/arch/x86/include/asm/msi.h index b85147d75626..d71c7e8b738d 100644 --- a/arch/x86/include/asm/msi.h +++ b/arch/x86/include/asm/msi.h @@ -12,14 +12,17 @@ int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec, /* Structs and defines for the X86 specific MSI message format */ typedef struct x86_msi_data { - u32 vector : 8, - delivery_mode : 3, - dest_mode_logical : 1, - reserved : 2, - active_low : 1, - is_level : 1; - - u32 dmar_subhandle; + union { + struct { + u32 vector : 8, + delivery_mode : 3, + dest_mode_logical : 1, + reserved : 2, + active_low : 1, + is_level : 1; + }; + u32 dmar_subhandle; + }; } __attribute__ ((packed)) arch_msi_msg_data_t; #define arch_msi_msg_data x86_msi_data diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index a3c33b79fb86..13c0d63ed55e 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -38,9 +38,9 @@ #define arch_raw_cpu_ptr(ptr) \ ({ \ unsigned long tcp_ptr__; \ - asm volatile("add " __percpu_arg(1) ", %0" \ - : "=r" (tcp_ptr__) \ - : "m" (this_cpu_off), "0" (ptr)); \ + asm ("add " __percpu_arg(1) ", %0" \ + : "=r" (tcp_ptr__) \ + : "m" (this_cpu_off), "0" (ptr)); \ (typeof(*(ptr)) __kernel __force *)tcp_ptr__; \ }) #else diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 58d9e4b1fa0a..b06e4c573add 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -241,6 +241,11 @@ struct x86_pmu_capability { #define INTEL_PMC_IDX_FIXED_SLOTS (INTEL_PMC_IDX_FIXED + 3) #define INTEL_PMC_MSK_FIXED_SLOTS (1ULL << INTEL_PMC_IDX_FIXED_SLOTS) +static inline bool use_fixed_pseudo_encoding(u64 code) +{ + return !(code & 0xff); +} + /* * We model BTS tracing as another fixed-mode PMC. * diff --git a/arch/x86/include/asm/static_call.h b/arch/x86/include/asm/static_call.h index ed4f8bb6c2d9..2455d721503e 100644 --- a/arch/x86/include/asm/static_call.h +++ b/arch/x86/include/asm/static_call.h @@ -38,6 +38,8 @@ #define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) \ __ARCH_DEFINE_STATIC_CALL_TRAMP(name, "ret; int3; nop; nop; nop") +#define ARCH_DEFINE_STATIC_CALL_RET0_TRAMP(name) \ + ARCH_DEFINE_STATIC_CALL_TRAMP(name, __static_call_return0) #define ARCH_ADD_TRAMP_KEY(name) \ asm(".pushsection .static_call_tramp_key, \"a\" \n" \ diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c index 531fb4cbb63f..aa72cefdd5be 100644 --- a/arch/x86/kernel/static_call.c +++ b/arch/x86/kernel/static_call.c @@ -12,10 +12,9 @@ enum insn_type { }; /* - * data16 data16 xorq %rax, %rax - a single 5 byte instruction that clears %rax - * The REX.W cancels the effect of any data16. + * cs cs cs xorl %eax, %eax - a single 5 byte instruction that clears %[er]ax */ -static const u8 xor5rax[] = { 0x66, 0x66, 0x48, 0x31, 0xc0 }; +static const u8 xor5rax[] = { 0x2e, 0x2e, 0x2e, 0x31, 0xc0 }; static const u8 retinsn[] = { RET_INSN_OPCODE, 0xcc, 0xcc, 0xcc, 0xcc }; diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 6eb4d91d5365..d400b6d9d246 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -855,13 +855,11 @@ done: nr_invalidate); } -static bool tlb_is_not_lazy(int cpu) +static bool tlb_is_not_lazy(int cpu, void *data) { return !per_cpu(cpu_tlbstate_shared.is_lazy, cpu); } -static DEFINE_PER_CPU(cpumask_t, flush_tlb_mask); - DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state_shared, cpu_tlbstate_shared); EXPORT_PER_CPU_SYMBOL(cpu_tlbstate_shared); @@ -890,36 +888,11 @@ STATIC_NOPV void native_flush_tlb_multi(const struct cpumask *cpumask, * up on the new contents of what used to be page tables, while * doing a speculative memory access. */ - if (info->freed_tables) { + if (info->freed_tables) on_each_cpu_mask(cpumask, flush_tlb_func, (void *)info, true); - } else { - /* - * Although we could have used on_each_cpu_cond_mask(), - * open-coding it has performance advantages, as it eliminates - * the need for indirect calls or retpolines. In addition, it - * allows to use a designated cpumask for evaluating the - * condition, instead of allocating one. - * - * This code works under the assumption that there are no nested - * TLB flushes, an assumption that is already made in - * flush_tlb_mm_range(). - * - * cond_cpumask is logically a stack-local variable, but it is - * more efficient to have it off the stack and not to allocate - * it on demand. Preemption is disabled and this code is - * non-reentrant. - */ - struct cpumask *cond_cpumask = this_cpu_ptr(&flush_tlb_mask); - int cpu; - - cpumask_clear(cond_cpumask); - - for_each_cpu(cpu, cpumask) { - if (tlb_is_not_lazy(cpu)) - __cpumask_set_cpu(cpu, cond_cpumask); - } - on_each_cpu_mask(cond_cpumask, flush_tlb_func, (void *)info, true); - } + else + on_each_cpu_cond_mask(tlb_is_not_lazy, flush_tlb_func, + (void *)info, 1, cpumask); } void flush_tlb_multi(const struct cpumask *cpumask, diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 8fe35ed11fd6..16b6efacf7c6 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -412,6 +412,7 @@ static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip) EMIT_LFENCE(); EMIT2(0xFF, 0xE0 + reg); } else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE)) { + OPTIMIZER_HIDE_VAR(reg); emit_jump(&prog, &__x86_indirect_thunk_array[reg], ip); } else #endif diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 9f2b251e83c5..3822666fb73d 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -40,7 +40,8 @@ static void msr_save_context(struct saved_context *ctxt) struct saved_msr *end = msr + ctxt->saved_msrs.num; while (msr < end) { - msr->valid = !rdmsrl_safe(msr->info.msr_no, &msr->info.reg.q); + if (msr->valid) + rdmsrl(msr->info.msr_no, msr->info.reg.q); msr++; } } @@ -424,8 +425,10 @@ static int msr_build_context(const u32 *msr_id, const int num) } for (i = saved_msrs->num, j = 0; i < total_num; i++, j++) { + u64 dummy; + msr_array[i].info.msr_no = msr_id[j]; - msr_array[i].valid = false; + msr_array[i].valid = !rdmsrl_safe(msr_id[j], &dummy); msr_array[i].info.reg.q = 0; } saved_msrs->num = total_num; @@ -500,10 +503,24 @@ static int pm_cpu_check(const struct x86_cpu_id *c) return ret; } +static void pm_save_spec_msr(void) +{ + u32 spec_msr_id[] = { + MSR_IA32_SPEC_CTRL, + MSR_IA32_TSX_CTRL, + MSR_TSX_FORCE_ABORT, + MSR_IA32_MCU_OPT_CTRL, + MSR_AMD64_LS_CFG, + }; + + msr_build_context(spec_msr_id, ARRAY_SIZE(spec_msr_id)); +} + static int pm_check_save_msr(void) { dmi_check_system(msr_save_dmi_table); pm_cpu_check(msr_save_cpu_table); + pm_save_spec_msr(); return 0; } |